From 293aba1437b2aa6cdf8cf0d3f62664b6a0026226 Mon Sep 17 00:00:00 2001 From: samber Date: Sun, 26 Feb 2023 01:34:30 +0000 Subject: [PATCH] Publish --- dist/rules/host-and-hardware/node-exporter.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/dist/rules/host-and-hardware/node-exporter.yml b/dist/rules/host-and-hardware/node-exporter.yml index a784410..db590f4 100644 --- a/dist/rules/host-and-hardware/node-exporter.yml +++ b/dist/rules/host-and-hardware/node-exporter.yml @@ -122,7 +122,7 @@ groups: description: "Disk latency is growing (write operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostHighCpuLoad - expr: '100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80' + expr: 'sum by (instance) (avg by (mode, instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m]))) > 0.8' for: 0m labels: severity: warning @@ -149,13 +149,13 @@ groups: description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostCpuHighIowait - expr: 'avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 5' + expr: 'avg by (instance) (rate(node_cpu_seconds_total{mode="iowait"}[5m])) * 100 > 10' for: 0m labels: severity: warning annotations: summary: Host CPU high iowait (instance {{ $labels.instance }}) - description: "CPU iowait > 5%. A high iowait means that you are disk or network bound.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + description: "CPU iowait > 10%. A high iowait means that you are disk or network bound.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: HostUnusualDiskIo expr: 'rate(node_disk_io_time_seconds_total[1m]) > 0.5'