From mboxrd@z Thu Jan 1 00:00:00 1970 From: sshtylyov@mvista.com (Sergei Shtylyov) Date: Thu, 22 Mar 2012 17:14:12 +0400 Subject: [PATCH] ep93xx: Implement double buffering for M2M DMA channels In-Reply-To: <4F6AF845.9070209@metasoft.pl> References: <4F683B36.8090101@metasoft.pl> <4F6A78ED.3050403@gmail.com> <4F6AF845.9070209@metasoft.pl> Message-ID: <4F6B25A4.4090006@mvista.com> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org Hello. On 22-03-2012 14:00, Rafal Prylowski wrote: >> I haven't looked through the patch yet, since I'm waiting on more >> information from Mika and Hartley's testing. >> However, the commit log doesn't tell me why we want this change. Is it a >> performance improvement? If so, do you have some numbers that we can >> paste into the commit log? > In principle, using double buffering should be faster than using only > one buffer and disabling/enabling channel each time. But my measurements > doesn't show any significant change. > The real reason for this change is that current code is not 100% reliable > in IDE-DMA (I'm planning to submit ep93xx ide driver to linux-ide soon). IDE or libata driver? Asking because IDE drivers are not accepted anymore. WBR, Sergei From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757998Ab2CVNPk (ORCPT ); Thu, 22 Mar 2012 09:15:40 -0400 Received: from mail-bk0-f46.google.com ([209.85.214.46]:36938 "EHLO mail-bk0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755608Ab2CVNPi (ORCPT ); Thu, 22 Mar 2012 09:15:38 -0400 Message-ID: <4F6B25A4.4090006@mvista.com> Date: Thu, 22 Mar 2012 17:14:12 +0400 From: Sergei Shtylyov User-Agent: Mozilla/5.0 (Windows NT 5.1; rv:11.0) Gecko/20120312 Thunderbird/11.0 MIME-Version: 1.0 To: Rafal Prylowski CC: Ryan Mallon , "vinod.koul@intel.com" , Mika Westerberg , "linux-kernel@vger.kernel.org" , "linux-arm-kernel@lists.infradead.org" , H Hartley Sweeten Subject: Re: [PATCH] ep93xx: Implement double buffering for M2M DMA channels References: <4F683B36.8090101@metasoft.pl> <4F6A78ED.3050403@gmail.com> <4F6AF845.9070209@metasoft.pl> In-Reply-To: <4F6AF845.9070209@metasoft.pl> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hello. On 22-03-2012 14:00, Rafal Prylowski wrote: >> I haven't looked through the patch yet, since I'm waiting on more >> information from Mika and Hartley's testing. >> However, the commit log doesn't tell me why we want this change. Is it a >> performance improvement? If so, do you have some numbers that we can >> paste into the commit log? > In principle, using double buffering should be faster than using only > one buffer and disabling/enabling channel each time. But my measurements > doesn't show any significant change. > The real reason for this change is that current code is not 100% reliable > in IDE-DMA (I'm planning to submit ep93xx ide driver to linux-ide soon). IDE or libata driver? Asking because IDE drivers are not accepted anymore. WBR, Sergei