85725abd8f
- DQN/PPO trainers now record epoch, loss, val_loss, batch/s every epoch - CI training jobs get Prometheus scrape annotations via runner overrides - Allow Prometheus (foxhunt namespace) to scrape foxhunt-ci pods - Skip no-model metrics in monitoring service session grouping Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
77 lines
2.6 KiB
YAML
77 lines
2.6 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: gitlab
|
|
tolerations:
|
|
- key: gitlab
|
|
operator: Equal
|
|
value: "true"
|
|
effect: NoSchedule
|
|
|
|
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", "gpu"]
|
|
[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 = ["scw-registry", "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"
|
|
# 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,gpu"
|
|
|
|
concurrent: 2
|