Skip to content

Commit e467a57

Browse files
Merge pull request #340 from brancz/remove-etcd-grpc-failed-alerts
manifests: Remove etcd gRPC calls failed alerts
2 parents 44b4406 + 400f412 commit e467a57

File tree

3 files changed

+14
-26
lines changed

3 files changed

+14
-26
lines changed

assets/prometheus-k8s/rules.yaml

-24
Original file line numberDiff line numberDiff line change
@@ -1163,30 +1163,6 @@ spec:
11631163
for: 15m
11641164
labels:
11651165
severity: warning
1166-
- alert: etcdHighNumberOfFailedGRPCRequests
1167-
annotations:
1168-
message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for
1169-
{{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
1170-
expr: |
1171-
100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
1172-
/
1173-
sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method)
1174-
> 1
1175-
for: 10m
1176-
labels:
1177-
severity: warning
1178-
- alert: etcdHighNumberOfFailedGRPCRequests
1179-
annotations:
1180-
message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for
1181-
{{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
1182-
expr: |
1183-
100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
1184-
/
1185-
sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method)
1186-
> 5
1187-
for: 5m
1188-
labels:
1189-
severity: critical
11901166
- alert: etcdGRPCRequestsSlow
11911167
annotations:
11921168
message: 'etcd cluster "{{ $labels.job }}": gRPC requests to {{ $labels.grpc_method

jsonnet/main.jsonnet

+12
Original file line numberDiff line numberDiff line change
@@ -28,6 +28,18 @@ local kp = (import 'kube-prometheus/kube-prometheus.libsonnet') +
2828
},
2929
},
3030
},
31+
} + {
32+
prometheusAlerts+:: {
33+
groups:
34+
std.map(
35+
function(ruleGroup)
36+
if ruleGroup.name == 'etcd' then
37+
ruleGroup { rules: std.filter(function(rule) !('alert' in rule && rule.alert == 'etcdHighNumberOfFailedGRPCRequests'), ruleGroup.rules) }
38+
else
39+
ruleGroup,
40+
super.groups,
41+
),
42+
},
3143
} +
3244
(import 'telemeter-client/client.libsonnet') +
3345
{

0 commit comments

Comments
 (0)