# Quick cluster health
kubectl get nodes
kubectl get pods -A | grep -v Running
kubectl get events -A --sort-by='.lastTimestamp' | tail -30

# Namespace health
kubectl get all -n <ns>
kubectl get events -n <ns> --sort-by='.lastTimestamp'
kubectl top pods -n <ns>

# Check exit code and reason
kubectl describe pod <pod> -n <ns> | grep -A10 "Last State"

# View logs from crashed container
kubectl logs <pod> -n <ns> --previous

# Check if OOMKilled
kubectl get pod <pod> -n <ns> -o jsonpath='{.status.containerStatuses[0].lastState.terminated.reason}'

# Increase memory if OOMKilled
kubectl set resources deployment/<name> -n <ns> --limits=memory=1Gi

# Disable liveness probe temporarily for debugging
kubectl edit deployment/<name> -n <ns>  # Remove livenessProbe

# Shell into running container to debug
kubectl exec -it <pod> -n <ns> -- /bin/sh

kubectl describe pod <pod> -n <ns> | grep -A5 "Events"
# Look for: "Failed to pull image" messages

# Verify image exists
docker pull <image>

# Check imagePullSecrets
kubectl get pod <pod> -n <ns> -o jsonpath='{.spec.imagePullSecrets}'

# Create registry secret
kubectl create secret docker-registry regcred \
  --docker-server=<registry> \
  --docker-username=<user> \
  --docker-password=<pass> \
  -n <ns>

# Add to deployment
kubectl patch deployment <name> -n <ns> -p '{"spec":{"template":{"spec":{"imagePullSecrets":[{"name":"regcred"}]}}}}'

kubectl describe pod <pod> -n <ns> | grep -A10 "Events"
# Look for scheduling failure reasons

# Check node resources
kubectl describe nodes | grep -A5 "Allocated resources"

# Check taints
kubectl get nodes -o custom-columns=NAME:.metadata.name,TAINTS:.spec.taints

# Check PVC status
kubectl get pvc -n <ns>

# Check resource quota
kubectl describe resourcequota -n <ns>

kubectl describe pod <pod> -n <ns> | grep -A5 "Warning"

# Check if configmap exists
kubectl get configmap <name> -n <ns>

# Check if secret exists
kubectl get secret <name> -n <ns>

# List expected volumes
kubectl get pod <pod> -n <ns> -o jsonpath='{.spec.volumes[*].name}'

kubectl describe pod <pod> -n <ns> | grep -A5 "Last State"
kubectl top pod <pod> -n <ns>

# Check limits
kubectl get pod <pod> -n <ns> -o jsonpath='{.spec.containers[0].resources}'

# Increase memory limit
kubectl set resources deployment/<name> -n <ns> --limits=memory=2Gi

# Or patch
kubectl patch deployment <name> -n <ns> --type='json' -p='[
  {"op":"replace","path":"/spec/template/spec/containers/0/resources/limits/memory","value":"2Gi"}
]'

# Check endpoints
kubectl get endpoints <service> -n <ns>
# Empty endpoints = selector mismatch or no ready pods

# Check service selector
kubectl get svc <service> -n <ns> -o jsonpath='{.spec.selector}'

# Check pod labels
kubectl get pods -n <ns> --show-labels

# Test from within cluster
kubectl run debug --rm -it --image=busybox -n <ns> -- wget -qO- <service>:<port>

# Fix selector
kubectl patch svc <service> -n <ns> -p '{"spec":{"selector":{"app":"correct-label"}}}'

# Check readiness
kubectl get pods -n <ns> -o wide  # Check READY column
kubectl describe pod <pod> -n <ns> | grep -A10 "Readiness"

# Test DNS from pod
kubectl run dns-test --rm -it --image=busybox -- nslookup kubernetes.default
kubectl run dns-test --rm -it --image=busybox -- nslookup <service>.<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

