Subject: Re: Link performance over NFS degraded in RHEL5. -- was :
 Read/Write NFS I/O performance degraded by FLUSH_STABLE page flushing
From: Trond Myklebust <trond.myklebust@fys.uio.no>
To: Steve Dickson <SteveD@redhat.com>
Cc: Neil Brown <neilb@suse.de>, Greg Banks <gnb@fmeh.org>,
        Brian R Cowan <brcowan@us.ibm.com>, linux-nfs@vger.kernel.org
In-Reply-To: <4A2902E6.2080006@RedHat.com>
References: <OF3EBF546E.60A83A8F-ON852575A8.006EBB38-852575A8.006EFDE6@us.ibm.com>
	 <OF820C8732.74757E21-ON852575C5.0055C089-852575C5.00578071@us.ibm.com>
	 <1243615595.7155.48.camel@heimdal.trondhjem.org>
	 <OF0EEDB635.561D17D4-ON852575C5.005CBABA-852575C5.005FAD0D@us.ibm.com>
	 <1243618500.7155.56.camel@heimdal.trondhjem.org>
	 <ac442c870905291722x1ec811b2sda997d464898fcda@mail.gmail.com>
	 <1243686363.5209.16.camel@heimdal.trondhjem.org>
	 <ac442c870905300602v6950ec42y5195d2d6ea7dd4c@mail.gmail.com>
	 <BA67D2A4-1752-4789-ADB9-D1B3C6D197F6@oracle.com>
	 <1243963631.4868.124.camel@heimdal.trondhjem.org>
	 <18982.41770.293636.786518@fisica.ufpr.br>
	 <1244049027.5603.5.camel@heimdal.trondhjem.org>
	 <OFB53BFCCB.0CEC7A7E-ON852575C <1244138698.5203.59.camel@heimdal.trondhjem.org>
	 <OF37FCED66.33F08949-ON852575CB.006DE109-852575CB.0071CFBD@us.ibm.com>
	 <4A2902E6.2080006@RedHat.com>
Content-Type: text/plain
Date: Fri, 05 Jun 2009 08:46:38 -0400
Message-Id: <1244205998.5410.25.camel@heimdal.trondhjem.org>
Sender: linux-nfs-owner@vger.kernel.org
MIME-Version: 1.0

On Fri, 2009-06-05 at 07:35 -0400, Steve Dickson wrote:
> Brian R Cowan wrote:
> > Trond Myklebust <trond.myklebust@fys.uio.no> wrote on 06/04/2009 02:04:58 
> > PM:
> > 
> >> Did you try turning off write gathering on the server (i.e. add the
> >> 'no_wdelay' export option)? As I said earlier, that forces a delay of
> >> 10ms per RPC call, which might explain the FILE_SYNC slowness.
> > 
> > Just tried it, this seems to be a very useful workaround as well. The 
> > FILE_SYNC write calls come back in about the same amount of time as the 
> > write+commit pairs... Speeds up building regardless of the network 
> > filesystem (ClearCase MVFS or straight NFS).
> 
> Does anybody had the history as to why 'no_wdelay' is an 
> export default? As Brian mentioned later in this thread
> it only helps Linux servers, but that's good thing, IMHO. ;-)
> 
> So I would have no problem changing the default export
> options in nfs-utils, but it would be nice to know why 
> it was there in the first place...

It dates back to the days when most Linux clients in use in the field
were NFSv2 only. After all, it has only been 15 years...

  Trond