From owner-freebsd-smp Sun Jun 9 06:17:15 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id GAA13056 for smp-outgoing; Sun, 9 Jun 1996 06:17:15 -0700 (PDT) Received: from TYO2.gate.nec.co.jp (TYO2.gate.nec.co.jp [202.32.8.10]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id GAA13030 for ; Sun, 9 Jun 1996 06:17:12 -0700 (PDT) Received: from mailsv.nec.co.jp ([133.200.254.203]) by TYO2.gate.nec.co.jp (8.7.5+2.6Wbeta6/3.3Wb-NEC-TYO2) with ESMTP id WAA21608 for ; Sun, 9 Jun 1996 22:17:10 +0900 (JST) Received: from king.sdd3.mt.nec.co.jp (king.sdd3.mt.nec.co.jp [133.201.177.179]) by mailsv.nec.co.jp (8.7.5+2.6Wbeta6/3.4W-96052015) with SMTP id WAA27395 for ; Sun, 9 Jun 1996 22:17:09 +0900 (JST) Received: from atlas.sdd3.mt.nec.co.jp by king.sdd3.mt.nec.co.jp (8.6.9/6.4J.6-sdd3_mx) id WAA18251; Sun, 9 Jun 1996 22:17:14 +0900 Received: by atlas.sdd3.mt.nec.co.jp (5.67+1.6W/6.4J.6-sdd3-slave) id AA06406; Sun, 9 Jun 96 22:16:07 JST Message-Id: <9606091316.AA06406@atlas.sdd3.mt.nec.co.jp> From: Shigeji Ishikawa To: smp@freebsd.org Subject: subscribe Reply-To: Shigeji Ishikawa X-Mailer: Mew version 1.05 on Emacs 19.28.1, Mule 2.3 X-Fingerprint: 80 CB 5C 78 6D DA 39 3A DE C8 ED F5 55 23 AE 56 Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Date: Sun, 09 Jun 1996 22:16:05 +0900 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk subscribe From owner-freebsd-smp Sun Jun 9 13:02:15 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA14963 for smp-outgoing; Sun, 9 Jun 1996 13:02:15 -0700 (PDT) Received: from phaeton.artisoft.com (phaeton.Artisoft.COM [198.17.250.211]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id NAA14952; Sun, 9 Jun 1996 13:02:11 -0700 (PDT) Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id NAA01419; Sun, 9 Jun 1996 13:01:56 -0700 From: Terry Lambert Message-Id: <199606092001.NAA01419@phaeton.artisoft.com> Subject: Re: does freebsd support SMP? To: phk@FreeBSD.ORG (Poul-Henning Kamp) Date: Sun, 9 Jun 1996 13:01:55 -0700 (MST) Cc: terry@lambert.org, nathan@netrail.net, freebsd-current@FreeBSD.ORG, freebsd-smp@FreeBSD.ORG In-Reply-To: <968.834348207@critter.tfs.com> from "Poul-Henning Kamp" at Jun 9, 96 12:23:27 pm X-Mailer: ELM [version 2.4 PL24] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > >> DOes freebsd supoort SMP? > > > >Yes. There is a working SMP /usr/src/sys code tree that can be SUP'ed > >or CTM'ed. You do a normal CVS checkout, then you add: > > > >options SMP # enable SMP > >options NCPU=2 # or whatever max you want > > > >To your normal -current config file, config, makedepend, make, and > >install the SMP kernel. Then rebbot. You are running SMP. > > Well, you clearly havn't tried it Terry :-) > > Boot single user and then: > sysctl -w kern.smp_active=2 > to start the second CPU... That didn't used to be in there... clearly, I haven't tried it recently. 8-). Thanks for telling me, though, since I just pulled down the sources yesterday, and the only reason I'm in today is to play with it. I would have figured it out eventually. 4 hours or so. 8-) 8-). It seems that smp_active wants to be cpu.active, and wants to default to 1 (not zero). Actually, looking at the code, the values are only allowed to be 0 or 2 -- and it looks like 2 will actually start 'n' (the loop in mp_begin in locore.s). The locking code (mplock.s) only checks for non-zero. The code in swtch.s -- is it ever hit in the smp_active zero case? It seems to be an error to have the old idle loop present at all... am I missing something in the UP case, where the kernel is still compiled with SMP set? Also, in the idle spin loop, re: processor power consumption and heating: any chance of integrating a Linux-style "halt instruction" test and using it in the case that it works? Anyway, the reason I went looking was