From owner-freebsd-smp Mon Feb 8 16:33:08 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id QAA02302 for freebsd-smp-outgoing; Mon, 8 Feb 1999 16:33:08 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from fire.starkreality.com (fire.starkreality.com [208.24.48.226]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id QAA02287 for ; Mon, 8 Feb 1999 16:33:04 -0800 (PST) (envelope-from caesar@starkreality.com) Received: from armageddon (armageddon.starkreality.com [208.24.48.227]) by fire.starkreality.com (8.9.2/8.9.2) with SMTP id SAA00890 for ; Mon, 8 Feb 1999 18:24:54 -0600 (CST) Message-Id: <4.1.19990208181440.03d1d4c0@fire.starkreality.com> X-Sender: caesar@fire.starkreality.com X-Mailer: QUALCOMM Windows Eudora Pro Version 4.1 Date: Mon, 08 Feb 1999 18:24:42 -0600 To: freebsd-smp@FreeBSD.ORG From: "William S. Duncanson" Subject: Problems keeping time Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I just upgraded a FreeBSD box to a SMP system (basically, I swapped out the MB and added a processor). Now, I'm having horrendous problems with the kernel clock drifting (it's running fast, about 7 seconds every 10 minutes). So far, xntpd seems to be keeping everything relatively close, but it's updating the clock every 10 minutes or so. ntpq claims that all of the configured peers are "insane". I'm pretty sure that this is a SMP issue, since it worked fine with a single processor (4.0-current). So, the question is, how do I fix this? Here's my kernel config. I added the "CLK_USE_I8254_CALIBRATION" after I noticed the problem, but it doesn't appear to have fixed it: machine "i386" ident FIRE maxusers 256 options "MAXDSIZ=(256*1024*1024)" options "DFLDSIZ=(256*1024*1024)" options PQ_HUGECACHE # color for 1024k/16k cache options INCLUDE_CONFIG_FILE # Include this file in kernel config kernel root on wd0s1a swap on wd0s1b cpu "I586_CPU" # aka Pentium(tm) options "CPU_DISABLE_5X86_LSSER" options "CPU_FASTER_5X86_FPU" options SMP # Symmetric MultiProcessor Kernel options APIC_IO # Symmetric (APIC) I/O options NCPU=2 # number of CPUs options NBUS=5 # number of busses options NAPIC=2 # number of IO APICs options NINTR=25 # number of INTs options "COMPAT_43" options SYSVSHM options SYSVSEM options SYSVMSG options "MD5" options KTRACE #kernel tracing options PERFMON options UCONSOLE options USERCONFIG #boot -c editor options VISUAL_USERCONFIG #visual boot -c editor options INET #Internet communications protocols pseudo-device ether #Generic Ethernet pseudo-device loop #Network loopback device pseudo-device bpfilter 4 #Berkeley packet filter options PPP_BSDCOMP #PPP BSD-compress support options PPP_DEFLATE #PPP zlib/deflate/gzip support options PPP_FILTER #enable bpf filtering (needs bpfilter) options "ICMP_BANDLIM" options FFS #Fast filesystem options FFS_ROOT #FFS usable as root device options SOFTUPDATES options NSWAPDEV=20 options QUOTA #enable disk quotas options "NFS_MINATTRTIMO=3" # VREG attrib cache timeout in sec options "NFS_MAXATTRTIMO=60" options "NFS_MINDIRATTRTIMO=30" # VDIR attrib cache timeout in sec options "NFS_MAXDIRATTRTIMO=60" options "NFS_GATHERDELAY=10" # Default write gather delay (msec) options "NFS_UIDHASHSIZ=29" # Tune the size of nfssvc_sock with this options "NFS_WDELAYHASHSIZ=16" # and with this options "NFS_MUIDHASHSIZ=63" # Tune the size of nfsmount with this options NFS_DEBUG # Enable NFS Debugging options "P1003_1B" options "_KPOSIX_PRIORITY_SCHEDULING" options "_KPOSIX_VERSION=199309L" controller scbus0 #base SCSI code device da0 #SCSI direct access devices (aka disks) device sa0 #SCSI tapes device cd0 #SCSI CD-ROMs device pass0 #CAM passthrough driver options "CAM_MAX_HIGHPOWER=4" options SCSI_NO_SENSE_STRINGS options SCSI_NO_OP_STRINGS options SCSI_REPORT_GEOMETRY options SCSI_DELAY=8000 # Be pessimistic about Joe SCSI device options "CHANGER_MIN_BUSY_SECONDS=2" options "CHANGER_MAX_BUSY_SECONDS=10" options "SA_SPACE_TIMEOUT=(60)" options "SA_REWIND_TIMEOUT=(2*60)" options "SA_ERASE_TIMEOUT=(4*60)" pseudo-device pty 256 #Pseudo ttys - can go as high as 256 pseudo-device speaker #Play IBM BASIC-style noises out your speaker pseudo-device gzip #Exec gzipped a.out's pseudo-device vn #Vnode driver (turns a file into a device) pseudo-device snp 4 #Snoop device - to look at pty/vty/etc.. options "MSGBUF_SIZE=40960" controller isa0 options "AUTO_EOI_1" options "AUTO_EOI_2" options "MAXMEM=(144*1024)" controller pnp0 controller atkbdc0 at isa? port IO_KBD tty device atkbd0 at isa? tty irq 1 device vga0 at isa? port ? conflicts pseudo-device splash #device vt0 at isa? tty #options XSERVER # support for running an X serve r. #options FAT_CURSOR # start with block cursor device sc0 at isa? tty options MAXCONS=16 # number of virtual consoles options "STD8X16FONT" # Compile font in makeoptions "STD8X16FONT"="cp850" options SC_HISTORY_SIZE=200 # number of history buffer lines options SC_DISABLE_REBOOT # disable reboot key sequence device npx0 at isa? port IO_NPX iosiz 0x0 flags 0x0 irq 13 controller wdc0 at isa? port "IO_WD1" bio irq 14 flags 0xa0ffa0ff disk wd0 at wdc0 drive 0 disk wd1 at wdc0 drive 1 controller wdc1 at isa? port "IO_WD2" bio irq 15 flags 0xa0ffa0ff options ATAPI #Enable ATAPI support for IDE bus options ATAPI_STATIC #Don't do it as an LKM options IDE_DELAY=8000 # Be optimistic about Joe IDE device device acd0 controller fdc0 at isa? port "IO_FD1" bio irq 6 drq 2 disk fd0 at fdc0 drive 0 device lpt0 at isa? port? tty irq 7 device sio0 at isa? port "IO_COM1" tty flags 0x10 irq 4 device sio0 at isa? port "IO_COM2" tty flags 0x10 irq 3 device ed0 at isa? port 0x300 net irq 10 iomem 0xd8000 device pcm0 at isa? port ? tty irq 10 