From: Mark Lord <lkml@rtr.ca>
To: bzolnier@milosz.na.pl
Cc: Lee Revell <rlrevell@joe-job.com>, Greg Stark <gsstark@mit.edu>,
Denis Vlasenko <vda@port.imtp.ilyichevsk.odessa.ua>,
Alan Cox <alan@lxorguk.ukuu.org.uk>,
Todd Poynor <tpoynor@mvista.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
tim.bird@am.sony.com, dsingleton@mvista.com
Subject: Re: [PATCH] Configure IDE probe delays
Date: Wed, 01 Sep 2004 09:20:30 -0400 [thread overview]
Message-ID: <4135CC9E.5060905@rtr.ca> (raw)
In-Reply-To: <200408272059.51779.bzolnier@elka.pw.edu.pl>
Bartlomiej Zolnierkiewicz wrote:
>
>>What determines whether 48 bit addressing will be used then?
>
> Availability of 48-bit addressing feature set and host capabilities
> (some don't support LBA48 when DMA is used etc.).
I haven't examined the "released" IDE drivers in some time,
but one optimisation that can save a LOT of CPU usage
is for the driver to only use LBA48 *when necessary*,
and use LBA28 I/O otherwise.
Each access to an IDE register typically chews up 600+ns,
or the equivalent of a couple thousand instruction executions
on a modern core. Avoiding LBA48 when it's not needed will
save four such accesses per I/O, or about 2.5us.
LBA48 is only needed when (1) the sector count is greater than 256,
and/or (2) the ending sector number >= (1<<28).
I regularly include this optimisation in the drivers I have been
working on since LBA48 first appeared.
Cheers
--
Mark Lord
(hdparm keeper & the original "Linux IDE Guy")
next prev parent reply other threads:[~2004-09-01 13:24 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-07-30 19:11 [PATCH] Configure IDE probe delays Todd Poynor
2004-07-30 21:36 ` Lee Revell
2004-07-30 22:35 ` Alan Cox
2004-07-31 0:12 ` Lee Revell
[not found] ` <200407311434.59604.vda@port.imtp.ilyichevsk.odessa.ua>
2004-07-31 18:00 ` Lee Revell
2004-08-27 17:45 ` Greg Stark
2004-08-27 17:53 ` Lee Revell
2004-08-27 18:05 ` Bartlomiej Zolnierkiewicz
2004-08-27 18:08 ` Lee Revell
2004-08-27 18:59 ` Bartlomiej Zolnierkiewicz
2004-09-01 13:20 ` Mark Lord [this message]
2004-09-01 14:43 ` Jeff Garzik
2004-09-01 15:30 ` Mark Lord
2004-09-01 15:36 ` Mark Lord
2004-09-01 19:36 ` Lee Revell
2004-09-01 18:42 ` Alan Cox
2004-09-01 15:06 ` Alan Cox
2004-09-01 19:08 ` Lee Revell
2004-09-02 16:04 ` Mark Lord
2004-09-01 15:40 ` Bartlomiej Zolnierkiewicz
2004-07-31 18:06 ` Lee Revell
2004-07-31 19:35 ` Alan Cox
2004-07-31 21:35 ` Lee Revell
2004-07-31 21:44 ` Jeff Garzik
2004-07-31 22:12 ` Lee Revell
2004-08-04 17:30 ` Anthony de Boer
2004-08-05 21:39 ` Tim Bird
2004-07-31 0:54 ` Jeff Garzik
2004-08-03 17:47 ` Mark Lord
2004-08-06 15:48 ` Jeff Garzik
2004-08-06 19:29 ` Tim Bird
2004-08-06 20:46 ` Todd Poynor
2004-08-02 21:56 ` Tim Bird
2004-08-02 21:01 ` 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=4135CC9E.5060905@rtr.ca \
--to=lkml@rtr.ca \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=bzolnier@milosz.na.pl \
--cc=dsingleton@mvista.com \
--cc=gsstark@mit.edu \
--cc=linux-kernel@vger.kernel.org \
--cc=rlrevell@joe-job.com \
--cc=tim.bird@am.sony.com \
--cc=tpoynor@mvista.com \
--cc=vda@port.imtp.ilyichevsk.odessa.ua \
/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