for a kernel variable like cpu.count for number of available cpu's so I could put it in my rc file instead of booting single-user: CPUCOUNT=`sysctl -n kern.cpu.count` if test "$CPUCOUNT" != "1" then echo -n "Starting auxillary processors..." sysctl -w kern.cpu.active=$CPUCOUNT echo "$(CPUCOUNT) PROCESSORS ACTIVE" fi This code could go into the main line rc file with no adverse affect, assuming the cpu.count wasn't conditional on being compiled with the SMP flag (the active could be conditional, since the count will never be non-1 in the UP/non-SMP options case) Who is actively hacking where in the assembly code? This seems like an easy fix that wouldn't drag me down into dealing with page tables. ;-). Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. From owner-freebsd-smp Sun Jun 9 20:37:47 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id UAA16092 for smp-outgoing; Sun, 9 Jun 1996 20:37:47 -0700 (PDT) Received: from mail (mail.bcpl.lib.md.us [204.255.212.10]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id UAA16043 for ; Sun, 9 Jun 1996 20:37:42 -0700 (PDT) Received: from localhost by mail (5.0/SMI-SVR4) id AA23648; Sun, 9 Jun 1996 23:38:12 +0500 Date: Sun, 9 Jun 1996 23:38:11 -0400 (EDT) From: "Paul H." X-Sender: broome@mail To: FreeBSD-SMP@FreeBSD.org Subject: Re: does freebsd support SMP? In-Reply-To: <199606092001.NAA01419@phaeton.artisoft.com> Message-Id: Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Let me take advantage of this short pause in the discussion. I'd like to try out FreeBSD on an SMP system but to do so I'll have to first buy some hardware. Can anyone give me suggestions on good, reliable, fast mainboard/processor combinations? (Also, is this mailing list archived? I could find any archive in the usual places.) My limited experience installing FreeBSD2.1 has been quite positive thus far - first with a generic 386 system, then with a P75 on an ASUS mainboard. The fact that the installations were easy for me means that somebody else put in some hard work. Of course I'll pass along anything I learn that might be useful. -Paul I can also be reached at broome@msiadmin.cit.cornell.edu From owner-freebsd-smp Sun Jun 9 22:41:46 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id WAA07532 for smp-outgoing; Sun, 9 Jun 1996 22:41:46 -0700 (PDT) Received: from spinner.DIALix.COM (spinner.DIALix.COM [192.203.228.67]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id WAA07420; Sun, 9 Jun 1996 22:41:36 -0700 (PDT) Received: from spinner.DIALix.COM (localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.7.5/8.7.3) with ESMTP id NAA02800; Mon, 10 Jun 1996 13:40:00 +0800 (WST) Message-Id: <199606100540.NAA02800@spinner.DIALix.COM> To: Terry Lambert cc: phk@FreeBSD.ORG (Poul-Henning Kamp), nathan@netrail.net, freebsd-current@FreeBSD.ORG, freebsd-smp@FreeBSD.ORG Subject: Re: does freebsd support SMP? In-reply-to: Your message of "Sun, 09 Jun 1996 13:01:55 MST." <199606092001.NAA01419@phaeton.artisoft.com> Date: Mon, 10 Jun 1996 13:39:59 +0800 From: Peter Wemm Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk >> >> DOes freebsd supoort SMP? >> > >> >Yes. There is a working SMP /usr/src/sys code tree that can be SUP'ed >> >or CTM'ed. You do a normal CVS checkout, then you add: >> > >> >options SMP # enable SMP >> >options NCPU=2 # or whatever max you want >> > >> >To your normal -current config file, config, makedepend, make, and >> >install the SMP kernel. Then rebbot. You are running SMP. >> >> Well, you clearly havn't tried it Terry :-) >> >> Boot single user and then: >> sysctl -w kern.smp_active=2 >> to start the second CPU... > > >That didn't used to be in there... clearly, I haven't tried it >recently. 