drq 1 flags 0x0 device pca0 at isa? port "IO_TIMER1" tty controller pci0 controller ahc1 device de0 device xl0 options HW_WDOG options COMPAT_LINUX options PANIC_REBOOT_WAIT_TIME=16 options options SHOW_BUSYBUFS # List buffers that prevent root unmount William S. Duncanson caesar@starkreality.com The driving force behind the NC is the belief that the companies who brought us things like Unix, relational databases, and Windows can make an appliance that is inexpensive and easy to use if they choose to do that. -- Scott Adams To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Feb 8 16:54:34 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id QAA04832 for freebsd-smp-outgoing; Mon, 8 Feb 1999 16:54:34 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from rain.futuresouth.com (rain.futuresouth.com [198.79.79.125]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id QAA04824 for ; Mon, 8 Feb 1999 16:54:31 -0800 (PST) (envelope-from stormy@rain.futuresouth.com) Received: (from stormy@localhost) by rain.futuresouth.com (8.9.2/8.9.2) id SAA23251 for freebsd-smp@FreeBSD.ORG; Mon, 8 Feb 1999 18:54:29 -0600 (CST) (envelope-from stormy) Date: Mon, 8 Feb 1999 18:54:29 -0600 From: Stormy Henderson To: freebsd-smp@FreeBSD.ORG Subject: Re: Problems keeping time Message-ID: <19990208185429.E8550@rain.futuresouth.com> Mail-Followup-To: freebsd-smp@FreeBSD.ORG References: <4.1.19990208181440.03d1d4c0@fire.starkreality.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.95.1i In-Reply-To: <4.1.19990208181440.03d1d4c0@fire.starkreality.com>; from William S. Duncanson on Mon, Feb 08, 1999 at 06:24:42PM -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org A happy camper (William S. Duncanson, caesar@starkreality.com) once wrote... > I just upgraded a FreeBSD box to a SMP system (basically, I swapped out the > MB and added a processor). Now, I'm having horrendous problems with the > kernel clock drifting (it's running fast, about 7 seconds every 10 > minutes). So far, xntpd seems to be keeping everything relatively close, I have the same problem on my venerable Tyan 2xP133. FreeBSD 3.0-STABLE #10: Fri Jan 22 11:57:05 CST 1999 Timecounter "i8254" frequency 1193182 Hz CPU: Pentium/P54C (586-class CPU) Origin = "GenuineIntel" Id = 0x52c Stepping=12 Features=0x3bf Programming 24 pins in IOAPIC #0 FreeBSD/SMP: Multiprocessor motherboard cpu0 (BSP): apic id: 0, version: 0x00030010, at 0xfee00000 cpu1 (AP): apic id: 1, version: 0x00030010, at 0xfee00000 io0 (APIC): apic id: 2, version: 0x00170011, at 0xfec00000 Be happy... -- Stormy Henderson To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Feb 8 17:05:42 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id RAA06392 for freebsd-smp-outgoing; Mon, 8 Feb 1999 17:05:42 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from picnic.mat.net (b133.mat.net [206.246.122.133] (may be forged)) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id RAA06384 for ; Mon, 8 Feb 1999 17:05:37 -0800 (PST) (envelope-from chuckr@mat.net) Received: from localhost (chuckr@localhost) by picnic.mat.net (8.9.2/8.8.5) with ESMTP id UAA40238; Mon, 8 Feb 1999 20:02:49 -0500 (EST) Date: Mon, 8 Feb 1999 20:02:49 -0500 (EST) From: Chuck Robey To: "William S. Duncanson" cc: freebsd-smp@FreeBSD.ORG Subject: Re: Problems keeping time In-Reply-To: <4.1.19990208181440.03d1d4c0@fire.starkreality.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Mon, 8 Feb 1999, William S. Duncanson wrote: > I just upgraded a FreeBSD box to a SMP system (basically, I swapped out the > MB and added a processor). Now, I'm having horrendous problems with the > kernel clock drifting (it's running fast, about 7 seconds every 10 > minutes). So far, xntpd seems to be keeping everything relatively close, > but it's updating the clock every 10 minutes or so. ntpq claims that all > of the configured peers are "insane". I'm pretty sure that this is a SMP > issue, since it worked fine with a single processor (4.0-current). So, the > question is, how do I fix this? > > Here's my kernel config. I added the "CLK_USE_I8254_CALIBRATION" after I > noticed the problem, but it doesn't appear to have fixed it: I have a smp system too. I've never had to use this method, but I recall Poul-Henning talking about it, so I'll pass it on. You can tweak the method used to keep time via a sysctl: sysctl -w kern.timecounter.method=1 I don't know more than that, you can either experiment (and let us know if it worked) or wait for Poul-Henning to comment. ----------------------------+----------------------------------------------- Chuck Robey | Interests include any kind of voice or data chuckr@glue.umd.edu | communications topic, C programming, and Unix. 213 Lakeside Drive Apt T-1 | Greenbelt, MD 20770 | I run picnic (FreeBSD-current) (301) 220-2114 | and jaunt (Solaris7). ----------------------------+----------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Feb 8 19:12:33 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id TAA22543 for freebsd-smp-outgoing; Mon, 8 Feb 1999 19:12:33 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from fire.starkreality.com (fire.starkreality.com [208.24.48.226]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id TAA22530 for ; Mon, 8 Feb 1999 19:12:31 -0800 (PST) (envelope-from caesar@starkreality.com) Received: from armageddon (armageddon.starkreality.com [208.24.48.227]) by fire.starkreality.com (8.9.2/8.9.2) with SMTP id VAA20539; Mon, 8 Feb 1999 21:12:35 -0600 (CST) Message-Id: <4.1.19990208211126.00c5ab40@fire.starkreality.com> X-Sender: caesar@fire.starkreality.com X-Mailer: QUALCOMM Windows Eudora Pro Version 4.1 Date: Mon, 08 Feb 1999 21:12:24 -0600 To: Chuck Robey From: "William S. Duncanson" Subject: Re: Problems keeping time Cc: freebsd-smp@FreeBSD.ORG In-Reply-To: References: <4.1.19990208181440.03d1d4c0@fire.starkreality.