mirror of
https://github.com/etcd-io/etcd.git
synced 2024-09-27 06:25:44 +00:00
Revert "Remove mixin from Doc"
This commit is contained in:
Sahdev Zala
GitHub
parent
080453d416
commit
9fed697435
25
Documentation/etcd-mixin/README.md
Normal file
25
Documentation/etcd-mixin/README.md
Normal file
@ -0,0 +1,25 @@
|
||||
# Prometheus Monitoring Mixin for etcd
|
||||
|
||||
> NOTE: This project is *alpha* stage. Flags, configuration, behaviour and design may change significantly in following releases.
|
||||
|
||||
A set of customisable Prometheus alerts for etcd.
|
||||
|
||||
Instructions for use are the same as the [kubernetes-mixin](https://github.com/kubernetes-monitoring/kubernetes-mixin).
|
||||
|
||||
## Background
|
||||
|
||||
* For more information about monitoring mixins, see this [design doc](https://docs.google.com/document/d/1A9xvzwqnFVSOZ5fD3blKODXfsat5fg6ZhnKu9LK3lB4/edit#).
|
||||
|
||||
## Testing alerts
|
||||
|
||||
Make sure to have [jsonnet](https://jsonnet.org/) and [gojsontoyaml](https://github.com/brancz/gojsontoyaml) installed.
|
||||
|
||||
First compile the mixin to a YAML file, which the promtool will read:
|
||||
```
|
||||
jsonnet -e '(import "mixin.libsonnet").prometheusAlerts' | gojsontoyaml > mixin.yaml
|
||||
```
|
||||
|
||||
Then run the unit test:
|
||||
```
|
||||
promtool test rules test.yaml
|
||||
```
|
||||
1311
Documentation/etcd-mixin/mixin.libsonnet
Normal file
1311
Documentation/etcd-mixin/mixin.libsonnet
Normal file
File diff suppressed because it is too large
Load Diff
135
Documentation/etcd-mixin/test.yaml
Normal file
135
Documentation/etcd-mixin/test.yaml
Normal file
@ -0,0 +1,135 @@
|
||||
rule_files:
|
||||
- mixin.yaml
|
||||
|
||||
evaluation_interval: 1m
|
||||
|
||||
tests:
|
||||
- interval: 1m
|
||||
input_series:
|
||||
- series: 'up{job="etcd",instance="10.10.10.0"}'
|
||||
values: '1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0'
|
||||
- series: 'up{job="etcd",instance="10.10.10.1"}'
|
||||
values: '1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0'
|
||||
- series: 'up{job="etcd",instance="10.10.10.2"}'
|
||||
values: '1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0'
|
||||
alert_rule_test:
|
||||
- eval_time: 3m
|
||||
alertname: etcdInsufficientMembers
|
||||
- eval_time: 5m
|
||||
alertname: etcdInsufficientMembers
|
||||
- eval_time: 12m
|
||||
alertname: etcdMembersDown
|
||||
- eval_time: 14m
|
||||
alertname: etcdMembersDown
|
||||
exp_alerts:
|
||||
- exp_labels:
|
||||
job: etcd
|
||||
severity: critical
|
||||
exp_annotations:
|
||||
description: 'etcd cluster "etcd": members are down (3).'
|
||||
summary: 'etcd cluster members are down.'
|
||||
- eval_time: 7m
|
||||
alertname: etcdInsufficientMembers
|
||||
- eval_time: 11m
|
||||
alertname: etcdInsufficientMembers
|
||||
exp_alerts:
|
||||
- exp_labels:
|
||||
job: etcd
|
||||
severity: critical
|
||||
exp_annotations:
|
||||
description: 'etcd cluster "etcd": insufficient members (1).'
|
||||
summary: 'etcd cluster has insufficient number of members.'
|
||||
- eval_time: 15m
|
||||
alertname: etcdInsufficientMembers
|
||||
exp_alerts:
|
||||
- exp_labels:
|
||||
job: etcd
|
||||
severity: critical
|
||||
exp_annotations:
|
||||
description: 'etcd cluster "etcd": insufficient members (0).'
|
||||
summary: 'etcd cluster has insufficient number of members.'