8-). > >Thanks for telling me, though, since I just pulled down the sources >yesterday, and the only reason I'm in today is to play with it. I >would have figured it out eventually. 4 hours or so. 8-) 8-). > >It seems that smp_active wants to be cpu.active, and wants to >default to 1 (not zero). Actually, no, it's just a hack so that we can progressively unlock the cpu's and trace various stages of booting them. >The locking code (mplock.s) only checks for non-zero. Yes.. smp_active=1 means you can get the second cpu up in protected mode and running virtual, but not scheduling yet. >The code in swtch.s -- is it ever hit in the smp_active zero >case? It seems to be an error to have the old idle loop >present at all... am I missing something in the UP case, where >the kernel is still compiled with SMP set? > >Also, in the idle spin loop, re: processor power consumption and >heating: any chance of integrating a Linux-style "halt instruction" >test and using it in the case that it works? Yes, this is a 'work-in-progress'. The only reason it's spinning at all at the moment is because a) it works for the moment, and b) we've been busy on other things. A lack of documentation doesn't help, we have just about solved that problem, all we need is detail on the IO-APIC... >Who is actively hacking where in the assembly code? This seems like >an easy fix that wouldn't drag me down into dealing with page tables. >;-). I've got a whole mess of uncommitted stuff yet that I've not quite finished and debugged yet. I've mentioned some of this to phk so far.. - generic apic IPI message sender, eg: to send (say) an int 0x20 to a processor to snap it out of it's hlt loop and schedule a process. This also makes the boot more robust as there are are timeouts now - almost all special case code removed from locore.s and pmap.c. Instead of booting the second processor on _IdlePTD, and using the idle process's stacks and ptd's, a PTD is cloned from _idlePTD, and a stack and pcb allocated and initialised. The clone PTD has the temporary 4MB V==P mapping at 0 so that the kernel can turn on paging without getting killed by the new pipeline flushes on the P6. Since it has it's own pcb, it now has it's own mplock nesting count. This means that we can ressurect a real idle loop with a hlt. - sysctl string with handler function, rather than just an int variable. This means that simple commands can be written. (eg: sysctl -w cpu.smp=bootall) - Simple parsing of the MP config block, although I dont use it yet. - Support for 'N' cpus. Since all per-cpu state is allocated after boot now, booting the processors is somewhat simpler... int cpu_alive[NCPU]; /* cpu touches this when it wakes up, then waits */ ..... my_id = cpunumber(); for (i = 0; i < NCPU; i++) { if (i == my_id) continue; smp_cpu_startup(i); /* sleep a short while */ if (cpu_alive[i]) { smp_alloc(i); /* allocates and sets up ptd, stack, etc */ smp_cpu_unlock(i); /* releases it from lock, it sets up it's vm etc */ } else { /* in case the cpu is alive but didn't survive boot, halt it */ smp_cpu_halt(i); /* does an init ipi to make the cpu execute a cli;hlt*/ } } This is pretty trivial, and does not cope with apic id's outside 0..NCPU. I'd like to parse the MP block to find all the cpus, and reprogram the apic id's of the ones outside the range to make them sequential if needed. This means booting all cpus, keeping them locked, calculating a new mapping, leaving the boot cpu alone, letting all cpus reset their apic_id at once, then letting the boot cpu figure out the mess. - (on a sidetrack) I'm trying to eliminate the user area to allow vmspace sharing. This is somewhat complicated by each cpu needing a tss pointer in the gdt, so it may force dynamic allocation of the gdt. (or, reserve NCPU slots and initialise them manually rather than statically. For now, I've just left a 31 entry "hole" since