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hmm...doesn't appear to be working. I'm grepping through the source trying to find the valid values for this parameter, but haven't been able to find it yet. At 20:02 2/8/99 -0500, Chuck Robey wrote: >On Mon, 8 Feb 1999, William S. Duncanson wrote: > >> I just upgraded a FreeBSD box to a SMP system (basically, I swapped out the >> MB and added a processor). Now, I'm having horrendous problems with the >> kernel clock drifting (it's running fast, about 7 seconds every 10 >> minutes). So far, xntpd seems to be keeping everything relatively close, >> but it's updating the clock every 10 minutes or so. ntpq claims that all >> of the configured peers are "insane". I'm pretty sure that this is a SMP >> issue, since it worked fine with a single processor (4.0-current). So, the >> question is, how do I fix this? >> >> Here's my kernel config. I added the "CLK_USE_I8254_CALIBRATION" after I >> noticed the problem, but it doesn't appear to have fixed it: > >I have a smp system too. I've never had to use this method, but I >recall Poul-Henning talking about it, so I'll pass it on. You can tweak >the method used to keep time via a sysctl: > >sysctl -w kern.timecounter.method=1 > >I don't know more than that, you can either experiment (and let us know >if it worked) or wait for Poul-Henning to comment. > >----------------------------+----------------------------------------------- >Chuck Robey | Interests include any kind of voice or data >chuckr@glue.umd.edu | communications topic, C programming, and Unix. >213 Lakeside Drive Apt T-1 | >Greenbelt, MD 20770 | I run picnic (FreeBSD-current) >(301) 220-2114 | and jaunt (Solaris7). >----------------------------+----------------------------------------------- > > > > > >To Unsubscribe: send mail to majordomo@FreeBSD.org >with "unsubscribe freebsd-smp" in the body of the message William S. Duncanson caesar@starkreality.com The driving force behind the NC is the belief that the companies who brought us things like Unix, relational databases, and Windows can make an appliance that is inexpensive and easy to use if they choose to do that. -- Scott Adams To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon Feb 8 19:29:47 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id TAA24678 for freebsd-smp-outgoing; Mon, 8 Feb 1999 19:29:47 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from picnic.mat.net (b133.mat.net [206.246.122.133] (may be forged)) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id TAA24664 for ; Mon, 8 Feb 1999 19:29:39 -0800 (PST) (envelope-from chuckr@mat.net) Received: from localhost (chuckr@localhost) by picnic.mat.net (8.9.2/8.8.5) with ESMTP id WAA09741; Mon, 8 Feb 1999 22:26:25 -0500 (EST) Date: Mon, 8 Feb 1999 22:26:25 -0500 (EST) From: Chuck Robey To: "William S. Duncanson" cc: freebsd-smp@FreeBSD.ORG Subject: Re: Problems keeping time In-Reply-To: <4.1.19990208211126.00c5ab40@fire.starkreality.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Mon, 8 Feb 1999, William S. Duncanson wrote: > Hmm...doesn't appear to be working. I'm grepping through the source trying > to find the valid values for this parameter, but haven't been able to find > it yet. I've seen his posting, that WAS the other valid value. > > At 20:02 2/8/99 -0500, Chuck Robey wrote: > >On Mon, 8 Feb 1999, William S. Duncanson wrote: > > > >> I just upgraded a FreeBSD box to a SMP system (basically, I swapped out the > >> MB and added a processor). Now, I'm having horrendous problems with the > >> kernel clock drifting (it's running fast, about 7 seconds every 10 > >> minutes). So far, xntpd seems to be keeping everything relatively close, > >> but it's updating the clock every 10 minutes or so. ntpq claims that all > >> of the configured peers are "insane". I'm pretty sure that this is a SMP > >> issue, since it worked fine with a single processor (4.0-current). So, the > >> question is, how do I fix this? > >> > >> Here's my kernel config. I added the "CLK_USE_I8254_CALIBRATION" after I > >> noticed the problem, but it doesn't appear to have fixed it: > > > >I have a smp system too. I've never had to use this method, but I > >recall Poul-Henning talking about it, so I'll pass it on. You can tweak > >the method used to keep time via a sysctl: > > > >sysctl -w kern.timecounter.method=1 > > > >I don't know more than that, you can either experiment (and let us know > >if it worked) or wait for Poul-Henning to comment. ----------------------------+----------------------------------------------- Chuck Robey | Interests include any kind of voice or data chuckr@glue.umd.edu | communications topic, C programming, and Unix. 213 Lakeside Drive Apt T-1 | Greenbelt, MD 20770 | I run picnic (FreeBSD-current) (301) 220-2114 | and jaunt (Solaris7). ----------------------------+----------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Feb 9 08:14:10 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id IAA03734 for freebsd-smp-outgoing; Tue, 9 Feb 1999 08:14:10 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from mel.alcatel.fr (mel.alcatel.fr [212.208.74.132]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id IAA03729 for ; Tue, 9 Feb 1999 08:14:06 -0800 (PST) (envelope-from Thierry.Herbelot@alcatel.fr) Received: from aifhs2.alcatel.fr (mailhub.alcatel.fr [155.132.180.80]) by mel.alcatel.fr (ALCANET/SMTP) with ESMTP id RAA28934 for ; Tue, 9 Feb 1999 17:13:15 +0100 Received: from