...
Code Block | ||||
---|---|---|---|---|
| ||||
#!/bin/bash
jobid=$JOB_ID
machinefile=$TMPDIR/machines
head_node=''
password=''
portnum=0
declare -a list_machines
# ports are used by ray
declare -a skip_ports=(11123 10001 38717 44006)
while true
do
# assign random port in range 20000 - 52767
portnum=$(($jobid % $RANDOM + 20000))
if [[ ! "${skip_ports[*]}" =~ "$portnum" ]]
then
break
fi
done
# build uniq list of machines assigned by scheduler
for machine in $(cat $machinefile | uniq)
do
list_machines[${#list_machines[@]}]=$machine
done
# first node is head node
master_node=${list_machines[0]}
# changedir
cd $TMPDIR
# head node bootstrap
if [[ "x$(hostname)" == "x$master_node" ]]
then
numcpus=$(grep $master_node $machinefile | wc -l)
echo "Isabella Ray head - $numcpus cores @ $master_node port=$portnum"
head_start_log=$(ray start --num-cpus $numcpus --port=$portnum --head | grep "ray start")
head_start_log=${head_start_log#*ray start}
head_node=$(echo $head_start_log | awk '{print $1}' | awk -F'=' '{print $2}')
head_node="${head_node%\'*}'"
head_node="'${head_node#*\'}"
password=$(echo $head_start_log | awk '{print $2}' | awk -F'=' '{print $2}')
password="${password%\'*}'"
password="'${password#*\'}"
fi
sleep 10
# worker nodes bootstrap
for machine in ${list_machines[@]:1}
do
numcpus=$(grep $machine $machinefile | wc -l)
echo "Isabella Ray worker - $numcpus cores @ $machine"
master_arg="${head_node//\'/}"
password_arg="${password//\'/}"
ssh $machine ray start --num-cpus $numcpus --address=$master_arg --redis-password=$password_arg
ssh $machine "eval `/usr/bin/modulecmd bash load ray/1.10.0` ray start --num-cpus $numcpus --address=$master_arg --redis-password=$password_arg --block"&
done |
...