From c8273cf9e9cda472760fd2167fb7425124e34d84 Mon Sep 17 00:00:00 2001 From: Paul Gier Date: Wed, 23 Oct 2019 01:38:31 -0500 Subject: [PATCH 01/17] Scripts and readme (#258) * Avoid race condition when deploying quickstart example The namespace and CRD creation must happen before any dependent objects are created. So we can put these in a separate directory (manifest/setup) so they can be created before the other objects. Some minor updates to the README and added a couple of scripts for the quickstarts Update travis script to avoid race condition Signed-off-by: Paul Gier * simplify the example quickstart script and improve readme Signed-off-by: Paul Gier * increase minikube memory to 6g for quickstart example --- README.md | 38 +++++++++++-------- build.sh | 2 +- ...prometheus-rules-and-grafana-dashboards.md | 9 ++++- example.jsonnet | 9 ++++- examples/kustomize.jsonnet | 9 ++++- kustomization.yaml | 24 ++++++------ ...> prometheus-operator-serviceMonitor.yaml} | 0 .../0namespace-namespace.yaml} | 0 ...alertmanagerCustomResourceDefinition.yaml} | 0 ...-0podmonitorCustomResourceDefinition.yaml} | 0 ...-0prometheusCustomResourceDefinition.yaml} | 0 ...ometheusruleCustomResourceDefinition.yaml} | 0 ...rvicemonitorCustomResourceDefinition.yaml} | 0 .../prometheus-operator-clusterRole.yaml} | 0 ...ometheus-operator-clusterRoleBinding.yaml} | 0 .../prometheus-operator-deployment.yaml} | 0 .../prometheus-operator-service.yaml} | 0 .../prometheus-operator-serviceAccount.yaml} | 0 scripts/minikube-start-kvm.sh | 12 ++++++ scripts/minikube-start.sh | 11 ++++++ scripts/monitoring-deploy.sh | 11 ++++++ tests/e2e/travis-e2e.sh | 14 +++---- 22 files changed, 98 insertions(+), 41 deletions(-) rename manifests/{0prometheus-operator-serviceMonitor.yaml => prometheus-operator-serviceMonitor.yaml} (100%) rename manifests/{00namespace-namespace.yaml => setup/0namespace-namespace.yaml} (100%) rename manifests/{0prometheus-operator-0alertmanagerCustomResourceDefinition.yaml => setup/prometheus-operator-0alertmanagerCustomResourceDefinition.yaml} (100%) rename manifests/{0prometheus-operator-0podmonitorCustomResourceDefinition.yaml => setup/prometheus-operator-0podmonitorCustomResourceDefinition.yaml} (100%) rename manifests/{0prometheus-operator-0prometheusCustomResourceDefinition.yaml => setup/prometheus-operator-0prometheusCustomResourceDefinition.yaml} (100%) rename manifests/{0prometheus-operator-0prometheusruleCustomResourceDefinition.yaml => setup/prometheus-operator-0prometheusruleCustomResourceDefinition.yaml} (100%) rename manifests/{0prometheus-operator-0servicemonitorCustomResourceDefinition.yaml => setup/prometheus-operator-0servicemonitorCustomResourceDefinition.yaml} (100%) rename manifests/{0prometheus-operator-clusterRole.yaml => setup/prometheus-operator-clusterRole.yaml} (100%) rename manifests/{0prometheus-operator-clusterRoleBinding.yaml => setup/prometheus-operator-clusterRoleBinding.yaml} (100%) rename manifests/{0prometheus-operator-deployment.yaml => setup/prometheus-operator-deployment.yaml} (100%) rename manifests/{0prometheus-operator-service.yaml => setup/prometheus-operator-service.yaml} (100%) rename manifests/{0prometheus-operator-serviceAccount.yaml => setup/prometheus-operator-serviceAccount.yaml} (100%) create mode 100755 scripts/minikube-start-kvm.sh create mode 100755 scripts/minikube-start.sh create mode 100755 scripts/monitoring-deploy.sh diff --git a/README.md b/README.md index 6fcdb3c4..2ca8757a 100644 --- a/README.md +++ b/README.md @@ -71,13 +71,13 @@ This adapter is an Extension API Server and Kubernetes needs to be have this fea ### minikube -In order to just try out this stack, start [minikube](https://github.com/kubernetes/minikube) with the following command: +To try out this stack, start [minikube](https://github.com/kubernetes/minikube) with the following command: ```shell -$ minikube delete && minikube start --kubernetes-version=v1.14.4 --memory=4096 --bootstrapper=kubeadm --extra-config=kubelet.authentication-token-webhook=true --extra-config=kubelet.authorization-mode=Webhook --extra-config=scheduler.address=0.0.0.0 --extra-config=controller-manager.address=0.0.0.0 +$ minikube delete && minikube start --kubernetes-version=v1.16.0 --memory=6g --bootstrapper=kubeadm --extra-config=kubelet.authentication-token-webhook=true --extra-config=kubelet.authorization-mode=Webhook --extra-config=scheduler.address=0.0.0.0 --extra-config=controller-manager.address=0.0.0.0 ``` -The kube-prometheus stack includes a resource metrics API server, like the metrics-server does. So ensure the metrics-server plugin is disabled on minikube: +The kube-prometheus stack includes a resource metrics API server, so the metrics-server addon is not necessary. Ensure the metrics-server addon is disabled on minikube: ```shell $ minikube addons disable metrics-server @@ -90,20 +90,23 @@ $ minikube addons disable metrics-server This project is intended to be used as a library (i.e. the intent is not for you to create your own modified copy of this repository). Though for a quickstart a compiled version of the Kubernetes [manifests](manifests) generated with this library (specifically with `example.jsonnet`) is checked into this repository in order to try the content out quickly. To try out the stack un-customized run: - * Simply create the stack: + * Create the monitoring stack using the config in the `manifests` directory: + ```shell -$ kubectl create -f manifests/ - -# It can take a few seconds for the above 'create manifests' command to fully create the following resources, so verify the resources are ready before proceeding. -$ until kubectl get customresourcedefinitions servicemonitors.monitoring.coreos.com ; do date; sleep 1; echo ""; done -$ until kubectl get servicemonitors --all-namespaces ; do date; sleep 1; echo ""; done - -$ kubectl apply -f manifests/ # This command sometimes may need to be done twice (to workaround a race condition). +# Create the namespace and CRDs, and then wait for them to be availble before creating the remaining resources +kubectl create -f manifests/setup +until kubectl get servicemonitors --all-namespaces ; do date; sleep 1; echo ""; done +kubectl create -f manifests/ ``` +We create the namespace and CustomResourceDefinitions first to avoid race conditions when deploying the monitoring components. +Alternatively, the resources in both folders can be applied with a single command +`kubectl create -f manifests/setup -f manifests`, but it may be necessary to run the command multiple times for all components to +be created successfullly. + * And to teardown the stack: ```shell -$ kubectl delete -f manifests/ +kubectl delete --ignore-not-found=true -f manifests/ -f manifests/setup ``` ### Access the dashboards @@ -187,8 +190,13 @@ local kp = }, }; -{ ['00namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } + -{ ['0prometheus-operator-' + name]: kp.prometheusOperator[name] for name in std.objectFields(kp.prometheusOperator) } + +{ ['setup/0namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } + +{ + ['setup/prometheus-operator-' + name]: kp.prometheusOperator[name] + for name in std.filter((function(name) name != 'serviceMonitor'), std.objectFields(kp.prometheusOperator)) +} + +// serviceMonitor is separated so that it can be created after the CRDs are ready +{ 'prometheus-operator-serviceMonitor': kp.prometheusOperator.serviceMonitor } + { ['node-exporter-' + name]: kp.nodeExporter[name] for name in std.objectFields(kp.nodeExporter) } + { ['kube-state-metrics-' + name]: kp.kubeStateMetrics[name] for name in std.objectFields(kp.kubeStateMetrics) } + { ['alertmanager-' + name]: kp.alertmanager[name] for name in std.objectFields(kp.alertmanager) } + @@ -212,7 +220,7 @@ set -o pipefail # Make sure to start with a clean 'manifests' dir rm -rf manifests -mkdir manifests +mkdir -p manifests/setup # optional, but we would like to generate yaml, not json jsonnet -J vendor -m manifests "${1-example.jsonnet}" | xargs -I{} sh -c 'cat {} | gojsontoyaml > {}.yaml; rm -f {}' -- {} diff --git a/build.sh b/build.sh index f68cd447..0663889d 100755 --- a/build.sh +++ b/build.sh @@ -9,7 +9,7 @@ set -o pipefail # Make sure to start with a clean 'manifests' dir rm -rf manifests -mkdir manifests +mkdir -p manifests/setup # optional, but we would like to generate yaml, not json jsonnet -J vendor -m manifests "${1-example.jsonnet}" | xargs -I{} sh -c 'cat {} | gojsontoyaml > {}.yaml; rm -f {}' -- {} diff --git a/docs/developing-prometheus-rules-and-grafana-dashboards.md b/docs/developing-prometheus-rules-and-grafana-dashboards.md index aa1283ec..34801a88 100644 --- a/docs/developing-prometheus-rules-and-grafana-dashboards.md +++ b/docs/developing-prometheus-rules-and-grafana-dashboards.md @@ -24,8 +24,13 @@ local kp = }, }; -{ ['00namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } + -{ ['0prometheus-operator-' + name]: kp.prometheusOperator[name] for name in std.objectFields(kp.prometheusOperator) } + +{ ['setup/0namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } + +{ + ['setup/prometheus-operator-' + name]: kp.prometheusOperator[name] + for name in std.filter((function(name) name != 'serviceMonitor'), std.objectFields(kp.prometheusOperator)) +} + +// serviceMonitor is separated so that it can be created after the CRDs are ready +{ 'prometheus-operator-serviceMonitor': kp.prometheusOperator.serviceMonitor } + { ['node-exporter-' + name]: kp.nodeExporter[name] for name in std.objectFields(kp.nodeExporter) } + { ['kube-state-metrics-' + name]: kp.kubeStateMetrics[name] for name in std.objectFields(kp.kubeStateMetrics) } + { ['alertmanager-' + name]: kp.alertmanager[name] for name in std.objectFields(kp.alertmanager) } + diff --git a/example.jsonnet b/example.jsonnet index 7002eff2..77864e09 100644 --- a/example.jsonnet +++ b/example.jsonnet @@ -12,8 +12,13 @@ local kp = }, }; -{ ['00namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } + -{ ['0prometheus-operator-' + name]: kp.prometheusOperator[name] for name in std.objectFields(kp.prometheusOperator) } + +{ ['setup/0namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } + +{ + ['setup/prometheus-operator-' + name]: kp.prometheusOperator[name] + for name in std.filter((function(name) name != 'serviceMonitor'), std.objectFields(kp.prometheusOperator)) +} + +// serviceMonitor is separated so that it can be created after the CRDs are ready +{ 'prometheus-operator-serviceMonitor': kp.prometheusOperator.serviceMonitor } + { ['node-exporter-' + name]: kp.nodeExporter[name] for name in std.objectFields(kp.nodeExporter) } + { ['kube-state-metrics-' + name]: kp.kubeStateMetrics[name] for name in std.objectFields(kp.kubeStateMetrics) } + { ['alertmanager-' + name]: kp.alertmanager[name] for name in std.objectFields(kp.alertmanager) } + diff --git a/examples/kustomize.jsonnet b/examples/kustomize.jsonnet index db3ba344..38dd6c89 100644 --- a/examples/kustomize.jsonnet +++ b/examples/kustomize.jsonnet @@ -8,8 +8,13 @@ local kp = local manifests = // Uncomment line below to enable vertical auto scaling of kube-state-metrics //{ ['ksm-autoscaler-' + name]: kp.ksmAutoscaler[name] for name in std.objectFields(kp.ksmAutoscaler) } + - { ['00namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } + - { ['0prometheus-operator-' + name]: kp.prometheusOperator[name] for name in std.objectFields(kp.prometheusOperator) } + + { ['setup/0namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } + + { + ['setup/prometheus-operator-' + name]: kp.prometheusOperator[name] + for name in std.filter((function(name) name != 'serviceMonitor'), std.objectFields(kp.prometheusOperator)) + } + + // serviceMonitor is separated so that it can be created after the CRDs are ready + { 'prometheus-operator-serviceMonitor': kp.prometheusOperator.serviceMonitor } + { ['node-exporter-' + name]: kp.nodeExporter[name] for name in std.objectFields(kp.nodeExporter) } + { ['kube-state-metrics-' + name]: kp.kubeStateMetrics[name] for name in std.objectFields(kp.kubeStateMetrics) } + { ['alertmanager-' + name]: kp.alertmanager[name] for name in std.objectFields(kp.alertmanager) } + diff --git a/kustomization.yaml b/kustomization.yaml index a580ed8e..bd03a83e 100644 --- a/kustomization.yaml +++ b/kustomization.yaml @@ -1,18 +1,6 @@ apiVersion: kustomize.config.k8s.io/v1beta1 kind: Kustomization resources: -- ./manifests/00namespace-namespace.yaml -- ./manifests/0prometheus-operator-0alertmanagerCustomResourceDefinition.yaml -- ./manifests/0prometheus-operator-0podmonitorCustomResourceDefinition.yaml -- ./manifests/0prometheus-operator-0prometheusCustomResourceDefinition.yaml -- ./manifests/0prometheus-operator-0prometheusruleCustomResourceDefinition.yaml -- ./manifests/0prometheus-operator-0servicemonitorCustomResourceDefinition.yaml -- ./manifests/0prometheus-operator-clusterRole.yaml -- ./manifests/0prometheus-operator-clusterRoleBinding.yaml -- ./manifests/0prometheus-operator-deployment.yaml -- ./manifests/0prometheus-operator-service.yaml -- ./manifests/0prometheus-operator-serviceAccount.yaml -- ./manifests/0prometheus-operator-serviceMonitor.yaml - ./manifests/alertmanager-alertmanager.yaml - ./manifests/alertmanager-secret.yaml - ./manifests/alertmanager-service.yaml @@ -52,6 +40,7 @@ resources: - ./manifests/prometheus-adapter-serviceAccount.yaml - ./manifests/prometheus-clusterRole.yaml - ./manifests/prometheus-clusterRoleBinding.yaml +- ./manifests/prometheus-operator-serviceMonitor.yaml - ./manifests/prometheus-prometheus.yaml - ./manifests/prometheus-roleBindingConfig.yaml - ./manifests/prometheus-roleBindingSpecificNamespaces.yaml @@ -66,3 +55,14 @@ resources: - ./manifests/prometheus-serviceMonitorKubeControllerManager.yaml - ./manifests/prometheus-serviceMonitorKubeScheduler.yaml - ./manifests/prometheus-serviceMonitorKubelet.yaml +- ./manifests/setup/0namespace-namespace.yaml +- ./manifests/setup/prometheus-operator-0alertmanagerCustomResourceDefinition.yaml +- ./manifests/setup/prometheus-operator-0podmonitorCustomResourceDefinition.yaml +- ./manifests/setup/prometheus-operator-0prometheusCustomResourceDefinition.yaml +- ./manifests/setup/prometheus-operator-0prometheusruleCustomResourceDefinition.yaml +- ./manifests/setup/prometheus-operator-0servicemonitorCustomResourceDefinition.yaml +- ./manifests/setup/prometheus-operator-clusterRole.yaml +- ./manifests/setup/prometheus-operator-clusterRoleBinding.yaml +- ./manifests/setup/prometheus-operator-deployment.yaml +- ./manifests/setup/prometheus-operator-service.yaml +- ./manifests/setup/prometheus-operator-serviceAccount.yaml diff --git a/manifests/0prometheus-operator-serviceMonitor.yaml b/manifests/prometheus-operator-serviceMonitor.yaml similarity index 100% rename from manifests/0prometheus-operator-serviceMonitor.yaml rename to manifests/prometheus-operator-serviceMonitor.yaml diff --git a/manifests/00namespace-namespace.yaml b/manifests/setup/0namespace-namespace.yaml similarity index 100% rename from manifests/00namespace-namespace.yaml rename to manifests/setup/0namespace-namespace.yaml diff --git a/manifests/0prometheus-operator-0alertmanagerCustomResourceDefinition.yaml b/manifests/setup/prometheus-operator-0alertmanagerCustomResourceDefinition.yaml similarity index 100% rename from manifests/0prometheus-operator-0alertmanagerCustomResourceDefinition.yaml rename to manifests/setup/prometheus-operator-0alertmanagerCustomResourceDefinition.yaml diff --git a/manifests/0prometheus-operator-0podmonitorCustomResourceDefinition.yaml b/manifests/setup/prometheus-operator-0podmonitorCustomResourceDefinition.yaml similarity index 100% rename from manifests/0prometheus-operator-0podmonitorCustomResourceDefinition.yaml rename to manifests/setup/prometheus-operator-0podmonitorCustomResourceDefinition.yaml diff --git a/manifests/0prometheus-operator-0prometheusCustomResourceDefinition.yaml b/manifests/setup/prometheus-operator-0prometheusCustomResourceDefinition.yaml similarity index 100% rename from manifests/0prometheus-operator-0prometheusCustomResourceDefinition.yaml rename to manifests/setup/prometheus-operator-0prometheusCustomResourceDefinition.yaml diff --git a/manifests/0prometheus-operator-0prometheusruleCustomResourceDefinition.yaml b/manifests/setup/prometheus-operator-0prometheusruleCustomResourceDefinition.yaml similarity index 100% rename from manifests/0prometheus-operator-0prometheusruleCustomResourceDefinition.yaml rename to manifests/setup/prometheus-operator-0prometheusruleCustomResourceDefinition.yaml diff --git a/manifests/0prometheus-operator-0servicemonitorCustomResourceDefinition.yaml b/manifests/setup/prometheus-operator-0servicemonitorCustomResourceDefinition.yaml similarity index 100% rename from manifests/0prometheus-operator-0servicemonitorCustomResourceDefinition.yaml rename to manifests/setup/prometheus-operator-0servicemonitorCustomResourceDefinition.yaml diff --git a/manifests/0prometheus-operator-clusterRole.yaml b/manifests/setup/prometheus-operator-clusterRole.yaml similarity index 100% rename from manifests/0prometheus-operator-clusterRole.yaml rename to manifests/setup/prometheus-operator-clusterRole.yaml diff --git a/manifests/0prometheus-operator-clusterRoleBinding.yaml b/manifests/setup/prometheus-operator-clusterRoleBinding.yaml similarity index 100% rename from manifests/0prometheus-operator-clusterRoleBinding.yaml rename to manifests/setup/prometheus-operator-clusterRoleBinding.yaml diff --git a/manifests/0prometheus-operator-deployment.yaml b/manifests/setup/prometheus-operator-deployment.yaml similarity index 100% rename from manifests/0prometheus-operator-deployment.yaml rename to manifests/setup/prometheus-operator-deployment.yaml diff --git a/manifests/0prometheus-operator-service.yaml b/manifests/setup/prometheus-operator-service.yaml similarity index 100% rename from manifests/0prometheus-operator-service.yaml rename to manifests/setup/prometheus-operator-service.yaml diff --git a/manifests/0prometheus-operator-serviceAccount.yaml b/manifests/setup/prometheus-operator-serviceAccount.yaml similarity index 100% rename from manifests/0prometheus-operator-serviceAccount.yaml rename to manifests/setup/prometheus-operator-serviceAccount.yaml diff --git a/scripts/minikube-start-kvm.sh b/scripts/minikube-start-kvm.sh new file mode 100755 index 00000000..da82a95c --- /dev/null +++ b/scripts/minikube-start-kvm.sh @@ -0,0 +1,12 @@ +#!/bin/bash +minikube delete +minikube addons disable metrics-server +minikube start \ + --vm-driver=kvm2 \ + --kubernetes-version=v1.16.0 \ + --memory=6g \ + --bootstrapper=kubeadm \ + --extra-config=kubelet.authentication-token-webhook=true \ + --extra-config=kubelet.authorization-mode=Webhook \ + --extra-config=scheduler.address=0.0.0.0 \ + --extra-config=controller-manager.address=0.0.0.0 diff --git a/scripts/minikube-start.sh b/scripts/minikube-start.sh new file mode 100755 index 00000000..eb29e860 --- /dev/null +++ b/scripts/minikube-start.sh @@ -0,0 +1,11 @@ +#!/bin/bash +minikube delete +minikube addons disable metrics-server +minikube start \ + --kubernetes-version=v1.16.0 \ + --memory=6g \ + --bootstrapper=kubeadm \ + --extra-config=kubelet.authentication-token-webhook=true \ + --extra-config=kubelet.authorization-mode=Webhook \ + --extra-config=scheduler.address=0.0.0.0 \ + --extra-config=controller-manager.address=0.0.0.0 diff --git a/scripts/monitoring-deploy.sh b/scripts/monitoring-deploy.sh new file mode 100755 index 00000000..7bc20905 --- /dev/null +++ b/scripts/monitoring-deploy.sh @@ -0,0 +1,11 @@ +#!/bin/bash + +# create namespace and CRDs +kubectl create -f manifests/setup + +# wait for CRD creation to complete +until kubectl get servicemonitors --all-namespaces ; do date; sleep 1; echo ""; done + +# create monitoring components +kubectl create -f manifests/ + diff --git a/tests/e2e/travis-e2e.sh b/tests/e2e/travis-e2e.sh index aa32d668..4efb2bd1 100755 --- a/tests/e2e/travis-e2e.sh +++ b/tests/e2e/travis-e2e.sh @@ -16,13 +16,13 @@ chmod +x kind ./kind create cluster export KUBECONFIG="$(./kind get kubeconfig-path)" -./kubectl apply -f manifests/0prometheus-operator-0alertmanagerCustomResourceDefinition.yaml -./kubectl apply -f manifests/0prometheus-operator-0prometheusCustomResourceDefinition.yaml -./kubectl apply -f manifests/0prometheus-operator-0prometheusruleCustomResourceDefinition.yaml -./kubectl apply -f manifests/0prometheus-operator-0servicemonitorCustomResourceDefinition.yaml +# create namespace, permissions, and CRDs +./kubectl create -f manifests/setup -# Wait for CRDs to be successfully registered -sleep 10 +# wait for CRD creation to complete +until ./kubectl get servicemonitors --all-namespaces ; do date; sleep 1; echo ""; done + +# create monitoring components +./kubectl create -f manifests/ -./kubectl apply -f manifests make test-e2e From a7884a6c180a1b2a61b7f1d43efd857a5001efdb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Beno=C3=AEt=20Knecht?= Date: Wed, 23 Oct 2019 10:58:24 +0200 Subject: [PATCH 02/17] node-exporter: Use configured resources for kube-rbac-proxy (#279) Since #132, `kube-rbac-proxy` resources can be configured in `config.resources['kube-rbac-proxy']`, but the node-exporter daemonset was still using hard-coded values. This commit sets the request and limit resources to the configured values for the `kube-rbac-proxy` container in the node-exporter pods. --- jsonnet/kube-prometheus/node-exporter/node-exporter.libsonnet | 4 ++-- manifests/node-exporter-daemonset.yaml | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/jsonnet/kube-prometheus/node-exporter/node-exporter.libsonnet b/jsonnet/kube-prometheus/node-exporter/node-exporter.libsonnet index 9a3d29eb..06a7397f 100644 --- a/jsonnet/kube-prometheus/node-exporter/node-exporter.libsonnet +++ b/jsonnet/kube-prometheus/node-exporter/node-exporter.libsonnet @@ -118,8 +118,8 @@ local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet'; // forgo declaring the host port, however it is important to declare // it so that the scheduler can decide if the pod is schedulable. container.withPorts(containerPort.new($._config.nodeExporter.port) + containerPort.withHostPort($._config.nodeExporter.port) + containerPort.withName('https')) + - container.mixin.resources.withRequests({ cpu: '10m', memory: '20Mi' }) + - container.mixin.resources.withLimits({ cpu: '20m', memory: '60Mi' }) + + container.mixin.resources.withRequests($._config.resources['kube-rbac-proxy'].requests) + + container.mixin.resources.withLimits($._config.resources['kube-rbac-proxy'].limits) + container.withEnv([ip]); local c = [nodeExporter, proxy]; diff --git a/manifests/node-exporter-daemonset.yaml b/manifests/node-exporter-daemonset.yaml index 0a6ce3b1..436c462e 100644 --- a/manifests/node-exporter-daemonset.yaml +++ b/manifests/node-exporter-daemonset.yaml @@ -61,7 +61,7 @@ spec: resources: limits: cpu: 20m - memory: 60Mi + memory: 40Mi requests: cpu: 10m memory: 20Mi From 4e5b454ba80999ffded72f774caea3033b07204d Mon Sep 17 00:00:00 2001 From: Jake Utley Date: Thu, 24 Oct 2019 00:16:57 -0700 Subject: [PATCH 03/17] Add metrics_path label to kubelet servicemonitor endpoints (#277) * Add metrics_path label to kubelet servicemonitor endpoints * Set kubelet metric_path label in jsonnet * Add generated kubelet servicemonitor --- go.mod | 13 +++++--- go.sum | 32 +++++++++++++++++++ ...kube-prometheus-insecure-kubelet.libsonnet | 21 ++++++++++++ .../prometheus/prometheus.libsonnet | 12 +++++++ .../prometheus-serviceMonitorKubelet.yaml | 8 +++++ 5 files changed, 82 insertions(+), 4 deletions(-) diff --git a/go.mod b/go.mod index b67b2a09..2be821b6 100644 --- a/go.mod +++ b/go.mod @@ -4,25 +4,30 @@ go 1.12 require ( github.com/Jeffail/gabs v1.2.0 - github.com/davecgh/go-spew v1.1.1 // indirect + github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751 // indirect + github.com/alecthomas/units v0.0.0-20190924025748-f65c72e2690d // indirect github.com/gogo/protobuf v1.1.1 // indirect github.com/google/gofuzz v0.0.0-20170612174753-24818f796faf // indirect github.com/googleapis/gnostic v0.0.0-20170729233727-0c5108395e2d // indirect github.com/imdario/mergo v0.3.7 // indirect github.com/json-iterator/go v0.0.0-20180701071628-ab8a2e0c74be // indirect + github.com/jsonnet-bundler/jsonnet-bundler v0.1.0 // indirect + github.com/mattn/go-colorable v0.1.4 // indirect + github.com/mattn/go-isatty v0.0.10 // indirect github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect github.com/modern-go/reflect2 v1.0.1 // indirect github.com/pkg/errors v0.8.1 - github.com/pmezard/go-difflib v1.0.0 // indirect github.com/spf13/pflag v1.0.3 // indirect - github.com/stretchr/testify v1.2.2 // indirect + github.com/stretchr/objx v0.2.0 // indirect golang.org/x/crypto v0.0.0-20190411191339-88737f569e3a // indirect golang.org/x/net v0.0.0-20190206173232-65e2d4e15006 // indirect golang.org/x/oauth2 v0.0.0-20190402181905-9f3314589c9a // indirect + golang.org/x/sys v0.0.0-20191023151326-f89234f9a2c2 // indirect golang.org/x/text v0.3.1-0.20181227161524-e6919f6577db // indirect golang.org/x/time v0.0.0-20190308202827-9d24e82272b4 // indirect + gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 // indirect gopkg.in/inf.v0 v0.9.1 // indirect - gopkg.in/yaml.v2 v2.2.2 // indirect + gopkg.in/yaml.v2 v2.2.4 // indirect k8s.io/api v0.0.0-20190313235455-40a48860b5ab // indirect k8s.io/apimachinery v0.0.0-20190313205120-d7deff9243b1 k8s.io/client-go v11.0.0+incompatible diff --git a/go.sum b/go.sum index 94564ff1..a53919d6 100644 --- a/go.sum +++ b/go.sum @@ -1,8 +1,18 @@ cloud.google.com/go v0.34.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw= github.com/Jeffail/gabs v1.2.0 h1:uFhoIVTtsX7hV2RxNgWad8gMU+8OJdzFbOathJdhD3o= github.com/Jeffail/gabs v1.2.0/go.mod h1:6xMvQMK4k33lb7GUUpaAPh6nKMmemQeg5d4gn7/bOXc= +github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc= +github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751 h1:JYp7IbQjafoB+tBA3gMyHYHrpOtNuDiK/uB5uXxq5wM= +github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc= +github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0= +github.com/alecthomas/units v0.0.0-20190924025748-f65c72e2690d h1:UQZhZ2O0vMHr2cI+DC1Mbh0TJxzA3RcLoMsFw+aXw7E= +github.com/alecthomas/units v0.0.0-20190924025748-f65c72e2690d/go.mod h1:rBZYJk541a8SKzHPHnH3zbiI+7dagKZ0cgpgrD7Fyho= +github.com/campoy/embedmd v1.0.0/go.mod h1:oxyr9RCiSXg0M3VJ3ks0UGfp98BpSSGr0kpiX3MzVl8= +github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/fatih/color v1.7.0 h1:DkWD4oS2D8LGGgTQ6IvwJJXSL5Vp2ffcQg58nFV38Ys= +github.com/fatih/color v1.7.0/go.mod h1:Zm6kSWBoL9eyXnKyktHP6abPY2pDugNf5KwzbycvMj4= github.com/gogo/protobuf v1.1.1 h1:72R+M5VuhED/KujmZVcIquuo8mBgX4oVda//DQb3PXo= github.com/gogo/protobuf v1.1.1/go.mod h1:r8qH/GZQm5c6nD/R0oafs1akxWv10x8SbQlK7atdtwQ= github.com/golang/protobuf v1.2.0 h1:P3YflyNX/ehuJFLhxviNdFxQPkGK5cDcApsge1SqnvM= @@ -15,18 +25,32 @@ github.com/imdario/mergo v0.3.7 h1:Y+UAYTZ7gDEuOfhxKWy+dvb5dRQ6rJjFSdX2HZY1/gI= github.com/imdario/mergo v0.3.7/go.mod h1:2EnlNZ0deacrJVfApfmtdGgDfMuh/nq6Ok1EcJh5FfA= github.com/json-iterator/go v0.0.0-20180701071628-ab8a2e0c74be h1:AHimNtVIpiBjPUhEF5KNCkrUyqTSA5zWUl8sQ2bfGBE= github.com/json-iterator/go v0.0.0-20180701071628-ab8a2e0c74be/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU= +github.com/jsonnet-bundler/jsonnet-bundler v0.1.0 h1:T/HtHFr+mYCRULrH1x/RnoB0prIs0rMkolJhFMXNC9A= +github.com/jsonnet-bundler/jsonnet-bundler v0.1.0/go.mod h1:YKsSFc9VFhhLITkJS3X2PrRqWG9u2Jq99udTdDjQLfM= +github.com/mattn/go-colorable v0.0.9/go.mod h1:9vuHe8Xs5qXnSaW/c/ABM9alt+Vo+STaOChaDxuIBZU= +github.com/mattn/go-colorable v0.1.4 h1:snbPLB8fVfU9iwbbo30TPtbLRzwWu6aJS6Xh4eaaviA= +github.com/mattn/go-colorable v0.1.4/go.mod h1:U0ppj6V5qS13XJ6of8GYAs25YV2eR4EVcfRqFIhoBtE= +github.com/mattn/go-isatty v0.0.6/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s= +github.com/mattn/go-isatty v0.0.8/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s= +github.com/mattn/go-isatty v0.0.10 h1:qxFzApOv4WsAL965uUPIsXzAKCZxN2p9UqdhFS4ZW10= +github.com/mattn/go-isatty v0.0.10/go.mod h1:qgIWMr58cqv1PHHyhnkY9lrL7etaEgOFcMEpPG5Rm84= github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg= github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= github.com/modern-go/reflect2 v1.0.1 h1:9f412s+6RmYXLWZSEzVVgPGK7C2PphHj5RJrvfx9AWI= github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0= +github.com/pkg/errors v0.8.0/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= github.com/pkg/errors v0.8.1 h1:iURUrRGxPUNPdy5/HRSm+Yj6okJ6UtLINN0Q9M4+h3I= github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/spf13/pflag v1.0.3 h1:zPAT6CGy6wXeQ7NtTnaTerfKOsV6V6F8agHXFiazDkg= github.com/spf13/pflag v1.0.3/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4= +github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= +github.com/stretchr/objx v0.2.0/go.mod h1:qt09Ya8vawLte6SNmTgCsAVtYtaKzEcn8ATUoHMkEqE= github.com/stretchr/testify v1.2.2 h1:bSDNvY7ZPG5RlJ8otE/7V6gMiyenm9RtJ7IUVIAoJ1w= github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs= +github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= +github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4= golang.org/x/crypto v0.0.0-20190411191339-88737f569e3a h1:Igim7XhdOpBnWPuYJ70XcNpq8q3BCACtVgNfoJxOV7g= golang.org/x/crypto v0.0.0-20190411191339-88737f569e3a/go.mod h1:WFFai1msRO1wXaEeE5yQxYXgSfI8pQAWXbQop6sCtWE= golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= @@ -37,8 +61,12 @@ golang.org/x/oauth2 v0.0.0-20190402181905-9f3314589c9a h1:tImsplftrFpALCYumobsd0 golang.org/x/oauth2 v0.0.0-20190402181905-9f3314589c9a/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw= golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4 h1:YUO/7uOKsKeq9UokNS62b8FYywz3ker1l1vDZRCRefw= golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sys v0.0.0-20190222072716-a9d3bda3a223/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20190310054646-10058d7d4faa/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20190403152447-81d4e9dc473e h1:nFYrTHrdrAOpShe27kaFHjsqYSEQ0KWqdWLu3xuZJts= golang.org/x/sys v0.0.0-20190403152447-81d4e9dc473e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20191008105621-543471e840be/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20191023151326-f89234f9a2c2/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= golang.org/x/text v0.3.1-0.20181227161524-e6919f6577db h1:6/JqlYfC1CCaLnGceQTI+sDGhC9UBSPAsBqI0Gun6kU= golang.org/x/text v0.3.1-0.20181227161524-e6919f6577db/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk= @@ -47,12 +75,16 @@ golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxb golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= google.golang.org/appengine v1.4.0 h1:/wp5JvzpHIxhs/dumFmF7BXTf3Z+dd4uXta4kVyO508= google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4= +gopkg.in/alecthomas/kingpin.v2 v2.2.6 h1:jMFz6MfLP0/4fUyZle81rXUoxOBFi19VUFKVDOQfozc= +gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/inf.v0 v0.9.1 h1:73M5CoZyi3ZLMOyDlQh031Cx6N9NDJ2Vvfl76EDAgDc= gopkg.in/inf.v0 v0.9.1/go.mod h1:cWUDdTG/fYaXco+Dcufb5Vnc6Gp2YChqWtbxRZE0mXw= gopkg.in/yaml.v2 v2.2.2 h1:ZCJp+EgiOT7lHqUV2J862kp8Qj64Jo6az82+3Td9dZw= gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= +gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= k8s.io/api v0.0.0-20190313235455-40a48860b5ab h1:DG9A67baNpoeweOy2spF1OWHhnVY5KR7/Ek/+U1lVZc= k8s.io/api v0.0.0-20190313235455-40a48860b5ab/go.mod h1:iuAfoD4hCxJ8Onx9kaTIt30j7jUFS00AXQi6QMi99vA= k8s.io/apimachinery v0.0.0-20190313205120-d7deff9243b1 h1:IS7K02iBkQXpCeieSiyJjGoLSdVOv2DbPaWHJ+ZtgKg= diff --git a/jsonnet/kube-prometheus/kube-prometheus-insecure-kubelet.libsonnet b/jsonnet/kube-prometheus/kube-prometheus-insecure-kubelet.libsonnet index 1bd64e1b..ab5dceae 100644 --- a/jsonnet/kube-prometheus/kube-prometheus-insecure-kubelet.libsonnet +++ b/jsonnet/kube-prometheus/kube-prometheus-insecure-kubelet.libsonnet @@ -9,6 +9,12 @@ scheme: 'http', interval: '30s', bearerTokenFile: '/var/run/secrets/kubernetes.io/serviceaccount/token', + relabelings: [ + { + sourceLabels: ['__metrics_path__'], + targetLabel: 'metrics_path' + }, + ], }, { port: 'http-metrics', @@ -17,6 +23,21 @@ interval: '30s', honorLabels: true, bearerTokenFile: '/var/run/secrets/kubernetes.io/serviceaccount/token', + relabelings: [ + { + sourceLabels: ['__metrics_path__'], + targetLabel: 'metrics_path' + }, + ], + metricRelabelings: [ + // Drop a bunch of metrics which are disabled but still sent, see + // https://github.com/google/cadvisor/issues/1925. + { + sourceLabels: ['__name__'], + regex: 'container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s)', + action: 'drop', + }, + ], }, ], }, diff --git a/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet b/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet index 42baf52a..958206ad 100644 --- a/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet +++ b/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet @@ -281,6 +281,12 @@ local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet'; insecureSkipVerify: true, }, bearerTokenFile: '/var/run/secrets/kubernetes.io/serviceaccount/token', + relabelings: [ + { + sourceLabels: ['__metrics_path__'], + targetLabel: 'metrics_path' + }, + ], }, { port: 'https-metrics', @@ -292,6 +298,12 @@ local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet'; insecureSkipVerify: true, }, bearerTokenFile: '/var/run/secrets/kubernetes.io/serviceaccount/token', + relabelings: [ + { + sourceLabels: ['__metrics_path__'], + targetLabel: 'metrics_path' + }, + ], metricRelabelings: [ // Drop a bunch of metrics which are disabled but still sent, see // https://github.com/google/cadvisor/issues/1925. diff --git a/manifests/prometheus-serviceMonitorKubelet.yaml b/manifests/prometheus-serviceMonitorKubelet.yaml index 91da377a..64edb0e4 100644 --- a/manifests/prometheus-serviceMonitorKubelet.yaml +++ b/manifests/prometheus-serviceMonitorKubelet.yaml @@ -11,6 +11,10 @@ spec: honorLabels: true interval: 30s port: https-metrics + relabelings: + - sourceLabels: + - __metrics_path__ + targetLabel: metrics_path scheme: https tlsConfig: insecureSkipVerify: true @@ -24,6 +28,10 @@ spec: - __name__ path: /metrics/cadvisor port: https-metrics + relabelings: + - sourceLabels: + - __metrics_path__ + targetLabel: metrics_path scheme: https tlsConfig: insecureSkipVerify: true From dc77f255de2b594d03b1b37a4ae8f3c2f08825e7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Beno=C3=AEt=20Knecht?= Date: Thu, 24 Oct 2019 09:39:04 +0200 Subject: [PATCH 04/17] prometheus: Let name and replicas be set in _config Before #260, the Prometheus name and number of replicas could be configured in `_config.prometheus.name` and `_config.prometheus.replicas` respectively. It isn't the case anymore, which means that configurations that did set a custom name for Prometheus will get a second Prometheus instance called `k8s` when they upgrade kube-prometheus. This commit adds back the ability to configure both of these parameters in `_config`. --- jsonnet/kube-prometheus/prometheus/prometheus.libsonnet | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet b/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet index 42baf52a..5e817a11 100644 --- a/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet +++ b/jsonnet/kube-prometheus/prometheus/prometheus.libsonnet @@ -18,6 +18,8 @@ local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet'; }, prometheus+:: { + name: 'k8s', + replicas: 2, rules: {}, namespaces: ['default', 'kube-system', $._config.namespace], }, @@ -26,10 +28,10 @@ local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet'; prometheus+:: { local p = self, - name:: 'k8s', + name:: $._config.prometheus.name, namespace:: $._config.namespace, roleBindingNamespaces:: $._config.prometheus.namespaces, - replicas:: 2, + replicas:: $._config.prometheus.replicas, prometheusRules:: $._config.prometheus.rules, alertmanagerName:: $.alertmanager.service.metadata.name, From 5686d7b43927b559634ad5359ce709866f399987 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Beno=C3=AEt=20Knecht?= Date: Thu, 24 Oct 2019 13:37:11 +0200 Subject: [PATCH 05/17] Makefile: Fix manifests target dependency (#285) Since 1664600, manifests are built using `examples/kustomize.jsonnet` instead of `example.jsonnet`. This commit updates the dependencies in the `manifests` target to reflect that change. --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 5f2eaa4e..994fa5ae 100644 --- a/Makefile +++ b/Makefile @@ -34,9 +34,9 @@ generate: manifests **.md **.md: $(shell find examples) build.sh example.jsonnet $(EMBEDMD_BINARY) -w `find . -name "*.md" | grep -v vendor` -manifests: vendor example.jsonnet build.sh +manifests: examples/kustomize.jsonnet vendor build.sh rm -rf manifests - ./build.sh ./examples/kustomize.jsonnet + ./build.sh $< vendor: jsonnetfile.json jsonnetfile.lock.json rm -rf vendor From f72d49ca269d5296febf8d3ef1a2bcf6e0ab4032 Mon Sep 17 00:00:00 2001 From: Paul Gier Date: Thu, 24 Oct 2019 15:01:29 -0500 Subject: [PATCH 06/17] update kube-state-metrics 1.7.2 -> 1.8.0 --- .../kube-state-metrics/kube-state-metrics.libsonnet | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/jsonnet/kube-prometheus/kube-state-metrics/kube-state-metrics.libsonnet b/jsonnet/kube-prometheus/kube-state-metrics/kube-state-metrics.libsonnet index aeca71bc..e30a63c3 100644 --- a/jsonnet/kube-prometheus/kube-state-metrics/kube-state-metrics.libsonnet +++ b/jsonnet/kube-prometheus/kube-state-metrics/kube-state-metrics.libsonnet @@ -14,7 +14,7 @@ local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet'; }, versions+:: { - kubeStateMetrics: 'v1.7.2', + kubeStateMetrics: 'v1.8.0', kubeRbacProxy: 'v0.4.1', }, From ebb960ee5e487b780cf4ce41feeb71e9a72ad9d6 Mon Sep 17 00:00:00 2001 From: Paul Gier Date: Thu, 24 Oct 2019 15:02:29 -0500 Subject: [PATCH 07/17] update generated files for kube-state-metrics 1.7.2 -> 1.8.0 --- manifests/kube-state-metrics-deployment.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/manifests/kube-state-metrics-deployment.yaml b/manifests/kube-state-metrics-deployment.yaml index 065e8703..b8ff2795 100644 --- a/manifests/kube-state-metrics-deployment.yaml +++ b/manifests/kube-state-metrics-deployment.yaml @@ -55,7 +55,7 @@ spec: - --port=8081 - --telemetry-host=127.0.0.1 - --telemetry-port=8082 - image: quay.io/coreos/kube-state-metrics:v1.7.2 + image: quay.io/coreos/kube-state-metrics:v1.8.0 name: kube-state-metrics resources: limits: From 6e0ca7565fbbee7f9b1431fda29147f7bfceccd9 Mon Sep 17 00:00:00 2001 From: Clayton Coleman Date: Fri, 25 Oct 2019 00:14:24 -0400 Subject: [PATCH 08/17] jsonnet: Update to latest kubernetes-mixin Pick up new alerts for unreachable nodes. --- README.md | 48 +- ...ditional-namespaces-servicemonitor.jsonnet | 48 +- jsonnetfile.lock.json | 2 +- manifests/grafana-dashboardDefinitions.yaml | 11537 +++++++++++++++- manifests/grafana-deployment.yaml | 30 + manifests/prometheus-rules.yaml | 34 + 6 files changed, 11599 insertions(+), 100 deletions(-) diff --git a/README.md b/README.md index 2ca8757a..50659f95 100644 --- a/README.md +++ b/README.md @@ -573,34 +573,34 @@ You can define ServiceMonitor resources in your `jsonnet` spec. See the snippet ```jsonnet local kp = (import 'kube-prometheus/kube-prometheus.libsonnet') + { _config+:: { - namespace: 'monitoring', - prometheus+:: { - namespaces+: ['my-namespace', 'my-second-namespace'], - } - }, + namespace: 'monitoring', prometheus+:: { - serviceMonitorMyNamespace: { - apiVersion: 'monitoring.coreos.com/v1', - kind: 'ServiceMonitor', - metadata: { - name: 'my-servicemonitor', - namespace: 'my-namespace', + namespaces+: ['my-namespace', 'my-second-namespace'], + }, + }, + prometheus+:: { + serviceMonitorMyNamespace: { + apiVersion: 'monitoring.coreos.com/v1', + kind: 'ServiceMonitor', + metadata: { + name: 'my-servicemonitor', + namespace: 'my-namespace', + }, + spec: { + jobLabel: 'app', + endpoints: [ + { + port: 'http-metrics', }, - spec: { - jobLabel: 'app', - endpoints: [ - { - port: 'http-metrics', - }, - ], - selector: { - matchLabels: { - 'app': 'myapp', - }, - }, + ], + selector: { + matchLabels: { + app: 'myapp', }, }, - }, + }, + }, + }, }; diff --git a/examples/additional-namespaces-servicemonitor.jsonnet b/examples/additional-namespaces-servicemonitor.jsonnet index 0262b4e0..0f3add96 100644 --- a/examples/additional-namespaces-servicemonitor.jsonnet +++ b/examples/additional-namespaces-servicemonitor.jsonnet @@ -1,33 +1,33 @@ local kp = (import 'kube-prometheus/kube-prometheus.libsonnet') + { _config+:: { - namespace: 'monitoring', - prometheus+:: { - namespaces+: ['my-namespace', 'my-second-namespace'], - } - }, + namespace: 'monitoring', prometheus+:: { - serviceMonitorMyNamespace: { - apiVersion: 'monitoring.coreos.com/v1', - kind: 'ServiceMonitor', - metadata: { - name: 'my-servicemonitor', - namespace: 'my-namespace', + namespaces+: ['my-namespace', 'my-second-namespace'], + }, + }, + prometheus+:: { + serviceMonitorMyNamespace: { + apiVersion: 'monitoring.coreos.com/v1', + kind: 'ServiceMonitor', + metadata: { + name: 'my-servicemonitor', + namespace: 'my-namespace', + }, + spec: { + jobLabel: 'app', + endpoints: [ + { + port: 'http-metrics', }, - spec: { - jobLabel: 'app', - endpoints: [ - { - port: 'http-metrics', - }, - ], - selector: { - matchLabels: { - 'app': 'myapp', - }, - }, + ], + selector: { + matchLabels: { + app: 'myapp', }, }, - }, + }, + }, + }, }; diff --git a/jsonnetfile.lock.json b/jsonnetfile.lock.json index 5d054e2b..b64313fe 100644 --- a/jsonnetfile.lock.json +++ b/jsonnetfile.lock.json @@ -27,7 +27,7 @@ "subdir": "" } }, - "version": "15ddfa20a6921ffbd43172eb54f6bdc1bcf8d3d3" + "version": "a08a6754d527eae13c553bd7565d5f4e9e9f3c0e" }, { "name": "grafonnet", diff --git a/manifests/grafana-dashboardDefinitions.yaml b/manifests/grafana-dashboardDefinitions.yaml index 1065be04..41841404 100644 --- a/manifests/grafana-dashboardDefinitions.yaml +++ b/manifests/grafana-dashboardDefinitions.yaml @@ -1238,7 +1238,7 @@ items: "query": "label_values(apiserver_request_total{job=\"apiserver\"}, instance)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -1287,6 +1287,1372 @@ items: metadata: name: grafana-dashboard-apiserver namespace: monitoring +- apiVersion: v1 + data: + cluster-total.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 3, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A" + } + ], + "title": "Current Rate of Bytes Received", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "id": 4, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A" + } + ], + "title": "Current Rate of Bytes Transmitted", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "columns": [ + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + } + ], + "datasource": "prometheus", + "fill": 1, + "fontSize": "90%", + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "lines": true, + "linewidth": 1, + "minSpan": 24, + "nullPointMode": "null as zero", + "renderer": "flot", + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": false + }, + "spaceLength": 10, + "span": 24, + "styles": [ + { + "alias": "Time", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Time", + "thresholds": [ + + ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Current Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "d/8b7a8b326d7a6f1f04244066368c67af/kubernetes-networking-namespace-pods?orgId=1&refresh=30s&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "title": "Current Status", + "transform": "table", + "type": "table" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 6, + "panels": [ + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 11 + }, + "id": 7, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A" + } + ], + "title": "Average Rate of Bytes Received", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 11 + }, + "id": 8, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A" + } + ], + "title": "Average Rate of Bytes Transmitted", + "type": "grafana-piechart-panel", + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 11 + }, + "id": 9, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth History", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 12 + }, + "id": 10, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 21 + }, + "id": 11, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 30 + }, + "id": 12, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 31 + }, + "id": 13, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 40 + }, + "id": 14, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 31 + }, + "id": 15, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 50 + }, + "id": 16, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 59 + }, + "id": 17, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "30s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Networking / Cluster", + "uid": "ff635a025bcfea7bc3dd4f508990a3e9", + "version": 0 + } + kind: ConfigMap + metadata: + name: grafana-dashboard-cluster-total + namespace: monitoring - apiVersion: v1 data: controller-manager.json: |- @@ -2355,7 +3721,7 @@ items: "query": "label_values(process_cpu_seconds_total{job=\"kube-controller-manager\"}, instance)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -3775,6 +5141,1084 @@ items: "showTitle": true, "title": "Memory Requests", "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "avg(irate(container_network_receive_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Namespace: Received", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "avg(irate(container_network_transmit_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Namespace: Transmitted", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 18, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\".+\"}[$interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" } ], "schemaVersion": 14, @@ -3826,6 +6270,41 @@ items: "tagsQuery": "", "type": "query", "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false } ] }, @@ -4695,6 +7174,888 @@ items: "showTitle": true, "title": "Memory Quota", "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" } ], "schemaVersion": 14, @@ -4773,6 +8134,41 @@ items: "tagsQuery": "", "type": "query", "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false } ] }, @@ -5522,7 +8918,7 @@ items: ], "targets": [ { - "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)", + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -5540,7 +8936,7 @@ items: "step": 10 }, { - "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{node=\"$node\"}) by (pod)", + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{node=\"$node\"}) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -5558,7 +8954,7 @@ items: "step": 10 }, { - "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{node=\"$node\"}) by (pod)", + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{node=\"$node\"}) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -5567,7 +8963,7 @@ items: "step": 10 }, { - "expr": "sum(container_memory_rss{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)", + "expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -5576,7 +8972,7 @@ items: "step": 10 }, { - "expr": "sum(container_memory_cache{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)", + "expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -5585,7 +8981,7 @@ items: "step": 10 }, { - "expr": "sum(container_memory_swap{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)", + "expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -6605,6 +10001,594 @@ items: "showTitle": true, "title": "Memory Quota", "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" } ], "schemaVersion": 14, @@ -6710,6 +10694,41 @@ items: "tagsQuery": "", "type": "query", "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false } ] }, @@ -7498,6 +11517,1084 @@ items: "showTitle": true, "title": "Memory Quota", "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Pod: Received", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Pod: Transmitted", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod) \ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" } ], "schemaVersion": 14, @@ -7630,6 +12727,41 @@ items: "tagsQuery": "", "type": "query", "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false } ] }, @@ -8508,6 +13640,1102 @@ items: "showTitle": true, "title": "Memory Quota", "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down to pods", + "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$type", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Workload: Received", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Workload: Transmitted", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod) \ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" } ], "schemaVersion": 14, @@ -8582,6 +14810,73 @@ items: "tagValuesQuery": "", "tags": [ + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "deployment", + "value": "deployment" + }, + "datasource": "prometheus", + "definition": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [ + ], "tagsQuery": "", "type": "query", @@ -8717,7 +15012,7 @@ items: "tableColumn": "", "targets": [ { - "expr": "sum(up{job=\"kubelet\"})", + "expr": "sum(up{cluster=\"$cluster\", job=\"kubelet\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "", @@ -8801,7 +15096,7 @@ items: "tableColumn": "", "targets": [ { - "expr": "sum(kubelet_running_pod_count{job=\"kubelet\", instance=~\"$instance\"})", + "expr": "sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -8885,7 +15180,7 @@ items: "tableColumn": "", "targets": [ { - "expr": "sum(kubelet_running_container_count{job=\"kubelet\", instance=~\"$instance\"})", + "expr": "sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -8969,7 +15264,7 @@ items: "tableColumn": "", "targets": [ { - "expr": "sum(volume_manager_total_volumes{job=\"kubelet\", instance=~\"$instance\", state=\"actual_state_of_world\"})", + "expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\", state=\"actual_state_of_world\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -9053,7 +15348,7 @@ items: "tableColumn": "", "targets": [ { - "expr": "sum(volume_manager_total_volumes{job=\"kubelet\", instance=~\"$instance\",state=\"desired_state_of_world\"})", + "expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\",state=\"desired_state_of_world\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -9137,7 +15432,7 @@ items: "tableColumn": "", "targets": [ { - "expr": "sum(rate(kubelet_node_config_error{job=\"kubelet\", instance=~\"$instance\"}[5m]))", + "expr": "sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -9217,7 +15512,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(rate(kubelet_runtime_operations_total{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (operation_type, instance)", + "expr": "sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (operation_type, instance)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} {{operation_type}}", @@ -9308,7 +15603,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(rate(kubelet_runtime_operations_errors_total{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type)", + "expr": "sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} {{operation_type}}", @@ -9412,7 +15707,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type, le))", + "expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type, le))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} {{operation_type}}", @@ -9516,14 +15811,14 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(rate(kubelet_pod_start_duration_seconds_count{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)", + "expr": "sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} pod", "refId": "A" }, { - "expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)", + "expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} worker", @@ -9614,14 +15909,14 @@ items: "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_count{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))", + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} pod", "refId": "A" }, { - "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))", + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} worker", @@ -9727,7 +16022,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(rate(storage_operation_duration_seconds_count{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)", + "expr": "sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}", @@ -9820,7 +16115,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(rate(storage_operation_errors_total{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)", + "expr": "sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}", @@ -9926,7 +16221,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin, le))", + "expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin, le))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}", @@ -10030,7 +16325,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type)", + "expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{operation_type}}", @@ -10121,7 +16416,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type, le))", + "expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type, le))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} {{operation_type}}", @@ -10226,7 +16521,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance)", + "expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -10317,7 +16612,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))", + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -10421,7 +16716,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))", + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -10525,28 +16820,28 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(rate(rest_client_requests_total{job=\"kubelet\", instance=~\"$instance\",code=~\"2..\"}[5m]))", + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"2..\"}[5m]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "2xx", "refId": "A" }, { - "expr": "sum(rate(rest_client_requests_total{job=\"kubelet\", instance=~\"$instance\",code=~\"3..\"}[5m]))", + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"3..\"}[5m]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "3xx", "refId": "B" }, { - "expr": "sum(rate(rest_client_requests_total{job=\"kubelet\", instance=~\"$instance\",code=~\"4..\"}[5m]))", + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"4..\"}[5m]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "4xx", "refId": "C" }, { - "expr": "sum(rate(rest_client_requests_total{job=\"kubelet\", instance=~\"$instance\",code=~\"5..\"}[5m]))", + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"5..\"}[5m]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "5xx", @@ -10650,7 +16945,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))", + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}} {{verb}} {{url}}", @@ -10754,7 +17049,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "process_resident_memory_bytes{job=\"kubelet\",instance=~\"$instance\"}", + "expr": "process_resident_memory_bytes{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -10845,7 +17140,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "rate(process_cpu_seconds_total{job=\"kubelet\",instance=~\"$instance\"}[5m])", + "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -10936,7 +17231,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "go_goroutines{job=\"kubelet\",instance=~\"$instance\"}", + "expr": "go_goroutines{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -11020,6 +17315,32 @@ items: "allValue": null, "current": { + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + }, "datasource": "$datasource", "hide": 0, @@ -11030,10 +17351,10 @@ items: "options": [ ], - "query": "label_values(kubelet_runtime_operations{job=\"kubelet\"}, instance)", + "query": "label_values(kubelet_runtime_operations{cluster=\"$cluster\", job=\"kubelet\"}, instance)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -11082,6 +17403,2826 @@ items: metadata: name: grafana-dashboard-kubelet namespace: monitoring +- apiVersion: v1 + data: + namespace-by-pod.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "prometheus", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "height": 9, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "prometheus", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "height": 9, + "id": 4, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "columns": [ + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + } + ], + "datasource": "prometheus", + "fill": 1, + "fontSize": "100%", + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "lines": true, + "linewidth": 1, + "minSpan": 24, + "nullPointMode": "null as zero", + "renderer": "flot", + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": false + }, + "spaceLength": 10, + "span": 24, + "styles": [ + { + "alias": "Time", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Time", + "thresholds": [ + + ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "d/7a18067ce943a40ae25454675c19ff5c/kubernetes-networking-pod?orgId=1&refresh=30s&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "title": "Current Status", + "transform": "table", + "type": "table" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 19 + }, + "id": 6, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 20 + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 20 + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 29 + }, + "id": 9, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 30 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 30 + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 30 + }, + "id": 12, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 40 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 40 + }, + "id": 14, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "30s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "prometheus", + "definition": "label_values(container_network_receive_packets_total, namespace)", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total, namespace)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Networking / Namespace (Pods)", + "uid": "8b7a8b326d7a6f1f04244066368c67af", + "version": 0 + } + kind: ConfigMap + metadata: + name: grafana-dashboard-namespace-by-pod + namespace: monitoring +- apiVersion: v1 + data: + namespace-by-workload.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 3, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A" + } + ], + "title": "Current Rate of Bytes Received", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "id": 4, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A" + } + ], + "title": "Current Rate of Bytes Transmitted", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "columns": [ + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + }, + { + "text": "", + "value": "" + } + ], + "datasource": "prometheus", + "fill": 1, + "fontSize": "90%", + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "lines": true, + "linewidth": 1, + "minSpan": 24, + "nullPointMode": "null as zero", + "renderer": "flot", + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": false + }, + "spaceLength": 10, + "span": 24, + "styles": [ + { + "alias": "Time", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Time", + "thresholds": [ + + ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Current Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "d/728bf77cc1166d2f3133bf25846876cc/kubernetes-networking-workload?orgId=1&refresh=30s&var-namespace=$namespace&var-type=$type&var-workload=$__cell", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "title": "Current Status", + "transform": "table", + "type": "table" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 19 + }, + "id": 6, + "panels": [ + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 20 + }, + "id": 7, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A" + } + ], + "title": "Average Rate of Bytes Received", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 20 + }, + "id": 8, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A" + } + ], + "title": "Average Rate of Bytes Transmitted", + "type": "grafana-piechart-panel", + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 29 + }, + "id": 9, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth HIstory", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 38 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 38 + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 39 + }, + "id": 12, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 40 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 40 + }, + "id": 14, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 40 + }, + "id": 15, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 41 + }, + "id": 16, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 41 + }, + "id": 17, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "30s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "prometheus", + "definition": "label_values(container_network_receive_packets_total, namespace)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total, namespace)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "deployment", + "value": "deployment" + }, + "datasource": "prometheus", + "definition": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Networking / Namespace (Workload)", + "uid": "bbb2a765a623ae38130206c7d94a160f", + "version": 0 + } + kind: ConfigMap + metadata: + name: grafana-dashboard-namespace-by-workload + namespace: monitoring - apiVersion: v1 data: node-cluster-rsrc-use.json: |- @@ -14432,7 +23573,7 @@ items: "query": "label_values(kubelet_volume_stats_capacity_bytes, cluster)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -14458,7 +23599,7 @@ items: "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\"}, namespace)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -14484,7 +23625,7 @@ items: "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\"}, persistentvolumeclaim)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -14533,6 +23674,1164 @@ items: metadata: name: grafana-dashboard-persistentvolumesusage namespace: monitoring +- apiVersion: v1 + data: + pod-total.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "prometheus", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "height": 9, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace: $pod", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "prometheus", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "height": 9, + "id": 4, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace: $pod", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 11 + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 11 + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 20 + }, + "id": 8, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 21 + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 21 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 21 + }, + "id": 11, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 32 + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 32 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "30s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "prometheus", + "definition": "label_values(container_network_receive_packets_total, namespace)", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total, namespace)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "", + "value": "" + }, + "datasource": "prometheus", + "definition": "label_values(container_network_receive_packets_total{namespace=~\"$namespace\"}, pod)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "pod", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{namespace=~\"$namespace\"}, pod)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Networking / Pod", + "uid": "7a18067ce943a40ae25454675c19ff5c", + "version": 0 + } + kind: ConfigMap + metadata: + name: grafana-dashboard-pod-total + namespace: monitoring - apiVersion: v1 data: pods.json: |- @@ -15070,7 +25369,7 @@ items: "query": "label_values(kube_pod_info, cluster)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -15096,7 +25395,7 @@ items: "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -15122,7 +25421,7 @@ items: "query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=~\"$namespace\"}, pod)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -15148,7 +25447,7 @@ items: "query": "label_values(kube_pod_container_info{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}, container)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -18509,7 +28808,7 @@ items: "query": "label_values(kubeproxy_network_programming_duration_seconds_bucket{job=\"kube-proxy\"}, instance)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -19551,7 +29850,7 @@ items: "query": "label_values(process_cpu_seconds_total{job=\"kube-scheduler\"}, instance)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -20409,7 +30708,7 @@ items: "query": "label_values(kube_statefulset_metadata_generation, cluster)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -20435,7 +30734,7 @@ items: "query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -20461,7 +30760,7 @@ items: "query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, statefulset)", "refresh": 2, "regex": "", - "sort": 0, + "sort": 1, "tagValuesQuery": "", "tags": [ @@ -20510,4 +30809,1140 @@ items: metadata: name: grafana-dashboard-statefulset namespace: monitoring +- apiVersion: v1 + data: + workload-total.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 3, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A" + } + ], + "title": "Current Rate of Bytes Received", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "id": 4, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A" + } + ], + "title": "Current Rate of Bytes Transmitted", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "panels": [ + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 11 + }, + "id": 6, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A" + } + ], + "title": "Average Rate of Bytes Received", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "aliasColors": { + + }, + "breakpoint": "50%", + "cacheTimeout": null, + "combine": { + "label": "Others", + "threshold": 0 + }, + "datasource": "prometheus", + "fontSize": "80%", + "format": "Bps", + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 11 + }, + "id": 7, + "interval": null, + "legend": { + "percentage": true, + "percentageDecimals": null, + "show": true, + "values": true + }, + "legendType": "Right side", + "maxDataPoints": 3, + "nullPointMode": "connected", + "pieType": "donut", + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A" + } + ], + "title": "Average Rate of Bytes Transmitted", + "type": "grafana-piechart-panel", + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 11 + }, + "id": 8, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth HIstory", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 12 + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 12 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 21 + }, + "id": 11, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 22 + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 22 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 22 + }, + "id": 14, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 23 + }, + "id": 15, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "prometheus", + "fill": 2, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 23 + }, + "id": 16, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "30s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "prometheus", + "definition": "label_values(container_network_receive_packets_total, namespace)", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total, namespace)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "", + "value": "" + }, + "datasource": "prometheus", + "definition": "label_values(mixin_pod_workload{namespace=~\"$namespace\"}, workload)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "workload", + "options": [ + + ], + "query": "label_values(mixin_pod_workload{namespace=~\"$namespace\"}, workload)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "deployment", + "value": "deployment" + }, + "datasource": "prometheus", + "definition": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "prometheus", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Kubernetes / Networking / Workload", + "uid": "728bf77cc1166d2f3133bf25846876cc", + "version": 0 + } + kind: ConfigMap + metadata: + name: grafana-dashboard-workload-total + namespace: monitoring kind: ConfigMapList diff --git a/manifests/grafana-deployment.yaml b/manifests/grafana-deployment.yaml index e4bd4d73..aec58617 100644 --- a/manifests/grafana-deployment.yaml +++ b/manifests/grafana-deployment.yaml @@ -45,6 +45,9 @@ spec: - mountPath: /grafana-dashboard-definitions/0/apiserver name: grafana-dashboard-apiserver readOnly: false + - mountPath: /grafana-dashboard-definitions/0/cluster-total + name: grafana-dashboard-cluster-total + readOnly: false - mountPath: /grafana-dashboard-definitions/0/controller-manager name: grafana-dashboard-controller-manager readOnly: false @@ -69,6 +72,12 @@ spec: - mountPath: /grafana-dashboard-definitions/0/kubelet name: grafana-dashboard-kubelet readOnly: false + - mountPath: /grafana-dashboard-definitions/0/namespace-by-pod + name: grafana-dashboard-namespace-by-pod + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/namespace-by-workload + name: grafana-dashboard-namespace-by-workload + readOnly: false - mountPath: /grafana-dashboard-definitions/0/node-cluster-rsrc-use name: grafana-dashboard-node-cluster-rsrc-use readOnly: false @@ -81,6 +90,9 @@ spec: - mountPath: /grafana-dashboard-definitions/0/persistentvolumesusage name: grafana-dashboard-persistentvolumesusage readOnly: false + - mountPath: /grafana-dashboard-definitions/0/pod-total + name: grafana-dashboard-pod-total + readOnly: false - mountPath: /grafana-dashboard-definitions/0/pods name: grafana-dashboard-pods readOnly: false @@ -99,6 +111,9 @@ spec: - mountPath: /grafana-dashboard-definitions/0/statefulset name: grafana-dashboard-statefulset readOnly: false + - mountPath: /grafana-dashboard-definitions/0/workload-total + name: grafana-dashboard-workload-total + readOnly: false nodeSelector: beta.kubernetes.io/os: linux securityContext: @@ -117,6 +132,9 @@ spec: - configMap: name: grafana-dashboard-apiserver name: grafana-dashboard-apiserver + - configMap: + name: grafana-dashboard-cluster-total + name: grafana-dashboard-cluster-total - configMap: name: grafana-dashboard-controller-manager name: grafana-dashboard-controller-manager @@ -141,6 +159,12 @@ spec: - configMap: name: grafana-dashboard-kubelet name: grafana-dashboard-kubelet + - configMap: + name: grafana-dashboard-namespace-by-pod + name: grafana-dashboard-namespace-by-pod + - configMap: + name: grafana-dashboard-namespace-by-workload + name: grafana-dashboard-namespace-by-workload - configMap: name: grafana-dashboard-node-cluster-rsrc-use name: grafana-dashboard-node-cluster-rsrc-use @@ -153,6 +177,9 @@ spec: - configMap: name: grafana-dashboard-persistentvolumesusage name: grafana-dashboard-persistentvolumesusage + - configMap: + name: grafana-dashboard-pod-total + name: grafana-dashboard-pod-total - configMap: name: grafana-dashboard-pods name: grafana-dashboard-pods @@ -171,3 +198,6 @@ spec: - configMap: name: grafana-dashboard-statefulset name: grafana-dashboard-statefulset + - configMap: + name: grafana-dashboard-workload-total + name: grafana-dashboard-workload-total diff --git a/manifests/prometheus-rules.yaml b/manifests/prometheus-rules.yaml index 007b3548..88a02050 100644 --- a/manifests/prometheus-rules.yaml +++ b/manifests/prometheus-rules.yaml @@ -79,6 +79,22 @@ spec: rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container!="POD"}[5m]) ) * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info) record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate + - expr: | + container_memory_working_set_bytes{job="kubelet", image!=""} + * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info) + record: node_namespace_pod_container:container_memory_working_set_bytes + - expr: | + container_memory_rss{job="kubelet", image!=""} + * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info) + record: node_namespace_pod_container:container_memory_rss + - expr: | + container_memory_cache{job="kubelet", image!=""} + * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info) + record: node_namespace_pod_container:container_memory_cache + - expr: | + container_memory_swap{job="kubelet", image!=""} + * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info) + record: node_namespace_pod_container:container_memory_swap - expr: | sum(container_memory_usage_bytes{job="kubelet", image!="", container!="POD"}) by (namespace) record: namespace:container_memory_usage_bytes:sum @@ -583,6 +599,16 @@ spec: for: 15m labels: severity: critical + - alert: KubeContainerWaiting + annotations: + message: Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}} + has been in waiting state for longer than 1 hour. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting + expr: | + sum by (namespace, pod, container) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0 + for: 1h + labels: + severity: warning - alert: KubeDaemonSetNotScheduled annotations: message: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset @@ -797,6 +823,14 @@ spec: for: 15m labels: severity: warning + - alert: KubeNodeUnreachable + annotations: + message: '{{ $labels.node }} is unreachable and some workloads may be rescheduled.' + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable + expr: | + kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} == 1 + labels: + severity: warning - alert: KubeVersionMismatch annotations: message: There are {{ $value }} different semantic versions of Kubernetes From 059e74d15652ea5bf52de2706c6a3577dda3eae1 Mon Sep 17 00:00:00 2001 From: Deepak Jain Date: Mon, 14 Oct 2019 13:07:19 +0530 Subject: [PATCH 09/17] Docs for rawGrafanaDashboards filed Propose in this https://github.com/brancz/kubernetes-grafana/pull/78 --- ...prometheus-rules-and-grafana-dashboards.md | 20 +++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/docs/developing-prometheus-rules-and-grafana-dashboards.md b/docs/developing-prometheus-rules-and-grafana-dashboards.md index 34801a88..d3fbd93e 100644 --- a/docs/developing-prometheus-rules-and-grafana-dashboards.md +++ b/docs/developing-prometheus-rules-and-grafana-dashboards.md @@ -310,3 +310,23 @@ local kp = (import 'kube-prometheus/kube-prometheus.libsonnet') + { { ['prometheus-' + name]: kp.prometheus[name] for name in std.objectFields(kp.prometheus) } + { ['grafana-' + name]: kp.grafana[name] for name in std.objectFields(kp.grafana) } ``` + +Incase you have lots of json dashboard exported out from grafan UI the above approch is going to take lots of time. to improve performance we can use `rawGrafanaDashboards` field and provide it's value as json string by using importstr +```jsonnet +local kp = (import 'kube-prometheus/kube-prometheus.libsonnet') + { + _config+:: { + namespace: 'monitoring', + }, + rawGrafanaDashboards+:: { + 'my-dashboard.json': (importstr 'example-grafana-dashboard.json'), + }, +}; + +{ ['00namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } + +{ ['0prometheus-operator-' + name]: kp.prometheusOperator[name] for name in std.objectFields(kp.prometheusOperator) } + +{ ['node-exporter-' + name]: kp.nodeExporter[name] for name in std.objectFields(kp.nodeExporter) } + +{ ['kube-state-metrics-' + name]: kp.kubeStateMetrics[name] for name in std.objectFields(kp.kubeStateMetrics) } + +{ ['alertmanager-' + name]: kp.alertmanager[name] for name in std.objectFields(kp.alertmanager) } + +{ ['prometheus-' + name]: kp.prometheus[name] for name in std.objectFields(kp.prometheus) } + +{ ['grafana-' + name]: kp.grafana[name] for name in std.objectFields(kp.grafana) } +``` From d99aefe27628d01fcc6fb764e3bca4203742a92d Mon Sep 17 00:00:00 2001 From: Deepak Jain Date: Mon, 14 Oct 2019 14:29:11 +0530 Subject: [PATCH 10/17] CLOUD-3031| Deepak Jain| adding example file --- ...ng-prometheus-rules-and-grafana-dashboards.md | 1 + ...ditional-rendered-dashboard-example-2.jsonnet | 16 ++++++++++++++++ 2 files changed, 17 insertions(+) create mode 100644 examples/grafana-additional-rendered-dashboard-example-2.jsonnet diff --git a/docs/developing-prometheus-rules-and-grafana-dashboards.md b/docs/developing-prometheus-rules-and-grafana-dashboards.md index d3fbd93e..974c3cc4 100644 --- a/docs/developing-prometheus-rules-and-grafana-dashboards.md +++ b/docs/developing-prometheus-rules-and-grafana-dashboards.md @@ -312,6 +312,7 @@ local kp = (import 'kube-prometheus/kube-prometheus.libsonnet') + { ``` Incase you have lots of json dashboard exported out from grafan UI the above approch is going to take lots of time. to improve performance we can use `rawGrafanaDashboards` field and provide it's value as json string by using importstr +[embedmd]:# (../examples/grafana-additional-rendered-dashboard-example-2.jsonnet) ```jsonnet local kp = (import 'kube-prometheus/kube-prometheus.libsonnet') + { _config+:: { diff --git a/examples/grafana-additional-rendered-dashboard-example-2.jsonnet b/examples/grafana-additional-rendered-dashboard-example-2.jsonnet new file mode 100644 index 00000000..391b0f02 --- /dev/null +++ b/examples/grafana-additional-rendered-dashboard-example-2.jsonnet @@ -0,0 +1,16 @@ +local kp = (import 'kube-prometheus/kube-prometheus.libsonnet') + { + _config+:: { + namespace: 'monitoring', + }, + rawGrafanaDashboards+:: { + 'my-dashboard.json': (importstr 'example-grafana-dashboard.json'), + }, +}; + +{ ['00namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) } + +{ ['0prometheus-operator-' + name]: kp.prometheusOperator[name] for name in std.objectFields(kp.prometheusOperator) } + +{ ['node-exporter-' + name]: kp.nodeExporter[name] for name in std.objectFields(kp.nodeExporter) } + +{ ['kube-state-metrics-' + name]: kp.kubeStateMetrics[name] for name in std.objectFields(kp.kubeStateMetrics) } + +{ ['alertmanager-' + name]: kp.alertmanager[name] for name in std.objectFields(kp.alertmanager) } + +{ ['prometheus-' + name]: kp.prometheus[name] for name in std.objectFields(kp.prometheus) } + +{ ['grafana-' + name]: kp.grafana[name] for name in std.objectFields(kp.grafana) } From fd5b77cadf0de374cf3ad01a8a526f4246b77bbd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Beno=C3=AEt=20Knecht?= Date: Mon, 28 Oct 2019 16:25:51 +0100 Subject: [PATCH 11/17] jsonnetfile.lock.json: Update node-mixin dependency Upgrade to prometheus/node_exporter@d574b4b, which includes a better metric for memory saturation. See prometheus/node_exporter#1524. --- jsonnetfile.lock.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/jsonnetfile.lock.json b/jsonnetfile.lock.json index b64313fe..0df0f590 100644 --- a/jsonnetfile.lock.json +++ b/jsonnetfile.lock.json @@ -97,7 +97,7 @@ "subdir": "docs/node-mixin" } }, - "version": "9f49fff79ef85fcebb69289622150e6d5346528b" + "version": "d574b4b41b72966a2ace4d6d81195081dfca8301" }, { "name": "promgrafonnet", From 20eb5b312aaff6cce2208001c4ca99b3c9e5ff70 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Beno=C3=AEt=20Knecht?= Date: Mon, 28 Oct 2019 16:35:12 +0100 Subject: [PATCH 12/17] manifests: Regenerate with new node-mixin dependency Generate manifests for fd5b77c. --- manifests/grafana-dashboardDefinitions.yaml | 10 +++++----- manifests/prometheus-rules.yaml | 8 ++------ 2 files changed, 7 insertions(+), 11 deletions(-) diff --git a/manifests/grafana-dashboardDefinitions.yaml b/manifests/grafana-dashboardDefinitions.yaml index 41841404..a9c7baba 100644 --- a/manifests/grafana-dashboardDefinitions.yaml +++ b/manifests/grafana-dashboardDefinitions.yaml @@ -20553,7 +20553,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "instance:node_memory_swap_io_pages:rate1m{job=\"node-exporter\"}", + "expr": "instance:node_vmstat_pgmajfault:rate1m{job=\"node-exporter\"}", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{instance}}", @@ -20566,7 +20566,7 @@ items: ], "timeFrom": null, "timeShift": null, - "title": "Memory Saturation (Swapped Pages)", + "title": "Memory Saturation (Major Page Faults)", "tooltip": { "shared": false, "sort": 0, @@ -21501,10 +21501,10 @@ items: "steppedLine": false, "targets": [ { - "expr": "instance:node_memory_swap_io_pages:rate1m{job=\"node-exporter\", instance=\"$instance\"}", + "expr": "instance:node_vmstat_pgmajfault:rate1m{job=\"node-exporter\", instance=\"$instance\"}", "format": "time_series", "intervalFactor": 2, - "legendFormat": "Swap IO", + "legendFormat": "Major page faults", "legendLink": null, "step": 10 } @@ -21514,7 +21514,7 @@ items: ], "timeFrom": null, "timeShift": null, - "title": "Memory Saturation (pages swapped per second)", + "title": "Memory Saturation (Major Page Faults)", "tooltip": { "shared": false, "sort": 0, diff --git a/manifests/prometheus-rules.yaml b/manifests/prometheus-rules.yaml index 88a02050..2b9e6d26 100644 --- a/manifests/prometheus-rules.yaml +++ b/manifests/prometheus-rules.yaml @@ -37,12 +37,8 @@ spec: ) record: instance:node_memory_utilisation:ratio - expr: | - ( - rate(node_vmstat_pgpgin{job="node-exporter"}[1m]) - + - rate(node_vmstat_pgpgout{job="node-exporter"}[1m]) - ) - record: instance:node_memory_swap_io_pages:rate1m + rate(node_vmstat_pgmajfault{job="node-exporter"}[1m]) + record: instance:node_vmstat_pgmajfault:rate1m - expr: | rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m]) record: instance_device:node_disk_io_time_seconds:rate1m From 01d30382aa5e5006473019aed36838758b13f231 Mon Sep 17 00:00:00 2001 From: Lili Cosic Date: Tue, 29 Oct 2019 14:27:39 +0100 Subject: [PATCH 13/17] jsonnet/kube-prometheus/alerts: Add namespace to TargetDown msg --- jsonnet/kube-prometheus/alerts/general.libsonnet | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/jsonnet/kube-prometheus/alerts/general.libsonnet b/jsonnet/kube-prometheus/alerts/general.libsonnet index 79eba7d9..441ec777 100644 --- a/jsonnet/kube-prometheus/alerts/general.libsonnet +++ b/jsonnet/kube-prometheus/alerts/general.libsonnet @@ -7,7 +7,7 @@ { alert: 'TargetDown', annotations: { - message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }} targets are down.', + message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }} targets in {{ $labels.namespace }} namespace are down.', }, expr: '100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job, namespace, service)) > 10', 'for': '10m', From 78b9183837bc59ed34532a415a6c404181334a5e Mon Sep 17 00:00:00 2001 From: Lili Cosic Date: Tue, 29 Oct 2019 14:59:13 +0100 Subject: [PATCH 14/17] manifests/prometheus-rules.yaml: Regenerate file --- manifests/prometheus-rules.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/manifests/prometheus-rules.yaml b/manifests/prometheus-rules.yaml index 769e6559..e258b84b 100644 --- a/manifests/prometheus-rules.yaml +++ b/manifests/prometheus-rules.yaml @@ -1148,8 +1148,8 @@ spec: rules: - alert: TargetDown annotations: - message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }} targets are - down.' + message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }} targets in + {{ $labels.namespace }} namespace are down.' expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job, namespace, service)) > 10 for: 10m From 02369dd1da07cd0f78d74e021ed84979a14cef1f Mon Sep 17 00:00:00 2001 From: Sergiusz Urbaniak Date: Fri, 1 Nov 2019 14:20:12 +0100 Subject: [PATCH 15/17] jsonnet/kube-prometheus: bump prometheus-operator --- jsonnet/kube-prometheus/jsonnetfile.