Discard Prometheus etcd gRPC failure alert

* Kubernetes watch expiry is not a gRPC code we care about
* Background: This rule is typically removed, but was added back in
This commit is contained in:
Dalton Hubble 2020-11-14 13:17:56 -08:00
parent 1b3a0f6ebc
commit f884de847e

View File

@ -50,28 +50,6 @@ data:
"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)\n /\nsum(rate(grpc_server_handled_total{job=~\".*etcd.*\"}[5m])) without (grpc_type, grpc_code)\n > 1\n",
"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)\n /\nsum(rate(grpc_server_handled_total{job=~\".*etcd.*\"}[5m])) without (grpc_type, grpc_code)\n > 5\n",
"for": "5m",
"labels": {
"severity": "critical"
}
},
{
"alert": "etcdGRPCRequestsSlow",
"annotations": {