All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@suse.de>
To: Andrew Morton <akpm@osdl.org>
Cc: Dave Jones <davej@codemonkey.org.uk>,
	mroos@linux.ee, linux-kernel@vger.kernel.org
Subject: Re: 2.5 'what to expect'
Date: Sun, 13 Jul 2003 02:08:32 +0200	[thread overview]
Message-ID: <20030713000832.GT843@suse.de> (raw)
In-Reply-To: <20030712151511.107c1f59.akpm@osdl.org>

On Sat, Jul 12 2003, Andrew Morton wrote:
> Dave Jones <davej@codemonkey.org.uk> wrote:
> >
> > ..
> > 
> > Something seems amiss. The deprecated elvtune interface is the old -r/-w/-b command line.
> > I was lead to believe a new elvtune appeared which supports an option
> > for changing the elevator under 2.5, however a quick google doesn't turn
> > up any such patched elvtune, so I'm somewhat puzzled.
> 
> No, we planned to do the selection via sysfs rather than ioctl.

Right

> >  > Maybe just suggest the sysfs interface at once and not mention
> >  > elvtune?
> > 
> > Changing the elevator type per device via sysfs does seem to make
> > sense, however /sys/block/<devicename>/queue/iosched/ doesn't yield
> > anything that would suggest this is possible (yet).  I think Jens
> > has patches for this?
> 
> But it never happened.  There are all sorts of nasties wrt actually

Well the code exists.

> making the switch.  Some related to request queueing, some to sysfs
> itself.

I don't recall any request queueing problems, it's pretty straight
forward to lock the queue down and prevent any new requests from
entering. sysfs problems is the only issue, and before Al does his magic
on that stuff, the patch just doesn't make sense. So it hasn't been
posted publically. With the sysfs disabled, I can switch io schedulers
on the fly quite easily.

> So yes, we should have runtime selection, and maybe sometime we will,
> but the lowness of the return-to-effort ratio means it won't happen
> soon.

Depends. If the sysfs stuff doesn't get fixed, then no it wont happen.

-- 
Jens Axboe


  reply	other threads:[~2003-07-12 23:53 UTC|newest]

