c97c02677e
Applied terragrunt to recreate the L4 GPU pool with the correct name `ci-rl` (was `ci-compile` due to immutable Scaleway pool names). Updated all K8s manifests and comments to match. Removed the 3 stale `moved` blocks from main.tf since the state renames are now applied. Pool naming is now consistent across Terraform, Scaleway, and K8s configs: - ci-compile-cpu (POP2-32C-128G) — CPU compilation - ci-rl (L4-1-24G) — RL training / CUDA compile - ci-training (L40S-1-48G) — supervised training + hyperopt Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
141 lines
4.1 KiB
HCL
141 lines
4.1 KiB
HCL
resource "scaleway_vpc_private_network" "foxhunt" {
|
|
name = "${var.cluster_name}-pn"
|
|
region = var.region
|
|
}
|
|
|
|
resource "scaleway_k8s_cluster" "foxhunt" {
|
|
name = var.cluster_name
|
|
version = var.k8s_version
|
|
cni = "cilium"
|
|
region = var.region
|
|
delete_additional_resources = true
|
|
private_network_id = scaleway_vpc_private_network.foxhunt.id
|
|
|
|
auto_upgrade {
|
|
enable = true
|
|
maintenance_window_start_hour = 4
|
|
maintenance_window_day = "sunday"
|
|
}
|
|
|
|
autoscaler_config {
|
|
disable_scale_down = false
|
|
scale_down_delay_after_add = "10m"
|
|
scale_down_unneeded_time = "10m"
|
|
estimator = "binpacking"
|
|
ignore_daemonsets_utilization = true
|
|
}
|
|
}
|
|
|
|
resource "scaleway_k8s_pool" "services" {
|
|
cluster_id = scaleway_k8s_cluster.foxhunt.id
|
|
name = "services"
|
|
node_type = var.services_type
|
|
size = 1
|
|
min_size = 1
|
|
max_size = var.services_max_size
|
|
autoscaling = true
|
|
autohealing = true
|
|
public_ip_disabled = var.public_ip_disabled
|
|
region = var.region
|
|
|
|
lifecycle {
|
|
ignore_changes = [size]
|
|
}
|
|
}
|
|
|
|
# GitLab CE node pool (dedicated DEV1-L for GitLab + Runner manager)
|
|
resource "scaleway_k8s_pool" "gitlab" {
|
|
count = var.enable_gitlab_pool ? 1 : 0
|
|
cluster_id = scaleway_k8s_cluster.foxhunt.id
|
|
name = "gitlab"
|
|
node_type = var.gitlab_type
|
|
size = 1
|
|
min_size = 1
|
|
max_size = 1
|
|
autoscaling = false
|
|
autohealing = true
|
|
public_ip_disabled = var.public_ip_disabled
|
|
region = var.region
|
|
}
|
|
|
|
# CI RL pool (L4 — 24GB VRAM, CUDA CC 89, for RL training + hyperopt)
|
|
# Nodes auto-labeled: k8s.scaleway.com/pool-name=ci-rl
|
|
resource "scaleway_k8s_pool" "ci_rl" {
|
|
count = var.enable_ci_rl_pool ? 1 : 0
|
|
cluster_id = scaleway_k8s_cluster.foxhunt.id
|
|
name = "ci-rl"
|
|
node_type = var.ci_rl_type
|
|
size = 1
|
|
min_size = 0
|
|
max_size = var.ci_rl_max_size
|
|
autoscaling = true
|
|
autohealing = true
|
|
public_ip_disabled = var.public_ip_disabled
|
|
region = var.region
|
|
|
|
lifecycle {
|
|
ignore_changes = [size]
|
|
}
|
|
}
|
|
|
|
# CI training pool (L40S — 48GB VRAM, for supervised hyperopt + training)
|
|
# Nodes auto-labeled: k8s.scaleway.com/pool-name=ci-training
|
|
resource "scaleway_k8s_pool" "ci_training" {
|
|
count = var.enable_ci_training_pool ? 1 : 0
|
|
cluster_id = scaleway_k8s_cluster.foxhunt.id
|
|
name = "ci-training"
|
|
node_type = var.ci_training_type
|
|
size = 1
|
|
min_size = 0
|
|
max_size = var.ci_training_max_size
|
|
autoscaling = true
|
|
autohealing = true
|
|
public_ip_disabled = var.public_ip_disabled
|
|
region = var.region
|
|
|
|
lifecycle {
|
|
ignore_changes = [size]
|
|
}
|
|
}
|
|
|
|
# CPU compile pool (POP2 — high CPU, no GPU, for cargo check/build)
|
|
# Nodes auto-labeled: k8s.scaleway.com/pool-name=ci-compile-cpu
|
|
resource "scaleway_k8s_pool" "ci_compile_cpu" {
|
|
count = var.enable_ci_compile_cpu_pool ? 1 : 0
|
|
cluster_id = scaleway_k8s_cluster.foxhunt.id
|
|
name = "ci-compile-cpu"
|
|
node_type = var.ci_compile_cpu_type
|
|
size = 1
|
|
min_size = 0
|
|
max_size = var.ci_compile_cpu_max_size
|
|
autoscaling = true
|
|
autohealing = true
|
|
public_ip_disabled = var.public_ip_disabled
|
|
region = var.region
|
|
|
|
lifecycle {
|
|
ignore_changes = [size]
|
|
}
|
|
}
|
|
|
|
# CPU pool for remote development (DevPod — autoscales to zero)
|
|
# Nodes auto-labeled: k8s.scaleway.com/pool-name=gpu-dev
|
|
resource "scaleway_k8s_pool" "dev" {
|
|
count = var.enable_dev_pool ? 1 : 0
|
|
cluster_id = scaleway_k8s_cluster.foxhunt.id
|
|
name = "gpu-dev"
|
|
node_type = var.dev_pool_type
|
|
size = 1
|
|
min_size = 0
|
|
max_size = var.dev_pool_max_size
|
|
autoscaling = true
|
|
autohealing = true
|
|
public_ip_disabled = var.public_ip_disabled
|
|
wait_for_pool_ready = false
|
|
region = var.region
|
|
|
|
lifecycle {
|
|
ignore_changes = [size]
|
|
}
|
|
}
|