All of lore.kernel.org
 help / color / mirror / Atom feed
From: Konstantin Dorfman <kdorfman@codeaurora.org>
To: "Per Förlin" <per.forlin@stericsson.com>
Cc: "cjb@laptop.org" <cjb@laptop.org>,
	"linux-mmc@vger.kernel.org" <linux-mmc@vger.kernel.org>,
	"per.lkml@gmail.com" <per.lkml@gmail.com>
Subject: Re: [PATCH v2] mmc: fix async request mechanism for sequential read scenarios
Date: Mon, 12 Nov 2012 14:49:00 +0200	[thread overview]
Message-ID: <50A0F03C.10502@codeaurora.org> (raw)
In-Reply-To: <50975AA8.8030304@stericsson.com>

On 11/05/2012 08:20 AM, Per Förlin wrote:
> Hi Konstantin,
> 
> On 11/01/2012 03:40 PM, Konstantin Dorfman wrote:
>> When current request is running on the bus and if next request fetched
>> by mmcqd is NULL, mmc context (mmcqd thread) gets blocked until the
>> current request completes. This means if new request comes in while
>> the mmcqd thread is blocked, this new request can not be prepared in
>> parallel to current ongoing request. This may result in latency to
>> start new request.
>>
>> This change allows to wake up the MMC thread (which
>> is waiting for the current running request to complete). Now once the
>> MMC thread is woken up, new request can be fetched and prepared in
>> parallel to current running request which means this new request can
>> be started immediately after the current running request completes.
>>
>> With this change read throughput is improved by 16%.
> What HW and what test cases have you been running?

I use the msm_sdcc controller and ran lmdd, tiotest, iozone benchmark
tool (details were on other mail in this thread).

I ran it on Qualcomm® SnapdragonT S4 ProAPQ8064

Thanks,

-- 
Konstantin Dorfman,
QUALCOMM ISRAEL, on behalf of Qualcomm Innovation Center,
Inc. is a member of Code Aurora Forum,
hosted by The Linux Foundation

  parent reply	other threads:[~2012-11-12 12:49 UTC|newest]

