[GE users] Installing 6.2u4 with BDB spooling on NFSv4

ccaamad m.c.dixon at leeds.ac.uk
Wed Jan 6 16:20:58 GMT 2010

On Fri, 4 Dec 2009, dom wrote:

> jlb,
> we tested it with different linux distributions. The configuration was
> always solaris server, linux client.
> Some of our supporter did same testing and they ran in permanent
> problems. I'm not if a really new linux used for server and client
> has these problems two. I tried on my private linux box Open SuSe 11,
> did a export and a local mount as nfsv4, this made no problems, the same
> machine as server and client. So perhaps it's possible to find any
> configuration which is working.
> That's the reason why I'm interested in.
> I forgot to write, with our next release this filesystem type check is
> fixed.
> Marco

Hi Marco,

Do you know if the observed problems with Linux and NFSv4 made the cluster 
completely unusable, or did they only emerge through quite a bit of usage?

I've just done a simple install and - like jlb's report - nothing seems 
immediately wrong beyond some installation trouble. Nothing weird in 

Something's obviously wrong with me today but, as we're in a pilot phase 
for a new system, I'm wondering about going with it :o


   SGE        : 6.2u4

   NFS Server : RHEL5.4 (with 5.3 kernel 2.6.18-128.7.1.el5)

   SGE qmaster: RHEL5.4 (with 5.3 kernel 2.6.18-128.7.1.el5), berkleydb
                spooling over NFSv4.

   SGE exec's : CentOS 5.4 (with 5.3 kernel 2.6.18-128.7.1.el5), local
                spooling, SGE_ROOT mounted with NFSv3.

Mark Dixon                       Email    : m.c.dixon at leeds.ac.uk
HPC/Grid Systems Support         Tel (int): 35429
Information Systems Services     Tel (ext): +44(0)113 343 5429
University of Leeds, LS2 9JT, UK


To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].

More information about the gridengine-users mailing list