SIENTIAPDE-1478

Update sientia-mlops-library dependency to version 0.40.7 and modify liveness/readiness probes in values.yaml for improved health checks

requirements.txt

@@ -4,7 +4,7 @@ sqlalchemy
 asyncua
 redis
 git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.8.0
-git+ssh://git@github.com/Aignosi/sientia-mlops-library.git@0.40.6
+git+ssh://git@github.com/Aignosi/sientia-mlops-library.git@0.40.7
 prometheus-client
 botocore
 boto3

values.yaml

@@ -62,24 +62,32 @@ resources:
     cpu: 1000m  # 1 CPU core
     memory: 2Gi  # 2 GB memory
 
+# This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
 # This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
 livenessProbe:
   exec:
     command:
       - sh
       - -c
-      - pgrep -f "laborious.worker.worker"
-  initialDelaySeconds: 20
-  periodSeconds: 30
+      - |
+        curl -sf http://localhost:9090/metrics | grep -q '^app_up{.*} 1'
+  initialDelaySeconds: 30
+  periodSeconds: 15
+  timeoutSeconds: 5
+  failureThreshold: 3
 
 readinessProbe:
   exec:
     command:
       - sh
       - -c
-      - pgrep -f "laborious.worker.worker"
-  initialDelaySeconds: 10
-  periodSeconds: 15
+      - |
+        curl -sf http://localhost:9090/metrics | grep -q '^app_up{.*} 1'
+  initialDelaySeconds: 20
+  periodSeconds: 10
+  timeoutSeconds: 3
+  failureThreshold: 2
+
 
 
 # This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/