Initial commit

scripts/health-check.sh

@@ -0,0 +1,46 @@
+#!/bin/bash
+# Health check script for Kubernetes cluster
+
+echo "======================================"
+echo "  Kubernetes Cluster Health Check"
+echo "======================================"
+echo ""
+
+echo "=== Node Resources ==="
+kubectl top nodes 2>&1 || echo "❌ Metrics server not working!"
+echo ""
+
+echo "=== High Memory Nodes (>85%) ==="
+kubectl top nodes --no-headers | awk '$5 > 85 {print "⚠️  "$1" - "$5"% memory"}'
+echo ""
+
+echo "=== Pods without Resource Limits ==="
+COUNT=$(kubectl get pods -A -o json | jq -r '.items[] | select(.spec.containers[].resources.limits == null) | .metadata.namespace + "/" + .metadata.name' 2>/dev/null | wc -l)
+echo "$COUNT pods without resource limits"
+echo ""
+
+echo "=== Failing Pods ==="
+kubectl get pods -A --field-selector=status.phase!=Running,status.phase!=Succeeded 2>/dev/null | grep -v "No resources found" || echo "✅ All pods running"
+echo ""
+
+echo "=== HPA Status ==="
+kubectl get hpa -A 2>/dev/null | grep -v "No resources found" || echo "ℹ️  No HPAs configured"
+echo ""
+
+echo "=== Pods with High Restarts (>10) ==="
+kubectl get pods -A -o json | jq -r '.items[] | select(.status.containerStatuses != null) | select(.status.containerStatuses[].restartCount > 10) | .metadata.namespace + "/" + .metadata.name + " - " + (.status.containerStatuses[].restartCount|tostring) + " restarts"' 2>/dev/null || echo "✅ No pods with excessive restarts"
+echo ""
+
+echo "=== Storage Status ==="
+kubectl get pv | grep -c "Bound"
+echo "persistent volumes bound"
+echo ""
+
+echo "=== Ingress Status ==="
+kubectl get ingress -A | tail -n +2 | wc -l
+echo "ingresses configured"
+echo ""
+
+echo "======================================"
+echo "  Health Check Complete"
+echo "======================================"