From 943c4fac92964f4164680a9245d46a1adf620d1b Mon Sep 17 00:00:00 2001
From: Ilya Mashchenko <ilya@netdata.cloud>
Date: Fri, 5 Jul 2024 11:33:18 +0300
Subject: [PATCH] health add alarm docker container down (#18075)

---
 src/health/health.d/docker.conf | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/src/health/health.d/docker.conf b/src/health/health.d/docker.conf
index 668614d4dcd29e..edb63a08ca06f0 100644
--- a/src/health/health.d/docker.conf
+++ b/src/health/health.d/docker.conf
@@ -1,4 +1,6 @@
- template: docker_container_unhealthy
+# you can disable an alarm notification by setting the 'to' line to: silent
+
+template: docker_container_unhealthy
        on: docker.container_health_status
     class: Errors
      type: Containers
@@ -10,3 +12,22 @@ component: Docker
   summary: Docker container ${label:container_name} health
      info: ${label:container_name} docker container health status is unhealthy
        to: sysadmin
+
+# This alert monitors the status of Docker containers and triggers if any container is exited (down).
+# To enable this alert for specific containers, you need to modify the "chart labels" filter.
+# This filter uses Netdata's simple pattern matching syntax.
+
+    template: docker_container_down
+          on: docker.container_state
+       class: Errors
+        type: Containers
+   component: Docker
+chart labels: container_name=!*
+       units: status
+       every: 10s
+      lookup: average -10s of exited
+        warn: $this > 0
+       delay: down 1m multiplier 1.5 max 2h
+     summary: Docker container ${label:container_name} down
+        info: Docker container ${label:container_name} is currently not running
+          to: sysadmin