monitoring-mixins-website/assets/etcd/alerts.yaml

groups:
- name: etcd
  rules:
  - alert: etcdMembersDown
    annotations:
      message: 'etcd cluster "{{ $labels.job }}": members are down ({{ $value }}).'
    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
  - alert: etcdInsufficientMembers
    annotations:
      message: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value
        }}).'
    expr: |
      sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"}) without (instance) + 1) / 2)      
    for: 3m
    labels:
      severity: critical
  - alert: etcdNoLeader
    annotations:
      message: 'etcd cluster "{{ $labels.job }}": member {{ $labels.instance }} has
        no leader.'
    expr: |
      etcd_server_has_leader{job=~".*etcd.*"} == 0      
    for: 1m
    labels:
      severity: critical
  - alert: etcdHighNumberOfLeaderChanges
    annotations:
      message: '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.'
    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
  - alert: etcdHighNumberOfFailedGRPCRequests
    annotations:
      message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{
        $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
    expr: |
      100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[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
  - alert: etcdHighNumberOfFailedGRPCRequests
    annotations:
      message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{
        $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
    expr: |
      100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[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
  - alert: etcdGRPCRequestsSlow
    annotations:
      message: 'etcd cluster "{{ $labels.job }}": gRPC requests to {{ $labels.grpc_method
        }} are taking {{ $value }}s on etcd instance {{ $labels.instance }}.'
    expr: |
      histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_type="unary"}[5m])) without(grpc_type))
      > 0.15      
    for: 10m
    labels:
      severity: critical
  - alert: etcdMemberCommunicationSlow
    annotations:
      message: 'etcd cluster "{{ $labels.job }}": member communication with {{ $labels.To
        }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.'
    expr: |
      histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m]))
      > 0.15      
    for: 10m
    labels:
      severity: warning
  - alert: etcdHighNumberOfFailedProposals
    annotations:
      message: 'etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures within
        the last 30 minutes on etcd instance {{ $labels.instance }}.'
    expr: |
      rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5      
    for: 15m
    labels:
      severity: warning
  - alert: etcdHighFsyncDurations
    annotations:
      message: 'etcd cluster "{{ $labels.job }}": 99th percentile fync durations are
        {{ $value }}s on etcd instance {{ $labels.instance }}.'
    expr: |
      histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
      > 0.5      
    for: 10m
    labels:
      severity: warning
  - alert: etcdHighCommitDurations
    annotations:
      message: 'etcd cluster "{{ $labels.job }}": 99th percentile commit durations
        {{ $value }}s on etcd instance {{ $labels.instance }}.'
    expr: |
      histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
      > 0.25      
    for: 10m
    labels:
      severity: warning
  - alert: etcdHighNumberOfFailedHTTPRequests
    annotations:
      message: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
        instance {{ $labels.instance }}'
    expr: |
      sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) without (code) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
      without (code) > 0.01      
    for: 10m
    labels:
      severity: warning
  - alert: etcdHighNumberOfFailedHTTPRequests
    annotations:
      message: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd
        instance {{ $labels.instance }}.'
    expr: |
      sum(rate(etcd_http_failed_total{job=~".*etcd.*", code!="404"}[5m])) without (code) / sum(rate(etcd_http_received_total{job=~".*etcd.*"}[5m]))
      without (code) > 0.05      
    for: 10m
    labels:
      severity: critical
  - alert: etcdHTTPRequestsSlow
    annotations:
      message: etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method
        }} are slow.
    expr: |
      histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m]))
      > 0.15      
    for: 10m
    labels:
      severity: warning