wehub/ray-project--ray
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

chore: import upstream snapshot with attribution

Browse Source
This commit is contained in:
wehub-resource-sync
2026-07-13 13:17:40 +08:00
commit f1825c8ceb
10096 changed files with 2364182 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/ray/tests/kuberay/test_files/podlist1.yaml
+607
View File
@@ -0,0 +1,607 @@
apiVersion: v1
items:
- apiVersion: v1
kind: Pod
metadata:
annotations:
ray.io/ft-enabled: "false"
ray.io/health-state: ""
creationTimestamp: "2022-11-14T23:10:15Z"
generateName: raycluster-autoscaler-head-
labels:
app.kubernetes.io/created-by: kuberay-operator
app.kubernetes.io/name: kuberay
ray.io/cluster: raycluster-autoscaler
ray.io/cluster-dashboard: raycluster-autoscaler-dashboard
ray.io/group: headgroup
ray.io/identifier: raycluster-autoscaler-head
ray.io/is-ray-node: "yes"
ray.io/node-type: head
name: raycluster-autoscaler-head-8zsc8
namespace: default
ownerReferences:
- apiVersion: ray.io/v1alpha1
blockOwnerDeletion: true
controller: true
kind: RayCluster
name: raycluster-autoscaler
uid: ec79effb-0295-4f40-b08b-8633aa7f786a
resourceVersion: "4519"
uid: 539ea57c-8d51-4503-a395-08779efb3bf0
spec:
containers:
- args:
- 'ulimit -n 65536; ray start --head --resources="{\"Custom1\": 1, \"Custom2\":
5}" --block --dashboard-host=0.0.0.0 --metrics-export-port=8080 --no-monitor --num-cpus=1 --memory=1000000000 '
command:
- /bin/bash
- -c
- --
env:
- name: RAY_IP
value: 127.0.0.1
- name: RAY_PORT
value: "6379"
- name: RAY_ADDRESS
value: 127.0.0.1:6379
- name: REDIS_PASSWORD
image: gekho/ray
imagePullPolicy: Always
lifecycle:
preStop:
exec:
command:
- /bin/sh
- -c
- ray stop
name: ray-head
ports:
- containerPort: 6379
name: gcs
protocol: TCP
- containerPort: 8265
name: dashboard
protocol: TCP
- containerPort: 10001
name: client
protocol: TCP
- containerPort: 8080
name: metrics
protocol: TCP
resources:
limits:
cpu: "1"
memory: 1G
requests:
cpu: 500m
memory: 512Mi
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /dev/shm
name: shared-mem
- mountPath: /tmp/ray
name: ray-logs
- mountPath: /var/run/secrets/kubernetes.io/serviceaccount
name: kube-api-access-tmxvr
readOnly: true
- args:
- kuberay-autoscaler
- --cluster-name
- $(RAY_CLUSTER_NAME)
- --cluster-namespace
- $(RAY_CLUSTER_NAMESPACE)
command:
- ray
env:
- name: RAY_CLUSTER_NAME
valueFrom:
fieldRef:
apiVersion: v1
fieldPath: metadata.labels['ray.io/cluster']
- name: RAY_CLUSTER_NAMESPACE
valueFrom:
fieldRef:
apiVersion: v1
fieldPath: metadata.namespace
image: gekho/ray
imagePullPolicy: Always
name: autoscaler
resources:
limits:
cpu: 500m
memory: 512Mi
requests:
cpu: 500m
memory: 512Mi
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /tmp/ray
name: ray-logs
- mountPath: /var/run/secrets/kubernetes.io/serviceaccount
name: kube-api-access-tmxvr
readOnly: true
dnsPolicy: ClusterFirst
enableServiceLinks: true
nodeName: gke-cluster-1-default-pool-a5503908-181p
preemptionPolicy: PreemptLowerPriority
priority: 0
restartPolicy: Always
schedulerName: default-scheduler
securityContext: {}
serviceAccount: raycluster-autoscaler
serviceAccountName: raycluster-autoscaler
terminationGracePeriodSeconds: 30
tolerations:
- effect: NoExecute
key: node.kubernetes.io/not-ready
operator: Exists
tolerationSeconds: 300
- effect: NoExecute
key: node.kubernetes.io/unreachable
operator: Exists
tolerationSeconds: 300
volumes:
- emptyDir:
medium: Memory
sizeLimit: 512Mi
name: shared-mem
- emptyDir: {}
name: ray-logs
- name: kube-api-access-tmxvr
projected:
defaultMode: 420
sources:
- serviceAccountToken:
expirationSeconds: 3607
path: token
- configMap:
items:
- key: ca.crt
path: ca.crt
name: kube-root-ca.crt
- downwardAPI:
items:
- fieldRef:
apiVersion: v1
