From owner-freebsd-smp Sun Nov 10 09:33:50 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA20664 for smp-outgoing; Sun, 10 Nov 1996 09:33:50 -0800 (PST) Received: from spinner.DIALix.COM (root@spinner.DIALix.COM [192.203.228.67]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA20658; Sun, 10 Nov 1996 09:33:44 -0800 (PST) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.2/8.8.2) with ESMTP id BAA15722; Mon, 11 Nov 1996 01:33:36 +0800 (WST) Message-Id: <199611101733.BAA15722@spinner.DIALix.COM> X-Mailer: exmh version 1.6.9 8/22/96 To: Bruce Evans cc: smp@freefall.freebsd.org, nate@freefall.freebsd.org Subject: Re: cvs commit: src/sys/i386/isa syscons.c syscons.h In-reply-to: Your message of "Mon, 11 Nov 1996 04:14:53 +1100." <199611101714.EAA12879@godzilla.zeta.org.au> Date: Mon, 11 Nov 1996 01:33:35 +0800 From: Peter Wemm Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Bruce Evans wrote: > I'm going to replace the i586 optimized copying options (including the > one for copyin/copyout that went away) by negative-logic npx flags. > This is mainly for 2.2. I don't trust copying through the FPU to work > on i586 clones. We currently have to #ifdef out the i586_bcopy on the SMP code which does not yet understand the fact that there is more than one FPU involved... (duh!) This probably explains why floating point is *extremely* unreliable.. Just the same as we have to #ifdef out the pentium_microtime stuff, although I must take a closer look again now that you fixed the problem of masked-for-too-long clock interrupts.. There was some discussion a while ago about having the 100Hz timer interleaved across all cpus in a round-robin fashion, and if each cpu kept per-cpu smoothing/rate/etc variables, it might just be able to cope with it with enough tweaks. Cheers, -Peter From owner-freebsd-smp Sun Nov 10 12:37:20 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA01560 for smp-outgoing; Sun, 10 Nov 1996 12:37:20 -0800 (PST) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id MAA01541; Sun, 10 Nov 1996 12:37:14 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id NAA16738; Sun, 10 Nov 1996 13:35:32 -0700 Message-Id: <199611102035.NAA16738@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: Peter Wemm cc: Bruce Evans , smp@freefall.freebsd.org, nate@freefall.freebsd.org Subject: Re: cvs commit: src/sys/i386/isa syscons.c syscons.h In-reply-to: Your message of "Mon, 11 Nov 1996 01:33:35 +0800." <199611101733.BAA15722@spinner.DIALix.COM> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 10 Nov 1996 13:35:32 -0700 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Hi, > Bruce Evans wrote: > > I'm going to replace the i586 optimized copying options (including the > > one for copyin/copyout that went away) by negative-logic npx flags. > > This is mainly for 2.2. I don't trust copying through the FPU to work > > on i586 clones. > > We currently have to #ifdef out the i586_bcopy on the SMP code which does > not yet understand the fact that there is more than one FPU involved... > (duh!) This probably explains why floating point is *extremely* > unreliable.. > > Just the same as we have to #ifdef out the pentium_microtime stuff, > although I must take a closer look again now that you fixed the problem of > masked-for-too-long clock interrupts.. There was some discussion a > while ago about having the 100Hz timer interleaved across all cpus in a > round-robin fashion, and if each cpu kept per-cpu smoothing/rate/etc > variables, it might just be able to cope with it with enough tweaks. this is currently available in SMP by using the APIC_IO option in the kernel config file AND NOT defining "TEST_LOPRIO" in i386/include/smptests.h. TEST_LOPRIO causes all INTs to be offered to all available CPUs via the "lowest priority" algorithm of the APICs. Without TEST_LOPRIO defined only the system clock INT is sent to all CPUs (assumming options APIC_IO is set). I guess this means that it is unpredictable as to which CPU gets the clock tick. We could do a psuedo round robin scheme by explicily reprogramming the target for that INT each tick, but the "masked-for-too-long clock interrupts" would still be a problem. This is out of my area of knowledge, but would it make sense to localize the tick service to one CPU, but make it aware that it needs to broadcast a "tick" IPI ("all but self" InterProcess Interrupt) to the APIC bus for puposes of context switch on the other CPUs? If the "per-cpu smoothing/rate/etc" is do-able it would be better in the sense that there would be less problem with INTerrupt latency. Still, we would need the "tick IPI" to guarantee good accuracy for the context switches on the other CPUs. And then there was talk of "per-process-variable time quantums"... -- Steve Passe | powered by smp@csn.net | FreeBSD From owner-freebsd-smp Sun Nov 10 23:53:01 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id XAA26357 for smp-outgoing; Sun, 10 Nov 1996 23:53:01 -0800 (PST) Received: (from fsmp@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id XAA26344 for freebsd-smp; Sun, 10 Nov 1996 23:52:59 -0800 (PST) Date: Sun, 10 Nov 1996 23:52:59 -0800 (PST) From: Steve Passe Message-Id: <199611110752.XAA26344@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/i386 autoconf.c mp_machdep.c mpapic.c pmap.c sys/i386/include apic.h mpapic.h smp.h smptests.h sys/i386/isa clock.c vector.s Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk fsmp 96/11/10 23:52:58 Modified: i386/i386 autoconf.c mp_machdep.c mpapic.c pmap.c i386/include apic.h mpapic.h smp.h smptests.h i386/isa clock.c vector.s Log: Fixed many bugs in "default configuration" code. Fixed several EISA support bugs, default configuration EISA busses should now work (but NOT EISA cards). non-default EISA busses are broken. More cleanup towards multiple IO APICs. With help from: "Eric L. Hernes" Revision Changes Path 1.7 +6 -20 sys/i386/i386/autoconf.c 1.14 +193 -54 sys/i386/i386/mp_machdep.c 1.15 +99 -26 sys/i386/i386/mpapic.c 1.27 +5 -1 sys/i386/i386/pmap.c 1.14 +22 -1 sys/i386/include/apic.h 1.5 +24 -8 sys/i386/include/mpapic.h 1.18 +13 -1 sys/i386/include/smp.h 1.3 +9 -1 sys/i386/include/smptests.h 1.9 +15 -3 sys/i386/isa/clock.c 1.20 +27 -16 sys/i386/isa/vector.s From owner-freebsd-smp Mon Nov 11 00:22:15 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA28536 for smp-outgoing; Mon, 11 Nov 1996 00:22:15 -0800 (PST) Received: (from fsmp@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA28529 for freebsd-smp; Mon, 11 Nov 1996 00:22:13 -0800 (PST) Date: Mon, 11 Nov 1996 00:22:13 -0800 (PST) From: Steve Passe Message-Id: <199611110822.AAA28529@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/i386 mpapic.c Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk fsmp 96/11/11 00:22:12 Modified: i386/i386 mpapic.c Log: oops, put a bandaid in the wrong location. Revision Changes Path 1.16 +13 -9 sys/i386/i386/mpapic.c From owner-freebsd-smp Mon Nov 11 13:41:55 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA12080 for smp-outgoing; Mon, 11 Nov 1996 13:41:55 -0800 (PST) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id NAA12054; Mon, 11 Nov 1996 13:41:42 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id OAA23737; Mon, 11 Nov 1996 14:41:34 -0700 Message-Id: <199611112141.OAA23737@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: freebsd-smp@freefall.freebsd.org Cc: peter@freefall.freebsd.org Subject: mail bouncing Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 11 Nov 1996 14:41:34 -0700 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Peter, I've