From owner-freebsd-hackers  Sun Jun 17 12:54:48 2001
Delivered-To: freebsd-hackers@freebsd.org
Received: from sockratte.schell.de (polz.de [195.20.238.74])
	by hub.freebsd.org (Postfix) with SMTP id E75E537B407
	for <freebsd-hackers@FreeBSD.ORG>; Sun, 17 Jun 2001 12:54:35 -0700 (PDT)
	(envelope-from sascha@schumann.cx)
Received: (qmail 2429 invoked from network); 17 Jun 2001 19:54:34 -0000
Received: from unknown (HELO rossini.schumann.cx) (217.81.236.238)
  by polz.de with SMTP; 17 Jun 2001 19:54:34 -0000
Received: from localhost (localhost [127.0.0.1])
	by rossini.schumann.cx (Postfix) with ESMTP
	id 0A49C5E007; Sun, 17 Jun 2001 21:53:59 +0200 (MEST)
Date: Sun, 17 Jun 2001 21:53:59 +0200 (MEST)
From: Sascha Schumann <sascha@schumann.cx>
X-X-Sender:  <sas@rossini.schumann.cx>
To: Alfred Perlstein <bright@rush.net>
Cc: Valentin Nechayev <netch@iv.nn.kiev.ua>,
	<freebsd-hackers@FreeBSD.ORG>
Subject: Re: poll(2)'s arbitrary limit
In-Reply-To: <20010617153129.N1832@superconductor.rush.net>
Message-ID: <Pine.LNX.4.33.0106172146470.6072-100000@rossini.schumann.cx>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-freebsd-hackers@FreeBSD.ORG
Precedence: bulk
List-ID: <freebsd-hackers.FreeBSD.ORG>
List-Archive: <http://docs.freebsd.org/mail/> (Web Archive)
List-Help: <mailto:majordomo?subject=help> (List Instructions)
List-Subscribe: <mailto:majordomo?subject=subscribe%20freebsd-hackers>
List-Unsubscribe: <mailto:majordomo?subject=unsubscribe%20freebsd-hackers>
X-Loop: FreeBSD.ORG

> You've misinterpreted the paper. :(

    Sorry, I got the reference wrong.  I was referring to a
    recently published HP paper[1] which concluded that "contrary
    to conventional wisdom, even a select based server can
    provide high throughput if its overhead is amortized by
    performing more useful work per select call."

    This supported the results of benchmarks I conducted on
    FreeBSD using select, poll and kqueue at the heart of the
    State Threads implementation.

    [1] http://www.hpl.hp.com/techreports/2000/HPL-2000-174.pdf

> As far as raising the amount of pollable entries, can you try your
> app with your kernel recompiled to accept 2xNO_FILE and 2xFD_SETSIZE
> and let us know if that solves your problem?

    I've been using kern.maxproc=kern.maxprocfiles=2*32768 for my
    tests and that worked successfully.

    Thanks,
    - Sascha                                     Experience IRCG
      http://schumann.cx/                http://schumann.cx/ircg


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message