[torqueusers] torque does not kill jobs when wall_time or cpu_time reached

David Singleton David.Singleton at anu.edu.au
Tue Jun 8 18:06:33 MDT 2010


On 06/09/2010 09:50 AM, Glen Beane wrote:
>
>>
>> Note that virtual processors != physical processors causes a number of
>> problems.
>
> Generally virtual processors is set to the number of CPUs * cores per
> CPU. Some (but not all) users know each processor has multiple core
> and think that by requesting the processor they are allocated all
> cores of the processor.
>

Oops, good point. Sorry about the sloppy terminology.  I think of
cores = cpus = processors in the resource allocation context because
logically that's what they are.   The sockets/packaging details are
more a secondary issue of locality.

David


More information about the torqueusers mailing list