sent several mailings to you today, just got my first "4-hour notice" that they are bouncing: ... Deferred: No route to host -- summary (in case you can see freefall): >I have a suspicion that there was a syscons bug found and fixed since the >last -current merge, this might be the cause of some problems. I'd like >to do a -current resync asap. I have found that I NEED to compile kernels with the '/sys' link pointing to mk SMP kernel source, or I get wierd acting kernels. (I CVSuped -current several days ago). Ie, my source is on /d1usr/src/sys, a second disk, so: lrwxr-xr-x 1 root wheel 14 Nov 11 01:56 /sys@ -> /d1usr/src/sys is necessary to build a working SMP kernel. If I use: lrwxr-xr-x 1 root wheel 14 Nov 11 01:56 /sys@ -> /usr/src/sys the resultant kernel runs really wierd, hangs, burps, etc. This is a good time for a resync, I'm not planning any commits soon... -- >> level = trigger( apic, pin, &flags ); >> polarity( apic, pin, &flags, level ); /** * FIXME: FIXME: FIXME: this breaks non-default EISA bus systems!!! */ level = trigger( apic, pin, &flags ); polarity( apic, pin, &flags, level ); #if 0 /** FIXME: this is a BIG bandaid!!! */ i see that I include the trigger()/polarity() lines TWICE. -- I suggest removing this second pass loop ENTIRELY, letting the first pass ISA loop do all the work: /** FIXME: is this redundant with next loop??? */ select = IOAPIC_REDTBL0; vector = NRSVIDT; /** FIXME: MAPICSXXX */ for ( pin = 0; pin < maxpin; ++pin, ++vector, select += 2 ) { ioApicWrite( select, DEFAULT_ISA_FLAGS | vector ); ioApicWrite( select+1, target ); } #if 0 /* * program each IO APIC entry according to MP table */ select = IOAPIC_REDTBL0; vector = NRSVIDT; /** FIXME: MAPICSXXX */ for ( pin = 0; pin < maxpin; ++pin, ++vector, select += 2 ) { ... ioApicWrite( select, flags | vector ); ioApicWrite( select+1, target ); } #endif /** 0 */ -- Steve Passe | powered by smp@csn.net | FreeBSD -----BEGIN PGP PUBLIC KEY BLOCK----- Version: 2.6.2 mQCNAzHe7tEAAAEEAM274wAEEdP+grIrV6UtBt54FB5ufifFRA5ujzflrvlF8aoE 04it5BsUPFi3jJLfvOQeydbegexspPXL6kUejYt2OeptHuroIVW5+y2M2naTwqtX WVGeBP6s2q/fPPAS+g+sNZCpVBTbuinKa/C4Q6HJ++M9AyzIq5EuvO0a8Rr9AAUR tBlTdGV2ZSBQYXNzZSA8c21wQGNzbi5uZXQ+ =ds99 -----END PGP PUBLIC KEY BLOCK----- From owner-freebsd-smp Mon Nov 11 13:59:50 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA13375 for smp-outgoing; Mon, 11 Nov 1996 13:59:50 -0800 (PST) Received: (from fsmp@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA13363 for freebsd-smp; Mon, 11 Nov 1996 13:59:42 -0800 (PST) Date: Mon, 11 Nov 1996 13:59:42 -0800 (PST) From: Steve Passe Message-Id: <199611112159.NAA13363@freefall.freebsd.org> To: freebsd-smp Subject: cvs commit: sys/i386/i386 mpapic.c Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk fsmp 96/11/11 13:59:39 Modified: i386/i386 mpapic.c Log: CHEAP FIX for EISA/ISA bus INT APIC problem. Blindly program first 16 pins as ISA levels. Program pins 16-23 according to bus they originate from. Revision Changes Path 1.17 +9 -7 sys/i386/i386/mpapic.c From owner-freebsd-smp Mon Nov 11 18:47:35 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA09245 for smp-outgoing; Mon, 11 Nov 1996 18:47:35 -0800 (PST) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id SAA09237 for ; Mon, 11 Nov 1996 18:47:21 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id TAA25124; Mon, 11 Nov 1996 19:46:38 -0700 Message-Id: <199611120246.TAA25124@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: Peter Wemm cc: "Eric L. Hernes" , Janick.Taillandier@ratp.fr (Janick TAILLANDIER), freebsd-smp@freefall.freebsd.org Subject: Re: One In A Row!!! In-reply-to: Your message of "Tue, 12 Nov 1996 00:09:41 +0800." <199611111609.AAA00340@spinner.DIALix.COM> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 11 Nov 1996 19:46:38 -0700 Sender: owner-smp@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Peter, >I did notice one BIG difference this time, and I'll bet this would explain >the timer/syscons problems I was seeing yesterday before the commits.. > >Before: imen: 0x00ffdb07 >After: imen: 0x00ffdb05 any idea WHY the timer started to become unmasked? -- >Note also that irq13 is enabled! so the score here is: happens on 2 Neptunes doesn't on my TritonII: imen: 0x00f3ff25 < 19, 18, 7, 6, 4, 3, 1 this is before 2,8 are started. -- >The system slowed to a crawl with keyboard interrupts being lost or ignored. >I think I'll try it again without APIC_LAZY. this is like the symptom I get when /sys is linked to /usr/src/sys (ie current) instead of /d1usr/src/sys (the SMP sys, ie last synced Oct 6). Its a very preditcable way to create broken SMP kernels here. More specifically if I continue to type, the "missing" chars seem to be there, just not echoed. for instance typing: 'ls -alt' echoes 'ls -al' but causes ls -alt to run. if I re-type the missing chars during the sequence the command gets screwed. doesn't matter whether APIC_LAZY is defined or not. -- >My initial thoughts are that we need a different strategy for each type, and >both would be reasonably different to the 8259 case (they are different >animals). Another important fact to remember about the APIC is that it uses a different method of setting priority. its based on the 'vector group'. Specifically each group of 16 vectors have equal priority, so INTs 0-15 are all of equal priority in this paradigm. The way I read the datasheet, within this group its just potluck as to which is serviced first. So we might want to start using other vectors, maybe group tty INTS into group 48-63, bio into 64-79, etc. Also: there is a 2 deep fifo for each priority level. the datasheet recommends ONLY ALLOCATING 2 INT VECTORS per group. If the fifo is full the message is discarded and the IO APIC has to resend till it takes. Section 19.3.1.1 of the P5 manual describes these 2 facts. Section 7.4.2 of the P6 manual discusses the same thing, but more grimely: "To avoid loosing interrupts software should allocate no more than 2 interrupt vectors per priority" -- >Also, we should keep in mind that we will need to deal with systems that >have some interrupts only visible to the 8259's and are not connected to >the APIC (eg: one of Dell's current range apparently). On these systems, >we have 16 "mask" bits in imen, plus at least 16 more APIC "mask" bits, >plus the 4 software interrupt bits. That's more than 32 for those who > ... >Macros like INTREN() would be thrown into chaos by this, as they'd need >to know whether the IRQ was being handled on an 8259 input, or on one of >the IO apics.. Oh, what fun.. :-) I agree with the strategy you go on to descibe, but as to this specific issue of the DELL, The only INT "unconnected" is the timer. I plan to: program the 8259 for auto EOI, mask ALL 8259 INTs but the timer, program the IO APIC to expect a type 3 INT (ie 8259 vectored) on pin 1 (INT0) NEVER mess with the 8259 once initially programmed. it would be a programming nightemare to have to determine whether we are touching the 8259 and/or IO APIC in the INT routines on an INT by INT basis. the only 2 "possible non-connects" are IRQ 0 (timer) and IRQ 13 (EISA chaining INT). Correct me if I'm wrong, but its my belief that EISA DMA chaining is only used by NON-busmaster EISA cards, so I think we can afford to not support it. That leaves only IRQ0 as possibly "unconnected". The strategy I outline above should make using "mixed mode", ie vectored 8259, INTs not too terribly painful for unconnected IRQ0s. I personally would rather start contributing to a "Hardware Replacement Foundation" than have to tackle arbitrary mixed 8259/IO APIC programming models!!! -- Steve Passe | powered by smp@csn.net | FreeBSD -----BEGIN PGP PUBLIC KEY BLOCK----- Version: 2.6.2 mQCNAzHe7tEAAAEEAM274wAEEdP+grIrV6UtBt54FB5ufifFRA5ujzflrvlF8aoE 04it5BsUPFi3jJLfvOQeydbegexspPXL6kUejYt2OeptHuroIVW5+y2M2naTwqtX WVGeBP6s2q/fPPAS+g+sNZCpVBTbuinKa/C4Q6HJ++M9AyzIq5EuvO0a8Rr9AAUR tBlTdGV2ZSBQYXNzZSA8c21wQGNzbi5uZXQ+ =ds99 -----END PGP PUBLIC KEY BLOCK----- From owner-freebsd-smp Mon Nov 11 21:16:13 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id VAA22316 for smp-outgoing; Mon, 11 Nov 1996 21:16:13 -0800 (PST) Received: from quagmire.ki.net (root@quagmire.ki.net [205.150.102.