From c87bb41a4d13a06e8e4b7687e15bed63595ad50b Mon Sep 17 00:00:00 2001 From: Eric Ho Date: Sat, 18 May 2024 05:32:26 +0800 Subject: [PATCH] feat: Add upgrade_settings for NAP created node pools (#1908) --- README.md | 2 +- autogen/main/cluster.tf.tmpl | 19 ++++++++++++ autogen/main/variables.tf.tmpl | 29 ++++++++++++------- cluster.tf | 19 ++++++++++++ .../README.md | 2 +- .../cluster.tf | 19 ++++++++++++ .../variables.tf | 29 ++++++++++++------- modules/beta-private-cluster/README.md | 2 +- modules/beta-private-cluster/cluster.tf | 19 ++++++++++++ modules/beta-private-cluster/variables.tf | 29 ++++++++++++------- .../README.md | 2 +- .../cluster.tf | 19 ++++++++++++ .../variables.tf | 29 ++++++++++++------- modules/beta-public-cluster/README.md | 2 +- modules/beta-public-cluster/cluster.tf | 19 ++++++++++++ modules/beta-public-cluster/variables.tf | 29 ++++++++++++------- .../private-cluster-update-variant/README.md | 2 +- .../private-cluster-update-variant/cluster.tf | 19 ++++++++++++ .../variables.tf | 29 ++++++++++++------- modules/private-cluster/README.md | 2 +- modules/private-cluster/cluster.tf | 19 ++++++++++++ modules/private-cluster/variables.tf | 29 ++++++++++++------- variables.tf | 29 ++++++++++++------- 23 files changed, 303 insertions(+), 95 deletions(-) diff --git a/README.md b/README.md index 24d24fc81..f9f0f4ac2 100644 --- a/README.md +++ b/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) | 
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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| no | +| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | 
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)
    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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| 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 | diff --git a/autogen/main/cluster.tf.tmpl b/autogen/main/cluster.tf.tmpl index aeaa4266d..d870a46cd 100644 --- a/autogen/main/cluster.tf.tmpl +++ b/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 %} diff --git a/autogen/main/variables.tf.tmpl b/autogen/main/variables.tf.tmpl index 09c707165..8cb575bed 100644 --- a/autogen/main/variables.tf.tmpl +++ b/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 diff --git a/cluster.tf b/cluster.tf index 228a1d641..140d7d754 100644 --- a/cluster.tf +++ b/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" diff --git a/modules/beta-private-cluster-update-variant/README.md b/modules/beta-private-cluster-update-variant/README.md index 5f25cf811..6252b260a 100644 --- a/modules/beta-private-cluster-update-variant/README.md +++ b/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) | 
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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| no | +| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | 
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)
    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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| 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 | diff --git a/modules/beta-private-cluster-update-variant/cluster.tf b/modules/beta-private-cluster-update-variant/cluster.tf index 0f0be2326..15a7c2d9a 100644 --- a/modules/beta-private-cluster-update-variant/cluster.tf +++ b/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", "") } } diff --git a/modules/beta-private-cluster-update-variant/variables.tf b/modules/beta-private-cluster-update-variant/variables.tf index 527908244..9e25085fd 100644 --- a/modules/beta-private-cluster-update-variant/variables.tf +++ b/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 diff --git a/modules/beta-private-cluster/README.md b/modules/beta-private-cluster/README.md index 6cbf21810..fc937d8ea 100644 --- a/modules/beta-private-cluster/README.md +++ b/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) | 
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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| no | +| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | 
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)
    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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| 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 | diff --git a/modules/beta-private-cluster/cluster.tf b/modules/beta-private-cluster/cluster.tf index 4c7d34592..5a2caa5d0 100644 --- a/modules/beta-private-cluster/cluster.tf +++ b/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", "") } } diff --git a/modules/beta-private-cluster/variables.tf b/modules/beta-private-cluster/variables.tf index 527908244..9e25085fd 100644 --- a/modules/beta-private-cluster/variables.tf +++ b/modules/beta-private-cluster/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 diff --git a/modules/beta-public-cluster-update-variant/README.md b/modules/beta-public-cluster-update-variant/README.md index 4b26ef1b3..5d3e3a1d3 100644 --- a/modules/beta-public-cluster-update-variant/README.md +++ b/modules/beta-public-cluster-update-variant/README.md @@ -165,7 +165,7 @@ 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) | 
