How to fix API server timeout in Kubernetes

# For kubeadm clusters:
sudo docker logs -f kube-apiserver  # Check for errors

# Or via kubelet:
sudo journalctl -u kubelet -f

# Or via systemd:
sudo journalctl -u kube-apiserver -f

# SSH to control plane
top -p $(pgrep kube-apiserver)  # Real-time usage

# Check connection count:
ss -tunap | grep 6443

# Or use Prometheus if available:
kubectl port-forward -n kube-system svc/prometheus 9090:9090
# Then view: http://localhost:9090
# Query: apiserver_request_duration_seconds

# Check how many API calls are happening:
kubectl top nodes --all-namespaces

# If operators/controllers are making excessive requests:
kubectl get events --all-namespaces --sort-by=.metadata.creationTimestamp

# Identify noisy pods/controllers:
kubectl logs -n kube-system deployment/your-controller --tail=100

# Reduce custom controller reconciliation frequency:
# Edit your controller deployment and increase resyncPeriod
# Example: change resyncPeriod from 10s to 60s

# SSH to control plane
sudo docker exec etcd etcdctl endpoint health

# Check database size:
sudo docker exec etcd etcdctl endpoint status

# For large databases, run defrag:
sudo docker exec etcd etcdctl defrag

# SSH to a worker node
ping -c 5 <control-plane-ip>

# Test TCP connection to API server:
telnet <control-plane-ip> 6443

# Check network policy:
kubectl get networkpolicies --all-namespaces

# Measure latency:
time curl -k https://<control-plane-ip>:6443/api/v1 --cert /etc/kubernetes/pki/apiserver-kubelet-client.crt --key /etc/kubernetes/pki/apiserver-kubelet-client.key

# For kubeadm, edit API server pod manifest:
sudo nano /etc/kubernetes/manifests/kube-apiserver.yaml

# Add or modify:
apiVersion: v1
kind: Pod
metadata:
  name: kube-apiserver
  namespace: kube-system
spec:
  containers:
  - name: kube-apiserver
    command:
    - kube-apiserver
    - --request-timeout=90s      # Increase from 60s
    - --min-request-timeout=10s  # Minimum for watch requests

kubectl get pod -n kube-system kube-apiserver-<node> -o yaml | grep request-timeout

# List webhooks:
kubectl get validatingwebhookconfigurations
kubectl get mutatingwebhookconfigurations

# Check webhook timeout:
kubectl get validatingwebhookconfigurations -o yaml | grep timeoutSeconds

# Temporarily disable problematic webhook:
kubectl delete validatingwebhookconfigurations <webhook-name>

# If you need to keep it, increase timeout:
kubectl patch validatingwebhookconfigurations <webhook-name> --type='json' -p='[{"op": "replace", "path": "/webhooks/0/timeoutSeconds", "value":30}]'

# Check control plane node resources:
kubectl describe node <control-plane-node> | grep -A 10 "Allocated resources"

# Minimum recommendations:
# - CPU: 2+ cores (4+ for production)
# - RAM: 4GB minimum (8GB+ recommended)
# - Disk: 50GB+ for etcd

# Check actual usage:
kubectl top node <control-plane-node>

# For cloud clusters (EKS, AKS, GKE):
# - Verify control plane tier (standard, ha)
# - Scale up control plane if needed

# SSH to a node
kubectl describe node <node-name> | grep -A 5 "Conditions"

# Test kubelet connectivity from node:
curl -k --key /var/lib/kubelet/pki/kubelet-client-current.pem --cert /var/lib/kubelet/pki/kubelet-client-current.pem https://<api-server>:6443/api/v1

# Check kubelet logs:
sudo journalctl -u kubelet --tail=100

# Restart kubelet if stuck:
sudo systemctl restart kubelet