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id VAA22292; Mon, 11 Nov 1996 21:16:06 -0800 (PST) Received: from localhost (scrappy@localhost) by quagmire.ki.net (8.8.2/8.7.5) with SMTP id AAA07321; Tue, 12 Nov 1996 00:16:04 -0500 (EST) Date: Tue, 12 Nov 1996 00:16:02 -0500 (EST) From: "Marc G. Fournier" To: smp@freebsd.org cc: current@freebsd.org Subject: GigaByte GA-586DX-512 Motherboard Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi... I asked my supplier for a quote on the GigaByte GA-586DX-512 Motherboard, and got the following response: ---- I am still searching for the GigaByte GA-586DX-512 Motherboard. Apparantly they have had a great deal of problems with this board and are not carrying it anymore. I still might find one but would you consider getting something more reliable. eg. Asus. Let me know what you need ie: PCI/ISA/EISA and tomarrow I can find prices for you. ---- Can anyone comment on this? I've always had good dealing with the ASUS brand of motherboards, but is there an equivalent ASUS motherboard that ppl would recommend? I'm wondering if their "great deal of problems" might have been with earlier models, and they just said to hell with carrying it altogether? Thanks... Marc G. Fournier scrappy@ki.net Systems Administrator @ ki.net scrappy@freebsd.org From owner-freebsd-smp Mon Nov 11 23:21:14 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id XAA28545 for smp-outgoing; Mon, 11 Nov 1996 23:21:14 -0800 (PST) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id XAA28527; Mon, 11 Nov 1996 23:21:10 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id AAA26401; Tue, 12 Nov 1996 00:20:55 -0700 Message-Id: <199611120720.AAA26401@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: "Marc G. Fournier" cc: smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-reply-to: Your message of "Tue, 12 Nov 1996 00:16:02 EST." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 12 Nov 1996 00:20:55 -0700 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > I asked my supplier for a quote on the GigaByte GA-586DX-512 > Motherboard, and got the following response: > > ---- > I am still searching for the GigaByte GA-586DX-512 Motherboard. > Apparantly they have had a great deal of problems with this board and are not > carrying it anymore. I still might find one but would you consider getting > something more reliable. eg. Asus. Let me know what you need ie: PCI/ISA/EISA > and tomarrow I can find prices for you. > ---- > > Can anyone comment on this? I've always had good dealing with > the ASUS brand of motherboards, but is there an equivalent ASUS motherboard > that ppl would recommend? > > I'm wondering if their "great deal of problems" might have been > with earlier models, and they just said to hell with carrying it altogether? or they just want to sell you what they have experience with (or can make more money on). This is the board that I pound on many hours a day, and have never had a lick of trouble with it. It supports the MP spec properly (and there's a LOT of room in that spec to do stupid things). Never seen a sigfault that "smells" of the flaky memory sub-system variety. I do see occasional faults, but we know the current SMP kernel is not "doing the good thing" in all respects yet. From my limited experience of one board I would not hesitate to recommend it. Try www.atipa.com, they could probably have one to you by end of the week. -- Steve Passe | powered by smp@csn.net | FreeBSD From owner-freebsd-smp Tue Nov 12 00:09:05 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA00986 for smp-outgoing; Tue, 12 Nov 1996 00:09:05 -0800 (PST) Received: from quagmire.ki.net (root@quagmire.ki.net [205.150.102.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id AAA00968; Tue, 12 Nov 1996 00:09:00 -0800 (PST) Received: from localhost (scrappy@localhost) by quagmire.ki.net (8.8.2/8.7.5) with SMTP id DAA10379; Tue, 12 Nov 1996 03:08:56 -0500 (EST) Date: Tue, 12 Nov 1996 03:08:55 -0500 (EST) From: "Marc G. Fournier" To: Steve Passe cc: smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: <199611120720.AAA26401@clem.systemsix.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 On Tue, 12 Nov 1996, Steve Passe wrote: > Hi, > > > I asked my supplier for a quote on the GigaByte GA-586DX-512 > > Motherboard, and got the following response: > > > > ---- > > I am still searching for the GigaByte GA-586DX-512 Motherboard. > > Apparantly they have had a great deal of problems with this board and are not > > carrying it anymore. I still might find one but would you consider getting > > something more reliable. eg. Asus. Let me know what you need ie: PCI/ISA/EISA > > and tomarrow I can find prices for you. > > ---- > > > > Can anyone comment on this? I've always had good dealing with > > the ASUS brand of motherboards, but is there an equivalent ASUS motherboard > > that ppl would recommend? > > > > I'm wondering if their "great deal of problems" might have been > > with earlier models, and they just said to hell with carrying it altogether? > > or they just want to sell you what they have experience with (or can make > more money on). > > This is the board that I pound on many hours a day, and have never had a lick > of trouble with it. It supports the MP spec properly (and there's a LOT >of room in that spec to do stupid things). Never seen a sigfault that "smells" > of the flaky memory sub-system variety. I do see occasional faults, but we > know the current SMP kernel is not "doing the good thing" in all respects >yet. From my limited experience of one board I would not hesitate to recommend >it. Try www.atipa.com, they could probably have one to you by end of the week. > Okay...sound arguments :) How does this sound: GigaByte GA-586DX-512 Intel Pentium 133 (is 133 that much better then 120 to warrant extra cost?) 64Meg of RAM (EDO?) How about Hard Drive? atipa doesn't list Seagates, that I can find, and recent experiencees with Quantum are steering me clear of them. Essentially, I'm looking at setting up a server that I can play with SMP on, but if I get a crash/core, I can confidently send in a bug report on without being worried its a hardware problem :) Thanks... Marc G. Fournier scrappy@ki.net Systems Administrator @ ki.net scrappy@freebsd.org From owner-freebsd-smp Tue Nov 12 00:22:06 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA01665 for smp-outgoing; Tue, 12 Nov 1996 00:22:06 -0800 (PST) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id AAA01641; Tue, 12 Nov 1996 00:21:59 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id BAA26733; Tue, 12 Nov 1996 01:21:46 -0700 Message-Id: <199611120821.BAA26733@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: "Marc G. Fournier" cc: smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-reply-to: Your message of "Tue, 12 Nov 1996 03:08:55 EST." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 12 Nov 1996 01:21:46 -0700 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > How does this sound: > > GigaByte GA-586DX-512 > Intel Pentium 133 (is 133 that much better then 120 to warrant extra > cost?) yes, not only faster, but 133s use a 66mHz bus, while 120s use a 60mHz bus. > 64Meg of RAM (EDO?) I recommend 64meg of parity. Don't really have direct knowledge of EDO vs not. > How about Hard Drive? atipa doesn't list Seagates, that I can find, >and recent experiencees with Quantum are steering me clear of them. atipa carries a rather limited selection in general, just how they do business. I would suggest getting the drive from someplace that carries what you want. -- Steve Passe | powered by smp@csn.net | FreeBSD -----BEGIN PGP PUBLIC KEY BLOCK----- Version: 2.6.2 mQCNAzHe7tEAAAEEAM274wAEEdP+grIrV6UtBt54FB5ufifFRA5ujzflrvlF8aoE 04it5BsUPFi3jJLfvOQeydbegexspPXL6kUejYt2OeptHuroIVW5+y2M2naTwqtX WVGeBP6s2q/fPPAS+g+sNZCpVBTbuinKa/C4Q6HJ++M9AyzIq5EuvO0a8Rr9AAUR tBlTdGV2ZSBQYXNzZSA8c21wQGNzbi5uZXQ+ =ds99 -----END PGP PUBLIC KEY BLOCK----- From owner-freebsd-smp Tue Nov 12 00:46:11 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA02987 for smp-outgoing; Tue, 12 Nov 1996 00:46:11 -0800 (PST) Received: from quagmire.ki.net (root@quagmire.ki.net [205.150.102.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id AAA02965; Tue, 12 Nov 1996 00:46:06 -0800 (PST) Received: from localhost (scrappy@localhost) by quagmire.ki.net (8.8.2/8.7.5) with SMTP id DAA10792; Tue, 12 Nov 1996 03:46:11 -0500 (EST) Date: Tue, 12 Nov 1996 03:46:11 -0500 (EST) From: "Marc G. Fournier" To: Steve Passe cc: smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: <199611120821.BAA26733@clem.systemsix.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 On Tue, 12 Nov 1996, Steve Passe wrote: > > 64Meg of RAM (EDO?) > >I recommend 64meg of parity. Don't really have direct knowledge of EDO vs not. > Hrmmm...I had thought that EDO RAM was better because it had 'on chip' cache or something like that ... > > How about Hard Drive? atipa doesn't list Seagates, that I can find, > >and recent experiencees with Quantum are steering me clear of them. > >atipa carries a rather limited selection in general, just how they do business. > I would suggest getting the drive from someplace that carries what you want. > Does anyone have any recommendations on drives? Or, any drives in particular I should stick away from? I heard that SeaGate went downhill for awhile there...anyone have a current opinion of them? Marc G. Fournier scrappy@ki.net Systems Administrator @ ki.net scrappy@freebsd.org From owner-freebsd-smp Tue Nov 12 03:01:53 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id DAA09809 for smp-outgoing; Tue, 12 Nov 1996 03:01:53 -0800 (PST) Received: from mail.gmd.de (mail.gmd.de [129.26.8.90]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id DAA09804 for ; Tue, 12 Nov 1996 03:01:45 -0800 (PST) Received: from hoss.gmd.de (hoss) by mail.gmd.de with SMTP id AA25515 (5.67b8/IDA-1.5 for ); Tue, 12 Nov 1996 12:01:39 +0100 Received: by hoss.gmd.de id AA16244 (5.67b/IDA-1.5 for smp@freebsd.org); Tue, 12 Nov 1996 12:01:35 +0100 From: "Mathias Kretschmer" Message-Id: <9611121201.ZM16242@mats> Date: Tue, 12 Nov 1996 12:01:34 +0100 In-Reply-To: "Marc G. Fournier" "Re: GigaByte GA-586DX-512 Motherboard" (Nov 12, 3:46am) References: X-Mailer: Z-Mail (3.2.0 06sep94) To: smp@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Nov 12, 3:46am, Marc G. Fournier wrote: > > > How about Hard Drive? atipa doesn't list Seagates, that I can find, > > >and recent experiencees with Quantum are steering me clear of them. > > > >atipa carries a rather limited selection in general, just how they do business. > > I would suggest getting the drive from someplace that carries what you want. > > > > Does anyone have any recommendations on drives? Or, any drives > in particular I should stick away from? I heard that SeaGate went downhill > for awhile there...anyone have a current opinion of them? Hi, Currently I'm using a Seagate Wide-SCSI-Barracuda 2LP with an Apactec 2940 with FreeBSD-UP (with an WIDE to FAST Adapter). The drive performs petty cool...I've got no problems with it. I'm planing to buy the GA-586-DX board this week, an I hope my Barracuda will work with the onboard WIDE-SCSI-Adaptec.... bye Mathias From owner-freebsd-smp Tue Nov 12 03:12:56 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id DAA10347 for smp-outgoing; Tue, 12 Nov 1996 03:12:56 -0800 (PST) Received: from smily.3skel.com (3skel.com [206.138.212.40]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id DAA10293; Tue, 12 Nov 1996 03:12:37 -0800 (PST) Received: from fnur.3skel.com (root@fnur.3skel.com [192.168.0.8]) by smily.3skel.com (8.8.2/8.8.2) with ESMTP id GAA07879; Tue, 12 Nov 1996 06:12:16 -0500 (EST) Received: (from danj@localhost) by fnur.3skel.com (8.8.2/8.8.2) id GAA24880; Tue, 12 Nov 1996 06:12:15 -0500 (EST) Date: Tue, 12 Nov 1996 06:12:15 -0500 (EST) Message-Id: <199611121112.GAA24880@fnur.3skel.com> From: Dan Janowski To: "Marc G. Fournier" Cc: Steve Passe , smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: References: <199611120821.BAA26733@clem.systemsix.com> Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Marc G. Fournier writes: > > Does anyone have any recommendations on drives? Or, any drives > in particular I should stick away from? I heard that SeaGate went downhill > for awhile there...anyone have a current opinion of them? The Conner stuff that Seagate bought is less than desirable. I have two IDEs that I am swapping out. If you are doing SCSI, the Baracudas are really good. I have an ST32550N, two of them. I would recommend the Baracuda or the IBM starfire, both high spindle speed, fast drives. Quantum, hold on to your .... No Atlas 1s, Atlas 2s I have not tried. Dan From owner-freebsd-smp Tue Nov 12 04:42:59 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id EAA21032 for smp-outgoing; Tue, 12 Nov 1996 04:42:59 -0800 (PST) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id EAA20987; Tue, 12 Nov 1996 04:42:34 -0800 (PST) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id NAA10429; Tue, 12 Nov 1996 13:30:32 +0100 (MET) Received: from localhost (localhost [127.0.0.1]) by klemm.gtn.com (8.8.2/8.8.2) with SMTP id MAA02670; Tue, 12 Nov 1996 12:28:36 +0100 (MET) Date: Tue, 12 Nov 1996 12:28:35 +0100 (MET) From: Andreas Klemm To: "Marc G. Fournier" cc: Steve Passe , smp@FreeBSD.org, current@FreeBSD.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: Message-ID: X-try-apsfilter: ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz X-Fax: +49 2137 2018 X-Phone: +49 2137 2020 MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Tue, 12 Nov 1996, Marc G. Fournier wrote: > Does anyone have any recommendations on drives? Or, any drives > in particular I should stick away from? I heard that SeaGate went downhill > for awhile there...anyone have a current opinion of them? Quantum Atlas 2GB, the 4GB modell is too loud for a home environment. Both drives have 1 MB cache ! Another fast, but loud and expensive drive, is the IBM DHFS .... sorry forgot the model number. The Quantum drives are also available as wide scsi disks. Andreas /// -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-smp Tue Nov 12 04:43:16 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id EAA21064 for smp-outgoing; Tue, 12 Nov 1996 04:43:16 -0800 (PST) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id EAA21021; Tue, 12 Nov 1996 04:42:52 -0800 (PST) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id NAA10417; Tue, 12 Nov 1996 13:30:25 +0100 (MET) Received: from localhost (localhost [127.0.0.1]) by klemm.gtn.com (8.8.2/8.8.2) with SMTP id MAA02577; Tue, 12 Nov 1996 12:26:01 +0100 (MET) Date: Tue, 12 Nov 1996 12:26:01 +0100 (MET) From: Andreas Klemm To: "Marc G. Fournier" cc: Steve Passe , smp@FreeBSD.org, current@FreeBSD.