lune.telspace.alcatel.fr (lune.telspace.alcatel.fr [155.132.144.65]) by aifhs2.alcatel.fr (ALCANET/SMTP2) with ESMTP id RAA21815 for ; Tue, 9 Feb 1999 17:10:48 +0100 (MET) Received: from telss1.telspace.alcatel.fr (telss1.telspace.alcatel.fr [155.132.51.4]) by lune.telspace.alcatel.fr (8.9.1a/8.9.1) with SMTP id QAA21957 for ; Tue, 9 Feb 1999 16:49:51 +0100 (MET) Received: from telspace.alcatel.fr (nairobi.telspace.alcatel.fr) by telss1.telspace.alcatel.fr (4.1/SMI-4.1) id AA19534; Tue, 9 Feb 99 16:57:57 +0100 Message-Id: <36C05C25.21A58851@telspace.alcatel.fr> Date: Tue, 09 Feb 1999 17:02:45 +0100 From: HERBELOT Thierry Organization: Alcatel Telspace X-Mailer: Mozilla 4.5 [en] (X11; I; SunOS 5.5.1 sun4m) X-Accept-Language: en Mime-Version: 1.0 To: smp@FreeBSD.ORG Subject: Mixing P2 Types Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org (re-post from -questions : this is the right place) Hello, I'm contemplating buying an SMP motherboard, now that SMP is a "mainstream" feature of FreeBSD-Stable. I was wondering if it is possible to mix P2-types on an SMP motherborad (I've got already a p2-266, and I would like to buy just an SMP motherboard (perhaps an ASUS P2L-DS) and the cheapest p2 I can buy today, which must be a p2-333) I remember that you had to be very strict when running SMP-Pentiums (same mask level, same speed ....) Is it still the case for P2 ? TIA TfH PS : after some research : In the SMP spec v1.4 : B.8 Supporting Unequal Processors: Some MP operating systems that exist today do not support processors of different types, speeds, or capabilities. However, as processor lifetimes increase and new generations of processors arrive, the potential for dissimilarity among processors increases. The MP specification addresses this potential by providing an MP configuration table to help the operating system configure itself. Operating system writers should factor in processor variations, such as processor type, family, model, and features, to arrive at a configuration that maximizes overall system performance. At a minimum, the MP operating system should remain operational and should support the common features of unequal processors. BUT the spec for an ASUS P2L97DS shows that there is only on jumper set to define the bus and core clock of both CPUs (chapter III Installation / page 15) So : the OS may allow some difference in the processor type, but the motherboard does not. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Feb 9 08:54:06 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id IAA08210 for freebsd-smp-outgoing; Tue, 9 Feb 1999 08:54:06 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from tomservo.ee.calpoly.edu (tomservo.ee.calpoly.edu [129.65.26.123]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id IAA08202 for ; Tue, 9 Feb 1999 08:54:02 -0800 (PST) (envelope-from kwayman@tomservo.ee.calpoly.edu) Received: (from kwayman@localhost) by tomservo.ee.calpoly.edu (8.8.8/8.8.8) id IAA01149 for freebsd-smp@FreeBSD.ORG; Tue, 9 Feb 1999 08:51:38 -0800 (PST) (envelope-from kwayman) From: Kyle Wayman Message-Id: <199902091651.IAA01149@tomservo.ee.calpoly.edu> Subject: Intel Dakota MB To: freebsd-smp@FreeBSD.ORG Date: Tue, 9 Feb 1999 08:51:37 -0800 (PST) X-Mailer: ELM [version 2.4ME+ PL43 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I can't remember if anyone has discussed the Dakota MB for SMP use, and the SMP web page listing MBs that work seems a bit out of date. Does this MB work, and has anyone had problems that I should know about before trying to get SMP working on it? ----------------------------------------------------------------- = Kyle Wayman kwayman@gauss.calpoly.edu = = System Administrator office: 805-756-1390 = = EE Department, Cal Poly, SLO page: 805-542-5777 = ----------------------------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Feb 9 09:13:24 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id JAA10615 for freebsd-smp-outgoing; Tue, 9 Feb 1999 09:13:24 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from fast.cs.utah.edu (fast.cs.utah.edu [155.99.212.1]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id JAA10610 for ; Tue, 9 Feb 1999 09:13:23 -0800 (PST) (envelope-from vanmaren@fast.cs.utah.edu) Received: (from vanmaren@localhost) by fast.cs.utah.edu (8.9.1/8.9.1) id KAA17064; Tue, 9 Feb 1999 10:13:10 -0700 (MST) Date: Tue, 9 Feb 1999 10:13:10 -0700 (MST) From: Kevin Van Maren Message-Id: <199902091713.KAA17064@fast.cs.utah.edu> To: Thierry.Herbelot@alcatel.fr, smp@FreeBSD.ORG Subject: Re: Mixing P2 Types Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Well, it *should* work, but they will both have to run at the speed of the slowest processor. The only problem with that is Intel has added multiplier-locking to many of the Pentium II processors, preventing them from running if the multiplier is wrong. If they just locked the multiplier, you would have processors at different speeks (probably okay), but they won't POST if the multiplier is changed. Allegedly the multiplier isn't locked for `older' P-IIs with the locking if they are running at 66MHz bus. There are a few high-end machines that supported unequal Pentium processors ($80k+ range), and some of the Quad Pro boards could set the multiplier for the pairs of CPUs independantly, but I don't know of any Pentium II board that will do that. As for the SMP spec, that is true. However, Intel has said that they will not support mixing speeds/caches on the Xeon line, although (I believe) Compaq has said that they will. It it wasn't for the multiplier locking on the newer P-IIs, I'd tell you to get a 350 (or faster) CPU and the P2B-DS, and run the 