wehub-resource-sync
77 lines
2.3 KiB
YAML
77 lines
2.3 KiB
YAML
# This is a copy from the `ray-cluster.autoscaler-template.yaml` with modifications needed
|
|
# to make kuberary work with Ray's Autoscaler V2.
|
|
# See more at `ray-cluster.autoscaler-template.yaml` for the non autoscaler-v2 definition.
|
|
apiVersion: ray.io/v1
|
|
kind: RayCluster
|
|
metadata:
|
|
name: raycluster-autoscaler
|
|
spec:
|
|
# The version of Ray you are using. Make sure all Ray containers are running this version of Ray.
|
|
rayVersion: '2.46.0'
|
|
# If `enableInTreeAutoscaling` is true, the Autoscaler sidecar will be added to the Ray head pod.
|
|
# Ray Autoscaler integration is Beta with KubeRay >= 0.3.0 and Ray >= 2.0.0.
|
|
enableInTreeAutoscaling: true
|
|
autoscalerOptions:
|
|
# Use version: v2 instead of env var RAY_enable_autoscaler_v2 and restartPolicy: Never below if
|
|
# you're using KubeRay >= 1.4.0.
|
|
version: v2
|
|
upscalingMode: Default
|
|
idleTimeoutSeconds: 60
|
|
imagePullPolicy: IfNotPresent
|
|
resources:
|
|
limits:
|
|
cpu: "500m"
|
|
memory: "512Mi"
|
|
requests:
|
|
cpu: "500m"
|
|
memory: "512Mi"
|
|
headGroupSpec:
|
|
template:
|
|
spec:
|
|
containers:
|
|
- name: ray-head
|
|
image: rayproject/ray:2.46.0
|
|
ports:
|
|
- containerPort: 6379
|
|
name: gcs
|
|
- containerPort: 8265
|
|
name: dashboard
|
|
- containerPort: 10001
|
|
name: client
|
|
imagePullPolicy: IfNotPresent
|
|
lifecycle:
|
|
preStop:
|
|
exec:
|
|
command: ["/bin/sh","-c","ray stop"]
|
|
resources:
|
|
limits:
|
|
cpu: "1"
|
|
memory: "2G"
|
|
requests:
|
|
cpu: "500m"
|
|
memory: "2G"
|
|
restartPolicy: Never # No restart to avoid reuse of pod for different ray nodes.
|
|
workerGroupSpecs:
|
|
- replicas: 1
|
|
minReplicas: 1
|
|
maxReplicas: 10
|
|
groupName: small-group
|
|
template:
|
|
spec:
|
|
containers:
|
|
- name: ray-worker
|
|
image: rayproject/ray:2.46.0
|
|
lifecycle:
|
|
preStop:
|
|
exec:
|
|
command: ["/bin/sh","-c","ray stop"]
|
|
imagePullPolicy: IfNotPresent
|
|
resources:
|
|
limits:
|
|
cpu: "1"
|
|
memory: "1G"
|
|
requests:
|
|
cpu: "500m"
|
|
memory: "1G"
|
|
restartPolicy: Never # Never restart a pod to avoid pod reuse
|