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: Message-ID: X-try-apsfilter: ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz X-Fax: +49 2137 2018 X-Phone: +49 2137 2020 MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Tue, 12 Nov 1996, Marc G. Fournier wrote: > Okay...sound arguments :) > How does this sound: > > GigaByte GA-586DX-512 > Intel Pentium 133 (is 133 that much better then 120 to warrant extra > cost?) > 64Meg of RAM (EDO?) > How about Hard Drive? atipa doesn't list Seagates, that I can find, > and recent experiencees with Quantum are steering me clear of them. > > Essentially, I'm looking at setting up a server that I can play with > SMP on, but if I get a crash/core, I can confidently send in a bug report on > without being worried its a hardware problem :) The performance difference between PS/2 and EDO Ram's isn't so large, that it's worth the higher price. This was the case with single processor boards, and I think it's also true with mp boards. I'd buy PS/2 RAMS with 60ns and Parity (since most mp boards support parity checking - or am I wrong -) and would choose a 133 MHZ CPU, because then memory and bus bandwidth are higher ! 66MHz instead of 60 MHz. Many people say, that it's better to choose a - 200 MHz CPU instead of a 180 MHz CPU - 166 MHz CPU instead of a 150 MHz CPU - 133 MHz CPU instead of a 150 MHz CPU - 100 MHz CPU instead of a 120 MHz CPU because bus and memory speed have a more impact on overall performance on a multiuser/multitasking system, than the 20MHz clock frequency... Andreas /// -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-smp Tue Nov 12 05:57:04 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id FAA25506 for smp-outgoing; Tue, 12 Nov 1996 05:57:04 -0800 (PST) Received: from charlotte.spiders.com (charlotte.spiders.com [199.224.7.188]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id FAA25489; Tue, 12 Nov 1996 05:56:56 -0800 (PST) Received: (from gwh@localhost) by charlotte.spiders.com (8.6.12/8.6.12) id IAA12311; Tue, 12 Nov 1996 08:59:49 -0500 Message-Id: <199611121359.IAA12311@charlotte.spiders.com> From: gwh@spiders.com (Gene W Homicki) Date: Tue, 12 Nov 1996 08:59:49 -0500 In-Reply-To: Steve Passe's message as of Nov 12, 0:20 X-Mailer: Mail User's Shell (7.2.5 10/14/92) To: Steve Passe , "Marc G. Fournier" Subject: Re: GigaByte GA-586DX-512 Motherboard Cc: smp@freebsd.org, current@freebsd.org Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk +--- | This is the board that I pound on many hours a day, and have never had a lick | of trouble with it. It supports the MP spec properly (and there's a LOT +--- I'll second this. I'm still using the board as a uniprocessor, but I've had no trouble with it. Running a current SNAP (non-smp) I've had this box up for over 3 weeks (and I pound on it pretty hard). Now to get a second P166. B-) --Gene -- Gene W. Homicki gwh@spiders.com Objective Consulting, Inc. http://www.spiders.com/ Internet Presence Design voice: +1 914.353.3511 From owner-freebsd-smp Tue Nov 12 06:05:54 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id GAA26023 for smp-outgoing; Tue, 12 Nov 1996 06:05:54 -0800 (PST) Received: from charlotte.spiders.com (charlotte.spiders.com [199.224.7.188]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id GAA26000; Tue, 12 Nov 1996 06:05:41 -0800 (PST) Received: (from gwh@localhost) by charlotte.spiders.com (8.6.12/8.6.12) id JAA12381; Tue, 12 Nov 1996 09:08:38 -0500 Message-Id: <199611121408.JAA12381@charlotte.spiders.com> From: gwh@spiders.com (Gene W Homicki) Date: Tue, 12 Nov 1996 09:08:38 -0500 In-Reply-To: Andreas Klemm's message as of Nov 12, 12:26 X-Mailer: Mail User's Shell (7.2.5 10/14/92) To: Andreas Klemm , "Marc G. Fournier" Subject: Re: GigaByte GA-586DX-512 Motherboard Cc: Steve Passe , smp@FreeBSD.org, current@FreeBSD.org Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk +--- | The performance difference between PS/2 and EDO Ram's isn't so | large, that it's worth the higher price. This was the case with | single processor boards, and I think it's also true with mp boards. +--- Actually, FPM RAM is slightly MORE expensive than EDO at the moment. Parity RAM is defintely more expensive than both. Seems like comapnies are producing a lot more EDO these days so prices have come down. One good source for RAM is ChipMerchant: http://www.thechipmerchant.com/ (Careful, the CPU prices are "cash only", bu the listed RAM prices are Credit Card prices). +--- | I'd buy PS/2 RAMS with 60ns and Parity (since most mp boards support | parity checking - or am I wrong -) and would choose a 133 MHZ CPU, | because then memory and bus bandwidth are higher ! 66MHz instead of | 60 MHz. +--- All the 430HX (Triton II) boards support parity (and ECC). Most current (Pentium) baords are Triton-II, inclduing the Gigabyte 586DX-512. --Gene -- Gene W. Homicki gwh@spiders.com Objective Consulting, Inc. http://www.spiders.com/ Internet Presence Design voice: +1 914.353.3511 From owner-freebsd-smp Tue Nov 12 07:08:43 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id HAA29263 for smp-outgoing; Tue, 12 Nov 1996 07:08:43 -0800 (PST) Received: from cs.utah.edu (cs.utah.edu [128.110.4.21]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id HAA29205; Tue, 12 Nov 1996 07:08:20 -0800 (PST) Received: from fast.cs.utah.edu by cs.utah.edu (8.6.12/utah-2.21-cs) id IAA24250; Tue, 12 Nov 1996 08:08:16 -0700 Received: by fast.cs.utah.edu (8.6.10/utah-2.15-leaf) id IAA02827; Tue, 12 Nov 1996 08:08:15 -0700 Date: Tue, 12 Nov 1996 08:08:15 -0700 From: vanmaren@fast.cs.utah.edu (Kevin Van Maren) Message-Id: <199611121508.IAA02827@fast.cs.utah.edu> To: current@FreeBSD.org, smp@FreeBSD.org, smp@csn.net Subject: Re: GigaByte GA-586DX-512 Motherboard Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk +--- | The performance difference between PS/2 and EDO Ram's isn't so | large, that it's worth the higher price. This was the case with | single processor boards, and I think it's also true with mp boards. +--- Actually, FPM RAM is slightly MORE expensive than EDO at the moment. Parity RAM is defintely more expensive than both. Seems like comapnies are producing a lot more EDO these days so prices have come down. One good source for RAM is ChipMerchant: http://www.thechipmerchant.com/ (Careful, the CPU prices are "cash only", bu the listed RAM prices are Credit Card prices). +--- | I'd buy PS/2 RAMS with 60ns and Parity (since most mp boards support | parity checking - or am I wrong -) and would choose a 133 MHZ CPU, | because then memory and bus bandwidth are higher ! 66MHz instead of | 60 MHz. +--- All the 430HX (Triton II) boards support parity (and ECC). Most current (Pentium) baords are Triton-II, inclduing the Gigabyte 586DX-512. --Gene Actually, there are a couple of places that *say* they have Parity EDO...for $12/MB. If you want reliable hardware, go Parity; if it crashes, you'll at least know you have a memory problem. EDO will give a read B/W improvement, but hopefully most things are in the cache anyway. Burst EDO (I haven't found anyplace that wants to sell it to me) improves Write B/W as well. When Parity Burst EDO (or SDRAM is also supported) is available, I'll probably make the plunge; until then I'll stick with 60ns FPM w/parity. From owner-freebsd-smp Tue Nov 12 07:33:08 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id HAA00345 for smp-outgoing; Tue, 12 Nov 1996 07:33:08 -0800 (PST) Received: from gargoyle.bazzle.com (gargoyle.bazzle.com [206.103.246.190]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id HAA00320; Tue, 12 Nov 1996 07:32:34 -0800 (PST) Received: from gargoyle.bazzle.com (localhost [127.0.0.1]) by gargoyle.bazzle.com (8.8.2/8.6.12) with SMTP id KAA04441; Tue, 12 Nov 1996 10:30:45 -0500 (EST) Date: Tue, 12 Nov 1996 10:30:45 -0500 (EST) From: "Eric J. Chet" To: Andreas Klemm cc: "Marc G. Fournier" , Steve Passe , smp@FreeBSD.org, current@FreeBSD.