From mboxrd@z Thu Jan 1 00:00:00 1970 From: merez@codeaurora.org Subject: Re: [PATCH v2 1/1] mmc: block: Add write packing control Date: Wed, 13 Jun 2012 12:52:58 -0700 (PDT) Message-ID: References: <1338576911-17089-1-git-send-email-merez@codeaurora.org> <1338576911-17089-2-git-send-email-merez@codeaurora.org> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7BIT Return-path: Received: from wolverine01.qualcomm.com ([199.106.114.254]:14914 "EHLO wolverine01.qualcomm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752476Ab2FMTxB (ORCPT ); Wed, 13 Jun 2012 15:53:01 -0400 In-Reply-To: Sender: linux-arm-msm-owner@vger.kernel.org List-Id: linux-arm-msm@vger.kernel.org To: Muthu Kumar Cc: Maya Erez , linux-mmc@vger.kernel.org, linux-arm-msm@vger.kernel.org, DOCUMENTATION , open list On Mon, June 11, 2012 5:28 pm, Muthu Kumar wrote: > On Mon, Jun 11, 2012 at 2:19 PM, Muthu Kumar wrote: >> On Fri, Jun 1, 2012 at 11:55 AM, Maya Erez wrote: >>> The write packing control will ensure that read requests latency is >>> not increased due to long write packed commands. >>> >>> The trigger for enabling the write packing is managing to pack several >>> write requests. The number of potential packed requests that will >>> trigger >>> the packing can be configured via sysfs by writing the required value >>> to: >>> /sys/block//num_wr_reqs_to_start_packing. >>> The trigger for disabling the write packing is fetching a read request. >>> >> >> If it is applicable only to MMC why do we have this sysfs attr for all >> block devices? > > Just to be clear, please create a directory, say mmc, under > /sys/block// and create the attr inside that. > > You can refer to dm (dm-sysfs.c) for sample implementation. > > Regards, > Muthu > Hi Muthu, I released a new version of this patch which doesn't include this change yet. I understand why you think it would be best to distinguish the MMC specific attribute from the general block devices attributes. However, since this attribute is created only for the MMC block device, other block devices won't be aware of it. Therefore, it doesn't necessarily require a separation to a different folder. Currently there is another MMC specific attribute (force_ro) which is also created in the root directory. I think it would be better to also create the num_wr_reqs_to_start_packing in the same folder as force_ro and not make it an exceptional attribute in its location and the code that handles it. I would appreciate your opinion on that. Thanks, Maya -- Sent by consultant of Qualcomm Innovation Center, Inc. Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum