From: Trond Myklebust Subject: Re: Server bottleneck(?) due to large record write() buffer size from client app Date: Thu, 21 Aug 2008 12:20:17 -0700 Message-ID: <1219346417.7052.36.camel@localhost> References: <48AB9A2F.1050005@cse.unsw.edu.au> <1219259723.7547.26.camel@localhost> <48ACCD61.60504@cse.unsw.edu.au> Mime-Version: 1.0 Content-Type: text/plain Cc: linux-nfs@vger.kernel.org To: Shehjar Tikoo Return-path: Received: from mail-out1.uio.no ([129.240.10.57]:55432 "EHLO mail-out1.uio.no" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754805AbYHUTUV (ORCPT ); Thu, 21 Aug 2008 15:20:21 -0400 In-Reply-To: <48ACCD61.60504-YbfuJp6tym7X/JP9YwkgDA@public.gmane.org> Sender: linux-nfs-owner@vger.kernel.org List-ID: On Thu, 2008-08-21 at 12:05 +1000, Shehjar Tikoo wrote: > By changing pdflush settings on the client, I'd be changing the > settings for the whole system. Is there a proc FS entry or any other > config param that lets me lower the number of write requests buffered > at client before the commit request is sent? Write buffering is not something which is under the control of the NFS filesystem: it is entirely managed by the VM. The filesystem only enforces the close-to-open cache consistency requirements, which of course are specific to NFS. Trond