All of lore.kernel.org
 help / color / mirror / Atom feed
From: Corrado Zoccolo <czoccolo@gmail.com>
To: Jeff Garzik <jeff@garzik.org>
Cc: Jens Axboe <jens.axboe@oracle.com>,
	Linux-Kernel <linux-kernel@vger.kernel.org>,
	Jeff Moyer <jmoyer@redhat.com>, Vivek Goyal <vgoyal@redhat.com>,
	Shaohua Li <shaohua.li@intel.com>,
	Gui Jianfeng <guijianfeng@cn.fujitsu.com>
Subject: Re: [PATCH] cfq-iosched: NCQ SSDs do not need read queue merging
Date: Mon, 11 Jan 2010 13:26:22 +0100	[thread overview]
Message-ID: <4e5e476b1001110426t2afa0502p7f19a9b24e48ba82@mail.gmail.com> (raw)
In-Reply-To: <4B4B0AA9.5020900@garzik.org>

On Mon, Jan 11, 2010 at 12:25 PM, Jeff Garzik <jeff@garzik.org> wrote:
> On 01/10/2010 04:04 PM, Corrado Zoccolo wrote:
>>
>> NCQ SSDs' performances are not affected by
>> distance of read requests, so there is no point in having
>> overhead to merge such queues.
>>
>> Non-NCQ SSDs showed regression in some special cases, so
>> they are ruled out by this patch.
>>
>> This patch intentionally doesn't affect writes, so
>> it changes the queued[] field, to be indexed by
>> READ/WRITE instead of SYNC/ASYNC, and only compute proximity
>> for queues with WRITE requests.
>>
>> Signed-off-by: Corrado Zoccolo<czoccolo@gmail.com>
>
> That's not really true.  Overhead always increases as the total number of
> ATA commands issued increases.

Jeff Moyer tested the patch on the workload that mostly benefit of
queue merging, and found that
the performance was improved by the patch.
So removing the CPU overhead helps much more than the marginal gain
given by merging on this hardware.

Corrado

>
>        Jeff
>
>
>
>
>

  reply	other threads:[~2010-01-11 12:26 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-12-30 12:10 [PATCH] cfq-iosched: non-rot devices do not need queue merging Corrado Zoccolo
2009-12-30 18:45 ` Jens Axboe
2009-12-30 20:31   ` Corrado Zoccolo
2009-12-30 21:11     ` Jens Axboe
2009-12-30 21:21       ` Corrado Zoccolo
2009-12-30 21:34         ` Jens Axboe
2009-12-30 22:22           ` [PATCH] cfq-iosched: non-rot devices do not need read " Corrado Zoccolo
2010-01-04 14:47             ` Vivek Goyal
2010-01-04 16:36               ` Corrado Zoccolo
2010-01-04 16:51                 ` Jeff Moyer
2010-01-04 18:32                   ` Vivek Goyal
2010-01-04 18:37                   ` Corrado Zoccolo
2010-01-04 18:51                     ` Vivek Goyal
2010-01-04 19:04                       ` Jeff Moyer
2010-01-04 20:37                         ` Corrado Zoccolo
2010-01-05 14:58                           ` Jeff Moyer
2010-01-05 15:13                             ` Vivek Goyal
2010-01-05 21:19                               ` Jeff Moyer
2010-01-05 21:48                                 ` Corrado Zoccolo
2010-01-07 10:56                                   ` Kirill Afonshin
2010-01-07 13:38                                     ` Corrado Zoccolo
2010-01-07 14:36                                       ` Vivek Goyal
2010-01-07 17:00                                         ` Corrado Zoccolo
2010-01-07 18:37                                           ` Vivek Goyal
2010-01-07 20:16                                             ` Corrado Zoccolo
2010-01-08 18:53                                               ` Vivek Goyal
2010-01-10 12:55                                   ` Corrado Zoccolo
2010-01-10 21:04             ` [PATCH] cfq-iosched: NCQ SSDs " Corrado Zoccolo
2010-01-10 21:08               ` Corrado Zoccolo
2010-01-11 11:25               ` Jeff Garzik
2010-01-11 12:26                 ` Corrado Zoccolo [this message]
2010-01-11 13:13                   ` Jens Axboe
2010-01-11 13:18                     ` Jeff Garzik
2010-01-11 13:24                       ` Jens Axboe
2010-01-11 14:53                       ` Corrado Zoccolo
2010-01-11 16:44                         ` Vivek Goyal
2010-01-11 17:00                           ` Corrado Zoccolo
2010-01-11 17:07                             ` Vivek Goyal
2010-01-11 19:05                               ` Corrado Zoccolo
2010-01-11 17:11                             ` Vivek Goyal
2010-01-11 19:09                               ` Corrado Zoccolo

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=4e5e476b1001110426t2afa0502p7f19a9b24e48ba82@mail.gmail.com \
    --to=czoccolo@gmail.com \
    --cc=guijianfeng@cn.fujitsu.com \
    --cc=jeff@garzik.org \
    --cc=jens.axboe@oracle.com \
    --cc=jmoyer@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=shaohua.li@intel.com \
    --cc=vgoyal@redhat.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.