From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751359Ab1GYIVp (ORCPT ); Mon, 25 Jul 2011 04:21:45 -0400 Received: from mx2.fusionio.com ([66.114.96.31]:33428 "EHLO mx2.fusionio.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750977Ab1GYIVi (ORCPT ); Mon, 25 Jul 2011 04:21:38 -0400 X-ASG-Debug-ID: 1311582088-01de280c1eec9b0001-xx1T2L X-Barracuda-Envelope-From: JAxboe@fusionio.com Message-ID: <4E2D2784.3060701@fusionio.com> Date: Mon, 25 Jul 2011 10:21:24 +0200 From: Jens Axboe MIME-Version: 1.0 To: Shaohua Li CC: Dan Williams , Christoph Hellwig , Roland Dreier , Dave Jiang , "linux-kernel@vger.kernel.org" , "linux-scsi@vger.kernel.org" Subject: Re: [RFC PATCH 1/2] block: strict rq_affinity References: <20110722205736.17420.41366.stgit@localhost6.localdomain6> <20110722205938.17420.68621.stgit@localhost6.localdomain6> <4E2B15DB.4090302@fusionio.com> X-ASG-Orig-Subj: Re: [RFC PATCH 1/2] block: strict rq_affinity In-Reply-To: Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit X-Barracuda-Connect: mail1.int.fusionio.com[10.101.1.21] X-Barracuda-Start-Time: 1311582088 X-Barracuda-URL: http://10.101.1.181:8000/cgi-mod/mark.cgi X-Barracuda-Spam-Score: 0.00 X-Barracuda-Spam-Status: No, SCORE=0.00 using global scores of TAG_LEVEL=1000.0 QUARANTINE_LEVEL=1000.0 KILL_LEVEL=9.0 tests=INFO_TLD X-Barracuda-Spam-Report: Code version 3.2, rules version 3.2.2.69905 Rule breakdown below pts rule name description ---- ---------------------- -------------------------------------------------- 0.00 INFO_TLD URI: Contains an URL in the INFO top-level domain Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 2011-07-25 03:14, Shaohua Li wrote: > 2011/7/24 Jens Axboe : >> On 2011-07-22 22:59, Dan Williams wrote: >>> Some storage controllers benefit from completions always being steered >>> to the strict requester cpu rather than the looser "per-socket" steering >>> that blk_cpu_to_group() attempts by default. >>> >>> echo 2 > /sys/block//queue/rq_affinity >> >> I have applied this one, with a modified patch description. >> >> I like the adaptive solution, but it should be rewritten to not declare >> and expose softirq internals. Essentially have an API from >> kernel/softirq.c that can return whether a given (or perhaps just local) >> softirq handler is busy or not. > Jens, > I posted a similar patch about two years ago( > http://marc.info/?l=linux-kernel&m=126136252929329&w=2). > At that time, you actually did a lot of tests and said the same cpu > approach will cause huge lock contention and bounce. Is that get fixed? Yep, it's not ideal. But if we are running out of steam on a single processor, there's really not much of an option currently. -- Jens Axboe