Merge pull request #658 from kube-hetzner/staging

Further tweaks to placement group

agents.tf

@@ -15,7 +15,7 @@ module "agents" {
   ssh_private_key              = var.ssh_private_key
   ssh_additional_public_keys   = length(var.ssh_hcloud_key_label) > 0 ? concat(var.ssh_additional_public_keys, data.hcloud_ssh_keys.keys_by_selector[0].ssh_keys.*.public_key) : var.ssh_additional_public_keys
   firewall_ids                 = [hcloud_firewall.k3s.id]
-  placement_group_id           = var.placement_group_disable ? null : hcloud_placement_group.agent[floor((index(keys(local.agent_nodes), each.key) + 1) / 10)].id
+  placement_group_id           = var.placement_group_disable ? null : hcloud_placement_group.agent[floor(index(keys(local.agent_nodes), each.key) / 10)].id
   location                     = each.value.location
   server_type                  = each.value.server_type
   backups                      = each.value.backups

control_planes.tf

@@ -15,7 +15,7 @@ module "control_planes" {
   ssh_private_key              = var.ssh_private_key
   ssh_additional_public_keys   = length(var.ssh_hcloud_key_label) > 0 ? concat(var.ssh_additional_public_keys, data.hcloud_ssh_keys.keys_by_selector[0].ssh_keys.*.public_key) : var.ssh_additional_public_keys
   firewall_ids                 = [hcloud_firewall.k3s.id]
-  placement_group_id           = var.placement_group_disable ? null : hcloud_placement_group.control_plane[floor((index(keys(local.control_plane_nodes), each.key) + 1) / 10)].id
+  placement_group_id           = var.placement_group_disable ? null : hcloud_placement_group.control_plane[floor(index(keys(local.control_plane_nodes), each.key) / 10)].id
   location                     = each.value.location
   server_type                  = each.value.server_type
   backups                      = each.value.backups

init.tf

@@ -286,7 +286,7 @@ resource "null_resource" "kustomization" {
       # Wait for k3s to become ready (we check one more time) because in some edge cases,
       # the cluster had become unvailable for a few seconds, at this very instant.
       <<-EOT
-      timeout 180 bash <<EOF
+      timeout 360 bash <<EOF
         until [[ "\$(kubectl get --raw='/readyz' 2> /dev/null)" == "ok" ]]; do
           echo "Waiting for the cluster to become ready..."
           sleep 2
@@ -300,13 +300,13 @@ resource "null_resource" "kustomization" {
         # Ready, set, go for the kustomization
         "kubectl apply -k /var/post_install",
         "echo 'Waiting for the system-upgrade-controller deployment to become available...'",
-        "kubectl -n system-upgrade wait --for=condition=available --timeout=180s deployment/system-upgrade-controller",
-        "sleep 5", # important as the system upgrade controller CRDs sometimes don't get ready right away, especially with Cilium.
+        "kubectl -n system-upgrade wait --for=condition=available --timeout=360s deployment/system-upgrade-controller",
+        "sleep 7", # important as the system upgrade controller CRDs sometimes don't get ready right away, especially with Cilium.
         "kubectl -n system-upgrade apply -f /var/post_install/plans.yaml"
       ],
       local.has_external_load_balancer ? [] : [
         <<-EOT
-      timeout 180 bash <<EOF
+      timeout 360 bash <<EOF
       until [ -n "\$(kubectl get -n ${lookup(local.ingress_controller_namespace_names, local.ingress_controller)} service/${lookup(local.ingress_controller_service_names, local.ingress_controller)} --output=jsonpath='{.status.loadBalancer.ingress[0].${var.lb_hostname != "" ? "hostname" : "ip"}}' 2> /dev/null)" ]; do
           echo "Waiting for load-balancer to get an IP..."
           sleep 2