Alessandra Forti wrote:
> Hi,
>
> I don't know about the other VOs but I know for sure that LHCB is not
> requiring any CPU time in their jdl.
Strange I remember they where even requiring cputime*ksi2k and the RB
was doing the match to find a proper queue knowing the ksi2k published
by the site.
Cheers, Olivier.
>
> cheers
> alessandra
>
>
> Burke, S (Stephen) wrote:
>> Testbed Support for GridPP member institutes
>>> [mailto:[log in to unmask]] On Behalf Of Duncan Rand said:
>>> Is a job with no time requirements a long job or a short job?
>>
>> Effectively it's a very short job :)
>>
>>> Also in my experience users don't pay much attention to jobs which fail
>>> - they just get automatically resubmitted elsewhere until they
>>> eventually run to completion, often after having travelled around
>>> several sites. There seems to be little incentive to improve the job
>>> success rates for users, VO's or sites.
>>
>> Well, specifying the cpu time for a job is pretty general for any batch
>> system. I think "serious" users do figure these things out, certainly
>> the production jobs for the big VOs are quite sophisticated, but for new
>> users it may be a problem - not least because as usual you probably
>> don't get an error message that makes sense. I'll add some comments on
>> the gridpp web site at least, and also try to feed this into other
>> documentation.
>>
>> Stephen
>
--
- O. van der Aa - Imperial College London -
- LT2 Technical Coordinator -
- tel: +442075947810, +442071005426 -
- SIP: [log in to unmask] -
- fax: +442078238830 -
- http://surl.se/agtu -
|