feat: Add upgrade_settings for NAP created node pools (#1908)

README.md

@@ -138,7 +138,7 @@ Then perform the following commands on the root folder:
 | add\_shadow\_firewall\_rules | Create GKE shadow firewall (the same as default firewall rules with firewall logs enabled). | `bool` | `false` | no |
 | additional\_ip\_range\_pods | List of _names_ of the additional secondary subnet ip ranges to use for pods | `list(string)` | `[]` | no |
 | authenticator\_security\_group | The name of the RBAC security group for use with Google security groups in Kubernetes RBAC. Group name must be in format gke-security-groups@yourdomain.com | `string` | `null` | no |
-| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | <pre>object({<br>    enabled             = bool<br>    autoscaling_profile = string<br>    min_cpu_cores       = number<br>    max_cpu_cores       = number<br>    min_memory_gb       = number<br>    max_memory_gb       = number<br>    gpu_resources       = list(object({ resource_type = string, minimum = number, maximum = number }))<br>    auto_repair         = bool<br>    auto_upgrade        = bool<br>    disk_size           = optional(number)<br>    disk_type           = optional(string)<br>  })</pre> | <pre>{<br>  "auto_repair": true,<br>  "auto_upgrade": true,<br>  "autoscaling_profile": "BALANCED",<br>  "disk_size": 100,<br>  "disk_type": "pd-standard",<br>  "enabled": false,<br>  "gpu_resources": [],<br>  "max_cpu_cores": 0,<br>  "max_memory_gb": 0,<br>  "min_cpu_cores": 0,<br>  "min_memory_gb": 0<br>}</pre> | no |
+| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | <pre>object({<br>    enabled                 = bool<br>    autoscaling_profile     = string<br>    min_cpu_cores           = number<br>    max_cpu_cores           = number<br>    min_memory_gb           = number<br>    max_memory_gb           = number<br>    gpu_resources           = list(object({ resource_type = string, minimum = number, maximum = number }))<br>    auto_repair             = bool<br>    auto_upgrade            = bool<br>    disk_size               = optional(number)<br>    disk_type               = optional(string)<br>    strategy                = optional(string)<br>    max_surge               = optional(number)<br>    max_unavailable         = optional(number)<br>    node_pool_soak_duration = optional(string)<br>    batch_soak_duration     = optional(string)<br>    batch_percentage        = optional(number)<br>    batch_node_count        = optional(number)<br>  })</pre> | <pre>{<br>  "auto_repair": true,<br>  "auto_upgrade": true,<br>  "autoscaling_profile": "BALANCED",<br>  "disk_size": 100,<br>  "disk_type": "pd-standard",<br>  "enabled": false,<br>  "gpu_resources": [],<br>  "max_cpu_cores": 0,<br>  "max_memory_gb": 0,<br>  "min_cpu_cores": 0,<br>  "min_memory_gb": 0<br>}</pre> | no |
 | cluster\_dns\_domain | The suffix used for all cluster service records. | `string` | `""` | no |
 | cluster\_dns\_provider | Which in-cluster DNS provider should be used. PROVIDER\_UNSPECIFIED (default) or PLATFORM\_DEFAULT or CLOUD\_DNS. | `string` | `"PROVIDER_UNSPECIFIED"` | no |
 | cluster\_dns\_scope | The scope of access to cluster DNS records. DNS\_SCOPE\_UNSPECIFIED (default) or CLUSTER\_SCOPE or VPC\_SCOPE. | `string` | `"DNS_SCOPE_UNSPECIFIED"` | no |

autogen/main/cluster.tf.tmpl

@@ -147,6 +147,25 @@ resource "google_container_cluster" "primary" {
         disk_size = lookup(var.cluster_autoscaling, "disk_size", 100)
         disk_type = lookup(var.cluster_autoscaling, "disk_type", "pd-standard")
 
+        upgrade_settings {
+          strategy        = lookup(var.cluster_autoscaling, "strategy", "SURGE")
+          max_surge       = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "SURGE" ? lookup(var.cluster_autoscaling, "max_surge", 0) : null
+          max_unavailable = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "SURGE" ? lookup(var.cluster_autoscaling, "max_unavailable", 0) : null
+
+          dynamic "blue_green_settings" {
+            for_each = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "BLUE_GREEN" ? [1] : []
+            content {
+              node_pool_soak_duration = lookup(var.cluster_autoscaling, "node_pool_soak_duration", null)
+
+              standard_rollout_policy {
+                batch_soak_duration = lookup(var.cluster_autoscaling, "batch_soak_duration", null)
+                batch_percentage    = lookup(var.cluster_autoscaling, "batch_percentage", null)
+                batch_node_count    = lookup(var.cluster_autoscaling, "batch_node_count", null)
+              }
+            }
+          }
+        }
+
         {% if beta_cluster %}
         min_cpu_platform = lookup(var.node_pools[0], "min_cpu_platform", "")
         {% endif %}