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/jsonnet/kube-prometheus/jsonnetfile.json b/jsonnet/kube-prometheus/jsonnetfile.json index 4817e20c..fa7545af 100644 --- a/jsonnet/kube-prometheus/jsonnetfile.json +++ b/jsonnet/kube-prometheus/jsonnetfile.json @@ -38,7 +38,7 @@ "subdir": "jsonnet/prometheus-operator" } }, - "version": "release-0.33" + "version": "release-0.34" }, { "name": "etcd-mixin", From 5e75f27ae28db3bb7de4c8c298a5cec5eeae8f15 Mon Sep 17 00:00:00 2001 From: Sergiusz Urbaniak Date: Fri, 1 Nov 2019 15:26:56 +0100 Subject: [PATCH 16/17] jsonnet: pin node-mixin due to upstream bug --- jsonnetfile.json | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/jsonnetfile.json b/jsonnetfile.json index 3062e3bc..561224c2 100644 --- a/jsonnetfile.json +++ b/jsonnetfile.json @@ -1,13 +1,23 @@ { - "dependencies": [ - { - "name": "kube-prometheus", - "source": { - "local": { - "directory": "jsonnet/kube-prometheus" - } - }, - "version": "" + "dependencies": [ + { + "name": "kube-prometheus", + "source": { + "local": { + "directory": "jsonnet/kube-prometheus" } - ] + }, + "version": "" + }, + { + "name": "node-mixin", + "source": { + "git": { + "remote": "https://github.com/prometheus/node_exporter", + "subdir": "docs/node-mixin" + } + }, + "version": "5a7b85876d6108a91f0d8673c0d7eca38687671b" + } + ] } From c8f0471279c71f8ca51d069ddfe646a280443574 Mon Sep 17 00:00:00 2001 From: Sergiusz Urbaniak Date: Fri, 1 Nov 2019 15:27:14 +0100 Subject: [PATCH 17/17] jsonnet: regenerate --- jsonnetfile.lock.json | 230 ++--- manifests/grafana-dashboardDefinitions.yaml | 771 ++++++++++++---- .../prometheus-operator-serviceMonitor.yaml | 4 +- manifests/prometheus-rules.yaml | 260 +++--- ...0alertmanagerCustomResourceDefinition.yaml | 728 +++++++-------- ...r-0podmonitorCustomResourceDefinition.yaml | 8 +- ...r-0prometheusCustomResourceDefinition.yaml | 857 +++++++++--------- ...rometheusruleCustomResourceDefinition.yaml | 205 +---- ...ervicemonitorCustomResourceDefinition.yaml | 53 +- .../prometheus-operator-clusterRole.yaml | 2 +- ...rometheus-operator-clusterRoleBinding.yaml | 2 +- .../setup/prometheus-operator-deployment.yaml | 8 +- .../setup/prometheus-operator-service.yaml | 2 +- .../prometheus-operator-serviceAccount.yaml | 2 +- 14 files changed, 1702 insertions(+), 1430 deletions(-) diff --git a/jsonnetfile.lock.json b/jsonnetfile.lock.json index 0df0f590..daa3bb8f 100644 --- a/jsonnetfile.lock.json +++ b/jsonnetfile.lock.json @@ -1,113 +1,123 @@ { - "dependencies": [ - { - "name": "kube-prometheus", - "source": { - "local": { - "directory": "jsonnet/kube-prometheus" - } - }, - "version": "" - }, - { - "name": "ksonnet", - "source": { - "git": { - "remote": "https://github.com/ksonnet/ksonnet-lib", - "subdir": "" - } - }, - "version": "0d2f82676817bbf9e4acf6495b2090205f323b9f" - }, - { - "name": "kubernetes-mixin", - "source": { - "git": { - "remote": "https://github.com/kubernetes-monitoring/kubernetes-mixin", - "subdir": "" - } - }, - "version": "a08a6754d527eae13c553bd7565d5f4e9e9f3c0e" - }, - { - "name": "grafonnet", - "source": { - "git": { - "remote": "https://github.com/grafana/grafonnet-lib", - "subdir": "grafonnet" - } - }, - "version": "69bc267211790a1c3f4ea6e6211f3e8ffe22f987" - }, - { - "name": "grafana-builder", - "source": { - "git": { - "remote": "https://github.com/kausalco/public", - "subdir": "grafana-builder" - } - }, - "version": "e59d64a96a73e65ba53ba7fe05c9598974cc4a52" - }, - { - "name": "grafana", - "source": { - "git": { - "remote": "https://github.com/brancz/kubernetes-grafana", - "subdir": "grafana" - } - }, - "version": "539a90dbf63c812ad0194d8078dd776868a11c81" - }, - { - "name": "prometheus-operator", - "source": { - "git": { - "remote": "https://github.com/coreos/prometheus-operator", - "subdir": "jsonnet/prometheus-operator" - } - }, - "version": "908ee0372a9ac2c6574d589fdc56a4f3cb5f12d1" - }, - { - "name": "etcd-mixin", - "source": { - "git": { - "remote": "https://github.com/coreos/etcd", - "subdir": "Documentation/etcd-mixin" - } - }, - "version": "3ef2ad8e115449a7004b628a873e2629855ed468" - }, - { - "name": "prometheus", - "source": { - "git": { - "remote": "https://github.com/prometheus/prometheus", - "subdir": "documentation/prometheus-mixin" - } - }, - "version": "b05b5f9a300b0209689c06d70f676291f23774c4" - }, - { - "name": "node-mixin", - "source": { - "git": { - "remote": "https://github.com/prometheus/node_exporter", - "subdir": "docs/node-mixin" - } - }, - "version": "d574b4b41b72966a2ace4d6d81195081dfca8301" - }, - { - "name": "promgrafonnet", - "source": { - "git": { - "remote": "https://github.com/kubernetes-monitoring/kubernetes-mixin", - "subdir": "lib/promgrafonnet" - } - }, - "version": "15ddfa20a6921ffbd43172eb54f6bdc1bcf8d3d3" + "dependencies": [ + { + "name": "etcd-mixin", + "source": { + "git": { + "remote": "https://github.com/coreos/etcd", + "subdir": "Documentation/etcd-mixin" } - ] + }, + "version": "fa972cf29666e821c44195c51df15b6e28ed29c4", + "sum": "bkp18AxkOUYnVC15Gh9EoIi+mMAn0IT3hMzb8mlzpSw=" + }, + { + "name": "grafana", + "source": { + "git": { + "remote": "https://github.com/brancz/kubernetes-grafana", + "subdir": "grafana" + } + }, + "version": "539a90dbf63c812ad0194d8078dd776868a11c81", + "sum": "b8faWX1qqLGyN67sA36oRqYZ5HX+tHBRMPtrWRqIysE=" + }, + { + "name": "grafana-builder", + "source": { + "git": { + "remote": "https://github.com/grafana/jsonnet-libs", + "subdir": "grafana-builder" + } + }, + "version": "1f273dd3c7a619bcd05c3e1c2650204104a273d8", + "sum": "ELsYwK+kGdzX1mee2Yy+/b2mdO4Y503BOCDkFzwmGbE=" + }, + { + "name": "grafonnet", + "source": { + "git": { + "remote": "https://github.com/grafana/grafonnet-lib", + "subdir": "grafonnet" + } + }, + "version": "47db72da03fc4a7a0658a87791e13c3315a3a252", + "sum": "ssLOSIiYWYBvEYJHwRtwMY4kPQoP+MuIUkT0bp2Mb6A=" + }, + { + "name": "ksonnet", + "source": { + "git": { + "remote": "https://github.com/ksonnet/ksonnet-lib", + "subdir": "" + } + }, + "version": "0d2f82676817bbf9e4acf6495b2090205f323b9f", + "sum": "h28BXZ7+vczxYJ2sCt8JuR9+yznRtU/iA6DCpQUrtEg=" + }, + { + "name": "kube-prometheus", + "source": { + "local": { + "directory": "jsonnet/kube-prometheus" + } + }, + "version": "" + }, + { + "name": "kubernetes-mixin", + "source": { + "git": { + "remote": "https://github.com/kubernetes-monitoring/kubernetes-mixin", + "subdir": "" + } + }, + "version": "325f8a46fac9605f1de8bc20ca811cb92d1ef7e5", + "sum": "qfm0EpLrEZ1+fe93LFLa9tyOalK6JehpholxO2d0xXU=" + }, + { + "name": "node-mixin", + "source": { + "git": { + "remote": "https://github.com/prometheus/node_exporter", + "subdir": "docs/node-mixin" + } + }, + "version": "5a7b85876d6108a91f0d8673c0d7eca38687671b", + "sum": "3N77msMjqClzQHbZOxn4GTlV+FZpU+y1gCekvCvxwy0=" + }, + { + "name": "prometheus", + "source": { + "git": { + "remote": "https://github.com/prometheus/prometheus", + "subdir": "documentation/prometheus-mixin" + } + }, + "version": "74726367cf7a7e8d0332238defd2e7f4169030bd", + "sum": "wSDLAXS5Xzla9RFRE2IW5mRToeRFULHb7dSYYBDfEsM=" + }, + { + "name": "prometheus-operator", + "source": { + "git": { + "remote": "https://github.com/coreos/prometheus-operator", + "subdir": "jsonnet/prometheus-operator" + } + }, + "version": "8d44e0990230144177f97cf62ae4f43b1c4e3168", + "sum": "5U7/8MD3pF9O0YDTtUhg4vctkUBRVFxZxWUyhtNiBM8=" + }, + { + "name": "promgrafonnet", + "source": { + "git": { + "remote": "https://github.com/kubernetes-monitoring/kubernetes-mixin", + "subdir": "lib/promgrafonnet" + } + }, + "version": "325f8a46fac9605f1de8bc20ca811cb92d1ef7e5", + "sum": "VhgBM39yv0f4bKv8VfGg4FXkg573evGDRalip9ypKbc=" + } + ] } diff --git a/manifests/grafana-dashboardDefinitions.yaml b/manifests/grafana-dashboardDefinitions.yaml index a9c7baba..9fcb6c5c 100644 --- a/manifests/grafana-dashboardDefinitions.yaml +++ b/manifests/grafana-dashboardDefinitions.yaml @@ -1753,7 +1753,6 @@ items: } ], "title": "Current Status", - "transform": "table", "type": "table" }, { @@ -2529,7 +2528,7 @@ items: "schemaVersion": 18, "style": "dark", "tags": [ - + "kubernetes-mixin" ], "templating": { "list": [ @@ -4083,7 +4082,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "1 - sum(:node_memory_MemFreeCachedBuffers_bytes:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_memory_bytes{cluster=\"$cluster\"})", + "expr": "1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_memory_bytes{cluster=\"$cluster\"})", "format": "time_series", "instant": true, "intervalFactor": 2, @@ -5333,7 +5332,7 @@ items: ], "targets": [ { - "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "table", "instant": true, "intervalFactor": 2, @@ -5342,7 +5341,7 @@ items: "step": 10 }, { - "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "table", "instant": true, "intervalFactor": 2, @@ -5351,7 +5350,7 @@ items: "step": 10 }, { - "expr": "sum(irate(container_network_receive_packets_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "table", "instant": true, "intervalFactor": 2, @@ -5360,7 +5359,7 @@ items: "step": 10 }, { - "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "table", "instant": true, "intervalFactor": 2, @@ -5369,7 +5368,7 @@ items: "step": 10 }, { - "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "table", "instant": true, "intervalFactor": 2, @@ -5378,7 +5377,7 @@ items: "step": 10 }, { - "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "table", "instant": true, "intervalFactor": 2, @@ -5478,7 +5477,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", @@ -5576,7 +5575,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", @@ -5674,7 +5673,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "avg(irate(container_network_receive_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", @@ -5772,7 +5771,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "avg(irate(container_network_transmit_bytes_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", @@ -5870,7 +5869,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_receive_packets_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", @@ -5968,7 +5967,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_receive_packets_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", @@ -6066,7 +6065,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", @@ -6164,7 +6163,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\".+\"}[$interval])) by (namespace)", + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", @@ -7366,7 +7365,7 @@ items: ], "targets": [ { - "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -7375,7 +7374,7 @@ items: "step": 10 }, { - "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -7384,7 +7383,7 @@ items: "step": 10 }, { - "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -7393,7 +7392,7 @@ items: "step": 10 }, { - "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -7402,7 +7401,7 @@ items: "step": 10 }, { - "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -7411,7 +7410,7 @@ items: "step": 10 }, { - "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "table", "instant": true, "intervalFactor": 2, @@ -7511,7 +7510,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -7609,7 +7608,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -7707,7 +7706,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -7805,7 +7804,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -7903,7 +7902,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -8001,7 +8000,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])) by (pod)", + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -8635,7 +8634,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\", container!=\"\"}) by (pod)", + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\", container!=\"\"}) by (pod)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -11709,7 +11708,7 @@ items: ], "targets": [ { - "expr": "(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -11718,7 +11717,7 @@ items: "step": 10 }, { - "expr": "(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -11727,7 +11726,7 @@ items: "step": 10 }, { - "expr": "(sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -11736,7 +11735,7 @@ items: "step": 10 }, { - "expr": "(sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -11745,7 +11744,7 @@ items: "step": 10 }, { - "expr": "(sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -11754,7 +11753,7 @@ items: "step": 10 }, { - "expr": "(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -11854,7 +11853,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -11952,7 +11951,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -12050,7 +12049,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(avg(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -12148,7 +12147,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(avg(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -12246,7 +12245,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -12344,7 +12343,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -12442,7 +12441,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -12540,7 +12539,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod) \ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod) \ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", @@ -12863,7 +12862,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}} - {{workload_type}}", @@ -13128,7 +13127,7 @@ items: ], "targets": [ { - "expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}) by (workload, workload_type)", + "expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)", "format": "table", "instant": true, "intervalFactor": 2, @@ -13137,7 +13136,7 @@ items: "step": 10 }, { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13146,7 +13145,7 @@ items: "step": 10 }, { - "expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13155,7 +13154,7 @@ items: "step": 10 }, { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13164,7 +13163,7 @@ items: "step": 10 }, { - "expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13173,7 +13172,7 @@ items: "step": 10 }, { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13273,7 +13272,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}} - {{workload_type}}", @@ -13538,7 +13537,7 @@ items: ], "targets": [ { - "expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}) by (workload, workload_type)", + "expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)", "format": "table", "instant": true, "intervalFactor": 2, @@ -13547,7 +13546,7 @@ items: "step": 10 }, { - "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13556,7 +13555,7 @@ items: "step": 10 }, { - "expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13565,7 +13564,7 @@ items: "step": 10 }, { - "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13574,7 +13573,7 @@ items: "step": 10 }, { - "expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13583,7 +13582,7 @@ items: "step": 10 }, { - "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13850,7 +13849,7 @@ items: ], "targets": [ { - "expr": "(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13859,7 +13858,7 @@ items: "step": 10 }, { - "expr": "(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13868,7 +13867,7 @@ items: "step": 10 }, { - "expr": "(sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13877,7 +13876,7 @@ items: "step": 10 }, { - "expr": "(sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13886,7 +13885,7 @@ items: "step": 10 }, { - "expr": "(sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13895,7 +13894,7 @@ items: "step": 10 }, { - "expr": "(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -13995,7 +13994,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", @@ -14093,7 +14092,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", @@ -14191,7 +14190,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(avg(irate(container_network_receive_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", @@ -14289,7 +14288,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(avg(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", @@ -14387,7 +14386,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", @@ -14485,7 +14484,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", @@ -14583,7 +14582,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", @@ -14681,7 +14680,7 @@ items: "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod) \ngroup_left(workload,workload_type) mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])\n* on (namespace,pod) \ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", @@ -14859,7 +14858,7 @@ items: "text": "deployment", "value": "deployment" }, - "datasource": "prometheus", + "datasource": "$datasource", "definition": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)", "hide": 0, "includeAll": false, @@ -17971,7 +17970,6 @@ items: } ], "title": "Current Status", - "transform": "table", "type": "table" }, { @@ -18637,7 +18635,7 @@ items: "schemaVersion": 18, "style": "dark", "tags": [ - + "kubernetes-mixin" ], "templating": { "list": [ @@ -19259,7 +19257,6 @@ items: } ], "title": "Current Status", - "transform": "table", "type": "table" }, { @@ -20035,7 +20032,7 @@ items: "schemaVersion": 18, "style": "dark", "tags": [ - + "kubernetes-mixin" ], "templating": { "list": [ @@ -24644,7 +24641,7 @@ items: "schemaVersion": 18, "style": "dark", "tags": [ - + "kubernetes-mixin" ], "templating": { "list": [ @@ -25500,6 +25497,12 @@ items: data: prometheus-remote-write.json: |- { + "__inputs": [ + + ], + "__requires": [ + + ], "annotations": { "list": [ @@ -25509,14 +25512,15 @@ items: "gnetId": null, "graphTooltip": 0, "hideControls": false, + "id": null, "links": [ ], - "refresh": "10s", + "refresh": "", "rows": [ { "collapse": false, - "height": "250px", + "collapsed": false, "panels": [ { "aliasColors": { @@ -25527,12 +25531,17 @@ items: "dashes": false, "datasource": "$datasource", "fill": 1, - "id": 1, + "gridPos": { + + }, + "id": 2, "legend": { + "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, + "rightSide": false, "show": true, "total": false, "values": false @@ -25542,11 +25551,12 @@ items: "links": [ ], - "nullPointMode": "null as zero", + "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", + "repeat": null, "seriesOverrides": [ ], @@ -25556,12 +25566,11 @@ items: "steppedLine": false, "targets": [ { - "expr": "prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} - ignoring(queue) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}", + "expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(queue) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}\n)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}}:{{instance}}-{{queue}}", - "legendLink": null, - "step": 10 + "refId": "A" } ], "thresholds": [ @@ -25587,11 +25596,11 @@ items: }, "yaxes": [ { - "format": "s", + "format": "short", "label": null, "logBase": 1, "max": null, - "min": 0, + "min": null, "show": true }, { @@ -25600,7 +25609,7 @@ items: "logBase": 1, "max": null, "min": null, - "show": false + "show": true } ] }, @@ -25613,12 +25622,17 @@ items: "dashes": false, "datasource": "$datasource", "fill": 1, - "id": 2, + "gridPos": { + + }, + "id": 3, "legend": { + "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, + "rightSide": false, "show": true, "total": false, "values": false @@ -25628,11 +25642,12 @@ items: "links": [ ], - "nullPointMode": "null as zero", + "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", + "repeat": null, "seriesOverrides": [ ], @@ -25642,12 +25657,11 @@ items: "steppedLine": false, "targets": [ { - "expr": "rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) - ignoring (queue) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", + "expr": "(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (queue) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}}:{{instance}}-{{queue}}", - "legendLink": null, - "step": 10 + "refId": "A" } ], "thresholds": [ @@ -25677,7 +25691,7 @@ items: "label": null, "logBase": 1, "max": null, - "min": 0, + "min": null, "show": true }, { @@ -25686,7 +25700,7 @@ items: "logBase": 1, "max": null, "min": null, - "show": false + "show": true } ] } @@ -25696,11 +25710,12 @@ items: "repeatRowId": null, "showTitle": true, "title": "Timestamps", - "titleSize": "h6" + "titleSize": "h6", + "type": "row" }, { "collapse": false, - "height": "250px", + "collapsed": false, "panels": [ { "aliasColors": { @@ -25711,12 +25726,17 @@ items: "dashes": false, "datasource": "$datasource", "fill": 1, - "id": 3, + "gridPos": { + + }, + "id": 4, "legend": { + "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, + "rightSide": false, "show": true, "total": false, "values": false @@ -25726,11 +25746,12 @@ items: "links": [ ], - "nullPointMode": "null as zero", + "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", + "repeat": null, "seriesOverrides": [ ], @@ -25740,12 +25761,11 @@ items: "steppedLine": false, "targets": [ { - "expr": "rate(prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])- ignoring(queue) group_right(instance) rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) - rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", + "expr": "rate(\n prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n ignoring(queue) group_right(instance) rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}}:{{instance}}-{{queue}}", - "legendLink": null, - "step": 10 + "refId": "A" } ], "thresholds": [ @@ -25775,7 +25795,7 @@ items: "label": null, "logBase": 1, "max": null, - "min": 0, + "min": null, "show": true }, { @@ -25784,7 +25804,7 @@ items: "logBase": 1, "max": null, "min": null, - "show": false + "show": true } ] } @@ -25794,11 +25814,12 @@ items: "repeatRowId": null, "showTitle": true, "title": "Samples", - "titleSize": "h6" + "titleSize": "h6", + "type": "row" }, { "collapse": false, - "height": "250px", + "collapsed": false, "panels": [ { "aliasColors": { @@ -25809,12 +25830,17 @@ items: "dashes": false, "datasource": "$datasource", "fill": 1, - "id": 4, + "gridPos": { + + }, + "id": 5, "legend": { + "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, + "rightSide": false, "show": true, "total": false, "values": false @@ -25824,26 +25850,51 @@ items: "links": [ ], - "nullPointMode": "null as zero", + "minSpan": 6, + "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", + "repeat": "queue", "seriesOverrides": [ - + { + "alias": "/max_shards/", + "yaxis": 2 + } ], "spaceLength": 10, - "span": 6, + "span": 12, "stack": false, "steppedLine": false, "targets": [ + { + "expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "max_shards:{{queue}}", + "refId": "A" + }, + { + "expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "min_shards:{{queue}}", + "refId": "B" + }, + { + "expr": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "desired_shards:{{queue}}", + "refId": "C" + }, { "expr": "prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}", "format": "time_series", "intervalFactor": 2, - "legendFormat": "{{cluster}}:{{instance}}-{{queue}}", - "legendLink": null, - "step": 10 + "legendFormat": "current_shards:{{queue}}", + "refId": "D" } ], "thresholds": [ @@ -25851,7 +25902,7 @@ items: ], "timeFrom": null, "timeShift": null, - "title": "Num. Shards", + "title": "Shards: $queue", "tooltip": { "shared": true, "sort": 0, @@ -25873,7 +25924,7 @@ items: "label": null, "logBase": 1, "max": null, - "min": 0, + "min": null, "show": true }, { @@ -25882,10 +25933,23 @@ items: "logBase": 1, "max": null, "min": null, - "show": false + "show": true } ] - }, + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Shards", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ { "aliasColors": { @@ -25895,12 +25959,17 @@ items: "dashes": false, "datasource": "$datasource", "fill": 1, - "id": 5, + "gridPos": { + + }, + "id": 6, "legend": { + "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, + "rightSide": false, "show": true, "total": false, "values": false @@ -25910,11 +25979,12 @@ items: "links": [ ], - "nullPointMode": "null as zero", + "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", + "repeat": "queue", "seriesOverrides": [ ], @@ -25928,8 +25998,7 @@ items: "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}}:{{instance}}-{{queue}}", - "legendLink": null, - "step": 10 + "refId": "A" } ], "thresholds": [ @@ -25937,7 +26006,7 @@ items: ], "timeFrom": null, "timeShift": null, - "title": "Capacity", + "title": "Shard Capacity: $queue", "tooltip": { "shared": true, "sort": 0, @@ -25959,7 +26028,7 @@ items: "label": null, "logBase": 1, "max": null, - "min": 0, + "min": null, "show": true }, { @@ -25968,7 +26037,98 @@ items: "logBase": 1, "max": null, "min": null, - "show": false + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": "queue", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}}-{{queue}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Pending Samples: $queue", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true } ] } @@ -25977,12 +26137,13 @@ items: "repeatIteration": null, "repeatRowId": null, "showTitle": true, - "title": "Shards", - "titleSize": "h6" + "title": "Shard Details", + "titleSize": "h6", + "type": "row" }, { "collapse": false, - "height": "250px", + "collapsed": false, "panels": [ { "aliasColors": { @@ -25993,12 +26154,17 @@ items: "dashes": false, "datasource": "$datasource", "fill": 1, - "id": 6, + "gridPos": { + + }, + "id": 8, "legend": { + "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, + "rightSide": false, "show": true, "total": false, "values": false @@ -26008,11 +26174,207 @@ items: "links": [ ], - "nullPointMode": "null as zero", + "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_tsdb_wal_segment_current{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "TSDB Current Segment", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_wal_watcher_current_segment{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}}-{{queue}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Remote Write Current Segment", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Segments", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, "seriesOverrides": [ ], @@ -26026,8 +26388,7 @@ items: "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}}:{{instance}}-{{queue}}", - "legendLink": null, - "step": 10 + "refId": "A" } ], "thresholds": [ @@ -26057,7 +26418,7 @@ items: "label": null, "logBase": 1, "max": null, - "min": 0, + "min": null, "show": true }, { @@ -26066,7 +26427,7 @@ items: "logBase": 1, "max": null, "min": null, - "show": false + "show": true } ] }, @@ -26079,12 +26440,17 @@ items: "dashes": false, "datasource": "$datasource", "fill": 1, - "id": 7, + "gridPos": { + + }, + "id": 11, "legend": { + "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, + "rightSide": false, "show": true, "total": false, "values": false @@ -26094,11 +26460,12 @@ items: "links": [ ], - "nullPointMode": "null as zero", + "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", + "repeat": null, "seriesOverrides": [ ], @@ -26112,8 +26479,7 @@ items: "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}}:{{instance}}-{{queue}}", - "legendLink": null, - "step": 10 + "refId": "A" } ], "thresholds": [ @@ -26143,7 +26509,7 @@ items: "label": null, "logBase": 1, "max": null, - "min": 0, + "min": null, "show": true }, { @@ -26152,7 +26518,7 @@ items: "logBase": 1, "max": null, "min": null, - "show": false + "show": true } ] }, @@ -26165,12 +26531,17 @@ items: "dashes": false, "datasource": "$datasource", "fill": 1, - "id": 8, + "gridPos": { + + }, + "id": 12, "legend": { + "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, + "rightSide": false, "show": true, "total": false, "values": false @@ -26180,11 +26551,12 @@ items: "links": [ ], - "nullPointMode": "null as zero", + "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", + "repeat": null, "seriesOverrides": [ ], @@ -26198,8 +26570,7 @@ items: "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}}:{{instance}}-{{queue}}", - "legendLink": null, - "step": 10 + "refId": "A" } ], "thresholds": [ @@ -26229,7 +26600,7 @@ items: "label": null, "logBase": 1, "max": null, - "min": 0, + "min": null, "show": true }, { @@ -26238,7 +26609,7 @@ items: "logBase": 1, "max": null, "min": null, - "show": false + "show": true } ] }, @@ -26251,12 +26622,17 @@ items: "dashes": false, "datasource": "$datasource", "fill": 1, - "id": 9, + "gridPos": { + + }, + "id": 13, "legend": { + "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, + "rightSide": false, "show": true, "total": false, "values": false @@ -26266,11 +26642,12 @@ items: "links": [ ], - "nullPointMode": "null as zero", + "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", + "repeat": null, "seriesOverrides": [ ], @@ -26284,8 +26661,7 @@ items: "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}}:{{instance}}-{{queue}}", - "legendLink": null, - "step": 10 + "refId": "A" } ], "thresholds": [ @@ -26315,7 +26691,7 @@ items: "label": null, "logBase": 1, "max": null, - "min": 0, + "min": null, "show": true }, { @@ -26324,7 +26700,7 @@ items: "logBase": 1, "max": null, "min": null, - "show": false + "show": true } ] } @@ -26333,8 +26709,9 @@ items: "repeatIteration": null, "repeatRowId": null, "showTitle": true, - "title": "Misc Rates.", - "titleSize": "h6" + "title": "Misc. Rates", + "titleSize": "h6", + "type": "row" } ], "schemaVersion": 14, @@ -26345,10 +26722,6 @@ items: "templating": { "list": [ { - "current": { - "text": "Prometheus", - "value": "Prometheus" - }, "hide": 0, "label": null, "name": "datasource", @@ -26363,23 +26736,30 @@ items: { "allValue": null, "current": { - "selected": true, - "text": "All", - "value": "$__all" + "text": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "value": { + "selected": true, + "text": "All", + "value": "$__all" + } }, "datasource": "$datasource", "hide": 0, "includeAll": true, - "label": "instance", - "multi": true, + "label": null, + "multi": false, "name": "instance", "options": [ ], "query": "label_values(prometheus_build_info, instance)", - "refresh": 1, + "refresh": 2, "regex": "", - "sort": 2, + "sort": 0, "tagValuesQuery": "", "tags": [ @@ -26391,23 +26771,65 @@ items: { "allValue": null, "current": { - "selected": true, - "text": "All", - "value": "$__all" + "text": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "value": { + "selected": true, + "text": "All", + "value": "$__all" + } }, "datasource": "$datasource", "hide": 0, "includeAll": true, - "label": "cluster", - "multi": true, + "label": null, + "multi": false, "name": "cluster", "options": [ ], "query": "label_values(kube_pod_container_info{image=~\".