Date: Wed, 30 Mar 2005 16:20:56 +0200
From: Ingo Molnar <mingo@elte.hu>
To: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Lee Revell <rlrevell@joe-job.com>,
       linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: NFS client latencies
Message-ID: <20050330142056.GA3043@elte.hu>
References: <1112137487.5386.33.camel@mindpipe> <1112138283.11346.2.camel@lade.trondhjem.org> <1112139155.5386.35.camel@mindpipe> <1112139263.11892.0.camel@lade.trondhjem.org> <20050330080224.GB19683@elte.hu> <1112191860.10634.29.camel@lade.trondhjem.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1112191860.10634.29.camel@lade.trondhjem.org>
User-Agent: Mutt/1.4.2.1i
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1350
Lines: 28


* Trond Myklebust <trond.myklebust@fys.uio.no> wrote:

> > the comment suggests that this is optimized for append writes (which is 
> > quite common, but by far not the only write workload) - but the 
> > worst-case behavior of this code is very bad. How about disabling this 
> > sorting altogether and benchmarking the result? Maybe it would get 
> > comparable coalescing (higher levels do coalesce after all), but wastly 
> > improved CPU utilization on the client side. (Note that the server 
> > itself will do sorting of any write IO anyway, if this is to hit any 
> > persistent storage - and if not then sorting so agressively on the 
> > client side makes little sense.)
> 
> No. Coalescing on the client makes tons of sense. The overhead of
> sending 8 RPC requests for 4k writes instead of sending 1 RPC request
> for a single 32k write is huge: among other things, you end up tying up
> 8 RPC slots on the client + 8 nfsd threads on the server instead of just
> one of each.

yes - coalescing a few pages makes sense, but linearly scanning 
thousands of entries is entirely pointless.

	Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/