Re: [Condor-users] nfs and condor

[Steven Timm <timm@xxxxxxxx>]

Yes, we had this problem.. we spent the money to buy a top-end Bluearc
NAS/NFS appliance, and then put in a series of locking scripts to
make sure that the number of I/O handles from any different user
groups are limited at any given time.

There are two places NFS can slow you down, one on the schedd
which has got to write stuff to the home areas, and one on the
startd which would just time out if it can't get to the file.
On the schedd/shadow end there are a number of timeouts and
retries that can be lengthened, although there is no substitute for cpu
speed and lots of RMA.  On the startd end you basically just
have basic nfs client tuning you can do.

Steve Timm


On Sun, 12 Jun 2011, Mag Gam wrote:

> At our university we are a heavy NFS user. When we run run long jobs
> with condor and there is a performance problem with our home
> directories (which on are NFS). It seems the job gets requeued.
>
> I was wondering if anyone else out there have a similar problem and
> what they did to fix it :-)
> _______________________________________________
> Condor-users mailing list
> To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a
> subject: Unsubscribe
> You can also unsubscribe by visiting
> https://lists.cs.wisc.edu/mailman/listinfo/condor-users
>
> The archives can be found at:
> https://lists.cs.wisc.edu/archive/condor-users/

--
------------------------------------------------------------------
Steven C. Timm, Ph.D  (630) 840-8525
timm@xxxxxxxx  http://home.fnal.gov/~timm/
Fermilab Computing Division, Scientific Computing Facilities,
Grid Facilities Department, FermiGrid Services Group, Group Leader.
Lead of FermiCloud project.