RepoMirrors
/
node_exporter
mirror of https://github.com/prometheus/node_exporter
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add thresholds for memory alerts 

Signed-off-by: Vitaly Zhuravlev <v-zhuravlev@users.noreply.github.com>
This commit is contained in:
Vitaly Zhuravlev 2023-04-06 00:21:50 +08:00
parent 2111e70ac7
commit 77ae769179
2 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
docs/node-mixin/alerts/alerts.libsonnet
View File

@ -344,7 +344,7 @@
{ {
alert: 'NodeMemoryMajorPagesFaults', alert: 'NodeMemoryMajorPagesFaults',
expr: ||| expr: |||
rate(node_vmstat_pgmajfault{%(nodeExporterSelector)s}[5m]) > 500 rate(node_vmstat_pgmajfault{%(nodeExporterSelector)s}[5m]) > %(memoryMajorPagesFaultsWarningThreshold)s
||| % $._config, ||| % $._config,
'for': '15m', 'for': '15m',
labels: { labels: {
@ -353,15 +353,15 @@
annotations: { annotations: {
summary: 'Memory major page faults are occurring at very high rate.', summary: 'Memory major page faults are occurring at very high rate.',
description: ||| description: |||
Memory major pages are occurring at very high rate at {{ $labels.instance }}, 500 major page faults per second for the last 15 minutes, is currently at {{ printf "%.2f" $value }}. Memory major pages are occurring at very high rate at {{ $labels.instance }}, %(memoryMajorPagesFaultsWarningThreshold)s major page faults per second for the last 15 minutes, is currently at {{ printf "%.2f" $value }}.
Please check that there is enough memory available at this instance. Please check that there is enough memory available at this instance.
|||, ||| % $._config,
}, },
}, },
{ {
alert: 'NodeMemoryHighUtilization', alert: 'NodeMemoryHighUtilization',
expr: ||| expr: |||
100 - (node_memory_MemAvailable_bytes{%(nodeExporterSelector)s} / node_memory_MemTotal_bytes{%(nodeExporterSelector)s} * 100) > 90 100 - (node_memory_MemAvailable_bytes{%(nodeExporterSelector)s} / node_memory_MemTotal_bytes{%(nodeExporterSelector)s} * 100) > %(memoryHighUtilizationThreshold)s
||| % $._config, ||| % $._config,
'for': '15m', 'for': '15m',
labels: { labels: {
@ -370,7 +370,7 @@
annotations: { annotations: {
summary: 'Host is running out of memory.', summary: 'Host is running out of memory.',
description: ||| description: |||
Memory is filling up at {{ $labels.instance }}, has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%. Memory is filling up at {{ $labels.instance }}, has been above %(memoryHighUtilizationThreshold)s% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%.
|||, |||,
}, },
}, },

8
docs/node-mixin/config.libsonnet
View File

@ -60,6 +60,14 @@
fsSpaceAvailableWarningThreshold: 5, fsSpaceAvailableWarningThreshold: 5,
fsSpaceAvailableCriticalThreshold: 3, fsSpaceAvailableCriticalThreshold: 3,
// Memory utilzation (%) level on which to trigger the
// 'NodeMemoryHighUtilization' alert.
memoryHighUtilizationThreshold: 90,
// Threshold for the rate of memory major page faults to trigger
// 'NodeMemoryMajorPagesFaults' alert.
memoryMajorPagesFaultsWarningThreshold: 500,
rateInterval: '5m', rateInterval: '5m',
// Opt-in for multi-cluster support. // Opt-in for multi-cluster support.
showMultiCluster: false, showMultiCluster: false,