Extend `cluster_autoscaling` fields in gke-cluster-standard (#1845)
* feat(gke-cluster-standard): Add feature to setup `cluster_autoscaling` * feat(gke-cluster-standard): Add GPUs setup feature for `cluster_autoscaling` * feat(gke-cluster-standard): Add validation for `autoscaling_profile` and `disk_type` to ensure only valid values are specified * feat(gke-cluster-standard): Fix validation condition for `cluster_autoscaling`
This commit is contained in:
Tone
GitHub
parent
82c74e4ab6
commit
0f446e89d4
|
|
@ -310,28 +310,28 @@ module "cluster-1" {
|
|||
|
||||
| name | description | type | required | default |
|
||||
|---|---|:---:|:---:|:---:|
|
||||
| [location](variables.tf#L154) | Cluster zone or region. | <code>string</code> | ✓ | |
|
||||
| [name](variables.tf#L265) | Cluster name. | <code>string</code> | ✓ | |
|
||||
| [project_id](variables.tf#L291) | Cluster project id. | <code>string</code> | ✓ | |
|
||||
| [vpc_config](variables.tf#L314) | VPC-level configuration. | <code title="object({ network = string subnetwork = string master_ipv4_cidr_block = optional(string) secondary_range_blocks = optional(object({ pods = string services = string })) secondary_range_names = optional(object({ pods = optional(string, "pods") services = optional(string, "services") })) master_authorized_ranges = optional(map(string)) stack_type = optional(string) })">object({…})</code> | ✓ | |
|
||||
| [location](variables.tf#L178) | Cluster zone or region. | <code>string</code> | ✓ | |
|
||||
| [name](variables.tf#L289) | Cluster name. | <code>string</code> | ✓ | |
|
||||
| [project_id](variables.tf#L315) | Cluster project id. | <code>string</code> | ✓ | |
|
||||
| [vpc_config](variables.tf#L338) | VPC-level configuration. | <code title="object({ network = string subnetwork = string master_ipv4_cidr_block = optional(string) secondary_range_blocks = optional(object({ pods = string services = string })) secondary_range_names = optional(object({ pods = optional(string, "pods") services = optional(string, "services") })) master_authorized_ranges = optional(map(string)) stack_type = optional(string) })">object({…})</code> | ✓ | |
|
||||
| [backup_configs](variables.tf#L17) | Configuration for Backup for GKE. | <code title="object({ enable_backup_agent = optional(bool, false) backup_plans = optional(map(object({ region = string applications = optional(map(list(string))) encryption_key = optional(string) include_secrets = optional(bool, true) include_volume_data = optional(bool, true) namespaces = optional(list(string)) schedule = optional(string) retention_policy_days = optional(number) retention_policy_lock = optional(bool, false) retention_policy_delete_lock_days = optional(number) })), {}) })">object({…})</code> | | <code>{}</code> |
|
||||
| [cluster_autoscaling](variables.tf#L38) | Enable and configure limits for Node Auto-Provisioning with Cluster Autoscaler. | <code title="object({ auto_provisioning_defaults = optional(object({ boot_disk_kms_key = optional(string) image_type = optional(string) oauth_scopes = optional(list(string)) service_account = optional(string) })) cpu_limits = optional(object({ min = number max = number })) mem_limits = optional(object({ min = number max = number })) })">object({…})</code> | | <code>null</code> |
|
||||
| [deletion_protection](variables.tf#L59) | Whether or not to allow Terraform to destroy the cluster. Unless this field is set to false in Terraform state, a terraform destroy or terraform apply that would delete the cluster will fail. | <code>bool</code> | | <code>true</code> |
|
||||
| [description](variables.tf#L66) | Cluster description. | <code>string</code> | | <code>null</code> |
|
||||
