[PATCH] /dev/poll (RE: web server (and TCP) performance tuning?)

• Next message: Keith Owens: "Re: [Q.] sk_buff headroom size increases by 16, why?"
• Previous message: Olivier Galibert: "Re: [Q.] sk_buff headroom size increases by 16, why?"
• In reply to: Lucius Chang: "RE: web server (and TCP) performance tuning?"
• Next in thread: Michal Ostrowski: "[PATCH] /dev/poll (RE: web server (and TCP) performance tuning?)"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

I just happened to be working with Neils Provos' /dev/poll patch
(porting it to 2.3/2.4).

For those of you who are interested, the patch is available at:

http://www.citi.umich.edu/projects/linux-scalability/patches/devpoll-2.4.0.diff

The patch is against 2.4.0-test1-ac7, though I think it should apply
cleanly against any recent version. This patch is hot out of XEmacs
(though I've tested it successfully with Provos' modified thttpd).
Consider that as the standard disclaimer.

If you haven't seen it already, I'll take this opportunity refer you
 to an excellent paper by Niels Provos on the topic:

"Scalable Network I/O in Linux":
http://www.citi.umich.edu/techreports/reports/citi-tr-00-4.ps.gz

Michal Ostrowski
mostrows@styx.uwaterloo.ca

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

• Next message: Keith Owens: "Re: [Q.] sk_buff headroom size increases by 16, why?"
• Previous message: Olivier Galibert: "Re: [Q.] sk_buff headroom size increases by 16, why?"
• In reply to: Lucius Chang: "RE: web server (and TCP) performance tuning?"
• Next in thread: Michal Ostrowski: "[PATCH] /dev/poll (RE: web server (and TCP) performance tuning?)"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Thu Jun 15 2000 - 21:00:31 EST