autogen/main/variables.tf.tmpl

@@ -244,17 +244,24 @@ variable "enable_resource_consumption_export" {
 {% if autopilot_cluster != true %}
 variable "cluster_autoscaling" {
   type = object({
-    enabled             = bool
-    autoscaling_profile = string
-    min_cpu_cores       = number
-    max_cpu_cores       = number
-    min_memory_gb       = number
-    max_memory_gb       = number
-    gpu_resources       = list(object({ resource_type = string, minimum = number, maximum = number }))
-    auto_repair         = bool
-    auto_upgrade        = bool
-    disk_size           = optional(number)
-    disk_type           = optional(string)
+    enabled                 = bool
+    autoscaling_profile     = string
+    min_cpu_cores           = number
+    max_cpu_cores           = number
+    min_memory_gb           = number
+    max_memory_gb           = number
+    gpu_resources           = list(object({ resource_type = string, minimum = number, maximum = number }))
+    auto_repair             = bool
+    auto_upgrade            = bool
+    disk_size               = optional(number)
+    disk_type               = optional(string)
+    strategy                = optional(string)
+    max_surge               = optional(number)
+    max_unavailable         = optional(number)
+    node_pool_soak_duration = optional(string)
+    batch_soak_duration     = optional(string)
+    batch_percentage        = optional(number)
+    batch_node_count        = optional(number)
   })
   default = {
     enabled             = false

cluster.tf

@@ -120,6 +120,25 @@ resource "google_container_cluster" "primary" {
         disk_size = lookup(var.cluster_autoscaling, "disk_size", 100)
         disk_type = lookup(var.cluster_autoscaling, "disk_type", "pd-standard")
 
+        upgrade_settings {
+          strategy        = lookup(var.cluster_autoscaling, "strategy", "SURGE")
+          max_surge       = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "SURGE" ? lookup(var.cluster_autoscaling, "max_surge", 0) : null
+          max_unavailable = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "SURGE" ? lookup(var.cluster_autoscaling, "max_unavailable", 0) : null
+
+          dynamic "blue_green_settings" {
+            for_each = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "BLUE_GREEN" ? [1] : []
+            content {
+              node_pool_soak_duration = lookup(var.cluster_autoscaling, "node_pool_soak_duration", null)
+
+              standard_rollout_policy {
+                batch_soak_duration = lookup(var.cluster_autoscaling, "batch_soak_duration", null)
+                batch_percentage    = lookup(var.cluster_autoscaling, "batch_percentage", null)
+                batch_node_count    = lookup(var.cluster_autoscaling, "batch_node_count", null)
+              }
+            }
+          }
+        }
+
       }
     }
     autoscaling_profile = var.cluster_autoscaling.autoscaling_profile != null ? var.cluster_autoscaling.autoscaling_profile : "BALANCED"