fieldPath: metadata.namespace
path: namespace
status:
conditions:
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:10:15Z"
status: "True"
type: Initialized
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:11:23Z"
status: "True"
type: Ready
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:11:23Z"
status: "True"
type: ContainersReady
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:10:15Z"
status: "True"
type: PodScheduled
containerStatuses:
- containerID: containerd://0b008432be839bec8dd97437d3f2be9ac8d7f017b91067a46ec45a487f141ebf
image: docker.io/gekho/ray:latest
imageID: docker.io/gekho/ray@sha256:7859a78d1a089bb88691864d5c4a2aad529f5353d7d9c82cc0274842fbda242b
lastState: {}
name: autoscaler
ready: true
restartCount: 0
started: true
state:
running:
startedAt: "2022-11-14T23:11:23Z"
- containerID: containerd://b2aae80ed028cc41bad1e350bb70a0a4e8ea722df098b38781efabe54adbc5ec
image: docker.io/gekho/ray:latest
imageID: docker.io/gekho/ray@sha256:7859a78d1a089bb88691864d5c4a2aad529f5353d7d9c82cc0274842fbda242b
lastState: {}
name: ray-head
ready: true
restartCount: 0
started: true
state:
running:
startedAt: "2022-11-14T23:11:22Z"
hostIP: 10.128.0.45
phase: Running
podIP: 10.4.2.6
podIPs:
- ip: 10.4.2.6
qosClass: Burstable
startTime: "2022-11-14T23:10:15Z"
- apiVersion: v1
kind: Pod
metadata:
annotations:
key: value
ray.io/ft-enabled: "false"
ray.io/health-state: ""
creationTimestamp: "2022-11-14T23:11:45Z"
deletionGracePeriodSeconds: 30
deletionTimestamp: "2022-11-14T23:12:20Z"
generateName: raycluster-autoscaler-worker-small-group-
labels:
app.kubernetes.io/created-by: kuberay-operator
app.kubernetes.io/name: kuberay
key: value
ray.io/cluster: raycluster-autoscaler
ray.io/cluster-dashboard: raycluster-autoscaler-dashboard
ray.io/group: small-group
ray.io/identifier: raycluster-autoscaler-worker
ray.io/is-ray-node: "yes"
ray.io/node-type: worker
name: raycluster-autoscaler-worker-small-group-4wxfm
namespace: default
ownerReferences:
- apiVersion: ray.io/v1alpha1
blockOwnerDeletion: true
controller: true
kind: RayCluster
name: raycluster-autoscaler
uid: ec79effb-0295-4f40-b08b-8633aa7f786a
resourceVersion: "4845"
uid: 3698ed9b-7e06-4d47-b9f6-09e4bd08365a
spec:
containers:
- args:
- 'ulimit -n 65536; ray start --resources="{\"Custom1\": 1, \"Custom2\": 5}" --address=raycluster-autoscaler-head-svc:6379 --metrics-export-port=8080 --num-cpus=1 --memory=536870912 --block '
command:
- /bin/bash
- -c
- --
env:
- name: RAY_IP
value: raycluster-autoscaler-head-svc
- name: RAY_PORT
value: "6379"
- name: RAY_ADDRESS
value: raycluster-autoscaler-head-svc:6379
- name: REDIS_PASSWORD
image: gekho/ray
imagePullPolicy: Always
lifecycle:
preStop:
exec:
command:
- /bin/sh
- -c
- ray stop
name: machine-learning
ports:
- containerPort: 8080
name: metrics
protocol: TCP
resources:
limits:
cpu: "1"
memory: 512Mi
requests:
cpu: 500m
memory: 256Mi
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /dev/shm
name: shared-mem
- mountPath: /var/run/secrets/kubernetes.io/serviceaccount
name: kube-api-access-wthw9
readOnly: true
dnsPolicy: ClusterFirst
enableServiceLinks: true
initContainers:
- command:
- sh
- -c
- until nslookup $RAY_IP.$(cat /var/run/secrets/kubernetes.io/serviceaccount/namespace).svc.cluster.local;
do echo waiting for myservice; sleep 2; done
env:
- name: RAY_IP
value: raycluster-autoscaler-head-svc
image: busybox:1.28
imagePullPolicy: IfNotPresent
name: init-myservice
resources: {}
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /var/run/secrets/kubernetes.io/serviceaccount
name: kube-api-access-wthw9
readOnly: true
nodeName: gke-cluster-1-default-pool-a5503908-dpst
preemptionPolicy: PreemptLowerPriority
priority: 0
restartPolicy: Always
schedulerName: default-scheduler