the #if's were a nightmare to reserve the correct amount in the static structure). Once this is done, we can have real threaded programs executing multiple threads on both cpus at once. - Somebody mentioned NCPU vs. MAXCPU.. I use NCPU as "the maximum number of cpus that we can support", it's little more than a size of a couple of int arrays. It could quite reasonably be hardwired to a default of 32. - I'm sure I've forgotten something.. :-) Cheers, -Peter From owner-freebsd-smp Mon Jun 10 06:48:16 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id GAA13158 for smp-outgoing; Mon, 10 Jun 1996 06:48:16 -0700 (PDT) Received: from thuvia.qstools.com (thuvia.qstools.com [205.179.159.64]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id GAA13152 for ; Mon, 10 Jun 1996 06:48:10 -0700 (PDT) Received: from localhost.qstools.com (localhost.qstools.com [127.0.0.1]) by thuvia.qstools.com (8.6.12/8.6.12) with SMTP id GAA12586; Mon, 10 Jun 1996 06:48:16 -0700 Message-Id: <199606101348.GAA12586@thuvia.qstools.com> X-Authentication-Warning: thuvia.qstools.com: Host localhost.qstools.com didn't use HELO protocol To: "Paul H." CC: FreeBSD-SMP@FreeBSD.org Subject: Re: does freebsd support SMP? In-reply-to: Your message of "Sun, 09 Jun 1996 23:38:11 EDT." Date: Mon, 10 Jun 1996 06:48:16 -0700 From: Bill Cox Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Well, right now, I would not recommend the AMI Titan II motherboard, although it can hold two Pentia and appears to use the Intel-standard APIC communications scheme. I bought one back in mid-December and added the second Pentium just last week. I've been running Windows NT beta 4.0 on the board for a revenue-generating project while SMP is being developed. After adding and enabling the second Pentium, the board won't even consistently recognize its 64Mb of memory. But disable the second Pentium and it's rock-solid... I'd recommend the ASUS, sight unseen. From owner-freebsd-smp Mon Jun 10 08:55:16 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA20417 for smp-outgoing; Mon, 10 Jun 1996 08:55:16 -0700 (PDT) Received: from critter.tfs.com ([140.145.16.108]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id IAA20410; Mon, 10 Jun 1996 08:55:14 -0700 (PDT) Received: from critter.tfs.com (localhost [127.0.0.1]) by critter.tfs.com (8.7.5/8.7.3) with ESMTP id IAA02135; Mon, 10 Jun 1996 08:54:44 -0700 (PDT) To: "Paul H." cc: FreeBSD-SMP@FreeBSD.org Subject: Re: does freebsd support SMP? In-reply-to: Your message of "Sun, 09 Jun 1996 23:38:11 EDT." Date: Mon, 10 Jun 1996 08:54:43 -0700 Message-ID: <2133.834422083@critter.tfs.com> From: Poul-Henning Kamp Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk So far we have yet to find some SMP stuff that we couldn't run on. Take your pick! Neptune chipsets are quite slow. Triton-II havn't been tried yet I think, but look promising. P6+Orion works fine too. -- Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. whois: [PHK] | phk@ref.tfs.com TRW Financial Systems, Inc. Future will arrive by its own means, progress not so. From owner-freebsd-smp Mon Jun 10 12:16:53 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA05973 for smp-outgoing; Mon, 10 Jun 1996 12:16:53 -0700 (PDT) Received: from phaeton.artisoft.com (phaeton.Artisoft.COM [198.17.250.211]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id MAA05968; Mon, 10 Jun 1996 12:16:51 -0700 (PDT) Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id MAA04084; Mon, 10 Jun 1996 12:15:53 -0700 From: Terry Lambert Message-Id: <199606101915.MAA04084@phaeton.artisoft.com> Subject: Re: does freebsd support SMP? To: peter@spinner.dialix.com (Peter Wemm) Date: Mon, 10 Jun 1996 12:15:53 -0700 (MST) Cc: terry@lambert.org, phk@FreeBSD.org, nathan@netrail.net, freebsd-current@FreeBSD.org, freebsd-smp@FreeBSD.org