Skip to content
Permalink
Branch: master
Find file Copy path
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
246 lines (216 sloc) 9.75 KB
# An unique identifier for the head node and workers of this cluster.
cluster_name: default
# The minimum number of workers nodes to launch in addition to the head
# node. This number should be >= 0.
min_workers: 0
# The maximum number of workers nodes to launch in addition to the head
# node. This takes precedence over min_workers.
max_workers: 2
# The initial number of worker nodes to launch in addition to the head
# node. When the cluster is first brought up (or when it is refreshed with a
# subsequent `ray up`) this number of nodes will be started.
initial_workers: 0
# Whether or not to autoscale aggressively. If this is enabled, if at any point
# we would start more workers, we start at least enough to bring us to
# initial_workers.
autoscaling_mode: default
# The autoscaler will scale up the cluster to this target fraction of resource
# usage. For example, if a cluster of 10 nodes is 100% busy and
# target_utilization is 0.8, it would resize the cluster to 13. This fraction
# can be decreased to increase the aggressiveness of upscaling.
# This value must be less than 1.0 for scaling to happen.
target_utilization_fraction: 0.8
# If a node is idle for this many minutes, it will be removed.
idle_timeout_minutes: 5
# Kubernetes resources that need to be configured for the autoscaler to be
# able to manage the Ray cluster. If any of the provided resources don't
# exist, the autoscaler will attempt to create them. If this fails, you may
# not have the required permissions and will have to request them to be
# created by your cluster administrator.
provider:
type: kubernetes
# Exposing external IP addresses for ray pods isn't currently supported.
use_internal_ips: true
# Namespace to use for all resources created.
namespace: ray
# ServiceAccount created by the autoscaler for the head node pod that it
# runs in. If this field isn't provided, the head pod config below must
# contain a user-created service account with the proper permissions.
autoscaler_service_account:
apiVersion: v1
kind: ServiceAccount
metadata:
name: autoscaler
# Role created by the autoscaler for the head node pod that it runs in.
# If this field isn't provided, the role referenced in
# autoscaler_role_binding must exist and have at least these permissions.
autoscaler_role:
kind: Role
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: autoscaler
rules:
- apiGroups: [""]
resources: ["pods", "pods/status", "pods/exec"]
verbs: ["get", "watch", "list", "create", "delete", "patch"]
# RoleBinding created by the autoscaler for the head node pod that it runs
# in. If this field isn't provided, the head pod config below must contain
# a user-created service account with the proper permissions.
autoscaler_role_binding:
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
name: autoscaler
subjects:
- kind: ServiceAccount
name: autoscaler
roleRef:
kind: Role
name: autoscaler
apiGroup: rbac.authorization.k8s.io
# Kubernetes pod config for the head node pod.
head_node:
apiVersion: v1
kind: Pod
metadata:
# Automatically generates a name for the pod with this prefix.
generateName: ray-head-
spec:
# Change this if you altered the autoscaler_service_account above
# or want to provide your own.
serviceAccountName: autoscaler
# Restarting the head node automatically is not currently supported.
# If the head node goes down, `ray up` must be run again.
restartPolicy: Never
# This volume allocates shared memory for Ray to use for its plasma
# object store. If you do not provide this, Ray will fall back to
# /tmp which cause slowdowns if is not a shared memory volume.
volumes:
- name: dshm
emptyDir:
medium: Memory
containers:
- name: ray-node
imagePullPolicy: Always
# You are free (and encouraged) to use your own container image,
# but it should have the following installed:
# - rsync (used for `ray rsync` commands and file mounts)
# - screen (used for `ray attach`)
# - kubectl (used by the autoscaler to manage worker pods)
image: rayproject/autoscaler
# Do not change this command - it keeps the pod alive until it is
# explicitly killed.
command: ["/bin/bash", "-c", "--"]
args: ["trap : TERM INT; sleep infinity & wait;"]
ports:
- containerPort: 6379 # Redis port.
- containerPort: 6380 # Redis port.
