From: "Nigel Roles" <nigel@9fs.org>
To: <9fans@cse.psu.edu>
Subject: RE: [9fans] Threads: Sewing badges of honor onto a Kernel
Date: Sat, 28 Feb 2004 09:44:24 +0000 [thread overview]
Message-ID: <000d01c3fddf$72cc45b0$2bdcfea9@blue> (raw)
In-Reply-To: <20040228105025.1a94f714.martin@parvat.com>
9fans-admin@cse.psu.edu wrote:
> If I understand right, I could summarise (one of) Linus's arguments,
> as follows:
>
> The cost of sharing some of VM, but not all (in terms of peformance,
> due to less-visible things like TLB flushes, etc), out-weighs having
> to write a little bit of assembler wrapping the clone system call
> (which only has to be got right once, however horrible it might be).
>
> I haven't seen any argument rebutting this in any way. If it is true,
> then surely a performance hit on all (forked?) processes, is more
> important than having to shim a system call? If it is not true, then
> it would be nice to know!
>
> Tell me where I'm wrong, please?
>
The performance argument may well still be regarded by Linus as
stronger, but there are other differences. One is that the stack
used by the clone, being allocated on the heap, is fixed in size,
and unprotected from overflow.
next prev parent reply other threads:[~2004-02-28 9:44 UTC|newest]
Thread overview: 191+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-02-27 4:45 dbailey27
2004-02-27 5:05 ` Scott Schwartz
2004-02-27 5:06 ` andrey mirtchovski
2004-02-27 5:05 ` dbailey27
2004-02-27 5:26 ` Rob Pike
2004-02-27 5:37 ` dbailey27
2004-02-27 5:47 ` ron minnich
2004-02-27 7:43 ` boyd, rounin
2004-02-27 5:54 ` Rob Pike
2004-02-27 6:01 ` dbailey27
2004-02-29 21:14 ` boyd, rounin
2004-03-01 4:40 ` Kenji Okamoto
2004-02-27 5:06 ` dbailey27
2004-02-27 5:28 ` Rob Pike
2004-02-27 6:19 ` Scott Schwartz
2004-02-28 9:38 ` Bruce Ellis
2004-02-28 10:10 ` Charles Forsyth
2004-02-28 10:28 ` Bruce Ellis
2004-02-28 10:11 ` [9fans] limbo? David Tolpin
2004-02-28 10:22 ` Geoff Collyer
2004-02-28 19:27 ` Charles Forsyth
2004-02-28 21:16 ` Russ Cox
2004-02-28 13:28 ` [9fans] Threads: Sewing badges of honor onto a Kernel boyd, rounin
2004-02-29 20:59 ` boyd, rounin
2004-02-27 5:43 ` ron minnich
2004-02-27 5:50 ` George Michaelson
2004-02-27 5:59 ` ron minnich
2004-02-27 6:07 ` George Michaelson
2004-02-27 7:47 ` boyd, rounin
2004-02-27 6:20 ` [9fans] " Linus Torvalds
2004-02-27 6:31 ` dbailey27
2004-02-27 6:49 ` Linus Torvalds
2004-02-27 6:48 ` dbailey27
2004-02-27 7:04 ` Linus Torvalds
2004-02-27 7:06 ` dbailey27
2004-02-27 7:30 ` a
2004-02-27 7:49 ` dbailey27
2004-02-27 7:39 ` Lucio De Re
2004-02-27 7:57 ` Linus Torvalds
2004-02-27 8:00 ` Rob Pike
2004-02-27 8:05 ` Lucio De Re
2004-02-27 8:06 ` boyd, rounin
2004-02-27 7:47 ` Linus Torvalds
2004-02-27 7:46 ` dbailey27
2004-02-27 8:08 ` Linus Torvalds
2004-02-27 8:04 ` dbailey27
2004-02-27 8:19 ` Geoff Collyer
2004-02-27 15:28 ` Rob Pike
2004-02-27 16:57 ` Linus Torvalds
2004-02-27 8:11 ` Lucio De Re
2004-02-27 8:17 ` Rob Pike
2004-02-27 8:31 ` Lucio De Re
2004-02-27 9:46 ` Linus Torvalds
2004-02-27 8:44 ` boyd, rounin
2004-02-27 10:00 ` Linus Torvalds
2004-02-27 9:52 ` Lucio De Re
2004-02-27 10:00 ` Charles Forsyth
2004-02-27 10:07 ` Lucio De Re
2004-02-27 10:14 ` Charles Forsyth
2004-02-27 10:24 ` Lucio De Re
2004-02-27 11:40 ` C H Forsyth
2004-02-28 9:58 ` Bruce Ellis
2004-02-27 10:11 ` Linus Torvalds
2004-02-27 10:13 ` Lucio De Re
2004-02-27 10:36 ` Linus Torvalds
2004-02-27 19:07 ` Donald Brownlee
2004-02-27 7:47 ` Fco.J.Ballesteros
2004-02-27 8:04 ` boyd, rounin
2004-02-29 21:17 ` boyd, rounin
2004-02-27 7:12 ` Rob Pike
2004-02-27 7:17 ` Charles Forsyth
2004-02-27 8:01 ` boyd, rounin
2004-02-27 8:06 ` Scott Schwartz
2004-02-27 8:15 ` Rob Pike
2004-02-27 7:06 ` Lucio De Re
2004-02-27 7:53 ` boyd, rounin
2004-02-27 12:23 ` Dave Lukes
2004-02-27 16:08 ` Linus Torvalds
2004-02-27 16:39 ` Dave Lukes
2004-02-27 17:05 ` Linus Torvalds
2004-02-27 17:03 ` Fco.J.Ballesteros
2004-02-27 17:50 ` Dave Lukes
2004-02-27 18:26 ` Linus Torvalds
2004-02-27 18:27 ` matt
2004-02-27 18:39 ` andrey mirtchovski
2004-02-27 23:39 ` boyd, rounin
2004-03-01 8:44 ` Fco.J.Ballesteros
2004-03-01 8:48 ` Fco.J.Ballesteros
2004-03-01 8:59 ` Lucio De Re
2004-03-01 9:04 ` Fco.J.Ballesteros
2004-03-01 9:16 ` Kenji Okamoto
2004-03-01 9:19 ` Kenji Okamoto
2004-03-01 15:47 ` ron minnich
2004-03-01 16:23 ` lucio
2004-03-01 18:04 ` viro
2004-03-02 9:37 ` Douglas A. Gwyn
2004-03-02 10:16 ` lucio
2004-03-03 1:36 ` Kenji Okamoto
2004-03-02 1:40 ` rob pike, esq.
2004-02-27 23:20 ` boyd, rounin
2004-03-01 10:34 ` Bengt Kleberg
2004-03-01 14:40 ` Russ Cox
2004-03-01 15:17 ` boyd
2004-03-02 9:42 ` Bengt Kleberg
2004-03-02 9:53 ` Fco.J.Ballesteros
2004-03-02 14:51 ` ron minnich
2004-03-03 9:33 ` Bengt Kleberg
2004-03-03 12:59 ` ron minnich
2004-03-03 13:10 ` Fco.J.Ballesteros
2004-03-03 13:21 ` ron minnich
2004-03-04 10:00 ` Yi Li
2004-03-04 11:22 ` Fco.J.Ballesteros
2004-03-05 15:17 ` Yi Li
2004-03-03 13:38 ` rog
2004-03-03 17:57 ` a
2004-03-01 15:56 ` ron minnich
2004-03-02 9:42 ` Bengt Kleberg
2004-02-27 17:32 ` C H Forsyth
2004-02-29 21:10 ` boyd, rounin
2004-03-01 8:19 ` Charles Forsyth
2004-03-01 8:46 ` dbailey27
2004-03-01 9:34 ` David Tolpin
2004-03-01 10:02 ` Charles Forsyth
2004-03-01 10:12 ` David Tolpin
2004-03-01 10:40 ` Charles Forsyth
2004-03-01 11:56 ` David Tolpin
2004-03-01 17:29 ` rog
2004-03-02 6:38 ` 9nut
2004-03-01 19:02 ` Taj Khattra
2004-03-01 19:15 ` David Tolpin
2004-03-01 19:22 ` Joel Salomon
2004-03-01 19:43 ` David Tolpin
2004-03-01 21:07 ` Derek Fawcus
2004-03-01 21:12 ` David Tolpin
2004-03-02 2:46 ` boyd, rounin
2004-03-02 6:02 ` David Tolpin
2004-03-02 12:31 ` Bruce Ellis
2004-03-02 18:46 ` boyd, rounin
2004-03-02 12:19 ` Dick Davies
2004-03-02 18:40 ` boyd, rounin
2004-03-04 3:52 ` Martin C.Atkins
2004-03-04 9:07 ` Bruce Ellis
2004-03-01 21:15 ` Charles Forsyth
2004-03-01 21:20 ` rog
2004-03-02 2:48 ` Joel Salomon
2004-03-03 3:58 ` Martin C.Atkins
2004-03-01 9:36 ` Geoff Collyer
2004-03-01 12:06 ` boyd
2004-03-01 14:55 ` David Presotto
2004-03-01 12:18 ` boyd
2004-03-01 13:29 ` Fco.J.Ballesteros
2004-03-01 13:33 ` lucio
2004-03-01 13:55 ` boyd
2004-03-02 4:13 ` Taj Khattra
2004-03-02 4:34 ` Roman Shaposhnick
2004-03-02 4:47 ` ron minnich
2004-03-02 5:53 ` Roman Shaposhnick
2004-03-02 5:58 ` ron minnich
2004-03-02 15:49 ` boyd, rounin
2004-03-02 7:00 ` rob pike, esq.
2004-03-02 20:58 ` Andrew Simmons
2004-03-02 21:23 ` boyd, rounin
2004-03-03 7:05 ` Anastasopoulos S
2004-03-03 5:11 ` Kenji Okamoto
2004-03-03 5:26 ` boyd, rounin
2004-03-03 9:49 ` Bruce Ellis
2004-03-03 12:41 ` boyd, rounin
2004-03-03 9:42 ` Bruce Ellis
2004-03-03 7:55 ` 9nut
2004-02-27 6:59 ` Donald Brownlee
2004-02-27 7:49 ` boyd, rounin
2004-02-27 10:11 ` [9fans] " Douglas A. Gwyn
2004-02-28 5:20 ` Martin C.Atkins
2004-02-28 9:44 ` Nigel Roles [this message]
2004-02-28 11:08 ` viro
2004-02-28 13:40 ` Nigel Roles
2004-02-28 13:36 ` boyd, rounin
2004-02-28 14:14 ` viro
2004-02-28 18:16 ` Nigel Roles
2004-02-28 18:53 ` viro
2004-02-28 19:44 ` Charles Forsyth
2004-02-28 20:13 ` Rob Pike
2004-03-01 11:50 ` viro
2004-03-01 11:49 ` dbailey27
2004-02-28 13:32 ` boyd, rounin
2004-03-01 10:35 ` Douglas A. Gwyn
2004-03-01 11:01 ` Geoff Collyer
2004-03-01 19:13 ` Joel Salomon
2004-03-01 10:35 ` Douglas A. Gwyn
2004-02-28 13:41 ` David Presotto
2004-03-02 21:59 Keith Nash
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='000d01c3fddf$72cc45b0$2bdcfea9@blue' \
--to=nigel@9fs.org \
--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).