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

*: Regenerate

Browse Source
This commit is contained in:
Lili Cosic
2020-10-23 11:44:26 +02:00
parent 0118932183
commit 08550c2db8
9 changed files with 189 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
manifests/prometheus-rules.yaml
View File

@@ -40,10 +40,10 @@ spec:
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-.+|dasd.+"}[1m])
rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[1m])
record: instance_device:node_disk_io_time_seconds:rate1m
- expr: |
rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[1m])
rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[1m])
record: instance_device:node_disk_io_time_weighted_seconds:rate1m
- expr: |
sum without (device) (
@@ -1041,6 +1041,16 @@ spec:
for: 15m
labels:
severity: warning
- alert: PrometheusOperatorSyncFailed
annotations:
description: Controller {{ $labels.controller }} in {{ $labels.namespace }} namespace fails to reconcile {{ $value }} objects.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatorsyncfailed
summary: Last controller reconciliation failed
expr: |
min_over_time(prometheus_operator_syncs{status="failed",job="prometheus-operator",namespace="monitoring"}[5m]) > 0
for: 10m
labels:
severity: warning
- alert: PrometheusOperatorReconcileErrors
annotations:
description: '{{ $value | humanizePercentage }} of reconciling operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.'
@@ -1061,6 +1071,26 @@ spec:
for: 10m
labels:
severity: warning
- alert: PrometheusOperatorNotReady
annotations:
description: Prometheus operator in {{ $labels.namespace }} namespace isn't ready to reconcile {{ $labels.controller }} resources.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatornotready
summary: Prometheus operator not ready
expr: |
min by(namespace, controller) (max_over_time(prometheus_operator_ready{job="prometheus-operator",namespace="monitoring"}[5m]) == 0)
for: 5m
labels:
severity: warning
- alert: PrometheusOperatorRejectedResources
annotations:
description: Prometheus operator in {{ $labels.namespace }} namespace rejected {{ printf "%0.0f" $value }} {{ $labels.controller }}/{{ $labels.resource }} resources.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatorrejectedresources
summary: Resources rejected by Prometheus operator
expr: |
min_over_time(prometheus_operator_managed_resources{state="rejected",job="prometheus-operator",namespace="monitoring"}[5m]) > 0
for: 5m
labels:
severity: warning
- name: kubernetes-apps
rules:
- alert: KubePodCrashLooping
@@ -1251,7 +1281,7 @@ spec:
severity: warning
- alert: KubeJobFailed
annotations:
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed
summary: Job failed to complete.
expr: |