350 at 266 until you upgraded to a second 350. The faster bus makes a bigger difference under SMP due to increased usage of the shared bus, and the 350 isn't much more than the 333. Maybe getting two 350s isn't too far out of reach? Kevin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Feb 9 09:57:12 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id JAA15588 for freebsd-smp-outgoing; Tue, 9 Feb 1999 09:57:12 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from mel.alcatel.fr (mel.alcatel.fr [212.208.74.132]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id JAA15578 for ; Tue, 9 Feb 1999 09:57:08 -0800 (PST) (envelope-from Thierry.Herbelot@alcatel.fr) Received: from aifhs2.alcatel.fr (mailhub.alcatel.fr [155.132.180.80]) by mel.alcatel.fr (ALCANET/SMTP) with ESMTP id SAA19109; Tue, 9 Feb 1999 18:56:01 +0100 Received: from lune.telspace.alcatel.fr (lune.telspace.alcatel.fr [155.132.144.65]) by aifhs2.alcatel.fr (ALCANET/SMTP2) with ESMTP id SAA01763; Tue, 9 Feb 1999 18:53:34 +0100 (MET) Received: from telss1.telspace.alcatel.fr (telss1.telspace.alcatel.fr [155.132.51.4]) by lune.telspace.alcatel.fr (8.9.1a/8.9.1) with SMTP id SAA00275; Tue, 9 Feb 1999 18:31:02 +0100 (MET) Received: from telspace.alcatel.fr (nairobi.telspace.alcatel.fr) by telss1.telspace.alcatel.fr (4.1/SMI-4.1) id AA22090; Tue, 9 Feb 99 18:39:13 +0100 Message-Id: <36C073E3.F2B82050@telspace.alcatel.fr> Date: Tue, 09 Feb 1999 18:44:03 +0100 From: HERBELOT Thierry Organization: Alcatel Telspace X-Mailer: Mozilla 4.5 [en] (X11; I; SunOS 5.5.1 sun4m) X-Accept-Language: en Mime-Version: 1.0 To: Kevin Van Maren Cc: smp@FreeBSD.ORG Subject: Re: Mixing P2 Types References: <199902091713.KAA17064@fast.cs.utah.edu> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Kevin Van Maren wrote: > [Snip] > It it wasn't for the multiplier locking on the newer P-IIs, > I'd tell you to get a 350 (or faster) CPU and the P2B-DS, and > run the 350 at 266 until you upgraded to a second 350. The > faster bus makes a bigger difference under SMP due to increased > usage of the shared bus, and the 350 isn't much more than the 333. > Maybe getting two 350s isn't too far out of reach? There is a big price difference between a P2LDS and a P2BDS, and I could find a second-hand P2-266 (then much cheaper than a P2-333 or a P2-350). (anyway, it's only for my personnal use, so utmost performance is NOT the driving factor) TfH > > Kevin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Feb 9 10:09:20 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id KAA16823 for freebsd-smp-outgoing; Tue, 9 Feb 1999 10:09:20 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from opus.cts.cwu.edu (opus.cts.cwu.edu [198.104.92.71]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id KAA16817 for ; Tue, 9 Feb 1999 10:09:17 -0800 (PST) (envelope-from skynyrd@opus.cts.cwu.edu) Received: from localhost (skynyrd@localhost) by opus.cts.cwu.edu (8.9.1/8.9.1) with SMTP id KAA03483; Tue, 9 Feb 1999 10:08:54 -0800 (PST) Date: Tue, 9 Feb 1999 10:08:54 -0800 (PST) From: Chris Timmons To: "William S. Duncanson" cc: freebsd-smp@FreeBSD.ORG, Bruce Evans Subject: Re: Problems keeping time In-Reply-To: <4.1.19990208181440.03d1d4c0@fire.starkreality.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org There used to be universal problems with SMP and timekeeping, but if I recall correctly, bde fixed them. Ever since he did, I haven't had any trouble with a dual-ppro tyan titan, nor a dual-PII/266 tyan tiger. Both are running pre-branch 3.0-current from January. So, either something recently has been rebroken, or the hardware on particular motherboards is related... -Chris To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Feb 9 10:30:50 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id KAA19115 for freebsd-smp-outgoing; Tue, 9 Feb 1999 10:30:50 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from cannon.ma.ikos.com (cannon.ma.ikos.com [137.103.105.19]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id KAA19107 for ; Tue, 9 Feb 1999 10:30:48 -0800 (PST) (envelope-from tich@cannon.ma.ikos.com) Received: from lonesome.ma.ikos.com (lonesome [137.103.105.44]) by cannon.ma.ikos.com (8.9.1/8.8.8) with ESMTP id NAA02369; Tue, 9 Feb 1999 13:31:56 -0500 (EST) From: Richard Cownie Received: (from tich@localhost) by lonesome.ma.ikos.com (8.8.8/8.8.8) id NAA24011; Tue, 9 Feb 1999 13:31:56 -0500 (EST) Date: Tue, 9 Feb 1999 13:31:56 -0500 (EST) Message-Id: <199902091831.NAA24011@lonesome.ma.ikos.com> To: Thierry.Herbelot@alcatel.fr, smp@FreeBSD.ORG Subject: Re: Mixing P2 Types Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org With the PentiumPro it was definitely true that all CPU's in an SMP system had to be identical (same speed, same silicon stepping) - one particular problem that would occur if you violated this was that the cpu's would come out of reset and start their APIC bus negotiation at different times, resulting in more than one cpu acting as the Boot CPU and attempting to run the BIOS; this would usually cause severe confusion. There may be other problems as well. Since nothing much has changed in the bus architecture, boot protocol, or indeed the CPU core between PentiumPro and Pentium-II, I believe it's probably still true that all cpu's in an SMP system must be identical. Not to say that a mixed-CPU system won't work at all - but it isn't guaranteed to work, and it probably won't work reliably. In my former incarnation at Axil Computer, I had to write the diagnostic code that would allow us to check the silicon stepping info of each CPU in an 8-way SMP NX801 to detect any mismatches. Believe me, I wouldn't have