Thread overview: 95+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-07-11 14:02 2.5 'what to expect' Dave Jones
2003-07-11 14:26 ` Alan Cox
2003-07-11 14:46   ` Tomas Szepe
2003-07-11 15:00     ` Alan Cox
2003-07-11 15:11       ` Larry McVoy
2003-07-11 15:37         ` Steven Cole
2003-07-11 17:19           ` Alan Cox
2003-07-11 17:51           ` Brian Gerst
2003-07-12 10:34             ` Dave Jones
2003-07-11 14:55   ` Bartlomiej Zolnierkiewicz
2003-07-11 15:58     ` Jeff Garzik
2003-07-11 16:23       ` Bartlomiej Zolnierkiewicz
2003-07-11 17:02         ` Jeff Garzik
2003-07-11 17:09       ` Christoph Hellwig
2003-07-11 20:43     ` Andries Brouwer
2003-07-11 15:05   ` Paul Mundt
2003-07-11 15:56   ` Jeff Garzik
2003-07-11 20:38     ` Andries Brouwer
2003-07-12 15:38       ` Jamie Lokier
     [not found]       ` <20030715000331.GB904@matchmail.com>
2003-07-15 17:08         ` Andries Brouwer
2003-07-15 19:42           ` Mike Fedyk
2003-07-15 20:03             ` Andries Brouwer
2003-07-15 21:14           ` Kevin Corry
2003-07-16  4:16           ` Peter Chubb
2003-07-16 17:07             ` Mike Fedyk
2003-07-16 17:53               ` Martin Hermanowski
2003-07-11 17:33   ` Robert Love
2003-07-12  0:38     ` Barry K. Nathan
2003-07-12  1:03       ` Jeff Garzik
2003-07-14 17:18       ` Robert Love
2003-07-11 20:07   ` Andries Brouwer
2003-07-11 20:53   ` Brian Gerst
2003-07-11 21:19     ` Shawn
2003-07-11 22:00       ` Alan Cox
2003-07-12  2:31   ` Wichert Akkerman
2003-07-11 14:37 ` Oleg Drokin
2003-07-11 14:50 ` Paul Dickson
2003-07-11 15:02 ` Paul Nasrat
2003-07-14  9:07   ` Vojtech Pavlik
2003-07-11 15:43 ` James Morris
2003-07-11 17:10   ` Christoph Hellwig
2003-07-12 17:38     ` James Morris
2003-07-11 15:59 ` Flameeyes
2003-07-11 16:04   ` Jeff Garzik
2003-07-11 17:23     ` Flameeyes
2003-07-11 16:01 ` Wiktor Wodecki
2003-07-11 16:03 ` Matthew Dharm
2003-07-11 16:23 ` Tom Rini
2003-07-11 18:14 ` Mike Fedyk
2003-07-11 19:33   ` Jeff Garzik
2003-07-11 22:01     ` Alan Cox
2003-07-11 19:22 ` Davide Libenzi
2003-07-11 19:37 ` Andrew Theurer
2003-07-11 19:54   ` Jeff Garzik
2003-07-11 20:06     ` Andrew Theurer
2003-07-11 19:59   ` Mike Fedyk
2003-07-11 20:30     ` Andrew Theurer
2003-07-11 21:16 ` James H. Cloos Jr.
2003-07-11 22:24 ` Greg KH
2003-07-12 13:10 ` Meelis Roos
2003-07-12 20:23   ` Dave Jones
2003-07-12 22:15     ` Andrew Morton
2003-07-13  0:08       ` Jens Axboe [this message]
2003-07-12 15:24 ` Jamie Lokier
2003-07-12 15:58   ` Jeff Garzik
2003-07-12 18:27     ` Andrew Morton
2003-07-12 18:39       ` Jamie Lokier
2003-07-12 19:03         ` Jeff Garzik
2003-07-12 19:34           ` Jamie Lokier
2003-07-12 19:38             ` Jeff Garzik
2003-07-12 19:46               ` Jamie Lokier
2003-07-13 15:51                 ` Andreas Dilger
2003-07-13 15:55                   ` Jeff Garzik
2003-07-14  0:03                   ` Rob van Nieuwkerk
2003-07-14  8:01                     ` Alan Cox
2003-07-13 12:48 ` Pavel Machek
2003-07-14  6:51 ` Maneesh Soni
2003-07-14 11:39   ` Dave Jones
2003-07-14  8:30 ` Romano Giannetti
2003-07-14 11:41   ` Dave Jones
2003-07-14 11:52     ` Bernhard Rosenkraenzer
2003-07-14 12:13     ` Arjan van de Ven
2003-07-14 12:19       ` Paul Nasrat
2003-07-14 12:37       ` Philip Wyett
2003-07-14 14:05         ` Arjan van de Ven
2003-07-14 19:34           ` Paul Nasrat
2003-07-17 20:54 ` Jeff Garzik
2003-07-17 21:16   ` Mike Fedyk
2003-07-17 21:23     ` Jeff Garzik
2003-07-18  8:10       ` Christoph Hellwig
2003-07-18 18:48         ` Krzysztof Halasa
2003-07-11 17:51 Mikael Pettersson
     [not found] <fa.eq8e50t.1hkoiqh@ifi.uio.no>
2003-07-12 13:25 ` Terje Kvernes
2003-07-16 22:43 Matt_Domsch
2003-07-16 23:05 ` Kevin P. Fleming

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=20030713000832.GT843@suse.de \
    --to=axboe@suse.de \
    --cc=akpm@osdl.org \
    --cc=davej@codemonkey.org.uk \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mroos@linux.ee \
    /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.