|
||||
|
||||
- interval: 1m
|
||||
input_series:
|
||||
- series: 'up{job="etcd",instance="10.10.10.0"}'
|
||||
values: '1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0'
|
||||
- series: 'up{job="etcd",instance="10.10.10.1"}'
|
||||
values: '1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0'
|
||||
- series: 'up{job="etcd",instance="10.10.10.2"}'
|
||||
values: '1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0'
|
||||
alert_rule_test:
|
||||
- eval_time: 14m
|
||||
alertname: etcdMembersDown
|
||||
exp_alerts:
|
||||
- exp_labels:
|
||||
job: etcd
|
||||
severity: critical
|
||||
exp_annotations:
|
||||
description: 'etcd cluster "etcd": members are down (3).'
|
||||
summary: 'etcd cluster members are down.'
|
||||
|
||||
- interval: 1m
|
||||
input_series:
|
||||
- series: 'up{job="etcd",instance="10.10.10.0"}'
|
||||
values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0'
|
||||
- series: 'up{job="etcd",instance="10.10.10.1"}'
|
||||
values: '1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0'
|
||||
- series: 'etcd_network_peer_sent_failures_total{To="member-1",job="etcd",endpoint="test"}'
|
||||
values: '0 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18'
|
||||
alert_rule_test:
|
||||
- eval_time: 13m
|
||||
alertname: etcdMembersDown
|
||||
exp_alerts:
|
||||
- exp_labels:
|
||||
job: etcd
|
||||
severity: critical
|
||||
exp_annotations:
|
||||
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"}'
|
||||
values: '0 0 2 0 0 1 0 0 0 0 0 0 0 0 0 0'
|
||||
- series: 'etcd_server_leader_changes_seen_total{job="etcd",instance="10.10.10.1"}'
|
||||
values: '0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0'
|
||||
- series: 'etcd_server_leader_changes_seen_total{job="etcd",instance="10.10.10.2"}'
|
||||
values: '0 0 0 0 0 0 0 0'
|
||||
alert_rule_test:
|
||||
- eval_time: 10m
|
||||
alertname: etcdHighNumberOfLeaderChanges
|
||||
exp_alerts:
|
||||
- exp_labels:
|
||||
job: etcd
|
||||
severity: warning
|
||||
exp_annotations:
|
||||
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"}'
|
||||
values: '0 0 2 0 0 0 0 0 0 0 0 0 0 0 0 0'
|
||||
- series: 'etcd_server_leader_changes_seen_total{job="etcd",instance="10.10.10.1"}'
|
||||
values: '0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0'
|
||||
- series: 'etcd_server_leader_changes_seen_total{job="etcd",instance="10.10.10.2"}'
|
||||
values: '0 0 0 0 0 0 0 0'
|
||||
alert_rule_test:
|
||||
- eval_time: 10m
|
||||
alertname: etcdHighNumberOfLeaderChanges
|
||||
exp_alerts:
|
||||
- interval: 1m
|
||||
input_series:
|
||||
- series: '((etcd_mvcc_db_total_size_in_bytes/etcd_server_quota_backend_bytes)*100){job="etcd",instance="10.10.10.0"}'
|
||||
values: '0 10 20 0 0 10 0 0 30 0 0 0 0 0 0 0'
|
||||
- series: '((etcd_mvcc_db_total_size_in_bytes/etcd_server_quota_backend_bytes)*100){job="etcd",instance="10.10.10.1"}'
|
||||
values: '0 0 10 0 20 0 0 0 0 0 0 0 0 0 0 0'
|
||||
- series: '((etcd_mvcc_db_total_size_in_bytes/etcd_server_quota_backend_bytes)*100){job="etcd",instance="10.10.10.2"}'
|
||||
values: '0 0 0 0 0 0 0 0'
|
||||
alert_rule_test:
|
||||
- eval_time: 10m
|
||||
alertname: etcdExcessiveDatabaseGrowth
|
||||
exp_alerts:
|
||||
- exp_labels:
|
||||
job: etcd
|
||||
severity: warning
|
||||
exp_annotations:
|
||||
message: 'etcd cluster "etcd": Observed surge in etcd writes leading to 50% increase in database size over the past four hours, please check as it might be disruptive.'
|
||||
Loading…
x
Reference in New Issue
Block a user