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

Merge pull request #2485 from goll/addon-resizer

Browse Source 
Use recommended addon-resizer 1.8.4
This commit is contained in:
Frederic Branczyk
2019-03-18 13:38:34 +01:00
committed by GitHub
parent 6ca02abac4 369bb62349
commit b04d1e61d5
15 changed files with 512 additions and 216 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
README.md
View File

@@ -260,12 +260,12 @@ These are the available fields with their respective default values:
namespace: "default",
versions+:: {
alertmanager: "v0.16.0",
alertmanager: "v0.16.1",
nodeExporter: "v0.17.0",
kubeStateMetrics: "v1.5.0",
kubeRbacProxy: "v0.4.1",
addonResizer: "2.1",
prometheusOperator: "v0.28.0",
addonResizer: "1.8.4",
prometheusOperator: "v0.29.0",
prometheus: "v2.5.0",
},
@@ -274,7 +274,7 @@ These are the available fields with their respective default values:
alertmanager: "quay.io/prometheus/alertmanager",
kubeStateMetrics: "quay.io/coreos/kube-state-metrics",
kubeRbacProxy: "quay.io/coreos/kube-rbac-proxy",
addonResizer: "gcr.io/google-containers/addon-resizer-amd64",
addonResizer: "k8s.gcr.io/addon-resizer",
nodeExporter: "quay.io/prometheus/node-exporter",
prometheusOperator: "quay.io/coreos/prometheus-operator",
},
@@ -298,7 +298,7 @@ These are the available fields with their respective default values:
receiver: 'null'
routes:
- match:
alertname: DeadMansSwitch
alertname: Watchdog
receiver: 'null'
receivers:
- name: 'null'
@@ -402,12 +402,12 @@ To produce the `docker pull/tag/push` commands that will synchronize upstream im
```shell
$ jsonnet -J vendor -S --tla-str repository=internal-registry.com/organization sync-to-internal-registry.jsonnet
docker pull gcr.io/google-containers/addon-resizer-amd64:2.1
docker tag gcr.io/google-containers/addon-resizer-amd64:2.1 internal-registry.com/organization/addon-resizer:2.1
docker push internal-registry.com/organization/addon-resizer:2.1
docker pull quay.io/prometheus/alertmanager:v0.15.3
docker tag quay.io/prometheus/alertmanager:v0.15.3 internal-registry.com/organization/alertmanager:v0.15.3
docker push internal-registry.com/organization/alertmanager:v0.15.3
docker pull k8s.gcr.io/addon-resizer:1.8.4
docker tag k8s.gcr.io/addon-resizer:1.8.4 internal-registry.com/organization/addon-resizer:1.8.4
docker push internal-registry.com/organization/addon-resizer:1.8.4
docker pull quay.io/prometheus/alertmanager:v0.16.1
docker tag quay.io/prometheus/alertmanager:v0.16.1 internal-registry.com/organization/alertmanager:v0.16.1
docker push internal-registry.com/organization/alertmanager:v0.16.1
...
```
@@ -497,7 +497,7 @@ The Alertmanager configuration is located in the `_config.alertmanager.config` c
receiver: 'null'
routes:
- match:
alertname: DeadMansSwitch
alertname: Watchdog
receiver: 'null'
receivers:
- name: 'null'

4
docs/developing-prometheus-rules-and-grafana-dashboards.md
View File

@@ -49,13 +49,13 @@ local kp = (import 'kube-prometheus/kube-prometheus.libsonnet') + {
name: 'example-group',
rules: [
{
alert: 'DeadMansSwitch',
alert: 'Watchdog',
expr: 'vector(1)',
labels: {
severity: 'none',
},
annotations: {
description: 'This is a DeadMansSwitch meant to ensure that the entire alerting pipeline is functional.',
description: 'This is a Watchdog meant to ensure that the entire alerting pipeline is functional.',
},
},
],

2
examples/alertmanager-config.jsonnet
View File

@@ -12,7 +12,7 @@
receiver: 'null'
routes:
- match:
alertname: DeadMansSwitch
alertname: Watchdog
receiver: 'null'
receivers:
- name: 'null'

2
examples/alertmanager-config.yaml
View File

@@ -9,7 +9,7 @@ route:
receiver: 'null'
routes:
- match:
alertname: DeadMansSwitch
alertname: Watchdog
receiver: 'null'
receivers:
- name: 'null'

2
examples/existingrule.json
View File

@@ -1 +1 @@
{"groups":[{"name":"example-group","rules":[{"alert":"DeadMansSwitch","annotations":{"description":"This is a DeadMansSwitch meant to ensure that the entire alerting pipeline is functional."},"expr":"vector(1)","labels":{"severity":"none"}}]}]}
{"groups":[{"name":"example-group","rules":[{"alert":"Watchdog","annotations":{"description":"This is a Watchdog meant to ensure that the entire alerting pipeline is functional."},"expr":"vector(1)","labels":{"severity":"none"}}]}]}

4
examples/existingrule.yaml
View File

@@ -1,9 +1,9 @@
groups:
- name: example-group
rules:
- alert: DeadMansSwitch
- alert: Watchdog
expr: vector(1)
labels:
severity: "none"
annotations:
description: This is a DeadMansSwitch meant to ensure that the entire alerting pipeline is functional.
description: This is a Watchdog meant to ensure that the entire alerting pipeline is functional.

