2017-11-10 16:58:13 +03:00
|
|
|
groups:
|
|
|
|
- name: etcd3_alert.rules
|
|
|
|
rules:
|
|
|
|
- alert: InsufficientMembers
|
|
|
|
expr: 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
|
|
|
|
- alert: NoLeader
|
|
|
|
expr: 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
|
|
|
|
- alert: HighNumberOfLeaderChanges
|
|
|
|
expr: 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
|
|
|
|
- alert: HighNumberOfFailedGRPCRequests
|
2017-11-15 16:33:52 +03:00
|
|
|
expr: 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
|
2017-11-10 16:58:13 +03:00
|
|
|
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
|
|
|
|
- alert: HighNumberOfFailedGRPCRequests
|
2017-11-15 16:33:52 +03:00
|
|
|
expr: 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
|
2017-11-10 16:58:13 +03:00
|
|
|
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
|
|
|
|
- alert: GRPCRequestsSlow
|
2017-11-15 16:33:52 +03:00
|
|
|
expr: histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job="etcd",grpc_type="unary"}[5m])) by (grpc_service, grpc_method, le))
|
2017-11-10 16:58:13 +03:00
|
|
|
> 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
|
|
|
|
- alert: HighNumberOfFailedHTTPRequests
|
|
|
|
expr: 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
|
|
|
|
- alert: HighNumberOfFailedHTTPRequests
|
|
|
|
expr: 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
|
|
|
|
- alert: HTTPRequestsSlow
|
|
|
|
expr: 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
|
|
|
|
expr: process_open_fds / process_max_fds
|
|
|
|
- alert: FdExhaustionClose
|
|
|
|
expr: 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
|
|
|
|
- alert: FdExhaustionClose
|
|
|
|
expr: 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
|
|
|
|
- alert: EtcdMemberCommunicationSlow
|
2017-12-20 13:37:47 +03:00
|
|
|
expr: histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket[5m]))
|
2017-11-10 16:58:13 +03:00
|
|
|
> 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
|
|
|
|
- alert: HighNumberOfFailedProposals
|
|
|
|
expr: 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
|
|
|
|
- alert: HighFsyncDurations
|
|
|
|
expr: 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
|
|
|
|
- alert: HighCommitDurations
|
|
|
|
expr: 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
|