From owner-freebsd-smp@FreeBSD.ORG Tue May 24 11:20:51 2005 Return-Path: X-Original-To: freebsd-smp@freebsd.org Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 0F8B816A41C for ; Tue, 24 May 2005 11:20:50 +0000 (GMT) (envelope-from sirmoo@cowbert.2y.net) Received: from cowbert.2y.net (d46h180.public.uconn.edu [137.99.46.180]) by mx1.FreeBSD.org (Postfix) with SMTP id 5B63543D1D for ; Tue, 24 May 2005 11:20:49 +0000 (GMT) (envelope-from sirmoo@cowbert.2y.net) Received: (qmail 53036 invoked by uid 1001); 24 May 2005 11:20:49 -0000 Date: Tue, 24 May 2005 07:20:49 -0400 From: "Peter C. Lai" To: freebsd-smp@freebsd.org Message-ID: <20050524112049.GF608@cowbert.2y.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.6i Subject: 5.4-R ULE peformance and MPI X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 May 2005 11:20:51 -0000 On 5.4-R, the 4BSD scheduler appears to be much faster than the ULE scheduler, all else being equal, when an application is being parallelized by MPI. The hardward is dual pentium3. The particular application that we are using to benchmark this is the science/gromacs molecular dynamics simulation port, custom built to work with the single precision floating point configuration of math/fftw and net/mpich ports. None of these are threadsafe so we do not link to a threading library. In repeated runs of the same initial conditions of a particular test simulation, gromacs reports about 350mflops calculated while on ULE and 700mflops on 4BSD and the total cpu time used is ~230s on ULE and 118s on 4BSD. Using top(1), we notice that under ULE, the two gromacs processes are unable to fully use the two cpus because the IPC causes them to both request the same cpu about half the time (and therefore each process runs at 50% all the time), I am guessing ULE is spin locking so that one process is effectively blocking the other. I don't have time(1) data to show the context switching though. My cursory googling didn't turn up anything related to this so I was wondering if you already know about this issue. Thanks peter -- Peter C. Lai University of Connecticut Dept. of Molecular and Cell Biology Yale University School of Medicine SenseLab | Research Assistant http://cowbert.2y.net/ From owner-freebsd-smp@FreeBSD.ORG Thu May 26 21:04:29 2005 Return-Path: X-Original-To: freebsd-smp@freebsd.org Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 43C5116A424 for ; Thu, 26 May 2005 21:04:29 +0000 (GMT) (envelope-from Vijay.Singh@netapp.com) Received: from mx1.netapp.com (mx1.netapp.com [216.240.18.38]) by mx1.FreeBSD.org (Postfix) with ESMTP id A6D6B43D48 for ; Thu, 26 May 2005 21:04:28 +0000 (GMT) (envelope-from Vijay.Singh@netapp.com) Received: from smtp2.corp.netapp.com (10.57.159.114) by mx1.netapp.com with ESMTP; 26 May 2005 14:04:28 -0700 X-IronPort-AV: i="3.93,140,1115017200"; d="scan'208,217"; a="174445639:sNHT160512272" Received: from svlexc03.hq.netapp.com (svlexc03.corp.netapp.com [10.57.156.149]) by smtp2.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id j4QL4SDS015542 for ; Thu, 26 May 2005 14:04:28 -0700 (PDT) Received: from burgundy.hq.netapp.com ([10.56.10.66]) by svlexc03.