Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753277AbZLVNIa (ORCPT ); Tue, 22 Dec 2009 08:08:30 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751761AbZLVNI3 (ORCPT ); Tue, 22 Dec 2009 08:08:29 -0500 Received: from web113309.mail.gq1.yahoo.com ([98.136.167.9]:48062 "HELO web113309.mail.gq1.yahoo.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751165AbZLVNI2 (ORCPT ); Tue, 22 Dec 2009 08:08:28 -0500 Message-ID: <787373.9318.qm@web113309.mail.gq1.yahoo.com> X-YMail-OSG: kwXfo5UVM1nTpZRwOPhNm0VjRACOvzJpAOs0OEJYPbGm1ctxn13hgMhZz1cz3I_XalP1F_ZMasGfxylafsrxAn3q5LbqZMdzXN.8cHgMxBCoIKwL5PlnOB2akOQ2YGilTCMQ9UZ3VFUeq6xImMXKNnrDSTPe7ZcGMGxsPAKTqcjfpD.tfb6sGnTUCgNyQN9RhPCCFCSilODgJhijQri1kxkYL8jl9hAtc_zD1qFtyXpK.EtYvuaJU.GTN0Dj5TldJWWOCmGTQdcx8QvaYFzvW7EqTqm4H2.2eCIN3s.FBnMA7rbWyt.mdlWQBt4T1kaD1w1D6Lk6Ilr5esd.0uscaUh6_Nx8vojSJcjvs8tF X-RocketYMMF: knobi.rm X-Mailer: YahooMailRC/240.3 YahooMailWebService/0.8.100.260964 References: <1261015420.1947.54.camel@serenity> <1261037877.27920.36.camel@laptop> <20091219122033.GA11360@localhost> <1261232747.1947.194.camel@serenity> <20091222015907.GA6223@localhost> Date: Tue, 22 Dec 2009 05:01:46 -0800 (PST) From: Martin Knoblauch Subject: Re: [PATCH] improve the performance of large sequential write NFS workloads To: Wu Fengguang , Steve Rago Cc: Peter Zijlstra , "linux-nfs@vger.kernel.org" , "linux-kernel@vger.kernel.org" , "Trond.Myklebust@netapp.com" , "jens.axboe" In-Reply-To: <20091222015907.GA6223@localhost> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1346 Lines: 31 ----- Original Message ---- > From: Wu Fengguang > To: Steve Rago > Cc: Peter Zijlstra ; "linux-nfs@vger.kernel.org" ; "linux-kernel@vger.kernel.org" ; "Trond.Myklebust@netapp.com" ; jens.axboe > Sent: Tue, December 22, 2009 2:59:07 AM > Subject: Re: [PATCH] improve the performance of large sequential write NFS workloads > [big snip] > > In general it's reasonable to keep NFS per-file nr_dirty low, however > questionable to do per-file nr_writeback throttling. This does not > work well with the global limits - eg. when there are many dirty > files, the summed-up nr_writeback will still grow out of control. > And it's more likely to impact user visible responsiveness than > a global limit. But my opinion can be biased -- me have a patch to > do global NFS nr_writeback limit ;) > is that "NFS: introduce writeback wait queue", which you sent me a while ago and I did not test until now :-( ? Cheers Martin -- 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/