mirror of
https://github.com/vale981/ray
synced 2025-03-06 10:31:39 -05:00
65 lines
No EOL
1.8 KiB
Bash
65 lines
No EOL
1.8 KiB
Bash
#!/bin/bash
|
|
# shellcheck disable=SC2206
|
|
#SBATCH --job-name=test
|
|
#SBATCH --cpus-per-task=5
|
|
#SBATCH --mem-per-cpu=1GB
|
|
#SBATCH --nodes=4
|
|
#SBATCH --tasks-per-node=1
|
|
#SBATCH --time=00:30:00
|
|
|
|
set -x
|
|
|
|
# __doc_head_address_start__
|
|
|
|
# Getting the node names
|
|
nodes=$(scontrol show hostnames "$SLURM_JOB_NODELIST")
|
|
nodes_array=($nodes)
|
|
|
|
head_node=${nodes_array[0]}
|
|
head_node_ip=$(srun --nodes=1 --ntasks=1 -w "$head_node" hostname --ip-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 [[ "$head_node_ip" == *" "* ]]; then
|
|
IFS=' ' read -ra ADDR <<<"$head_node_ip"
|
|
if [[ ${#ADDR[0]} -gt 16 ]]; then
|
|
head_node_ip=${ADDR[1]}
|
|
else
|
|
head_node_ip=${ADDR[0]}
|
|
fi
|
|
echo "IPV6 address detected. We split the IPV4 address as $head_node_ip"
|
|
fi
|
|
# __doc_head_address_end__
|
|
|
|
# __doc_head_ray_start__
|
|
port=6379
|
|
ip_head=$head_node_ip:$port
|
|
export ip_head
|
|
echo "IP Head: $ip_head"
|
|
|
|
echo "Starting HEAD at $head_node"
|
|
srun --nodes=1 --ntasks=1 -w "$head_node" \
|
|
ray start --head --node-ip-address="$head_node_ip" --port=$port \
|
|
--num-cpus "${SLURM_CPUS_PER_TASK}" --num-gpus "${SLURM_GPUS_PER_TASK}" --block &
|
|
# __doc_head_ray_end__
|
|
|
|
# __doc_worker_ray_start__
|
|
# optional, though may be useful in certain versions of Ray < 1.0.
|
|
sleep 10
|
|
|
|
# number of nodes other than the head node
|
|
worker_num=$((SLURM_JOB_NUM_NODES - 1))
|
|
|
|
for ((i = 1; i <= worker_num; i++)); do
|
|
node_i=${nodes_array[$i]}
|
|
echo "Starting WORKER $i at $node_i"
|
|
srun --nodes=1 --ntasks=1 -w "$node_i" \
|
|
ray start --address "$ip_head" \
|
|
--num-cpus "${SLURM_CPUS_PER_TASK}" --num-gpus "${SLURM_GPUS_PER_TASK}" --block &
|
|
sleep 5
|
|
done
|
|
# __doc_worker_ray_end__
|
|
|
|
# __doc_script_start__
|
|
# ray/doc/source/cluster/examples/simple-trainer.py
|
|
python -u simple-trainer.py "$SLURM_CPUS_PER_TASK" |