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Thu, 26 May 2005 14:04:27 -0700 Received: from magenta.hq.netapp.com ([10.56.11.84]) by burgundy.hq.netapp.com with Microsoft SMTPSVC(5.0.2195.6713); Thu, 26 May 2005 14:04:28 -0700 X-MimeOLE: Produced By Microsoft Exchange V6.5.7226.0 Content-class: urn:content-classes:message MIME-Version: 1.0 Date: Thu, 26 May 2005 14:04:27 -0700 Message-ID: <637A278D8D0DBC438EA5E75C6E1818B9044107CB@magenta.hq.netapp.com> X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: SMP with HTT disabled Thread-Index: AcViNoCayqz+QYiuS6mwgFFK1NkavQ== From: "Singh, Vijay" To: X-OriginalArrivalTime: 26 May 2005 21:04:28.0049 (UTC) FILETIME=[80E9D010:01C56236] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Subject: SMP with HTT disabled X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 26 May 2005 21:04:29 -0000 Hello, I am trying to disable HTT to run some tests. From dmesg I have: =20 CPU: Intel(R) Xeon(TM) CPU 2.66GHz (2666.77-MHz 686-class CPU) Origin =3D "GenuineIntel" Id =3D 0xf29 Stepping =3D 9 =20 Features=3D0xbfebfbff Hyperthreading: 2 logical CPUs real memory =3D 1073676288 (1023 MB) avail memory =3D 1041121280 (992 MB) ACPI APIC Table: FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs cpu0 (BSP): APIC ID: 0 cpu1 (AP): APIC ID: 1 # cat /boot/loader.conf machdep.hlt_logical_cpus=3D1 =20 And mptable output is below. It seems to me that the kernel does not bring up the 2nd physical CPU. Am I right or wrong. =20 br vijay =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =3D=3D=3D=3D=3D=3D=3D MPTable, version 2.0.15 ------------------------------------------------------------------------ ------- MP Floating Pointer Structure: location: BIOS physical address: 0x000ff780 signature: '_MP_' length: 16 bytes version: 1.4 checksum: 0xb4 mode: Virtual Wire ------------------------------------------------------------------------ ------- MP Config Table Header: physical address: 0x000f8d50 signature: 'PCMP' base table length: 344 version: 1.4 checksum: 0xec OEM ID: 'INTEL ' Product ID: 'KingsCanyonC' OEM table pointer: 0x00000000 OEM table size: 0 entry count: 36 local APIC address: 0xfee00000 extended table length: 124 extended table checksum: 10 ------------------------------------------------------------------------ ------- MP Config Base Table Entries: -- Processors: APIC ID Version State Family Model Step Flags 0 0x14 BSP, usable 15 2 9 0xbfebfbff -- Bus: Bus ID Type 0 PCI=20 1 PCI=20 2 PCI=20 3 PCI=20 4 PCI=20 5 ISA=20 -- I/O APICs: APIC ID Version State Address 2 0x20 usable 0xfec00000 3 0x20 usable 0xfec80000 4 0x20 usable 0xfec80400 -- I/O Ints: Type Polarity Trigger Bus ID IRQ APIC ID PIN# ExtINT conforms conforms 5 0 2 0 INT conforms conforms 5 1 2 1 INT conforms conforms 5 0 2 2 INT conforms conforms 5 3 2 3 INT conforms conforms 5 4 2 4 INT conforms conforms 5 6 2 6 INT conforms conforms 5 7 2 7 INT active-hi edge 5 8 2 8 INT conforms conforms 5 10 2 10 INT conforms conforms 5 12 2 12 INT conforms conforms 5 13 2 13 INT conforms conforms 5 14 2 14 INT conforms conforms 5 15 2 15 INT active-lo level 0 31:A 2 18 INT active-lo level 0 31:B 2 17 INT active-lo level 0 29:A 2 16 INT active-lo level 0 29:B 2 19 INT active-lo level 0 29:C 2 18 INT active-lo level 1 4:A 2 21 INT active-lo level 3 1:A 3 4 INT active-lo level 4 1:A 4 0 INT active-lo level 4 1:B 4 1 INT active-lo level 4 2:A 4 4 INT active-lo level 4 2:B 4 5 -- Local Ints: Type Polarity Trigger Bus ID IRQ APIC ID PIN# ExtINT conforms conforms 0 0:A 255 0 NMI conforms conforms 0 0:A 255 1 ------------------------------------------------------------------------ ------- MP