From mboxrd@z Thu Jan 1 00:00:00 1970 From: Per Forlin Subject: Re: [PATCH v2 03/12] mmc: mmc_test: add test for none blocking transfers Date: Wed, 20 Apr 2011 09:30:16 +0200 Message-ID: References: <1302116833-24540-1-git-send-email-per.forlin@linaro.org> <1302116833-24540-4-git-send-email-per.forlin@linaro.org> <97D3A72708D04647A5AC84A04996E5B5125FB8@039-SN1MPN1-006.039d.mgd.msft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Received: from mail-qy0-f174.google.com ([209.85.216.174]:46283 "EHLO mail-qy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752924Ab1DTHaR convert rfc822-to-8bit (ORCPT ); Wed, 20 Apr 2011 03:30:17 -0400 In-Reply-To: <97D3A72708D04647A5AC84A04996E5B5125FB8@039-SN1MPN1-006.039d.mgd.msft.net> Sender: linux-mmc-owner@vger.kernel.org List-Id: linux-mmc@vger.kernel.org To: Lin Tony-B19295 Cc: "linux-mmc@vger.kernel.org" , "linux-arm-kernel@lists.infradead.org" , "linux-kernel@vger.kernel.org" , "linaro-dev@lists.linaro.org" , Chris Ball On 17 April 2011 09:09, Lin Tony-B19295 wrote: > Hi Per > > =A0 =A0 =A0 =A0Just have a glance of your patch, good thinking. But I= have a question about this patch. You modified mmc_test to test your d= river. Does it mean your driver's performance enhancement depends on ap= plication? I added those tests in mmc_test to compare the performance between blocking and none blocking. Basically it tests performance gain if running dma_map and dma_unmap in parallel with the transfer, compared to running dma_map and dma_unmap in serial with the transfer. > The caller must have to know the next request so that could make driv= er prepare next during current transfer? mmc_test tests the ideal performance gain (all request are linked toget= her). > So testing your driver with blocking request & non blocking request w= ill have different throughput due to different application mechanism. Yes. I added support for mmc non blocking in the mmc block device but the performance gain here depends on how the FS-requests are propagated down to the mmc block device. If the request are added one by one, waiting for the last request to complete before adding the new request, there will be no performance gain. To test the mmc block performance I have run IOZone in user space. > =A0 =A0 =A0 =A0Thanks > > BR > Tony BR Per