4
examples/prometheus-additional-alert-rule-example.jsonnet
View File

@@ -8,13 +8,13 @@ local kp = (import 'kube-prometheus/kube-prometheus.libsonnet') + {
name: 'example-group',
rules: [
{
alert: 'DeadMansSwitch',
alert: 'Watchdog',
expr: 'vector(1)',
labels: {
severity: 'none',
},
annotations: {
description: 'This is a DeadMansSwitch meant to ensure that the entire alerting pipeline is functional.',
description: 'This is a Watchdog meant to ensure that the entire alerting pipeline is functional.',
},
},
],

4
jsonnet/kube-prometheus/alertmanager/alertmanager.libsonnet
View File

@@ -5,7 +5,7 @@ local k = import 'ksonnet/ksonnet.beta.3/k.libsonnet';
namespace: 'default',
versions+:: {
alertmanager: 'v0.16.0',
alertmanager: 'v0.16.1',
},
imageRepos+:: {
@@ -28,7 +28,7 @@ local k = import 'ksonnet/ksonnet.beta.3/k.libsonnet';
{
receiver: 'null',
match: {
alertname: 'DeadMansSwitch',
alertname: 'Watchdog',
},
},
],

6
jsonnet/kube-prometheus/kube-state-metrics/kube-state-metrics.libsonnet
View File

@@ -18,13 +18,13 @@ local k = import 'ksonnet/ksonnet.beta.3/k.libsonnet';
versions+:: {
kubeStateMetrics: 'v1.5.0',
kubeRbacProxy: 'v0.4.1',
addonResizer: '2.1',
addonResizer: '1.8.4',
},
imageRepos+:: {
kubeStateMetrics: 'quay.io/coreos/kube-state-metrics',
kubeRbacProxy: 'quay.io/coreos/kube-rbac-proxy',
addonResizer: 'gcr.io/google-containers/addon-resizer-amd64',
addonResizer: 'k8s.gcr.io/addon-resizer',
},
},
@@ -175,7 +175,7 @@ local k = import 'ksonnet/ksonnet.beta.3/k.libsonnet';
'--extra-cpu=' + $._config.kubeStateMetrics.cpuPerNode,
'--memory=' + $._config.kubeStateMetrics.baseMemory,
'--extra-memory=' + $._config.kubeStateMetrics.memoryPerNode,
'--acceptance-offset=5',
'--threshold=5',
'--deployment=kube-state-metrics',
]) +
container.withEnv([

8
jsonnetfile.lock.json
View File

@@ -8,7 +8,7 @@
"subdir": "contrib/kube-prometheus/jsonnet/kube-prometheus"
}
},
"version": "df002d09f7b7a50321786c4f19c70d371494410b"
"version": "9faab58c2b1cce4def2cc35045162554b8e4a706"
},
{
"name": "ksonnet",
@@ -28,7 +28,7 @@
"subdir": ""
}
},
"version": "ccb787a44f2ebdecbb346d57490fa7e49981b323"
"version": "b8b1a40066bd40bf7612bbb1cc9208f76530f44a"
},
{
"name": "grafonnet",
@@ -48,7 +48,7 @@
"subdir": "grafana-builder"
}
},
"version": "5d7e5391010c768a6ddd39163c35662f379e20ca"
"version": "5cc4bfab6e2453266e47d01b78cbae0b2643426e"
},
{
"name": "grafana",
@@ -78,7 +78,7 @@
"subdir": "Documentation/etcd-mixin"
}
},
"version": "a7e3bd06b2ef0286e1571836997287a81146c25a"
"version": "e1ca3b4434945e57e8e3a451cdbde74a903cc8e1"
}
]
}

2
manifests/alertmanager-alertmanager.yaml
View File

@@ -15,4 +15,4 @@ spec:
runAsNonRoot: true
runAsUser: 1000
serviceAccountName: alertmanager-main
version: v0.16.0
version: v0.16.1

