feat: add CPU threshold variable

matbgn · Nov 17, 2023 · 8d2de46 · 8d2de46
1 parent f1bf6c3
commit 8d2de46
Show file tree

Hide file tree

Showing 5 changed files with 15 additions and 4 deletions.
diff --git a/.env.example b/.env.example
@@ -31,6 +31,8 @@ BLACKBOX_URL_TO_PROBE="http://localhost:9500/metrics, http://localhost:9560/,"
 ALERTMANAGER_REPEAT_INTERVAL=4h
 # [OPTIONAL] Set another Temperature threshold alarm [°C]
 ALERTMANAGER_TEMPERATURE_THRESHOLD=77
+# [OPTIONAL] Set another CPU threshold alarm [%]
+ALERTMANAGER_CPU_THRESHOLD=80
 
 # [OPTIONAL] Add supplementary services to be notified from (space separated!)
 # (see https://pingme.lmno.pk/ - except Email and Zulip NOT SUPPORTED HERE because provided by default, see above)

diff --git a/.gitignore b/.gitignore
@@ -7,3 +7,4 @@ ansible/group_vars/*
 ansible/host_vars/*
 !ansible/host_vars/.gitkeep
 !.env.example
+.vscode
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/).
 ## [Unreleased]
 ...
 
+## [5.2.0] - 2023-11-17
+### Add
+- Add possibility to adapt CPU threshold for alarms firing with ALERTMANAGER_CPU_THRESHOLD
+
 ## [5.1.4] - 2023-06-17
 ### Fix
 - Fix node_exporter goroutine error
@@ -131,7 +135,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/).
 ### Removed
 - [WARNING] Breaking changes for script arguments
 
-[Unreleased]: https://github.com/matbgn/prommanager/compare/v5.1.4...HEAD
+[Unreleased]: https://github.com/matbgn/prommanager/compare/v5.2.0...HEAD
+[5.1.4]: https://github.com/matbgn/prommanager/compare/v5.1.4...v5.2.0
 [5.1.2]: https://github.com/matbgn/prommanager/compare/v5.1.2...v5.1.4
 [5.1.2]: https://github.com/matbgn/prommanager/compare/v5.1.1...v5.1.2
 [5.1.1]: https://github.com/matbgn/prommanager/compare/v5.1.0...v5.1.1

diff --git a/docs/README.md b/docs/README.md
@@ -176,6 +176,8 @@ BLACKBOX_URL_TO_PROBE="http://localhost:9500/metrics, http://localhost:9560/,"
 ALERTMANAGER_REPEAT_INTERVAL=4h
 # [OPTIONAL] Set another Temperature threshold alarm [°C]
 ALERTMANAGER_TEMPERATURE_THRESHOLD=77
+# [OPTIONAL] Set another CPU threshold alarm [%]
+ALERTMANAGER_CPU_THRESHOLD=80
 ```
 
 ### Tweaking alert rules

diff --git a/prommanager b/prommanager
@@ -1,5 +1,5 @@
 #!/bin/bash
-MOTD="Welcome to Prometheus manager v5.1.4 !"
+MOTD="Welcome to Prometheus manager v5.2.0 !"
 
 # Set default values
 SYSTEM_ARCH=amd64 # -> can be changed by script argument --arch arm64
@@ -32,6 +32,7 @@ PROMETHEUS_PORT=9590
 
 ALERTMANAGER_REPEAT_INTERVAL=4h
 ALERTMANAGER_TEMPERATURE_THRESHOLD=77
+ALERTMANAGER_CPU_THRESHOLD=80
 
 EXECUTE=false
 KILL_APPS=false
@@ -829,13 +830,13 @@ groups:
       summary: HTTP probe failed (instance {{ \$labels.instance }})
       description: "Probe failed\n  VALUE = {{ \$value }}\n  LABELS = {{ \$labels }}"
   - alert: HostHighCpuLoad
-    expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80
+    expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > $ALERTMANAGER_CPU_THRESHOLD
     for: 0m
     labels:
       severity: warning
     annotations:
       summary: Host high CPU load (instance {{ \$labels.instance }})
-      description: "CPU load is greater than 80%\n  VALUE = {{ \$value }}\n  LABELS = {{ \$labels }}"
+      description: "CPU load is greater than $ALERTMANAGER_CPU_THRESHOLD%\n  VALUE = {{ \$value }}\n  LABELS = {{ \$labels }}"
   - alert: HostOutOfMemory
     expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 15
     for: 2m