From: tytso@mit.edu Subject: Re: ext4 dbench performance with CONFIG_PREEMPT_RT Date: Sat, 10 Apr 2010 07:58:16 -0400 Message-ID: <20100410115816.GH1849@thunk.org> References: <1270682478.3755.58.camel@localhost.localdomain> <87d3y8wrq5.fsf@basil.nowhere.org> <20100409233325.GF1849@thunk.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Andi Kleen , john stultz , "linux-ext4@vger.kernel.org" , Mingming Cao , keith maanthey , Thomas Gleixner , Ingo Molnar , Darren Hart To: "Chen, Tim C" Return-path: Received: from thunk.org ([69.25.196.29]:34000 "EHLO thunker.thunk.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750980Ab0DJL72 (ORCPT ); Sat, 10 Apr 2010 07:59:28 -0400 Content-Disposition: inline In-Reply-To: Sender: linux-ext4-owner@vger.kernel.org List-ID: On Fri, Apr 09, 2010 at 05:48:23PM -0600, Chen, Tim C wrote: > > Your patch did remove the contention on the j_state_lock for dbench > in my testing with 64 threads. The contention point now > moves dcache_lock, which is also another tricky bottleneck. > > In our other testing with FFSB that creates/rename/remove a lot of directories, > we found that journal->j_revoke_lock was also heavily contended. > Do you have lock_stat reports handy? I'd love to take a look at them. Thanks, - Ted