prometheus/server/alert/etcd.yml

parameters:
  prometheus:
    server:
        alert:
          InsufficientMembers:
            if: >-
              count(up{job="etcd"} == 0) > (count(up{job="etcd"}) / 2 - 1)
            for: 3m
            labels:
              severity: critical
            annotations:
              description: 'If one more etcd member goes down the cluster will be unavailable'
              summary: 'etcd cluster insufficient members'
          NoLeader:
            if: >-
              etcd_server_has_leader{job="etcd"} == 0
            for: 1m
            labels:
              severity: critical
            annotations:
              description: 'etcd member {{ $labels.instance }} has no leader'
              summary: 'etcd member has no leader'
          HighNumberOfLeaderChanges:
            if: >-
              increase(etcd_server_leader_changes_seen_total{job="etcd"}[1h]) > 3
            labels:
              severity: warning
            annotations:
              description: 'etcd instance {{ $labels.instance }} has seen {{ $value }} leader changes within the last hour'
              summary: 'a high number of leader changes within the etcd cluster are happening'
          HighNumberOfFailedGRPCRequests:
            if: >-
              sum(rate(grpc_server_handled_total{grpc_code!="OK",job="etcd"}[5m])) BY (grpc_service, grpc_method) / sum(rate(grpc_server_handled_total{job="etcd"}[5m])) BY (grpc_service, grpc_method) > 0.01
            for: 10m
            labels:
              severity: warning
            annotations:
              description: '{{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}'
              summary: 'a high number of gRPC requests are failing'
          HighNumberOfFailedGRPCRequests:
            if: >-
              sum(rate(grpc_server_handled_total{grpc_code!="OK",job="etcd"}[5m])) BY (grpc_service, grpc_method) / sum(rate(grpc_server_handled_total{job="etcd"}[5m])) BY (grpc_service, grpc_method) > 0.05
            for: 5m
            labels:
              severity: critical
            annotations:
              description: '{{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}'
              summary: 'a high number of gRPC requests are failing'
          GRPCRequestsSlow:
            if: >-
              histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job="etcd",grpc_type="unary"}[5m])) by (grpc_service, grpc_method, le)) > 0.15
            for: 10m
            labels:
              severity: critical
            annotations:
              description: 'on etcd instance {{ $labels.instance }} gRPC requests to {{ $labels.grpc_method }} are slow'
              summary: 'slow gRPC requests'
          HighNumberOfFailedHTTPRequests:
            if: >-
              sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m])) BY (method) > 0.01
            for: 10m
            labels:
              severity: warning
            annotations:
              description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}'
              summary: 'a high number of HTTP requests are failing'
          HighNumberOfFailedHTTPRequests:
            if: >-
              sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m])) BY (method) > 0.05
            for: 5m
            labels:
              severity: critical
            annotations:
              description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}'
              summary: 'a high number of HTTP requests are failing'
          HTTPRequestsSlow:
            if: >-
              histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m])) > 0.15
            for: 10m
            labels:
              severity: warning
            annotations:
              description: 'on etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow'
              summary: 'slow HTTP requests'
            record: instance:fd_utilization
            if: >-
              process_open_fds / process_max_fds
          FdExhaustionClose:
            if: >-
              predict_linear(instance:fd_utilization[1h], 3600 * 4) > 1
            for: 10m
            labels:
              severity: warning
            annotations:
              description: '{{ $labels.job }} instance {{ $labels.instance }} will exhaust its file descriptors soon'
              summary: 'file descriptors soon exhausted'
          FdExhaustionClose:
            if: >-
              predict_linear(instance:fd_utilization[10m], 3600) > 1
            for: 10m
            labels:
              severity: critical
            annotations:
              description: '{{ $labels.job }} instance {{ $labels.instance }} will exhaust its file descriptors soon'
              summary: 'file descriptors soon exhausted'
          EtcdMemberCommunicationSlow:
            if: >-
              histogram_quantile(0.99, rate(etcd_network_member_round_trip_time_seconds_bucket[5m])) > 0.15
            for: 10m
            labels:
              severity: warning
            annotations:
              description: 'etcd instance {{ $labels.instance }} member communication with {{ $labels.To }} is slow'
              summary: 'etcd member communication is slow'
          HighNumberOfFailedProposals:
            if: >-
              increase(etcd_server_proposals_failed_total{job="etcd"}[1h]) > 5
            labels:
              severity: warning
            annotations:
              description: 'etcd instance {{ $labels.instance }} has seen {{ $value }} proposal failures within the last hour'
              summary: 'a high number of proposals within the etcd cluster are failing'
          HighFsyncDurations:
            if: >-
              histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) > 0.5
            for: 10m
            labels:
              severity: warning
            annotations:
              description: 'etcd instance {{ $labels.instance }} fync durations are high'
              summary: 'high fsync durations'
          HighCommitDurations:
            if: >-
              histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) > 0.25
            for: 10m
            labels:
              severity: warning
            annotations:
              description: 'etcd instance {{ $labels.instance }} commit durations are high'
              summary: 'high commit durations'