feat: add monitoring script and update Helm templates for autoscaling and resource management

Author: tsviz

monitor-cluster-resources.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+
+# Script to monitor cluster resources during deployments
+# Usage: ./monitor-resources.sh
+
+echo "🔍 Monitoring AKS cluster resources..."
+echo "=================================="
+
+# Check node capacity and allocation
+echo "📊 Node Resource Capacity:"
+kubectl describe nodes | grep -E "(Name:|cpu:|memory:|Allocated resources)"
+
+echo ""
+echo "📈 Current Resource Usage:"
+kubectl top nodes 2>/dev/null || echo "❌ Metrics server not available. Install with: kubectl apply -f https://github.com/kubernetes-sigs/metrics-server/releases/latest/download/components.yaml"
+
+echo ""
+echo "🏃 Running Pods Resource Usage:"
+kubectl top pods --all-namespaces 2>/dev/null || echo "❌ Metrics server not available"
+
+echo ""
+echo "🎯 Resource Requests vs Limits by Namespace:"
+kubectl describe nodes | grep -A 10 "Allocated resources"
+
+echo ""
+echo "⚠️  Pending Pods (Resource constraints):"
+kubectl get pods --all-namespaces --field-selector=status.phase=Pending
+
+echo ""
+echo "🔄 Current Deployments Status:"
+kubectl get deployments --all-namespaces
+
+echo ""
+echo "📋 Horizontal Pod Autoscaler Status:"
+kubectl get hpa --all-namespaces
+
+echo ""
+echo "🛡️  Pod Disruption Budgets:"
+kubectl get pdb --all-namespaces

my-chart/templates/hpa.yaml

@@ -0,0 +1,63 @@
+{{- if .Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "my-chart.fullname" . }}-hpa-v1
+  labels:
+    {{- include "my-chart.labels" . | nindent 4 }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "my-chart.fullname" . }}-v1
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    {{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+    {{- end }}
+    {{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: memory
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    {{- end }}
+---
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "my-chart.fullname" . }}-hpa-v2
+  labels:
+    {{- include "my-chart.labels" . | nindent 4 }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "my-chart.fullname" . }}-v2
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    {{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+    {{- end }}
+    {{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: memory
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    {{- end }}
+{{- end }}

my-chart/templates/poddisruptionbudget.yaml

@@ -0,0 +1,38 @@
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: {{ include "my-chart.fullname" . }}-spring-app-pdb
+  labels:
+    {{- include "my-chart.labels" . | nindent 4 }}
+spec:
+  minAvailable: 1
+  selector:
+    matchLabels:
+      app: spring-app
+      {{- include "my-chart.selectorLabels" . | nindent 6 }}
+---
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: {{ include "my-chart.fullname" . }}-postgres-pdb
+  labels:
+    {{- include "my-chart.labels" . | nindent 4 }}
+spec:
+  minAvailable: 1
+  selector:
+    matchLabels:
+      app: postgres-database
+      {{- include "my-chart.selectorLabels" . | nindent 6 }}
+---
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: {{ include "my-chart.fullname" . }}-redis-pdb
+  labels:
+    {{- include "my-chart.labels" . | nindent 4 }}
+spec:
+  minAvailable: 1
+  selector:
+    matchLabels:
+      app: redis-database
+      {{- include "my-chart.selectorLabels" . | nindent 6 }}

my-chart/templates/spring-app-deployment-v1.yaml

@@ -6,6 +6,11 @@ metadata:
   {{- include "my-chart.labels" . | nindent 4 }}
 spec:
   replicas: {{ .Values.v1.replicas }}
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxSurge: 1
+      maxUnavailable: 0
   selector:
     matchLabels:
       app: spring-app
@@ -38,6 +43,22 @@ spec:
         name: spring-app-container
         ports:
         - containerPort: 8086
+        livenessProbe:
+          httpGet:
+            path: /actuator/health
+            port: 8086
+          initialDelaySeconds: 60
+          periodSeconds: 30
+          timeoutSeconds: 5
+          failureThreshold: 3
+        readinessProbe:
+          httpGet:
+            path: /actuator/health
+            port: 8086
+          initialDelaySeconds: 30
+          periodSeconds: 10
+          timeoutSeconds: 5
+          failureThreshold: 3
         resources:
           limits:
             cpu: {{ .Values.v1.springAppContainer.resources.limits.cpu }}

my-chart/templates/spring-app-deployment-v2.yaml

@@ -6,6 +6,11 @@ metadata:
   {{- include "my-chart.labels" . | nindent 4 }}
 spec:
   replicas: {{ .Values.v2.replicas }}
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxSurge: 1
+      maxUnavailable: 0
   selector:
     matchLabels:
       app: spring-app
@@ -36,6 +41,22 @@ spec:
         name: spring-app-container
         ports:
         - containerPort: 8086
+        livenessProbe:
+          httpGet:
+            path: /actuator/health
+            port: 8086
+          initialDelaySeconds: 60
+          periodSeconds: 30
+          timeoutSeconds: 5
+          failureThreshold: 3
+        readinessProbe:
+          httpGet:
+            path: /actuator/health
+            port: 8086
+          initialDelaySeconds: 30
+          periodSeconds: 10
+          timeoutSeconds: 5
+          failureThreshold: 3
         resources:
           limits:
             cpu: {{ .Values.v2.springAppContainer.resources.limits.cpu }}

my-chart/values.yaml

@@ -1,5 +1,18 @@
+# Rolling update configuration
+rollingUpdate:
+  maxSurge: 1
+  maxUnavailable: 0
+
+# Horizontal Pod Autoscaler configuration
+autoscaling:
+  enabled: true
+  minReplicas: 2
+  maxReplicas: 6
+  targetCPUUtilizationPercentage: 70
+  targetMemoryUtilizationPercentage: 80
+  
 v1:
-  replicas: 1
+  replicas: 2  # Increased for better availability during updates
   springAppContainer:
     env:
       changelogVersion: changelog_version-3.3.xml
@@ -14,10 +27,10 @@ v1:
     resources:
       limits:
         cpu: "1"
-        memory: 512Mi
+        memory: 768Mi  # Increased memory limit
       requests:
-        cpu: 125m
-        memory: 128Mi
+        cpu: 250m      # Increased CPU request for better performance
+        memory: 256Mi  # Increased memory request
 v2:
   replicas: 2
   springAppContainer:
@@ -34,10 +47,10 @@ v2:
     resources:
       limits:
         cpu: "1"
-        memory: 512Mi
+        memory: 768Mi  # Increased memory limit
       requests:
-        cpu: 125m
-        memory: 128Mi
+        cpu: 250m      # Increased CPU request for better performance
+        memory: 256Mi  # Increased memory request
 kubernetesClusterDomain: cluster.local
 postgresConfig:
   POSTGRES_DB: postgresdb

src/main/resources/application.properties

@@ -15,4 +15,4 @@ spring.redis.port=6379
 # spring.data.jpa.repositories.enabled=false
 # spring.jpa.hibernate.naming.physical-strategy=org.hibernate.boot.model.naming.PhysicalNamingStrategyStandardImpl
 spring.jpa.hibernate.ddl-auto=none
-enableSearchFeature=false
+enableSearchFeature=true