Add feature auto-heal action

.github/workflows/docker-publish.yml

@@ -0,0 +1,48 @@
+#
+name: Create and publish a Docker image
+
+# Configures this workflow to run every time a change is pushed to the branch called `release`.
+on:
+  push:
+    branches: ['main']
+
+# Defines two custom environment variables for the workflow. These are used for the Container registry domain, and a name for the Docker image that this workflow builds.
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
+    permissions:
+      contents: read
+      packages: write
+      # 
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      # Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
+      - name: Log in to the Container registry
+        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      # This step uses [docker/metadata-action](https://github.com/docker/metadata-action#about) to extract tags and labels that will be applied to the specified image. The `id` "meta" allows the output of this step to be referenced in a subsequent step. The `images` value provides the base name for the tags and labels.
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+      # This step uses the `docker/build-push-action` action to build the image, based on your repository's `Dockerfile`. If the build succeeds, it pushes the image to GitHub Packages.
+      # It uses the `context` parameter to define the build's context as the set of files located in the specified path. For more information, see "[Usage](https://github.com/docker/build-push-action#usage)" in the README of the `docker/build-push-action` repository.
+      # It uses the `tags` and `labels` parameters to tag and label the image with the output from the "meta" step.
+      - name: Build and push Docker image
+        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

Dockerfile

@@ -15,12 +15,13 @@ ENV AUTOHEAL_CONTAINER_LABEL=autoheal \
     WEBHOOK_URL="" \
     WEBHOOK_JSON_KEY="content" \
     APPRISE_URL="" \
-    POST_RESTART_SCRIPT=""
+    POST_ACTION_SCRIPT=""\
+    AUTOHEAL_ACTION="RESTART"
 
 COPY docker-entrypoint /
 
 HEALTHCHECK --interval=5s CMD pgrep -f autoheal || exit 1
 
 ENTRYPOINT ["/docker-entrypoint"]
 
-CMD ["autoheal"]
+CMD ["autoheal"]

README.md

@@ -58,6 +58,7 @@ AUTOHEAL_CONTAINER_LABEL=autoheal
 AUTOHEAL_INTERVAL=5   # check every 5 seconds
 AUTOHEAL_START_PERIOD=0   # wait 0 seconds before first health check
 AUTOHEAL_DEFAULT_STOP_TIMEOUT=10   # Docker waits max 10 seconds (the Docker default) for a container to stop before killing during restarts (container overridable via label, see below)
+AUTOHEAL_ACTION=RESTART # Action to process unhealthy containers ('RESTART' or 'STOP')
 DOCKER_SOCK=/var/run/docker.sock   # Unix socket for curl requests to Docker API
 CURL_TIMEOUT=30     # --max-time seconds for curl requests to Docker API
 WEBHOOK_URL=""    # post message to the webhook if a container was restarted (or restart failed)

docker-entrypoint

@@ -29,6 +29,7 @@ AUTOHEAL_CONTAINER_LABEL=${AUTOHEAL_CONTAINER_LABEL:-autoheal}
 AUTOHEAL_START_PERIOD=${AUTOHEAL_START_PERIOD:-0}
 AUTOHEAL_INTERVAL=${AUTOHEAL_INTERVAL:-5}
 AUTOHEAL_DEFAULT_STOP_TIMEOUT=${AUTOHEAL_DEFAULT_STOP_TIMEOUT:-10}
+AUTOHEAL_ACTION=${AUTOHEAL_ACTION:-RESTART}
 
 docker_curl() {
   curl --max-time "${CURL_TIMEOUT}" --no-buffer -s \
@@ -61,6 +62,46 @@ restart_container() {
   docker_curl -f -X POST "${HTTP_ENDPOINT}/containers/${container_id}/restart?t=${timeout}"
 }
 
