From: Jeff Garzik <jgarzik@pobox.com>
To: Jens Axboe <axboe@suse.de>
Cc: Bartlomiej Zolnierkiewicz <B.Zolnierkiewicz@elka.pw.edu.pl>,
"Prakash K. Cheemplavam" <prakashkc@gmx.de>,
marcush@onlinehome.de, linux-kernel@vger.kernel.org,
eric_mudama@Maxtor.com
Subject: Re: Silicon Image 3112A SATA trouble
Date: Sun, 30 Nov 2003 11:41:55 -0500 [thread overview]
Message-ID: <3FCA1DD3.70004@pobox.com> (raw)
In-Reply-To: <20031130162523.GV10679@suse.de>
Jens Axboe wrote:
> On Sun, Nov 30 2003, Bartlomiej Zolnierkiewicz wrote:
>>Hmm. actually I was under influence that we have generic ioctls in 2.6.x,
>>but I can find only BLKSECTGET, BLKSECTSET was somehow lost. Jens?
>
>
> Probably because it's very dangerous to expose, echo something too big
> and watch your data disappear.
IMO, agreed.
Max KB per request really should be set by the driver, as it's a
hardware-specific thing that (as we see :)) is often errata-dependent.
Tangent: My non-pessimistic fix will involve submitting a single sector
DMA r/w taskfile manually, then proceeding with the remaining sectors in
another r/w taskfile. This doubles the interrupts on the affected
chipset/drive combos, but still allows large requests. I'm not terribly
fond of partial completions, as I feel they add complexity, particularly
so in my case: I can simply use the same error paths for both the
single-sector taskfile and the "everything else" taskfile, regardless of
which taskfile throws the error.
(thinking out loud) Though best for simplicity, I am curious if a
succession of "tiny/huge" transaction pairs are efficient? I am hoping
that the drive's cache, coupled with the fact that each pair of
taskfiles is sequentially contiguous, will not hurt speed too much over
a non-errata configuration...
Jeff
next prev parent reply other threads:[~2003-11-30 16:42 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-11-25 13:59 Silicon Image 3112A SATA trouble Prakash K. Cheemplavam
2003-11-29 15:39 ` Prakash K. Cheemplavam
2003-11-29 16:38 ` Julien Oster
2003-11-29 16:54 ` Jeff Garzik
2003-11-29 17:07 ` Craig Bradney
2003-11-30 1:51 ` Prakash K. Cheemplavam
2003-11-29 16:56 ` Jeff Garzik
2003-11-29 17:41 ` Miquel van Smoorenburg
2003-11-29 18:39 ` Jeff Garzik
2003-11-29 20:24 ` Marcus Hartig
2003-11-30 2:00 ` Prakash K. Cheemplavam
2003-11-30 14:47 ` Bartlomiej Zolnierkiewicz
2003-11-30 15:52 ` Prakash K. Cheemplavam
2003-11-30 16:21 ` Bartlomiej Zolnierkiewicz
2003-11-30 16:25 ` Jens Axboe
2003-11-30 16:41 ` Jeff Garzik [this message]
2003-11-30 16:51 ` Jens Axboe
2003-11-30 16:58 ` Bartlomiej Zolnierkiewicz
2003-11-30 17:06 ` Jeff Garzik
2003-11-30 17:10 ` Jens Axboe
2003-11-30 17:22 ` Jeff Garzik
2003-11-30 17:31 ` Jens Axboe
2003-11-30 17:48 ` Jeff Garzik
2003-11-30 17:56 ` Vojtech Pavlik
2003-11-30 18:17 ` Jens Axboe
2003-11-30 18:19 ` Jeff Garzik
2003-11-30 18:22 ` Jens Axboe
2003-11-30 18:31 ` Jeff Garzik
2003-11-30 19:44 ` Vojtech Pavlik
2003-11-30 21:05 ` Yaroslav Klyukin
2003-11-30 17:08 ` Jens Axboe
2003-11-30 17:13 ` Bartlomiej Zolnierkiewicz
2003-11-30 17:13 ` Jens Axboe
2003-11-30 17:18 ` Jeff Garzik
2003-11-30 17:28 ` Jens Axboe
2003-11-30 17:41 ` Jeff Garzik
2003-11-30 17:45 ` Jens Axboe
2003-11-30 17:57 ` Jeff Garzik
2003-11-30 18:21 ` Jens Axboe
2003-11-30 19:04 ` Jeff Garzik
2003-11-30 19:39 ` Jens Axboe
2003-11-30 20:35 ` Jeff Garzik
2003-12-01 9:02 ` Jens Axboe
2003-11-30 17:19 ` Prakash K. Cheemplavam
2003-11-30 18:07 ` Bartlomiej Zolnierkiewicz
2003-11-30 21:34 ` Prakash K. Cheemplavam
2003-11-30 16:27 ` Jeff Garzik
2003-11-30 16:34 ` Bartlomiej Zolnierkiewicz
[not found] <Pine.LNX.4.44.0311291453550.838-100000@coffee.psychology.mcmaster.ca>
2003-11-30 16:45 ` Jeff Garzik
2003-11-30 17:52 Luis Miguel García
2003-11-30 17:13 ` Craig Bradney
2003-11-30 18:27 ` Jeff Garzik
2003-11-30 18:41 Luis Miguel García
2003-11-30 21:15 ` Craig Bradney
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=3FCA1DD3.70004@pobox.com \
--to=jgarzik@pobox.com \
--cc=B.Zolnierkiewicz@elka.pw.edu.pl \
--cc=axboe@suse.de \
--cc=eric_mudama@Maxtor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=marcush@onlinehome.de \
--cc=prakashkc@gmx.de \
/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).