securityContext: {}
serviceAccount: default
serviceAccountName: default
terminationGracePeriodSeconds: 30
tolerations:
- effect: NoExecute
key: node.kubernetes.io/not-ready
operator: Exists
tolerationSeconds: 300
- effect: NoExecute
key: node.kubernetes.io/unreachable
operator: Exists
tolerationSeconds: 300
volumes:
- emptyDir:
medium: Memory
sizeLimit: 256Mi
name: shared-mem
- name: kube-api-access-wthw9
projected:
defaultMode: 420
sources:
- serviceAccountToken:
expirationSeconds: 3607
path: token
- configMap:
items:
- key: ca.crt
path: ca.crt
name: kube-root-ca.crt
- downwardAPI:
items:
- fieldRef:
apiVersion: v1
fieldPath: metadata.namespace
path: namespace
status:
conditions:
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:11:47Z"
status: "True"
type: Initialized
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:11:45Z"
message: 'containers with unready status: [machine-learning]'
reason: ContainersNotReady
status: "False"
type: Ready
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:11:45Z"
message: 'containers with unready status: [machine-learning]'
reason: ContainersNotReady
status: "False"
type: ContainersReady
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:11:45Z"
status: "True"
type: PodScheduled
containerStatuses:
- image: gekho/ray
imageID: ""
lastState: {}
name: machine-learning
ready: false
restartCount: 0
started: false
state:
waiting:
reason: PodInitializing
hostIP: 10.128.0.31
initContainerStatuses:
- containerID: containerd://c7f5a0c3f63957213213ed1ebb6446cd205bd60346d010a879c5fa24e37f5145
image: docker.io/library/busybox:1.28
imageID: docker.io/library/busybox@sha256:141c253bc4c3fd0a201d32dc1f493bcf3fff003b6df416dea4f41046e0f37d47
lastState: {}
name: init-myservice
ready: true
restartCount: 0
state:
terminated:
containerID: containerd://c7f5a0c3f63957213213ed1ebb6446cd205bd60346d010a879c5fa24e37f5145
exitCode: 0
finishedAt: "2022-11-14T23:11:47Z"
reason: Completed
startedAt: "2022-11-14T23:11:47Z"
phase: Pending
podIP: 10.4.0.4
podIPs:
- ip: 10.4.0.4
qosClass: Burstable
startTime: "2022-11-14T23:11:45Z"
- apiVersion: v1
kind: Pod
metadata:
annotations:
key: value
ray.io/ft-enabled: "false"
ray.io/health-state: ""
creationTimestamp: "2022-11-14T23:11:50Z"
generateName: raycluster-autoscaler-worker-small-group-
labels:
app.kubernetes.io/created-by: kuberay-operator
app.kubernetes.io/name: kuberay
key: value
ray.io/cluster: raycluster-autoscaler
ray.io/cluster-dashboard: raycluster-autoscaler-dashboard
ray.io/group: small-group
ray.io/identifier: raycluster-autoscaler-worker
ray.io/is-ray-node: "yes"
ray.io/node-type: worker
name: raycluster-autoscaler-worker-small-group-dkz2r
namespace: default
ownerReferences:
- apiVersion: ray.io/v1alpha1
blockOwnerDeletion: true
controller: true
kind: RayCluster
name: raycluster-autoscaler
uid: ec79effb-0295-4f40-b08b-8633aa7f786a
resourceVersion: "4776"
uid: b4fb3233-6024-48a8-9f4f-a18f5e490629
spec:
containers:
- args:
- 'ulimit -n 65536; ray start --block --resources="{\"Custom1\": 1, \"Custom2\":
5}" --address=raycluster-autoscaler-head-svc:6379 --metrics-export-port=8080 --num-cpus=1 --memory=536870912 '
command:
- /bin/bash
- -c
- --
env:
- name: RAY_IP
value: raycluster-autoscaler-head-svc
- name: RAY_PORT
value: "6379"
- name: RAY_ADDRESS
value: raycluster-autoscaler-head-svc:6379
- name: REDIS_PASSWORD
image: gekho/ray
imagePullPolicy: Always
lifecycle:
preStop:
exec:
command:
- /bin/sh
- -c
- ray stop
name: machine-learning
ports:
- containerPort: 8080
name: metrics
protocol: TCP
resources:
limits:
cpu: "1"
memory: 512Mi
requests:
cpu: 500m
memory: 256Mi
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /dev/shm
name: shared-mem
- mountPath: /var/run/secrets/kubernetes.io/serviceaccount
