wehub-resource-sync
128 lines
5.7 KiB
YAML
128 lines
5.7 KiB
YAML
# An unique identifier for the head node and workers of this cluster.
|
|
cluster_name: default
|
|
|
|
# The maximum number of workers nodes to launch in addition to the head
|
|
# node.
|
|
max_workers: 5
|
|
|
|
# The autoscaler will scale up the cluster faster with higher upscaling speed.
|
|
# E.g., if the task requires adding more nodes then autoscaler will gradually
|
|
# scale up the cluster in chunks of upscaling_speed*currently_running_nodes.
|
|
# This number should be > 0.
|
|
upscaling_speed: 1.0
|
|
|
|
# This executes all commands on all nodes in the docker container,
|
|
# and opens all the necessary ports to support the Ray cluster.
|
|
# Empty string means disabled.
|
|
docker:
|
|
image: "rayproject/ray-ml:latest"
|
|
# image: rayproject/ray:latest # use this one if you don't need ML dependencies, it's faster to pull
|
|
container_name: "ray_container"
|
|
# If true, pulls latest version of image. Otherwise, `docker run` will only pull the image
|
|
# if no cached version is present.
|
|
pull_before_run: True
|
|
run_options: # Extra options to pass into "docker run"
|
|
- --ulimit nofile=65536:65536
|
|
|
|
# If a node is idle for this many minutes, it will be removed.
|
|
idle_timeout_minutes: 5
|
|
|
|
# Cloud-provider specific configuration.
|
|
provider:
|
|
type: vsphere
|
|
|
|
# How Ray will authenticate with newly launched nodes.
|
|
auth:
|
|
ssh_user: ray
|
|
# By default Ray creates a new private keypair, but you can also use your own.
|
|
# If you do so, make sure to also set "KeyName" in the head and worker node
|
|
# configurations below.
|
|
ssh_private_key: ~/ray-bootstrap-key.pem
|
|
|
|
# Tell the autoscaler the allowed node types and the resources they provide.
|
|
# The key is the name of the node type, which is just for debugging purposes.
|
|
# The node config specifies the launch config and physical instance type.
|
|
available_node_types:
|
|
ray.head.default:
|
|
# You can override the resources here. Adding GPU to the head node is not recommended.
|
|
# resources: { "CPU": 2, "Memory": 4096}
|
|
resources: {}
|
|
node_config: {"vm_class": "best-effort-xlarge"}
|
|
worker:
|
|
# The minimum number of nodes of this type to launch.
|
|
# This number should be >= 0.
|
|
min_workers: 1
|
|
max_workers: 3
|
|
# You can override the resources here. For GPU, currently only NVIDIA GPU is supported. If no ESXi host can
|
|
# fulfill the requirement, the Ray node creation will fail. The number of created nodes may not meet the desired
|
|
# minimum number. The vSphere node provider will not distinguish the GPU type. It will just count the quantity:
|
|
# mount the first k random available NVIDIA GPU to the VM, if the user set {"GPU": k}.
|
|
# resources: {"CPU": 2, "Memory": 4096, "GPU": 1}
|
|
resources: {}
|
|
node_config: {"vm_class": "best-effort-xlarge"}
|
|
worker_2:
|
|
# The minimum number of nodes of this type to launch.
|
|
# This number should be >= 0.
|
|
min_workers: 1
|
|
max_workers: 2
|
|
# You can override the resources here. For GPU, currently only NVIDIA GPU is supported. If no ESXi host can
|
|
# fulfill the requirement, the Ray node creation will fail. The number of created nodes may not meet the desired
|
|
# minimum number. The vSphere node provider will not distinguish the GPU type. It will just count the quantity:
|
|
# mount the first k random available NVIDIA GPU to the VM, if the user set {"GPU": k}.
|
|
# resources: {"CPU": 2, "Memory": 4096, "GPU": 1}
|
|
resources: {}
|
|
node_config: {"vm_class": "best-effort-xlarge"}
|
|
|
|
# Specify the node type of the head node (as configured above).
|
|
head_node_type: ray.head.default
|
|
|
|
# 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",
|
|
}
|
|
|
|
# Files or directories to copy from the head node to the worker nodes. The format is a
|
|
# list of paths. The same path on the head node will be copied to the worker node.
|
|
# This behavior is a subset of the file_mounts behavior. In the vast majority of cases
|
|
# you should just use file_mounts. Only use this if you know what you're doing!
|
|
cluster_synced_files: []
|
|
|
|
# Whether changes to directories in file_mounts or cluster_synced_files in the head node
|
|
# should sync to the worker node continuously
|
|
file_mounts_sync_continuously: False
|
|
|
|
# Patterns for files to exclude when running rsync up or rsync down
|
|
rsync_exclude: []
|
|
|
|
# Pattern files to use for filtering out files when running rsync up or rsync down. The file is searched for
|
|
# in the source directory and recursively through all subdirectories. For example, if .gitignore is provided
|
|
# as a value, the behavior will match git's behavior for finding and using .gitignore files.
|
|
rsync_filter: []
|
|
|
|
# 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:
|
|
- pip install 'git+https://github.com/vmware/vsphere-automation-sdk-python.git'
|
|
|
|
# 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 --port=6379 --autoscaling-config=~/ray_bootstrap_config.yaml --dashboard-host=0.0.0.0
|
|
|
|
# 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 --address=$RAY_HEAD_IP:6379
|