From owner-freebsd-isp@FreeBSD.ORG Tue Apr 18 12:54:24 2006 Return-Path: X-Original-To: freebsd-isp@freebsd.org Delivered-To: freebsd-isp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 17B7816A401 for ; Tue, 18 Apr 2006 12:54:24 +0000 (UTC) (envelope-from dgilbert@daveg.ca) Received: from ox.eicat.ca (ox.eicat.ca [66.96.30.35]) by mx1.FreeBSD.org (Postfix) with ESMTP id B192C43D46 for ; Tue, 18 Apr 2006 12:54:23 +0000 (GMT) (envelope-from dgilbert@daveg.ca) Received: by ox.eicat.ca (Postfix, from userid 66) id CD92F15D20; Tue, 18 Apr 2006 08:54:22 -0400 (EDT) Received: by canoe.dclg.ca (Postfix, from userid 101) id 94F8D4AC2B; Tue, 18 Apr 2006 08:54:10 -0400 (EDT) From: David Gilbert MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <17476.57714.38638.380701@canoe.dclg.ca> Date: Tue, 18 Apr 2006 08:54:10 -0400 To: Eric Anderson In-Reply-To: <4444D029.8060109@centtech.com> References: <17475.43946.264571.52593@canoe.dclg.ca> <17475.54375.95109.55657@canoe.dclg.ca> <4444D029.8060109@centtech.com> X-Mailer: VM 7.17 under 21.4 (patch 19) "Constant Variable" XEmacs Lucid Cc: FreeBSD ISP , Francisco Reyes , David Gilbert Subject: Re: NFS optimization X-BeenThere: freebsd-isp@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Internet Services Providers List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 18 Apr 2006 12:54:24 -0000 >>>>> "Eric" == Eric Anderson writes: Eric> David Gilbert wrote: >> Consider that if you are "out" of nfsd's, the penalty is increased >> latency for some small number of transactions that wait for an nfsd >> to become available.. Even if you have tonnes of NFSd processes, >> if disk is a limiting factor, more nfsd's won't speed the process. Eric> I have found that having too little can easily cause clients to Eric> block on nfs under peak usage times, so I tend to bump the Eric> number way up. There's little to no harm in it. I have never, ever seen this behaviour. I'd go as far as to say that it shouldn't happen. Not categorically, but NFS packets should be entirely independant... meaning it shouldn't prefer one client's pakcets over another unless it is massively starved for NFSd's, the queue should be somewhat FIFO. Eric> I usually look at my nfsd's, and see what the distribution of Eric> run time is on them. I like to see at minimum a few (maybe 5% Eric> or so) with 0:00.00 runtime - which (to me) means that I had Eric> enough to service the queue, and a few extra that were bored. Eric> For my setup, this means typically between 256 and 512 nfsd's Eric> (with one server at 1024). I have run incredibly busy NFS servers (20 to 40 disks, 16 to 20 ethernet and 100 (or more) busy diskless clients (computation cluster) and I have never run more than 32. I've never found a performance advantage beyond 1:1 nfsd's to disks. Dave. -- ============================================================================ |David Gilbert, Independent Contractor. | Two things can be | |Mail: dave@daveg.ca | equal if and only if they | |http://daveg.ca | are precisely opposite. | =========================================================GLO================