# Check ingress status
kubectl describe ingress <name> -n <ns>

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

# Verify backend service
kubectl get svc <backend-service> -n <ns>
kubectl get endpoints <backend-service> -n <ns>

kubectl describe pvc <name> -n <ns>
kubectl get storageclass
kubectl get pv

kubectl describe pod <pod> -n <ns> | grep -A10 "Volumes"
kubectl describe pod <pod> -n <ns> | grep -A10 "Mounts"
kubectl get events -n <ns> | grep -i volume

kubectl describe node <node> | grep -A10 "Conditions"
kubectl get events --field-selector involvedObject.name=<node>

# Check kubelet logs (on node)
journalctl -u kubelet -n 100

# Mark node unschedulable
kubectl cordon <node>

# Drain (evict pods)
kubectl drain <node> --ignore-daemonsets --delete-emptydir-data

# Uncordon
kubectl uncordon <node>

# Node resources
kubectl top nodes
kubectl describe nodes | grep -A5 "Allocated resources"

# Pod resources
kubectl top pods -n <ns> --sort-by=memory
kubectl top pods -n <ns> --sort-by=cpu

# Resource quotas
kubectl describe resourcequota -n <ns>
kubectl describe limitrange -n <ns>

# Top memory consumers
kubectl top pods -A --sort-by=memory | head -20

# Top CPU consumers
kubectl top pods -A --sort-by=cpu | head -20

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

# Add debug container to running pod
kubectl debug -it <pod> -n <ns> --image=busybox --target=<container>

# Debug with network tools
kubectl debug -it <pod> -n <ns> --image=nicolaka/netshoot --target=<container>

# Create copy with different command
kubectl debug <pod> -n <ns> --copy-to=debug-pod --container=<container> -- sleep infinity

# Then exec into it
kubectl exec -it debug-pod -n <ns> -- /bin/sh

# Network debugging
kubectl run netshoot --rm -it --image=nicolaka/netshoot -n <ns> -- /bin/bash

# Common debug commands inside:
curl -v http://<service>:<port>/
nslookup <service>
ping <pod-ip>
traceroute <service>
nc -zv <service> <port>

# Follow logs
kubectl logs -f <pod> -n <ns>

# All containers
kubectl logs <pod> -n <ns> --all-containers

# Previous container (after crash)
kubectl logs <pod> -n <ns> --previous

# Since time
kubectl logs <pod> -n <ns> --since=1h
kubectl logs <pod> -n <ns> --since-time="2024-01-01T00:00:00Z"

# Tail specific lines
kubectl logs <pod> -n <ns> --tail=100

# Multiple pods
kubectl logs -l app=<label> -n <ns> --all-containers

# With timestamps
kubectl logs <pod> -n <ns> --timestamps

# Namespace events
kubectl get events -n <ns> --sort-by='.lastTimestamp'

# Watch events
kubectl get events -n <ns> -w

# Filter warnings
kubectl get events -n <ns> --field-selector type=Warning

# Pod-specific events
kubectl get events -n <ns> --field-selector involvedObject.name=<pod>

#!/usr/bin/env bash
# k8s-diag.sh - Quick namespace diagnostic

NS="${1:?Usage: $0 <namespace>}"

echo "=== Namespace: $NS ==="
echo ""
echo "--- Pod Status ---"
kubectl get pods -n "$NS" -o wide
echo ""
echo "--- Non-Running Pods ---"
kubectl get pods -n "$NS" | grep -v Running | grep -v Completed
echo ""
echo "--- Recent Events ---"
kubectl get events -n "$NS" --sort-by='.lastTimestamp' | tail -20
echo ""
echo "--- Resource Usage ---"
kubectl top pods -n "$NS" 2>/dev/null || echo "Metrics not available"
echo ""
echo "--- Services ---"
kubectl get svc -n "$NS"
echo ""
echo "--- Endpoints ---"
kubectl get endpoints -n "$NS"