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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| no | +| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | 
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)
    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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| 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 | diff --git a/modules/beta-public-cluster-update-variant/cluster.tf b/modules/beta-public-cluster-update-variant/cluster.tf index 22a144fdd..68c40f010 100644 --- a/modules/beta-public-cluster-update-variant/cluster.tf +++ b/modules/beta-public-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", "") } } diff --git a/modules/beta-public-cluster-update-variant/variables.tf b/modules/beta-public-cluster-update-variant/variables.tf index f440b77f0..66f68f5c9 100644 --- a/modules/beta-public-cluster-update-variant/variables.tf +++ b/modules/beta-public-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 diff --git a/modules/beta-public-cluster/README.md b/modules/beta-public-cluster/README.md index d7cfb53ae..da6310fb6 100644 --- a/modules/beta-public-cluster/README.md +++ b/modules/beta-public-cluster/README.md @@ -143,7 +143,7 @@ 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) | 
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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| no | +| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | 
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)
    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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| 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 | diff --git a/modules/beta-public-cluster/cluster.tf b/modules/beta-public-cluster/cluster.tf index 6944647cf..431bf9b02 100644 --- a/modules/beta-public-cluster/cluster.tf +++ b/modules/beta-public-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", "") } } diff --git a/modules/beta-public-cluster/variables.tf b/modules/beta-public-cluster/variables.tf index f440b77f0..66f68f5c9 100644 --- a/modules/beta-public-cluster/variables.tf +++ b/modules/beta-public-cluster/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 diff --git a/modules/private-cluster-update-variant/README.md b/modules/private-cluster-update-variant/README.md index 2d885826c..3584eb155 100644 --- a/modules/private-cluster-update-variant/README.md +++ b/modules/private-cluster-update-variant/README.md @@ -166,7 +166,7 @@ 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) | 
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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| no | +| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | 
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)
    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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| 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 | diff --git a/modules/private-cluster-update-variant/cluster.tf b/modules/private-cluster-update-variant/cluster.tf index 8a1c33ab9..44c2e2260 100644 --- a/modules/private-cluster-update-variant/cluster.tf +++ b/modules/private-cluster-update-variant/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" diff --git a/modules/private-cluster-update-variant/variables.tf b/modules/private-cluster-update-variant/variables.tf index 687f54ed8..787352a83 100644 --- a/modules/private-cluster-update-variant/variables.tf +++ b/modules/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 diff --git a/modules/private-cluster/README.md b/modules/private-cluster/README.md index 68daa2241..daec89ea7 100644 --- a/modules/private-cluster/README.md +++ b/modules/private-cluster/README.md @@ -144,7 +144,7 @@ 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) | 
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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| no | +| cluster\_autoscaling | Cluster autoscaling configuration. See [more details](https://cloud.google.com/kubernetes-engine/docs/reference/rest/v1beta1/projects.locations.clusters#clusterautoscaling) | 
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)
    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)
  })
| 
{
  "auto_repair": true,
  "auto_upgrade": true,
  "autoscaling_profile": "BALANCED",
  "disk_size": 100,
  "disk_type": "pd-standard",
  "enabled": false,
  "gpu_resources": [],
  "max_cpu_cores": 0,
  "max_memory_gb": 0,
  "min_cpu_cores": 0,
  "min_memory_gb": 0
}
| 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 | diff --git a/modules/private-cluster/cluster.tf b/modules/private-cluster/cluster.tf index 37e445697..f8bf29487 100644 --- a/modules/private-cluster/cluster.tf +++ b/modules/private-cluster/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" diff --git a/modules/private-cluster/variables.tf b/modules/private-cluster/variables.tf index 687f54ed8..787352a83 100644 --- a/modules/private-cluster/variables.tf +++ b/modules/private-cluster/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 diff --git a/variables.tf b/variables.tf index 0e05d7459..dc2352b24 100644 --- a/variables.tf +++ b/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