Config Extended Table Entries: -- System Address Space bus ID: 0 address type: I/O address address base: 0x9000 address range: 0x6000 -- System Address Space bus ID: 0 address type: I/O address address base: 0x0 address range: 0x100 -- System Address Space bus ID: 0 address type: memory address address base: 0xa0000 address range: 0x20000 -- System Address Space bus ID: 0 address type: memory address address base: 0xfc200000 address range: 0x2a00000 -- System Address Space bus ID: 0 address type: prefetch address address base: 0xff600000 address range: 0x500000 -- Bus Heirarchy bus ID: 5 bus info: 0x01 parent bus ID: 0 -- Compatibility Bus Address bus ID: 0 address modifier: add predefined range: 0x00000000 -- Compatibility Bus Address bus ID: 0 address modifier: add predefined range: 0x00000001 =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =3D=3D=3D=3D=3D=3D=3D =20 From owner-freebsd-smp@FreeBSD.ORG Thu May 26 23:03:57 2005 Return-Path: X-Original-To: freebsd-smp@freebsd.org Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4CAE316A41C for ; Thu, 26 May 2005 23:03:57 +0000 (GMT) (envelope-from gcoon@inch.com) Received: from util.inch.com (mx.inch.com [216.223.198.27]) by mx1.FreeBSD.org (Postfix) with ESMTP id E52BF43D1F for ; Thu, 26 May 2005 23:03:56 +0000 (GMT) (envelope-from gcoon@inch.com) Received: from kod.inch.com (kod.inch.com [216.223.192.68]) by util.inch.com (8.12.10/8.12.10/UTIL-INCH-3.0.10) with ESMTP id j4QN3tqK014595; Thu, 26 May 2005 19:03:55 -0400 (EDT) (envelope-from gcoon@inch.com) Date: Thu, 26 May 2005 19:03:55 -0400 (EDT) From: Gerald To: "Singh, Vijay" In-Reply-To: <637A278D8D0DBC438EA5E75C6E1818B9044107CB@magenta.hq.netapp.com> Message-ID: <20050526184952.W94331@kod.inch.com> References: <637A278D8D0DBC438EA5E75C6E1818B9044107CB@magenta.hq.netapp.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-smp@freebsd.org Subject: Re: SMP with HTT disabled X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 26 May 2005 23:03:57 -0000 On Thu, 26 May 2005, Singh, Vijay wrote: > Hello, I am trying to disable HTT to run some tests. From dmesg I have: I think you want: machdep.hyperthreading_allowed=0 http://www.mail-archive.com/freebsd-security@freebsd.org/msg00157.html and http://www.freebsd.org/cgi/cvsweb.cgi/src/sys/i386/i386/mp_machdep.c The default was change to 1 in -current Fri May 13 00:57:04 2005 UTC (13 days, 22 hours ago) according to cvsweb. Gerald Coon From owner-freebsd-smp@FreeBSD.ORG Fri May 27 14:49:49 2005 Return-Path: X-Original-To: freebsd-smp@FreeBSD.org Delivered-To: freebsd-smp@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 408E216A41C for ; Fri, 27 May 2005 14:49:49 +0000 (GMT) (envelope-from jhb@FreeBSD.org) Received: from mail26.sea5.speakeasy.net (mail26.sea5.speakeasy.net [69.17.117.28]) by mx1.FreeBSD.org (Postfix) with ESMTP id EAB5443D4C for ; Fri, 27 May 2005 14:49:48 +0000 (GMT) (envelope-from jhb@FreeBSD.org) Received: (qmail 31424 invoked from network); 27 May 2005 14:49:48 -0000 Received: from server.baldwin.cx ([216.27.160.63]) (envelope-sender ) by mail26.sea5.speakeasy.net (qmail-ldap-1.03) with AES256-SHA encrypted SMTP for ; 27 May 2005 14:49:48 -0000 Received: from [10.50.40.212] (gw1.twc.weather.com [216.133.140.1]) (authenticated bits=0) by server.baldwin.cx (8.13.1/8.13.1) with ESMTP id j4REnMe5012347; Fri, 27 May 2005 10:49:38 -0400 (EDT) (envelope-from