From: "Jakob Østergaard" <jakob@unthought.net>
To: Pavel Machek <pavel@suse.cz>
Cc: David Ford <david@blue-labs.org>, linux-kernel@vger.kernel.org
Subject: Re: "VM watchdog"? [was Re: VM nuisance]
Date: Fri, 17 Aug 2001 00:24:20 +0200 [thread overview]
Message-ID: <20010817002420.C30521@unthought.net> (raw)
In-Reply-To: <3B748AA8.4010105@blue-labs.org> <20010814140011.B38@toy.ucw.cz>
In-Reply-To: <20010814140011.B38@toy.ucw.cz>; from pavel@suse.cz on Tue, Aug 14, 2001 at 02:00:11PM +0000
On Tue, Aug 14, 2001 at 02:00:11PM +0000, Pavel Machek wrote:
> Hi!
>
...
> > Again, it doesn't matter if I have swap or not, if I get within ~6 megs
> > of the end of memory, the kernel goes FMM. I've tested with and without
> > swap. And _please_ don't tell me "just add more swap". That's
> > ludicruous and isn't solving the problem, it's covering up a symptom.
>
> Maybe creating userland program that
> *) allocates few megs
> *) while 1 sleep 1m, gettimeofday. If more tha two minutes elapsed,
> tell OOM handler to kick in.
On my compute-server in the basement this is completely unacceptable because it
*may* just be working hard on something big. The excessive swapping may just
be 10-30 minutes where some app is using way more memory than the box has RAM,
in this case it's no problem at all, and all your suggestion would give me is
randomly dying compute jobs.
On my desktop this is unacceptable as well. You want the system to be frozen
for more than two minutes before doing anything about it ?
The problem with using such vague heuristics against fixed (arbitrary) limits
is that the effect will almost always be completely unacceptable. Either your
arbitrary limit is way too high, or way too low.
I can't tell you how to do it - but I think your suggestion is an excellent way
to *not* do it :)
>
> Or maybe kernel could have some "VM watchdog", which would trigger OOM if
> it is not polled once a minute...
Didn't everyone pretty much agree that if we could turn off overcommit
completely and reliably, that would be the preferred solution ? Simply sig11
the app that's unlucky enough to want more memory than there's in the system
(or, horror, have malloc() fail)
Now, I don't remember the entire thread, but IIRC it was difficult to kill
overcommit completely.
--
................................................................
: jakob@unthought.net : And I see the elder races, :
:.........................: putrid forms of man :
: Jakob Østergaard : See him rise and claim the earth, :
: OZ9ABN : his downfall is at hand. :
:.........................:............{Konkhra}...............:
next prev parent reply other threads:[~2001-08-16 22:24 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2001-08-11 1:30 VM nuisance David Ford
2001-08-11 2:48 ` Rik van Riel
2001-08-11 2:59 ` H. Peter Anvin
2001-08-11 4:17 ` Rik van Riel
2001-08-11 4:40 ` David Ford
2001-08-11 4:46 ` Rik van Riel
2001-08-11 4:41 ` safemode
2001-08-11 5:00 ` H. Peter Anvin
2001-08-11 13:13 ` Alan Cox
2001-08-11 15:39 ` David Ford
2001-08-11 3:50 ` safemode
2001-08-12 13:09 ` Maciej Zenczykowski
2001-08-12 13:45 ` Rik van Riel
2001-08-16 23:29 ` Justin A
2001-08-17 0:06 ` Dr. Kelsey Hudson
2001-08-17 0:24 ` Justin A
2001-08-17 2:54 ` Dr. Kelsey Hudson
2001-08-12 23:05 ` Dan Mann
[not found] ` <9l5v9a$ha9$1@ns1.clouddancer.com>
2001-08-13 0:01 ` Colonel
2001-08-13 14:32 ` dean gaudet
2001-08-13 19:47 ` Brian
2001-08-14 8:27 ` Helge Hafting
2001-08-17 13:34 ` Szabolcs Szakacsits
2001-08-17 17:29 ` Rik van Riel
2001-08-14 14:00 ` "VM watchdog"? [was Re: VM nuisance] Pavel Machek
2001-08-16 22:24 ` Jakob Østergaard [this message]
2001-08-17 1:26 ` David Ford
2001-08-17 1:41 ` Jakob Østergaard
[not found] ` <9li6sf$h5$1@ns1.clouddancer.com>
2001-08-17 9:04 ` Colonel
2001-08-17 20:38 ` David Ford
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=20010817002420.C30521@unthought.net \
--to=jakob@unthought.net \
--cc=david@blue-labs.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pavel@suse.cz \
/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