From: Tejun Heo <tj@kernel.org>
To: Mark Lord <liml@rtr.ca>
Cc: Chris Webb <chris@arachsys.com>,
Ric Wheeler <rwheeler@redhat.com>, Andrei Tanas <andrei@tanas.ca>,
NeilBrown <neilb@suse.de>,
linux-kernel@vger.kernel.org,
IDE/ATA development list <linux-ide@vger.kernel.org>,
linux-scsi@vger.kernel.org, Jeff Garzik <jgarzik@redhat.com>,
Mark Lord <mlord@pobox.com>
Subject: Re: MD/RAID time out writing superblock
Date: Fri, 18 Sep 2009 00:47:44 +0900 [thread overview]
Message-ID: <4AB25A20.3040103@kernel.org> (raw)
In-Reply-To: <4AB23B17.2040204@rtr.ca>
Hello,
Mark Lord wrote:
>> That's interesting. One important side effect of issuing IDENTIFY is
>> that they will serialize command streams as they are not NCQ commands
>> and thus could change command patterns significantly.
> ..
>
> SMART is the opcode that is most frequently implicated here, not IDENTIFY.
Yeap, any non-NCQ commands would do it.
> Note that even a barrier FLUSH CACHE is non NCQ and will serialize
> the stream.
Yeah, I was just thinking that issuing non-NCQ commands mixed with NCQ
commands would make the command stream fluctuate more. Modern drives
are pretty good at lowering power consumption while idle so being more
fluctuative (is it a word?) might have something to do with the
problem. Just a wild speculation tho.
Thanks.
--
tejun
next prev parent reply other threads:[~2009-09-17 15:48 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-08-26 0:32 MD/RAID: what's wrong with sector 1953519935? Andrei Tanas
2009-08-26 0:50 ` NeilBrown
2009-08-26 1:06 ` Ric Wheeler
2009-08-26 1:24 ` NeilBrown
2009-08-26 1:31 ` Ric Wheeler
2009-08-26 2:22 ` Andrei Tanas
2009-08-26 2:41 ` Ric Wheeler
2009-08-26 3:45 ` Andrei Tanas
2009-08-26 10:34 ` Ric Wheeler
2009-08-26 14:46 ` Andrei Tanas
2009-08-26 14:49 ` Andrei Tanas
2009-08-26 15:39 ` Ric Wheeler
2009-08-26 18:12 ` Andrei Tanas
2009-08-26 18:12 ` Andrei Tanas
2009-08-27 0:07 ` Mark Lord
2009-08-27 1:37 ` Andrei Tanas
2009-08-27 1:37 ` Andrei Tanas
2009-08-27 2:33 ` Robert Hancock
2009-08-27 21:22 ` MD/RAID time out writing superblock Andrei Tanas
2009-08-27 21:57 ` Ric Wheeler
2009-08-31 8:10 ` Tejun Heo
2009-08-31 12:04 ` Ric Wheeler
2009-08-31 12:20 ` Tejun Heo
2009-09-07 11:44 ` Chris Webb
2009-09-07 11:59 ` Chris Webb
2009-09-09 12:02 ` Chris Webb
2009-09-14 7:41 ` Tejun Heo
2009-09-14 7:44 ` Tejun Heo
2009-09-14 12:48 ` Mark Lord
2009-09-14 13:05 ` Tejun Heo
2009-09-14 14:25 ` Mark Lord
2009-09-16 23:19 ` Chris Webb
2009-09-17 13:29 ` Mark Lord
2009-09-17 13:32 ` Mark Lord
2009-09-17 13:37 ` Chris Webb
2009-09-17 15:35 ` Tejun Heo
2009-09-17 16:16 ` Mark Lord
2009-09-17 16:17 ` Mark Lord
2009-09-18 17:05 ` Chris Webb
2009-09-20 17:35 ` Allan Wind
2009-09-28 5:32 ` Allan Wind
2009-09-21 10:26 ` Chris Webb
2009-09-21 19:47 ` Mark Lord
2009-09-22 6:16 ` Robert Hancock
2009-09-20 18:36 ` Robert Hancock
2009-09-14 13:11 ` Henrique de Moraes Holschuh
2009-09-14 13:24 ` Tejun Heo
2009-09-14 14:02 ` Henrique de Moraes Holschuh
2009-09-14 14:34 ` Tejun Heo
2009-09-14 13:14 ` Gabor Gombas
2009-09-07 16:55 ` Allan Wind
2009-09-07 23:26 ` Thomas Fjellstrom
2009-09-07 23:26 ` Thomas Fjellstrom
2009-09-14 7:46 ` Tejun Heo
2009-09-14 21:13 ` Thomas Fjellstrom
2009-09-14 22:23 ` Tejun Heo
2009-09-07 16:55 ` Allan Wind
2009-09-16 22:28 ` Chris Webb
2009-09-16 23:47 ` Tejun Heo
2009-09-17 0:34 ` Neil Brown
2009-09-17 12:00 ` Chris Webb
2009-09-17 11:57 ` Chris Webb
2009-09-17 15:44 ` Tejun Heo
2009-09-17 16:36 ` Allan Wind
2009-09-18 0:16 ` Tejun Heo
2009-09-18 2:47 ` Allan Wind
2009-09-18 17:07 ` Chris Webb
2009-09-20 18:46 ` Robert Hancock
2009-09-21 0:02 ` Kyle Moffett
2009-09-17 13:35 ` Mark Lord
2009-09-17 15:47 ` Tejun Heo [this message]
2009-08-31 12:21 ` Mark Lord
2009-08-31 23:45 ` Mark Lord
2009-09-01 13:07 ` Andrei Tanas
2009-09-01 13:07 ` Andrei Tanas
2009-09-01 13:15 ` Mark Lord
2009-09-01 13:30 ` Tejun Heo
2009-09-01 13:47 ` Ric Wheeler
2009-09-01 14:18 ` Andrei Tanas
2009-09-01 14:18 ` Andrei Tanas
2009-09-14 5:30 ` Marc Giger
2009-09-14 5:30 ` Marc Giger
2009-09-02 21:58 ` Allan Wind
2009-09-04 19:39 ` Andrei Tanas
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=4AB25A20.3040103@kernel.org \
--to=tj@kernel.org \
--cc=andrei@tanas.ca \
--cc=chris@arachsys.com \
--cc=jgarzik@redhat.com \
--cc=liml@rtr.ca \
--cc=linux-ide@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=mlord@pobox.com \
--cc=neilb@suse.de \
--cc=rwheeler@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.