Not those two, but I've got 6,000 ilc jobs that look like they'll take a
_very_ long time to clear (and seem to be causing problems on one of our
CEs).
I was thinking of implmenting the max_queuable or max_user_queuable
parameters on my queues.
Does anyone have any experience of these, do the get published/handled
gracefully by the WMS?
Yours,
Chris.
> -----Original Message-----
> From: Testbed Support for GridPP member institutes
> [mailto:[log in to unmask]] On Behalf Of Alessandra Forti
> Sent: 13 January 2009 17:26
> To: [log in to unmask]
> Subject: queued jobs
>
> Hi,
>
> is anybody having problems with thousands of jobs being
> queued by lhcb
> production and
> phenogrid? One of the manchester clusters has over 12000
> queued jobs and
> they will probably all die of proxy expiration.
>
> cheers
> alessandra
>
>
>
> --
> Alessandra Forti - NorthGrid Technical Coordinator
> http://www.hep.manchester.ac.uk/computing/tier2
>
> Well you'll still need a tray
>
--
Scanned by iCritical.
|