Add liveness and readiness probes to API deployment (dask#256)

* Add liveness and readiness probes to API deployment

Co-authored-by: Alexander Perlman <alex@Alexanders-MacBook-Pro.local>

Author: droctothorpe

.gitignore

@@ -7,3 +7,4 @@ htmlcov/
 .cache/
 .pytest_cache/
 .DS_Store
+.vscode

resources/helm/dask-gateway/templates/gateway/deployment.yaml

@@ -57,3 +57,25 @@ spec:
           ports:
             - containerPort: 8000
               name: api
+
+          {{- if .Values.gateway.livenessProbe.enabled }}
+          livenessProbe:
+            httpGet:
+              path: /api/health
+              port: api
+            initialDelaySeconds: {{ .Values.gateway.livenessProbe.initialDelaySeconds }}
+            periodSeconds: {{ .Values.gateway.livenessProbe.periodSeconds }}
+            timeoutSeconds: {{ .Values.gateway.livenessProbe.timeoutSeconds }}
+            failureThreshold: {{ .Values.gateway.livenessProbe.failureThreshold }}
+          {{- end }}
+
+          {{- if .Values.gateway.readinessProbe.enabled }}
+          readinessProbe:
+            httpGet:
+              path: /api/health
+              port: api
+            initialDelaySeconds: {{ .Values.gateway.readinessProbe.initialDelaySeconds }}
+            periodSeconds: {{ .Values.gateway.readinessProbe.periodSeconds }}
+            timeoutSeconds: {{ .Values.gateway.readinessProbe.timeoutSeconds }}
+            failureThreshold: {{ .Values.gateway.readinessProbe.failureThreshold }}
+          {{- end }}

resources/helm/dask-gateway/values.yaml

@@ -54,6 +54,23 @@ gateway:
       # Configuration fields to set on the authenticator class.
       options: {}
 
+  livenessProbe:
+    # Enables the livenessProbe. 
+    enabled: true
+    # Configures the livenessProbe. 
+    initialDelaySeconds: 5
+    timeoutSeconds: 2
+    periodSeconds: 10
+    failureThreshold: 6
+  readinessProbe:
+    # Enables the readinessProbe.
+    enabled: true
+    # Configures the readinessProbe.
+    initialDelaySeconds: 5
+    timeoutSeconds: 2
+    periodSeconds: 10
+    failureThreshold: 3
+
   backend:
     # The image to use for both schedulers and workers.
     image: