From: Dipankar Sarma <dipankar@in.ibm.com>
To: torvalds@transmeta.com
Cc: linux-kernel@vger.kernel.org
Subject: Re: [Lse-tech] Re: RFC: patch to allow lock-free traversal of lists with insertion
Date: Wed, 10 Oct 2001 12:24:00 +0530 [thread overview]
Message-ID: <20011010122400.A17006@in.ibm.com> (raw)
In article <Pine.LNX.4.33.0110092236210.1305-100000@penguin.transmeta.com> Linus Torvalds wrote:
> Now, in all fairness I can imagine hacky lock-less removals too. To get
> them to work, you have to (a) change the "next" pointer to point to the
> next->next (and have some serialization between removals, but removals
> only, to make sure you don't have next->next also going away from you) and
> (b) leave the old "next" pointer (and thus the data structure) around
> until you can _prove_ that nobody is looking anything up any more, and
> that the now-defunct data structure can truly be removed.
This is exactly what Read-Copy Update does. You keep the old data
structure around until you are sure that all the CPUs have lost
references to it by context switching. There are more than
one relatively non-intrusive ways of detecting completion of such a cycle
and "deleted" data can be freed afterwards.
The details are in http://lse.sourceforge.net/locking/rcupdate.html.
Thanks
Dipankar
--
Dipankar Sarma <dipankar@in.ibm.com> Project: http://lse.sourceforge.net
Linux Technology Center, IBM Software Lab, Bangalore, India.
next reply other threads:[~2001-10-10 6:50 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2001-10-10 6:54 Dipankar Sarma [this message]
-- strict thread matches above, loose matches on Subject: below --
2001-10-13 14:42 [Lse-tech] Re: RFC: patch to allow lock-free traversal of lists with insertion Paul McKenney
2001-10-13 17:23 ` Linus Torvalds
2001-10-13 17:28 ` Linus Torvalds
2001-10-14 7:25 ` Dipankar Sarma
2001-10-13 18:42 ` Andi Kleen
2001-10-13 19:15 ` Alexander Viro
2001-10-13 20:44 ` Rusty Russell
2001-10-13 21:19 ` Rusty Russell
2001-10-11 10:34 Dipankar Sarma
2001-10-10 21:44 Paul McKenney
2001-10-10 16:00 Paul McKenney
2001-10-10 15:24 Paul McKenney
2001-10-10 16:58 ` Andrea Arcangeli
2001-10-10 17:25 ` Linus Torvalds
2001-10-12 5:06 ` Rusty Russell
2001-10-12 16:28 ` Linus Torvalds
2001-10-12 19:50 ` Al Dunsmuir
2001-10-13 1:07 ` Paul Mackerras
2001-10-13 1:54 ` Davide Libenzi
2001-10-13 2:04 ` Linus Torvalds
2001-10-13 2:31 ` Davide Libenzi
2001-10-13 2:46 ` Davide Libenzi
2001-10-13 3:30 ` Linus Torvalds
2001-10-13 2:49 ` Paul Mackerras
2001-10-13 2:00 ` Linus Torvalds
2001-10-13 7:38 ` Rusty Russell
2001-10-10 10:06 Dipankar Sarma
2001-10-10 10:18 ` Linus Torvalds
2001-10-10 11:43 ` Dipankar Sarma
2001-10-12 3:27 ` Rusty Russell
2001-10-12 16:56 ` Linus Torvalds
2001-10-12 18:53 ` Dipankar Sarma
2001-10-13 7:25 ` Rusty Russell
[not found] <20011010182730.0077454b.rusty@rustcorp.com.au>
2001-10-10 9:36 ` Linus Torvalds
2001-10-11 6:50 ` Rusty Russell
2001-10-10 7:58 Dipankar Sarma
2001-10-10 7:06 Dipankar Sarma
2001-10-10 7:21 ` BALBIR SINGH
2001-10-10 9:06 ` Dipankar Sarma
2001-10-10 4:43 Paul McKenney
2001-10-09 15:45 Paul McKenney
2001-10-10 2:05 ` [Lse-tech] " Andrea Arcangeli
2001-10-10 5:05 ` Linus Torvalds
2001-10-10 5:17 ` BALBIR SINGH
2001-10-10 5:29 ` Davide Libenzi
2001-10-10 5:46 ` Linus Torvalds
2001-10-10 6:01 ` BALBIR SINGH
2001-10-10 15:23 ` Victor Yodaiken
2001-10-10 6:16 ` Paul Mackerras
2001-10-10 6:30 ` Linus Torvalds
2001-10-10 7:36 ` Paul Mackerras
2001-10-10 15:54 ` Victor Yodaiken
2001-10-10 21:56 ` Keith Owens
2001-10-10 22:24 ` Victor Yodaiken
2001-10-10 23:46 ` David S. Miller
2001-10-11 0:24 ` Davide Libenzi
2001-10-10 11:54 ` Keith Owens
2001-10-10 13:24 ` Ivan Kokshaysky
2001-10-10 13:41 ` Andrea Arcangeli
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=20011010122400.A17006@in.ibm.com \
--to=dipankar@in.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=torvalds@transmeta.com \
/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