chore(netbox): add healthchecks (#5439)

* chore(netbox): add healthchecks

* smooth upgrade

charts/incubator/netbox/Chart.yaml

@@ -27,7 +27,7 @@ name: netbox
 sources:
   - https://github.com/truecharts/charts/tree/master/charts/incubator/netbox
   - https://github.com/netbox-community/netbox-docker
-version: 3.0.12
+version: 3.0.13
 annotations:
   truecharts.org/catagories: |
     - network

charts/incubator/netbox/templates/_housekeeper.tpl

@@ -30,4 +30,37 @@ volumeMounts:
   - name: configfile
     mountPath: /etc/netbox/config/01-config.py
     subPath: config.py
+readinessProbe:
+  exec:
+    command:
+      - /bin/bash
+      - -c
+      - |
+        ps -aux | grep -v grep | grep -q housekeeping || exit 1
+  initialDelaySeconds: {{ .Values.probes.readiness.spec.initialDelaySeconds }}
+  timeoutSeconds: {{ .Values.probes.readiness.spec.timeoutSeconds }}
+  periodSeconds: {{ .Values.probes.readiness.spec.periodSeconds }}
+  failureThreshold: {{ .Values.probes.readiness.spec.failureThreshold }}
+livenessProbe:
+  exec:
+    command:
+      - /bin/bash
+      - -c
+      - |
+        ps -aux | grep -v grep | grep -q housekeeping || exit 1
+  initialDelaySeconds: {{ .Values.probes.liveness.spec.initialDelaySeconds }}
+  timeoutSeconds: {{ .Values.probes.liveness.spec.timeoutSeconds }}
+  periodSeconds: {{ .Values.probes.liveness.spec.periodSeconds }}
+  failureThreshold: {{ .Values.probes.liveness.spec.failureThreshold }}
+startupProbe:
+  exec:
+    command:
+      - /bin/bash
+      - -c
+      - |
+        ps -aux | grep -v grep | grep -q housekeeping || exit 1
+  initialDelaySeconds: {{ .Values.probes.startup.spec.initialDelaySeconds }}
+  timeoutSeconds: {{ .Values.probes.startup.spec.timeoutSeconds }}
+  periodSeconds: {{ .Values.probes.startup.spec.periodSeconds }}
+  failureThreshold: {{ .Values.probes.startup.spec.failureThreshold }}
 {{- end -}}

charts/incubator/netbox/templates/_worker.tpl

@@ -29,10 +29,13 @@ volumeMounts:
   - name: configfile
     mountPath: /etc/netbox/config/01-config.py
     subPath: config.py
-{{/*readinessProbe:
+readinessProbe:
   exec:
     command:
-      - TODO: find a healthcheck
+      - /bin/bash
+      - -c
+      - |
+        ps -aux | grep -v grep | grep -q rqworker || exit 1
   initialDelaySeconds: {{ .Values.probes.readiness.spec.initialDelaySeconds }}
   timeoutSeconds: {{ .Values.probes.readiness.spec.timeoutSeconds }}
   periodSeconds: {{ .Values.probes.readiness.spec.periodSeconds }}
@@ -40,7 +43,10 @@ volumeMounts:
 livenessProbe:
   exec:
     command:
-      - TODO: find a healthcheck
+      - /bin/bash
+      - -c
+      - |
+        ps -aux | grep -v grep | grep -q rqworker || exit 1
   initialDelaySeconds: {{ .Values.probes.liveness.spec.initialDelaySeconds }}
   timeoutSeconds: {{ .Values.probes.liveness.spec.timeoutSeconds }}
   periodSeconds: {{ .Values.probes.liveness.spec.periodSeconds }}
@@ -48,9 +54,12 @@ livenessProbe:
 startupProbe:
   exec:
     command:
-      - TODO: find a healthcheck
+      - /bin/bash
+      - -c
+      - |
+        ps -aux | grep -v grep | grep -q rqworker || exit 1
   initialDelaySeconds: {{ .Values.probes.startup.spec.initialDelaySeconds }}
   timeoutSeconds: {{ .Values.probes.startup.spec.timeoutSeconds }}
   periodSeconds: {{ .Values.probes.startup.spec.periodSeconds }}
-  failureThreshold: {{ .Values.probes.startup.spec.failureThreshold }}*/}}
+  failureThreshold: {{ .Values.probes.startup.spec.failureThreshold }}
 {{- end -}}

charts/incubator/netbox/values.yaml

@@ -14,13 +14,13 @@ podSecurityContext:
 probes:
   liveness:
     type: HTTP
-    path: /login
+    path: /api
   readiness:
     type: HTTP
-    path: /login
+    path: /api
   startup:
     type: HTTP
-    path: /login
+    path: /api
     # Gives some time for app to run db migrations
     initialDelaySeconds: 60