modules/beta-private-cluster-update-variant/README.md

@@ -171,7 +171,7 @@ Then perform the following commands on the root folder:
 | authenticator\_security\_group | The name of the RBAC security group for use with Google security groups in Kubernetes RBAC. Group name must be in format gke-security-groups@yourdomain.com | `string` | `null` | no |
 | cloudrun | (Beta) Enable CloudRun addon | `bool` | `false` | no |
 | cloudrun\_load\_balancer\_type | (Beta) Configure the Cloud Run load balancer type. External by default. Set to `LOAD_BALANCER_TYPE_INTERNAL` to configure as an internal load balancer. | `string` | `""` | no |
-| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | <pre>object({<br>    enabled             = bool<br>    autoscaling_profile = string<br>    min_cpu_cores       = number<br>    max_cpu_cores       = number<br>    min_memory_gb       = number<br>    max_memory_gb       = number<br>    gpu_resources       = list(object({ resource_type = string, minimum = number, maximum = number }))<br>    auto_repair         = bool<br>    auto_upgrade        = bool<br>    disk_size           = optional(number)<br>    disk_type           = optional(string)<br>  })</pre> | <pre>{<br>  "auto_repair": true,<br>  "auto_upgrade": true,<br>  "autoscaling_profile": "BALANCED",<br>  "disk_size": 100,<br>  "disk_type": "pd-standard",<br>  "enabled": false,<br>  "gpu_resources": [],<br>  "max_cpu_cores": 0,<br>  "max_memory_gb": 0,<br>  "min_cpu_cores": 0,<br>  "min_memory_gb": 0<br>}</pre> | no |
+| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | <pre>object({<br>    enabled                 = bool<br>    autoscaling_profile     = string<br>    min_cpu_cores           = number<br>    max_cpu_cores           = number<br>    min_memory_gb           = number<br>    max_memory_gb           = number<br>    gpu_resources           = list(object({ resource_type = string, minimum = number, maximum = number }))<br>    auto_repair             = bool<br>    auto_upgrade            = bool<br>    disk_size               = optional(number)<br>    disk_type               = optional(string)<br>    strategy                = optional(string)<br>    max_surge               = optional(number)<br>    max_unavailable         = optional(number)<br>    node_pool_soak_duration = optional(string)<br>    batch_soak_duration     = optional(string)<br>    batch_percentage        = optional(number)<br>    batch_node_count        = optional(number)<br>  })</pre> | <pre>{<br>  "auto_repair": true,<br>  "auto_upgrade": true,<br>  "autoscaling_profile": "BALANCED",<br>  "disk_size": 100,<br>  "disk_type": "pd-standard",<br>  "enabled": false,<br>  "gpu_resources": [],<br>  "max_cpu_cores": 0,<br>  "max_memory_gb": 0,<br>  "min_cpu_cores": 0,<br>  "min_memory_gb": 0<br>}</pre> | no |
 | cluster\_dns\_domain | The suffix used for all cluster service records. | `string` | `""` | no |
 | cluster\_dns\_provider | Which in-cluster DNS provider should be used. PROVIDER\_UNSPECIFIED (default) or PLATFORM\_DEFAULT or CLOUD\_DNS. | `string` | `"PROVIDER_UNSPECIFIED"` | no |
 | cluster\_dns\_scope | The scope of access to cluster DNS records. DNS\_SCOPE\_UNSPECIFIED (default) or CLUSTER\_SCOPE or VPC\_SCOPE. | `string` | `"DNS_SCOPE_UNSPECIFIED"` | no |

modules/beta-private-cluster-update-variant/cluster.tf

@@ -126,6 +126,25 @@ resource "google_container_cluster" "primary" {
         disk_size = lookup(var.cluster_autoscaling, "disk_size", 100)
         disk_type = lookup(var.cluster_autoscaling, "disk_type", "pd-standard")
 
+        upgrade_settings {
+          strategy        = lookup(var.cluster_autoscaling, "strategy", "SURGE")
+          max_surge       = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "SURGE" ? lookup(var.cluster_autoscaling, "max_surge", 0) : null
+          max_unavailable = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "SURGE" ? lookup(var.cluster_autoscaling, "max_unavailable", 0) : null
+
+          dynamic "blue_green_settings" {
+            for_each = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "BLUE_GREEN" ? [1] : []
+            content {
+              node_pool_soak_duration = lookup(var.cluster_autoscaling, "node_pool_soak_duration", null)
+
+              standard_rollout_policy {
+                batch_soak_duration = lookup(var.cluster_autoscaling, "batch_soak_duration", null)
+                batch_percentage    = lookup(var.cluster_autoscaling, "batch_percentage", null)
+                batch_node_count    = lookup(var.cluster_autoscaling, "batch_node_count", null)
+              }
+            }
+          }
+        }
+
         min_cpu_platform = lookup(var.node_pools[0], "min_cpu_platform", "")
       }
     }

modules/beta-private-cluster-update-variant/variables.tf

@@ -239,17 +239,24 @@ variable "enable_resource_consumption_export" {
 
 variable "cluster_autoscaling" {
   type = object({
-    enabled             = bool
-    autoscaling_profile = string
-    min_cpu_cores       = number
-    max_cpu_cores       = number
-    min_memory_gb       = number
-    max_memory_gb       = number
-    gpu_resources       = list(object({ resource_type = string, minimum = number, maximum = number }))
-    auto_repair         = bool
-    auto_upgrade        = bool
-    disk_size           = optional(number)
-    disk_type           = optional(string)
+    enabled                 = bool
+    autoscaling_profile     = string
+    min_cpu_cores           = number
+    max_cpu_cores           = number
+    min_memory_gb           = number
+    max_memory_gb           = number
+    gpu_resources           = list(object({ resource_type = string, minimum = number, maximum = number }))
+    auto_repair             = bool
+    auto_upgrade            = bool
+    disk_size               = optional(number)
+    disk_type               = optional(string)
+    strategy                = optional(string)
+    max_surge               = optional(number)
+    max_unavailable         = optional(number)
+    node_pool_soak_duration = optional(string)
+    batch_soak_duration     = optional(string)
+    batch_percentage        = optional(number)
+    batch_node_count        = optional(number)
   })
   default = {
     enabled             = false