| [enable_addons](variables.tf#L72) | Addons enabled in the cluster (true means enabled). | <code title="object({ cloudrun = optional(bool, false) config_connector = optional(bool, false) dns_cache = optional(bool, false) gce_persistent_disk_csi_driver = optional(bool, false) gcp_filestore_csi_driver = optional(bool, false) gcs_fuse_csi_driver = optional(bool, false) horizontal_pod_autoscaling = optional(bool, false) http_load_balancing = optional(bool, false) istio = optional(object({ enable_tls = bool })) kalm = optional(bool, false) network_policy = optional(bool, false) })">object({…})</code> | | <code title="{ horizontal_pod_autoscaling = true http_load_balancing = true }">{…}</code> |
|
||||
| [enable_features](variables.tf#L96) | Enable cluster-level features. Certain features allow configuration. | <code title="object({ binary_authorization = optional(bool, false) cost_management = optional(bool, false) dns = optional(object({ provider = optional(string) scope = optional(string) domain = optional(string) })) database_encryption = optional(object({ state = string key_name = string })) dataplane_v2 = optional(bool, false) fqdn_network_policy = optional(bool, false) gateway_api = optional(bool, false) groups_for_rbac = optional(string) intranode_visibility = optional(bool, false) l4_ilb_subsetting = optional(bool, false) mesh_certificates = optional(bool) pod_security_policy = optional(bool, false) resource_usage_export = optional(object({ dataset = string enable_network_egress_metering = optional(bool) enable_resource_consumption_metering = optional(bool) })) shielded_nodes = optional(bool, false) tpu = optional(bool, false) upgrade_notifications = optional(object({ topic_id = optional(string) })) vertical_pod_autoscaling = optional(bool, false) workload_identity = optional(bool, true) })">object({…})</code> | | <code title="{ workload_identity = true }">{…}</code> |
|
||||
| [issue_client_certificate](variables.tf#L142) | Enable issuing client certificate. | <code>bool</code> | | <code>false</code> |
|
||||
| [labels](variables.tf#L148) | Cluster resource labels. | <code>map(string)</code> | | <code>null</code> |
|
||||
| [logging_config](variables.tf#L159) | Logging configuration. | <code title="object({ enable_system_logs = optional(bool, true) enable_workloads_logs = optional(bool, false) enable_api_server_logs = optional(bool, false) enable_scheduler_logs = optional(bool, false) enable_controller_manager_logs = optional(bool, false) })">object({…})</code> | | <code>{}</code> |
|
||||
| [maintenance_config](variables.tf#L180) | Maintenance window configuration. | <code title="object({ daily_window_start_time = optional(string) recurring_window = optional(object({ start_time = string end_time = string recurrence = string })) maintenance_exclusions = optional(list(object({ name = string start_time = string end_time = string scope = optional(string) }))) })">object({…})</code> | | <code title="{ daily_window_start_time = "03:00" recurring_window = null maintenance_exclusion = [] }">{…}</code> |
|
||||
| [max_pods_per_node](variables.tf#L203) | Maximum number of pods per node in this cluster. | <code>number</code> | | <code>110</code> |
|
||||
| [min_master_version](variables.tf#L209) | Minimum version of the master, defaults to the version of the most recent official release. | <code>string</code> | | <code>null</code> |
|
||||
| [monitoring_config](variables.tf#L215) | Monitoring configuration. Google Cloud Managed Service for Prometheus is enabled by default. | <code title="object({ enable_system_metrics = optional(bool, true) enable_api_server_metrics = optional(bool, false) enable_controller_manager_metrics = optional(bool, false) enable_scheduler_metrics = optional(bool, false) enable_daemonset_metrics = optional(bool, false) enable_deployment_metrics = optional(bool, false) enable_hpa_metrics = optional(bool, false) enable_pod_metrics = optional(bool, false) enable_statefulset_metrics = optional(bool, false) enable_storage_metrics = optional(bool, false) enable_managed_prometheus = optional(bool, true) })">object({…})</code> | | <code>{}</code> |
|
||||
| [node_locations](variables.tf#L270) | Zones in which the cluster's nodes are located. | <code>list(string)</code> | | <code>[]</code> |
|
||||
| [private_cluster_config](variables.tf#L277) | Private cluster configuration. | <code title="object({ enable_private_endpoint = optional(bool) master_global_access = optional(bool) peering_config = optional(object({ export_routes = optional(bool) import_routes = optional(bool) project_id = optional(string) })) })">object({…})</code> | | <code>null</code> |
|
||||
| [release_channel](variables.tf#L296) | Release channel for GKE upgrades. | <code>string</code> | | <code>null</code> |
|
||||
| [service_account](variables.tf#L302) | Service account used for the default node pool, only useful if the default GCE service account has been disabled. | <code>string</code> | | <code>null</code> |
|
||||
| [tags](variables.tf#L308) | Network tags applied to nodes. | <code>list(string)</code> | | <code>null</code> |
|
||||
| [cluster_autoscaling](variables.tf#L38) | Enable and configure limits for Node Auto-Provisioning with Cluster Autoscaler. | <code title="object({ autoscaling_profile = optional(string, "BALANCED") auto_provisioning_defaults = optional(object({ boot_disk_kms_key = optional(string) disk_size = optional(number) disk_type = optional(string, "pd-standard") image_type = optional(string) oauth_scopes = optional(list(string)) service_account = optional(string) management = optional(object({ auto_repair = optional(bool, true) auto_upgrade = optional(bool, true) })) shielded_instance_config = object({ integrity_monitoring = optional(bool, true) secure_boot = optional(bool, false) }) })) cpu_limits = optional(object({ min = number max = number })) mem_limits = optional(object({ min = number max = number })) gpu_resources = optional(list(object({ resource_type = string min = number max = number }))) })">object({…})</code> | | <code>null</code> |
|
||||
| [deletion_protection](variables.tf#L83) | Whether or not to allow Terraform to destroy the cluster. Unless this field is set to false in Terraform state, a terraform destroy or terraform apply that would delete the cluster will fail. | <code>bool</code> | | <code>true</code> |
|
||||
| [description](variables.tf#L90) | Cluster description. | <code>string</code> | | <code>null</code> |
|
||||
| [enable_addons](variables.tf#L96) | Addons enabled in the cluster (true means enabled). | <code title="object({ cloudrun = optional(bool, false) config_connector = optional(bool, false) dns_cache = optional(bool, false) gce_persistent_disk_csi_driver = optional(bool, false) gcp_filestore_csi_driver = optional(bool, false) gcs_fuse_csi_driver = optional(bool, false) horizontal_pod_autoscaling = optional(bool, false) http_load_balancing = optional(bool, false) istio = optional(object({ enable_tls = bool })) kalm = optional(bool, false) network_policy = optional(bool, false) })">object({…})</code> | | <code title="{ horizontal_pod_autoscaling = true http_load_balancing = true }">{…}</code> |
|
||||
| [enable_features](variables.tf#L120) | Enable cluster-level features. Certain features allow configuration. | <code title="object({ binary_authorization = optional(bool, false) cost_management = optional(bool, false) dns = optional(object({ provider = optional(string) scope = optional(string) domain = optional(string) })) database_encryption = optional(object({ state = string key_name = string })) dataplane_v2 = optional(bool, false) fqdn_network_policy = optional(bool, false) gateway_api = optional(bool, false) groups_for_rbac = optional(string) intranode_visibility = optional(bool, false) l4_ilb_subsetting = optional(bool, false) mesh_certificates = optional(bool) pod_security_policy = optional(bool, false) resource_usage_export = optional(object({ dataset = string enable_network_egress_metering = optional(bool) enable_resource_consumption_metering = optional(bool) })) shielded_nodes = optional(bool, false) tpu = optional(bool, false) upgrade_notifications = optional(object({ topic_id = optional(string) })) vertical_pod_autoscaling = optional(bool, false) workload_identity = optional(bool, true) })">object({…})</code> | | <code title="{ workload_identity = true }">{…}</code> |
