K3S Guide

Got it 👍 You want a practice note / guide to learn k3s with a demo.
Here’s a step-by-step note you can follow to get hands-on quickly:

---

📝 k3s Practice Note (Demo Setup)

1. What is k3s?

• k3s = lightweight Kubernetes (by Rancher/ SUSE).
• Perfect for local testing, small clusters, IoT, edge, CI/CD.
• Single binary, very easy to install.

---

2. Prerequisites

• A Linux server (VM, VPS, or local with Docker/Multipass).

  • Ubuntu 20.04+ or CentOS 8 recommended.

• At least 2 vCPU, 2GB RAM, 10GB disk.

• Root or sudo access.

---

3. Install k3s (Server Node)

On your node (VM / VPS):

curl -sfL https://get.k3s.io | sh -

Check status:

systemctl status k3s

Check cluster nodes:

kubectl get nodes

👉 By default, kubectl is already installed and configured (/etc/rancher/k3s/k3s.yaml).

---

4. Deploy a Demo App

Let’s deploy nginx to test the cluster.

kubectl create deployment demo-nginx --image=nginx --replicas=2
kubectl expose deployment demo-nginx --type=NodePort --port=80

Check resources:

kubectl get pods
kubectl get svc

Find NodePort service (e.g., 30000-32767).
Access in browser:

http://<server-ip>:<nodeport>

---

5. (Optional) Add Worker Nodes

On another Linux machine, run (replace <token> and <server-ip>):

curl -sfL https://get.k3s.io | K3S_URL=https://<server-ip>:6443 K3S_TOKEN=<token> sh -

Find token on master:

cat /var/lib/rancher/k3s/server/node-token

Check cluster:

kubectl get nodes

---

6. Try Scaling the App

kubectl scale deployment demo-nginx --replicas=5
kubectl get pods -o wide

---

7. Cleanup

Remove k3s:

/usr/local/bin/k3s-uninstall.sh

---

✅ Practice Checklist

• Install k3s server
• Verify cluster (kubectl get nodes)
• Deploy nginx demo app
• Expose service (NodePort)
• Scale deployment
• (Optional) Add worker node

---

Perfect 👌 You already learned how to deploy a simple app with NodePort — now let’s step it up with an Ingress (which is the “Kubernetes way” to expose apps).

Here’s a practice note for a simple Ingress demo in k3s:

---

📝 Practising Ingress in k3s

1. Background

• Ingress lets you expose HTTP/HTTPS routes to services inside your cluster.
• In normal Kubernetes, you need to install an Ingress Controller (like Nginx).
• In k3s, the Traefik Ingress Controller is already built-in 🎉 (enabled by default).

---

2. Create a Test Deployment & Service

Let’s make two apps so you can see how Ingress routes traffic.

App 1: app1

kubectl create deployment app1 --image=nginx
kubectl expose deployment app1 --port=80

App 2: app2

kubectl create deployment app2 --image=httpd
kubectl expose deployment app2 --port=80

Check:

kubectl get svc

---

3. Create an Ingress Resource

Make a YAML file demo-ingress.yaml:

apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: demo-ingress
  annotations:
    kubernetes.io/ingress.class: "traefik"
spec:
  rules:
  - host: app1.local
    http:
      paths:
      - path: /
        pathType: Prefix
        backend:
          service:
            name: app1
            port:
              number: 80
  - host: app2.local
    http:
      paths:
      - path: /
        pathType: Prefix
        backend:
          service:
            name: app2
            port:
              number: 80

Apply it:

kubectl apply -f demo-ingress.yaml

---

4. Test the Ingress

Find your server IP:

kubectl get nodes -o wide

Edit your local machine’s hosts file (/etc/hosts on Linux/Mac, C:\Windows\System32\drivers\etc\hosts on Windows) and add:

<server-ip>  app1.local
<server-ip>  app2.local

Now test in browser or curl:

curl http://app1.local
curl http://app2.local

You should see nginx page for app1 and Apache httpd page for app2.

---

5. Cleanup

kubectl delete ingress demo-ingress
kubectl delete svc app1 app2
kubectl delete deployment app1 app2

---

✅ Ingress Practice Checklist

• Deploy two apps (nginx + httpd)
• Create services for them
• Write an Ingress with host-based routing
• Edit /etc/hosts to resolve test domains
• Verify with curl or browser

---

Sure! Here's a clear, practical UFW example for a small k3s cluster with 1 server, 1 worker, and ingress:

---

🛡️ UFW Rules for k3s Cluster

1. Server Node (control-plane + ingress)

# k3s control-plane
ufw allow 6443/tcp       # Kubernetes API server
ufw allow 8472/udp       # Flannel VXLAN networking (pod network)
ufw allow 10250/tcp      # Kubelet API

# NodePort / LoadBalancer / Ingress traffic
ufw allow 30000:32767/tcp  # NodePort range
ufw allow 80/tcp           # HTTP (Ingress)
ufw allow 443/tcp          # HTTPS (Ingress)

---

2. Worker Node

# Needed to join the cluster and run pods
ufw allow 10250/tcp      # Kubelet API
ufw allow 8472/udp       # Flannel VXLAN networking (pod network)

# NodePort / Ingress traffic
ufw allow 30000:32767/tcp  # NodePort range
ufw allow 80/tcp           # HTTP (Ingress)
ufw allow 443/tcp          # HTTPS (Ingress)

---

3. Optional: etcd / HA setup

If you later set up multi-server high-availability, also open on server nodes:

ufw allow 2379:2380/tcp  # etcd client/peer communication

---

4. Enable UFW (if not already)

ufw enable
ufw status

---

✅ Summary

• Server: open control-plane ports + NodePort + ingress
• Worker: open kubelet & networking + NodePort + ingress
• Ingress: traffic comes through NodePort or 80/443

---