- containerPort: 6381 # Redis port.
- containerPort: 12345 # Ray internal communication.
- containerPort: 12346 # Ray internal communication.
# This volume allocates shared memory for Ray to use for its plasma
# object store. If you do not provide this, Ray will fall back to
# /tmp which cause slowdowns if is not a shared memory volume.
volumeMounts:
- mountPath: /dev/shm
name: dshm
resources:
requests:
cpu: 1000m
memory: 512Mi
limits:
# The maximum memory that this pod is allowed to use. The
# limit will be detected by ray and split to use 10% for
# redis, 30% for the shared memory object store, and the
# rest for application memory. If this limit is not set and
# the object store size is not set manually, ray will
# allocate a very large object store in each pod that may
# cause problems for other pods.
memory: 2Gi
env:
# This is used in the head_start_ray_commands below so that
# Ray can spawn the correct number of processes. Omitting this
# may lead to degraded performance.
- name: MY_CPU_REQUEST
valueFrom:
resourceFieldRef:
resource: requests.cpu
# Kubernetes pod config for worker node pods.
worker_nodes:
apiVersion: v1
kind: Pod
metadata:
# Automatically generates a name for the pod with this prefix.
generateName: ray-worker-
spec:
serviceAccountName: default
# Worker nodes will be managed automatically by the head node, so
# do not change the restart policy.
restartPolicy: Never
# This volume allocates shared memory for Ray to use for its plasma
# object store. If you do not provide this, Ray will fall back to
# /tmp which cause slowdowns if is not a shared memory volume.
volumes:
- name: dshm
emptyDir:
medium: Memory
containers:
- name: ray-node
imagePullPolicy: Always
# You are free (and encouraged) to use your own container image,
# but it should have the following installed:
# - rsync (used for `ray rsync` commands and file mounts)
image: rayproject/autoscaler
# Do not change this command - it keeps the pod alive until it is
# explicitly killed.
command: ["/bin/bash", "-c", "--"]
args: ["trap : TERM INT; sleep infinity & wait;"]
ports:
- containerPort: 12345 # Ray internal communication.
- containerPort: 12346 # Ray internal communication.
# This volume allocates shared memory for Ray to use for its plasma
# object store. If you do not provide this, Ray will fall back to
# /tmp which cause slowdowns if is not a shared memory volume.
volumeMounts:
- mountPath: /dev/shm
name: dshm
resources:
requests:
cpu: 1000m
memory: 512Mi
limits:
# This memory limit will be detected by ray and split into
# 30% for plasma, and 70% for workers.
memory: 2Gi
env:
# This is used in the head_start_ray_commands below so that
# Ray can spawn the correct number of processes. Omitting this
# may lead to degraded performance.
- name: MY_CPU_REQUEST
valueFrom:
resourceFieldRef:
resource: requests.cpu
# Files or directories to copy to the head and worker nodes. The format is a
# dictionary from REMOTE_PATH: LOCAL_PATH, e.g.
file_mounts: {
# "/path1/on/remote/machine": "/path1/on/local/machine",
# "/path2/on/remote/machine": "/path2/on/local/machine",
}
# List of commands that will be run before `setup_commands`. If docker is
# enabled, these commands will run outside the container and before docker
# is setup.
initialization_commands: []
# List of shell commands to run to set up nodes.
setup_commands: []
# Custom commands that will be run on the head node after common setup.
head_setup_commands: []
# Custom commands that will be run on worker nodes after common setup.
worker_setup_commands: []
# Command to start ray on the head node. You don't need to change this.
head_start_ray_commands:
- ray stop
- ulimit -n 65536; ray start --head --num-cpus=$MY_CPU_REQUEST --redis-port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml
# Command to start ray on worker nodes. You don't need to change this.
worker_start_ray_commands:
- ray stop
- ulimit -n 65536; ray start --num-cpus=$MY_CPU_REQUEST --redis-address=$RAY_HEAD_IP:6379 --object-manager-port=8076
You can’t perform that action at this time.