a252119fd4
Reasons: - h100-sxm: Scaleway account quota is 0/0 for the SXM instance type (cp_servers_type_H100_SXM_2_80G). The pool was perpetually trying to maintain size=1 with a creation_error node, which JAMMED the cluster autoscaler. That blocked L40S scale-up entirely during today's alpha-perception cluster run. - h100x2: more expensive than current workloads justify. Every training path (alpha perception, future PPO) fits on either the single-GPU H100 or L40S. Removed: - Two `scaleway_k8s_pool` resources from infra/modules/kapsule/main.tf - Six variables (enable + type + max_size for each pool) - Two outputs (pool_id for each) - Corresponding inputs in infra/live/production/kapsule/terragrunt.hcl The live cluster has the SXM pool stuck node manually deleted via `scw k8s node delete` (this commit-session); the pool resource itself will be destroyed on next `terragrunt apply`. Post-cleanup pool inventory: - platform (DEV1-L × 3) - ci-training-h100 (H100-1-80G, max 1) <- regular single-GPU - ci-training-l40s (L40S-1-48G, max 1) <- primary training target - ci-compile-cpu (POP2-HC, max 4) - ci-compile-cpu-hm (POP2-HM, max 1) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
41 lines
1.2 KiB
HCL
41 lines
1.2 KiB
HCL
output "cluster_id" {
|
|
description = "ID of the Kapsule cluster"
|
|
value = scaleway_k8s_cluster.foxhunt.id
|
|
}
|
|
|
|
output "kubeconfig" {
|
|
description = "Kubeconfig file content for the cluster"
|
|
value = scaleway_k8s_cluster.foxhunt.kubeconfig[0].config_file
|
|
sensitive = true
|
|
}
|
|
|
|
output "apiserver_url" {
|
|
description = "URL of the Kubernetes API server"
|
|
value = scaleway_k8s_cluster.foxhunt.apiserver_url
|
|
}
|
|
|
|
output "platform_pool_id" {
|
|
description = "ID of the platform node pool"
|
|
value = scaleway_k8s_pool.platform.id
|
|
}
|
|
|
|
output "ci_compile_cpu_pool_id" {
|
|
description = "ID of the CPU compile node pool"
|
|
value = var.enable_ci_compile_cpu_pool ? scaleway_k8s_pool.ci_compile_cpu[0].id : ""
|
|
}
|
|
|
|
output "ci_training_l40s_pool_id" {
|
|
description = "ID of the L40S training node pool"
|
|
value = var.enable_ci_training_l40s_pool ? scaleway_k8s_pool.ci_training_l40s[0].id : ""
|
|
}
|
|
|
|
output "ci_training_h100_pool_id" {
|
|
description = "ID of the H100 training node pool"
|
|
value = var.enable_ci_training_h100_pool ? scaleway_k8s_pool.ci_training_h100[0].id : ""
|
|
}
|
|
|
|
output "private_network_id" {
|
|
description = "ID of the VPC private network the cluster is attached to"
|
|
value = scaleway_vpc_private_network.foxhunt.id
|
|
}
|