|
||||
| [issue_client_certificate](variables.tf#L166) | Enable issuing client certificate. | <code>bool</code> | | <code>false</code> |
|
||||
| [labels](variables.tf#L172) | Cluster resource labels. | <code>map(string)</code> | | <code>null</code> |
|
||||
| [logging_config](variables.tf#L183) | Logging configuration. | <code title="object({ enable_system_logs = optional(bool, true) enable_workloads_logs = optional(bool, false) enable_api_server_logs = optional(bool, false) enable_scheduler_logs = optional(bool, false) enable_controller_manager_logs = optional(bool, false) })">object({…})</code> | | <code>{}</code> |
|
||||
| [maintenance_config](variables.tf#L204) | Maintenance window configuration. | <code title="object({ daily_window_start_time = optional(string) recurring_window = optional(object({ start_time = string end_time = string recurrence = string })) maintenance_exclusions = optional(list(object({ name = string start_time = string end_time = string scope = optional(string) }))) })">object({…})</code> | | <code title="{ daily_window_start_time = "03:00" recurring_window = null maintenance_exclusion = [] }">{…}</code> |
|
||||
| [max_pods_per_node](variables.tf#L227) | Maximum number of pods per node in this cluster. | <code>number</code> | | <code>110</code> |
|
||||
| [min_master_version](variables.tf#L233) | Minimum version of the master, defaults to the version of the most recent official release. | <code>string</code> | | <code>null</code> |
|
||||
| [monitoring_config](variables.tf#L239) | Monitoring configuration. Google Cloud Managed Service for Prometheus is enabled by default. | <code title="object({ enable_system_metrics = optional(bool, true) enable_api_server_metrics = optional(bool, false) enable_controller_manager_metrics = optional(bool, false) enable_scheduler_metrics = optional(bool, false) enable_daemonset_metrics = optional(bool, false) enable_deployment_metrics = optional(bool, false) enable_hpa_metrics = optional(bool, false) enable_pod_metrics = optional(bool, false) enable_statefulset_metrics = optional(bool, false) enable_storage_metrics = optional(bool, false) enable_managed_prometheus = optional(bool, true) })">object({…})</code> | | <code>{}</code> |
|
||||
| [node_locations](variables.tf#L294) | Zones in which the cluster's nodes are located. | <code>list(string)</code> | | <code>[]</code> |
|
||||
| [private_cluster_config](variables.tf#L301) | Private cluster configuration. | <code title="object({ enable_private_endpoint = optional(bool) master_global_access = optional(bool) peering_config = optional(object({ export_routes = optional(bool) import_routes = optional(bool) project_id = optional(string) })) })">object({…})</code> | | <code>null</code> |
|
||||
| [release_channel](variables.tf#L320) | Release channel for GKE upgrades. | <code>string</code> | | <code>null</code> |
|
||||
| [service_account](variables.tf#L326) | Service account used for the default node pool, only useful if the default GCE service account has been disabled. | <code>string</code> | | <code>null</code> |
|
||||
| [tags](variables.tf#L332) | Network tags applied to nodes. | <code>list(string)</code> | | <code>null</code> |
|
||||
|
||||
## Outputs
|
||||
|
||||
|
|
|
|||
|
|
@ -123,13 +123,31 @@ resource "google_container_cluster" "cluster" {
|
|||
content {
|
||||
enabled = true
|
||||
|
||||
autoscaling_profile = var.cluster_autoscaling.autoscaling_profile
|
||||
|
||||
dynamic "auto_provisioning_defaults" {
|
||||
for_each = var.cluster_autoscaling.auto_provisioning_defaults != null ? [""] : []
|
||||
content {
|
||||
boot_disk_kms_key = var.cluster_autoscaling.auto_provisioning_defaults.boot_disk_kms_key
|
||||
disk_size = var.cluster_autoscaling.auto_provisioning_defaults.disk_size
|
||||
disk_type = var.cluster_autoscaling.auto_provisioning_defaults.disk_type
|
||||
image_type = var.cluster_autoscaling.auto_provisioning_defaults.image_type
|
||||
oauth_scopes = var.cluster_autoscaling.auto_provisioning_defaults.oauth_scopes
|
||||
service_account = var.cluster_autoscaling.auto_provisioning_defaults.service_account
|
||||
dynamic "management" {
|
||||
for_each = var.cluster_autoscaling.auto_provisioning_defaults.management != null ? [""] : []
|
||||
content {
|
||||
auto_repair = var.cluster_autoscaling.auto_provisioning_defaults.management.auto_repair
|
||||
auto_upgrade = var.cluster_autoscaling.auto_provisioning_defaults.management.auto_upgrade
|
||||
}
|
||||
}
|
||||
dynamic "shielded_instance_config" {
|
||||
for_each = var.cluster_autoscaling.auto_provisioning_defaults.shielded_instance_config != null ? [""] : []
|
||||
content {
|
||||
enable_integrity_monitoring = var.cluster_autoscaling.auto_provisioning_defaults.shielded_instance_config.integrity_monitoring
|
||||
enable_secure_boot = var.cluster_autoscaling.auto_provisioning_defaults.shielded_instance_config.secure_boot
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
dynamic "resource_limits" {
|
||||
|
|
@ -148,7 +166,19 @@ resource "google_container_cluster" "cluster" {
|
|||
maximum = var.cluster_autoscaling.mem_limits.max
|
||||
}
|
||||
}
|
||||
// TODO: support GPUs too
|
||||
dynamic "resource_limits" {
|
||||
for_each = (
|
||||
try(var.cluster_autoscaling.gpu_resources, null) == null
|
||||
? []
|
||||
: var.cluster_autoscaling.gpu_resources
|
||||
)
|
||||
iterator = gpu_resources
|
||||
content {
|
||||
resource_type = gpu_resources.value.resource_type
|
||||
minimum = gpu_resources.value.min
|
||||
maximum = gpu_resources.value.max
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -38,11 +38,22 @@ variable "backup_configs" {
|
|||
variable "cluster_autoscaling" {
|
||||
description = "Enable and configure limits for Node Auto-Provisioning with Cluster Autoscaler."
|
||||
type = object({
|
||||
autoscaling_profile = optional(string, "BALANCED")
|
||||
auto_provisioning_defaults = optional(object({
|
||||
boot_disk_kms_key = optional(string)
|
||||
disk_size = optional(number)
|
||||
disk_type = optional(string, "pd-standard")
|
||||
image_type = optional(string)
|
||||
oauth_scopes = optional(list(string))
|
||||
service_account = optional(string)
|
||||
management = optional(object({
|
||||
auto_repair = optional(bool, true)
|
||||
auto_upgrade = optional(bool, true)
|
||||
}))
|
||||
shielded_instance_config = object({
|
||||
integrity_monitoring = optional(bool, true)
|
||||
secure_boot = optional(bool, false)
|
||||
})
|
||||
}))
|
||||
cpu_limits = optional(object({
|
||||
min = number
|
||||
|
|
@ -52,8 +63,21 @@ variable "cluster_autoscaling" {
|
|||
min = number
|
||||
max = number
|
||||
}))
|
||||
gpu_resources = optional(list(object({
|
||||
resource_type = string
|
||||
min = number
|
||||
max = number
|
||||
})))
|
||||
})
|
||||
default = null
|
||||
validation {
|
||||
condition = (var.cluster_autoscaling == null ? true : contains(["BALANCED", "OPTIMIZE_UTILIZATION"], var.cluster_autoscaling.autoscaling_profile))
|
||||
error_message = "Invalid autoscaling_profile."
|
||||
}
|
||||
validation {
|
||||
condition = (var.cluster_autoscaling == null ? true : contains(["pd-standard", "pd-ssd", "pd-balanced"], var.cluster_autoscaling.auto_provisioning_defaults.disk_type))
|
||||
error_message = "Invalid disk_type."
|
||||
}
|
||||
}
|
||||
|
||||
variable "deletion_protection" {
|
||||
|
|
|
|||
Loading…
Reference in New Issue