From: Avri Altman <Avri.Altman@sandisk.com>
To: Linus Walleij <linus.walleij@linaro.org>,
"linux-mmc@vger.kernel.org" <linux-mmc@vger.kernel.org>,
Ulf Hansson <ulf.hansson@linaro.org>,
"Adrian Hunter" <adrian.hunter@intel.com>,
Paolo Valente <paolo.valente@linaro.org>
Cc: Chunyan Zhang <zhang.chunyan@linaro.org>,
Baolin Wang <baolin.wang@linaro.org>,
"linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
Jens Axboe <axboe@kernel.dk>, "Christoph Hellwig" <hch@lst.de>,
Arnd Bergmann <arnd@arndb.de>
Subject: RE: [PATCH 00/16] multiqueue for MMC/SD third try
Date: Sat, 11 Feb 2017 13:03:03 +0000 [thread overview]
Message-ID: <9BEFCB713C10BF4B91D714797ECA5EEA117E08F5@ULS-OP-MBXIP04.sdcorp.global.sandisk.com> (raw)
In-Reply-To: <20170209153403.9730-1-linus.walleij@linaro.org>
>
> The iozone results seem a bit consistent and all values seem to be noisy and
> not say much. I don't know why really, maybe the test is simply not relevant,
> the tests don't seem to be significantly affected by any of the patches, so
> let's focus on the dd and find tests.
Maybe use a more selective testing mode instead of -az.
Also maybe you want to clear the cache between the sequential and random tests:
#sync�
#echo 3 > /proc/sys/vm/drop_caches�
#sync�
It helps to obtain a more robust results.
> What immediately jumps out at you is that linear read/writes perform just as
> nicely or actually better with MQ than with the old block layer.
How come 22.7MB/s before vs. 22.1MB/s after is better? or did I misunderstand the output?
Also as dd is probably using the buffer cache, unlike the iozone test in which you properly used -I
for direct mode to isolate the blk-mq effect - does it really say much?
WARNING: multiple messages have this Message-ID (diff)
From: Avri Altman <Avri.Altman@sandisk.com>
To: Linus Walleij <linus.walleij@linaro.org>,
"linux-mmc@vger.kernel.org" <linux-mmc@vger.kernel.org>,
Ulf Hansson <ulf.hansson@linaro.org>,
Adrian Hunter <adrian.hunter@intel.com>,
Paolo Valente <paolo.valente@linaro.org>
Cc: Chunyan Zhang <zhang.chunyan@linaro.org>,
Baolin Wang <baolin.wang@linaro.org>,
"linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
Jens Axboe <axboe@kernel.dk>, Christoph Hellwig <hch@lst.de>,
Arnd Bergmann <arnd@arndb.de>
Subject: RE: [PATCH 00/16] multiqueue for MMC/SD third try
Date: Sat, 11 Feb 2017 13:03:03 +0000 [thread overview]
Message-ID: <9BEFCB713C10BF4B91D714797ECA5EEA117E08F5@ULS-OP-MBXIP04.sdcorp.global.sandisk.com> (raw)
In-Reply-To: <20170209153403.9730-1-linus.walleij@linaro.org>
>
> The iozone results seem a bit consistent and all values seem to be noisy and
> not say much. I don't know why really, maybe the test is simply not relevant,
> the tests don't seem to be significantly affected by any of the patches, so
> let's focus on the dd and find tests.
Maybe use a more selective testing mode instead of -az.
Also maybe you want to clear the cache between the sequential and random tests:
#sync
#echo 3 > /proc/sys/vm/drop_caches
#sync
It helps to obtain a more robust results.
> What immediately jumps out at you is that linear read/writes perform just as
> nicely or actually better with MQ than with the old block layer.
How come 22.7MB/s before vs. 22.1MB/s after is better? or did I misunderstand the output?
Also as dd is probably using the buffer cache, unlike the iozone test in which you properly used -I
for direct mode to isolate the blk-mq effect - does it really say much?