done this if it wasn't a problem ... Regards Richard Cownie (tich@ma.ikos.com) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Feb 9 11:32:14 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id LAA25823 for freebsd-smp-outgoing; Tue, 9 Feb 1999 11:32:14 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from exchange-server.modacad.com (mail.modacad.com [206.253.27.98]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id LAA25814 for ; Tue, 9 Feb 1999 11:32:09 -0800 (PST) (envelope-from MattL@ModaCAD.com) Received: by EXCHANGE_SERVER with Internet Mail Service (5.5.2448.0) id <1LGCK3W5>; Tue, 9 Feb 1999 11:31:03 -0800 Received: by EXCHANGE_SERVER with Internet Mail Service (5.5.2448.0) id <1LGCK3WS>; Tue, 9 Feb 1999 11:29:31 -0800 Message-ID: From: Matt Liu To: "'smb@freebsd.org'" Date: Tue, 9 Feb 1999 11:29:30 -0800 Importance: high X-Priority: 1 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2448.0) Content-Type: text/plain Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I am looking around to find some smp hardware programming references. Can anyone give me a pointer UNIX/NT Admin @ModaCad Inc. The Berkeley Follower To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Feb 9 11:34:06 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id LAA26147 for freebsd-smp-outgoing; Tue, 9 Feb 1999 11:34:06 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from exchange-server.modacad.com (mail.modacad.com [206.253.27.98]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id LAA26141 for ; Tue, 9 Feb 1999 11:34:02 -0800 (PST) (envelope-from MattL@ModaCAD.com) Received: by EXCHANGE_SERVER with Internet Mail Service (5.5.2448.0) id <1LGCK3XB>; Tue, 9 Feb 1999 11:32:57 -0800 Message-ID: From: Matt Liu To: "'smp@freebsd.org'" Date: Tue, 9 Feb 1999 11:32:55 -0800 Importance: high X-Priority: 1 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2448.0) Content-Type: text/plain Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I am looking around to find some smp hardware programming references. Can anyone give me a pointer UNIX/NT Admin @ModaCad Inc. The Berkeley Follower To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Feb 9 11:51:53 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id LAA27985 for freebsd-smp-outgoing; Tue, 9 Feb 1999 11:51:53 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from isbalham.ist.co.uk (isbalham.ist.co.uk [192.31.26.1]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id LAA27980 for ; Tue, 9 Feb 1999 11:51:45 -0800 (PST) (envelope-from rb@gid.co.uk) Received: from gid.co.uk (uucp@localhost) by isbalham.ist.co.uk (8.8.7/8.8.7) with UUCP id TAA04170; Tue, 9 Feb 1999 19:51:04 GMT (envelope-from rb@gid.co.uk) Received: from [194.32.164.2] by seagoon.gid.co.uk; Tue, 9 Feb 1999 19:44:47 GMT X-Sender: rb@194.32.164.1 Message-Id: In-Reply-To: References: <4.1.19990208181440.03d1d4c0@fire.starkreality.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Date: Tue, 9 Feb 1999 19:44:45 +0000 To: Chris Timmons From: Bob Bishop Subject: Re: Problems keeping time Cc: "William S. Duncanson" , freebsd-smp@FreeBSD.ORG, Bruce Evans Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hi, At 10:08 am -0800 9/2/99, Chris Timmons wrote: >There used to be universal problems with SMP and timekeeping, but if I >recall correctly, bde fixed them. Ever since he did, I haven't had any >trouble with a dual-ppro tyan titan, nor a dual-PII/266 tyan tiger. Both >are running pre-branch 3.0-current from January. So, either something >recently has been rebroken, or the hardware on particular motherboards is >related... I'm running uptodate -CURRENT, 2xPII-350 on a Gigabyte 6BXD with no problems. If it's recent breakage, it's also hardware-specific. -- Bob Bishop (0118) 977 4017 international code +44 118 rb@gid.co.uk fax (0118) 989 4254 between 0800 and 1800 UK To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Feb 9 12:34:37 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id MAA03111 for freebsd-smp-outgoing; Tue, 9 Feb 1999 12:34:37 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from ix.netcom.com (pax-ca27-01.ix.netcom.com [207.93.145.33]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id MAA03099 for ; Tue, 9 Feb 1999 12:34:34 -0800 (PST) (envelope-from tomdean@ix.netcom.com) Received: (from tomdean@localhost) by ix.netcom.com (8.9.2/8.8.8) id MAA26635; Tue, 9 Feb 1999 12:34:21 -0800 (PST) (envelope-from tomdean) Date: Tue, 9 Feb 1999 12:34:21 -0800 (PST) Message-Id: <199902092034.MAA26635@ix.netcom.com> From: Thomas Dean To: MattL@ModaCAD.com CC: smp@FreeBSD.ORG In-reply-to: (message from Matt Liu on Tue, 9 Feb 1999 11:32:55 -0800) Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org ftp http://developer.intel.com/design/pentiumii/manuals/24319001.PDF ftp http://developer.intel.com/design/pentiumii/manuals/24319201.pdf ftp http://developer.intel.com/design/pentiumii/manuals/24369101.pdf ftp http://developer.intel.com/design/pentiumii/manuals/24368901.pdf ftp http://developer.intel.com/design/pentiumii/manuals/24369001.pdf To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Feb 9 13:42:45 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id NAA11585 for freebsd-smp-outgoing; Tue, 9 Feb 1999 13:42:45 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from smtp01.primenet.com (smtp01.primenet.com [206.165.6.131]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id NAA11576 for ; Tue, 9 Feb 1999 13:42:43 -0800 (PST) (envelope-from tlambert@usr02.primenet.com) Received: (from daemon@localhost) by smtp01.primenet.com (8.8.8/8.8.8) id OAA21373; Tue, 9 Feb 1999 14:42:42 -0700 (MST) Received: from