+remove_container(){
+local container_id="$1"
+local timeout="$2"
+
+docker_curl -f -X POST "${HTTP_ENDPOINT}/containers/${container_id}/stop?t=${timeout}"
+docker_curl -f -X DEL "${HTTP_ENDPOINT}/containers/${container_id}?force=true"
+sleep 10s
+}
+
+manage_unhealthy_container(){
+
+  if [ "$AUTOHEAL_ACTION" = "STOP" ]
+  then 
+
+ echo "$DATE Container $CONTAINER_NAME (${CONTAINER_SHORT_ID}) found to be unhealthy - Stopping container now"
+        if ! remove_container "$CONTAINER_ID" "$TIMEOUT"
+        then
+          echo "$DATE Stopping container $CONTAINER_SHORT_ID failed" >&2
+          notify_webhook "Container ${CONTAINER_NAME:1} (${CONTAINER_SHORT_ID}) found to be unhealthy. Failed to stop the container!" &
+        else
+          notify_webhook "Container ${CONTAINER_NAME:1} (${CONTAINER_SHORT_ID}) found to be unhealthy. Successfully stopped the container!" &
+        fi
+        notify_post_action_script "$CONTAINER_NAME" "$CONTAINER_SHORT_ID" "$CONTAINER_STATE" &
+
+  else
+
+  echo "$DATE Container $CONTAINER_NAME (${CONTAINER_SHORT_ID}) found to be unhealthy - Restarting container now with ${TIMEOUT}s timeout"
+        if ! restart_container "$CONTAINER_ID" "$TIMEOUT"
+        then
+          echo "$DATE Restarting container $CONTAINER_SHORT_ID failed" >&2
+          notify_webhook "Container ${CONTAINER_NAME:1} (${CONTAINER_SHORT_ID}) found to be unhealthy. Failed to restart the container!" &
+        else
+          notify_webhook "Container ${CONTAINER_NAME:1} (${CONTAINER_SHORT_ID}) found to be unhealthy. Successfully restarted the container!" &
+        fi
+        notify_post_action_script "$CONTAINER_NAME" "$CONTAINER_SHORT_ID" "$CONTAINER_STATE" "$TIMEOUT" &
+
+  fi 
+
+}
+
 notify_webhook() {
   local text="$@"
 
@@ -77,11 +118,11 @@ notify_webhook() {
   fi
 }
 
-notify_post_restart_script() {
-  if [ -n "$POST_RESTART_SCRIPT" ]
+notify_post_action_script() {
+  if [ -n "$POST_ACTION_SCRIPT" ]
   then
     # execute post restart script as background process to prevent healer from blocking
-    $POST_RESTART_SCRIPT "$@" &
+    $POST_ACTION_SCRIPT "$@" &
   fi
 }
 
@@ -141,20 +182,12 @@ then
 
       if [ "$CONTAINER_NAME" = "null" ]
       then
-        echo "$DATE Container name of (${CONTAINER_SHORT_ID}) is null, which implies container does not exist - don't restart" >&2
+        echo "$DATE Container name of (${CONTAINER_SHORT_ID}) is null, which implies container does not exist - no action" >&2
       elif [ "$CONTAINER_STATE" = "restarting" ]
       then
-        echo "$DATE Container $CONTAINER_NAME (${CONTAINER_SHORT_ID}) found to be restarting - don't restart"
+        echo "$DATE Container $CONTAINER_NAME (${CONTAINER_SHORT_ID}) found to be restarting - no action"
       else
-        echo "$DATE Container $CONTAINER_NAME (${CONTAINER_SHORT_ID}) found to be unhealthy - Restarting container now with ${TIMEOUT}s timeout"
-        if ! restart_container "$CONTAINER_ID" "$TIMEOUT"
-        then
-          echo "$DATE Restarting container $CONTAINER_SHORT_ID failed" >&2
-          notify_webhook "Container ${CONTAINER_NAME:1} (${CONTAINER_SHORT_ID}) found to be unhealthy. Failed to restart the container!" &
-        else
-          notify_webhook "Container ${CONTAINER_NAME:1} (${CONTAINER_SHORT_ID}) found to be unhealthy. Successfully restarted the container!" &
-        fi
-        notify_post_restart_script "$CONTAINER_NAME" "$CONTAINER_SHORT_ID" "$CONTAINER_STATE" "$TIMEOUT" &
+        manage_unhealthy_container
       fi
     done
     sleep "$AUTOHEAL_INTERVAL" &