[Beowulf] Looking for NFS Server performance comparison
joachim at ccrl-nece.de
Fri Dec 16 08:35:10 PST 2005
Bill Rankin wrote:
> Hi Gang,
> This may be a rehash, but I'm looking for any references to papers that
> address the issue of NFS server scalability in a cluster environment.
> Our current cluster here at Duke is right at 500 nodes (and growing)
> and the single NFS server with attached SCSI drives serving all data to
> all nodes just doesn't seem to hack it anymore.
> I know that there are clustered solutions like PVFS, IBRIX, et. al. as
> well as the dedicated filer approach (NetApp, EMC, etc.) and we are
> looking at those. But first we need to convince the powers that be that
> a Linux-based NFS server just ain't going to cut it as we move forward.
sorry if this sounds a bit perky, but: if you have I/O bound applications, I'm
quite sure you can show that they don't scale even with the current 500 nodes on
a single NFS server. And if you don't have such applications - well, than you
don't have a problem... ;-) You can still use a benchmark, but this might not
convince "the powers".
Above you say that the NFS server has already problems now: shouldn't that
convince the powers that you need something else than NFS? Which problems do you
refer to with "doesn't hack it anymore"?
Correct me if I just didn't understand your problem. However, I *do* understand
that NFS really is a bad idea for many nodes doing something else than just
loading the executable (and even this may show problems at scale). Ie. doing
MPI-IO correctly is a nightmare on NFS.
> So if anyone knows of good documents (white papers, conference papers,
> etc.) that will support my assertion, I would appreciate a pointer to
I'm quite sure the vendors will happily provide you with such material... A
quick search gave this GPFS vs. NFS evaluation:
Joachim Worringen - NEC C&C research lab St.Augustin
fon +49-2241-9252.20 - fax .99 - http://www.ccrl-nece.de
More information about the Beowulf