name: kube-api-access-djtd9
readOnly: true
dnsPolicy: ClusterFirst
enableServiceLinks: true
initContainers:
- command:
- sh
- -c
- until nslookup $RAY_IP.$(cat /var/run/secrets/kubernetes.io/serviceaccount/namespace).svc.cluster.local;
do echo waiting for myservice; sleep 2; done
env:
- name: RAY_IP
value: raycluster-autoscaler-head-svc
image: busybox:1.28
imagePullPolicy: IfNotPresent
name: init-myservice
resources: {}
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
volumeMounts:
- mountPath: /var/run/secrets/kubernetes.io/serviceaccount
name: kube-api-access-djtd9
readOnly: true
nodeName: gke-cluster-1-default-pool-a5503908-j51d
preemptionPolicy: PreemptLowerPriority
priority: 0
restartPolicy: Always
schedulerName: default-scheduler
securityContext: {}
serviceAccount: default
serviceAccountName: default
terminationGracePeriodSeconds: 30
tolerations:
- effect: NoExecute
key: node.kubernetes.io/not-ready
operator: Exists
tolerationSeconds: 300
- effect: NoExecute
key: node.kubernetes.io/unreachable
operator: Exists
tolerationSeconds: 300
volumes:
- emptyDir:
medium: Memory
sizeLimit: 256Mi
name: shared-mem
- name: kube-api-access-djtd9
projected:
defaultMode: 420
sources:
- serviceAccountToken:
expirationSeconds: 3607
path: token
- configMap:
items:
- key: ca.crt
path: ca.crt
name: kube-root-ca.crt
- downwardAPI:
items:
- fieldRef:
apiVersion: v1
fieldPath: metadata.namespace
path: namespace
status:
conditions:
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:11:51Z"
status: "True"
type: Initialized
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:11:50Z"
message: 'containers with unready status: [machine-learning]'
reason: ContainersNotReady
status: "False"
type: Ready
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:11:50Z"
message: 'containers with unready status: [machine-learning]'
reason: ContainersNotReady
status: "False"
type: ContainersReady
- lastProbeTime: null
lastTransitionTime: "2022-11-14T23:11:50Z"
status: "True"
type: PodScheduled
containerStatuses:
- image: gekho/ray
imageID: ""
lastState: {}
name: machine-learning
ready: false
restartCount: 0
started: false
state:
waiting:
reason: PodInitializing
hostIP: 10.128.0.43
initContainerStatuses:
- containerID: containerd://672d9a5836e27a17f57a4e15e1d86431cfee6f2edef1210d60e864e3c510aac0
image: docker.io/library/busybox:1.28
imageID: docker.io/library/busybox@sha256:141c253bc4c3fd0a201d32dc1f493bcf3fff003b6df416dea4f41046e0f37d47
lastState: {}
name: init-myservice
ready: true
restartCount: 0
state:
terminated:
containerID: containerd://672d9a5836e27a17f57a4e15e1d86431cfee6f2edef1210d60e864e3c510aac0
exitCode: 0
finishedAt: "2022-11-14T23:11:51Z"
reason: Completed
startedAt: "2022-11-14T23:11:51Z"
phase: Pending
podIP: 10.4.1.8
podIPs:
- ip: 10.4.1.8
qosClass: Burstable
startTime: "2022-11-14T23:11:50Z"
kind: List
metadata:
resourceVersion: ""
python/ray/tests/kuberay/test_files/podlist2.yaml
+1261
View File
File diff suppressed because it is too large Load Diff
python/ray/tests/kuberay/test_files/ray-cluster.autoscaler-template.yaml
+73
View File
@@ -0,0 +1,73 @@
# `ray-cluster.autoscaler-template.yaml` is a template for the RayCluster CR and
# is used by the function `_get_ray_cr_config` in `test_autoscaling_e2e.py`.
# [Note]
# (1) The VM test runner only has 4 CPUs, so we lower the CPU requests.
# (2) `test_autoscaling_e2e.py` assumes that each Ray Pod has 1 logical CPU.
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:
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"
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"
python/ray/tests/kuberay/test_files/ray-cluster.autoscaler-v2-template.yaml
+76
View File
@@ -0,0 +1,76 @@
# 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