From: Ingo Molnar <mingo@elte.hu>
To: Linus Torvalds <torvalds@transmeta.com>
Cc: linux-kernel@vger.kernel.org, Alex Larsson <alexl@redhat.com>,
<procps-list@redhat.com>, Alexander Viro <viro@math.psu.edu>
Subject: Re: [patch] procfs/procps threading performance speedup, 2.5.62
Date: Thu, 20 Feb 2003 18:14:38 +0100 (CET) [thread overview]
Message-ID: <Pine.LNX.4.44.0302201810160.32017-100000@localhost.localdomain> (raw)
In-Reply-To: <Pine.LNX.4.44.0302200902260.2493-100000@home.transmeta.com>
On Thu, 20 Feb 2003, Linus Torvalds wrote:
> > the main problem with threads in /proc is that there's a big slowdown when
> > using lots of threads.
>
> Well, part of the problem (I think) is that you added all the threads to
> the same main directory.
>
> Putting a "." in front of the name doesn't fix the /proc level directory
> scalability issues, it only means that you can avoid some of the user-
> level scalability ones.
>
> So to offset that bad design, you then add other cruft, like the lookup
> cursor and the "." marker. Which is not a bad idea in itself, but I
> claim that if you'd made the directory structure saner you wouldn't have
> needed it in the first place.
with the dot-marker it's not scaling badly at all - you can see the
numbers in the mail, all of the command variants (even a simple 'ps')
still reads the _full_ /proc directory. (just they dont go further than
that, because the readdir() output is enough to filter stuff.)
> It would just be _so_ much nicer if the threads would show up as
> subdirectories ie /proc/<tgid>/<tid>/xxx. More scalable, more readable,
> and just generally more sane.
Al says that this cannot be done sanely, and is fraught with security
problems. I'd vote for it if it were possible. Al?
but, if you worry about the scalability of large /proc directories - it's
not bad at all.
Ingo
next prev parent reply other threads:[~2003-02-20 17:05 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-02-20 16:33 Ingo Molnar
2003-02-20 16:47 ` Miquel van Smoorenburg
2003-02-20 16:55 ` Daniel Jacobowitz
2003-02-20 17:00 ` Nikita Danilov
2003-02-20 17:06 ` Linus Torvalds
2003-02-20 17:14 ` Ingo Molnar [this message]
2003-02-20 17:22 ` Linus Torvalds
2003-02-21 7:38 ` Oliver Xymoron
2003-02-20 17:23 ` Ingo Molnar
2003-02-22 20:52 ` Albert Cahalan
2003-02-22 21:55 ` Andrew Morton
2003-02-22 23:04 ` Albert Cahalan
2003-02-23 18:49 ` Ingo Molnar
2003-02-23 21:51 ` Albert D. Cahalan
2003-02-24 9:28 ` Ingo Molnar
2003-02-24 11:12 ` Albert D. Cahalan
2003-02-24 11:26 ` Ingo Molnar
2003-02-24 12:29 ` Albert D. Cahalan
2003-02-24 12:41 ` Ingo Molnar
2003-02-24 12:45 ` Ingo Molnar
2003-02-24 12:52 ` Ingo Molnar
2003-02-24 9:38 ` Ingo Molnar
2003-02-24 12:13 ` Albert D. Cahalan
2003-02-20 17:28 ` Jeff Garzik
2003-02-20 17:30 ` Ingo Molnar
2003-02-20 17:48 ` Linus Torvalds
2003-02-20 17:20 ` Linus Torvalds
2003-02-20 19:13 ` Daniel Jacobowitz
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=Pine.LNX.4.44.0302201810160.32017-100000@localhost.localdomain \
--to=mingo@elte.hu \
--cc=alexl@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=procps-list@redhat.com \
--cc=torvalds@transmeta.com \
--cc=viro@math.psu.edu \
/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
all inboxes | Powered by JetHome®