In-Reply-To: <199606100540.NAA02800@spinner.DIALix.COM> from "Peter Wemm" at Jun 10, 96 01:39:59 pm X-Mailer: ELM [version 2.4 PL24] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > >The locking code (mplock.s) only checks for non-zero. > > Yes.. smp_active=1 means you can get the second cpu up in protected mode > and running virtual, but not scheduling yet. ??? Not scheduling? I thought it was scheduling? Should I go back to my October 1994 kernel + hacks + Jack's patches + my patches to be able to work on kernel reentrancy at this time? I've been hacking FS code in this envirnment for some time already, without a lot of problems. When are you planning on committing your changes for APIC messaging, etc.? What can I do to help get scheduling up? I need multiple kernel entrances to test conflict resoloution and transitive closure calculation over the lock hierarchy code I've been pounding on... is the page containing the shared mutex tagged non-cacheable? Is there an allocation method for getting more of these pages, if I need them? Re: the NCPU vs. MAXCPU ... the reason I made a distinction is that you may not want all available CPU's active (I can only think of testing as wanting this, but it could happen). Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. From owner-freebsd-smp Mon Jun 10 21:42:22 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id VAA22266 for smp-outgoing; Mon, 10 Jun 1996 21:42:22 -0700 (PDT) Received: from fear.hungry.com (root@fear.hungry.com [205.158.21.135]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id VAA22261 for ; Mon, 10 Jun 1996 21:42:19 -0700 (PDT) Received: from localhost (tspencer@localhost [127.0.0.1]) by fear.hungry.com (8.7.5/8.6.12) with SMTP id VAA24747 for ; Mon, 10 Jun 1996 21:42:18 -0700 (PDT) Message-Id: <199606110442.VAA24747@fear.hungry.com> X-Authentication-Warning: fear.hungry.com: Host tspencer@localhost [127.0.0.1] didn't use HELO protocol To: freebsd-smp@freebsd.org Subject: SMP kernel source? Date: Mon, 10 Jun 1996 21:42:18 -0700 From: Tim Spencer Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hey there! I've got a 2 cpu p133 sitting here, and I'd like to get freebsd going on it... Where can I get the latest SMP source? Any tips anybody would care to give me to save me hassles? Hope there isn't a FAQ somewhere that I missed. Any info that you guys care to give would be highly appreciated... Thanks, and have fun!! -tspencer From owner-freebsd-smp Mon Jun 10 21:51:59 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id VAA22984 for smp-outgoing; Mon, 10 Jun 1996 21:51:59 -0700 (PDT) Received: from MindBender.HeadCandy.com (root@[199.238.225.168]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id VAA22975; Mon, 10 Jun 1996 21:51:55 -0700 (PDT) Received: from localhost.HeadCandy.com (michaelv@localhost.HeadCandy.com [127.0.0.1]) by MindBender.HeadCandy.com (8.7.5/8.6.9) with SMTP id VAA05982; Mon, 10 Jun 1996 21:49:40 -0700 (PDT) Message-Id: <199606110449.VAA05982@MindBender.HeadCandy.com> X-Authentication-Warning: MindBender.HeadCandy.com: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: Terry Lambert cc: peter@spinner.dialix.com (Peter Wemm), phk@freebsd.org, nathan@netrail.net, freebsd-current@freebsd.org, freebsd-smp@freebsd.org Subject: Re: does freebsd support SMP? In-reply-to: Your message of Mon, 10 Jun 96 12:15:53 -0700. <199606101915.MAA04084@phaeton.artisoft.com> Date: Mon, 10 Jun 1996 21:49:36 -0700 From: "Michael L. VanLoon -- HeadCandy.com" Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >Re: the NCPU vs. MAXCPU ... the reason I made a distinction is that >you may not want all available CPU's active (I can only think of >testing as wanting this, but it could happen). Maybe you'd want to reserve one of them