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

Documentation/etcd-mixin: Adhere to monitoring mixins annotation guidelines (#12224)

Browse Source 
* replaced `message` annotation field with `description`
* added simple `summary` field

Signed-off-by: paulfantom <pawel@krupa.net.pl>
This commit is contained in:
Paweł Krupa 2020-09-25 19:56:52 +02:00 committed by GitHub
parent add86bbd1a
commit 74fea11ddc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 40 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
Documentation/etcd-mixin/mixin.libsonnet
View File

@ -34,7 +34,8 @@
severity: 'critical',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": members are down ({{ $value }}).',
description: 'etcd cluster "{{ $labels.job }}": members are down ({{ $value }}).',
summary: 'etcd cluster members are down.',
},
},
{
@ -47,7 +48,8 @@
severity: 'critical',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value }}).',
description: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value }}).',
summary: 'etcd cluster has insufficient number of members.',
},
},
{
@ -60,7 +62,8 @@
severity: 'critical',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": member {{ $labels.instance }} has no leader.',
description: 'etcd cluster "{{ $labels.job }}": member {{ $labels.instance }} has no leader.',
summary: 'etcd cluster has no leader.',
},
},
{
@ -73,7 +76,8 @@
severity: 'warning',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.',
description: 'etcd cluster "{{ $labels.job }}": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.',
summary: 'etcd cluster has high number of leader changes.',
},
},
{
@ -89,7 +93,8 @@
severity: 'warning',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.',
description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.',
summary: 'etcd cluster has high number of failed grpc requests.',
},
},
{
@ -105,7 +110,8 @@
severity: 'critical',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.',
description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.',
summary: 'etcd cluster has high number of failed grpc requests.',
},
},
{
@ -119,7 +125,8 @@
severity: 'critical',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": gRPC requests to {{ $labels.grpc_method }} are taking {{ $value }}s on etcd instance {{ $labels.instance }}.',
description: 'etcd cluster "{{ $labels.job }}": gRPC requests to {{ $labels.grpc_method }} are taking {{ $value }}s on etcd instance {{ $labels.instance }}.',
summary: 'etcd grpc requests are slow',
},
},
{
@ -133,7 +140,8 @@
severity: 'warning',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.',
description: 'etcd cluster "{{ $labels.job }}": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.',
summary: 'etcd cluster member communication is slow.',
},
},
{
@ -146,7 +154,8 @@
severity: 'warning',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures within the last 30 minutes on etcd instance {{ $labels.instance }}.',
description: 'etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures within the last 30 minutes on etcd instance {{ $labels.instance }}.',
summary: 'etcd cluster has high number of proposal failures.',
},
},
{
@ -160,7 +169,8 @@
severity: 'warning',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": 99th percentile fync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.',
description: 'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.',
summary: 'etcd cluster 99th percentile fsync durations are too high.',
},
},
{
@ -174,7 +184,8 @@
severity: 'warning',
},
annotations: {
message: 'etcd cluster "{{ $labels.job }}": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}.',
description: 'etcd cluster "{{ $labels.job }}": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}.',
summary: 'etcd cluster 99th percentile commit durations are too high.',
},
},
{
@ -188,7 +199,8 @@
severity: 'warning',
},
annotations: {
message: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}',
description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}',
summary: 'etcd has high number of failed HTTP requests.',
},
},
{
@ -202,7 +214,8 @@
severity: 'critical',
},
annotations: {
message: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}.',
description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}.',
summary: 'etcd has high number of failed HTTP requests.',
},
},
{
@ -216,7 +229,8 @@
severity: 'warning',
},
annotations: {
message: 'etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow.',
description: 'etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow.',
summary: 'etcd instance HTTP requests are slow.',
},
},
],

18
Documentation/etcd-mixin/test.yaml
View File

@ -26,7 +26,8 @@ tests:
job: etcd
severity: critical
exp_annotations:
message: 'etcd cluster "etcd": members are down (3).'
description: 'etcd cluster "etcd": members are down (3).'
summary: 'etcd cluster members are down.'
- eval_time: 7m
alertname: etcdInsufficientMembers
- eval_time: 11m
@ -36,7 +37,8 @@ tests:
job: etcd
severity: critical
exp_annotations:
message: 'etcd cluster "etcd": insufficient members (1).'
description: 'etcd cluster "etcd": insufficient members (1).'
summary: 'etcd cluster has insufficient number of members.'
- eval_time: 15m
alertname: etcdInsufficientMembers
exp_alerts:
@ -44,7 +46,8 @@ tests:
job: etcd
severity: critical
exp_annotations:
message: 'etcd cluster "etcd": insufficient members (0).'
description: 'etcd cluster "etcd": insufficient members (0).'
summary: 'etcd cluster has insufficient number of members.'
- interval: 1m
input_series:
@ -62,7 +65,8 @@ tests:
job: etcd
severity: critical
exp_annotations:
message: 'etcd cluster "etcd": members are down (3).'
description: 'etcd cluster "etcd": members are down (3).'
summary: 'etcd cluster members are down.'
- interval: 1m
input_series:
@ -80,7 +84,8 @@ tests:
job: etcd
severity: critical
exp_annotations:
message: 'etcd cluster "etcd": members are down (1).'
description: 'etcd cluster "etcd": members are down (1).'
summary: 'etcd cluster members are down.'
- interval: 1m
input_series:
- series: 'etcd_server_leader_changes_seen_total{job="etcd",instance="10.10.10.0"}'
@ -97,7 +102,8 @@ tests:
job: etcd
severity: warning
exp_annotations:
message: 'etcd cluster "etcd": 4 leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.'
description: 'etcd cluster "etcd": 4 leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.'
summary: 'etcd cluster has high number of leader changes.'
- interval: 1m
input_series:
- series: 'etcd_server_leader_changes_seen_total{job="etcd",instance="10.10.10.0"}'