baremetal: run copy-controller-secrets step after recreating the node

Author: pothos

assets/terraform-modules/matchbox-flatcar/pxe-helper.sh.tmpl

@@ -3,7 +3,10 @@
 name=${name}
 domain=${domain}
 mac=${mac}
-asset_dir=${asset_dir}
+asset_dir="${asset_dir}"
+kernel_args="${kernel_args}"
+kernel_console="${kernel_console}"
+ignition_endpoint="${ignition_endpoint}"
 type=${type}
 # From now on use $var for dynamic shell substitution
 
@@ -20,6 +23,7 @@ if [ $node_exists = yes ]; then
     echo "Keeping old config because replacing a controller node is not safe"
     exit 0
   else
+    # run single commands that can be retried without a side effect in case the connection got disrupted
     count=30
     while [ $count -gt 0 ] && ! ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o NumberOfPasswordPrompts=0 core@$domain sudo touch /boot/flatcar/first_boot; do
       sleep 1
@@ -31,6 +35,15 @@ if [ $node_exists = yes ]; then
     fi
     echo "created the first_boot flag file to reprovision $domain"
     count=5
+    while [ $count -gt 0 ] && ! ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o NumberOfPasswordPrompts=0 core@$domain "printf 'set linux_append=\"$kernel_args ignition.config.url=$ignition_endpoint?mac=$mac&os=installed\"\\nset linux_console=\"$kernel_console\"\\n' | sudo tee /usr/share/oem/grub.cfg"; do
+      sleep 1
+      count=$((count - 1))
+    done
+    if [ $count -eq 0 ]; then
+      echo "error reaching $domain via SSH, please retry"
+      exit 1
+    fi
+    count=5
     while [ $count -gt 0 ] && ! ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o NumberOfPasswordPrompts=0 core@$domain sudo systemctl reboot; do
       sleep 1
       count=$((count - 1))

assets/terraform-modules/matchbox-flatcar/ssh.tf

@@ -7,6 +7,6 @@ resource "null_resource" "reprovision-node-when-ignition-changes" {
   depends_on = [matchbox_group.node]
   # Trigger running Ignition on the next reboot (first_boot flag file) and reboot the instance, or, if the instance needs to be (re)provisioned, run external commands for PXE booting (also runs on the first provisioning)
   provisioner "local-exec" {
-    command = templatefile("${path.module}/pxe-helper.sh.tmpl", { domain = var.node_domain, name = var.node_name, mac = var.node_mac, pxe_commands = var.pxe_commands, asset_dir = var.asset_dir, type = "node" })
+    command = templatefile("${path.module}/pxe-helper.sh.tmpl", { domain = var.node_domain, name = var.node_name, mac = var.node_mac, pxe_commands = var.pxe_commands, asset_dir = var.asset_dir, kernel_args = join(" ", var.kernel_args), kernel_console = join(" ", var.kernel_console), ignition_endpoint = format("%s/ignition", var.http_endpoint), type = "node" })
   }
 }