next prev parent reply other threads:[~2017-02-11 13:03 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-09 15:33 [PATCH 00/16] multiqueue for MMC/SD third try Linus Walleij
2017-02-09 15:33 ` [PATCH 01/16] mmc: core: move some code in mmc_start_areq() Linus Walleij
[not found] ` <CGME20170228145506epcas1p1dd72cc5738c3f36df97ac06603ad2731@epcas1p1.samsung.com>
2017-02-28 14:55 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:33 ` [PATCH 02/16] mmc: core: refactor asynchronous request finalization Linus Walleij
[not found] ` <CGME20170228145552epcas5p4a43c23971d58b30ad6ab9d2c612abe9a@epcas5p4.samsung.com>
2017-02-28 14:55 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:33 ` [PATCH 03/16] mmc: core: refactor mmc_request_done() Linus Walleij
[not found] ` <CGME20170228145627epcas1p18fb6390b7ae14a6961fac9703712e0a0@epcas1p1.samsung.com>
2017-02-28 14:56 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:33 ` [PATCH 04/16] mmc: core: move the asynchronous post-processing Linus Walleij
2017-02-09 15:33 ` [PATCH 05/16] mmc: core: add a kthread for completing requests Linus Walleij
[not found] ` <CGME20170228145719epcas5p33d013fd48483bfba477b3f607dcdccb4@epcas5p3.samsung.com>
2017-02-28 14:57 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:33 ` [PATCH 06/16] mmc: core: replace waitqueue with worker Linus Walleij
2017-02-22 13:29 ` Adrian Hunter
2017-03-09 22:49 ` Linus Walleij
2017-03-10 14:21 ` Adrian Hunter
2017-03-10 22:05 ` Jens Axboe
2017-03-13 9:25 ` Adrian Hunter
2017-03-13 14:19 ` Jens Axboe
2017-03-14 12:59 ` Adrian Hunter
2017-03-14 14:36 ` Jens Axboe
2017-03-14 14:43 ` Christoph Hellwig
2017-03-14 14:52 ` Jens Axboe
2017-03-28 7:47 ` Linus Walleij
2017-03-28 7:46 ` Linus Walleij
[not found] ` <CGME20170228161023epcas5p3916c2e171d57b8c7814be7841fbab3aa@epcas5p3.samsung.com>
2017-02-28 16:10 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:33 ` [PATCH 07/16] mmc: core: do away with is_done_rcv Linus Walleij
[not found] ` <CGME20170228161047epcas1p2f307733cb1c441d0c290e794a04a06a8@epcas1p2.samsung.com>
2017-02-28 16:10 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:33 ` [PATCH 08/16] mmc: core: do away with is_new_req Linus Walleij
[not found] ` <CGME20170228161102epcas5p25dc3b560013599fda6cc750f6d528595@epcas5p2.samsung.com>
2017-02-28 16:11 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:33 ` [PATCH 09/16] mmc: core: kill off the context info Linus Walleij
[not found] ` <CGME20170228161117epcas5p20a6e62146733466b98c0ef4ea6efbb5f@epcas5p2.samsung.com>
2017-02-28 16:11 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:33 ` [PATCH 10/16] mmc: queue: simplify queue logic Linus Walleij
[not found] ` <CGME20170228161132epcas5p265793e8675aa2f1e5dd199a9ee0ab6f1@epcas5p2.samsung.com>
2017-02-28 16:11 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:33 ` [PATCH 11/16] mmc: block: shuffle retry and error handling Linus Walleij
[not found] ` <CGME20170228174522epcas5p34dce6477eb96f7e0fb38431c4de35f60@epcas5p3.samsung.com>
2017-02-28 17:45 ` Bartlomiej Zolnierkiewicz
[not found] ` <CGME20170301114559epcas5p1a0c32fbc3a5573a6f1c6291792ea1b2e@epcas5p1.samsung.com>
2017-03-01 11:45 ` Bartlomiej Zolnierkiewicz
[not found] ` <CGME20170301155243epcas1p1140ce11db60b31065a0356525a2ee0a0@epcas1p1.samsung.com>
2017-03-01 15:52 ` Bartlomiej Zolnierkiewicz
[not found] ` <CGME20170301155822epcas5p103373c6afbd516e4792ebef9bb202b94@epcas5p1.samsung.com>
2017-03-01 15:58 ` Bartlomiej Zolnierkiewicz
[not found] ` <CGME20170301174856epcas5p16bdf861a0117a33f9dad37a81449a95e@epcas5p1.samsung.com>
2017-03-01 17:48 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:33 ` [PATCH 12/16] mmc: queue: stop flushing the pipeline with NULL Linus Walleij
[not found] ` <CGME20170228180309epcas5p317af83f41d3b0426868dcfd660bd0aec@epcas5p3.samsung.com>
2017-02-28 18:03 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:34 ` [PATCH 13/16] mmc: queue: issue struct mmc_queue_req items Linus Walleij
[not found] ` <CGME20170228181009epcas1p4ca0e714214097d07d7172182ba8e032b@epcas1p4.samsung.com>
2017-02-28 18:10 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:34 ` [PATCH 14/16] mmc: queue: get/put struct mmc_queue_req Linus Walleij
[not found] ` <CGME20170228182149epcas1p28789bce5433cee1579e8b8d083ba5811@epcas1p2.samsung.com>
2017-02-28 18:21 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:34 ` [PATCH 15/16] mmc: queue: issue requests in massive parallel Linus Walleij
[not found] ` <CGME20170301120247epcas1p1ad2be24dc9bbd1218dab8f565fb82b27@epcas1p1.samsung.com>
2017-03-01 12:02 ` Bartlomiej Zolnierkiewicz
2017-02-09 15:34 ` [PATCH 16/16] RFC: mmc: switch MMC/SD to use blk-mq multiqueueing v3 Linus Walleij
2017-02-09 15:39 ` [PATCH 00/16] multiqueue for MMC/SD third try Christoph Hellwig
2017-02-11 13:03 ` Avri Altman [this message]
2017-02-11 13:03 ` Avri Altman
2017-02-12 16:16 ` Linus Walleij
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=9BEFCB713C10BF4B91D714797ECA5EEA117E08F5@ULS-OP-MBXIP04.sdcorp.global.sandisk.com \
--to=avri.altman@sandisk.com \
--cc=adrian.hunter@intel.com \
--cc=arnd@arndb.de \
--cc=axboe@kernel.dk \
--cc=baolin.wang@linaro.org \
--cc=hch@lst.de \
--cc=linus.walleij@linaro.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-mmc@vger.kernel.org \
--cc=paolo.valente@linaro.org \
--cc=ulf.hansson@linaro.org \
--cc=zhang.chunyan@linaro.org \
/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.