easylinux/kube-prometheus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

jsonnet: Update to latest kubernetes-mixin

Browse Source 
Pick up new alerts for unreachable nodes.
This commit is contained in:
Clayton Coleman
2019-10-25 00:14:24 -04:00
parent 5686d7b439
commit 6e0ca7565f
6 changed files with 11599 additions and 100 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
README.md
View File

@@ -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',
},
},
},
},
},
},
};

48
examples/additional-namespaces-servicemonitor.jsonnet
View File

@@ -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',
},
},
},
},
},
},
};

2
jsonnetfile.lock.json
View File

@@ -27,7 +27,7 @@
"subdir": ""
}
},
"version": "15ddfa20a6921ffbd43172eb54f6bdc1bcf8d3d3"
"version": "a08a6754d527eae13c553bd7565d5f4e9e9f3c0e"
},
{
"name": "grafonnet",

11537
manifests/grafana-dashboardDefinitions.yaml
View File

File diff suppressed because it is too large Load Diff

30
manifests/grafana-deployment.yaml
View File

@@ -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

34
manifests/prometheus-rules.yaml
View File

@@ -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