jhb@FreeBSD.org) From: John Baldwin To: freebsd-smp@FreeBSD.org Date: Fri, 27 May 2005 10:37:37 -0400 User-Agent: KMail/1.8 References: <20050516171111.K522@a2.scoop.co.nz> <4288355E.4070409@pacific.net.sg> <20050516180322.W522@a2.scoop.co.nz> In-Reply-To: <20050516180322.W522@a2.scoop.co.nz> MIME-Version: 1.0 Content-Disposition: inline Message-Id: <200505271037.38110.jhb@FreeBSD.org> Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Spam-Status: No, score=-102.8 required=4.2 tests=ALL_TRUSTED, USER_IN_WHITELIST autolearn=failed version=3.0.2 X-Spam-Checker-Version: SpamAssassin 3.0.2 (2004-11-16) on server.baldwin.cx Cc: Andrew McNaughton Subject: Re: Stability of RELENG_5_4 with dual Xeon X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 27 May 2005 14:49:49 -0000 On Monday 16 May 2005 02:18 am, Andrew McNaughton wrote: > On Mon, 16 May 2005, Erich Dollansky wrote: > > Hi, > > > > Andrew McNaughton wrote: > >> I'd be interested to hear people's recent experiences with Dual Xeons > >> under load with SMP on and HTT off. > >> > >> A while back there were stability problems with Dual Xeon machines. > >> I've got one of these in production with SMP turned off for the time > > > > Do you refere to the scheduler? > > > > Use the old BSD scheduler and you should be fine. > > I'm not familiar with the scheduler options. Nothing changed from GENERIC > there. > > When I comissioned the machine in February I ran RELENG_5_3 with the SMP > kernel config as supplied. ie generic with the SMP option turned on. No > problems surfaced during setup, but when the box went live, it was having > kernel panics about every couple of hours. Going back to the GENERIC > kernel solved the problem. This problem was fixed in 5.4 and was also fixed in the RELENG_5_3 branch in CVS on January 25th. -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve" = http://www.FreeBSD.org From owner-freebsd-smp@FreeBSD.ORG Fri May 27 14:49:56 2005 Return-Path: X-Original-To: freebsd-smp@FreeBSD.org Delivered-To: freebsd-smp@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B259416A41C for ; Fri, 27 May 2005 14:49:56 +0000 (GMT) (envelope-from jhb@FreeBSD.org) Received: from mail26.sea5.speakeasy.net (mail26.sea5.speakeasy.net [69.17.117.28]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6CA6E43D4C for ; Fri, 27 May 2005 14:49:56 +0000 (GMT) (envelope-from jhb@FreeBSD.org) Received: (qmail 31574 invoked from network); 27 May 2005 14:49:56 -0000 Received: from server.baldwin.cx ([216.27.160.63]) (envelope-sender ) by mail26.sea5.speakeasy.net (qmail-ldap-1.03) with AES256-SHA encrypted SMTP for ; 27 May 2005 14:49:55 -0000 Received: from [10.50.40.212] (gw1.twc.weather.com [216.133.140.1]) (authenticated bits=0) by server.baldwin.cx (8.13.1/8.13.1) with ESMTP id j4REnMe7012347; Fri, 27 May 2005 10:49:51 -0400 (EDT) (envelope-from jhb@FreeBSD.org) From: John Baldwin To: freebsd-smp@FreeBSD.org Date: Fri, 27 May 2005 10:49:06 -0400 User-Agent: KMail/1.8 References: <637A278D8D0DBC438EA5E75C6E1818B9044107CB@magenta.hq.netapp.com> In-Reply-To: <637A278D8D0DBC438EA5E75C6E1818B9044107CB@magenta.hq.netapp.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200505271049.06850.jhb@FreeBSD.org> X-Spam-Status: No, score=-102.6 required=4.2 tests=ALL_TRUSTED, UPPERCASE_25_50,USER_IN_WHITELIST autolearn=failed version=3.0.2 X-Spam-Checker-Version: SpamAssassin 3.0.2 (2004-11-16) on server.baldwin.cx Cc: "Singh, Vijay" Subject: Re: SMP with HTT disabled X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 27 May 2005 14:49:56 -0000 On Thursday 26 May 2005 05:04 pm, Singh, Vijay wrote: > Hello, I am trying to disable HTT to run some tests. From dmesg I have: > > CPU: Intel(R) Xeon(TM) CPU 2.66GHz (2666.77-MHz 686-class CPU) > Origin = "GenuineIntel" Id = 0xf29 Stepping = 9 > > Features=0xbfebfbff ,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,S > SE2,SS,HTT,TM,PBE> > Hyperthreading: 2 logical CPUs > real memory = 1073676288 (1023 MB) > avail memory = 1041121280 (992 MB) > ACPI APIC Table: > FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs > cpu0 (BSP): APIC ID: 0 > cpu1 (AP): APIC ID: 1 > > # cat /boot/loader.conf > machdep.hlt_logical_cpus=1 > > And mptable output is below. It seems to me that the kernel does not > bring up the 2nd physical CPU. Am I right or wrong. The kernel only sees 1 physical CPU. The MPTable only shows 1 physical CPU as well: > MP Config Base Table Entries: > > -- > > Processors: APIC ID Version State Family Model Step Flags > > 0 0x14 BSP, usable 15 2 9 0xbfebfbff > > -- -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve" = http://www.FreeBSD.org From owner-freebsd-smp@FreeBSD.ORG Fri May 27 18:23:08 2005 Return-Path: X-Original-To: freebsd-smp@freebsd.org Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7872B16A41C; Fri, 27 May 2005 18:23:08 +0000 (GMT) (envelope-from julian@elischer.org) Received: from mail.vicor-nb.com (bigwoop.vicor-nb.com [208.206.78.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4FA4543D1D; Fri, 27 May 2005 18:23:05 +0000 (GMT) (envelope-from julian@elischer.org) Received: from [208.206.78.97] (julian.vicor-nb.com [208.206.78.97]) by mail.vicor-nb.com (Postfix) with ESMTP id F04887A425; Fri, 27 May 2005 11:23:04 -0700 (PDT) Message-ID: <42976588.8030807@elischer.org> Date: Fri, 27 May 2005 11:23:04 -0700 From: Julian Elischer User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.7) Gecko/20050423 X-Accept-Language: en, hu MIME-Version: 1.0 To: John Baldwin References: <637A278D8D0DBC438EA5E75C6E1818B9044107CB@magenta.hq.netapp.com> <200505271049.06850.jhb@FreeBSD.org> In-Reply-To: <200505271049.06850.jhb@FreeBSD.org> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-smp@freebsd.org, "Singh, Vijay" Subject: Re: SMP with HTT disabled X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 27 May 2005 18:23:08 -0000 John Baldwin wrote: >On Thursday 26 May 2005 05:04 pm, Singh, Vijay wrote: > > >>Hello, I am trying to disable HTT to run some tests. From dmesg I have: >> >>CPU: Intel(R) Xeon(TM) CPU 2.66GHz (2666.77-MHz 686-class CPU) >> Origin = "GenuineIntel" Id = 0xf29 Stepping = 9 >> >>Features=0xbfebfbff>,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,S >>SE2,SS,HTT,TM,PBE> >> Hyperthreading: 2 logical CPUs >>real memory = 1073676288 (1023 MB) >>avail memory = 1041121280 (992 MB) >>ACPI APIC Table: >>FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs >> cpu0 (BSP): APIC ID: 0 >> cpu1 (AP): APIC ID: 1 >> >># cat /boot/loader.conf >>machdep.hlt_logical_cpus=1 >> >>And mptable output is below. It seems to me that the kernel does not >>bring up the 2nd physical CPU. Am I right or wrong. >> >> > >The kernel only sees 1 physical CPU. The MPTable only shows 1 physical CPU as >well: > > note that mptable shows both HTT cpus on some