[dcmf] [PATCH 1/1] Issue 4362: Honor the romio_ds_write andromio_ds_read hints.

[Rajeev Thakur]

GPFS is supposed to be Posix-compliant even with the client cache and should
not require locking like NFS.
 
Rajeev


  _____  

From: dcmf-bounces at lists.anl-external.org
[mailto:dcmf-bounces at lists.anl-external.org] On Behalf Of Bob Cernohous
Sent: Monday, February 11, 2008 11:47 AM
To: Rob Ross
Cc: dcmf
Subject: Re: [dcmf] [PATCH 1/1] Issue 4362: Honor the romio_ds_write
andromio_ds_read hints.



That's basically the answer that I got from an original developer:  "we were
actively considering support for NFS and GPFS, both have client side
caching". 


Rob Ross <rross at mcs.anl.gov> wrote on 02/08/2008 08:39:34 PM:

> My guess is that it's the "lowest common denominator", that it works  
> for both GPFS (albeit with unnecessary locking calls) and for NFS,  
> which are the two configurations for which IBM is interested.
> 
> Rob
> 
> On Feb 8, 2008, at 5:40 PM, Bob Cernohous wrote:
> 
> >
> > robl at mcs.anl.gov (Robert Latham) wrote on 02/08/2008 04:22:17 PM:
> >
> > >
> > > Do you know why ad_bgl is based off of ad_nfs and not ad_ufs?  The
> > > aggressive locking in ad_nfs is an attempt to flush client-side
> > > caches, but shouldn't be needed for other file systems.
> >
> > No, sorry.  I'm pretty new to romio.  I'll try to find some answers
> > (and educate myself on  
> > this)._______________________________________________
> > dcmf mailing list
> > dcmf at lists.anl-external.org
> > http://lists.anl-external.org/cgi-bin/mailman/listinfo/dcmf
> > http://dcmf.anl-external.org/wiki
> 


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alcf.anl.gov/pipermail/dcmf/attachments/20080211/d652c32f/attachment.htm>