HPC/prometheus
11
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #70 from eduponte/version-2

Browse Source 
Update configs to Prometheus v2
This commit is contained in:
田浩 2017-11-10 23:33:54 +08:00 committed by GitHub
commit 8c8badfd74
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 15 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
prometheus/alert.rules
View File

@ -1,11 +1,22 @@
groups: groups:
- name: example - name: example
rules: rules:
- alert: InstanceDown
# Alert for any instance that is unreachable for >5 minutes.
- alert: service_down
expr: up == 0 expr: up == 0
for: 5m for: 2m
labels: labels:
severity: page severity: page
annotations: annotations:
summary: "Instance {{ $labels.instance }} down" summary: "Instance {{ $labels.instance }} down"
description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes." description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 2 minutes."
- alert: high_load
expr: node_load1 > 0.5
for: 2m
labels:
severity: page
annotations:
summary: "Instance {{ $labels.instance }} under high load"
description: "{{ $labels.instance }} of job {{ $labels.job }} is under high load."

2
prometheus/prometheus.yml
View File

@ -11,7 +11,7 @@ global:
# Load and evaluate rules in this file every 'evaluation_interval' seconds. # Load and evaluate rules in this file every 'evaluation_interval' seconds.
rule_files: rule_files:
- "alert.rules" - 'alert.rules'
# - "first.rules" # - "first.rules"
# - "second.rules" # - "second.rules"