-
Notifications
You must be signed in to change notification settings - Fork 402
/
ray-cluster.complete.yaml
135 lines (135 loc) · 6.13 KB
/
ray-cluster.complete.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
# The resource requests and limits in this config are too small for production!
# For examples with more realistic resource configuration, see
# ray-cluster.complete.large.yaml and
# ray-cluster.autoscaler.large.yaml.
apiVersion: ray.io/v1alpha1
kind: RayCluster
metadata:
labels:
controller-tools.k8s.io: "1.0"
# A unique identifier for the head node and workers of this cluster.
name: raycluster-complete
spec:
rayVersion: '2.3.0'
# Ray head pod configuration
headGroupSpec:
# Kubernetes Service Type. This is an optional field, and the default value is ClusterIP.
# Refer to https://kubernetes.io/docs/concepts/services-networking/service/#publishing-services-service-types.
serviceType: ClusterIP
# the following params are used to complete the ray start: ray start --head --block --dashboard-host: '0.0.0.0' ...
rayStartParams:
dashboard-host: '0.0.0.0'
block: 'true'
# pod template
template:
metadata:
# Custom labels. NOTE: To avoid conflicts with KubeRay operator, do not define custom labels start with `raycluster`.
# Refer to https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
labels: {}
spec:
containers:
- name: ray-head
image: rayproject/ray:2.3.0
ports:
- containerPort: 6379
name: gcs
- containerPort: 8265
name: dashboard
- containerPort: 10001
name: client
lifecycle:
preStop:
exec:
command: ["/bin/sh","-c","ray stop"]
volumeMounts:
- mountPath: /tmp/ray
name: ray-logs
# The resource requests and limits in this config are too small for production!
# For an example with more realistic resource configuration, see
# ray-cluster.autoscaler.large.yaml.
# It is better to use a few large Ray pod than many small ones.
# For production, it is ideal to size each Ray pod to take up the
# entire Kubernetes node on which it is scheduled.
resources:
limits:
cpu: "1"
memory: "2G"
requests:
# For production use-cases, we recommend specifying integer CPU reqests and limits.
# We also recommend setting requests equal to limits for both CPU and memory.
# For this example, we use a 500m CPU request to accomodate resource-constrained local
# Kubernetes testing environments such as KinD and minikube.
cpu: "500m"
memory: "2G"
volumes:
- name: ray-logs
emptyDir: {}
workerGroupSpecs:
# the pod replicas in this group typed worker
- replicas: 1
minReplicas: 1
maxReplicas: 10
# logical group name, for this called small-group, also can be functional
groupName: small-group
# If worker pods need to be added, we can increment the replicas.
# If worker pods need to be removed, we decrement the replicas, and populate the workersToDelete list.
# The operator will remove pods from the list until the desired number of replicas is satisfied.
# If the difference between the current replica count and the desired replicas is greater than the
# number of entries in workersToDelete, random worker pods will be deleted.
#scaleStrategy:
# workersToDelete:
# - raycluster-complete-worker-small-group-bdtwh
# - raycluster-complete-worker-small-group-hv457
# - raycluster-complete-worker-small-group-k8tj7
# the following params are used to complete the ray start: ray start --block
rayStartParams:
block: 'true'
#pod template
template:
spec:
containers:
- name: ray-worker
image: rayproject/ray:2.3.0
lifecycle:
preStop:
exec:
command: ["/bin/sh","-c","ray stop"]
# use volumeMounts.Optional.
# Refer to https://kubernetes.io/docs/concepts/storage/volumes/
volumeMounts:
- mountPath: /tmp/ray
name: ray-logs
# The resource requests and limits in this config are too small for production!
# For an example with more realistic resource configuration, see
# ray-cluster.autoscaler.large.yaml.
# It is better to use a few large Ray pod than many small ones.
# For production, it is ideal to size each Ray pod to take up the
# entire Kubernetes node on which it is scheduled.
resources:
limits:
cpu: "1"
memory: "1G"
# For production use-cases, we recommend specifying integer CPU reqests and limits.
# We also recommend setting requests equal to limits for both CPU and memory.
# For this example, we use a 500m CPU request to accomodate resource-constrained local
# Kubernetes testing environments such as KinD and minikube.
requests:
# For production use-cases, we recommend specifying integer CPU reqests and limits.
# We also recommend setting requests equal to limits for both CPU and memory.
# For this example, we use a 500m CPU request to accomodate resource-constrained local
# Kubernetes testing environments such as KinD and minikube.
cpu: "500m"
# For production use-cases, we recommend allocating at least 8Gb memory for each Ray container.
memory: "1G"
initContainers:
# the env var $FQ_RAY_IP is set by the operator if missing, with the value of the head service name
- name: init
image: busybox:1.28
# Change the cluster postfix if you don't have a default setting
command: ['sh', '-c', "until nslookup $RAY_IP.$(cat /var/run/secrets/kubernetes.io/serviceaccount/namespace).svc.cluster.local; do echo waiting for K8s Service $RAY_IP; sleep 2; done"]
# use volumes
# Refer to https://kubernetes.io/docs/concepts/storage/volumes/
volumes:
- name: ray-logs
emptyDir: {}
######################status#################################