Mirroristas/etcd
2
0
Fork 0
mirror of https://github.com/etcd-io/etcd.git synced 2024-09-27 06:25:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #9202 from olvesh/patch-1

Browse Source 
Documentation/op-guide: integer value of 1 is 100% not 1% for failing reqs
This commit is contained in:
Xiang Li 2018-01-24 09:56:37 -08:00 committed by GitHub
commit 216247570c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 16 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
Documentation/op-guide/etcd3_alert.rules
View File

@ -43,8 +43,8 @@ ANNOTATIONS {
# alert if more than 1% of gRPC method calls have failed within the last 5 minutes # alert if more than 1% of gRPC method calls have failed within the last 5 minutes
ALERT HighNumberOfFailedGRPCRequests ALERT HighNumberOfFailedGRPCRequests
IF sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) IF 100 * (sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m]))
/ sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m])) > 0.01 / sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m]))) > 1
FOR 10m FOR 10m
LABELS { LABELS {
severity = "warning" severity = "warning"
@ -56,8 +56,8 @@ ANNOTATIONS {
# alert if more than 5% of gRPC method calls have failed within the last 5 minutes # alert if more than 5% of gRPC method calls have failed within the last 5 minutes
ALERT HighNumberOfFailedGRPCRequests ALERT HighNumberOfFailedGRPCRequests
IF sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m])) IF 100 * (sum by(grpc_method) (rate(etcd_grpc_requests_failed_total{job="etcd"}[5m]))
/ sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m])) > 0.05 / sum by(grpc_method) (rate(etcd_grpc_total{job="etcd"}[5m]))) > 5
FOR 5m FOR 5m
LABELS { LABELS {
severity = "critical" 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 if more than 1% of requests to an HTTP endpoint have failed within the last 5 minutes
ALERT HighNumberOfFailedHTTPRequests ALERT HighNumberOfFailedHTTPRequests
IF sum(rate(grpc_server_handled_total{grpc_code!="OK",job="etcd"}[5m])) BY (grpc_service, grpc_method) IF 100 * (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 / sum(rate(grpc_server_handled_total{job="etcd"}[5m])) BY (grpc_service, grpc_method)) > 1
FOR 10m FOR 10m
LABELS { LABELS {
severity = "warning" 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 if more than 5% of requests to an HTTP endpoint have failed within the last 5 minutes
ALERT HighNumberOfFailedHTTPRequests ALERT HighNumberOfFailedHTTPRequests
IF sum(rate(grpc_server_handled_total{grpc_code!="OK",job="etcd"}[5m])) BY (grpc_service, grpc_method) IF 100 * (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 / sum(rate(grpc_server_handled_total{job="etcd"}[5m])) BY (grpc_service, grpc_method)) > 5
FOR 5m FOR 5m
LABELS { LABELS {
severity = "critical" severity = "critical"

16
Documentation/op-guide/etcd3_alert.rules.yml
View File

@ -26,8 +26,8 @@ groups:
changes within the last hour changes within the last hour
summary: a high number of leader changes within the etcd cluster are happening summary: a high number of leader changes within the etcd cluster are happening
- alert: HighNumberOfFailedGRPCRequests - alert: HighNumberOfFailedGRPCRequests
expr: sum(rate(grpc_server_handled_total{grpc_code!="OK",job="etcd"}[5m])) BY (grpc_service, grpc_method) expr: 100 * (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 / sum(rate(grpc_server_handled_total{job="etcd"}[5m])) BY (grpc_service, grpc_method)) > 1
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@ -36,8 +36,8 @@ groups:
on etcd instance {{ $labels.instance }}' on etcd instance {{ $labels.instance }}'
summary: a high number of gRPC requests are failing summary: a high number of gRPC requests are failing
- alert: HighNumberOfFailedGRPCRequests - alert: HighNumberOfFailedGRPCRequests
expr: sum(rate(grpc_server_handled_total{grpc_code!="OK",job="etcd"}[5m])) BY (grpc_service, grpc_method) expr: 100 * (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 / sum(rate(grpc_server_handled_total{job="etcd"}[5m])) BY (grpc_service, grpc_method)) > 5
for: 5m for: 5m
labels: labels:
severity: critical severity: critical
@ -56,8 +56,8 @@ groups:
}} are slow }} are slow
summary: slow gRPC requests summary: slow gRPC requests
- alert: HighNumberOfFailedHTTPRequests - alert: HighNumberOfFailedHTTPRequests
expr: sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m])) expr: 100 * (sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m]))
BY (method) > 0.01 BY (method)) > 1
for: 10m for: 10m
labels: labels:
severity: warning severity: warning
@ -66,8 +66,8 @@ groups:
instance {{ $labels.instance }}' instance {{ $labels.instance }}'
summary: a high number of HTTP requests are failing summary: a high number of HTTP requests are failing
- alert: HighNumberOfFailedHTTPRequests - alert: HighNumberOfFailedHTTPRequests
expr: sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m])) expr: 100 * (sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m]))
BY (method) > 0.05 BY (method)) > 5
for: 5m for: 5m
labels: labels:
severity: critical severity: critical