cluster_name: asedler_nesu
​
## NOTE: Typically for local clusters, min_workers == initial_workers == max_workers.
​
# The minimum number of workers nodes to launch in addition to the head
# node. This number should be >= 0.
# Typically, min_workers == initial_workers == max_workers.
min_workers: 1
# The initial number of worker nodes to launch in addition to the head node.
# Typically, min_workers == initial_workers == max_workers.
initial_workers: 1
​
# The maximum number of workers nodes to launch in addition to the head node.
# This takes precedence over min_workers.
# Typically, min_workers == initial_workers == max_workers.
max_workers: 1
​
# Autoscaling parameters.
# Ignore this if min_workers == initial_workers == max_workers.
autoscaling_mode: default
target_utilization_fraction: 0.8
idle_timeout_minutes: 5
​
# 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. Assumes Docker is installed.
docker:
    image: "" # e.g., tensorflow/tensorflow:1.5.0-py3
    container_name: "" # e.g. ray_docker
    # 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"
​
# Local specific configuration.
provider:
    type: local
    head_ip: neuron.bme.emory.edu
    worker_ips: 
        - sulcus.bme.emory.edu
​
# How Ray will authenticate with newly launched nodes.
auth:
    ssh_user: asedler
    ssh_private_key: ~/.ssh/id_rsa
​
# Leave this empty.
head_node: {}
​
# Leave this empty.
worker_nodes: {}
​
# 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 each 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: []
​
# NOTE: Modified the following commands to use the tf2-gpu environment 
# and to use specific ports that have been opened for this purpose
# by Andrew Sedler (asedler3@gatech.edu)
​
# Command to start ray on the head node. You don't need to change this.
head_start_ray_commands:
    - conda activate tf2-gpu && ray stop
    - conda activate tf2-gpu && ulimit -c unlimited && ray start --head --redis-port=6379 --redis-shard-ports=59519 --node-manager-port=19580 --object-manager-port=39066 --autoscaling-config=~/ray_bootstrap_config.yaml
​
# Command to start ray on worker nodes. You don't need to change this.
worker_start_ray_commands:
    - conda activate tf2-gpu && ray stop
    - conda activate tf2-gpu && ray start --redis-address=$RAY_HEAD_IP:6379 --node-manager-port=19580 --object-manager-port=39066

ray.init(address="localhost:6379")
import time
from pprint import pprint
@ray.remote
def f():
    time.sleep(0.01)
    return ray.services.get_node_ip_address()
# Get a list of the IP addresses of the nodes that have joined the cluster.
pprint(set(ray.get([f.remote() for _ in range(1000)])))