All of lore.kernel.org
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: dwalker@mvista.com
Cc: linux-kernel@vger.kernel.org, "Perez-Gonzalez,
	Inaky" <inaky.perez-gonzalez@intel.com>,
	Oleg Nesterov <oleg@tv-sign.ru>, Ingo Molnar <mingo@elte.hu>
Subject: Re: [PATCH] Priority Lists for the RT mutex
Date: Mon, 09 May 2005 15:21:46 -0400	[thread overview]
Message-ID: <1115666506.15027.3.camel@localhost.localdomain> (raw)
In-Reply-To: <1115662430.16016.4.camel@dhcp153.mvista.com>

On Mon, 2005-05-09 at 11:13 -0700, Daniel Walker wrote:
> On Mon, 2005-05-09 at 02:11, Ingo Molnar wrote:
> 
> > What would be nice to achieve are [low-cost] reductions of the size of 
> > struct rt_mutex (in include/linux/rt_lock.h), upon which all other 
> > PI-aware locking objects are based. Right now it's 9 words, of which 
> > struct plist is 5 words. Would be nice to trim this to 8 words - which 
> > would give a nice round size of 32 bytes on 32-bit.
> 
> Why not make rt_mutex->wait_lock a pointer ? Set it to NULL and handle
> it in rt.c .

That may make the rt_mutex structure smaller but this increases the size
of the kernel by the size of that pointer (times every rt_mutex in the
kernel!). You still need to allocate the size of the raw spin lock,
although now you just point to it. Is rounding worth that much overhead?

-- Steve


  reply	other threads:[~2005-05-09 19:22 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-05-06 18:13 [PATCH] Priority Lists for the RT mutex Perez-Gonzalez, Inaky
2005-05-07  7:25 ` Oleg Nesterov
2005-05-09  7:30   ` Ingo Molnar
2005-05-09  8:08     ` Oleg Nesterov
2005-05-09  9:11       ` Ingo Molnar
2005-05-09 14:32         ` Oleg Nesterov
2005-05-09 18:13         ` Daniel Walker
2005-05-09 19:21           ` Steven Rostedt [this message]
2005-05-09 21:29             ` Daniel Walker
2005-05-09 22:15               ` Daniel Walker
2005-05-09 14:07   ` Daniel Walker
  -- strict thread matches above, loose matches on Subject: below --
2005-05-06  9:05 Oleg Nesterov
2005-05-06 11:13 ` Oleg Nesterov
2005-05-06 18:56   ` Daniel Walker
2005-04-12  0:36 Perez-Gonzalez, Inaky
2005-04-11 23:28 Perez-Gonzalez, Inaky
2005-04-12  0:27 ` Bill Huey
2005-04-11 22:31 Perez-Gonzalez, Inaky
2005-04-11 23:11 ` Bill Huey
2005-04-11  9:03 Perez-Gonzalez, Inaky
2005-04-11  8:49 Perez-Gonzalez, Inaky
2005-04-11  8:57 ` Ingo Molnar
2005-04-11 22:17   ` Bill Huey
2005-04-12 20:35   ` Esben Nielsen
2005-04-11  8:27 Perez-Gonzalez, Inaky
2005-04-11  8:42 ` Ingo Molnar
2005-04-08 23:05 Perez-Gonzalez, Inaky
2005-04-08 21:25 Perez-Gonzalez, Inaky
2005-04-08 22:53 ` Daniel Walker
2005-04-07 17:52 Daniel Walker
2005-04-08  6:28 ` Ingo Molnar
2005-04-08  8:05   ` Sven-Thorsten Dietrich
2005-04-10 11:09     ` Ingo Molnar
2005-04-12 17:56       ` Daniel Walker
2005-04-08 17:11   ` Daniel Walker
2005-04-10 10:53 ` Ingo Molnar
2005-04-11 16:19   ` Daniel Walker
2005-04-12 18:37 ` Paul E. McKenney

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=1115666506.15027.3.camel@localhost.localdomain \
    --to=rostedt@goodmis.org \
    --cc=dwalker@mvista.com \
    --cc=inaky.perez-gonzalez@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=oleg@tv-sign.ru \
    /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.