From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755924Ab3BEO7A (ORCPT ); Tue, 5 Feb 2013 09:59:00 -0500 Received: from mail-bk0-f46.google.com ([209.85.214.46]:58159 "EHLO mail-bk0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755540Ab3BEO66 (ORCPT ); Tue, 5 Feb 2013 09:58:58 -0500 Date: Tue, 5 Feb 2013 15:58:54 +0100 From: Ingo Molnar To: Alex Shi Cc: torvalds@linux-foundation.org, paul.gortmaker@windriver.com, linux-kernel@vger.kernel.org Subject: Re: [PATCH] rwsem: steal writing sem for better performance Message-ID: <20130205145854.GA30949@gmail.com> References: <1360069915-31619-1-git-send-email-alex.shi@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1360069915-31619-1-git-send-email-alex.shi@intel.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Alex Shi wrote: > Commit 5a50508 change to rwsem from mutex, that cause aim7 fork_test > dropped 50%. Yuanhan liu does a good analysis, find it caused by > strict sequential writing. Ingo suggest stealing sem writing from > front task in waiting queue. https://lkml.org/lkml/2013/1/29/84 > So has this patch. > > In this patch, I just allow writing steal happen when the > first waiter is also writer. Then the performance fully > recovered. All the aim7 fork_test performance regression is recovered? Thanks, Ingo