health add alarm docker container down (#18075)
Ilya Mashchenko committed
Jul 5, 2024 at 11:33 UTC
943c4fac92964f4164680a9245d46a1adf620d1b
1 file changed
+22
-1
src/health/health.d/docker.conf
+22
-1
@@ -1,4 +1,6 @@
1
- template: docker_container_unhealthy
1
+# you can disable an alarm notification by setting the 'to' line to: silent
2
+
3
+template: docker_container_unhealthy
4
on: docker.container_health_status
5
class: Errors
6
type: Containers
@@ -10,3 +12,22 @@ component: Docker
12
summary: Docker container ${label:container_name} health
13
info: ${label:container_name} docker container health status is unhealthy
14
to: sysadmin
15
+
16
+# This alert monitors the status of Docker containers and triggers if any container is exited (down).
17
+# To enable this alert for specific containers, you need to modify the "chart labels" filter.
18
+# This filter uses Netdata's simple pattern matching syntax.
19
+
20
+ template: docker_container_down
21
+ on: docker.container_state
22
+ class: Errors
23
+ type: Containers
24
+ component: Docker
25
+chart labels: container_name=!*
26
+ units: status
27
+ every: 10s
28
+ lookup: average -10s of exited
29
+ warn: $this > 0
30
+ delay: down 1m multiplier 1.5 max 2h
31
+ summary: Docker container ${label:container_name} down
32
+ info: Docker container ${label:container_name} is currently not running
33
+ to: sysadmin