fixing traefik chart deployment!

.gitignore

@@ -1 +1,2 @@
 .env.local
+traefik-values.yaml

01_Basic_Setup/justfile

@@ -157,39 +157,65 @@ stop:
         echo "$(($(date +%s) - START_TIME))s"
     }
     nodenames=$(kubectl get nodes -o=jsonpath="{.items[*]['metadata.name']}")
-    # for node in ${nodenames}; do
+    for node in ${nodenames}; do
-    #     kubectl drain "${node}" --ignore-daemonsets --delete-emptydir-data --force --disable-eviction --grace-period=60 --timeout=180s 2>&1 || true
+        kubectl drain "${node}" --ignore-daemonsets --delete-emptydir-data --force --disable-eviction --grace-period=60 --timeout=180s 2>&1 || true
-    #     kubectl cordon "${node}"
+        kubectl cordon "${node}"
-    #     echo "Node ${node} stopped."
+        echo "Node ${node} stopped."
-    # done
+    done
-    # echo "Drain complete. Nodes are cordoned and drained."
+    echo "Drain complete. Nodes are cordoned and drained."
 
-    # if helm status longhorn -n ${LONGHORN_NAMESPACE} &>/dev/null; then
+    if helm status longhorn -n ${LONGHORN_NAMESPACE} &>/dev/null; then
-    #     echo "[$(elapsed)] Waiting for Longhorn volumes to be detached..."
+        echo "[$(elapsed)] Waiting for Longhorn volumes to be detached..."
-    #     TIMEOUT=90
+        TIMEOUT=90
-    #     ELAPSED=0
+        ELAPSED=0
-    #     while [ $ELAPSED -lt $TIMEOUT ]; do
+        while [ $ELAPSED -lt $TIMEOUT ]; do
 
-    #         ATTACHED=$(kubectl get volumes.longhorn.io -n ${LONGHORN_NAMESPACE} -o json 2>/dev/null | \
+            ATTACHED=$(kubectl get volumes.longhorn.io -n ${LONGHORN_NAMESPACE} -o json 2>/dev/null | \
-    #             jq -r '.items[] | select(.status.state == "attached") | .metadata.name' 2>/dev/null || true)
+                jq -r '.items[] | select(.status.state == "attached") | .metadata.name' 2>/dev/null || true)
 
-    #         if [ -z "$ATTACHED" ]; then
+            if [ -z "$ATTACHED" ]; then
-    #             echo "[$(elapsed)] ✓ All Longhorn volumes detached successfully"
+                echo "[$(elapsed)] ✓ All Longhorn volumes detached successfully"
-    #             break
+                break
-    #         fi
+            fi
 
-    #         ATTACHED_COUNT=$(echo "$ATTACHED" | grep -c . || echo 0)
+            ATTACHED_COUNT=$(echo "$ATTACHED" | grep -c . || echo 0)
-    #         echo "  Still waiting for $ATTACHED_COUNT volume(s) to detach..."
+            echo "  Still waiting for $ATTACHED_COUNT volume(s) to detach..."
-    #         sleep 2
+            sleep 2
-    #         ELAPSED=$((ELAPSED + 2))
+            ELAPSED=$((ELAPSED + 2))
-    #     done
+        done
-    #     if [ $ELAPSED -ge $TIMEOUT ]; then
+        if [ $ELAPSED -ge $TIMEOUT ]; then
-    #         echo "[$(elapsed)] ⚠ Warning: Timeout waiting for volumes to detach"
+            echo "[$(elapsed)] ⚠ Warning: Timeout waiting for volumes to detach"
-    #     fi
+        fi
-    # fi
+    fi
 
     for node in ${nodenames}; do
         echo "[$(elapsed)] Stopping and disabling k3s service..."
         ssh "${node}" "sudo systemctl stop k3s 2>/dev/null || true"
         ssh "${node}" "sudo systemctl disable k3s 2>/dev/null || true"
+    done
+
+start:
+    #!/bin/bash
+    set -euo pipefail
+    
+    is_schedulable() {
+        node_name="$1"
+        ! kubectl get node "$node_name" -o jsonpath='{.spec.unschedulable}' 2>/dev/null | grep -q "true"
+    }
+    
+    nodenames=$(kubectl get nodes -o=jsonpath="{.items[*]['metadata.name']}")
+
+
+    for node in ${nodenames}; do
+        echo "Starting k3s service on ${node}..."
+
+        if is_schedulable "$node"; then
+            echo "✓ Node $node is already schedulable"
+            exit 0
+        fi
+
+        echo "Uncordoning node $node..."
+        kubectl uncordon "$node" 2>&1 || true
+
+        echo "Wait for every node to become Ready..."
     done

07_KubePrometheusStack/justfile

@@ -24,15 +24,19 @@ install:
         --wait \
         -f kube-stack-config-values.yaml
 
-    echo "kubectl port-forward svc/kube-prometheus-stack-grafana 8080:80 -n ${PROMETHEUS_NAMESPACE}"
+    just KubePrometheusStack::show-ports
-    echo "kubectl port-forward svc/kube-prometheus-stack-prometheus 9090 -n ${PROMETHEUS_NAMESPACE}"
-    echo "kubectl port-forward svc/kube-prometheus-stack-alertmanager 9093 -n ${PROMETHEUS_NAMESPACE}"
-
-    echo "Get Grafana Password:"
-    echo "kubectl get secret --namespace monitoring -l app.kubernetes.io/component=admin-secret -o jsonpath=\"{.items[0].data.admin-password}\" | base64 --decode ; echo"
 
     gomplate -f ./grafana-certificate.gomplate.yaml | kubectl apply -f -
 
 
 uninstall:
-    helm uninstall kube-prometheus-stack -n ${PROMETHEUS_NAMESPACE}
+    helm uninstall kube-prometheus-stack -n ${PROMETHEUS_NAMESPACE}
+
+show-ports:
+    @echo "kubectl port-forward svc/kube-prometheus-stack-grafana 8080:80 -n ${PROMETHEUS_NAMESPACE}"
+    @echo "kubectl port-forward svc/kube-prometheus-stack-prometheus 9090 -n ${PROMETHEUS_NAMESPACE}"
+    @echo "kubectl port-forward svc/kube-prometheus-stack-alertmanager 9093 -n ${PROMETHEUS_NAMESPACE}"
+
+    @echo "Get Grafana Password:"
+    @echo "kubectl get secret --namespace monitoring -l app.kubernetes.io/component=admin-secret -o jsonpath=\"{.items[0].data.admin-user}\" | base64 --decode ; echo"
+    @echo "kubectl get secret --namespace monitoring -l app.kubernetes.io/component=admin-secret -o jsonpath=\"{.items[0].data.admin-password}\" | base64 --decode ; echo"

Traefik/justfile

@@ -2,6 +2,7 @@ set fallback:=true
 
 export CERT_MANAGER_NAMESPACE := env("CERT_MANAGER_NAMESPACE", "cert-manager")
 export TRAEFIK_NAMESPACE := env("TRAEFIK_NAMESPACE", "traefik")
+export TRAEFIK_CHART_VERSION := env("TRAEFIK_CHART_VERSION", "v39.0.7")
 
 add-helm-repos:
     helm repo add traefik https://helm.traefik.io/traefik --force-update
@@ -15,11 +16,14 @@ install:
 
     just add-helm-repos
 
+    gomplate -f traefik-values-gomplate.yaml -o traefik-values.yaml
+
     helm upgrade traefik traefik/traefik \
      --install \
      --cleanup-on-fail \
      --namespace ${TRAEFIK_NAMESPACE} \
      --create-namespace \
+     --version ${TRAEFIK_CHART_VERSION} \
      --values traefik-values.yaml
 
     helm upgrade cert-manager jetstack/cert-manager \
@@ -59,4 +63,9 @@ status:
     kubectl get services -n ${CERT_MANAGER_NAMESPACE}
     echo ""
     echo "CRDs:"
-    kubectl get crd | grep cert-manager.io
+    kubectl get crd | grep cert-manager.io
+
+ingressroute:
+    #!/bin/bash
+    set -euo pipefail
+    gomplate -f traefik-ingressroute-gomplate.yaml | kubectl apply -f -

Traefik/traefik-values-gomplate.yaml

@@ -1,15 +1,33 @@
+additionalArguments:
+  - "--serversTransport.insecureSkipVerify=true"
+  - "--log.level=INFO"
+
+deployment:
+  enabled: true
+  replicas: 1
+  annotations: {}
+  podAnnotations: {}
+  additionalContainers: []
+  initContainers: []
+
 ports:
   web:
-    redirections:
+    http:
-      entryPoint:
+      redirections:
-        to: websecure
+        entryPoint: 
-        scheme: https 
+          to: websecure
+  websecure:
+    http:
+      tls:
+        enabled: true
+
 logs:
   general:
     level: DEBUG
+
 ingressRoute:
   dashboard:
     enabled: true
-    entryPoints: [web, websecure]
     matchRule: Host(`traefik-dashboard.{{ .Env.EXTERNAL_DOMAIN }}`)
-      
+    entryPoints:
+      - websecure