From owner-freebsd-questions@FreeBSD.ORG Wed Apr 28 03:22:30 2010 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 0DA41106566B for ; Wed, 28 Apr 2010 03:22:30 +0000 (UTC) (envelope-from john@starfire.mn.org) Received: from elwood.starfire.mn.org (starfire.skypoint.net [173.8.102.29]) by mx1.freebsd.org (Postfix) with ESMTP id B0E578FC0A for ; Wed, 28 Apr 2010 03:22:29 +0000 (UTC) Received: from elwood.starfire.mn.org (john@localhost [127.0.0.1]) by elwood.starfire.mn.org (8.14.3/8.14.3) with ESMTP id o3S3MSUN096201; Tue, 27 Apr 2010 22:22:28 -0500 (CDT) (envelope-from john@elwood.starfire.mn.org) Received: (from john@localhost) by elwood.starfire.mn.org (8.14.3/8.14.3/Submit) id o3S3MSJI096200; Tue, 27 Apr 2010 22:22:28 -0500 (CDT) (envelope-from john) Date: Tue, 27 Apr 2010 22:22:28 -0500 From: John To: Neil Short Message-ID: <20100428032228.GA96137@elwood.starfire.mn.org> References: <535299.10507.qm@web56507.mail.re3.yahoo.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <535299.10507.qm@web56507.mail.re3.yahoo.com> User-Agent: Mutt/1.4.2.3i Cc: freebsd-questions@freebsd.org Subject: Re: Improving SMP performance? X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Apr 2010 03:22:30 -0000 On Tue, Apr 27, 2010 at 05:32:58PM -0700, Neil Short wrote: > I'm somewhat disappointed in the performance in my laptop which is supposed to have a really fast processor. Is there some way to get more out of the processor? > > > [neshort/] uname -a > FreeBSD carmen 8.0-STABLE FreeBSD 8.0-STABLE #1: Thu Apr 15 19:54:24 MST 2010 neshort@carmen:/usr/obj/usr/src/sys/CARMEN i386 > [neshort/] dmesg > ... > Timecounter "i8254" frequency 1193182 Hz quality 0 > CPU: Intel(R) Core(TM) i3 CPU M 330 @ 2.13GHz (2127.92-MHz 686-class CPU) > Origin = "GenuineIntel" Id = 0x20652 Family = 6 Model = 25 Stepping = 2 > Features=0xbfebfbff > Features2=0x98e3bd > AMD Features=0x28000000 > AMD Features2=0x1 > TSC: P-state invariant > real memory = 4294967296 (4096 MB) > avail memory = 3066707968 (2924 MB) > ACPI APIC Table: > FreeBSD/SMP: Multiprocessor System Detected: 4 CPUs > FreeBSD/SMP: 1 package(s) x 2 core(s) x 2 SMT threads > cpu0 (BSP): APIC ID: 0 > cpu1 (AP): APIC ID: 1 > cpu2 (AP): APIC ID: 4 > cpu3 (AP): APIC ID: 5 > > > ====== > > "What did you do?" the man holding the flashlight asked. > > "I put down a spider," he said, wondering why the man didn't see; in the beam of yellow light the spider bloated up larger than life. "So it could get away." > In what way are you disappointed? It may be SMP, but for any single thread, it cannot go faster than one of the processors. If you are measuring a single-threaded task, that's all you can get. Or could it be that IO is limiting your performance? Without knowing what it is you want to do, and what you are experiencing, it is very hard to know how to help you. If you are just looking at the clock speed, please understand that CPU manufacturers lately are working to LOWER clocks speeds because it saves power, and to speed up the processors by using wider microinstructions and more sophisticated pipelining techniques to gain speed without just wiggling things at a higher frequency. -- John Lind john@starfire.MN.ORG