fix: alert - add coredns, comment out some useless alert rules

This commit is contained in:
Ryan Yin
2025-09-14 10:40:12 +08:00
parent c8182216ae
commit 7a82b8085a
4 changed files with 47 additions and 33 deletions
@@ -203,18 +203,18 @@ groups:
summary: Host high CPU load (instance {{ $labels.instance }})
description: "CPU load is > 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: HostCpuIsUnderutilized
expr:
'(100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20) * on(instance)
group_left (nodename) node_uname_info{nodename=~".+"}'
for: 1w
labels:
severity: info
annotations:
summary: Host CPU is underutilized (instance {{ $labels.instance }})
description:
"CPU load is < 20% for 1 week. Consider reducing the number of CPUs.\n VALUE = {{
$value }}\n LABELS = {{ $labels }}"
# - alert: HostCpuIsUnderutilized
# expr:
# '(100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20) * on(instance)
# group_left (nodename) node_uname_info{nodename=~".+"}'
# for: 1w
# labels:
# severity: info
# annotations:
# summary: Host CPU is underutilized (instance {{ $labels.instance }})
# description:
# "CPU load is < 20% for 1 week. Consider reducing the number of CPUs.\n VALUE = {{
# $value }}\n LABELS = {{ $labels }}"
- alert: HostCpuStealNoisyNeighbor
expr: