linux-scsi.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jeff Garzik <jeff@garzik.org>
To: Linus Torvalds <torvalds@osdl.org>
Cc: Steve Byan <smb@egenera.com>, Mark Lord <lkml@rtr.ca>,
	Matthias Andree <matthias.andree@gmx.de>,
	Douglas Gilbert <dougg@torque.net>, Mark Rustad <mrustad@mac.com>,
	linux-scsi@vger.kernel.org,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: sg regression in 2.6.16-rc5
Date: Fri, 03 Mar 2006 14:42:44 -0500	[thread overview]
Message-ID: <44089C34.2030604@garzik.org> (raw)
In-Reply-To: <Pine.LNX.4.64.0603031035140.22647@g5.osdl.org>

Linus Torvalds wrote:
> For example, I think the IDE driver defaults to a maximum transfer of 256 
> sectors, and the same number of max scatter-gather entries. Some 
> controllers will actually lower that, due to silly hw problems.

Yep.  Just to be specific:

256 max sectors IDE driver, 200 max sectors libata (due to driver not 
hardware).

256 max s/g entries hardware limit, but due to a IOMMU merging worst 
case libata (IDE driver too?) winds up with a 128 entry practical limit.

Newer SATA controllers eliminate the s/g entry limit and DMA boundary 
limits, but its still 256 max-sectors for ATAPI (64k for LBA48 ATA).

	Jeff



  parent reply	other threads:[~2006-03-03 19:42 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-02-28 17:54 sg regression in 2.6.16-rc5 Mark Rustad
2006-02-28 19:53 ` Douglas Gilbert
2006-02-28 20:38   ` Kai Makisara
2006-03-01  2:04     ` Douglas Gilbert
2006-03-01  2:08     ` Mark Rustad
2006-03-01  8:38   ` Matthias Andree
2006-03-01 18:28     ` Linus Torvalds
2006-03-01 18:32       ` Mark Lord
2006-03-01 18:42         ` Linus Torvalds
2006-03-01 18:50           ` Matthew Wilcox
2006-03-03 18:27           ` Steve Byan
2006-03-03 18:55             ` Linus Torvalds
2006-03-03 19:13               ` Steve Byan
2006-03-03 19:42               ` Jeff Garzik [this message]
2006-03-03 20:09                 ` Linus Torvalds
2006-03-03 20:30                   ` Jeff Garzik
2006-03-01 19:33       ` Douglas Gilbert
2006-03-01 20:42         ` Mike Christie
2006-03-01 22:30           ` James Bottomley
2006-03-01 22:56             ` Mike Christie
2006-03-01 21:06         ` Kai Makisara
2006-03-02 19:50           ` Douglas Gilbert
2006-03-02 21:25             ` Linus Torvalds
2006-03-02 23:08               ` Matthias Andree
2006-03-02 23:20                 ` Linus Torvalds
2006-03-03  0:02                   ` Linus Torvalds
2006-03-03  0:12                     ` Linus Torvalds
2006-03-03 16:43                   ` Douglas Gilbert
2006-03-03 17:17                     ` Linus Torvalds
2006-03-02 23:06             ` Matthias Andree
  -- strict thread matches above, loose matches on Subject: below --
2006-03-02 23:04 Falkinder, David Malcolm
2006-03-03 20:24 Falkinder, David Malcolm
2006-03-03 21:54 ` Linus Torvalds

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=44089C34.2030604@garzik.org \
    --to=jeff@garzik.org \
    --cc=dougg@torque.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=lkml@rtr.ca \
    --cc=matthias.andree@gmx.de \
    --cc=mrustad@mac.com \
    --cc=smb@egenera.com \
    --cc=torvalds@osdl.org \
    /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).