motherboards and only one entry per chip on others. >>MP Config Base Table Entries: >> >>-- >> >>Processors: APIC ID Version State Family Model Step Flags >> >>0 0x14 BSP, usable 15 2 9 0xbfebfbff >> >>-- >> >> > > > From owner-freebsd-smp@FreeBSD.ORG Fri May 27 20:01:58 2005 Return-Path: X-Original-To: freebsd-smp@FreeBSD.org Delivered-To: freebsd-smp@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7843B16A41C for ; Fri, 27 May 2005 20:01:58 +0000 (GMT) (envelope-from jhb@FreeBSD.org) Received: from mail26.sea5.speakeasy.net (mail26.sea5.speakeasy.net [69.17.117.28]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3578443D1D for ; Fri, 27 May 2005 20:01:57 +0000 (GMT) (envelope-from jhb@FreeBSD.org) Received: (qmail 15394 invoked from network); 27 May 2005 20:01:57 -0000 Received: from server.baldwin.cx ([216.27.160.63]) (envelope-sender ) by mail26.sea5.speakeasy.net (qmail-ldap-1.03) with AES256-SHA encrypted SMTP for ; 27 May 2005 20:01:57 -0000 Received: from [10.50.40.212] (gw1.twc.weather.com [216.133.140.1]) (authenticated bits=0) by server.baldwin.cx (8.13.1/8.13.1) with ESMTP id j4RK1R07016026; Fri, 27 May 2005 16:01:44 -0400 (EDT) (envelope-from jhb@FreeBSD.org) From: John Baldwin To: Julian Elischer Date: Fri, 27 May 2005 15:52:19 -0400 User-Agent: KMail/1.8 References: <637A278D8D0DBC438EA5E75C6E1818B9044107CB@magenta.hq.netapp.com> <200505271049.06850.jhb@FreeBSD.org> <42976588.8030807@elischer.org> In-Reply-To: <42976588.8030807@elischer.org> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200505271552.20456.jhb@FreeBSD.org> X-Spam-Status: No, score=-102.8 required=4.2 tests=ALL_TRUSTED, USER_IN_WHITELIST autolearn=failed version=3.0.2 X-Spam-Checker-Version: SpamAssassin 3.0.2 (2004-11-16) on server.baldwin.cx Cc: freebsd-smp@FreeBSD.org, "Singh, Vijay" Subject: Re: SMP with HTT disabled X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 27 May 2005 20:01:58 -0000 On Friday 27 May 2005 02:23 pm, Julian Elischer wrote: > John Baldwin wrote: > >On Thursday 26 May 2005 05:04 pm, Singh, Vijay wrote: > >>Hello, I am trying to disable HTT to run some tests. From dmesg I have: > >> > >>CPU: Intel(R) Xeon(TM) CPU 2.66GHz (2666.77-MHz 686-class CPU) > >> Origin = "GenuineIntel" Id = 0xf29 Stepping = 9 > >> > >>Features=0xbfebfbff >>,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,S > >>SE2,SS,HTT,TM,PBE> > >> Hyperthreading: 2 logical CPUs > >>real memory = 1073676288 (1023 MB) > >>avail memory = 1041121280 (992 MB) > >>ACPI APIC Table: > >>FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs > >> cpu0 (BSP): APIC ID: 0 > >> cpu1 (AP): APIC ID: 1 > >> > >># cat /boot/loader.conf > >>machdep.hlt_logical_cpus=1 > >> > >>And mptable output is below. It seems to me that the kernel does not > >>bring up the 2nd physical CPU. Am I right or wrong. > > > >The kernel only sees 1 physical CPU. The MPTable only shows 1 physical > > CPU as well: > > note that mptable shows both HTT cpus on some motherboards and only one > entry > per chip on others. Yes, but clearly, the MP Table is only listing 1 CPU, so the machine cannot have _2_ physical CPUs in it that the BIOS knows about. > >>MP Config Base Table Entries: > >> > >>-- > >> > >>Processors: APIC ID Version State Family Model Step Flags > >> > >>0 0x14 BSP, usable 15 2 9 0xbfebfbff > >> > >>-- -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve" = http://www.FreeBSD.org