From: Andi Kleen <ak@muc.de>
To: Alan Cox <alan@redhat.com>
Cc: Andi Kleen <ak@muc.de>, Anton Blanchard <anton@samba.org>,
mark_salyzyn@adaptec.com, Christoph Hellwig <hch@infradead.org>,
linux-kernel@vger.kernel.org, linux-scsi@vger.kernel.org
Subject: Re: PATCH: Further aacraid work
Date: 17 Jun 2004 23:25:59 +0200
Date: Thu, 17 Jun 2004 23:25:59 +0200 [thread overview]
Message-ID: <20040617212559.GA71701@colin2.muc.de> (raw)
In-Reply-To: <20040617205414.GE8705@devserv.devel.redhat.com>
On Thu, Jun 17, 2004 at 04:54:14PM -0400, Alan Cox wrote:
> I would rather see it below the I/O layer for things like AMD64. The
> reason I say this is that many drivers would suffer from iommu merging not
> gain, and others may have limits.
>
> Something like
>
> new_sglist = sg_squash(old_sglist, [target max segments], [max per seg])
>
> could be used by drivers when appropriate to hand back a better sg list
> (or if not possible the existing one). That would put control rather closer
> to the driver.
My understanding was that it was too late in the driver because the SG lists
are already sized, because higher layer manage this. That is why
the BIO_VMERGE_BOUNDARY define is checked by BIO, not the driver.
The input of sg_squash should not be an already mapped list
(that would be too costly) better would be probably
a pci_map_sg_merge() with hints that tries to merge and other
than that works like normal pci_map_sg()
-Andi
next prev parent reply other threads:[~2004-06-17 21:26 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <286GI-5y3-11@gated-at.bofh.it>
[not found] ` <286Qp-5EU-19@gated-at.bofh.it>
2004-06-17 19:10 ` PATCH: Further aacraid work Andi Kleen
2004-06-17 20:54 ` Alan Cox
2004-06-17 21:13 ` James Bottomley
2004-06-17 21:25 ` Andi Kleen [this message]
2004-06-18 15:19 ` Benjamin Herrenschmidt
2004-06-18 5:57 ` Jeff Garzik
2004-06-18 14:07 ` James Bottomley
2004-06-18 15:17 ` Benjamin Herrenschmidt
2004-06-29 20:55 Salyzyn, Mark
2004-06-29 23:22 ` Byron Stanoszek
2004-06-30 19:52 ` Byron Stanoszek
2004-06-30 19:59 ` Dario
-- strict thread matches above, loose matches on Subject: below --
2004-06-29 19:27 Salyzyn, Mark
2004-06-29 20:20 ` Byron Stanoszek
2004-06-29 20:42 ` Alan Cox
2004-06-29 18:53 Salyzyn, Mark
2004-06-29 19:03 ` Byron Stanoszek
2004-06-28 13:17 Salyzyn, Mark
2004-06-18 20:53 Salyzyn, Mark
2004-06-18 20:53 ` Salyzyn, Mark
2004-06-17 17:54 Salyzyn, Mark
2004-06-17 20:38 ` Alan Cox
2004-06-17 20:48 ` William Lee Irwin III
2004-06-17 20:56 ` James Bottomley
2004-06-18 15:05 ` William Lee Irwin III
2004-06-18 20:32 ` William Lee Irwin III
2004-06-27 17:33 ` James Bottomley
2004-06-17 14:39 Salyzyn, Mark
2004-06-17 14:39 ` Salyzyn, Mark
2004-06-17 14:55 ` James Bottomley
2004-06-17 14:58 ` Alan Cox
2004-06-17 15:15 ` Arjan van de Ven
2004-06-17 19:16 ` James Bottomley
2004-06-17 16:32 ` Clay Haapala
2004-06-17 16:37 ` James Bottomley
2004-06-17 16:46 ` Alan Cox
2004-06-17 15:11 ` Anton Blanchard
2004-06-17 12:53 Salyzyn, Mark
2004-06-17 12:53 ` Salyzyn, Mark
2004-06-17 13:07 ` Matthew Wilcox
2004-06-17 13:19 ` Christoph Hellwig
2004-06-17 13:55 ` James Bottomley
2004-06-17 13:32 ` Christoph Hellwig
2004-06-17 14:02 ` Alan Cox
2004-06-16 21:04 Alan Cox
2004-06-16 21:33 ` Christoph Hellwig
2004-06-16 21:40 ` Alan Cox
2004-06-16 21:42 ` Christoph Hellwig
2004-06-16 21:48 ` Alan Cox
2004-06-16 21:58 ` Christoph Hellwig
2004-06-16 22:06 ` Alan Cox
2004-06-29 17:48 ` Byron Stanoszek
2004-06-29 18:27 ` Mark Haverkamp
2004-06-29 18:37 ` Alan Cox
2004-06-30 2:02 ` bm
2004-06-30 16:07 ` Alan Cox
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=20040617212559.GA71701@colin2.muc.de \
--to=ak@muc.de \
--cc=alan@redhat.com \
--cc=anton@samba.org \
--cc=hch@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=mark_salyzyn@adaptec.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.