From owner-freebsd-arch@FreeBSD.ORG Tue Oct 25 13:48:36 2005 Return-Path: X-Original-To: arch@freebsd.org Delivered-To: freebsd-arch@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id ABF8A16A41F; Tue, 25 Oct 2005 13:48:36 +0000 (GMT) (envelope-from marcolz@stack.nl) Received: from mailhost.stack.nl (vaak.stack.nl [131.155.140.140]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3C18443D49; Tue, 25 Oct 2005 13:48:35 +0000 (GMT) (envelope-from marcolz@stack.nl) Received: from hammer.stack.nl (hammer.stack.nl [IPv6:2001:610:1108:5010::153]) by mailhost.stack.nl (Postfix) with ESMTP id C2385A2FD1; Tue, 25 Oct 2005 15:48:34 +0200 (CEST) Received: by hammer.stack.nl (Postfix, from userid 333) id 9D6B8644A; Tue, 25 Oct 2005 15:48:34 +0200 (CEST) Date: Tue, 25 Oct 2005 15:48:34 +0200 From: Marc Olzheim To: David Xu Message-ID: <20051025134834.GB62148@stack.nl> References: <20051025120538.K52058@fledge.watson.org> <435E2DCF.6080809@freebsd.org> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="PEIAKu/WMn1b1Hv9" Content-Disposition: inline In-Reply-To: <435E2DCF.6080809@freebsd.org> X-Operating-System: FreeBSD hammer.stack.nl 6.0-BETA4 FreeBSD 6.0-BETA4 X-URL: http://www.stack.nl/~marcolz/ User-Agent: Mutt/1.5.11 Cc: Daniel Eischen , arch@freebsd.org, Robert Watson Subject: Re: libc_r is deprecated X-BeenThere: freebsd-arch@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussion related to FreeBSD architecture List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 25 Oct 2005 13:48:36 -0000 --PEIAKu/WMn1b1Hv9 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Tue, Oct 25, 2005 at 09:06:23PM +0800, David Xu wrote: > Robert Watson wrote: > >I'd like to keep it around in some form -- I recently ran a series of=20 > >HTTP-related benchmarks and libc_r benchmarked signicantly faster than= =20 > >other libraries on both UP and SMP. I'm working to refine the=20 > >benchmark for improved realism, and will see if that persists. =20 > >However, when it comes to understanding scheduling and threading=20 > >behavior, I think libc_r remains useful... > > > >Robert N M Watson > > > libc_r runs on single kernel thread, so if you are continue using libc_r, > you are not testing TCP/IP with multithreads program, this may give you > false data. Only kernel threads based server can test to see if the TCP/IP > stack locking works well. Erhm, its not about testing the TCP/IP stack locking, this is about stable and raw performance. Of course the single kernel thread might have a negative impact on total performance, but in our real world applications, I don't see a real performance boost from KSE. What I do see is easier and cleaner programming with KSE, but once you've done all the work to get usable libc_r based I/O, it works good. (Well, unless you need to fork+exec from a heavily mallocing thread system, without a patch similar to the one in PR threads/76690...) Marc --PEIAKu/WMn1b1Hv9 Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.2 (FreeBSD) iD8DBQFDXjeyezjnobFOgrERApNrAKDKz3rmw4DMpAz/aResf4552go9TACgqpHs pAdCxsv7NXp7J6NLYddcHFg= =Z7kg -----END PGP SIGNATURE----- --PEIAKu/WMn1b1Hv9--