#!/bin/bash
# cluster-health-check.sh
echo "=== CLUSTER HEALTH ASSESSMENT ==="

# 1. Node Health (Critical)
echo "### NODE HEALTH ###"
kubectl get nodes -o wide | grep -E "NotReady|Unknown" && \
  echo "BOOM: Unhealthy nodes detected!" || echo "✓ All nodes healthy"

# 2. Pod Issues (Critical)
echo -e "\n### POD HEALTH ###"
POD_ISSUES=$(kubectl get pods -A --field-selector=status.phase!=Running,status.phase!=Succeeded --no-headers | wc -l)
if [ $POD_ISSUES -gt 0 ]; then
    echo "WARN: $POD_ISSUES pods not running"
    kubectl get pods -A --field-selector=status.phase!=Running,status.phase!=Succeeded
else
    echo "✓ All pods running"
fi

# 3. Security (Critical)
echo -e "\n### SECURITY ASSESSMENT ###"
PRIVILEGED=$(kubectl get pods -A -o json | jq -r '.items[] | select(.spec.containers[].securityContext.privileged == true) | "\(.metadata.namespace)/\(.metadata.name)"' | wc -l)
[ $PRIVILEGED -gt 0 ] && echo "BOOM: $PRIVILEGED privileged containers!" || echo "✓ No privileged containers"

# 4. Resource Configuration (Warning)
echo -e "\n### RESOURCE CONFIGURATION ###"
NO_LIMITS=$(kubectl get pods -A -o json | jq -r '.items[] | select(.spec.containers[].resources.limits == null) | "\(.metadata.namespace)/\(.metadata.name)"' | wc -l)
[ $NO_LIMITS -gt 0 ] && echo "WARN: $NO_LIMITS containers without limits" || echo "✓ All have limits"

# 5. Storage (Warning)
echo -e "\n### STORAGE HEALTH ###"
PENDING_PVC=$(kubectl get pvc -A --field-selector=status.phase!=Bound --no-headers | wc -l)
[ $PENDING_PVC -gt 0 ] && echo "WARN: $PENDING_PVC PVCs not bound" || echo "✓ All PVCs bound"

# OpenShift: Cluster Operators
if command -v oc &> /dev/null; then
    echo -e "\n### OPENSHIFT OPERATORS ###"
    DEGRADED=$(oc get clusteroperators --no-headers | grep -c -E "False.*True|False.*False")
    [ $DEGRADED -gt 0 ] && echo "BOOM: $DEGRADED operators degraded!" || echo "✓ All operators healthy"
fi

# Pod status overview
kubectl get pods -n ${NAMESPACE} -o wide

# Recent events (sorted by time)
kubectl get events -n ${NAMESPACE} --sort-by='.lastTimestamp'

# Pod details and events
kubectl describe pod ${POD_NAME} -n ${NAMESPACE}

# Container logs (current)
kubectl logs ${POD_NAME} -n ${NAMESPACE} -c ${CONTAINER}

# Container logs (previous crashed instance)
kubectl logs ${POD_NAME} -n ${NAMESPACE} -c ${CONTAINER} --previous

# Multi-pod log streaming
stern -n ${NAMESPACE} ${POD_PREFIX}
stern -A -l app=${APP_NAME} --since 1h

# Node status
kubectl get nodes -o wide
kubectl describe node ${NODE_NAME}

# Resource usage
kubectl top pods -n ${NAMESPACE}
kubectl top nodes

"Insufficient cpu"           → Reduce requests or add capacity
"Insufficient memory"        → Reduce requests or add capacity
"node(s) had taint"          → Add toleration or remove taint
"node(s) didn't match selector" → Fix nodeSelector/affinity
"persistentvolumeclaim not found" → Create PVC or fix name

# Check image name
kubectl get pod ${POD} -o jsonpath='{.spec.containers[*].image}'

# Verify ImagePullSecrets
kubectl get pod ${POD} -o jsonpath='{.spec.imagePullSecrets}'
kubectl get secret ${SECRET} -n ${NAMESPACE}

kubectl describe pvc ${PVC_NAME} -n ${NAMESPACE}
kubectl get storageclass
kubectl get pv

# Search for errors
kubectl logs ${POD} -n ${NS} | grep -iE "(error|exception|fatal|panic)"

# Java OOM
java.lang.OutOfMemoryError → Increase memory, tune JVM heap

# Connection refused
ECONNREFUSED, Connection refused → Dependency not available

# DNS failure
ENOTFOUND, getaddrinfo → DNS resolution failed, check service name

# Permission denied
Permission denied → Check securityContext, runAsUser, fsGroup

Last State: Terminated
Reason: OOMKilled
Exit Code: 137

→ Solutions:
1. Increase memory limit
2. Profile application memory usage
3. For JVM: Set -Xmx < container limit (leave ~25% headroom)

kubectl describe node ${NODE_NAME}

# On the node (SSH or debug)
systemctl status kubelet
journalctl -u kubelet -f

# Check resources
df -h
free -m
top

# Test DNS resolution
kubectl run dns-test --image=busybox:1.28 --rm -it --restart=Never -- \
  nslookup ${SERVICE_NAME}.${NAMESPACE}.svc.cluster.local

# Check CoreDNS
kubectl get pods -n kube-system -l k8s-app=kube-dns
kubectl logs -n kube-system -l k8s-app=kube-dns

# Verify service and endpoints
kubectl get svc ${SERVICE} -n ${NS}
kubectl get endpoints ${SERVICE} -n ${NS}

# Test from debug pod
kubectl run curl-test --image=curlimages/curl --rm -it --restart=Never -- \
  curl -v http://${SERVICE}.${NS}.svc.cluster.local:${PORT}

# Check Ingress
kubectl describe ingress ${INGRESS} -n ${NS}

# Ingress controller logs
kubectl logs -n ingress-nginx -l app.kubernetes.io/name=ingress-nginx

# OpenShift Route
oc describe route ${ROUTE} -n ${NS}
oc get pods -n openshift-ingress

# Check overall health
oc get clusteroperators

# Investigate degraded operator
oc describe clusteroperator ${OPERATOR}
oc logs -n openshift-${OPERATOR} -l name=${OPERATOR}-operator

# List SCCs
oc get scc

# Check which SCC a pod is using
oc get pod ${POD} -n ${NS} -o yaml | grep scc

# Common error fix
# "unable to validate against any security context constraint"
oc adm policy add-scc-to-user ${SCC} -z ${SERVICE_ACCOUNT} -n ${NS}

# Check build status
oc get builds -n ${NS}
oc describe build ${BUILD} -n ${NS}
oc logs build/${BUILD} -n ${NS}

aws eks describe-cluster --name ${CLUSTER} --query 'cluster.status'
aws eks describe-addon --cluster-name ${CLUSTER} --addon-name vpc-cni
eksctl get nodegroup --cluster ${CLUSTER}

az aks show --resource-group ${RG} --name ${CLUSTER} --query provisioningState
az aks check-network outbound --resource-group ${RG} --name ${CLUSTER}

gcloud container clusters describe ${CLUSTER} --region ${REGION} --format='value(status)'
gcloud container operations list --filter="targetLink:${CLUSTER}" --limit=10

Pod Phase = Pending?
├── Yes → Check Scheduling
│   ├── "Insufficient cpu/memory" → Add nodes or reduce requests
│   ├── "node(s) had taint" → Add toleration
│   ├── "PVC not found" → Create PVC
│   └── No events → Check API server
│
└── No → Check Container Status
    ├── ImagePullBackOff → Fix image name/auth
    ├── CrashLoopBackOff → Check logs --previous
    ├── CreateContainerConfigError → Fix ConfigMap/Secret
    └── Running but not ready → Check readiness probe

Can reach Service?
├── No → Check Service
│   ├── No endpoints → Fix selector labels
│   ├── Wrong port → Fix targetPort
│   └── NetworkPolicy blocking → Adjust policy
│
└── Yes → Check Pod
    ├── Probe failing → Fix probe or application
    ├── High latency → Check resources, dependencies
    └── Errors in logs → Fix application

# Compare usage vs requests
kubectl top pods -n ${NS}

kubectl get pods -n ${NS} -o custom-columns=\
NAME:.metadata.name,\
CPU_REQ:.spec.containers[*].resources.requests.cpu,\
MEM_REQ:.spec.containers[*].resources.requests.memory

# Find pods without limits
kubectl get pods -A -o json | jq -r \
  '.items[] | select(.spec.containers[].resources.limits == null) |
   "\(.metadata.namespace)/\(.metadata.name)"'