Thread overview: 88+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <n@samsung.com>
2012-08-05 13:08 ` [RFC/PATCH] mmc: core: Add support for idle time BKOPs Maya Erez
2012-08-05 13:08   ` Maya Erez
2012-08-30  7:36   ` Jaehoon Chung
2012-09-04  5:42     ` merez
2012-09-04  5:42       ` merez
2012-10-04 22:28 ` [PATCH v2] mmc: core: Add support for idle time BKOPS Maya Erez
2012-10-04 22:28   ` Maya Erez
2012-10-09  3:52   ` merez
2012-10-09  3:52     ` merez
2012-10-16  7:53   ` Jaehoon Chung
2012-11-07  4:28     ` merez
2012-11-07  4:28       ` merez
2012-11-08  5:26       ` Jaehoon Chung
2012-11-11  9:25   ` Subhash Jadavani
2012-10-18 16:31 ` [PATCH 1/6] mmc: core: sdio_io.c: Fixed lines with > 80 chars Sangho Yi
2012-10-18 16:31   ` [PATCH 2/6] mmc: core: sdio_bus.c: Removed trailing whitespace error Sangho Yi
2012-10-18 16:31   ` [PATCH 3/6] mmc: core: sdio_bus.c: Fixed lines > 80 chars Sangho Yi
2012-10-18 23:54     ` Jaehoon Chung
2012-10-18 16:31   ` [PATCH 4/6] mmc: core: sdio_bus.c: Removed space between func name and () Sangho Yi
2012-10-18 16:31   ` [PATCH 5/6] mmc: core: sdio_bus.c: Fixed a warning for the pr_warning( Sangho Yi
2012-10-18 16:31   ` [PATCH 6/6] mmc: core: sdio_bus.c: Removed unnecessary NULL check routine Sangho Yi
2012-10-18 16:47   ` [PATCH 1/6] mmc: core: sdio_io.c: Fixed lines with > 80 chars Joe Perches
2012-11-01 14:40 ` [PATCH v2] mmc: fix async request mechanism for sequential read scenarios Konstantin Dorfman
2012-11-05  6:20   ` Per Förlin
2012-11-05  7:15     ` Jaehoon Chung
2012-11-12 12:10       ` Konstantin Dorfman
2012-11-08 10:41     ` Jaehoon Chung
2012-11-08 12:51       ` merez
2012-11-09  5:46         ` Jaehoon Chung
2012-11-12 12:49     ` Konstantin Dorfman [this message]
2012-11-06  8:40   ` Jaehoon Chung
2012-11-12 12:42     ` Konstantin Dorfman
2012-11-12 16:51 ` [PATCH v3] " Konstantin Dorfman
2012-11-13 13:42   ` Seungwon Jeon
2012-11-15 10:23     ` Seungwon Jeon
2012-11-20  2:05       ` Seungwon Jeon
2012-11-25 11:56 ` [PATCH v3] mmc: core: Add support for idle time BKOPS Maya Erez
2012-11-25 11:56   ` Maya Erez
2012-11-25 12:46   ` merez
2012-11-25 12:46     ` merez
2012-11-28 14:22     ` Chris Ball
2012-11-29 12:40   ` Jaehoon Chung
2012-12-03  9:49     ` merez
2012-12-04  9:52       ` Ulf Hansson
2012-12-04 21:17         ` merez
2012-12-06 10:18           ` Ulf Hansson
2012-12-12 12:32             ` merez
2012-12-13 10:17               ` Ulf Hansson
2012-12-21  8:35                 ` Maya Erez
2012-12-21  8:35                   ` Maya Erez
2012-12-21  9:56                   ` Ulf Hansson
2012-12-21 10:24                     ` Jaehoon Chung
2012-12-05 13:38 ` [PATCH v4] mmc: fix async request mechanism for sequential read scenarios Konstantin Dorfman
2012-12-06  5:24   ` Seungwon Jeon
2012-12-06 14:23     ` Konstantin Dorfman
2012-12-10 14:23 ` [RESEND PATCH " Konstantin Dorfman
2012-12-12  9:26   ` Seungwon Jeon
2012-12-17 12:26   ` Seungwon Jeon
2012-12-18 16:00     ` Konstantin Dorfman
2012-12-18 16:19       ` Chris Ball
2012-12-20  7:39       ` Seungwon Jeon
2012-12-26  9:26 ` [PATCH v5] " Konstantin Dorfman
2012-12-28 10:16   ` Seungwon Jeon
2013-01-14 19:31     ` Chris Ball
2013-01-15 12:00       ` Konstantin Dorfman
2013-01-22 10:48   ` [PATCH 1/2] mmc: core: fix permanent sleep of mmcqd during card removal Seungwon Jeon
2013-01-31 11:05     ` Jaehoon Chung
2013-01-31 11:25       ` Seungwon Jeon
2013-02-08 12:07     ` Konstantin Dorfman
2013-02-11 17:00     ` Chris Ball
2013-01-30  6:30   ` Seungwon Jeon
2013-01-31  6:53     ` Subhash Jadavani
2013-02-04 11:43     ` Subhash Jadavani
2013-02-05  5:57       ` Seungwon Jeon
2013-02-05  7:05         ` Jaehoon Chung
2013-02-05  7:32           ` Subhash Jadavani
2013-02-04 19:27     ` Konstantin Dorfman
2013-01-10 20:15 ` [PATCH v5 0/3] Add support for periodic BKOPS Maya Erez
2013-01-11 11:33   ` Jaehoon Chung
2014-11-10 17:13 ` [PATCH 0/3] mmc: Support FFU for eMMC v5.0 Avi Shchislowski
2014-11-11  3:33   ` Jaehoon Chung
2014-11-10 17:13 ` [PATCH 1/3] " Avi Shchislowski
2014-11-10 17:13   ` Avi Shchislowski
2014-11-11  3:07   ` Jaehoon Chung
2014-11-11  8:44     ` Avi Shchislowski
2014-11-10 17:18 ` [PATCH 2/3] " Avi Shchislowski
2014-11-10 17:18   ` Avi Shchislowski
2014-11-11  3:30   ` Jaehoon Chung

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=50A0F03C.10502@codeaurora.org \
    --to=kdorfman@codeaurora.org \
    --cc=cjb@laptop.org \
    --cc=linux-mmc@vger.kernel.org \
    --cc=per.forlin@stericsson.com \
    --cc=per.lkml@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.