From: Kris Maglione <bsdaemon@comcast.net>
To: 9fans@cse.psu.edu
Subject: Re: [9fans] Bay Area Plan 9 Users Group Meeting (August '07)
Date: Wed, 8 Aug 2007 13:27:17 -0400 [thread overview]
Message-ID: <20070808172717.GD68665@kris.home> (raw)
In-Reply-To: <13426df10708081013t7e4d0072g21f154bca5c94336@mail.gmail.com>
On Wed, Aug 08, 2007 at 10:13:41AM -0700, ron minnich wrote:
>On a more controversial note, we had a good discussion on scaling
>limitations of the current system call interface and how a new type of
>asynchrony might be introduced. One idea was that one could build on
>the current rendezvous interface so that it could accept a closure (or
>context). Then the user process would fire up a bunch of threads, most
>of which would hang out in the rendezvous. For non-blocking I/O, a
>process would kick off the system call, but the system call would
>return immediately after queueing up the I/O and the actual return
>would wake up one of the threads waiting in the rendezvous. This was
>just one idea, but it's interesting. The bigger question, for me,
>remains: how would we extend the system call interface to handle,
>e.g., 100,000 connections to "something(s)" without losing the essence
>of Plan 9? This question is not academic -- the BG/P machines are
>planned to have 256K CPUs, and we plan to run on them. We could just
>claim that firing up an ioproc for each file descriptor would work,
>but I've never been comfortable with that model -- for one thing, I
>can tell you from experience that seeing even 20,000 procs in a ps is
>fairly confusing. We could punt and just say "9p everything", but as
>David pointed out, that leaves us with a fairly chaotic universe -- we
>lose a lot of the ordering and such that the kernel gives us now via
>the basic open/read/write/close interface.
A student, advised by Russ, wrote a paper on async IO on Plan 9
without kernel modifications. The basic idea, as I understand
it, is to use the inherent asynchrony of 9P, and access files
via the kernel's exportfs interface. The concept could easily be
wrapped into a simple userspace aio lib. I prefer the idea to
modifying the kernel, but I'm not sure that the overhead would
be acceptable to all applications.
--
Kris Maglione
The severity of an itch is inversely proportional
to the reach.
next prev parent reply other threads:[~2007-08-08 17:27 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-07-29 23:02 David Hendricks
2007-07-30 20:43 ` David Leimbach
2007-07-31 6:22 ` Nick LaForge
2007-08-01 1:36 ` Gorka Guardiola
2007-08-01 1:54 ` erik quanstrom
2007-08-01 2:31 ` Gorka Guardiola
2007-08-01 2:35 ` erik quanstrom
2007-08-01 3:37 ` Paul Lalonde
2007-08-01 4:13 ` Skip Tavakkolian
2007-08-01 4:50 ` Lucio De Re
2007-08-01 8:14 ` Bruce Ellis
2007-08-01 20:55 ` Francisco J Ballesteros
2007-08-07 21:37 ` David Hendricks
2007-08-07 22:22 ` Kim Shrier
2007-08-07 22:35 ` David Hendricks
2007-08-08 1:56 ` David Leimbach
2007-08-08 11:26 ` Bruce Ellis
2007-08-08 17:13 ` ron minnich
2007-08-08 17:22 ` Charles Forsyth
2007-08-08 18:33 ` David Leimbach
2007-08-08 17:27 ` Kris Maglione [this message]
2007-08-08 19:16 ` Kris Maglione
2007-08-08 19:14 ` ron minnich
2007-08-08 20:37 ` Charles Forsyth
2007-08-08 20:41 ` ron minnich
2007-08-08 20:58 ` Charles Forsyth
2007-08-08 21:08 ` ron minnich
2007-08-08 21:14 ` Eric Van Hensbergen
2007-08-08 21:20 ` ron minnich
2007-08-08 19:16 ` David Hendricks
2007-08-08 19:40 ` David Leimbach
2007-08-08 20:35 ` Charles Forsyth
2007-08-08 20:41 ` ron minnich
2007-08-07 23:07 ` Tharaneedharan Vilwanathan
2007-08-07 23:11 ` Tharaneedharan Vilwanathan
2007-08-01 23:52 ` David Hendricks
2007-08-02 1:35 ` Gorka Guardiola
2007-08-08 1:15 ` [9fans] " David Hendricks
2007-08-10 22:45 ` [9fans] " Roman Shaposhnick
[not found] ` <dac0a5820708101945ud4e7fb4t6f09288cbdf54019@mail.gmail.com>
2007-08-11 4:37 ` Bruce Ellis
2007-08-11 5:13 ` Anthony Sorace
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=20070808172717.GD68665@kris.home \
--to=bsdaemon@comcast.net \
--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).