mirror of
https://github.com/etcd-io/etcd.git
synced 2024-09-27 06:25:44 +00:00
contrib/mixin/mixin.libsonnet: Adjust gRPC failed requests
OK is not the only one that is allowed, this before also captured context canceled, NotFound, and other non error requests.
This commit is contained in:
parent
f992d697ed
commit
f00231951d
@ -33,7 +33,7 @@
|
|||||||
)
|
)
|
||||||
)
|
)
|
||||||
> 0
|
> 0
|
||||||
||| % {etcd_instance_labels: $._config.etcd_instance_labels, etcd_selector: $._config.etcd_selector, network_failure_range: $._config.scrape_interval_seconds*4},
|
||| % { etcd_instance_labels: $._config.etcd_instance_labels, etcd_selector: $._config.etcd_selector, network_failure_range: $._config.scrape_interval_seconds * 4 },
|
||||||
'for': '10m',
|
'for': '10m',
|
||||||
labels: {
|
labels: {
|
||||||
severity: 'critical',
|
severity: 'critical',
|
||||||
@ -88,7 +88,7 @@
|
|||||||
{
|
{
|
||||||
alert: 'etcdHighNumberOfFailedGRPCRequests',
|
alert: 'etcdHighNumberOfFailedGRPCRequests',
|
||||||
expr: |||
|
expr: |||
|
||||||
100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) without (grpc_type, grpc_code)
|
100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code)
|
||||||
/
|
/
|
||||||
sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) without (grpc_type, grpc_code)
|
sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) without (grpc_type, grpc_code)
|
||||||
> 1
|
> 1
|
||||||
@ -105,7 +105,7 @@
|
|||||||
{
|
{
|
||||||
alert: 'etcdHighNumberOfFailedGRPCRequests',
|
alert: 'etcdHighNumberOfFailedGRPCRequests',
|
||||||
expr: |||
|
expr: |||
|
||||||
100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) without (grpc_type, grpc_code)
|
100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code)
|
||||||
/
|
/
|
||||||
sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) without (grpc_type, grpc_code)
|
sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) without (grpc_type, grpc_code)
|
||||||
> 5
|
> 5
|
||||||
@ -243,7 +243,7 @@
|
|||||||
uid: std.md5('etcd.json'),
|
uid: std.md5('etcd.json'),
|
||||||
title: 'etcd',
|
title: 'etcd',
|
||||||
description: 'etcd sample Grafana dashboard with Prometheus',
|
description: 'etcd sample Grafana dashboard with Prometheus',
|
||||||
tags: [ 'etcd-mixin' ],
|
tags: ['etcd-mixin'],
|
||||||
style: 'dark',
|
style: 'dark',
|
||||||
timezone: 'browser',
|
timezone: 'browser',
|
||||||
editable: true,
|
editable: true,
|
||||||
@ -369,7 +369,7 @@
|
|||||||
step: 2,
|
step: 2,
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
expr: 'sum(rate(grpc_server_handled_total{job="$cluster",grpc_type="unary",grpc_code!="OK"}[5m]))',
|
expr: 'sum(rate(grpc_server_handled_total{job="$cluster",grpc_type="unary",grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m]))',
|
||||||
format: 'time_series',
|
format: 'time_series',
|
||||||
intervalFactor: 2,
|
intervalFactor: 2,
|
||||||
legendFormat: 'RPC Failed Rate',
|
legendFormat: 'RPC Failed Rate',
|
||||||
|
Loading…
x
Reference in New Issue
Block a user