From: geoff@plan9.bell-labs.com
To: 9fans@cse.psu.edu
Subject: Re: [9fans] plan 9 overcommits memory?
Date: Sun, 2 Sep 2007 23:38:44 -0400 [thread overview]
Message-ID: <01b719eaabe004a9073ccb4b3425e1d0@plan9.bell-labs.com> (raw)
If system calls were the only way to change memory allocation, one
could probably keep a strict accounting of pages allocated and fail
system calls that require more VM than is available. But neither Plan
9 nor Unix works that way. The big exception is stack growth. The
kernel automatically extends a process's stack segment as needed. On
the pc, Plan 9 currently limits user-mode stacks to 16MB. On a CPU
server with 200 processes (fairly typical), that's 3.2GB of VM one
would have to commit just for stacks. With 2,000 processes, that
would rise to 32GB just for stacks.
next reply other threads:[~2007-09-03 3:38 UTC|newest]
Thread overview: 74+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-09-03 3:38 geoff [this message]
2007-09-03 5:35 ` Scott Schwartz
2007-09-03 6:05 ` Uriel
2007-09-03 13:33 ` erik quanstrom
2007-09-03 17:09 ` john
2007-09-03 17:17 ` Gorka Guardiola
2007-09-03 17:25 ` Francisco J Ballesteros
2007-09-03 17:30 ` john
2007-09-03 19:47 ` Charles Forsyth
2007-09-03 19:46 ` Uriel
2007-09-03 19:54 ` Charles Forsyth
2007-09-03 19:54 ` Uriel
2007-09-03 20:34 ` geoff
2007-09-03 20:16 ` erik quanstrom
2007-09-03 17:32 ` erik quanstrom
2007-09-03 17:39 ` Francisco J Ballesteros
2007-09-03 17:43 ` john
2007-09-03 17:45 ` john
2007-09-03 19:52 ` Charles Forsyth
2007-09-05 8:33 ` sqweek
2007-09-04 8:48 ` Douglas A. Gwyn
2007-09-03 18:13 ` geoff
2007-09-03 20:17 ` erik quanstrom
2007-09-03 20:48 ` geoff
2007-09-03 22:01 ` erik quanstrom
2007-09-03 22:43 ` Charles Forsyth
2007-09-03 23:51 ` erik quanstrom
2007-09-04 0:04 ` Charles Forsyth
2007-09-04 14:44 ` erik quanstrom
2007-09-04 15:07 ` Charles Forsyth
2007-09-04 15:18 ` ron minnich
2007-09-04 15:18 ` Charles Forsyth
2007-09-05 8:48 ` Douglas A. Gwyn
2007-09-05 10:53 ` erik quanstrom
2007-09-06 8:42 ` Douglas A. Gwyn
2007-09-06 17:15 ` Joel C. Salomon
2007-09-06 19:38 ` ron minnich
2007-09-06 20:18 ` Charles Forsyth
2007-09-06 23:37 ` Steve Simon
2007-09-07 3:09 ` Roman Shaposhnik
2007-09-07 4:09 ` Bruce Ellis
2007-09-07 4:25 ` Lyndon Nerenberg
2007-09-07 4:37 ` Bruce Ellis
2007-09-07 4:43 ` Lyndon Nerenberg
2007-09-10 15:24 ` roger peppe
2007-09-07 10:55 ` erik quanstrom
2007-09-04 23:32 ` erik quanstrom
2007-09-03 21:16 ` Charles Forsyth
2007-09-03 21:19 ` ron minnich
2007-09-03 21:41 ` Eric Van Hensbergen
2007-09-03 21:51 ` erik quanstrom
2007-09-03 13:21 ` erik quanstrom
2007-09-03 14:01 ` Sape Mullender
2007-09-03 14:32 ` erik quanstrom
2007-09-03 15:28 ` Sape Mullender
2007-09-04 4:32 ` lucio
2007-09-04 7:23 ` Dave Eckhardt
2007-09-04 8:48 ` Douglas A. Gwyn
-- strict thread matches above, loose matches on Subject: below --
2007-08-31 11:41 erik quanstrom
2007-09-02 21:27 ` Russ Cox
2007-09-03 0:43 ` erik quanstrom
2007-09-04 8:47 ` Douglas A. Gwyn
2007-09-04 13:39 ` David Leimbach
2007-09-04 14:41 ` erik quanstrom
2007-09-04 15:54 ` David Leimbach
2007-09-04 17:37 ` sqweek
2007-09-04 18:10 ` ron minnich
2007-09-04 18:53 ` sqweek
2007-09-03 1:23 ` Scott Schwartz
2007-09-03 1:47 ` ron minnich
2007-09-03 2:11 ` erik quanstrom
2007-09-03 2:11 ` erik quanstrom
2007-09-04 8:48 ` Douglas A. Gwyn
2007-09-03 5:28 ` Scott Schwartz
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=01b719eaabe004a9073ccb4b3425e1d0@plan9.bell-labs.com \
--to=geoff@plan9.bell-labs.com \
--cc=9fans@cse.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;
as well as URLs for NNTP newsgroup(s).