kazu634
/
itamae
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'modify-prometheus-alert-config' of kazu634/itamae into master

This commit is contained in:
Kazuhiro MUSASHI 2020-10-24 13:11:19 +09:00 committed by Gitea
parent a0907aade4 1a530ed7de
commit 85208d8447
2 changed files with 12 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
cookbooks/prometheus/files/etc/prometheus.d/alerts/filestat.yml
View File

@ -10,3 +10,11 @@ groups:
summary: "Instance {{ $labels.instance }} requires rebooting." summary: "Instance {{ $labels.instance }} requires rebooting."
description: "{{ $labels.instance }} requires rebooting." description: "{{ $labels.instance }} requires rebooting."
- alert: apt-mirror
expr: time() - file_stat_modif_time_seconds{path="/var/spool/apt-mirror/updated"} > 87000
for: 12h
labels:
severity: error
annotations:
summary: "apt-mirror is not updated."
description: "apt-mirror is not updated."

8
cookbooks/prometheus/files/etc/prometheus.d/alerts/node_exporter.yml
View File

@ -113,13 +113,13 @@ groups:
# Alert threshold depends on nature of application. # Alert threshold depends on nature of application.
# Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58 # Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
- alert: HostContextSwitching - alert: HostContextSwitching
expr: (rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 4000 expr: (rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 4500
for: 5m for: 5m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: "Host context switching (instance {{ $labels.instance }})" summary: "Host context switching (instance {{ $labels.instance }})"
description: "Context switching is growing on node (> 4000 / s)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" description: "Context switching is growing on node (> 4500 / s)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostSwapIsFillingUp - alert: HostSwapIsFillingUp
expr: (1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80 expr: (1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80
@ -176,8 +176,8 @@ groups:
description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: HostKernelVersionDeviations - alert: HostKernelVersionDeviations
expr: count(sum(label_replace(node_uname_info, "kernel", "$1", "release", "([0-9]+.[0-9]+.[0-9]+).*")) by (kernel)) > 1 expr: count(sum(label_replace(node_uname_info, "kernel", "$1", "release", "([0-9]+.[0-9]+.[0-9]+).*")) by (kernel)) > 2
for: 5m for: 24h
labels: labels:
severity: warning severity: warning
annotations: annotations: