From: Daniel Mack <daniel@zonque.org>
To: Andy Lutomirski <luto@amacapital.net>
Cc: David Herrmann <dh.herrmann@gmail.com>,
Tom Gundersen <teg@jklm.no>,
"Kalle A. Sandstrom" <ksandstr@iki.fi>,
Greg KH <gregkh@linuxfoundation.org>,
Borislav Petkov <bp@alien8.de>,
One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk>,
Havoc Pennington <havoc.pennington@gmail.com>,
Djalal Harouni <tixxdz@opendz.org>, cee1 <fykcee1@gmail.com>,
"Eric W. Biederman" <ebiederm@xmission.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: kdbus: to merge or not to merge?
Date: Fri, 7 Aug 2015 16:40:26 +0200 [thread overview]
Message-ID: <55C4C35A.4070306@zonque.org> (raw)
In-Reply-To: <CALCETrVr04ZdXHLZXLp_Y+m68Db5Mmh_Wnu6prNCfCqgWm0QzA@mail.gmail.com>
On 08/06/2015 08:43 PM, Andy Lutomirski wrote:
> Nonetheless, it looks like the slice logic (aside: it looks *way* more
> complicated than necessary -- what's wrong with circular buffers)
> will, under most (but not all!) workloads, concentrate access to a
> smallish fraction of the pool. This is IMO bad, since it means that
> most of the time most of the pool will remain uncommitted. If, at
> some point, something causes the access pattern to change and hit all
> the pages (even just once), suddenly all of the pools get committed,
> and your memory usage blows up.
That's a general problem with memory overcommitment, and not specific to
kdbus. IOW: You'd have the same problem with a similar logic implemented
in userspace, right?
Daniel
next prev parent reply other threads:[~2015-08-07 14:40 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-06-23 6:06 kdbus: to merge or not to merge? Andy Lutomirski
2015-06-23 6:31 ` Andy Lutomirski
2015-06-23 6:41 ` Greg KH
2015-06-23 7:22 ` Richard Weinberger
2015-06-23 9:25 ` Martin Steigerwald
2015-06-23 9:38 ` Martin Steigerwald
2015-06-23 15:07 ` Andy Lutomirski
2015-06-25 2:14 ` Steven Rostedt
2015-06-25 2:20 ` Linus Torvalds
2015-06-25 6:01 ` Martin Steigerwald
2015-06-25 6:05 ` Martin Steigerwald
2015-06-25 13:34 ` Theodore Ts'o
2015-06-25 14:03 ` Martin Steigerwald
2015-06-23 9:12 ` Borislav Petkov
2015-07-08 13:54 ` Pavel Machek
2015-07-09 8:39 ` Geert Uytterhoeven
2015-07-09 10:29 ` Joe Perches
2015-07-09 10:57 ` Geert Uytterhoeven
2015-07-09 11:36 ` Pavel Machek
2015-06-23 23:19 ` Linus Torvalds
2015-06-24 0:52 ` Andy Lutomirski
2015-06-24 8:05 ` Ingo Molnar
2015-06-24 10:41 ` Eric W. Biederman
2015-06-24 10:46 ` Martin Steigerwald
2015-06-24 13:18 ` Ingo Molnar
2015-06-24 17:39 ` David Lang
2015-06-24 18:41 ` Eric W. Biederman
2015-06-24 18:50 ` Martin Steigerwald
2015-06-24 19:12 ` David Lang
2015-06-25 7:57 ` Geert Uytterhoeven
2015-06-25 15:26 ` Steven Rostedt
2015-06-25 6:31 ` Greg KH
2015-06-25 6:48 ` David Lang
2015-06-25 7:47 ` Ingo Molnar
2015-06-25 7:51 ` Ingo Molnar
2015-06-24 11:43 ` Martin Steigerwald
2015-06-24 13:27 ` Ingo Molnar
2015-06-24 9:55 ` Alexander Larsson
2015-06-24 14:38 ` Andy Lutomirski
[not found] ` <CAHr-LrYWNwv6_YLoP-B3duQ1QsjPiTiaEnjBQ7j2brPMeTgA3A@mail.gmail.com>
[not found] ` <CALCETrW3F6YP_H1oRJa47f1DT7B35OubhJYSnq0U-_GmFQHNOA@mail.gmail.com>
2015-06-24 17:11 ` Alexander Larsson
2015-06-24 19:43 ` Andy Lutomirski
2015-06-24 20:45 ` Alexander Larsson
2015-08-03 23:02 ` Andy Lutomirski
2015-08-04 8:58 ` David Herrmann
2015-08-04 13:46 ` Linus Torvalds
2015-08-04 14:09 ` David Herrmann
2015-08-04 14:47 ` Andy Lutomirski
2015-08-05 0:18 ` Andy Lutomirski
2015-08-06 7:06 ` Daniel Mack
2015-08-06 15:27 ` Andy Lutomirski
2015-08-06 17:24 ` Daniel Mack
2015-08-05 7:10 ` David Herrmann
2015-08-05 20:11 ` Andy Lutomirski
2015-08-06 8:04 ` David Herrmann
2015-08-06 8:25 ` Martin Steigerwald
2015-08-06 15:21 ` Andy Lutomirski
2015-08-06 18:14 ` Daniel Mack
2015-08-06 18:43 ` Andy Lutomirski
2015-08-07 14:40 ` Daniel Mack [this message]
2015-08-07 15:09 ` Andy Lutomirski
[not found] ` <CA+55aFxDLt-5+=xXeYG4nJKMb8L_iD9FmwTZ2VuughBku-mW3g@mail.gmail.com>
2015-08-09 19:00 ` Greg Kroah-Hartman
2015-08-09 22:11 ` Daniel Mack
2015-08-09 22:11 ` Daniel Mack
2015-08-10 2:10 ` Andy Lutomirski
2015-08-10 2:10 ` Andy Lutomirski
2015-08-10 17:04 ` Linus Torvalds
2015-08-10 17:04 ` Linus Torvalds
2015-08-10 2:48 ` David Lang
2015-08-07 15:37 ` cee1
-- strict thread matches above, loose matches on Subject: below --
2015-07-01 0:03 Kalle A. Sandstrom
2015-07-01 16:51 ` David Herrmann
2015-07-06 21:18 ` Kalle A. Sandstrom
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=55C4C35A.4070306@zonque.org \
--to=daniel@zonque.org \
--cc=bp@alien8.de \
--cc=dh.herrmann@gmail.com \
--cc=ebiederm@xmission.com \
--cc=fykcee1@gmail.com \
--cc=gnomes@lxorguk.ukuu.org.uk \
--cc=gregkh@linuxfoundation.org \
--cc=havoc.pennington@gmail.com \
--cc=ksandstr@iki.fi \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=teg@jklm.no \
--cc=tixxdz@opendz.org \
--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.