From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bartlomiej Zolnierkiewicz Subject: Re: [PATCH RESEND 0/1] AHCI: Optimize interrupt processing Date: Thu, 11 Sep 2014 15:36:31 +0200 Message-ID: <4127129.ClfhyhZXo5@amdc1032> References: <20130521235003.GE6985@mtj.dyndns.org> <20140911124248.GA18490@dhcp-27-160.brq.redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7Bit Return-path: Received: from mailout1.samsung.com ([203.254.224.24]:16233 "EHLO mailout1.samsung.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753400AbaIKNgh (ORCPT ); Thu, 11 Sep 2014 09:36:37 -0400 In-reply-to: <20140911124248.GA18490@dhcp-27-160.brq.redhat.com> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Alexander Gordeev Cc: Tejun Heo , linux-kernel@vger.kernel.org, linux-ide@vger.kernel.org Hi, On Thursday, September 11, 2014 02:42:49 PM Alexander Gordeev wrote: > The numbers are taken by running 'dd if=/dev/sd{a,b} of=/dev/null' > in parallel. All time values are in us. > > Before this update host lock average holdtime was 2.45 and > average waittime was 1.24. After the update average holdtime > dropped to 0.29 (about eight times) while average waittime > decreased to 0.58 (about two times). > > Also, port events are handled with local interrupts enabled > and compete on individual per-port locks with average holdtime > 1.25 and average waittime 1.48. So combined average holdtime > spent while holding host and port locks decreased from 2.45 to > 0.29 + 1.25 = 1.54 (about 1.6 times). > > The downside of this change is introduction of a kernel thread. > > The upside is shorter access time to port locks and moving port > interrupts handling out of the hardware interrupt context. IMHO it would be great to put the above results into the patch description (it now looks a bit skimpy). Best regards, -- Bartlomiej Zolnierkiewicz Samsung R&D Institute Poland Samsung Electronics