From owner-freebsd-current@FreeBSD.ORG Wed Nov 10 02:02:06 2004 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5AA3E16A4CE for ; Wed, 10 Nov 2004 02:02:05 +0000 (GMT) Received: from out001.verizon.net (out001pub.verizon.net [206.46.170.140]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7A2C943D5D for ; Wed, 10 Nov 2004 02:02:05 +0000 (GMT) (envelope-from Alex.Kovalenko@verizon.net) Received: from [10.0.3.231] ([138.89.77.49]) by out001.verizon.net (InterMail vM.5.01.06.06 201-253-122-130-106-20030910) with ESMTP id <20041110020204.IDRB23519.out001.verizon.net@[10.0.3.231]>; Tue, 9 Nov 2004 20:02:04 -0600 From: "Alexandre \"Sunny\" Kovalenko" To: Randy Bush In-Reply-To: <16784.25080.724865.791932@ran.psg.com> References: <16784.25080.724865.791932@ran.psg.com> Content-Type: text/plain Message-Id: <1100052066.6786.10.camel@RabbitsDen> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.4.6 Date: Tue, 09 Nov 2004 21:01:07 -0500 Content-Transfer-Encoding: 7bit X-Authentication-Info: Submitted using SMTP AUTH at out001.verizon.net from [138.89.77.49] at Tue, 9 Nov 2004 20:02:03 -0600 cc: FreeBSD Current Subject: Re: htt & smp X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 10 Nov 2004 02:02:06 -0000 On Tue, 2004-11-09 at 01:21, Randy Bush wrote: > i have heard conflicting things, so thought i would ask. > > for a server running a bunch of net aps, if the cpu is htt, > is it worth turning on smp? > > randy > > --- > > CPU: Intel(R) Pentium(R) 4 CPU 2.80GHz (2795.24-MHz 686-class CPU) > Origin = "GenuineIntel" Id = 0xf34 Stepping = 4 > Features=0xbfebfbff > Hyperthreading: 2 logical CPUs > > _______________________________________________ > freebsd-current@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-current > To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" On heavily computational multithreaded application (plenty of RC4 and MD5 calculations done in parallel) two-way 2.8GHz Xeon without HTT was ~30% slower then same machine with HTT on (virtual 4-way), but machine was running SMP kernel in both cases, and the application was somewhat extreme. Then again, if you are terminating a lot of SSL sessions as part of the "bunch of net aps", your case might not be that different. On the other hand, this application scales almost linearly with addition of the CPU (tested on real 4-way hardware), so 30% is not that much of a gain. I have no experience comparing UP vs. SMP, though... HTH, Alexandre "Sunny" Kovalenko.