for a game of Descent... ;-) ----------------------------------------------------------------------------- Michael L. VanLoon michaelv@HeadCandy.com --< Free your mind and your machine -- NetBSD free un*x >-- NetBSD working ports: 386+PC, Mac 68k, Amiga, Atari 68k, HP300, Sun3, Sun4/4c/4m, DEC MIPS, DEC Alpha, PC532, VAX, MVME68k, arm32... NetBSD ports in progress: PICA, others... Roll your own Internet access -- Seattle People's Internet cooperative. If you're in the Seattle area, ask me how. ----------------------------------------------------------------------------- From owner-freebsd-smp Fri Jun 14 02:04:42 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id CAA19640 for smp-outgoing; Fri, 14 Jun 1996 02:04:42 -0700 (PDT) Received: from critter.tfs.com ([140.145.16.108]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id CAA19620; Fri, 14 Jun 1996 02:04:37 -0700 (PDT) Received: from critter.tfs.com (localhost [127.0.0.1]) by critter.tfs.com (8.7.5/8.7.3) with ESMTP id CAA04143; Fri, 14 Jun 1996 02:03:46 -0700 (PDT) To: current@freebsd.org, smp@freebsd.org Subject: a data-point for SMP Reply-to: phk@freebsd.org Date: Fri, 14 Jun 1996 02:03:43 -0700 Message-ID: <4141.834743023@critter.tfs.com> From: Poul-Henning Kamp Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk HP P6/250 x 2, 64M ram, 1 scsi disk on ahc0. make -j8 COPTFLAGS= -O2 -pipe time to make GENERIC kernel: 280.4u 53.0s 2:53.42 192.3% 484+645k 8+264io 0pf+0w ^^^^^^ not at all bad :-) -- Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. whois: [PHK] | phk@ref.tfs.com TRW Financial Systems, Inc. Future will arrive by its own means, progress not so. From owner-freebsd-smp Fri Jun 14 02:33:51 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id CAA24761 for smp-outgoing; Fri, 14 Jun 1996 02:33:51 -0700 (PDT) Received: from al.imforei.apana.org.au (al.imforei.apana.org.au [202.12.89.41]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id CAA24747 for ; Fri, 14 Jun 1996 02:33:43 -0700 (PDT) Received: (from pjchilds@localhost) by al.imforei.apana.org.au (8.7.5/8.7.3) id TAA00150 for freebsd-smp@freebsd.org; Fri, 14 Jun 1996 19:03:20 +0930 (CST) Date: Fri, 14 Jun 1996 19:03:20 +0930 (CST) From: Peter Childs Message-Id: <199606140933.TAA00150@al.imforei.apana.org.au> To: freebsd-smp@freebsd.org Subject: Re: a data-point for SMP Newsgroups: apana.sa.lists.freebsd-smp X-Newsreader: TIN [version 1.2 PL2] Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk In article <4praes$spq@al.imforei.apana.org.au> you wrote: : HP P6/250 x 2, 64M ram, 1 scsi disk on ahc0. : make -j8 : COPTFLAGS= -O2 -pipe : time to make GENERIC kernel: : 280.4u 53.0s 2:53.42 192.3% 484+645k 8+264io 0pf+0w : ^^^^^^ : not at all bad :-) Hmmm... time to put my HP calculator in the bin me-thinks... Does anyone have any feel for performance vs. value in high end PC's like these? In Australia it is possible to purchase two P5100's for the cost of a P133... would this provide a much better deal? What about 4 chip machines? How does the system scale over multiple processors? Also would say a dual pentium machine be of higher performance than a P6? Peter, still using that 486dx33, Childs -- Peter Childs --- http://www.imforei.apana.org.au/~pjchilds Active APANA SA Member --- Author PopWatch + Inf-HTML Email: pjchilds@imforei.apana.org.au Fax: 61-8-82784742 From owner-freebsd-smp Fri Jun 14 02:53:45 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id CAA28282 for smp-outgoing; Fri, 14 Jun 1996 02:53:45 -0700 (PDT) Received: from critter.tfs.com ([140.145.16.108]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id CAA28274; Fri, 14 Jun 1996 02:53:41 -0700 (PDT) Received: from critter.tfs.com (localhost [127.0.0.1]) by critter.tfs.com (8.7.5/8.7.3) with ESMTP id CAA04253; Fri, 14 Jun 1996 