usr02.primenet.com(206.165.6.202) via SMTP by smtp01.primenet.com, id smtpd021259; Tue Feb 9 14:42:39 1999 Received: (from tlambert@localhost) by usr02.primenet.com (8.8.5/8.8.5) id OAA04536; Tue, 9 Feb 1999 14:42:23 -0700 (MST) From: Terry Lambert Message-Id: <199902092142.OAA04536@usr02.primenet.com> Subject: Re: your mail To: MattL@ModaCAD.com (Matt Liu) Date: Tue, 9 Feb 1999 21:42:22 +0000 (GMT) Cc: smp@FreeBSD.ORG In-Reply-To: from "Matt Liu" at Feb 9, 99 11:32:55 am X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > I am looking around to find some smp hardware programming references. Can > anyone give me a pointer I don't know exactly what you are asking for here. If you are asking for "how to build SMP systems", I'd suggest: Unix Systems for Modern Architectures : Symmetric Multiprocesssing and Caching for Kernel Programmers (Addison-Wesley Professional Computing Series) Curt Schimmel Addison-Wesley Pub Co ISBN: 0201633388 Scheduling and Load Balancing in Parallel and Distributed Systems Editted by: Behrooz A. Shirazi, Ali R. Hurson, Krishna M. Kavi IEEE Computer Society Press IEEE Catalog Number: EH0417-6 ISBN: 0-8186-6587-4 For more introductory texts, I'd suggest: Unix Internals : The New Frontiers Uresh Vahalia Prentice Hall ISBN: 0131019082 The Magic Garden Explained : The Internals of Unix System V Release 4 : An Open Systems Design Berny Goodheart, James Cox, John R. Mashey Prentice Hall ISBN: 0130981389 Other than that, there are a lot of texts on programming for parallel systems available from Amazon. You might also want to check out NCSTRL: NCSTRL, Networked Computer Science Technical Reports Library (pronounced "ancestral") is an international collection of computer science technical reports from CS departments and industrial and government research laboratories, made available for non-commercial and educational use. NCSTRL includes reports of UC Berkeley Computer Science Division. The Berkeley gateway is: http://sunsite.Berkeley.EDU/NCSTRL/ But basically, any University that does CS research at all will have a gateway to the database. If you want to get heavy into the math for programming, this is a good reference: Domain Decomposition : Parallel Multilevel Methods for Elliptic Partial Differential Equations Barry F. Smith, Petter E. Bjrstad, William Gropp (Contributor), Petter Bjorstad (Contributor) Cambridge Univ Pr (Short) ISBN: 052149589X In general, most of the papers will be heavy into graph theory, Clifford algebras, and/or partial differential equations. The Domain Decomposition book (above) is interesting in that the proof of Fermat's last theorem involves a proof for Taniyama-Shimura, which states that all elliptic curves have modular forms. This means that there is probably room for a lot of interesting research using modular forms for domain decomposition to increase algorithmic concurrency. There's probably a PhD in there for someone. I guess now I'm waiting to see if someone can connect modular forms with hyperbolic factoring of the product of two primes. I wonder what problem domain that would apply to... ;-). Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Feb 10 16:50:15 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id QAA20727 for freebsd-smp-outgoing; Wed, 10 Feb 1999 16:50:15 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from smtp01.primenet.com (smtp01.primenet.com [206.165.6.131]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id QAA20715 for ; Wed, 10 Feb 1999 16:50:09 -0800 (PST) (envelope-from tlambert@usr08.primenet.com) Received: (from daemon@localhost) by smtp01.primenet.com (8.8.8/8.8.8) id RAA03013; Wed, 10 Feb 1999 17:50:01 -0700 (MST) Received: from usr08.primenet.com(206.165.6.208) via SMTP by smtp01.primenet.com, id smtpd002808; Wed Feb 10 17:49:53 1999 Received: (from tlambert@localhost) by usr08.primenet.com (8.8.5/8.8.5) id RAA26235; Wed, 10 Feb 1999 17:49:26 -0700 (MST) From: Terry Lambert Message-Id: <199902110049.RAA26235@usr08.primenet.com> Subject: Re: regarding the book:scheduling and load balancing To: mattl@modacad.com (mattl) Date: Thu, 11 Feb 1999 00:49:25 +0000 (GMT) Cc: tlambert@primenet.com, smp@FreeBSD.ORG In-Reply-To: <36C21DD0.90EDCC1F@modacad.com> from "mattl" at Feb 10, 99 04:01:20 pm X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org After bothering to type this in, I'm going to Cc my reply to the SMP list for everyone's edification (I have had two other similar inquiries). Hope you don't mind, but I'm pretty sure there's nothing you said that's non-disclosable, since you pretty much duplicate the other requests, verbatim. > I found the book(0-8186-6587-4) in amazon, but there is no table of > content nor any thing about the author's background. I don't know if i > should buy or not. Is this book about smp or distributed(networked) > parallel system? This book is published at 1995, kind of old. I don't > know if the idea in there are any new? These authors does look famous > professors and is titled editors in amazon, which make me worried. This book is a compendium of all IEEE papers on the topic to 1995. As such, it's 3 years out of date, and at least 9 years ahead of FreeBSD and Linux. Yes, there are newer references, though not many, if you subscribe to the ACM, Usenix, and IEEE publications themselves, or if you go through NCSTREL (some of the papers in the book are available online). I would suggest looking for them online; you will find perhaps 15-20% of them. Again, there's a *massive* amount of reference material in NCSTREL on this topic. It doesn't meet your "a book" requirement, but it's about 12 years ahead of FreeBSD or Linux. Yet more proof that you have to