linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Tejun Heo <htejun@gmail.com>
To: Jeff Garzik <jeff@garzik.org>
Cc: Carlo Wood <carlo@alinoe.com>, Manoj Kasichainula <manoj@io.com>,
	linux-kernel@vger.kernel.org,
	IDE/ATA development list <linux-ide@vger.kernel.org>
Subject: Re: SATA RAID5 speed drop of 100 MB/s
Date: Sat, 23 Jun 2007 16:54:16 +0900	[thread overview]
Message-ID: <467CD1A8.5070700@gmail.com> (raw)
In-Reply-To: <467CC5C5.6040201@garzik.org>

Jeff Garzik wrote:
> Carlo Wood wrote:
>> The dmesg output of 33480a0ede8dcc7e6483054279008f972bd56fd3 (thus
>> "before") is:
> [...]
>> And the dmesg output of 551c012d7eea3dc5ec063c7ff9c718d39e77634f (thus
>> "after") is:
> [...]
> 
> Your disk configurations are quite radically different between the two
> kernels (see attached diff for key highlights).
> 
> The new behavior of the more recent kernel (551c012d7...) is that it now
> fully drives your hardware :)  The reset problems go away, NCQ is
> enabled, and if you had 3.0Gbps drives (you don't) they would be driven
> at a faster speed.
> 
> Given that some drives might be better tuned for benchmarks in
> non-queued mode, and that a major behavior difference is that your
> drives are now NCQ-enabled, the first thing I would suggest you try is
> disabling NCQ:
>     http://linux-ata.org/faq.html#ncq
> 
> Other indicators are the other changes in the "ahci 0000:00:1f.2:
> flags:" line, which do affect other behaviors, though none so important
> to RAID5 performance as NCQ, I would think.
> 
> Turning on NCQ also potentially affects barrier behavior in RAID, though
> I'm guessing that is not a factor here.

Ah.. right.  That should have enabled NCQ.  Me slow today.  :-)

-- 
tejun

  reply	other threads:[~2007-06-23  7:54 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-06-20 22:48 SATA Harddisk speed drop of 100 MB/s Carlo Wood
2007-06-20 23:06 ` Jeff Garzik
2007-06-21  3:36   ` Arjan van de Ven
2007-06-22 16:21     ` Carlo Wood
2007-06-22 21:17       ` Henrique de Moraes Holschuh
2007-06-22 21:27         ` Carlo Wood
2007-06-23  1:31           ` Henrique de Moraes Holschuh
2007-06-23  2:59             ` Carlo Wood
2007-06-23 17:29               ` Andrew Morton
2007-06-23 22:21                 ` Jeff Garzik
2007-06-25 15:18               ` Lennart Sorensen
2007-06-25 16:04                 ` Carlo Wood
2007-06-22 21:44   ` SATA RAID5 " Carlo Wood
2007-06-23  3:54     ` Carlo Wood
2007-06-23  6:22       ` Tejun Heo
2007-06-22 21:48   ` Carlo Wood
2007-06-23  7:03     ` Jeff Garzik
2007-06-23  7:54       ` Tejun Heo [this message]
2007-06-23 12:53       ` Carlo Wood
2007-06-23 17:30         ` Bartlomiej Zolnierkiewicz
2007-06-23 22:43         ` Jeff Garzik
2007-06-24 11:58           ` Michael Tokarev
2007-06-24 12:59             ` Dr. David Alan Gilbert
2007-06-24 14:21               ` Justin Piszcz
2007-06-24 15:52                 ` Michael Tokarev
2007-06-24 16:59                   ` Justin Piszcz
2007-06-24 22:07                     ` Carlo Wood
2007-06-24 23:46                       ` Mark Lord
2007-06-25  0:23                       ` Patrick Mau
2007-06-24 15:48               ` Michael Tokarev
2007-07-05 22:12             ` Phillip Susi

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=467CD1A8.5070700@gmail.com \
    --to=htejun@gmail.com \
    --cc=carlo@alinoe.com \
    --cc=jeff@garzik.org \
    --cc=linux-ide@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=manoj@io.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).