02:52:48 -0700 (PDT) To: Peter Childs cc: freebsd-smp@freebsd.org Subject: Re: a data-point for SMP In-reply-to: Your message of "Fri, 14 Jun 1996 19:03:20 +0930." <199606140933.TAA00150@al.imforei.apana.org.au> Date: Fri, 14 Jun 1996 02:52:47 -0700 Message-ID: <4251.834745967@critter.tfs.com> From: Poul-Henning Kamp Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Lots of good questions, no good answers at this time, sorry. -- Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. whois: [PHK] | phk@ref.tfs.com TRW Financial Systems, Inc. Future will arrive by its own means, progress not so. From owner-freebsd-smp Fri Jun 14 02:55:39 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id CAA28642 for smp-outgoing; Fri, 14 Jun 1996 02:55:39 -0700 (PDT) Received: (from phk@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id CAA28630 for freebsd-smp; Fri, 14 Jun 1996 02:55:38 -0700 (PDT) Date: Fri, 14 Jun 1996 02:55:38 -0700 (PDT) From: Poul-Henning Kamp Message-Id: <199606140955.CAA28630@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/i386 machdep.c mplock.s pmap.c swtch.s sys/i386/isa icu.s vector.s sys/kern init_main.c kern_synch.c sys/i386/include smpasm.h spl.h sys/vm vm_glue.c Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk phk 96/06/14 02:55:35 Modified: i386/i386 machdep.c mplock.s pmap.c swtch.s i386/include smpasm.h spl.h i386/isa icu.s vector.s kern init_main.c kern_synch.c vm vm_glue.c Log: Make the GENERIC non-SMP kernel compile again. Havn't tried to boot it. Revision Changes Path 1.19 +2 -2 sys/i386/i386/machdep.c 1.11 +1 -8 sys/i386/i386/mplock.s 1.16 +0 -4 sys/i386/i386/pmap.c 1.19 +4 -8 sys/i386/i386/swtch.s 1.2 +17 -12 sys/i386/include/smpasm.h 1.3 +4 -5 sys/i386/include/spl.h 1.9 +0 -1 sys/i386/isa/icu.s 1.11 +2 -7 sys/i386/isa/vector.s 1.16 +0 -1 sys/kern/init_main.c 1.7 +4 -2 sys/kern/kern_synch.c 1.8 +0 -1 sys/vm/vm_glue.c From owner-freebsd-smp Fri Jun 14 03:07:25 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id DAA01142 for smp-outgoing; Fri, 14 Jun 1996 03:07:25 -0700 (PDT) Received: from al.imforei.apana.org.au (al.imforei.apana.org.au [202.12.89.41]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id DAA01114 for ; Fri, 14 Jun 1996 03:07:18 -0700 (PDT) Received: (from pjchilds@localhost) by al.imforei.apana.org.au (8.7.5/8.7.3) id TAA01093 for freebsd-smp@freebsd.org; Fri, 14 Jun 1996 19:37:14 +0930 (CST) Date: Fri, 14 Jun 1996 19:37:14 +0930 (CST) From: Peter Childs Message-Id: <199606141007.TAA01093@al.imforei.apana.org.au> To: freebsd-smp@freebsd.org Subject: Re: a data-point for SMP Newsgroups: apana.sa.lists.freebsd-smp X-Newsreader: TIN [version 1.2 PL2] Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk In article <4prcuk$nq@al.imforei.apana.org.au> you wrote: : Lots of good questions, no good answers at this time, sorry. Guess I'll just have to buy one of each and give it a whirl :) Peter -- Peter Childs --- http://www.imforei.apana.org.au/~pjchilds Active APANA SA Member --- Author PopWatch + Inf-HTML Email: pjchilds@imforei.apana.org.au Fax: 61-8-82784742 From owner-freebsd-smp Fri Jun 14 04:16:15 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id EAA08968 for smp-outgoing; Fri, 14 Jun 1996 04:16:15 -0700 (PDT) Received: (from phk@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id EAA08960 for freebsd-smp; Fri, 14 Jun 1996 04:16:14 -0700 (PDT) Date: Fri, 14 Jun 1996 04:16:14 -0700 (PDT) From: Poul-Henning Kamp Message-Id: <199606141116.EAA08960@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/include smpasm.h Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk phk 96/06/14 04:16:14 Modified: i386/include smpasm.h Log: Fix a botch I made in last commit. Now both SMP and !SMP should compile. Revision Changes Path 1.3 +14 -17 sys/i386/include/smpasm.h