torque作业调度系统安装

系统环境:RHEL6.0

selinux and iptables disabled

1. vi /etc/hosts (所有节点)

192.168.0.82    desktop82.example.com #调度端

192.168.0.82    desktop82.example.com #节点1

192.168.0.76    desktop82.example.com #节点2

 

～#yum install gcc gcc-c++ tcl-devel tk-devel make -y #安装依赖

～#tar zxf torque-3.0.0.tar.gz

～#cd torque-3.0.0

～#./configure --with-rcp=scp –with-default-server=desktop82.example.com

～#make && make install

～#make packages

～#cd contrib/init.d/

～#cp pbs_server pbs_sched pbs_mom /etc/init.d/

～#scp pbs_mom desktop76.example.com:/etc/init.d/

～#cd torque-3.0.0 #在这个目录

～#scp torque-package-clients-linux-x86_64.sh torque-package-mom-linux-x86_64.sh 192.168.0.76:

～#./torque.setup root

initializing TORQUE (admin: [e-mail])

Max open servers: 4

Max open servers: 4

~#cd /var/spool/torque/

~#cd server_priv/

~#vi nodes

desktop82.example.com

desktop76.example.com

~#cd ..

~#cd mom_priv/

~#vi config

$pbsserver desktop82.example.com

$logevent 255

~#qterm -t quick

~#/etc/init.d/pbs_server start

~#/etc/init.d/pbs_sched start

~#/etc/init.d/pbs_mom start

 

节点安装

[root@desktop76 ~]# ./torque-package-clients-linux-x86_64.sh --install

 

Installing TORQUE archive...

 

Done.

[root@desktop76 ~]# ./torque-package-mom-linux-x86_64.sh --install

 

Installing TORQUE archive...

 

Done.

[root@desktop76 ~]# cd /var/spool/torque/

[root@desktop76 torque]# ls

aux mom_logs pbs_environment server_name.new undelivered

checkpoint mom_priv server_name spool

[root@desktop76 torque]# cd mom_priv/

[root@desktop76 mom_priv]# ls

jobs

[root@desktop76 mom_priv]# vi config

$pbsserver desktop82.example.com

$logevent 255

[root@desktop76 mom_priv]# /etc/init.d/pbs_mom start

Starting TORQUE Mom: [ OK】

 

 

 

两个测试脚本

vi job1.pbs

#!/bin/bash

#PBS -N job1

#PBS -o job1.log

#PBS -e job1.err

#PBS -q batch

cd /home/wxh

echo Running on hosts `hostname`

echo Time is `date`

echo Directory is $PWD

echo This job runs on the following nodes:

cat $PBS_NODEFILE

echo This job has allocated 1 node

./prog

vi job2.pbs

#!/bin/bash

#PBS -N job2

#PBS -o job2.log

#PBS -e job2.err

#PBS -q batch

#PBS -l nodes=2

cd /home/wxh

echo Time is `date`

echo Directory is $PWD

echo This job runs on the following nodes:

cat $PBS_NODEFILE

NPROCS=`wc -l < $PBS_NODEFILE`

echo This job has allocated $NPROCS nodes

mpiexec -machinefile $PBS_NODEFILE -np $NPROCS ./prog

 

vi prog

#!/bin/bash

echo 1000000000 | ./icpi-64

chmod +x prog

 

qsub job1.pbs #提交作业

qstat

Job id Name User Time Use S Queue

------------------------- ---------------- --------------- -------- - -----

0.desktop82 job1 phl 00:00:55 C batch

 

pbsnodes

desktop82.example.com

state = job-exclusive

np = 1

ntype = cluster

jobs = 0/4.desktop82.example.com

status = rectime=1345343566,varattr=,jobs=,state=free,netload=113125565,gres=,loadave=0.55,ncpus=1,physmem=288352kb,availmem=11338584kb,totmem=11735672kb,idletime=2251,nusers=1,nsessions=2,sessions=2877 1451,uname=Linux desktop82.example.com 2.6.32-71.el6.x86_64 #1 SMP Wed Sep 1 01:33:01 EDT 2010 x86_64,opsys=linux

mom_service_port = 15002

mom_manager_port = 15003

gpus = 0

 

desktop76.example.com

state = free

np = 1

ntype = cluster

status = rectime=1345343552,varattr=,jobs=3.desktop82.example.com,state=free,netload=101075269,gres=,loadave=0.48,ncpus=1,physmem=288344kb,availmem=12967884kb,totmem=13541040kb,idletime=5884,nusers=1,nsessions=2,sessions=3370 3837,uname=Linux desktop76.example.com 2.6.32-71.el6.x86_64 #1 SMP Wed Sep 1 01:33:01 EDT 2010 x86_64,opsys=linux

mom_service_port = 15002

mom_manager_port = 15003

gpus = 0

qsub job2.pbs #提交作业

qstat

pbsnodes

desktop82.example.com

state = job-exclusive

np = 1

ntype = cluster

jobs = 0/4.desktop82.example.com

status = rectime=1345343608,varattr=,jobs=4.desktop82.example.com,state=free,netload=113180660,gres=,loadave=0.48,ncpus=1,physmem=288352kb,availmem=12953584kb,totmem=13541160kb,idletime=2296,nusers=1,nsessions=2,sessions=2877 1451,uname=Linux desktop82.example.com 2.6.32-71.el6.x86_64 #1 SMP Wed Sep 1 01:33:01 EDT 2010 x86_64,opsys=linux

mom_service_port = 15002

mom_manager_port = 15003

gpus = 0

 

desktop76.example.com

state = job-exclusive

np = 1

ntype = cluster

jobs = 0/5.desktop82.example.com

status = rectime=1345343597,varattr=,jobs=,state=free,netload=101253719,gres=,loadave=0.27,ncpus=1,physmem=288344kb,availmem=14590964kb,totmem=15346512kb,idletime=5929,nusers=1,nsessions=1,sessions=3370,uname=Linux desktop76.example.com 2.6.32-71.el6.x86_64 #1 SMP Wed Sep 1 01:33:01 EDT 2010 x86_64,opsys=linux

mom_service_port = 15002

mom_manager_port = 15003

gpus = 0