Documentation/op-guide: Adapt alerting rules to new gRPC metrics

release-3.3
Frederic Branczyk 2017-11-15 14:33:52 +01:00
parent 6f077bd74c
commit 79446ea677
No known key found for this signature in database
GPG Key ID: 7741A52782A90069
2 changed files with 10 additions and 10 deletions

View File

@ -69,7 +69,7 @@ ANNOTATIONS {
# alert if the 99th percentile of gRPC method calls take more than 150ms
ALERT GRPCRequestsSlow
IF histogram_quantile(0.99, rate(etcd_grpc_unary_requests_duration_seconds_bucket[5m])) > 0.15
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"
@ -84,8 +84,8 @@ ANNOTATIONS {
# alert if more than 1% of requests to an HTTP endpoint have failed within the last 5 minutes
ALERT HighNumberOfFailedHTTPRequests
IF sum by(method) (rate(etcd_http_failed_total{job="etcd"}[5m]))
/ sum by(method) (rate(etcd_http_received_total{job="etcd"}[5m])) > 0.01
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"
@ -97,8 +97,8 @@ ANNOTATIONS {
# alert if more than 5% of requests to an HTTP endpoint have failed within the last 5 minutes
ALERT HighNumberOfFailedHTTPRequests
IF sum by(method) (rate(etcd_http_failed_total{job="etcd"}[5m]))
/ sum by(method) (rate(etcd_http_received_total{job="etcd"}[5m])) > 0.05
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"

View File

@ -26,8 +26,8 @@ groups:
changes within the last hour
summary: a high number of leader changes within the etcd cluster are happening
- alert: HighNumberOfFailedGRPCRequests
expr: sum(rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) BY (grpc_method)
/ sum(rate(etcd_grpc_total{job="etcd"}[5m])) BY (grpc_method) > 0.01
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
for: 10m
labels:
severity: warning
@ -36,8 +36,8 @@ groups:
on etcd instance {{ $labels.instance }}'
summary: a high number of gRPC requests are failing
- alert: HighNumberOfFailedGRPCRequests
expr: sum(rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) BY (grpc_method)
/ sum(rate(etcd_grpc_total{job="etcd"}[5m])) BY (grpc_method) > 0.05
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
for: 5m
labels:
severity: critical
@ -46,7 +46,7 @@ groups:
on etcd instance {{ $labels.instance }}'
summary: a high number of gRPC requests are failing
- alert: GRPCRequestsSlow
expr: histogram_quantile(0.99, rate(etcd_grpc_unary_requests_duration_seconds_bucket[5m]))
expr: 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: