From: Theodore Tso Subject: Re: Revert Fix-EXT_MAX_BLOCK.patch Date: Mon, 14 Jul 2008 16:28:13 -0400 Message-ID: <20080714202813.GC3382@mit.edu> References: <20080619110947.GB11516@mit.edu> <20080710092425.GA16451@skywalker> <20080710092517.GB16451@skywalker> <20080711124304.GB8154@mit.edu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: "Aneesh Kumar K.V" , Girish Shilamkar , linux-ext4@vger.kernel.org To: Holger Kiehl Return-path: Received: from www.church-of-our-saviour.ORG ([69.25.196.31]:36459 "EHLO thunker.thunk.org" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1755402AbYGNU2e (ORCPT ); Mon, 14 Jul 2008 16:28:34 -0400 Content-Disposition: inline In-Reply-To: Sender: linux-ext4-owner@vger.kernel.org List-ID: On Mon, Jul 14, 2008 at 07:55:10PM +0000, Holger Kiehl wrote: > You are right. I did compare the .config of both and noticed that > CONFIG_FAIR_GROUP_SCHED was set in the rc9 test but not in rc8 test. > Doing the test without CONFIG_FAIR_GROUP_SCHED gave me back 6%. > Sorry. You may have told us already, but can you tell me the full configuration of your benchmark machine? (i.e., how many CPU's, how much memory, etc.) Also, what are the current mount options you are currently using? And have you redone the ext3 benchmark number with barriers enabled? Or was that the original number done with default mount options that leave barriers disabled? Thanks!! - Ted