From owner-freebsd-current  Wed Apr 21 14:25:34 1999
Delivered-To: freebsd-current@freebsd.org
Received: from alcanet.com.au (border.alcanet.com.au [203.62.196.10])
	by hub.freebsd.org (Postfix) with ESMTP id EAC13158F0
	for <current@FreeBSD.ORG>; Wed, 21 Apr 1999 14:24:40 -0700 (PDT)
	(envelope-from peter.jeremy@auss2.alcatel.com.au)
Received: by border.alcanet.com.au id <40329>; Thu, 22 Apr 1999 07:08:15 +1000
Date: Thu, 22 Apr 1999 07:22:02 +1000
From: Peter Jeremy <peter.jeremy@auss2.alcatel.com.au>
Subject: Re: Alright, who's the smart alleck that fixed NFS this last week? :)
To: dillon@apollo.backplane.com
Cc: current@FreeBSD.ORG
Message-Id: <99Apr22.070815est.40329@border.alcanet.com.au>
Sender: owner-freebsd-current@FreeBSD.ORG
Precedence: bulk
X-Loop: FreeBSD.ORG

Matthew Dillon <dillon@apollo.backplane.com> wrote:
[Partial writes]
> I finally gave up on it.  What NFS does now is optimize only two
> write situations:  ...  And (2) piecemeal writes in the write-append
> case.

I'm nothing like an NFS expert, so I may be talking through my hat,
but...  I presume NFS correctly supports O_APPEND semantics for
multiple clients (as seen from the server).  In this case, the
optimization only works when there's only one client machine (though
possibly multiple processes on that machine) is using write+O_APPEND.

Peter


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message