This README describes how to get the most basic working
torque service on a single host.
To setup a basic single-node localhost-only batch system, install the
torque-server, torque-mom, and torque-scheduler packages, and do something like
this:
0) If torque is built with munge support then this
must be enabled first on all nodes. The munge
package should allready be installed.
Create a munge key with
/usr/sbin/create-munge-key
Copy resulting key /etc/munge/munge.key to
all torque nodes in your cluster including
pbs_server, pbs_mom and client (qstat,qsub) nodes.
1) Get your full hostname with
# /bin/hostname --long
e.g myhost.example.org
2) Edit /etc/torque/server_name
to contain the single line
myhost.example.org
3) Edit /etc/torque/mom/config
to contain the single line
$pbsserver myhost.example.org
4) Create a torque serverdb file.
# /usr/sbin/pbs_server -D -t create
Warning this will remove any existing serverdb
file located at /var/lib/torque/server_priv/serverdb
You will have to Ctrl^C the pbs_server command, it will
only take a moment to create this file.
5) Start the pbs_server and configure it.
service pbs_server start
# qmgr -c "s s scheduling=true"
# qmgr -c "c q batch queue_type=execution"
# qmgr -c "s q batch started=true"
# qmgr -c "s q batch enabled=true"
# qmgr -c "s q batch resources_default.nodes=1"
# qmgr -c "s q batch resources_default.walltime=3600"
# qmgr -c "s s default_queue=batch"
6) Add one batch worker to your pbs_server.
# qmgr -c "c n myhost.example.org"
7) Start the pbs_mom and pbs_sched deamons.
# service pbs_mom start
# service pbs_sched start
8) Use chkconfig to start the services at boot time.
# /sbin/chkconfig pbs_mom on
# /sbin/chkconfig pbs_server on
# /sbin/chkconfig pbs_sched on
# /sbin/chkconfig munge on
9) Submit a test job.
As a user not as root run the following
$ qsub <<EOF
hostname
echo "Hi I am a batch job running in torque"
EOF
10 ) Monitor the state of that job with qstat.
In case of problems first of all look in /var/log/torque
a3e8771c8f
