68b6aa8313
Full migration off Scaleway Container Registry to internal GitLab registry backed by MinIO S3. All 4 images (ci-builder, ci-builder-cpu, foxhunt-runtime, foxhunt-training-runtime) rebuilt in internal registry. Registry & images: - All image refs → gitlab-registry.foxhunt.svc.cluster.local:5000/root/foxhunt/ - imagePullSecrets: scw-registry → gitlab-registry - Kaniko build template: two-step DAG (git-clone → kaniko-build) with shared PVC - Kaniko layer cache enabled at root/foxhunt/cache - AWS_ACCESS_KEY_ID: $SCW_ACCESS_KEY → $MINIO_ACCESS_KEY in .gitlab-ci.yml Network policies: - ci-pipeline: add HTTP/80, registry/5000, webservice/8181 egress rules DNS & Tailscale proxy cleanup: - Remove ci, prometheus, monitor DNS records (no longer exposed) - Rename s3 → minio DNS record - Remove Argo UI, Prometheus, monitor nginx server blocks - Remove argo-htpasswd volume mount - Tailscale proxy nodeSelector: infra → platform Terraform cleanup: - Delete infra/modules/registry/ (SCW CR namespace) - Delete infra/modules/object-storage/ (SCW S3 buckets) - Delete infra/modules/secrets/ (SCW secrets) - Delete corresponding live configs - TF state backend: S3 → GitLab HTTP Argo workflows: - Add events/ (GitLab push eventsource + ci-pipeline sensor) - ci-pipeline + training templates: SCW → internal registry - Delete obsolete compile-training-template.yaml Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
77 lines
2.8 KiB
YAML
77 lines
2.8 KiB
YAML
# GitLab Runner — RL training workloads (DQN, PPO)
|
|
# Runs on ci-training pool (L40S: 48GB VRAM)
|
|
# Mounts separate PVCs to avoid RWO conflicts with main runner
|
|
|
|
gitlabUrl: http://gitlab-webservice-default.foxhunt.svc.cluster.local:8181
|
|
# runnerToken set via --set at install time
|
|
|
|
replicas: 1
|
|
|
|
# Reuse the existing gitlab-runner SA (has pods/secrets/configmaps RBAC)
|
|
rbac:
|
|
create: false
|
|
serviceAccount:
|
|
create: false
|
|
name: gitlab-runner
|
|
|
|
nodeSelector:
|
|
k8s.scaleway.com/pool-name: infra
|
|
|
|
runners:
|
|
cloneUrl: http://gitlab-webservice-default.foxhunt.svc.cluster.local:8181
|
|
config: |
|
|
[[runners]]
|
|
clone_url = "http://gitlab-webservice-default.foxhunt.svc.cluster.local:8181"
|
|
tag_list = ["kapsule", "l40s"]
|
|
[runners.kubernetes]
|
|
namespace = "foxhunt"
|
|
service_account = "gitlab-runner"
|
|
image = "rust:1.89-slim"
|
|
privileged = false
|
|
node_selector_overwrite_allowed = ".*"
|
|
# Hyperopt RL jobs need 6000m CPU + 20Gi mem (PSO parallel trials)
|
|
cpu_request_overwrite_max_allowed = "8000m"
|
|
cpu_limit_overwrite_max_allowed = "8000m"
|
|
memory_request_overwrite_max_allowed = "48Gi"
|
|
memory_limit_overwrite_max_allowed = "48Gi"
|
|
poll_timeout = 600
|
|
# All RL runner jobs target GPU nodes → set nvidia runtime globally
|
|
runtime_class_name = "nvidia"
|
|
# Allow CI jobs to set pod annotations (training jobs expose Prometheus metrics)
|
|
pod_annotations_overwrite_allowed = ".*"
|
|
# Default resources for RL training on L40S
|
|
cpu_request = "2000m"
|
|
cpu_limit = "3800m"
|
|
memory_request = "4Gi"
|
|
memory_limit = "8Gi"
|
|
helper_cpu_request = "100m"
|
|
helper_cpu_limit = "500m"
|
|
helper_memory_request = "128Mi"
|
|
helper_memory_limit = "512Mi"
|
|
image_pull_secrets = ["gitlab-registry"]
|
|
[runners.kubernetes.node_selector]
|
|
"k8s.scaleway.com/pool-name" = "ci-training"
|
|
[runners.kubernetes.node_tolerations]
|
|
"nvidia.com/gpu" = "NoSchedule"
|
|
"node.cilium.io/agent-not-ready" = "NoSchedule"
|
|
[runners.kubernetes.pod_labels]
|
|
"app.kubernetes.io/part-of" = "foxhunt-ci"
|
|
# Request GPU via K8s scheduler so only one training pod runs per GPU
|
|
[[runners.kubernetes.pod_spec]]
|
|
name = "build"
|
|
patch_type = "strategic"
|
|
patch = '{"containers":[{"name":"build","resources":{"requests":{"nvidia.com/gpu":"1"},"limits":{"nvidia.com/gpu":"1"}}}]}'
|
|
# Training PVCs — separate from main runner to avoid RWO Multi-Attach errors
|
|
[[runners.kubernetes.volumes.pvc]]
|
|
name = "training-data-l4-pvc"
|
|
mount_path = "/mnt/training-data"
|
|
read_only = true
|
|
[[runners.kubernetes.volumes.pvc]]
|
|
name = "sccache-l4-pvc"
|
|
mount_path = "/mnt/sccache"
|
|
read_only = false
|
|
|
|
tags: "kapsule,l40s"
|
|
|
|
concurrent: 2
|