mirror of
https://github.com/vale981/ray
synced 2025-03-06 10:31:39 -05:00
64 lines
2.1 KiB
Bash
64 lines
2.1 KiB
Bash
#!/bin/bash
|
|
# shellcheck disable=SC2206
|
|
# THIS FILE IS GENERATED BY AUTOMATION SCRIPT! PLEASE REFER TO ORIGINAL SCRIPT!
|
|
# THIS FILE IS A TEMPLATE AND IT SHOULD NOT BE DEPLOYED TO PRODUCTION!
|
|
${PARTITION_OPTION}
|
|
#SBATCH --job-name=${JOB_NAME}
|
|
#SBATCH --output=${JOB_NAME}.log
|
|
${GIVEN_NODE}
|
|
### This script works for any number of nodes, Ray will find and manage all resources
|
|
#SBATCH --nodes=${NUM_NODES}
|
|
#SBATCH --exclusive
|
|
### Give all resources to a single Ray task, ray can manage the resources internally
|
|
#SBATCH --ntasks-per-node=1
|
|
#SBATCH --gpus-per-task=${NUM_GPUS_PER_NODE}
|
|
|
|
# Load modules or your own conda environment here
|
|
# module load pytorch/v1.4.0-gpu
|
|
# conda activate ${CONDA_ENV}
|
|
${LOAD_ENV}
|
|
|
|
# ===== DO NOT CHANGE THINGS HERE UNLESS YOU KNOW WHAT YOU ARE DOING =====
|
|
# This script is a modification to the implementation suggest by gregSchwartz18 here:
|
|
# https://github.com/ray-project/ray/issues/826#issuecomment-522116599
|
|
redis_password=$(uuidgen)
|
|
export redis_password
|
|
|
|
nodes=$(scontrol show hostnames "$SLURM_JOB_NODELIST") # Getting the node names
|
|
nodes_array=($nodes)
|
|
|
|
node_1=${nodes_array[0]}
|
|
ip=$(srun --nodes=1 --ntasks=1 -w "$node_1" hostname --ip-address) # making redis-address
|
|
|
|
# if we detect a space character in the head node IP, we'll
|
|
# convert it to an ipv4 address. This step is optional.
|
|
if [[ "$ip" == *" "* ]]; then
|
|
IFS=' ' read -ra ADDR <<< "$ip"
|
|
if [[ ${#ADDR[0]} -gt 16 ]]; then
|
|
ip=${ADDR[1]}
|
|
else
|
|
ip=${ADDR[0]}
|
|
fi
|
|
echo "IPV6 address detected. We split the IPV4 address as $ip"
|
|
fi
|
|
|
|
port=6379
|
|
ip_head=$ip:$port
|
|
export ip_head
|
|
echo "IP Head: $ip_head"
|
|
|
|
echo "STARTING HEAD at $node_1"
|
|
srun --nodes=1 --ntasks=1 -w "$node_1" \
|
|
ray start --head --node-ip-address="$ip" --port=$port --redis-password="$redis_password" --block &
|
|
sleep 30
|
|
|
|
worker_num=$((SLURM_JOB_NUM_NODES - 1)) #number of nodes other than the head node
|
|
for ((i = 1; i <= worker_num; i++)); do
|
|
node_i=${nodes_array[$i]}
|
|
echo "STARTING WORKER $i at $node_i"
|
|
srun --nodes=1 --ntasks=1 -w "$node_i" ray start --address "$ip_head" --redis-password="$redis_password" --block &
|
|
sleep 5
|
|
done
|
|
|
|
# ===== Call your code below =====
|
|
${COMMAND_PLACEHOLDER}
|