2
manifests/alertmanager-secret.yaml
View File

@@ -1,6 +1,6 @@
apiVersion: v1
data:
alertmanager.yaml: Imdsb2JhbCI6IAogICJyZXNvbHZlX3RpbWVvdXQiOiAiNW0iCiJyZWNlaXZlcnMiOiAKLSAibmFtZSI6ICJudWxsIgoicm91dGUiOiAKICAiZ3JvdXBfYnkiOiAKICAtICJqb2IiCiAgImdyb3VwX2ludGVydmFsIjogIjVtIgogICJncm91cF93YWl0IjogIjMwcyIKICAicmVjZWl2ZXIiOiAibnVsbCIKICAicmVwZWF0X2ludGVydmFsIjogIjEyaCIKICAicm91dGVzIjogCiAgLSAibWF0Y2giOiAKICAgICAgImFsZXJ0bmFtZSI6ICJEZWFkTWFuc1N3aXRjaCIKICAgICJyZWNlaXZlciI6ICJudWxsIg==
alertmanager.yaml: Imdsb2JhbCI6IAogICJyZXNvbHZlX3RpbWVvdXQiOiAiNW0iCiJyZWNlaXZlcnMiOiAKLSAibmFtZSI6ICJudWxsIgoicm91dGUiOiAKICAiZ3JvdXBfYnkiOiAKICAtICJqb2IiCiAgImdyb3VwX2ludGVydmFsIjogIjVtIgogICJncm91cF93YWl0IjogIjMwcyIKICAicmVjZWl2ZXIiOiAibnVsbCIKICAicmVwZWF0X2ludGVydmFsIjogIjEyaCIKICAicm91dGVzIjogCiAgLSAibWF0Y2giOiAKICAgICAgImFsZXJ0bmFtZSI6ICJXYXRjaGRvZyIKICAgICJyZWNlaXZlciI6ICJudWxsIg==
kind: Secret
metadata:
name: alertmanager-main

618
manifests/grafana-dashboardDefinitions.yaml
View File

File diff suppressed because it is too large Load Diff

4
manifests/kube-state-metrics-deployment.yaml
View File

@@ -71,7 +71,7 @@ spec:
- --extra-cpu=2m
- --memory=150Mi
- --extra-memory=30Mi
- --acceptance-offset=5
- --threshold=5
- --deployment=kube-state-metrics
env:
- name: MY_POD_NAME
@@ -84,7 +84,7 @@ spec:
fieldRef:
apiVersion: v1
fieldPath: metadata.namespace
image: gcr.io/google-containers/addon-resizer-amd64:2.1
image: k8s.gcr.io/addon-resizer:1.8.4
name: addon-resizer
resources:
limits:

42
manifests/prometheus-rules.yaml
View File

@@ -225,21 +225,21 @@ spec:
)
record: node:node_memory_swap_io_bytes:sum_rate
- expr: |
avg(irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+"}[1m]))
avg(irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m]))
record: :node_disk_utilisation:avg_irate
- expr: |
avg by (node) (
irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+"}[1m])
irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m])
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
record: node:node_disk_utilisation:avg_irate
- expr: |
avg(irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+"}[1m]) / 1e3)
avg(irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m]) / 1e3)
record: :node_disk_saturation:avg_irate
- expr: |
avg by (node) (
irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+"}[1m]) / 1e3
irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m]) / 1e3
* on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info:
)
@@ -769,9 +769,9 @@ spec:
message: API server is returning errors for {{ $value }}% of requests.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
expr: |
sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) without(instance, pod)
sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m]))
/
sum(rate(apiserver_request_count{job="apiserver"}[5m])) without(instance, pod) * 100 > 10
sum(rate(apiserver_request_count{job="apiserver"}[5m])) * 100 > 3
for: 10m
labels:
severity: critical
@@ -780,9 +780,33 @@ spec:
message: API server is returning errors for {{ $value }}% of requests.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
expr: |
sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) without(instance, pod)
sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m]))
/
sum(rate(apiserver_request_count{job="apiserver"}[5m])) without(instance, pod) * 100 > 5
sum(rate(apiserver_request_count{job="apiserver"}[5m])) * 100 > 1
for: 10m
labels:
severity: warning
- alert: KubeAPIErrorsHigh
annotations:
message: API server is returning errors for {{ $value }}% of requests for
{{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
expr: |
sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) by (resource,subresource,verb)
/
sum(rate(apiserver_request_count{job="apiserver"}[5m])) by (resource,subresource,verb) * 100 > 10
for: 10m
labels:
severity: critical
- alert: KubeAPIErrorsHigh
annotations:
message: API server is returning errors for {{ $value }}% of requests for
{{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
expr: |
sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) by (resource,subresource,verb)
/
sum(rate(apiserver_request_count{job="apiserver"}[5m])) by (resource,subresource,verb) * 100 > 5
for: 10m
labels:
severity: warning
@@ -951,7 +975,7 @@ spec:
log (WAL).'
summary: Prometheus write-ahead log is corrupted
expr: |
tsdb_wal_corruptions_total{job="prometheus-k8s",namespace="monitoring"} > 0
prometheus_tsdb_wal_corruptions_total{job="prometheus-k8s",namespace="monitoring"} > 0
for: 4h
labels:
severity: warning