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Tue, 12 Nov 1996, Andreas Klemm wrote: > On Tue, 12 Nov 1996, Marc G. Fournier wrote: > > > Does anyone have any recommendations on drives? Or, any drives > > in particular I should stick away from? I heard that SeaGate went downhill > > for awhile there...anyone have a current opinion of them? > > Quantum Atlas 2GB, the 4GB modell is too loud for a home environment. > Both drives have 1 MB cache ! > > Another fast, but loud and expensive drive, is the IBM DHFS .... sorry > forgot the model number. Hello Check out http://www.basoncomputer.com 2.0GB IBM DFHS SCSI 8mS, 3.5"LP, 7200RPM $429 Not a bad deal, Eric J. Chet - ejc@bazzle.com From owner-freebsd-smp Tue Nov 12 07:39:45 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id HAA00709 for smp-outgoing; Tue, 12 Nov 1996 07:39:45 -0800 (PST) Received: from neworder.cc.uky.edu (neworder.cc.uky.edu [128.163.18.198]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id HAA00670; Tue, 12 Nov 1996 07:39:21 -0800 (PST) Received: (from soward@localhost) by neworder.cc.uky.edu (8.7/Soward0.1) id KAA04858; Tue, 12 Nov 1996 10:39:18 -0500 (EST) Message-Id: <199611121539.KAA04858@neworder.cc.uky.edu> MIME-Version: 1.0 (NeXT Mail 4.0 v141) Content-Type: text/plain Received: by NeXT.Mailer (1.141) From: John Soward Date: Tue, 12 Nov 96 10:39:17 -0500 To: smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard cc: "Marc G. Fournier" Reply-To: soward@service1.uky.edu References: <199611120720.AAA26401@clem.systemsix.com> Organization: University of Kentucky Technical Services X-URL: "http://neworder.cc.uky.edu/" Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I too have had excellent luck with this motherboard (and I too bought mine from Atipa, though I had somewhat less luck there ;-). I am not using the smp code (yet), but I've had NT4, FreeBSD2.1.5, current, DOS, Win95, and NEXTSTEP on it. The only things that have irked me were the need to get an ATX case, and the lack of an external SCSI connector...It's been on pretty much 24 hours a day since early august... --- John Soward JpS Systems Programmer 'The Midnight sun will burn you up.' University of Kentucky (NeXT and MIME mail OK) -R. Smith From owner-freebsd-smp Tue Nov 12 08:01:03 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA01392 for smp-outgoing; Tue, 12 Nov 1996 08:01:03 -0800 (PST) Received: from charlotte.spiders.com (charlotte.spiders.com [199.224.7.188]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id IAA01372; Tue, 12 Nov 1996 08:00:45 -0800 (PST) Received: (from gwh@localhost) by charlotte.spiders.com (8.6.12/8.6.12) id LAA13027; Tue, 12 Nov 1996 11:03:38 -0500 Message-Id: <199611121603.LAA13027@charlotte.spiders.com> From: gwh@spiders.com (Gene W Homicki) Date: Tue, 12 Nov 1996 11:03:38 -0500 In-Reply-To: John Soward's message as of Nov 12, 10:39 X-Mailer: Mail User's Shell (7.2.5 10/14/92) To: soward@service1.uky.edu, smp@FreeBSD.org, current@FreeBSD.org Subject: Re: GigaByte GA-586DX-512 Motherboard Cc: "Marc G. Fournier" Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk +--- | I too have had excellent luck with this motherboard (and I too bought mine | from Atipa, though I had somewhat less luck there ;-). I am not using the smp +--- Me too, to getting it there and slight irks. +--- | on it. The only things that have irked me were the need to get an ATX case, and | the lack of an external SCSI connector...It's been on pretty much 24 hours a | day since early august... +--- Mine came with an external connector (got it a couple of months ago from Atipa). The thing that REALLY irked me was that it requires an ATX form factor case, but a standard power supply connector. So its some wort of AT/ATX hybrid (or low-bred B-). If you order from Atipa (or anywhere else), make sure they send you the right case, the first time. --Gene -- Gene W. Homicki gwh@spiders.com Objective Consulting, Inc. http://www.spiders.com/ Internet Presence Design voice: +1 914.353.3511 From owner-freebsd-smp Tue Nov 12 08:30:00 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA03436 for smp-outgoing; Tue, 12 Nov 1996 08:30:00 -0800 (PST) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id IAA03406; Tue, 12 Nov 1996 08:29:37 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id JAA29256; Tue, 12 Nov 1996 09:29:05 -0700 Message-Id: <199611121629.JAA29256@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: gwh@spiders.com (Gene W Homicki) cc: soward@service1.uky.edu, smp@FreeBSD.org, current@FreeBSD.org, "Marc G. Fournier" Subject: Re: GigaByte GA-586DX-512 Motherboard In-reply-to: Your message of "Tue, 12 Nov 1996 11:03:38 EST." <199611121603.LAA13027@charlotte.spiders.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 12 Nov 1996 09:29:05 -0700 Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi, > Mine came with an external connector (got it a couple of > months ago from Atipa). The thing that REALLY irked me was that it > requires an ATX form factor case, but a standard power supply > connector. So its some wort of AT/ATX hybrid (or low-bred B-). indeed a bad design point. I guess they were thinking that there were limited sources of ATX supplies at the time... never mind that the case is still different. > If you order from Atipa (or anywhere else), make sure they send you > the right case, the first time. I have to admit I was less than happy with the case. My big gripe is that the case has 6 backplane slot cutouts, but the board supports 7 cards (4 ISA, 4 PCI, one slot shared). So one PCI slot doesn't have a cutout! In general I really like the ATX formfactor. In this case all the MB mounts (except one) are steel posts instead of those flimsy nylon standoffs. Don't know if this is part of the ATX standard, but it fits great, no flexing of the MB when inserting cards! And ALL the card slots are full length, the CPUs and stuff being to the side of the slots. If anyone knows of a good source of ATX cases please speak up. -- Steve Passe | powered by smp@csn.net | FreeBSD From owner-freebsd-smp Tue Nov 12 08:31:06 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA03559 for smp-outgoing; Tue, 12 Nov 1996 08:31:06 -0800 (PST) Received: from GndRsh.aac.dev.com (GndRsh.aac.dev.com [198.145.92.241]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id IAA03499; Tue, 12 Nov 1996 08:30:31 -0800 (PST) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id IAA15688; Tue, 12 Nov 1996 08:29:54 -0800 (PST) From: "Rodney W. Grimes" Message-Id: <199611121629.IAA15688@GndRsh.aac.dev.com> Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: from Andreas Klemm at "Nov 12, 96 12:28:35 pm" To: andreas@klemm.gtn.com (Andreas Klemm) Date: Tue, 12 Nov 1996 08:29:53 -0800 (PST) Cc: scrappy@ki.net, smp@csn.net, smp@FreeBSD.org, current@FreeBSD.org X-Mailer: ELM [version 2.4ME+ PL25 (25)] 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 > On Tue, 12 Nov 1996, Marc G. Fournier wrote: > > > Does anyone have any recommendations on drives? Or, any drives > > in particular I should stick away from? I heard that SeaGate went downhill > > for awhile there...anyone have a current opinion of them? > > Quantum Atlas 2GB, the 4GB modell is too loud for a home environment. > Both drives have 1 MB cache ! I'll correct that, the 4GB model has a 2MB cache on it... -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation, Inc. Reliable computers for FreeBSD From owner-freebsd-smp Tue Nov 12 08:41:32 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA04461 for smp-outgoing; Tue, 12 Nov 1996 08:41:32 -0800 (PST) Received: from quagmire.ki.net (root@quagmire.ki.net [205.150.102.