From: Jens Axboe <email@example.com>
To: Andrew Vasquez <firstname.lastname@example.org>
Cc: Mike Anderson <email@example.com>,
Subject: Re: [ANNOUNCE] QLogic qla2xxx driver update available (v8.00.00b6).
Date: Thu, 6 Nov 2003 18:14:09 +0100 [thread overview]
Message-ID: <20031106171409.GN437@suse.de> (raw)
On Thu, Nov 06 2003, Andrew Vasquez wrote:
> > > o Given the ISPs inability to handle data segments that cross
> > > 32-bit page boundaries, and the overhead in defensive logic
> > > within the driver to prevent these cases (compare the 6.x
> > > code to the 8.x code and you will see what I mean), by
> > > disabling clustering we guarantee that a single SG element
> > > never crosses a 4GB boundary.
> > That is not, however. Linux will never give you a segment crossing a
> > 4GB boundary, exactly because most hardware cannot handle this.
> > > Now, in 2.6 there are some significant changes. For one, with the
> > > block layer rewrite and the ability to limit segment boundaries of a
> > > block queue request with the blk_queue_segment_boundary() call, a LLDD
> > > need not concern itself with any defensive fast-path logic to handle
> > > the 4GB cross.
> > Ditto 2.4. See BH_PHYS_4G().
> Yes, but if I recall, these checks did not enter until late in the 2.4
> branch. The original (engineering) intent of the 6.x series branch
> was to support all 2.4 kernels, though we are slowly (formally) moving
> away from the restrictions.
They were there at the same time as Linux supported > 1GB IO at all. So
that is incorrect, it's been there all along.
> > > So, we're left with the benefits of the overhead of this merge
> > > process done by the block layer. I'm certainly receptive to the
> > > notion of reexamining the use of clustering given some solid data
> > > points showing an (significant -- this is subjective) increase in
> > > performance and/or a resounding 'yeah, enable it!' from those in
> > > the block-layer 'know.'
> > In 2.6 clustering comes for free, so it would be silly not to enable
> > it.
> Thanks for the clarification, I'll add the parameter back into the
> template for the 8.x series driver.
next prev parent reply other threads:[~2003-11-06 17:15 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-11-06 17:11 [ANNOUNCE] QLogic qla2xxx driver update available (v8.00.00b6) Andrew Vasquez
2003-11-06 17:14 ` Jens Axboe [this message]
2003-11-06 17:43 ` Arjan van de Ven
2003-11-06 17:50 ` Jens Axboe
2003-11-06 17:55 ` Arjan van de Ven
2003-11-06 17:58 ` Jens Axboe
-- strict thread matches above, loose matches on Subject: below --
2003-11-06 19:33 Andrew Vasquez
2003-11-07 9:39 ` Christoph Hellwig
2003-11-06 17:45 Andrew Vasquez
2003-11-06 17:59 ` Arjan van de Ven
2003-11-07 9:37 ` Christoph Hellwig
2003-11-06 17:02 Andrew Vasquez
2003-11-06 17:53 ` Matthew Wilcox
2003-11-07 9:58 ` Christoph Hellwig
2003-11-07 9:33 ` Christoph Hellwig
2003-11-05 18:39 Andrew Vasquez
2003-11-06 9:17 ` Jens Axboe
2003-11-05 1:15 Andrew Vasquez
2003-11-05 9:17 ` Mike Anderson
2003-11-06 9:36 ` Christoph Hellwig
2003-11-06 10:51 ` Christoph Hellwig
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:
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
* 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).