63 lines
1.8 KiB
YAML
63 lines
1.8 KiB
YAML
# DaemonSet image pre-puller — keeps training images cached on GPU nodes
|
|
# Runs on ci-rl (L4) and ci-training (L40S) pools so training jobs skip the pull.
|
|
# Init containers pull :latest tags, then the main container sleeps forever.
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: DaemonSet
|
|
metadata:
|
|
name: image-prepuller
|
|
namespace: foxhunt
|
|
labels:
|
|
app: image-prepuller
|
|
app.kubernetes.io/part-of: foxhunt
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
app: image-prepuller
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: image-prepuller
|
|
spec:
|
|
affinity:
|
|
nodeAffinity:
|
|
requiredDuringSchedulingIgnoredDuringExecution:
|
|
nodeSelectorTerms:
|
|
- matchExpressions:
|
|
- key: k8s.scaleway.com/pool-name
|
|
operator: In
|
|
values:
|
|
- ci-rl
|
|
- ci-compile # remove after terragrunt apply renames pool
|
|
- ci-training
|
|
tolerations:
|
|
- key: nvidia.com/gpu
|
|
operator: Exists
|
|
effect: NoSchedule
|
|
- key: node.cilium.io/agent-not-ready
|
|
operator: Exists
|
|
effect: NoSchedule
|
|
imagePullSecrets:
|
|
- name: scw-registry
|
|
initContainers:
|
|
- name: pull-training-runtime
|
|
image: rg.fr-par.scw.cloud/foxhunt-ci/foxhunt-training-runtime:latest
|
|
command: ["echo", "foxhunt-training-runtime image pulled"]
|
|
resources:
|
|
requests:
|
|
cpu: 10m
|
|
memory: 16Mi
|
|
limits:
|
|
cpu: 10m
|
|
memory: 16Mi
|
|
containers:
|
|
- name: pause
|
|
image: registry.k8s.io/pause:3.10
|
|
resources:
|
|
requests:
|
|
cpu: 10m
|
|
memory: 16Mi
|
|
limits:
|
|
cpu: 10m
|
|
memory: 16Mi
|