[torqueusers] two queues for torque server and maui scheduler
chemadm at hamilton.edu
Mon Jun 15 10:57:55 MDT 2009
Looks like you have it...it's a fairly simple setup. The only thing
I'd wonder is with the acl_host stuff. Perhaps the host names have
some problems resolving or something. Try turning off the acl_host
entries and see if that helps at all. What's your nodes file and
pbsnodes command output look like? Also what scheduler you using too?
maui or pbs_sched? What does the pbs server logs tell you for the job
you ran? As well as for the scheduler logs. Sorry this asks more
questions than gives answers ;-) but I hope it helps you find where
the problem might be.
On Jun 15, 2009, at 11:14 AM, Zerony Zhao wrote:
> Garrick, Steve and Torque users,
> Sorry for responding late, I was out of town for several days. Thank
> you for help.
> Here is the output of qmgr -c 'p s'.
> # Create queues and set their attributes.
> # Create and define queue core2
> create queue core2
> set queue core2 queue_type = Execution
> set queue core2 acl_host_enable = False
> set queue core2 acl_hosts = core01
> set queue core2 resources_default.neednodes = core2
> set queue core2 resources_default.walltime = 1000:00:00
> set queue core2 enabled = True
> set queue core2 started = True
> # Create and define queue opteron
> create queue opteron
> set queue opteron queue_type = Execution
> set queue opteron acl_host_enable = False
> set queue opteron acl_hosts = opteron01
> set queue opteron resources_default.neednodes = opteron
> set queue opteron resources_default.walltime = 1000:00:00
> set queue opteron enabled = True
> set queue opteron started = True
> # Set server attributes.
> set server scheduling = True
> set server acl_hosts = master
> set server managers = root at master
> set server operators = root at master
> set server default_queue = core2
> set server log_events = 511
> set server mail_from = adm
> set server resources_default.nodes = 1
> set server resources_default.walltime = 1000:00:00
> set server scheduler_iteration = 600
> set server node_check_rate = 150
> set server tcp_timeout = 6
> set server node_pack = False
> set server auto_node_np = True
> set server next_job_number = 219
> The test pbs script is:
> #PBS -S /bin/tcsh
> #PBS -q opteron
> hostname >> host
> sleep 30
> Is there any problems, do I need use routine queue? Thanks.
> On Tue, Jun 9, 2009 at 2:08 AM, Garrick <garrick at usc.edu> wrote:
> Can we see the output of 'p s' in qmqr?
> HPCC/Linux Systems Admin
> On Jun 8, 2009, at 1:38 PM, Zerony Zhao <bw.linux at gmail.com> wrote:
>> Dear torque users,
>> A naive question again. Now I created two queues successfully, each
>> queue will only access the specified nodes, the two queues' name
>> are slownode and fastnode. I specified the queue name in pbs script,
>> #PBS -q slownode
>> #PBS -q fastnode
>> But the jobs always go to the default queue, instead of the
>> specified queue. I can't figure out what the problem is, could you
>> help me?
>> Thank you in advance,
>> torqueusers mailing list
>> torqueusers at supercluster.org
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the torqueusers