Hi,
LHCb jobs produce about 500 MB of files every 13-18 hours (depending on
processor speed). This is usually in the form of one main file, plus a
small number of log files. These are all transfered at the end of the job.
Ian
Simon George wrote:
> Hi,
>
> I'm trying to get a rough indication of the typical network bandwidth in
> and out of a site during a LHC data challenge.
>
> The network manager at our computer centre is concerned about the impact
> that use of our LCG farm could have on the campus network and our uplink
> to the London MAN, and she has reasonably asked me for some rough
> predictions of the bandwidth usage we anticipate. Obviously this will on
> how much bandwidth is available, farm size and load, etc.
>
> I would be grateful if sites that have already experienced a data
> challenge could feed back their experience of the network traffic that it
> generates.
>
> We have a farm size of ~ 75 nodes, 150 CPUs and our bandwidth bottleneck
> is probably the 100 Mb connection from RHUL to the London MAN. If you
> respond please comment on how your situation compares.
>
> Cheers,
> Simon
>
> ---------------------------------------------------------------------------
> Simon George, Dept of Physics, Royal Holloway college, University of London
> Email [log in to unmask] Tel. +44 1784 41 41 85 Fax. +44 1784 472794
--
Ian Stokes-Rees [log in to unmask]
Particle Physics, Oxford http://www-pnp.physics.ox.ac.uk/~stokes
|