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id IAA04421; Tue, 12 Nov 1996 08:41:01 -0800 (PST) Received: from localhost (scrappy@localhost) by quagmire.ki.net (8.8.2/8.7.5) with SMTP id LAA16408; Tue, 12 Nov 1996 11:40:50 -0500 (EST) Date: Tue, 12 Nov 1996 11:40:50 -0500 (EST) From: "Marc G. Fournier" To: soward@service1.uky.edu cc: smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: <199611121539.KAA04858@neworder.cc.uky.edu> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Tue, 12 Nov 1996, John Soward wrote: > > I too have had excellent luck with this motherboard (and I too bought mine > from Atipa, though I had somewhat less luck there ;-). I am not using the smp > code (yet), but I've had NT4, FreeBSD2.1.5, current, DOS, Win95, and NEXTSTEP > on it. The only things that have irked me were the need to get an ATX case, and ATX case? Marc G. Fournier scrappy@ki.net Systems Administrator @ ki.net scrappy@freebsd.org From owner-freebsd-smp Tue Nov 12 09:08:33 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA06281 for smp-outgoing; Tue, 12 Nov 1996 09:08:33 -0800 (PST) Received: from brimstone.gage.com (brimstone.gage.com [205.217.2.10]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA06272; Tue, 12 Nov 1996 09:08:22 -0800 (PST) Received: (from mail@localhost) by brimstone.gage.com (8.8.2/8.7.3) id LAA04391; Tue, 12 Nov 1996 11:07:16 -0600 (CST) Received: from octopus.gage.com(158.60.57.50) by brimstone.gage.com via smap (V2.0beta) id xma004389; Tue, 12 Nov 96 11:06:58 -0600 Received: from squid.gage.com (squid [158.60.57.101]) by octopus.gage.com (8.7.5/8.7.3) with SMTP id KAA05438; Tue, 12 Nov 1996 10:57:40 -0600 (CST) Received: from schemer by squid.gage.com (NX5.67e/NX3.0S) id AA14777; Tue, 12 Nov 96 10:57:38 -0600 Message-Id: <9611121657.AA14777@squid.gage.com> Received: by schemer.gage.com (NX5.67g/NX3.0X) id AA03568; Tue, 12 Nov 96 11:08:54 -0600 Content-Type: text/plain Mime-Version: 1.0 (NeXT Mail 4.0 v146.2) In-Reply-To: <199611121629.JAA29256@clem.systemsix.com> X-Nextstep-Mailer: Mail 3.3 (Enhance 1.3) Received: by NeXT.Mailer (1.146.2) From: Ben Black Date: Tue, 12 Nov 96 11:08:53 -0600 To: Steve Passe Subject: Re: GigaByte GA-586DX-512 Motherboard Cc: gwh@spiders.com (Gene W Homicki), soward@service1.uky.edu, smp@freebsd.org, current@freebsd.org, "Marc G. Fournier" References: <199611121629.JAA29256@clem.systemsix.com> Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >If anyone knows of a good source of ATX cases please speak up. > i have an In-Win Q500A full tower case. it is fantastic, but it costs an arm and a leg. the motherboard and cards are mounted on a tray that slide out the back of the case, it's all steel, and has lots of space for fans (i have tons of high flow panaflwo fans around). b3n From owner-freebsd-smp Tue Nov 12 09:27:46 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA07135 for smp-outgoing; Tue, 12 Nov 1996 09:27:46 -0800 (PST) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id JAA07099; Tue, 12 Nov 1996 09:27:18 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id KAA29604; Tue, 12 Nov 1996 10:21:13 -0700 Message-Id: <199611121721.KAA29604@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: "Marc G. Fournier" cc: soward@service1.uky.edu, smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-reply-to: Your message of "Tue, 12 Nov 1996 11:40:50 EST." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 12 Nov 1996 10:21:13 -0700 Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > On Tue, 12 Nov 1996, John Soward wrote: > ... > > on it. The only things that have irked me were the need to get an ATX case, and > > ATX case? yes, this is an ATX formfactor board, which is either what they all will be in the not too distant future, OR the "beta" of motherboards. see this for details on ATX: http://www.intel.com/pc-supp/motherbd/atx.htm heres a couple links to the GA586DX: http://www.giga-byte.com/GA586DX.html http://www.surfusa.com/mbs/ga/586dx.html -- Steve Passe | powered by smp@csn.net | FreeBSD From owner-freebsd-smp Tue Nov 12 09:33:56 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA07676 for smp-outgoing; Tue, 12 Nov 1996 09:33:56 -0800 (PST) Received: from troll.uunet.ca (troll.uunet.ca [142.77.1.10]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA07645; Tue, 12 Nov 1996 09:33:25 -0800 (PST) Received: from localhost by troll.uunet.ca with SMTP id <21007-14637>; Tue, 12 Nov 1996 12:33:04 -0500 Date: Tue, 12 Nov 1996 12:32:59 -0500 From: Cat Okita To: "Marc G. Fournier" cc: soward@service1.uky.edu, smp@FreeBSD.org, current@FreeBSD.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Tue, 12 Nov 1996, Marc G. Fournier wrote: > ATX case? What is ATX? ATX is a baseboard mechanical specification that addresses shortcomings in the Baby AT design. Think of ATX as a Baby AT board rotated 90 degrees so that the long side is to the rear of the chassis. This allows designers to add more on-board I/O, if they want. In addition, CPU and SIMM sockets are relocated to improve accessibility and eliminate interference with expansion slots. What are the main advantages? The ATX form-factor provides big advantages for manufacturers, integrators, and users of personal computers. For PC manufacturers, ATX brings the following benefits: 7 ATX allows use of higher integration and better design to reduce total system cost More on board I/O connectors reduce internal cabling and improve manufacturability 7 Relocated CPU and SIMM sockets allow easy access and dont interfere with add-in cards 7 All expansion slots support full length add-in cards 7 Improved layout allows a single fan to cool the entire baseboard, reducing cost and improving system acoustics 7 Double height flexible I/O supports multimedia requirements and highly integrated designs 7 Higher integration and less cabling means fewer emissions problems and easier CE mark certification with ATX based products 7 I/O supports future requirements like USB, video in/out, TV in/out, cable and ISDN 7 Single power connector located near the processor simplifies manufacturing and improves power trace routing 7 Floppy and IDE connectors are located close to peripheral bays to allow shorter cables 7 Mounting holes are defined to ease transition from Baby AT, allowing chassis to be designed that can accept ATX or Baby AT boards with minimal modification Advantages for Integrators and VARs For systems integrators and Value Added Resellers (VARs), ATX greatly eases the integration effort. With higher integration systems, there is less cable clutter and there are more empty expansion slots left for add-in card configuration; also, since the CPU and memory are relocated, these slots are all full length. Advantages for End Users For end users, ATX means better designed systems that are quieter, more reliable, easier to upgrade and easier to service. The improved layout gives the end user easy access to key components like memory and CPU sites, making upgrades much easier. Since all expansion slots in ATX systems are full length, end users need have no worries on fitting the latest full length multimedia upgrade boards in their systems. From owner-freebsd-smp Tue Nov 12 09:35:06 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA07792 for smp-outgoing; Tue, 12 Nov 1996 09:35:06 -0800 (PST) Received: from troll.uunet.ca (troll.uunet.ca [142.77.1.10]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA07718; Tue, 12 Nov 1996 09:34:22 -0800 (PST) Received: from localhost by troll.uunet.ca with SMTP id <21007-14637>; Tue, 12 Nov 1996 12:34:05 -0500 Date: Tue, 12 Nov 1996 12:33:58 -0500 From: Cat Okita To: Steve Passe cc: Gene W Homicki , soward@service1.uky.edu, smp@FreeBSD.org, current@FreeBSD.org, "Marc G. Fournier" Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: <199611121629.JAA29256@clem.systemsix.