modules/beta-private-cluster/README.md

@@ -149,7 +149,7 @@ Then perform the following commands on the root folder:
 | authenticator\_security\_group | The name of the RBAC security group for use with Google security groups in Kubernetes RBAC. Group name must be in format gke-security-groups@yourdomain.com | `string` | `null` | no |
 | cloudrun | (Beta) Enable CloudRun addon | `bool` | `false` | no |
 | cloudrun\_load\_balancer\_type | (Beta) Configure the Cloud Run load balancer type. External by default. Set to `LOAD_BALANCER_TYPE_INTERNAL` to configure as an internal load balancer. | `string` | `""` | no |
-| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | <pre>object({<br>    enabled             = bool<br>    autoscaling_profile = string<br>    min_cpu_cores       = number<br>    max_cpu_cores       = number<br>    min_memory_gb       = number<br>    max_memory_gb       = number<br>    gpu_resources       = list(object({ resource_type = string, minimum = number, maximum = number }))<br>    auto_repair         = bool<br>    auto_upgrade        = bool<br>    disk_size           = optional(number)<br>    disk_type           = optional(string)<br>  })</pre> | <pre>{<br>  "auto_repair": true,<br>  "auto_upgrade": true,<br>  "autoscaling_profile": "BALANCED",<br>  "disk_size": 100,<br>  "disk_type": "pd-standard",<br>  "enabled": false,<br>  "gpu_resources": [],<br>  "max_cpu_cores": 0,<br>  "max_memory_gb": 0,<br>  "min_cpu_cores": 0,<br>  "min_memory_gb": 0<br>}</pre> | no |
+| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | <pre>object({<br>    enabled                 = bool<br>    autoscaling_profile     = string<br>    min_cpu_cores           = number<br>    max_cpu_cores           = number<br>    min_memory_gb           = number<br>    max_memory_gb           = number<br>    gpu_resources           = list(object({ resource_type = string, minimum = number, maximum = number }))<br>    auto_repair             = bool<br>    auto_upgrade            = bool<br>    disk_size               = optional(number)<br>    disk_type               = optional(string)<br>    strategy                = optional(string)<br>    max_surge               = optional(number)<br>    max_unavailable         = optional(number)<br>    node_pool_soak_duration = optional(string)<br>    batch_soak_duration     = optional(string)<br>    batch_percentage        = optional(number)<br>    batch_node_count        = optional(number)<br>  })</pre> | <pre>{<br>  "auto_repair": true,<br>  "auto_upgrade": true,<br>  "autoscaling_profile": "BALANCED",<br>  "disk_size": 100,<br>  "disk_type": "pd-standard",<br>  "enabled": false,<br>  "gpu_resources": [],<br>  "max_cpu_cores": 0,<br>  "max_memory_gb": 0,<br>  "min_cpu_cores": 0,<br>  "min_memory_gb": 0<br>}</pre> | no |
 | cluster\_dns\_domain | The suffix used for all cluster service records. | `string` | `""` | no |
 | cluster\_dns\_provider | Which in-cluster DNS provider should be used. PROVIDER\_UNSPECIFIED (default) or PLATFORM\_DEFAULT or CLOUD\_DNS. | `string` | `"PROVIDER_UNSPECIFIED"` | no |
 | cluster\_dns\_scope | The scope of access to cluster DNS records. DNS\_SCOPE\_UNSPECIFIED (default) or CLUSTER\_SCOPE or VPC\_SCOPE. | `string` | `"DNS_SCOPE_UNSPECIFIED"` | no |

modules/beta-private-cluster/cluster.tf

@@ -126,6 +126,25 @@ resource "google_container_cluster" "primary" {
         disk_size = lookup(var.cluster_autoscaling, "disk_size", 100)
         disk_type = lookup(var.cluster_autoscaling, "disk_type", "pd-standard")
 
+        upgrade_settings {
+          strategy        = lookup(var.cluster_autoscaling, "strategy", "SURGE")
+          max_surge       = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "SURGE" ? lookup(var.cluster_autoscaling, "max_surge", 0) : null
+          max_unavailable = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "SURGE" ? lookup(var.cluster_autoscaling, "max_unavailable", 0) : null
+
+          dynamic "blue_green_settings" {
+            for_each = lookup(var.cluster_autoscaling, "strategy", "SURGE") == "BLUE_GREEN" ? [1] : []
+            content {
+              node_pool_soak_duration = lookup(var.cluster_autoscaling, "node_pool_soak_duration", null)
+
+              standard_rollout_policy {
+                batch_soak_duration = lookup(var.cluster_autoscaling, "batch_soak_duration", null)
+                batch_percentage    = lookup(var.cluster_autoscaling, "batch_percentage", null)
+                batch_node_count    = lookup(var.cluster_autoscaling, "batch_node_count", null)
+              }
+            }
+          }
+        }
+
         min_cpu_platform = lookup(var.node_pools[0], "min_cpu_platform", "")
       }
     }