Hi Elena,
75% of our cluster is fine with this (actually, closer to 50GB per
core!) but some nodes are only on 15GB per core. However, we've got a
load of new HDs on order (or possible already arrived - I lose track!)
specifically for these machines and they should be installed within a
few weeks. These would put all our machines at 50GB per core.
Thanks!
Mark
On 22/05/2012 06:39, Elena Korolkova wrote:
> Hello
>
> ATLAS requires to have 20 GB/core.
>
> For some reason a corresponding parameter in panda is set to 14 GB ATM.
> Some jobs can't be submitted to sites which have 14GB/core.
>
> ATLAS wants to change this parameter to 20 GB.
>
> Could sites check whether they really have 20GB/core at their WN, please
> If this is the case we can safely change schedconfig.
>
> RAL, Manchester and QM already have no limitation.
>
>
> Thanks
> Elena
>
> __________________________________________________
> Dr Elena Korolkova
> Email: [log in to unmask]
> Tel.: +44 (0)114 2223553
> Fax: +44 (0)114 2223555
> Department of Physics and Astronomy
> University of Sheffield
> Sheffield, S3 7RH, United Kingdom
|