ET-6009 Add probes

xaynetwork · May 6, 2024 · 80604a4 · 80604a4
1 parent d983cfe
commit 80604a4
Show file tree

Hide file tree

Showing 3 changed files with 25 additions and 2 deletions.
diff --git a/charts/vllm-otc/Chart.yaml b/charts/vllm-otc/Chart.yaml
@@ -15,7 +15,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.2.0
+version: 0.3.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

diff --git a/charts/vllm-otc/templates/deployment.yaml b/charts/vllm-otc/templates/deployment.yaml
@@ -51,6 +51,10 @@ spec:
           resources:
             limits:
               "nvidia.com/gpu": "{{ .Values.gpus }}"
+          livenessProbe:
+{{ toYaml .Values.livenessProbe | indent 10 }}
+          startupProbe:
+{{ toYaml .Values.startupProbe | indent 10 }}
           volumeMounts:
             - name: huggingface-cache
               mountPath: /models

diff --git a/charts/vllm-otc/values.yaml b/charts/vllm-otc/values.yaml
@@ -51,7 +51,6 @@ service:
   type: ClusterIP
   port: 8000
 
-# TODO most likely a PV must not be inside the Helm chart
 pv:
   cryptKeyID: ""
   exportLocation: ""
@@ -73,3 +72,23 @@ tolerations:
   - key: "gpu-node"
     operator: "Exists"
     effect: "PreferNoSchedule"
+
+livenessProbe:
+  httpGet:
+    path: "/v1/models"
+    port: http
+    scheme: HTTP
+  initialDelaySeconds: 5
+  timeoutSeconds: 5
+  periodSeconds: 10
+  successThreshold: 1
+  failureThreshold: 3
+
+startupProbe:
+ httpGet:
+   path: "/v1/models"
+   port: http
+   scheme: HTTP
+ initialDelaySeconds: 30
+ periodSeconds: 10
+ failureThreshold: 60