Merge pull request #1284 from kube-hetzner/tweak/autoscaler-timeout

Tweak autoscaler creation timeout

Author: mysticaltech

autoscaler-agents.tf

@@ -27,21 +27,21 @@ locals {
   autoscaler_yaml = length(var.autoscaler_nodepools) == 0 ? "" : templatefile(
     "${path.module}/templates/autoscaler.yaml.tpl",
     {
-      cloudinit_config                    = local.isUsingLegacyConfig ? base64encode(data.cloudinit_config.autoscaler_legacy_config[0].rendered) : ""
-      ca_image                            = var.cluster_autoscaler_image
-      ca_version                          = var.cluster_autoscaler_version
-      cluster_autoscaler_extra_args       = var.cluster_autoscaler_extra_args
-      cluster_autoscaler_log_level        = var.cluster_autoscaler_log_level
-      cluster_autoscaler_log_to_stderr    = var.cluster_autoscaler_log_to_stderr
-      cluster_autoscaler_stderr_threshold = var.cluster_autoscaler_stderr_threshold
-      cluster_autoscaler_server_creation_timeout = var.cluster_autoscaler_server_creation_timeout
-      ssh_key                             = local.hcloud_ssh_key_id
-      ipv4_subnet_id                      = data.hcloud_network.k3s.id
-      snapshot_id                         = local.first_nodepool_snapshot_id
-      cluster_config                      = base64encode(jsonencode(local.cluster_config))
-      firewall_id                         = hcloud_firewall.k3s.id
-      cluster_name                        = local.cluster_prefix
-      node_pools                          = var.autoscaler_nodepools
+      cloudinit_config                           = local.isUsingLegacyConfig ? base64encode(data.cloudinit_config.autoscaler_legacy_config[0].rendered) : ""
+      ca_image                                   = var.cluster_autoscaler_image
+      ca_version                                 = var.cluster_autoscaler_version
+      cluster_autoscaler_extra_args              = var.cluster_autoscaler_extra_args
+      cluster_autoscaler_log_level               = var.cluster_autoscaler_log_level
+      cluster_autoscaler_log_to_stderr           = var.cluster_autoscaler_log_to_stderr
+      cluster_autoscaler_stderr_threshold        = var.cluster_autoscaler_stderr_threshold
+      cluster_autoscaler_server_creation_timeout = tostring(var.cluster_autoscaler_server_creation_timeout)
+      ssh_key                                    = local.hcloud_ssh_key_id
+      ipv4_subnet_id                             = data.hcloud_network.k3s.id
+      snapshot_id                                = local.first_nodepool_snapshot_id
+      cluster_config                             = base64encode(jsonencode(local.cluster_config))
+      firewall_id                                = hcloud_firewall.k3s.id
+      cluster_name                               = local.cluster_prefix
+      node_pools                                 = var.autoscaler_nodepools
   })
   # A concatenated list of all autoscaled nodes
   autoscaled_nodes = length(var.autoscaler_nodepools) == 0 ? {} : {

kube.tf.example

@@ -367,7 +367,7 @@ module "kube-hetzner" {
   #   - cluster_autoscaler_stderr_threshold: Sets the threshold for logs that go to stderr (--stderrthreshold).
   #
   # Server/node creation timeout variable:
-  #   - cluster_autoscaler_server_creation_timeout: Sets the timeout (in minutes) until which a newly created server/node has to come available before giving up and destroying it (defaults to 5min)
+  #   - cluster_autoscaler_server_creation_timeout: Sets the timeout (in minutes) until which a newly created server/node has to become available before giving up and destroying it (defaults to 15, unit is minutes)
   #
   # Example:
   #
@@ -376,7 +376,7 @@ module "kube-hetzner" {
   # cluster_autoscaler_log_level = 4
   # cluster_autoscaler_log_to_stderr = true
   # cluster_autoscaler_stderr_threshold = "INFO"
-  # cluster_autoscaler_server_creation_timeout = "5"
+  # cluster_autoscaler_server_creation_timeout = 15
 
   # Additional Cluster Autoscaler binary configuration
   #

variables.tf

@@ -309,8 +309,9 @@ variable "cluster_autoscaler_extra_args" {
 }
 
 variable "cluster_autoscaler_server_creation_timeout" {
-  type        = string
-  description = "Timeout (in minutes) until which a newly created server/node has to come available before giving up and destroying it (defaults to 5min)"
+  type        = number
+  default     = 15
+  description = "Timeout (in minutes) until which a newly created server/node has to become available before giving up and destroying it."
 }
 
 variable "autoscaler_nodepools" {
@@ -323,7 +324,7 @@ variable "autoscaler_nodepools" {
     max_nodes    = number
     labels       = optional(map(string), {})
     kubelet_args = optional(list(string), ["kube-reserved=cpu=50m,memory=300Mi,ephemeral-storage=1Gi", "system-reserved=cpu=250m,memory=300Mi"])
-    taints       = optional(list(object({
+    taints = optional(list(object({
       key    = string
       value  = string
       effect = string