From: Arnd Bergmann <arnd@arndb.de>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nick Piggin <npiggin@suse.de>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [rfc] "fair" rw spinlocks
Date: Tue, 1 Dec 2009 18:03:24 +0100 [thread overview]
Message-ID: <200912011803.24664.arnd@arndb.de> (raw)
In-Reply-To: <alpine.LFD.2.00.0911300914240.2872@localhost.localdomain>
On Monday 30 November 2009, Linus Torvalds wrote:
> The best option really would be to try to make it all use RCU, rather than
> paper over things. That really should improve performance.
Are there any writers at interrupt time? If not, another option might be
to first convert all the readers that can happen from interrupts to RCU,
which lets us get rid of the irq disable in the write path.
Step two could either be the conversion of all nested readers to RCU,
or your tasklist_read_lock(), which should then be safe. Doing both of
these lets us turn tasklist_lock into a plain spinlock, possibly followed
by converting remaining readers that show measurable lock contention.
Arnd <><
next prev parent reply other threads:[~2009-12-01 17:04 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-11-23 14:54 [rfc] "fair" rw spinlocks Nick Piggin
2009-11-24 20:19 ` David Miller
2009-11-25 6:52 ` Nick Piggin
2009-11-25 8:49 ` Andi Kleen
2009-11-25 8:56 ` Nick Piggin
2009-11-24 20:47 ` Andi Kleen
2009-11-25 6:54 ` Nick Piggin
2009-11-25 8:48 ` Andi Kleen
2009-11-25 13:09 ` Arnd Bergmann
2009-11-28 2:07 ` Paul E. McKenney
2009-11-28 11:15 ` Andi Kleen
2009-11-28 15:20 ` Paul E. McKenney
2009-11-28 17:30 ` Linus Torvalds
2009-11-29 18:51 ` Paul E. McKenney
2009-11-30 7:57 ` Nick Piggin
2009-11-30 7:55 ` Nick Piggin
2009-11-30 15:22 ` Linus Torvalds
2009-11-30 15:40 ` Nick Piggin
2009-11-30 16:07 ` Linus Torvalds
2009-11-30 16:17 ` Nick Piggin
2009-11-30 16:39 ` Paul E. McKenney
2009-11-30 17:05 ` Linus Torvalds
2009-11-30 17:13 ` Nick Piggin
2009-11-30 17:18 ` Linus Torvalds
2009-12-01 17:03 ` Arnd Bergmann [this message]
2009-12-01 17:15 ` Linus Torvalds
2009-11-30 18:29 ` Paul E. McKenney
2009-11-30 16:20 ` Paul E. McKenney
2009-11-30 10:00 ` Christoph Hellwig
2009-11-30 15:52 ` Linus Torvalds
2009-11-30 17:46 ` Ingo Molnar
2009-11-30 21:12 ` Thomas Gleixner
2009-11-30 21:27 ` Peter Zijlstra
2009-11-30 22:02 ` Thomas Gleixner
2009-11-30 22:11 ` Linus Torvalds
2009-11-30 22:37 ` Thomas Gleixner
2009-11-30 22:49 ` Linus Torvalds
2009-12-01 17:37 ` [PATCH] audit: Call tty_audit_push_task() outside preempt disabled region Thomas Gleixner
2009-12-01 18:22 ` Oleg Nesterov
2009-12-01 19:53 ` Thomas Gleixner
2009-12-06 3:12 ` [rfc] "fair" rw spinlocks Eric W. Biederman
2009-12-07 18:18 ` Paul E. McKenney
2009-12-07 22:24 ` Eric W. Biederman
2009-12-07 22:35 ` Andi Kleen
2009-12-07 23:19 ` Eric W. Biederman
2009-12-08 1:39 ` Paul E. McKenney
2009-12-08 2:11 ` Eric W. Biederman
2009-12-08 2:37 ` Paul E. McKenney
2009-12-07 18:32 ` Oleg Nesterov
2009-12-07 20:38 ` Peter Zijlstra
2009-12-09 15:55 ` Oleg Nesterov
2009-12-07 22:10 ` Eric W. Biederman
2009-12-09 15:37 ` Oleg Nesterov
2009-12-10 3:36 ` Eric W. Biederman
2009-12-10 6:22 ` Paul E. McKenney
2009-12-10 10:31 ` Eric W. Biederman
2009-12-10 16:41 ` Paul E. McKenney
2009-12-01 19:01 ` Mathieu Desnoyers
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=200912011803.24664.arnd@arndb.de \
--to=arnd@arndb.de \
--cc=linux-kernel@vger.kernel.org \
--cc=npiggin@suse.de \
--cc=paulmck@linux.vnet.ibm.com \
--cc=torvalds@linux-foundation.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 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.