294 lines
15 KiB
YAML
294 lines
15 KiB
YAML
{{- /*
|
|
Generated from 'etcd' group from https://raw.githubusercontent.com/etcd-io/etcd/main/contrib/mixin/mixin.libsonnet
|
|
Do not change in-place! In order to change this file first read following link:
|
|
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
|
|
*/ -}}
|
|
{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }}
|
|
{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.kubeEtcd.enabled .Values.defaultRules.rules.etcd }}
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "etcd" | trunc 63 | trimSuffix "-" }}
|
|
namespace: {{ template "kube-prometheus-stack.namespace" . }}
|
|
labels:
|
|
app: {{ template "kube-prometheus-stack.name" . }}
|
|
{{ include "kube-prometheus-stack.labels" . | indent 4 }}
|
|
{{- if .Values.defaultRules.labels }}
|
|
{{ toYaml .Values.defaultRules.labels | indent 4 }}
|
|
{{- end }}
|
|
{{- if .Values.defaultRules.annotations }}
|
|
annotations:
|
|
{{ toYaml .Values.defaultRules.annotations | indent 4 }}
|
|
{{- end }}
|
|
spec:
|
|
groups:
|
|
- name: etcd
|
|
rules:
|
|
{{- if not (.Values.defaultRules.disabled.etcdMembersDown | default false) }}
|
|
- alert: etcdMembersDown
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": members are down ({{`{{`}} $value {{`}}`}}).'
|
|
summary: etcd cluster members are down.
|
|
expr: |-
|
|
max without (endpoint) (
|
|
sum without (instance) (up{job=~".*etcd.*"} == bool 0)
|
|
or
|
|
count without (To) (
|
|
sum without (instance) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[120s])) > 0.01
|
|
)
|
|
)
|
|
> 0
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdInsufficientMembers | default false) }}
|
|
- alert: etcdInsufficientMembers
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": insufficient members ({{`{{`}} $value {{`}}`}}).'
|
|
summary: etcd cluster has insufficient number of members.
|
|
expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"}) without (instance) + 1) / 2)
|
|
for: 3m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdNoLeader | default false) }}
|
|
- alert: etcdNoLeader
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": member {{`{{`}} $labels.instance {{`}}`}} has no leader.'
|
|
summary: etcd cluster has no leader.
|
|
expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdHighNumberOfLeaderChanges | default false) }}
|
|
- alert: etcdHighNumberOfLeaderChanges
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.'
|
|
summary: etcd cluster has high number of leader changes.
|
|
expr: increase((max without (instance) (etcd_server_leader_changes_seen_total{job=~".*etcd.*"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}))[15m:1m]) >= 4
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdHighNumberOfFailedGRPCRequests | default false) }}
|
|
- alert: etcdHighNumberOfFailedGRPCRequests
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.grpc_method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'
|
|
summary: etcd cluster has high number of failed grpc requests.
|
|
expr: |-
|
|
100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code)
|
|
/
|
|
sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code)
|
|
> 1
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdHighNumberOfFailedGRPCRequests | default false) }}
|
|
- alert: etcdHighNumberOfFailedGRPCRequests
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.grpc_method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'
|
|
summary: etcd cluster has high number of failed grpc requests.
|
|
expr: |-
|
|
100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code)
|
|
/
|
|
sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code)
|
|
> 5
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdGRPCRequestsSlow | default false) }}
|
|
- alert: etcdGRPCRequestsSlow
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile of gRPC requests is {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}} for {{`{{`}} $labels.grpc_method {{`}}`}} method.'
|
|
summary: etcd grpc requests are slow
|
|
expr: |-
|
|
histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type))
|
|
> 0.15
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdMemberCommunicationSlow | default false) }}
|
|
- alert: etcdMemberCommunicationSlow
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": member communication with {{`{{`}} $labels.To {{`}}`}} is taking {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'
|
|
summary: etcd cluster member communication is slow.
|
|
expr: |-
|
|
histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m]))
|
|
> 0.15
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdHighNumberOfFailedProposals | default false) }}
|
|
- alert: etcdHighNumberOfFailedProposals
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}} proposal failures within the last 30 minutes on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'
|
|
summary: etcd cluster has high number of proposal failures.
|
|
expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdHighFsyncDurations | default false) }}
|
|
- alert: etcdHighFsyncDurations
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile fsync durations are {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'
|
|
summary: etcd cluster 99th percentile fsync durations are too high.
|
|
expr: |-
|
|
histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
|
|
> 0.5
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdHighFsyncDurations | default false) }}
|
|
- alert: etcdHighFsyncDurations
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile fsync durations are {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'
|
|
summary: etcd cluster 99th percentile fsync durations are too high.
|
|
expr: |-
|
|
histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
|
|
> 1
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdHighCommitDurations | default false) }}
|
|
- alert: etcdHighCommitDurations
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile commit durations {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'
|
|
summary: etcd cluster 99th percentile commit durations are too high.
|
|
expr: |-
|
|
histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
|
|
> 0.25
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdDatabaseQuotaLowSpace | default false) }}
|
|
- alert: etcdDatabaseQuotaLowSpace
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": database size exceeds the defined quota on etcd instance {{`{{`}} $labels.instance {{`}}`}}, please defrag or increase the quota as the writes to etcd will be disabled when it is full.'
|
|
summary: etcd cluster database is running full.
|
|
expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes[5m]) / last_over_time(etcd_server_quota_backend_bytes[5m]))*100 > 95
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdExcessiveDatabaseGrowth | default false) }}
|
|
- alert: etcdExcessiveDatabaseGrowth
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": Predicting running out of disk space in the next four hours, based on write observations within the past four hours on etcd instance {{`{{`}} $labels.instance {{`}}`}}, please check as it might be disruptive.'
|
|
summary: etcd cluster database growing very fast.
|
|
expr: predict_linear(etcd_mvcc_db_total_size_in_bytes[4h], 4*60*60) > etcd_server_quota_backend_bytes
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.etcdDatabaseHighFragmentationRatio | default false) }}
|
|
- alert: etcdDatabaseHighFragmentationRatio
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": database size in use on instance {{`{{`}} $labels.instance {{`}}`}} is {{`{{`}} $value | humanizePercentage {{`}}`}} of the actual allocated disk space, please run defragmentation (e.g. etcdctl defrag) to retrieve the unused fragmented disk space.'
|
|
runbook_url: https://etcd.io/docs/v3.5/op-guide/maintenance/#defragmentation
|
|
summary: etcd database size in use is less than 50% of the actual allocated storage.
|
|
expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes[5m]) / last_over_time(etcd_mvcc_db_total_size_in_bytes[5m])) < 0.5
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- end }} |