have a strange and/or unpronouncible name, or at least have someone who does on the paper with you, to be published in Computer Science... Here's the Table Of Contents: -------------------------------------------------------------------------- Scheduling and Load Balancing in Parallel and Distributed Systems ISBN: 0-8186-6587-4 -------------------------------------------------------------------------- Table of Contents -------------------------------------------------------------------------- Preface Acknowledgements CHAPTER 1: INTRODUCTION TO SCHEDULING AND LOAD BALANCING A Taxonomy of Scheduling in General-Purpose Distributed Computing Systems - T.L. Casavan and J.G. Kuhl Multiprocessor Scheduling with the Aid of Network Fow Algorithms - H.S. Stone Load Distributing for Locally Distributed Systems - N.G. Shivaratri, P. Krueger, M. Singhal CHAPTER 2: STATIC SCHEDULING Analysis and Evaluation of Heuristic Methods for Static Task Scheduling - B. Shirazi, M. Wang, G. Pathak Compile-time Partitioning and Scheduling of Parallel Programs - V. Sarkar, J. Hennessy Guided Self-Scheduling: A Practical Scheduling Scheme for Parallel Supercomputers - C.D. Polychronopoulos, D.J. Kuck Multiprocessor Scheduling with Communication Delays - B. Veltman, B.J. Lageweg, J.K. Lenstra Heuristic Algorithms for Task Assignment in Distributed Systems - V.M. Lo Allocating Modules to Processors in a Distributed System - D. Fernandez-Baca Compile-Time Scheduling and Assignment of Data-Flow Program Graphs with Data-Dependent Iteration - S. Ha, E.A. Lee A Program Allocation Scheme for Data Flow Computers - A.R. Hurson et. al. CHAPTER 3: TASK GRANULARITY AND PARTITIONING On the Granularity and Clustering of Directed Acyclic Task Graphs - A. Gerasoulis, T. Yang The Effects of Problem Partitioning, Allocation, and Granularity on the Performance of Multiple-Processor Systems - Z. Cvetanovic Grain Size Determination for Parallel Processing - B. Kruatrachue, T. Lewis Lazy Task Creation: A Technique for Increasing the Granularity of Parallel Programs - E. Mohr, D.A. Kranz, R.H. Halstead, Jr. CHAPTER 4: SCHEDULING TOOLS PARSA: A Parallel Program Developement Tool - B. Shirazi et. al. The TOPSYS Architecture - T. Bemmerl Parallax: A Tool for Parallel Program Scheduling - T. Lewis, H. El-Rewini Parafrase-2: An Environment for Paralleling, Partitioning, Synchronizing, and Scheduling Programs on Multiprocessors - C.D. Polychronopoulos et. al. Mapping Function-Parallel Programs with the Prep.-P Automatic Mapping Preprocessor - F. Berman, B. Stramm OREGAMI: Tools for Mapping Parallel Computations to Parallel Architectures - V.M. Lo et. al. CHAPTER 5: LOAD BALANCING Load Sharing in Distributed Systems - Y.-T. Wang, R.J.T. Morris The Probability of Load Balancing Success in a Homogeneous Network - C.G. Rommel Adaptive Load Sharing in Homogeneous Distributed Systems - D.L. Eager, E.D. Lazowshka, J. Zahorjan Imbedding Gradient Estimators in Load Balancing Algorithms - S. Pulidas, D. Towsley, J.A. Stankovic The Diverse Objectives of Distributed Scheduling Policies - P. Krueger, M. Livny Effects of Response and Stability on Scheduling in Distributed Computing Systems - T.L. Casavant, J.G. Kuhl Condor - A Hunter of Idle Workstations - J.M. Litzkow, M. Livny, M.W. Mutka GAMMON: A Load Balancing Strategy for Local Computer Systems with Multiaccess Networks - K.M. Baumgartner, B.W. Wah The Stealth Distributed Scheduler - P. Krueger, R. Chawla CHAPTER 6: MECHANISMS FOR PROCESS MIGRATION Design Issues of Process Migration Facilities in Distributed Systems - M.R. Eskicioglu Heterogeneous Process Migration by Recompilation - M.M. Theimer, B. Hayes Attacking the Process Migration Bottleneck - E.R. Zayas Designing a Process Migration Facility - Y. Artsy, R. Finkel Process Migration in DEMOS/MP - M.L. Powell, B.P. Miller Preemptable Remote Execution Facilities for the V-System - M.M. Theimer, K.A. Lantz, D.R. Cheriton CHAPTER 7: LOAD INDICES Predictability of Process Resource Usage: A Measurement-Based Study on UNIX - M.V. Devarakonda, R.K. Iyer An Empirical Investigation of Load Indices for Load Balancing Applications - D. Ferrari, S. Zhou The Influence of Different Workload Descriptions on a Heuristic Load Balancing Scheme - T. Kunz About the Authors -------------------------------------------------------------------------- Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Feb 11 20:26:04 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id UAA16676 for freebsd-smp-outgoing; Thu, 11 Feb 1999 20:26:04 -0800 (PST) (envelope-from owner-freebsd-smp@FreeBSD.ORG) Received: from hotmail.com (law-f157.hotmail.com [209.185.131.220]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id UAA16634 for ; Thu, 11 Feb 1999 20:25:57 -0800 (PST) (envelope-from lao777@hotmail.com) Received: (qmail 27344 invoked by uid 0); 12 Feb 1999 04:09:40 -0000 Message-ID: <19990212040940.27343.qmail@hotmail.com> Received: from 206.105.232.61 by www.hotmail.com with HTTP; Thu, 11 Feb 1999 20:09:40 PST X-Originating-IP: [206.105.232.61] From: "manuel soto" To: grail@python.org, freebsd-smp@FreeBSD.ORG, nns-users@halcyon.com, freebsd-mozilla@FreeBSD.ORG, ifrt@ala.org, philosophy@freelance.com, streamingaudio@list.findmail.com, tiff@relay.engr.sgi.com, svlug-announce@svlug.org Subject: Hello!!! Date: Thu, 11 Feb 1999 20:09:40 PST Mime-Version: 1.0 Content-type: text/plain Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org http://www.lanzadera.com/caricaturas http://dinero.homepage.nu ______________________________________________________ Get Your Private, Free Email at http://www.hotmail.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message