*prometheus.*\"}, cluster)", - "refresh": 1, + "refresh": 2, "regex": "", - "sort": 2, + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "value": { + "selected": true, + "text": "All", + "value": "$__all" + } + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "queue", + "options": [ + + ], + "query": "label_values(prometheus_remote_storage_shards, queue)", + "refresh": 2, + "regex": "", + "sort": 0, "tagValuesQuery": "", "tags": [ @@ -26419,7 +26841,7 @@ items: ] }, "time": { - "from": "now-1h", + "from": "now-6h", "to": "now" }, "timepicker": { @@ -26447,9 +26869,8 @@ items: "30d" ] }, - "timezone": "utc", + "timezone": "browser", "title": "Prometheus Remote Write", - "uid": "", "version": 0 } kind: ConfigMap @@ -31725,7 +32146,7 @@ items: "schemaVersion": 18, "style": "dark", "tags": [ - + "kubernetes-mixin" ], "templating": { "list": [ diff --git a/manifests/prometheus-operator-serviceMonitor.yaml b/manifests/prometheus-operator-serviceMonitor.yaml index 828c9c6a..be164205 100644 --- a/manifests/prometheus-operator-serviceMonitor.yaml +++ b/manifests/prometheus-operator-serviceMonitor.yaml @@ -4,7 +4,7 @@ metadata: labels: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator - app.kubernetes.io/version: v0.33.0 + app.kubernetes.io/version: v0.34.0 name: prometheus-operator namespace: monitoring spec: @@ -15,4 +15,4 @@ spec: matchLabels: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator - app.kubernetes.io/version: v0.33.0 + app.kubernetes.io/version: v0.34.0 diff --git a/manifests/prometheus-rules.yaml b/manifests/prometheus-rules.yaml index 1bb7a429..93334a9e 100644 --- a/manifests/prometheus-rules.yaml +++ b/manifests/prometheus-rules.yaml @@ -65,6 +65,23 @@ spec: rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[1m]) ) record: instance:node_network_transmit_drop_excluding_lo:rate1m + - name: kube-apiserver.rules + rules: + - expr: | + histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod)) + labels: + quantile: "0.99" + record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod)) + labels: + quantile: "0.9" + record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod)) + labels: + quantile: "0.5" + record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile - name: k8s.rules rules: - expr: | @@ -96,14 +113,14 @@ spec: record: namespace:container_memory_usage_bytes:sum - expr: | sum by (namespace, label_name) ( - sum(kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1)) by (namespace, pod) + sum(kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"Pending|Running"} == 1)) by (namespace, pod) * on (namespace, pod) group_left(label_name) kube_pod_labels{job="kube-state-metrics"} ) record: namespace:kube_pod_container_resource_requests_memory_bytes:sum - expr: | sum by (namespace, label_name) ( - sum(kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1)) by (namespace, pod) + sum(kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"Pending|Running"} == 1)) by (namespace, pod) * on (namespace, pod) group_left(label_name) kube_pod_labels{job="kube-state-metrics"} ) @@ -188,23 +205,6 @@ spec: labels: quantile: "0.5" record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile - - name: kube-apiserver.rules - rules: - - expr: | - histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod)) - labels: - quantile: "0.99" - record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile - - expr: | - histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod)) - labels: - quantile: "0.9" - record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile - - expr: | - histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod)) - labels: - quantile: "0.5" - record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile - name: node.rules rules: - expr: sum(min(kube_pod_info) by (node)) @@ -220,8 +220,16 @@ spec: )) record: node:node_num_cpu:sum - expr: | - sum(node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Cached_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"}) - record: :node_memory_MemFreeCachedBuffers_bytes:sum + sum( + node_memory_MemAvailable_bytes{job="node-exporter"} or + ( + node_memory_Buffers_bytes{job="node-exporter"} + + node_memory_Cached_bytes{job="node-exporter"} + + node_memory_MemFree_bytes{job="node-exporter"} + + node_memory_Slab_bytes{job="node-exporter"} + ) + ) + record: :node_memory_MemAvailable_bytes:sum - name: kube-prometheus-node-recording.rules rules: - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[3m])) BY @@ -399,98 +407,6 @@ spec: for: 1h labels: severity: warning - - name: kubernetes-absent - rules: - - alert: AlertmanagerDown - annotations: - message: Alertmanager has disappeared from Prometheus target discovery. - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-alertmanagerdown - expr: | - absent(up{job="alertmanager-main",namespace="monitoring"} == 1) - for: 15m - labels: - severity: critical - - alert: CoreDNSDown - annotations: - message: CoreDNS has disappeared from Prometheus target discovery. - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-corednsdown - expr: | - absent(up{job="kube-dns"} == 1) - for: 15m - labels: - severity: critical - - alert: KubeAPIDown - annotations: - message: KubeAPI has disappeared from Prometheus target discovery. - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown - expr: | - absent(up{job="apiserver"} == 1) - for: 15m - labels: - severity: critical - - alert: KubeControllerManagerDown - annotations: - message: KubeControllerManager has disappeared from Prometheus target discovery. - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown - expr: | - absent(up{job="kube-controller-manager"} == 1) - for: 15m - labels: - severity: critical - - alert: KubeSchedulerDown - annotations: - message: KubeScheduler has disappeared from Prometheus target discovery. - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown - expr: | - absent(up{job="kube-scheduler"} == 1) - for: 15m - labels: - severity: critical - - alert: KubeStateMetricsDown - annotations: - message: KubeStateMetrics has disappeared from Prometheus target discovery. - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatemetricsdown - expr: | - absent(up{job="kube-state-metrics"} == 1) - for: 15m - labels: - severity: critical - - alert: KubeletDown - annotations: - message: Kubelet has disappeared from Prometheus target discovery. - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown - expr: | - absent(up{job="kubelet"} == 1) - for: 15m - labels: - severity: critical - - alert: NodeExporterDown - annotations: - message: NodeExporter has disappeared from Prometheus target discovery. - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodeexporterdown - expr: | - absent(up{job="node-exporter"} == 1) - for: 15m - labels: - severity: critical - - alert: PrometheusDown - annotations: - message: Prometheus has disappeared from Prometheus target discovery. - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusdown - expr: | - absent(up{job="prometheus-k8s",namespace="monitoring"} == 1) - for: 15m - labels: - severity: critical - - alert: PrometheusOperatorDown - annotations: - message: PrometheusOperator has disappeared from Prometheus target discovery. - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatordown - expr: | - absent(up{job="prometheus-operator",namespace="monitoring"} == 1) - for: 15m - labels: - severity: critical - name: kubernetes-apps rules: - alert: KubePodCrashLooping @@ -795,7 +711,7 @@ spec: ) < 0.15 and predict_linear(kubelet_volume_stats_available_bytes{job="kubelet"}[6h], 4 * 24 * 3600) < 0 - for: 5m + for: 1h labels: severity: critical - alert: KubePersistentVolumeErrors @@ -810,23 +726,6 @@ spec: severity: critical - name: kubernetes-system rules: - - alert: KubeNodeNotReady - annotations: - message: '{{ $labels.node }} has been unready for more than 15 minutes.' - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready - expr: | - kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0 - for: 15m - labels: - severity: warning - - alert: KubeNodeUnreachable - annotations: - message: '{{ $labels.node }} is unreachable and some workloads may be rescheduled.' - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable - expr: | - kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} == 1 - labels: - severity: warning - alert: KubeVersionMismatch annotations: message: There are {{ $value }} different semantic versions of Kubernetes @@ -850,23 +749,15 @@ spec: for: 15m labels: severity: warning - - alert: KubeletTooManyPods - annotations: - message: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage - }} of its Pod capacity. - runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods - expr: | - max(max(kubelet_running_pod_count{job="kubelet"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job="kubelet"}) by(node) / max(kube_node_status_capacity_pods{job="kube-state-metrics"}) by(node) > 0.95 - for: 15m - labels: - severity: warning + - name: kubernetes-system-apiserver + rules: - alert: KubeAPILatencyHigh annotations: message: The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}. runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh expr: | - cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$"} > 1 + cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|PROXY|CONNECT"} > 1 for: 10m labels: severity: warning @@ -876,7 +767,7 @@ spec: for {{ $labels.verb }} {{ $labels.resource }}. runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh expr: | - cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$"} > 4 + cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|PROXY|CONNECT"} > 4 for: 10m labels: severity: critical @@ -886,7 +777,7 @@ spec: }} of requests. runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh expr: | - sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[5m])) + sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m])) / sum(rate(apiserver_request_total{job="apiserver"}[5m])) > 0.03 for: 10m @@ -898,7 +789,7 @@ spec: }} of requests. runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh expr: | - sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[5m])) + sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m])) / sum(rate(apiserver_request_total{job="apiserver"}[5m])) > 0.01 for: 10m @@ -911,7 +802,7 @@ spec: }}. runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh expr: | - sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[5m])) by (resource,subresource,verb) + sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m])) by (resource,subresource,verb) / sum(rate(apiserver_request_total{job="apiserver"}[5m])) by (resource,subresource,verb) > 0.10 for: 10m @@ -924,7 +815,7 @@ spec: }}. runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh expr: | - sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[5m])) by (resource,subresource,verb) + sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m])) by (resource,subresource,verb) / sum(rate(apiserver_request_total{job="apiserver"}[5m])) by (resource,subresource,verb) > 0.05 for: 10m @@ -948,6 +839,75 @@ spec: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400 labels: severity: critical + - alert: KubeAPIDown + annotations: + message: KubeAPI has disappeared from Prometheus target discovery. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown + expr: | + absent(up{job="apiserver"} == 1) + for: 15m + labels: + severity: critical + - name: kubernetes-system-kubelet + rules: + - alert: KubeNodeNotReady + annotations: + message: '{{ $labels.node }} has been unready for more than 15 minutes.' + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready + expr: | + kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0 + for: 15m + labels: + severity: warning + - alert: KubeNodeUnreachable + annotations: + message: '{{ $labels.node }} is unreachable and some workloads may be rescheduled.' + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable + expr: | + kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} == 1 + labels: + severity: warning + - alert: KubeletTooManyPods + annotations: + message: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage + }} of its Pod capacity. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods + expr: | + max(max(kubelet_running_pod_count{job="kubelet"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job="kubelet"}) by(node) / max(kube_node_status_capacity_pods{job="kube-state-metrics"}) by(node) > 0.95 + for: 15m + labels: + severity: warning + - alert: KubeletDown + annotations: + message: Kubelet has disappeared from Prometheus target discovery. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown + expr: | + absent(up{job="kubelet"} == 1) + for: 15m + labels: + severity: critical + - name: kubernetes-system-scheduler + rules: + - alert: KubeSchedulerDown + annotations: + message: KubeScheduler has disappeared from Prometheus target discovery. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown + expr: | + absent(up{job="kube-scheduler"} == 1) + for: 15m + labels: + severity: critical + - name: kubernetes-system-controller-manager + rules: + - alert: KubeControllerManagerDown + annotations: + message: KubeControllerManager has disappeared from Prometheus target discovery. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown + expr: | + absent(up{job="kube-controller-manager"} == 1) + for: 15m + labels: + severity: critical - name: prometheus rules: - alert: PrometheusBadConfig @@ -1115,8 +1075,8 @@ spec: - alert: PrometheusRemoteWriteDesiredShards annotations: description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write - desired shards calculation wants to run {{ printf $value }} shards, which - is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}` + desired shards calculation wants to run {{ $value }} shards, which is more + than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}` $labels.instance | query | first | value }}. summary: Prometheus remote write desired shards calculation wants to run more than configured max shards. @@ -1125,7 +1085,7 @@ spec: # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. ( max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-k8s",namespace="monitoring"}[5m]) - > on(job, instance) group_right + > max_over_time(prometheus_remote_storage_shards_max{job="prometheus-k8s",namespace="monitoring"}[5m]) ) for: 15m diff --git a/manifests/setup/prometheus-operator-0alertmanagerCustomResourceDefinition.yaml b/manifests/setup/prometheus-operator-0alertmanagerCustomResourceDefinition.yaml index 43822f9e..17dfb160 100644 --- a/manifests/setup/prometheus-operator-0alertmanagerCustomResourceDefinition.yaml +++ b/manifests/setup/prometheus-operator-0alertmanagerCustomResourceDefinition.yaml @@ -15,16 +15,16 @@ spec: apiVersion: description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest - internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' type: string kind: description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client - submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string spec: description: 'AlertmanagerSpec is a specification of the desired behavior - of the Alertmanager cluster. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/api-conventions.md#spec-and-status' + of the Alertmanager cluster. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' properties: additionalPeers: description: AdditionalPeers allows injecting a set of additional Alertmanagers @@ -626,6 +626,12 @@ spec: items: type: string type: array + configSecret: + description: ConfigSecret is the name of a Kubernetes Secret in the + same namespace as the Alertmanager object, which contains configuration + for this Alertmanager instance. Defaults to 'alertmanager-' + The secret is mounted into /etc/alertmanager/config. + type: string containers: description: Containers allows injecting additional containers. This is meant to allow adding an authentication proxy to an Alertmanager @@ -1051,7 +1057,8 @@ spec: successThreshold: description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to - 1. Must be 1 for liveness. Minimum value is 1. + 1. Must be 1 for liveness and startup. Minimum value is + 1. format: int32 type: integer tcpSocket: @@ -1203,7 +1210,8 @@ spec: successThreshold: description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to - 1. Must be 1 for liveness. Minimum value is 1. + 1. Must be 1 for liveness and startup. Minimum value is + 1. format: int32 type: integer tcpSocket: @@ -1352,8 +1360,125 @@ spec: and is only honored by servers that enable the WindowsGMSA feature flag. type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint + of the container process. Defaults to the user specified + in image metadata if unspecified. May also be set in + PodSecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext + takes precedence. This field is alpha-level and it is + only honored by servers that enable the WindowsRunAsUserName + feature flag. + type: string type: object type: object + startupProbe: + description: Probe describes a health check to be performed against + a container to determine whether it is alive or ready to receive + traffic. + properties: + exec: + description: ExecAction describes a "run in container" action. + properties: + command: + description: Command is the command line to execute inside + the container, the working directory for the command is + root ('/') in the container's filesystem. The command + is simply exec'd, it is not run inside a shell, so traditional + shell instructions ('|', etc) won't work. To use a shell, + you need to explicitly call out to that shell. Exit + status of 0 is treated as live/healthy and non-zero + is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to + be considered failed after having succeeded. Defaults to + 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGetAction describes an action based on HTTP + Get requests. + properties: + host: + description: Host name to connect to, defaults to the + pod IP. You probably want to set "Host" in httpHeaders + instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP + allows repeated headers. + items: + description: HTTPHeader describes a custom header to + be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: string + - type: integer + scheme: + description: Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started + before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to + be considered successful after having failed. Defaults to + 1. Must be 1 for liveness and startup. Minimum value is + 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocketAction describes an action based on + opening a socket + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: string + - type: integer + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times + out. Defaults to 1 second. Minimum value is 1. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object stdin: description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from @@ -1918,7 +2043,8 @@ spec: successThreshold: description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to - 1. Must be 1 for liveness. Minimum value is 1. + 1. Must be 1 for liveness and startup. Minimum value is + 1. format: int32 type: integer tcpSocket: @@ -2070,7 +2196,8 @@ spec: successThreshold: description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to - 1. Must be 1 for liveness. Minimum value is 1. + 1. Must be 1 for liveness and startup. Minimum value is + 1. format: int32 type: integer tcpSocket: @@ -2219,8 +2346,125 @@ spec: and is only honored by servers that enable the WindowsGMSA feature flag. type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint + of the container process. Defaults to the user specified + in image metadata if unspecified. May also be set in + PodSecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext + takes precedence. This field is alpha-level and it is + only honored by servers that enable the WindowsRunAsUserName + feature flag. + type: string type: object type: object + startupProbe: + description: Probe describes a health check to be performed against + a container to determine whether it is alive or ready to receive + traffic. + properties: + exec: + description: ExecAction describes a "run in container" action. + properties: + command: + description: Command is the command line to execute inside + the container, the working directory for the command is + root ('/') in the container's filesystem. The command + is simply exec'd, it is not run inside a shell, so traditional + shell instructions ('|', etc) won't work. To use a shell, + you need to explicitly call out to that shell. Exit + status of 0 is treated as live/healthy and non-zero + is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to + be considered failed after having succeeded. Defaults to + 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGetAction describes an action based on HTTP + Get requests. + properties: + host: + description: Host name to connect to, defaults to the + pod IP. You probably want to set "Host" in httpHeaders + instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP + allows repeated headers. + items: + description: HTTPHeader describes a custom header to + be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: string + - type: integer + scheme: + description: Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started + before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to + be considered successful after having failed. Defaults to + 1. Must be 1 for liveness and startup. Minimum value is + 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocketAction describes an action based on + opening a socket + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: string + - type: integer + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times + out. Defaults to 1 second. Minimum value is 1. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object stdin: description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from @@ -2397,179 +2641,13 @@ spec: If this field is specified and the generated name exists, the server will NOT return a 409 - instead, it will either return 201 Created or 500 with Reason ServerTimeout indicating a unique name could not be found in the time allotted, and the client should retry (optionally after the time indicated in the Retry-After header). - Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#idempotency + Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#idempotency type: string generation: description: A sequence number representing a specific generation of the desired state. Populated by the system. Read-only. format: int64 type: integer - initializers: - description: Initializers tracks the progress of initialization. - properties: - pending: - description: Pending is a list of initializers that must execute - in order before this object is visible. When the last pending - initializer is removed, and no failing result is set, the - initializers struct will be set to nil and the object is considered - as initialized and visible to all clients. - items: - description: Initializer is information about an initializer - that has not yet completed. - properties: - name: - description: name of the process that is responsible for - initializing this object. - type: string - required: - - name - type: object - type: array - result: - description: Status is a return value for calls that don't return - other objects. - properties: - apiVersion: - description: 'APIVersion defines the versioned schema of - this representation of an object. Servers should convert - recognized schemas to the latest internal value, and may - reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' - type: string - code: - description: Suggested HTTP return code for this status, - 0 if not set. - format: int32 - type: integer - details: - description: StatusDetails is a set of additional properties - that MAY be set by the server to provide additional information - about a response. The Reason field of a Status object - defines what attributes will be set. Clients must ignore - fields that do not match the defined type of each attribute, - and should assume that any attribute may be empty, invalid, - or under defined. - properties: - causes: - description: The Causes array includes more details - associated with the StatusReason failure. Not all - StatusReasons may provide detailed causes. - items: - description: StatusCause provides more information - about an api.Status failure, including cases when - multiple errors are encountered. - properties: - field: - description: |- - The field of the resource that has caused this error, as named by its JSON serialization. May include dot and postfix notation for nested attributes. Arrays are zero-indexed. Fields may appear more than once in an array of causes due to fields having multiple errors. Optional. - - Examples: - "name" - the field "name" on the current resource - "items[0].name" - the field "name" on the first array entry in "items" - type: string - message: - description: A human-readable description of the - cause of the error. This field may be presented - as-is to a reader. - type: string - reason: - description: A machine-readable description of - the cause of the error. If this value is empty - there is no information available. - type: string - type: object - type: array - group: - description: The group attribute of the resource associated - with the status StatusReason. - type: string - kind: - description: 'The kind attribute of the resource associated - with the status StatusReason. On some operations may - differ from the requested resource Kind. More info: - https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' - type: string - name: - description: The name attribute of the resource associated - with the status StatusReason (when there is a single - name which can be described). - type: string - retryAfterSeconds: - description: If specified, the time in seconds before - the operation should be retried. Some errors may indicate - the client must take an alternate action - for those - errors this field may indicate how long to wait before - taking the alternate action. - format: int32 - type: integer - uid: - description: 'UID of the resource. (when there is a - single resource which can be described). More info: - http://kubernetes.io/docs/user-guide/identifiers#uids' - type: string - type: object - kind: - description: 'Kind is a string value representing the REST - resource this object represents. Servers may infer this - from the endpoint the client submits requests to. Cannot - be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' - type: string - message: - description: A human-readable description of the status - of this operation. - type: string - metadata: - description: ListMeta describes metadata that synthetic - resources must have, including lists and various status - objects. A resource may have only one of {ObjectMeta, - ListMeta}. - properties: - continue: - description: continue may be set if the user set a limit - on the number of items returned, and indicates that - the server has more data available. The value is opaque - and may be used to issue another request to the endpoint - that served this list to retrieve the next set of - available objects. Continuing a consistent list may - not be possible if the server configuration has changed - or more than a few minutes have passed. The resourceVersion - field returned when using this continue value will - be identical to the value in the first response, unless - you have received this token from an error message. - type: string - remainingItemCount: - description: |- - remainingItemCount is the number of subsequent items in the list which are not included in this list response. If the list request contained label or field selectors, then the number of remaining items is unknown and the field will be left unset and omitted during serialization. If the list is complete (either because it is not chunking or because this is the last chunk), then there are no more remaining items and this field will be left unset and omitted during serialization. Servers older than v1.15 do not set this field. The intended use of the remainingItemCount is *estimating* the size of a collection. Clients should not rely on the remainingItemCount to be set or to be exact. - - This field is alpha and can be changed or removed without notice. - format: int64 - type: integer - resourceVersion: - description: 'String that identifies the server''s internal - version of this object that can be used by clients - to determine when objects have changed. Value must - be treated as opaque by clients and passed unmodified - back to the server. Populated by the system. Read-only. - More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency' - type: string - selfLink: - description: selfLink is a URL representing this object. - Populated by the system. Read-only. - type: string - type: object - reason: - description: A machine-readable description of why this - operation is in the "Failure" status. If this value is - empty there is no information available. A Reason clarifies - an HTTP status code but does not override it. - type: string - status: - description: 'Status of the operation. One of: "Success" - or "Failure". More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#spec-and-status' - type: string - type: object - required: - - pending - type: object labels: description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match @@ -2577,10 +2655,13 @@ spec: http://kubernetes.io/docs/user-guide/labels' type: object managedFields: - description: |- - ManagedFields maps workflow-id and version to the set of fields that are managed by that workflow. This is mostly for internal housekeeping, and users typically shouldn't need to set or understand this field. A workflow can be the user's name, a controller's name, or the name of a specific apply path like "ci-cd". The set of fields is always in the version that the workflow used when modifying the object. - - This field is alpha and can be changed or removed without notice. + description: ManagedFields maps workflow-id and version to the set + of fields that are managed by that workflow. This is mostly for + internal housekeeping, and users typically shouldn't need to set + or understand this field. A workflow can be the user's name, a + controller's name, or the name of a specific apply path like "ci-cd". + The set of fields is always in the version that the workflow used + when modifying the object. items: description: ManagedFieldsEntry is a workflow-id, a FieldSet and the group version of the resource that the fieldset applies @@ -2593,9 +2674,18 @@ spec: to track the version of a field set because it cannot be automatically converted. type: string - fields: - description: 'Fields stores a set of fields in a data structure - like a Trie. To understand how this is used, see: https://github.com/kubernetes-sigs/structured-merge-diff' + fieldsType: + description: 'FieldsType is the discriminator for the different + fields format and version. There is currently only one possible + value: "FieldsV1"' + type: string + fieldsV1: + description: |- + FieldsV1 stores a set of fields in a data structure like a Trie, in JSON format. + + Each key is either a '.' representing the field itself, and will always map to an empty set, or a string representing a sub-field or item. The string will follow one of these four formats: 'f:', where is the name of a field in a struct, or key in a map 'v:', where is the exact json formatted value of a list item 'i:', where is position of a item in a list 'k:', where is a map of a list item's key fields to their unique values If a key maps to an empty Fields value, the field that key represents is part of the set. + + The exact format is defined in sigs.k8s.io/structured-merge-diff type: object manager: description: Manager is an identifier of the workflow managing @@ -2654,7 +2744,7 @@ spec: controller. type: boolean kind: - description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'Name of the referent. More info: http://kubernetes.io/docs/user-guide/identifiers#names' @@ -2673,11 +2763,13 @@ spec: description: |- An opaque value that represents the internal version of this object that can be used by clients to determine when objects have changed. May be used for optimistic concurrency, change detection, and the watch operation on a resource or set of resources. Clients must treat these values as opaque and passed unmodified back to the server. They may only be valid for a particular resource or set of resources. - Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency + Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency type: string selfLink: - description: SelfLink is a URL representing this object. Populated - by the system. Read-only. + description: |- + SelfLink is a URL representing this object. Populated by the system. Read-only. + + DEPRECATED Kubernetes will stop propagating this field in 1.20 release and the field is planned to be removed in 1.21 release. type: string uid: description: |- @@ -2835,6 +2927,15 @@ spec: credential spec to use. This field is alpha-level and is only honored by servers that enable the WindowsGMSA feature flag. type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint of + the container process. Defaults to the user specified in image + metadata if unspecified. May also be set in PodSecurityContext. + If set in both SecurityContext and PodSecurityContext, the + value specified in SecurityContext takes precedence. This + field is alpha-level and it is only honored by servers that + enable the WindowsRunAsUserName feature flag. + type: string type: object type: object serviceAccountName: @@ -2872,13 +2973,13 @@ spec: description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized - values. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' + values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' type: string kind: description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. - More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string metadata: description: ObjectMeta is metadata that all persisted resources @@ -2934,190 +3035,13 @@ spec: If this field is specified and the generated name exists, the server will NOT return a 409 - instead, it will either return 201 Created or 500 with Reason ServerTimeout indicating a unique name could not be found in the time allotted, and the client should retry (optionally after the time indicated in the Retry-After header). - Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#idempotency + Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#idempotency type: string generation: description: A sequence number representing a specific generation of the desired state. Populated by the system. Read-only. format: int64 type: integer - initializers: - description: Initializers tracks the progress of initialization. - properties: - pending: - description: Pending is a list of initializers that - must execute in order before this object is visible. - When the last pending initializer is removed, and - no failing result is set, the initializers struct - will be set to nil and the object is considered as - initialized and visible to all clients. - items: - description: Initializer is information about an initializer - that has not yet completed. - properties: - name: - description: name of the process that is responsible - for initializing this object. - type: string - required: - - name - type: object - type: array - result: - description: Status is a return value for calls that - don't return other objects. - properties: - apiVersion: - description: 'APIVersion defines the versioned schema - of this representation of an object. Servers should - convert recognized schemas to the latest internal - value, and may reject unrecognized values. More - info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' - type: string - code: - description: Suggested HTTP return code for this - status, 0 if not set. - format: int32 - type: integer - details: - description: StatusDetails is a set of additional - properties that MAY be set by the server to provide - additional information about a response. The Reason - field of a Status object defines what attributes - will be set. Clients must ignore fields that do - not match the defined type of each attribute, - and should assume that any attribute may be empty, - invalid, or under defined. - properties: - causes: - description: The Causes array includes more - details associated with the StatusReason failure. - Not all StatusReasons may provide detailed - causes. - items: - description: StatusCause provides more information - about an api.Status failure, including cases - when multiple errors are encountered. - properties: - field: - description: |- - The field of the resource that has caused this error, as named by its JSON serialization. May include dot and postfix notation for nested attributes. Arrays are zero-indexed. Fields may appear more than once in an array of causes due to fields having multiple errors. Optional. - - Examples: - "name" - the field "name" on the current resource - "items[0].name" - the field "name" on the first array entry in "items" - type: string - message: - description: A human-readable description - of the cause of the error. This field - may be presented as-is to a reader. - type: string - reason: - description: A machine-readable description - of the cause of the error. If this value - is empty there is no information available. - type: string - type: object - type: array - group: - description: The group attribute of the resource - associated with the status StatusReason. - type: string - kind: - description: 'The kind attribute of the resource - associated with the status StatusReason. On - some operations may differ from the requested - resource Kind. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' - type: string - name: - description: The name attribute of the resource - associated with the status StatusReason (when - there is a single name which can be described). - type: string - retryAfterSeconds: - description: If specified, the time in seconds - before the operation should be retried. Some - errors may indicate the client must take an - alternate action - for those errors this field - may indicate how long to wait before taking - the alternate action. - format: int32 - type: integer - uid: - description: 'UID of the resource. (when there - is a single resource which can be described). - More info: http://kubernetes.io/docs/user-guide/identifiers#uids' - type: string - type: object - kind: - description: 'Kind is a string value representing - the REST resource this object represents. Servers - may infer this from the endpoint the client submits - requests to. Cannot be updated. In CamelCase. - More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' - type: string - message: - description: A human-readable description of the - status of this operation. - type: string - metadata: - description: ListMeta describes metadata that synthetic - resources must have, including lists and various - status objects. A resource may have only one of - {ObjectMeta, ListMeta}. - properties: - continue: - description: continue may be set if the user - set a limit on the number of items returned, - and indicates that the server has more data - available. The value is opaque and may be - used to issue another request to the endpoint - that served this list to retrieve the next - set of available objects. Continuing a consistent - list may not be possible if the server configuration - has changed or more than a few minutes have - passed. The resourceVersion field returned - when using this continue value will be identical - to the value in the first response, unless - you have received this token from an error - message. - type: string - remainingItemCount: - description: |- - remainingItemCount is the number of subsequent items in the list which are not included in this list response. If the list request contained label or field selectors, then the number of remaining items is unknown and the field will be left unset and omitted during serialization. If the list is complete (either because it is not chunking or because this is the last chunk), then there are no more remaining items and this field will be left unset and omitted during serialization. Servers older than v1.15 do not set this field. The intended use of the remainingItemCount is *estimating* the size of a collection. Clients should not rely on the remainingItemCount to be set or to be exact. - - This field is alpha and can be changed or removed without notice. - format: int64 - type: integer - resourceVersion: - description: 'String that identifies the server''s - internal version of this object that can be - used by clients to determine when objects - have changed. Value must be treated as opaque - by clients and passed unmodified back to the - server. Populated by the system. Read-only. - More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency' - type: string - selfLink: - description: selfLink is a URL representing - this object. Populated by the system. Read-only. - type: string - type: object - reason: - description: A machine-readable description of why - this operation is in the "Failure" status. If - this value is empty there is no information available. - A Reason clarifies an HTTP status code but does - not override it. - type: string - status: - description: 'Status of the operation. One of: "Success" - or "Failure". More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#spec-and-status' - type: string - type: object - required: - - pending - type: object labels: description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. @@ -3125,10 +3049,14 @@ spec: More info: http://kubernetes.io/docs/user-guide/labels' type: object managedFields: - description: |- - ManagedFields maps workflow-id and version to the set of fields that are managed by that workflow. This is mostly for internal housekeeping, and users typically shouldn't need to set or understand this field. A workflow can be the user's name, a controller's name, or the name of a specific apply path like "ci-cd". The set of fields is always in the version that the workflow used when modifying the object. - - This field is alpha and can be changed or removed without notice. + description: ManagedFields maps workflow-id and version + to the set of fields that are managed by that workflow. + This is mostly for internal housekeeping, and users typically + shouldn't need to set or understand this field. A workflow + can be the user's name, a controller's name, or the name + of a specific apply path like "ci-cd". The set of fields + is always in the version that the workflow used when modifying + the object. items: description: ManagedFieldsEntry is a workflow-id, a FieldSet and the group version of the resource that the fieldset @@ -3141,10 +3069,18 @@ spec: field. It is necessary to track the version of a field set because it cannot be automatically converted. type: string - fields: - description: 'Fields stores a set of fields in a data - structure like a Trie. To understand how this is - used, see: https://github.com/kubernetes-sigs/structured-merge-diff' + fieldsType: + description: 'FieldsType is the discriminator for + the different fields format and version. There is + currently only one possible value: "FieldsV1"' + type: string + fieldsV1: + description: |- + FieldsV1 stores a set of fields in a data structure like a Trie, in JSON format. + + Each key is either a '.' representing the field itself, and will always map to an empty set, or a string representing a sub-field or item. The string will follow one of these four formats: 'f:', where is the name of a field in a struct, or key in a map 'v:', where is the exact json formatted value of a list item 'i:', where is position of a item in a list 'k:', where is a map of a list item's key fields to their unique values If a key maps to an empty Fields value, the field that key represents is part of the set. + + The exact format is defined in sigs.k8s.io/structured-merge-diff type: object manager: description: Manager is an identifier of the workflow @@ -3208,7 +3144,7 @@ spec: managing controller. type: boolean kind: - description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'Name of the referent. More info: http://kubernetes.io/docs/user-guide/identifiers#names' @@ -3227,11 +3163,13 @@ spec: description: |- An opaque value that represents the internal version of this object that can be used by clients to determine when objects have changed. May be used for optimistic concurrency, change detection, and the watch operation on a resource or set of resources. Clients must treat these values as opaque and passed unmodified back to the server. They may only be valid for a particular resource or set of resources. - Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency + Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency type: string selfLink: - description: SelfLink is a URL representing this object. - Populated by the system. Read-only. + description: |- + SelfLink is a URL representing this object. Populated by the system. Read-only. + + DEPRECATED Kubernetes will stop propagating this field in 1.20 release and the field is planned to be removed in 1.21 release. type: string uid: description: |- @@ -3597,7 +3535,7 @@ spec: properties: monitors: description: 'Required: Monitors is a collection of Ceph monitors - More info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it' + More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' items: type: string type: array @@ -3608,11 +3546,11 @@ spec: readOnly: description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More - info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it' + info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' type: boolean secretFile: description: 'Optional: SecretFile is the path to key ring - for User, default is /etc/ceph/user.secret More info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it' + for User, default is /etc/ceph/user.secret More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' type: string secretRef: description: LocalObjectReference contains enough information @@ -3625,7 +3563,7 @@ spec: type: object user: description: 'Optional: User is the rados user name, default - is admin More info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it' + is admin More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' type: string required: - monitors @@ -3640,12 +3578,12 @@ spec: description: 'Filesystem type to mount. Must be a filesystem type supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. - More info: https://releases.k8s.io/HEAD/examples/mysql-cinder-pd/README.md' + More info: https://examples.k8s.io/mysql-cinder-pd/README.md' type: string readOnly: description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More - info: https://releases.k8s.io/HEAD/examples/mysql-cinder-pd/README.md' + info: https://examples.k8s.io/mysql-cinder-pd/README.md' type: boolean secretRef: description: LocalObjectReference contains enough information @@ -3657,8 +3595,8 @@ spec: type: string type: object volumeID: - description: 'volume id used to identify the volume in cinder - More info: https://releases.k8s.io/HEAD/examples/mysql-cinder-pd/README.md' + description: 'volume id used to identify the volume in cinder. + More info: https://examples.k8s.io/mysql-cinder-pd/README.md' type: string required: - volumeID @@ -3981,16 +3919,16 @@ spec: properties: endpoints: description: 'EndpointsName is the endpoint name that details - Glusterfs topology. More info: https://releases.k8s.io/HEAD/examples/volumes/glusterfs/README.md#create-a-pod' + Glusterfs topology. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' type: string path: description: 'Path is the Glusterfs volume path. More info: - https://releases.k8s.io/HEAD/examples/volumes/glusterfs/README.md#create-a-pod' + https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' type: string readOnly: description: 'ReadOnly here will force the Glusterfs volume to be mounted with read-only permissions. Defaults to false. - More info: https://releases.k8s.io/HEAD/examples/volumes/glusterfs/README.md#create-a-pod' + More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' type: boolean required: - endpoints @@ -4437,24 +4375,24 @@ spec: https://kubernetes.io/docs/concepts/storage/volumes#rbd' type: string image: - description: 'The rados image name. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + description: 'The rados image name. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' type: string keyring: description: 'Keyring is the path to key ring for RBDUser. - Default is /etc/ceph/keyring. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + Default is /etc/ceph/keyring. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' type: string monitors: - description: 'A collection of Ceph monitors. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + description: 'A collection of Ceph monitors. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' items: type: string type: array pool: description: 'The rados pool name. Default is rbd. More info: - https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' type: string readOnly: description: 'ReadOnly here will force the ReadOnly setting - in VolumeMounts. Defaults to false. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + in VolumeMounts. Defaults to false. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' type: boolean secretRef: description: LocalObjectReference contains enough information @@ -4467,7 +4405,7 @@ spec: type: object user: description: 'The rados user name. Default is admin. More - info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' type: string required: - monitors @@ -4654,7 +4592,7 @@ spec: status: description: 'AlertmanagerStatus is the most recent observed status of the Alertmanager cluster. Read-only. Not included when requesting from the - apiserver, only from the Prometheus Operator API itself. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/api-conventions.md#spec-and-status' + apiserver, only from the Prometheus Operator API itself. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' properties: availableReplicas: description: Total number of available pods (ready for at least minReadySeconds) diff --git a/manifests/setup/prometheus-operator-0podmonitorCustomResourceDefinition.yaml b/manifests/setup/prometheus-operator-0podmonitorCustomResourceDefinition.yaml index ff67150f..8062b3dd 100644 --- a/manifests/setup/prometheus-operator-0podmonitorCustomResourceDefinition.yaml +++ b/manifests/setup/prometheus-operator-0podmonitorCustomResourceDefinition.yaml @@ -15,12 +15,12 @@ spec: apiVersion: description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest - internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' type: string kind: description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client - submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string spec: description: PodMonitorSpec contains specification parameters for a PodMonitor. @@ -52,6 +52,10 @@ spec: description: HonorLabels chooses the metric's labels on collisions with target labels. type: boolean + honorTimestamps: + description: HonorTimestamps controls whether Prometheus respects + the timestamps present in scraped data. + type: boolean interval: description: Interval at which metrics should be scraped type: string diff --git a/manifests/setup/prometheus-operator-0prometheusCustomResourceDefinition.yaml b/manifests/setup/prometheus-operator-0prometheusCustomResourceDefinition.yaml index bcf97c2c..9c450819 100644 --- a/manifests/setup/prometheus-operator-0prometheusCustomResourceDefinition.yaml +++ b/manifests/setup/prometheus-operator-0prometheusCustomResourceDefinition.yaml @@ -15,12 +15,12 @@ spec: apiVersion: description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest - internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' type: string kind: description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client - submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string spec: description: 'PrometheusSpec is a specification of the desired behavior @@ -693,18 +693,40 @@ spec: tlsConfig: description: TLSConfig specifies TLS configuration parameters. properties: + ca: {} caFile: - description: The CA cert to use for the targets. + description: Path to the CA cert in the Prometheus container + to use for the targets. type: string + cert: {} certFile: - description: The client cert file for the targets. + description: Path to the client cert file in the Prometheus + container for the targets. type: string insecureSkipVerify: description: Disable target certificate validation. type: boolean keyFile: - description: The client key file for the targets. + description: Path to the client key file in the Prometheus + container for the targets. type: string + keySecret: + description: SecretKeySelector selects a key of a Secret. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object serverName: description: Used to verify the hostname for the targets. type: string @@ -774,18 +796,40 @@ spec: tlsConfig: description: TLSConfig specifies TLS configuration parameters. properties: + ca: {} caFile: - description: The CA cert to use for the targets. + description: Path to the CA cert in the Prometheus container + to use for the targets. type: string + cert: {} certFile: - description: The client cert file for the targets. + description: Path to the client cert file in the Prometheus + container for the targets. type: string insecureSkipVerify: description: Disable target certificate validation. type: boolean keyFile: - description: The client key file for the targets. + description: Path to the client key file in the Prometheus container + for the targets. type: string + keySecret: + description: SecretKeySelector selects a key of a Secret. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object serverName: description: Used to verify the hostname for the targets. type: string @@ -793,6 +837,7 @@ spec: required: - host type: object + arbitraryFSAccessThroughSMs: {} baseImage: description: Base image to use for a Prometheus deployment. type: string @@ -1235,7 +1280,8 @@ spec: successThreshold: description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to - 1. Must be 1 for liveness. Minimum value is 1. + 1. Must be 1 for liveness and startup. Minimum value is + 1. format: int32 type: integer tcpSocket: @@ -1387,7 +1433,8 @@ spec: successThreshold: description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to - 1. Must be 1 for liveness. Minimum value is 1. + 1. Must be 1 for liveness and startup. Minimum value is + 1. format: int32 type: integer tcpSocket: @@ -1536,8 +1583,125 @@ spec: and is only honored by servers that enable the WindowsGMSA feature flag. type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint + of the container process. Defaults to the user specified + in image metadata if unspecified. May also be set in + PodSecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext + takes precedence. This field is alpha-level and it is + only honored by servers that enable the WindowsRunAsUserName + feature flag. + type: string type: object type: object + startupProbe: + description: Probe describes a health check to be performed against + a container to determine whether it is alive or ready to receive + traffic. + properties: + exec: + description: ExecAction describes a "run in container" action. + properties: + command: + description: Command is the command line to execute inside + the container, the working directory for the command is + root ('/') in the container's filesystem. The command + is simply exec'd, it is not run inside a shell, so traditional + shell instructions ('|', etc) won't work. To use a shell, + you need to explicitly call out to that shell. Exit + status of 0 is treated as live/healthy and non-zero + is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to + be considered failed after having succeeded. Defaults to + 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGetAction describes an action based on HTTP + Get requests. + properties: + host: + description: Host name to connect to, defaults to the + pod IP. You probably want to set "Host" in httpHeaders + instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP + allows repeated headers. + items: + description: HTTPHeader describes a custom header to + be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: string + - type: integer + scheme: + description: Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started + before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to + be considered successful after having failed. Defaults to + 1. Must be 1 for liveness and startup. Minimum value is + 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocketAction describes an action based on + opening a socket + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: string + - type: integer + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times + out. Defaults to 1 second. Minimum value is 1. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object stdin: description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from @@ -1655,6 +1819,11 @@ spec: authentication authorization via a proxy to ensure only clients authorized to perform these actions can do so. For more information see https://prometheus.io/docs/prometheus/latest/querying/api/#tsdb-admin-apis' type: boolean + enforcedNamespaceLabel: + description: EnforcedNamespaceLabel enforces adding a namespace label + of origin for each alert and metric that is user created. The label + value will always be the namespace of the object that is being created. + type: string evaluationInterval: description: Interval between consecutive evaluations. type: string @@ -1667,6 +1836,12 @@ spec: under. This is necessary to generate correct URLs. This is necessary if Prometheus is not served from root of a DNS name. type: string + ignoreNamespaceSelectors: + description: IgnoreNamespaceSelectors if set to true will ignore NamespaceSelector + settings from the podmonitor and servicemonitor configs, and they + will only discover endpoints within their current namespace. Defaults + to false. + type: boolean image: description: Image if specified has precedence over baseImage, tag and sha combinations. Specifying the version is still necessary to ensure @@ -2117,7 +2292,8 @@ spec: successThreshold: description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to - 1. Must be 1 for liveness. Minimum value is 1. + 1. Must be 1 for liveness and startup. Minimum value is + 1. format: int32 type: integer tcpSocket: @@ -2269,7 +2445,8 @@ spec: successThreshold: description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to - 1. Must be 1 for liveness. Minimum value is 1. + 1. Must be 1 for liveness and startup. Minimum value is + 1. format: int32 type: integer tcpSocket: @@ -2418,8 +2595,125 @@ spec: and is only honored by servers that enable the WindowsGMSA feature flag. type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint + of the container process. Defaults to the user specified + in image metadata if unspecified. May also be set in + PodSecurityContext. If set in both SecurityContext and + PodSecurityContext, the value specified in SecurityContext + takes precedence. This field is alpha-level and it is + only honored by servers that enable the WindowsRunAsUserName + feature flag. + type: string type: object type: object + startupProbe: + description: Probe describes a health check to be performed against + a container to determine whether it is alive or ready to receive + traffic. + properties: + exec: + description: ExecAction describes a "run in container" action. + properties: + command: + description: Command is the command line to execute inside + the container, the working directory for the command is + root ('/') in the container's filesystem. The command + is simply exec'd, it is not run inside a shell, so traditional + shell instructions ('|', etc) won't work. To use a shell, + you need to explicitly call out to that shell. Exit + status of 0 is treated as live/healthy and non-zero + is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to + be considered failed after having succeeded. Defaults to + 3. Minimum value is 1. + format: int32 + type: integer + httpGet: + description: HTTPGetAction describes an action based on HTTP + Get requests. + properties: + host: + description: Host name to connect to, defaults to the + pod IP. You probably want to set "Host" in httpHeaders + instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP + allows repeated headers. + items: + description: HTTPHeader describes a custom header to + be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: string + - type: integer + scheme: + description: Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started + before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to + be considered successful after having failed. Defaults to + 1. Must be 1 for liveness and startup. Minimum value is + 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocketAction describes an action based on + opening a socket + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: string + - type: integer + required: + - port + type: object + timeoutSeconds: + description: 'Number of seconds after which the probe times + out. Defaults to 1 second. Minimum value is 1. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object stdin: description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from @@ -2542,6 +2836,15 @@ spec: nodeSelector: description: Define which Nodes the Pods are scheduled on. type: object + overrideHonorLabels: + description: OverrideHonorLabels if set to true overrides all user configured + honor_labels. If HonorLabels is set in ServiceMonitor or PodMonitor + to true, this overrides honor_labels to false. + type: boolean + overrideHonorTimestamps: + description: OverrideHonorTimestamps allows to globally enforce honoring + timestamps in all scrape configs. + type: boolean paused: description: When a Prometheus deployment is paused, no actions except for deletion will be performed on the underlying objects. @@ -2595,179 +2898,13 @@ spec: If this field is specified and the generated name exists, the server will NOT return a 409 - instead, it will either return 201 Created or 500 with Reason ServerTimeout indicating a unique name could not be found in the time allotted, and the client should retry (optionally after the time indicated in the Retry-After header). - Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#idempotency + Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#idempotency type: string generation: description: A sequence number representing a specific generation of the desired state. Populated by the system. Read-only. format: int64 type: integer - initializers: - description: Initializers tracks the progress of initialization. - properties: - pending: - description: Pending is a list of initializers that must execute - in order before this object is visible. When the last pending - initializer is removed, and no failing result is set, the - initializers struct will be set to nil and the object is considered - as initialized and visible to all clients. - items: - description: Initializer is information about an initializer - that has not yet completed. - properties: - name: - description: name of the process that is responsible for - initializing this object. - type: string - required: - - name - type: object - type: array - result: - description: Status is a return value for calls that don't return - other objects. - properties: - apiVersion: - description: 'APIVersion defines the versioned schema of - this representation of an object. Servers should convert - recognized schemas to the latest internal value, and may - reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' - type: string - code: - description: Suggested HTTP return code for this status, - 0 if not set. - format: int32 - type: integer - details: - description: StatusDetails is a set of additional properties - that MAY be set by the server to provide additional information - about a response. The Reason field of a Status object - defines what attributes will be set. Clients must ignore - fields that do not match the defined type of each attribute, - and should assume that any attribute may be empty, invalid, - or under defined. - properties: - causes: - description: The Causes array includes more details - associated with the StatusReason failure. Not all - StatusReasons may provide detailed causes. - items: - description: StatusCause provides more information - about an api.Status failure, including cases when - multiple errors are encountered. - properties: - field: - description: |- - The field of the resource that has caused this error, as named by its JSON serialization. May include dot and postfix notation for nested attributes. Arrays are zero-indexed. Fields may appear more than once in an array of causes due to fields having multiple errors. Optional. - - Examples: - "name" - the field "name" on the current resource - "items[0].name" - the field "name" on the first array entry in "items" - type: string - message: - description: A human-readable description of the - cause of the error. This field may be presented - as-is to a reader. - type: string - reason: - description: A machine-readable description of - the cause of the error. If this value is empty - there is no information available. - type: string - type: object - type: array - group: - description: The group attribute of the resource associated - with the status StatusReason. - type: string - kind: - description: 'The kind attribute of the resource associated - with the status StatusReason. On some operations may - differ from the requested resource Kind. More info: - https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' - type: string - name: - description: The name attribute of the resource associated - with the status StatusReason (when there is a single - name which can be described). - type: string - retryAfterSeconds: - description: If specified, the time in seconds before - the operation should be retried. Some errors may indicate - the client must take an alternate action - for those - errors this field may indicate how long to wait before - taking the alternate action. - format: int32 - type: integer - uid: - description: 'UID of the resource. (when there is a - single resource which can be described). More info: - http://kubernetes.io/docs/user-guide/identifiers#uids' - type: string - type: object - kind: - description: 'Kind is a string value representing the REST - resource this object represents. Servers may infer this - from the endpoint the client submits requests to. Cannot - be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' - type: string - message: - description: A human-readable description of the status - of this operation. - type: string - metadata: - description: ListMeta describes metadata that synthetic - resources must have, including lists and various status - objects. A resource may have only one of {ObjectMeta, - ListMeta}. - properties: - continue: - description: continue may be set if the user set a limit - on the number of items returned, and indicates that - the server has more data available. The value is opaque - and may be used to issue another request to the endpoint - that served this list to retrieve the next set of - available objects. Continuing a consistent list may - not be possible if the server configuration has changed - or more than a few minutes have passed. The resourceVersion - field returned when using this continue value will - be identical to the value in the first response, unless - you have received this token from an error message. - type: string - remainingItemCount: - description: |- - remainingItemCount is the number of subsequent items in the list which are not included in this list response. If the list request contained label or field selectors, then the number of remaining items is unknown and the field will be left unset and omitted during serialization. If the list is complete (either because it is not chunking or because this is the last chunk), then there are no more remaining items and this field will be left unset and omitted during serialization. Servers older than v1.15 do not set this field. The intended use of the remainingItemCount is *estimating* the size of a collection. Clients should not rely on the remainingItemCount to be set or to be exact. - - This field is alpha and can be changed or removed without notice. - format: int64 - type: integer - resourceVersion: - description: 'String that identifies the server''s internal - version of this object that can be used by clients - to determine when objects have changed. Value must - be treated as opaque by clients and passed unmodified - back to the server. Populated by the system. Read-only. - More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency' - type: string - selfLink: - description: selfLink is a URL representing this object. - Populated by the system. Read-only. - type: string - type: object - reason: - description: A machine-readable description of why this - operation is in the "Failure" status. If this value is - empty there is no information available. A Reason clarifies - an HTTP status code but does not override it. - type: string - status: - description: 'Status of the operation. One of: "Success" - or "Failure". More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#spec-and-status' - type: string - type: object - required: - - pending - type: object labels: description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match @@ -2775,10 +2912,13 @@ spec: http://kubernetes.io/docs/user-guide/labels' type: object managedFields: - description: |- - ManagedFields maps workflow-id and version to the set of fields that are managed by that workflow. This is mostly for internal housekeeping, and users typically shouldn't need to set or understand this field. A workflow can be the user's name, a controller's name, or the name of a specific apply path like "ci-cd". The set of fields is always in the version that the workflow used when modifying the object. - - This field is alpha and can be changed or removed without notice. + description: ManagedFields maps workflow-id and version to the set + of fields that are managed by that workflow. This is mostly for + internal housekeeping, and users typically shouldn't need to set + or understand this field. A workflow can be the user's name, a + controller's name, or the name of a specific apply path like "ci-cd". + The set of fields is always in the version that the workflow used + when modifying the object. items: description: ManagedFieldsEntry is a workflow-id, a FieldSet and the group version of the resource that the fieldset applies @@ -2791,9 +2931,18 @@ spec: to track the version of a field set because it cannot be automatically converted. type: string - fields: - description: 'Fields stores a set of fields in a data structure - like a Trie. To understand how this is used, see: https://github.com/kubernetes-sigs/structured-merge-diff' + fieldsType: + description: 'FieldsType is the discriminator for the different + fields format and version. There is currently only one possible + value: "FieldsV1"' + type: string + fieldsV1: + description: |- + FieldsV1 stores a set of fields in a data structure like a Trie, in JSON format. + + Each key is either a '.' representing the field itself, and will always map to an empty set, or a string representing a sub-field or item. The string will follow one of these four formats: 'f:', where is the name of a field in a struct, or key in a map 'v:', where is the exact json formatted value of a list item 'i:', where is position of a item in a list 'k:', where is a map of a list item's key fields to their unique values If a key maps to an empty Fields value, the field that key represents is part of the set. + + The exact format is defined in sigs.k8s.io/structured-merge-diff type: object manager: description: Manager is an identifier of the workflow managing @@ -2852,7 +3001,7 @@ spec: controller. type: boolean kind: - description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'Name of the referent. More info: http://kubernetes.io/docs/user-guide/identifiers#names' @@ -2871,11 +3020,13 @@ spec: description: |- An opaque value that represents the internal version of this object that can be used by clients to determine when objects have changed. May be used for optimistic concurrency, change detection, and the watch operation on a resource or set of resources. Clients must treat these values as opaque and passed unmodified back to the server. They may only be valid for a particular resource or set of resources. - Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency + Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency type: string selfLink: - description: SelfLink is a URL representing this object. Populated - by the system. Read-only. + description: |- + SelfLink is a URL representing this object. Populated by the system. Read-only. + + DEPRECATED Kubernetes will stop propagating this field in 1.20 release and the field is planned to be removed in 1.21 release. type: string uid: description: |- @@ -3076,18 +3227,40 @@ spec: tlsConfig: description: TLSConfig specifies TLS configuration parameters. properties: + ca: {} caFile: - description: The CA cert to use for the targets. + description: Path to the CA cert in the Prometheus container + to use for the targets. type: string + cert: {} certFile: - description: The client cert file for the targets. + description: Path to the client cert file in the Prometheus + container for the targets. type: string insecureSkipVerify: description: Disable target certificate validation. type: boolean keyFile: - description: The client key file for the targets. + description: Path to the client key file in the Prometheus + container for the targets. type: string + keySecret: + description: SecretKeySelector selects a key of a Secret. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object serverName: description: Used to verify the hostname for the targets. type: string @@ -3202,18 +3375,40 @@ spec: tlsConfig: description: TLSConfig specifies TLS configuration parameters. properties: + ca: {} caFile: - description: The CA cert to use for the targets. + description: Path to the CA cert in the Prometheus container + to use for the targets. type: string + cert: {} certFile: - description: The client cert file for the targets. + description: Path to the client cert file in the Prometheus + container for the targets. type: string insecureSkipVerify: description: Disable target certificate validation. type: boolean keyFile: - description: The client key file for the targets. + description: Path to the client key file in the Prometheus + container for the targets. type: string + keySecret: + description: SecretKeySelector selects a key of a Secret. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object serverName: description: Used to verify the hostname for the targets. type: string @@ -3530,6 +3725,15 @@ spec: credential spec to use. This field is alpha-level and is only honored by servers that enable the WindowsGMSA feature flag. type: string + runAsUserName: + description: The UserName in Windows to run the entrypoint of + the container process. Defaults to the user specified in image + metadata if unspecified. May also be set in PodSecurityContext. + If set in both SecurityContext and PodSecurityContext, the + value specified in SecurityContext takes precedence. This + field is alpha-level and it is only honored by servers that + enable the WindowsRunAsUserName feature flag. + type: string type: object type: object serviceAccountName: @@ -3655,13 +3859,13 @@ spec: description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized - values. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' + values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' type: string kind: description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. - More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string metadata: description: ObjectMeta is metadata that all persisted resources @@ -3717,190 +3921,13 @@ spec: If this field is specified and the generated name exists, the server will NOT return a 409 - instead, it will either return 201 Created or 500 with Reason ServerTimeout indicating a unique name could not be found in the time allotted, and the client should retry (optionally after the time indicated in the Retry-After header). - Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#idempotency + Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#idempotency type: string generation: description: A sequence number representing a specific generation of the desired state. Populated by the system. Read-only. format: int64 type: integer - initializers: - description: Initializers tracks the progress of initialization. - properties: - pending: - description: Pending is a list of initializers that - must execute in order before this object is visible. - When the last pending initializer is removed, and - no failing result is set, the initializers struct - will be set to nil and the object is considered as - initialized and visible to all clients. - items: - description: Initializer is information about an initializer - that has not yet completed. - properties: - name: - description: name of the process that is responsible - for initializing this object. - type: string - required: - - name - type: object - type: array - result: - description: Status is a return value for calls that - don't return other objects. - properties: - apiVersion: - description: 'APIVersion defines the versioned schema - of this representation of an object. Servers should - convert recognized schemas to the latest internal - value, and may reject unrecognized values. More - info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' - type: string - code: - description: Suggested HTTP return code for this - status, 0 if not set. - format: int32 - type: integer - details: - description: StatusDetails is a set of additional - properties that MAY be set by the server to provide - additional information about a response. The Reason - field of a Status object defines what attributes - will be set. Clients must ignore fields that do - not match the defined type of each attribute, - and should assume that any attribute may be empty, - invalid, or under defined. - properties: - causes: - description: The Causes array includes more - details associated with the StatusReason failure. - Not all StatusReasons may provide detailed - causes. - items: - description: StatusCause provides more information - about an api.Status failure, including cases - when multiple errors are encountered. - properties: - field: - description: |- - The field of the resource that has caused this error, as named by its JSON serialization. May include dot and postfix notation for nested attributes. Arrays are zero-indexed. Fields may appear more than once in an array of causes due to fields having multiple errors. Optional. - - Examples: - "name" - the field "name" on the current resource - "items[0].name" - the field "name" on the first array entry in "items" - type: string - message: - description: A human-readable description - of the cause of the error. This field - may be presented as-is to a reader. - type: string - reason: - description: A machine-readable description - of the cause of the error. If this value - is empty there is no information available. - type: string - type: object - type: array - group: - description: The group attribute of the resource - associated with the status StatusReason. - type: string - kind: - description: 'The kind attribute of the resource - associated with the status StatusReason. On - some operations may differ from the requested - resource Kind. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' - type: string - name: - description: The name attribute of the resource - associated with the status StatusReason (when - there is a single name which can be described). - type: string - retryAfterSeconds: - description: If specified, the time in seconds - before the operation should be retried. Some - errors may indicate the client must take an - alternate action - for those errors this field - may indicate how long to wait before taking - the alternate action. - format: int32 - type: integer - uid: - description: 'UID of the resource. (when there - is a single resource which can be described). - More info: http://kubernetes.io/docs/user-guide/identifiers#uids' - type: string - type: object - kind: - description: 'Kind is a string value representing - the REST resource this object represents. Servers - may infer this from the endpoint the client submits - requests to. Cannot be updated. In CamelCase. - More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' - type: string - message: - description: A human-readable description of the - status of this operation. - type: string - metadata: - description: ListMeta describes metadata that synthetic - resources must have, including lists and various - status objects. A resource may have only one of - {ObjectMeta, ListMeta}. - properties: - continue: - description: continue may be set if the user - set a limit on the number of items returned, - and indicates that the server has more data - available. The value is opaque and may be - used to issue another request to the endpoint - that served this list to retrieve the next - set of available objects. Continuing a consistent - list may not be possible if the server configuration - has changed or more than a few minutes have - passed. The resourceVersion field returned - when using this continue value will be identical - to the value in the first response, unless - you have received this token from an error - message. - type: string - remainingItemCount: - description: |- - remainingItemCount is the number of subsequent items in the list which are not included in this list response. If the list request contained label or field selectors, then the number of remaining items is unknown and the field will be left unset and omitted during serialization. If the list is complete (either because it is not chunking or because this is the last chunk), then there are no more remaining items and this field will be left unset and omitted during serialization. Servers older than v1.15 do not set this field. The intended use of the remainingItemCount is *estimating* the size of a collection. Clients should not rely on the remainingItemCount to be set or to be exact. - - This field is alpha and can be changed or removed without notice. - format: int64 - type: integer - resourceVersion: - description: 'String that identifies the server''s - internal version of this object that can be - used by clients to determine when objects - have changed. Value must be treated as opaque - by clients and passed unmodified back to the - server. Populated by the system. Read-only. - More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency' - type: string - selfLink: - description: selfLink is a URL representing - this object. Populated by the system. Read-only. - type: string - type: object - reason: - description: A machine-readable description of why - this operation is in the "Failure" status. If - this value is empty there is no information available. - A Reason clarifies an HTTP status code but does - not override it. - type: string - status: - description: 'Status of the operation. One of: "Success" - or "Failure". More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#spec-and-status' - type: string - type: object - required: - - pending - type: object labels: description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. @@ -3908,10 +3935,14 @@ spec: More info: http://kubernetes.io/docs/user-guide/labels' type: object managedFields: - description: |- - ManagedFields maps workflow-id and version to the set of fields that are managed by that workflow. This is mostly for internal housekeeping, and users typically shouldn't need to set or understand this field. A workflow can be the user's name, a controller's name, or the name of a specific apply path like "ci-cd". The set of fields is always in the version that the workflow used when modifying the object. - - This field is alpha and can be changed or removed without notice. + description: ManagedFields maps workflow-id and version + to the set of fields that are managed by that workflow. + This is mostly for internal housekeeping, and users typically + shouldn't need to set or understand this field. A workflow + can be the user's name, a controller's name, or the name + of a specific apply path like "ci-cd". The set of fields + is always in the version that the workflow used when modifying + the object. items: description: ManagedFieldsEntry is a workflow-id, a FieldSet and the group version of the resource that the fieldset @@ -3924,10 +3955,18 @@ spec: field. It is necessary to track the version of a field set because it cannot be automatically converted. type: string - fields: - description: 'Fields stores a set of fields in a data - structure like a Trie. To understand how this is - used, see: https://github.com/kubernetes-sigs/structured-merge-diff' + fieldsType: + description: 'FieldsType is the discriminator for + the different fields format and version. There is + currently only one possible value: "FieldsV1"' + type: string + fieldsV1: + description: |- + FieldsV1 stores a set of fields in a data structure like a Trie, in JSON format. + + Each key is either a '.' representing the field itself, and will always map to an empty set, or a string representing a sub-field or item. The string will follow one of these four formats: 'f:', where is the name of a field in a struct, or key in a map 'v:', where is the exact json formatted value of a list item 'i:', where is position of a item in a list 'k:', where is a map of a list item's key fields to their unique values If a key maps to an empty Fields value, the field that key represents is part of the set. + + The exact format is defined in sigs.k8s.io/structured-merge-diff type: object manager: description: Manager is an identifier of the workflow @@ -3991,7 +4030,7 @@ spec: managing controller. type: boolean kind: - description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'Name of the referent. More info: http://kubernetes.io/docs/user-guide/identifiers#names' @@ -4010,11 +4049,13 @@ spec: description: |- An opaque value that represents the internal version of this object that can be used by clients to determine when objects have changed. May be used for optimistic concurrency, change detection, and the watch operation on a resource or set of resources. Clients must treat these values as opaque and passed unmodified back to the server. They may only be valid for a particular resource or set of resources. - Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency + Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency type: string selfLink: - description: SelfLink is a URL representing this object. - Populated by the system. Read-only. + description: |- + SelfLink is a URL representing this object. Populated by the system. Read-only. + + DEPRECATED Kubernetes will stop propagating this field in 1.20 release and the field is planned to be removed in 1.21 release. type: string uid: description: |- @@ -4210,6 +4251,10 @@ spec: to ensure the Prometheus Operator knows what version of Thanos is being configured. type: string + listenLocal: + description: ListenLocal makes the Thanos sidecar listen on loopback, + so that it does not bind against the Pod IP. + type: boolean objectStorageConfig: description: SecretKeySelector selects a key of a Secret. properties: @@ -4398,7 +4443,7 @@ spec: properties: monitors: description: 'Required: Monitors is a collection of Ceph monitors - More info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it' + More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' items: type: string type: array @@ -4409,11 +4454,11 @@ spec: readOnly: description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More - info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it' + info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' type: boolean secretFile: description: 'Optional: SecretFile is the path to key ring - for User, default is /etc/ceph/user.secret More info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it' + for User, default is /etc/ceph/user.secret More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' type: string secretRef: description: LocalObjectReference contains enough information @@ -4426,7 +4471,7 @@ spec: type: object user: description: 'Optional: User is the rados user name, default - is admin More info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it' + is admin More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' type: string required: - monitors @@ -4441,12 +4486,12 @@ spec: description: 'Filesystem type to mount. Must be a filesystem type supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. - More info: https://releases.k8s.io/HEAD/examples/mysql-cinder-pd/README.md' + More info: https://examples.k8s.io/mysql-cinder-pd/README.md' type: string readOnly: description: 'Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More - info: https://releases.k8s.io/HEAD/examples/mysql-cinder-pd/README.md' + info: https://examples.k8s.io/mysql-cinder-pd/README.md' type: boolean secretRef: description: LocalObjectReference contains enough information @@ -4458,8 +4503,8 @@ spec: type: string type: object volumeID: - description: 'volume id used to identify the volume in cinder - More info: https://releases.k8s.io/HEAD/examples/mysql-cinder-pd/README.md' + description: 'volume id used to identify the volume in cinder. + More info: https://examples.k8s.io/mysql-cinder-pd/README.md' type: string required: - volumeID @@ -4782,16 +4827,16 @@ spec: properties: endpoints: description: 'EndpointsName is the endpoint name that details - Glusterfs topology. More info: https://releases.k8s.io/HEAD/examples/volumes/glusterfs/README.md#create-a-pod' + Glusterfs topology. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' type: string path: description: 'Path is the Glusterfs volume path. More info: - https://releases.k8s.io/HEAD/examples/volumes/glusterfs/README.md#create-a-pod' + https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' type: string readOnly: description: 'ReadOnly here will force the Glusterfs volume to be mounted with read-only permissions. Defaults to false. - More info: https://releases.k8s.io/HEAD/examples/volumes/glusterfs/README.md#create-a-pod' + More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' type: boolean required: - endpoints @@ -5238,24 +5283,24 @@ spec: https://kubernetes.io/docs/concepts/storage/volumes#rbd' type: string image: - description: 'The rados image name. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + description: 'The rados image name. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' type: string keyring: description: 'Keyring is the path to key ring for RBDUser. - Default is /etc/ceph/keyring. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + Default is /etc/ceph/keyring. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' type: string monitors: - description: 'A collection of Ceph monitors. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + description: 'A collection of Ceph monitors. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' items: type: string type: array pool: description: 'The rados pool name. Default is rbd. More info: - https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' type: string readOnly: description: 'ReadOnly here will force the ReadOnly setting - in VolumeMounts. Defaults to false. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + in VolumeMounts. Defaults to false. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' type: boolean secretRef: description: LocalObjectReference contains enough information @@ -5268,7 +5313,7 @@ spec: type: object user: description: 'The rados user name. Default is admin. More - info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it' + info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' type: string required: - monitors @@ -5459,7 +5504,7 @@ spec: status: description: 'PrometheusStatus is the most recent observed status of the Prometheus cluster. Read-only. Not included when requesting from the apiserver, - only from the Prometheus Operator API itself. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/api-conventions.md#spec-and-status' + only from the Prometheus Operator API itself. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' properties: availableReplicas: description: Total number of available pods (ready for at least minReadySeconds) diff --git a/manifests/setup/prometheus-operator-0prometheusruleCustomResourceDefinition.yaml b/manifests/setup/prometheus-operator-0prometheusruleCustomResourceDefinition.yaml index b4848851..49ddbfb8 100644 --- a/manifests/setup/prometheus-operator-0prometheusruleCustomResourceDefinition.yaml +++ b/manifests/setup/prometheus-operator-0prometheusruleCustomResourceDefinition.yaml @@ -15,12 +15,12 @@ spec: apiVersion: description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest - internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' type: string kind: description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client - submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string metadata: description: ObjectMeta is metadata that all persisted resources must have, @@ -70,186 +70,26 @@ spec: If this field is specified and the generated name exists, the server will NOT return a 409 - instead, it will either return 201 Created or 500 with Reason ServerTimeout indicating a unique name could not be found in the time allotted, and the client should retry (optionally after the time indicated in the Retry-After header). - Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#idempotency + Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#idempotency type: string generation: description: A sequence number representing a specific generation of the desired state. Populated by the system. Read-only. format: int64 type: integer - initializers: - description: Initializers tracks the progress of initialization. - properties: - pending: - description: Pending is a list of initializers that must execute - in order before this object is visible. When the last pending - initializer is removed, and no failing result is set, the initializers - struct will be set to nil and the object is considered as initialized - and visible to all clients. - items: - description: Initializer is information about an initializer that - has not yet completed. - properties: - name: - description: name of the process that is responsible for initializing - this object. - type: string - required: - - name - type: object - type: array - result: - description: Status is a return value for calls that don't return - other objects. - properties: - apiVersion: - description: 'APIVersion defines the versioned schema of this - representation of an object. Servers should convert recognized - schemas to the latest internal value, and may reject unrecognized - values. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' - type: string - code: - description: Suggested HTTP return code for this status, 0 if - not set. - format: int32 - type: integer - details: - description: StatusDetails is a set of additional properties - that MAY be set by the server to provide additional information - about a response. The Reason field of a Status object defines - what attributes will be set. Clients must ignore fields that - do not match the defined type of each attribute, and should - assume that any attribute may be empty, invalid, or under - defined. - properties: - causes: - description: The Causes array includes more details associated - with the StatusReason failure. Not all StatusReasons may - provide detailed causes. - items: - description: StatusCause provides more information about - an api.Status failure, including cases when multiple - errors are encountered. - properties: - field: - description: |- - The field of the resource that has caused this error, as named by its JSON serialization. May include dot and postfix notation for nested attributes. Arrays are zero-indexed. Fields may appear more than once in an array of causes due to fields having multiple errors. Optional. - - Examples: - "name" - the field "name" on the current resource - "items[0].name" - the field "name" on the first array entry in "items" - type: string - message: - description: A human-readable description of the cause - of the error. This field may be presented as-is - to a reader. - type: string - reason: - description: A machine-readable description of the - cause of the error. If this value is empty there - is no information available. - type: string - type: object - type: array - group: - description: The group attribute of the resource associated - with the status StatusReason. - type: string - kind: - description: 'The kind attribute of the resource associated - with the status StatusReason. On some operations may differ - from the requested resource Kind. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' - type: string - name: - description: The name attribute of the resource associated - with the status StatusReason (when there is a single name - which can be described). - type: string - retryAfterSeconds: - description: If specified, the time in seconds before the - operation should be retried. Some errors may indicate - the client must take an alternate action - for those errors - this field may indicate how long to wait before taking - the alternate action. - format: int32 - type: integer - uid: - description: 'UID of the resource. (when there is a single - resource which can be described). More info: http://kubernetes.io/docs/user-guide/identifiers#uids' - type: string - type: object - kind: - description: 'Kind is a string value representing the REST resource - this object represents. Servers may infer this from the endpoint - the client submits requests to. Cannot be updated. In CamelCase. - More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' - type: string - message: - description: A human-readable description of the status of this - operation. - type: string - metadata: - description: ListMeta describes metadata that synthetic resources - must have, including lists and various status objects. A resource - may have only one of {ObjectMeta, ListMeta}. - properties: - continue: - description: continue may be set if the user set a limit - on the number of items returned, and indicates that the - server has more data available. The value is opaque and - may be used to issue another request to the endpoint that - served this list to retrieve the next set of available - objects. Continuing a consistent list may not be possible - if the server configuration has changed or more than a - few minutes have passed. The resourceVersion field returned - when using this continue value will be identical to the - value in the first response, unless you have received - this token from an error message. - type: string - remainingItemCount: - description: |- - remainingItemCount is the number of subsequent items in the list which are not included in this list response. If the list request contained label or field selectors, then the number of remaining items is unknown and the field will be left unset and omitted during serialization. If the list is complete (either because it is not chunking or because this is the last chunk), then there are no more remaining items and this field will be left unset and omitted during serialization. Servers older than v1.15 do not set this field. The intended use of the remainingItemCount is *estimating* the size of a collection. Clients should not rely on the remainingItemCount to be set or to be exact. - - This field is alpha and can be changed or removed without notice. - format: int64 - type: integer - resourceVersion: - description: 'String that identifies the server''s internal - version of this object that can be used by clients to - determine when objects have changed. Value must be treated - as opaque by clients and passed unmodified back to the - server. Populated by the system. Read-only. More info: - https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency' - type: string - selfLink: - description: selfLink is a URL representing this object. - Populated by the system. Read-only. - type: string - type: object - reason: - description: A machine-readable description of why this operation - is in the "Failure" status. If this value is empty there is - no information available. A Reason clarifies an HTTP status - code but does not override it. - type: string - status: - description: 'Status of the operation. One of: "Success" or - "Failure". More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#spec-and-status' - type: string - type: object - required: - - pending - type: object labels: description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. More info: http://kubernetes.io/docs/user-guide/labels' type: object managedFields: - description: |- - ManagedFields maps workflow-id and version to the set of fields that are managed by that workflow. This is mostly for internal housekeeping, and users typically shouldn't need to set or understand this field. A workflow can be the user's name, a controller's name, or the name of a specific apply path like "ci-cd". The set of fields is always in the version that the workflow used when modifying the object. - - This field is alpha and can be changed or removed without notice. + description: ManagedFields maps workflow-id and version to the set of + fields that are managed by that workflow. This is mostly for internal + housekeeping, and users typically shouldn't need to set or understand + this field. A workflow can be the user's name, a controller's name, + or the name of a specific apply path like "ci-cd". The set of fields + is always in the version that the workflow used when modifying the + object. items: description: ManagedFieldsEntry is a workflow-id, a FieldSet and the group version of the resource that the fieldset applies to. @@ -261,9 +101,18 @@ spec: the version of a field set because it cannot be automatically converted. type: string - fields: - description: 'Fields stores a set of fields in a data structure - like a Trie. To understand how this is used, see: https://github.com/kubernetes-sigs/structured-merge-diff' + fieldsType: + description: 'FieldsType is the discriminator for the different + fields format and version. There is currently only one possible + value: "FieldsV1"' + type: string + fieldsV1: + description: |- + FieldsV1 stores a set of fields in a data structure like a Trie, in JSON format. + + Each key is either a '.' representing the field itself, and will always map to an empty set, or a string representing a sub-field or item. The string will follow one of these four formats: 'f:', where is the name of a field in a struct, or key in a map 'v:', where is the exact json formatted value of a list item 'i:', where is position of a item in a list 'k:', where is a map of a list item's key fields to their unique values If a key maps to an empty Fields value, the field that key represents is part of the set. + + The exact format is defined in sigs.k8s.io/structured-merge-diff type: object manager: description: Manager is an identifier of the workflow managing @@ -321,7 +170,7 @@ spec: description: If true, this reference points to the managing controller. type: boolean kind: - description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string name: description: 'Name of the referent. More info: http://kubernetes.io/docs/user-guide/identifiers#names' @@ -340,11 +189,13 @@ spec: description: |- An opaque value that represents the internal version of this object that can be used by clients to determine when objects have changed. May be used for optimistic concurrency, change detection, and the watch operation on a resource or set of resources. Clients must treat these values as opaque and passed unmodified back to the server. They may only be valid for a particular resource or set of resources. - Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency + Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency type: string selfLink: - description: SelfLink is a URL representing this object. Populated by - the system. Read-only. + description: |- + SelfLink is a URL representing this object. Populated by the system. Read-only. + + DEPRECATED Kubernetes will stop propagating this field in 1.20 release and the field is planned to be removed in 1.21 release. type: string uid: description: |- diff --git a/manifests/setup/prometheus-operator-0servicemonitorCustomResourceDefinition.yaml b/manifests/setup/prometheus-operator-0servicemonitorCustomResourceDefinition.yaml index 75ccc673..5283e87d 100644 --- a/manifests/setup/prometheus-operator-0servicemonitorCustomResourceDefinition.yaml +++ b/manifests/setup/prometheus-operator-0servicemonitorCustomResourceDefinition.yaml @@ -15,12 +15,12 @@ spec: apiVersion: description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest - internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#resources' + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' type: string kind: description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client - submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds' + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' type: string spec: description: ServiceMonitorSpec contains specification parameters for a @@ -74,10 +74,31 @@ spec: bearerTokenFile: description: File to read bearer token for scraping targets. type: string + bearerTokenSecret: + description: SecretKeySelector selects a key of a Secret. + properties: + key: + description: The key of the secret to select from. Must be + a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + optional: + description: Specify whether the Secret or its key must be + defined + type: boolean + required: + - key + type: object honorLabels: description: HonorLabels chooses the metric's labels on collisions with target labels. type: boolean + honorTimestamps: + description: HonorTimestamps controls whether Prometheus respects + the timestamps present in scraped data. + type: boolean interval: description: Interval at which metrics should be scraped type: string @@ -199,18 +220,40 @@ spec: tlsConfig: description: TLSConfig specifies TLS configuration parameters. properties: + ca: {} caFile: - description: The CA cert to use for the targets. + description: Path to the CA cert in the Prometheus container + to use for the targets. type: string + cert: {} certFile: - description: The client cert file for the targets. + description: Path to the client cert file in the Prometheus + container for the targets. type: string insecureSkipVerify: description: Disable target certificate validation. type: boolean keyFile: - description: The client key file for the targets. + description: Path to the client key file in the Prometheus + container for the targets. type: string + keySecret: + description: SecretKeySelector selects a key of a Secret. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object serverName: description: Used to verify the hostname for the targets. type: string diff --git a/manifests/setup/prometheus-operator-clusterRole.yaml b/manifests/setup/prometheus-operator-clusterRole.yaml index 28379ea3..bbb37a0f 100644 --- a/manifests/setup/prometheus-operator-clusterRole.yaml +++ b/manifests/setup/prometheus-operator-clusterRole.yaml @@ -4,7 +4,7 @@ metadata: labels: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator - app.kubernetes.io/version: v0.33.0 + app.kubernetes.io/version: v0.34.0 name: prometheus-operator rules: - apiGroups: diff --git a/manifests/setup/prometheus-operator-clusterRoleBinding.yaml b/manifests/setup/prometheus-operator-clusterRoleBinding.yaml index 41113ff6..fc8b1b45 100644 --- a/manifests/setup/prometheus-operator-clusterRoleBinding.yaml +++ b/manifests/setup/prometheus-operator-clusterRoleBinding.yaml @@ -4,7 +4,7 @@ metadata: labels: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator - app.kubernetes.io/version: v0.33.0 + app.kubernetes.io/version: v0.34.0 name: prometheus-operator roleRef: apiGroup: rbac.authorization.k8s.io diff --git a/manifests/setup/prometheus-operator-deployment.yaml b/manifests/setup/prometheus-operator-deployment.yaml index b95de489..533c20cd 100644 --- a/manifests/setup/prometheus-operator-deployment.yaml +++ b/manifests/setup/prometheus-operator-deployment.yaml @@ -4,7 +4,7 @@ metadata: labels: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator - app.kubernetes.io/version: v0.33.0 + app.kubernetes.io/version: v0.34.0 name: prometheus-operator namespace: monitoring spec: @@ -18,15 +18,15 @@ spec: labels: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator - app.kubernetes.io/version: v0.33.0 + app.kubernetes.io/version: v0.34.0 spec: containers: - args: - --kubelet-service=kube-system/kubelet - --logtostderr=true - --config-reloader-image=quay.io/coreos/configmap-reload:v0.0.1 - - --prometheus-config-reloader=quay.io/coreos/prometheus-config-reloader:v0.33.0 - image: quay.io/coreos/prometheus-operator:v0.33.0 + - --prometheus-config-reloader=quay.io/coreos/prometheus-config-reloader:v0.34.0 + image: quay.io/coreos/prometheus-operator:v0.34.0 name: prometheus-operator ports: - containerPort: 8080 diff --git a/manifests/setup/prometheus-operator-service.yaml b/manifests/setup/prometheus-operator-service.yaml index 68f06c99..7bd21836 100644 --- a/manifests/setup/prometheus-operator-service.yaml +++ b/manifests/setup/prometheus-operator-service.yaml @@ -4,7 +4,7 @@ metadata: labels: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator - app.kubernetes.io/version: v0.33.0 + app.kubernetes.io/version: v0.34.0 name: prometheus-operator namespace: monitoring spec: diff --git a/manifests/setup/prometheus-operator-serviceAccount.yaml b/manifests/setup/prometheus-operator-serviceAccount.yaml index d74f8ec2..d100bb15 100644 --- a/manifests/setup/prometheus-operator-serviceAccount.yaml +++ b/manifests/setup/prometheus-operator-serviceAccount.yaml @@ -4,6 +4,6 @@ metadata: labels: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator - app.kubernetes.io/version: v0.33.0 + app.kubernetes.io/version: v0.34.0 name: prometheus-operator namespace: monitoring