[fluentd-elasticsearch] Add ability to setup livenessProbe on fluentd (#5703)

* Add ability to setup livenessProbe on fluentd

* Update README.md

* Update values.yaml

* Update Chart.yaml

incubator/fluentd-elasticsearch/Chart.yaml

@@ -1,5 +1,5 @@
 name: fluentd-elasticsearch
-version: 0.4.2
+version: 0.5.0
 appVersion: 2.0.4
 home: https://www.fluentd.org/
 description: A Fluentd Helm chart for Kubernetes with Elasticsearch output

incubator/fluentd-elasticsearch/README.md

@@ -60,6 +60,7 @@ The following table lists the configurable parameters of the Fluentd elasticsear
 | `resources.requests.memory`        | Memory request                             | `200Mi`                                                    |
 | `serviceAccount.create`            | Specifies whether a service account should be created.| `true`                                          |
 | `serviceAccount.name`              | Name of the service account.               |                                                            |   
+| `livenessProbe.enabled`            | Wether to enable livenessProbe             | `true`                                                    |   
 | `tolerations`                      | Optional daemonset tolerations             | `NULL`                                                     |
 
 

incubator/fluentd-elasticsearch/templates/daemonset.yaml

@@ -70,6 +70,40 @@ spec:
 {{- if .Values.extraVolumeMounts }}
 {{ toYaml .Values.extraVolumeMounts | indent 8 }}
 {{- end }}
+{{- if .Values.livenessProbe.enabled }}       
+        # Liveness probe is aimed to help in situarions where fluentd
+        # silently hangs for no apparent reasons until manual restart.
+        # The idea of this probe is that if fluentd is not queueing or
+        # flushing chunks for 5 minutes, something is not right. If
+        # you want to change the fluentd configuration, reducing amount of
+        # logs fluentd collects, consider changing the threshold or turning
+        # liveness probe off completely.
+        livenessProbe:
+          initialDelaySeconds: 600
+          periodSeconds: 60
+          exec:
+            command:
+            - '/bin/sh'
+            - '-c'
+            - >
+              LIVENESS_THRESHOLD_SECONDS=${LIVENESS_THRESHOLD_SECONDS:-300};
+              STUCK_THRESHOLD_SECONDS=${LIVENESS_THRESHOLD_SECONDS:-900};
+              if [ ! -e /var/log/fluentd-buffers ];
+              then
+                exit 1;
+              fi;
+              touch -d "${STUCK_THRESHOLD_SECONDS} seconds ago" /tmp/marker-stuck;
+              if [[ -z "$(find /var/log/fluentd-buffers -type f -newer /tmp/marker-stuck -print -quit)" ]];
+              then
+                rm -rf /var/log/fluentd-buffers;
+                exit 1;
+              fi;
+              touch -d "${LIVENESS_THRESHOLD_SECONDS} seconds ago" /tmp/marker-liveness;
+              if [[ -z "$(find /var/log/fluentd-buffers -type f -newer /tmp/marker-liveness -print -quit)" ]];
+              then
+                exit 1;
+              fi;
+{{- end }}              
       terminationGracePeriodSeconds: 30
       volumes:
       - name: varlog

incubator/fluentd-elasticsearch/values.yaml

@@ -33,6 +33,9 @@ serviceAccount:
   # If not set and create is true, a name is generated using the fullname template
   name:
 
+livenessProbe:
+  enabled: true
+
 annotations: {}
   # prometheus.io/scrape: "true"
   # prometheus.io/port: "24231"