[torquedev] nodes, procs, tpn and ncpus
glen.beane at gmail.com
Wed Jun 9 15:05:25 MDT 2010
On Wed, Jun 9, 2010 at 4:58 PM, Ken Nielson
<knielson at adaptivecomputing.com> wrote:
> On 06/09/2010 02:57 PM, Glen Beane wrote:
>> On Wed, Jun 9, 2010 at 4:49 PM, Ken Nielson
>> <knielson at adaptivecomputing.com> wrote:
>>> Here is why -l nodes=4<job.sh> will only give you one node.
>> ... but it gives everyone else more than one node, as it always has...
>> you can't convince me it will only give me one node when I can see
>> completely different behavior first hand :)
>> torquedev mailing list
>> torquedev at supercluster.org
> gdb the code. You have something else going on. Set the break point in
> listelem and do a qrun by hand and see where you deviate.
I don't believe I have anything else going on. You have been wrong on
the behavior of other specs, like nodex=X:ppn=Y only allocating one
node. It appears you have something else going on than every other
I can't gdb pbs_server on a production cluster to see where I am
different, maybe someone else can do that on a test cluster.
Anyway, the behavior you are seeing is not correct. It is either a bug
in torque or a problem with your setup.
More information about the torquedev