From: Jens Axboe <axboe@suse.de>
To: Alan Stern <stern@rowland.harvard.edu>
Cc: Kai Makisara <Kai.Makisara@kolumbus.fi>,
James Bottomley <James.Bottomley@steeleye.com>,
Oliver Neukum <oliver@neukum.org>,
Patrick Mansfield <patmans@us.ibm.com>,
Douglas Gilbert <dougg@torque.net>,
SCSI development list <linux-scsi@vger.kernel.org>,
USB development list <linux-usb-devel@lists.sourceforge.net>
Subject: Re: Re: Unaligned scatter-gather buffers and usb-storage
Date: Thu, 20 Nov 2003 17:24:58 +0100 [thread overview]
Message-ID: <20031120162457.GC1106@suse.de> (raw)
In-Reply-To: <Pine.LNX.4.44L0.0311201059130.878-100000@ida.rowland.org>
On Thu, Nov 20 2003, Alan Stern wrote:
> On Thu, 20 Nov 2003, Jens Axboe wrote:
>
> > Well yes, that's what my objection is against - adding that member. Did
> > you not read any of my mails? And it's quite simple why - basically
> > noone will add it, so it'll end up being 512 anyways.
>
> All right, fine. Host adapter drivers have the option of setting the
> dma_alignment mask in their slave_configure() routines. Doing it there
> won't add anything to the host template, will leave the value at its
> default 512 for host drivers that don't care, and will let drivers that do
> care set it to the optimal value.
>
> The important thing is that sg and st should check the alignment of the
> actual buffer against the dma_alignment mask, which they currently don't
> do.
Sure fine. I still don't think it's worth anybodies time messing with.
> > I just don't see the point. It's a miniscule optimization. If you need
> > that last bit of performance, then align your buffers and noone loses.
> > See?
>
> I'm not sure -- was that "you" directed at me personally or at userspace
> program writers in general? Telling me to align the user buffers won't
> help anything; it's the program writers who need to be informed of the
> restrictions. And it's the host-driver writers who need to loosen those
> restrictions where applicable.
You as in program writers, clearly you cannot do anything about it. Of
course sg/st/whatever cannot pass down badly aligned sg addresses,
that's a given. And I think they are currently broken that they don't
attempt to align to 512 bytes. I just think we've waisted way more time
discussion the issue than what will ever be saved in cpu time.
--
Jens Axboe
-------------------------------------------------------
This SF.net email is sponsored by: SF.net Giveback Program.
Does SourceForge.net help you be more productive? Does it
help you create better code? SHARE THE LOVE, and help us help
YOU! Click Here: http://sourceforge.net/donate/
_______________________________________________
linux-usb-devel@lists.sourceforge.net
To unsubscribe, use the last form field at:
https://lists.sourceforge.net/lists/listinfo/linux-usb-devel
next prev parent reply other threads:[~2003-11-20 16:24 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1068207145.3fab8c2988d43@webmail.netregistry.net>
2003-11-07 16:21 ` usb-storage and Sony Handycam Alan Stern
2003-11-07 17:29 ` Patrick Mansfield
2003-11-07 19:49 ` Alan Stern
2003-11-08 2:54 ` Dmitri Katchalov
2003-11-08 6:34 ` Patrick Mansfield
2003-11-08 13:29 ` Dmitri Katchalov
2003-11-08 16:28 ` Alan Stern
2003-11-08 20:37 ` Patrick Mansfield
2003-11-09 3:47 ` [linux-usb-devel] " Alan Stern
2003-11-09 8:45 ` Dmitri Katchalov
2003-11-10 20:45 ` Patrick Mansfield
2003-11-10 17:59 ` Patrick Mansfield
2003-11-10 18:46 ` Alan Stern
2003-11-10 19:04 ` [linux-usb-devel] " Patrick Mansfield
2003-11-10 19:57 ` Alan Stern
2003-11-10 22:46 ` Sancho Dauskardt
2003-11-18 15:20 ` Unaligned scatter-gather buffers and usb-storage Alan Stern
2003-11-18 22:37 ` Patrick Mansfield
2003-11-19 8:47 ` Jens Axboe
2003-11-19 13:01 ` [linux-usb-devel] " Oliver Neukum
2003-11-19 13:04 ` Jens Axboe
2003-11-19 14:37 ` James Bottomley
2003-11-19 14:39 ` Jens Axboe
2003-11-19 14:58 ` James Bottomley
2003-11-19 15:00 ` [linux-usb-devel] " Jens Axboe
2003-11-19 16:56 ` Kai Makisara
2003-11-19 20:19 ` Jens Axboe
2003-11-19 22:06 ` Kai Makisara
2003-11-20 6:53 ` Jens Axboe
2003-11-20 15:20 ` Alan Stern
2003-11-20 15:30 ` Jens Axboe
2003-11-20 16:09 ` Alan Stern
2003-11-20 16:24 ` Jens Axboe [this message]
2003-11-20 16:28 ` Oliver Neukum
2003-11-20 19:23 ` Kai Makisara
2003-11-20 17:18 ` Kai Makisara
2003-11-20 19:18 ` [linux-usb-devel] " Kai Mäkisara
2003-11-21 18:03 ` PATCH: (as141) " Alan Stern
2003-11-21 20:07 ` Kai Makisara
2003-12-01 1:30 ` Matthew Dharm
2004-01-05 0:41 ` Matthew Dharm
2004-01-05 10:08 ` Jens Axboe
2004-01-05 21:58 ` PATCH: (as141b) " Alan Stern
2004-01-06 11:28 ` Oliver Neukum
2004-01-06 16:10 ` Alan Stern
2004-02-02 15:51 ` James Bottomley
2004-02-03 15:47 ` Alan Stern
2004-02-03 15:55 ` James Bottomley
2004-02-03 16:02 ` Matthew Wilcox
2003-11-19 15:44 ` Alan Stern
2003-11-19 15:49 ` Jens Axboe
2003-11-19 16:58 ` Alan Stern
2003-11-19 17:03 ` Jens Axboe
2003-11-07 22:09 ` usb-storage and Sony Handycam Alan Stern
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=20031120162457.GC1106@suse.de \
--to=axboe@suse.de \
--cc=James.Bottomley@steeleye.com \
--cc=Kai.Makisara@kolumbus.fi \
--cc=dougg@torque.net \
--cc=linux-scsi@vger.kernel.org \
--cc=linux-usb-devel@lists.sourceforge.net \
--cc=oliver@neukum.org \
--cc=patmans@us.ibm.com \
--cc=stern@rowland.harvard.edu \
/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).