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 On Tue, 12 Nov 1996, Steve Passe wrote: > In general I really like the ATX formfactor. In this case all the MB > mounts (except one) are steel posts instead of those flimsy nylon > standoffs. Don't know if this is part of the ATX standard, but it > fits great, no flexing of the MB when inserting cards! And ALL the card > slots are full length, the CPUs and stuff being to the side of the slots. > > If anyone knows of a good source of ATX cases please speak up. I've just gotten a case from 'Procase' - I'll forward more once I've got the thing out of its box *grin* Cat From owner-freebsd-smp Tue Nov 12 09:43:50 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA08380 for smp-outgoing; Tue, 12 Nov 1996 09:43:50 -0800 (PST) Received: from spinner.DIALix.COM (root@spinner.DIALix.COM [192.203.228.67]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA08335; Tue, 12 Nov 1996 09:43:01 -0800 (PST) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.2/8.8.2) with ESMTP id BAA12031; Wed, 13 Nov 1996 01:41:53 +0800 (WST) Message-Id: <199611121741.BAA12031@spinner.DIALix.COM> X-Mailer: exmh version 1.6.9 8/22/96 To: "Marc G. Fournier" cc: soward@service1.uky.edu, smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-reply-to: Your message of "Tue, 12 Nov 1996 11:40:50 EST." Date: Wed, 13 Nov 1996 01:41:52 +0800 From: Peter Wemm Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk "Marc G. Fournier" wrote: > On Tue, 12 Nov 1996, John Soward wrote: > > > > > I too have had excellent luck with this motherboard (and I too bought mine > > from Atipa, though I had somewhat less luck there ;-). I am not using the s mp > > code (yet), but I've had NT4, FreeBSD2.1.5, current, DOS, Win95, and NEXTST EP > > on it. The only things that have irked me were the need to get an ATX case, and > > ATX case? yeah, a long overdue idea. Basically, it's a standard form factor defining the shape, size etc of motherboards and has the connectors on the rear edge (serial, parallel, mouse, kbd etc) rather than floating on ribbon cables. The cpu is moved to a standard location to the right of the slots, directly in the airflow through the power supply. This means there are no obstructions in front of the slots, which are generally all full length.. Typically, this means that you take a standard baby-AT motherboard, rotate it 90 degrees anti-clockwise, and rotate the slot connectors back so they are in the same position as before. For a sample of what they look like, a (large) ATX motherboard can be seen on: http://www.tyan.com/s1668.htm and http://www.tyan.com/s1668i.jpg (no comment on the motherboard, this was just the first ATX picture I could find in my bookmarks :-) > Marc G. Fournier scrappy@ki.net > Systems Administrator @ ki.net scrappy@freebsd.org > Cheers, -Peter From owner-freebsd-smp Tue Nov 12 09:47:45 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA08609 for smp-outgoing; Tue, 12 Nov 1996 09:47:45 -0800 (PST) Received: from mx.serv.net (mx.serv.net [199.201.191.10]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA08580; Tue, 12 Nov 1996 09:47:16 -0800 (PST) Received: from MindBender.serv.net by mx.serv.net (8.7.5/SERV Revision: 2.30) id JAA18456; Tue, 12 Nov 1996 09:46:49 -0800 (PST) Received: from localhost.HeadCandy.com (michaelv@localhost.HeadCandy.com [127.0.0.1]) by MindBender.serv.net (8.7.5/8.7.3) with SMTP id JAA06447; Tue, 12 Nov 1996 09:46:43 -0800 (PST) Message-Id: <199611121746.JAA06447@MindBender.serv.net> X-Authentication-Warning: MindBender.serv.net: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: Andreas Klemm cc: "Marc G. Fournier" , Steve Passe , smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-reply-to: Your message of Tue, 12 Nov 96 12:26:01 +0100. Date: Tue, 12 Nov 1996 09:46:42 -0800 From: "Michael L. VanLoon -- HeadCandy.com" Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >Many people say, that it's better to choose a > - 200 MHz CPU instead of a 180 MHz CPU > - 166 MHz CPU instead of a 150 MHz CPU > - 133 MHz CPU instead of a 150 MHz CPU These are OK, although I'd put "166 MHz CPU instead of a 180"... > - 100 MHz CPU instead of a 120 MHz CPU No, in my experience, a 120 is actually faster than a 100 for everything I've benchmarked. The 120 is 20% faster than a 100, but the advantage is much smaller than that. The difference is small enough that I can say that a 133 will probably be faster than a 150 in most cases, and a 166 will definitely be faster than a 180, in almost every case. Note also that these are specifically Pentiums. Pentium Pros and/or Cyrix 6x86s might have totally different characteristics (but I would expect them to roughly follow the same trend). ----------------------------------------------------------------------------- Michael L. VanLoon michaelv@MindBender.serv.net --< 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... ----------------------------------------------------------------------------- From owner-freebsd-smp Tue Nov 12 09:56:42 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA09298 for smp-outgoing; Tue, 12 Nov 1996 09:56:42 -0800 (PST) Received: from mx.serv.net (mx.serv.net [199.201.191.10]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA09266; Tue, 12 Nov 1996 09:56:22 -0800 (PST) Received: from MindBender.serv.net by mx.serv.net (8.7.5/SERV Revision: 2.30) id JAA18697; Tue, 12 Nov 1996 09:56:15 -0800 (PST) Received: from localhost.HeadCandy.com (michaelv@localhost.HeadCandy.com [127.0.0.1]) by MindBender.serv.net (8.7.5/8.7.3) with SMTP id JAA06618; Tue, 12 Nov 1996 09:56:09 -0800 (PST) Message-Id: <199611121756.JAA06618@MindBender.serv.net> X-Authentication-Warning: MindBender.serv.net: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: "Marc G. Fournier" cc: Steve Passe , smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-reply-to: Your message of Tue, 12 Nov 96 03:46:11 -0500. Date: Tue, 12 Nov 1996 09:56:09 -0800 From: "Michael L. VanLoon -- HeadCandy.com" Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >>I recommend 64meg of parity. Don't really have direct knowledge of EDO vs not. > Hrmmm...I had thought that EDO RAM was better because it had >'on chip' cache or something like that ... Uh, no. EDO RAM simply takes less clock cycles per access than standard (or FPM) RAM. And EDO isn't more expensive. It hasn't been for many months. Parity RAM will be more expensive (not that I'm saying you shouldn't buy it). >> > How about Hard Drive? atipa doesn't list Seagates, that I can find, >> >and recent experiencees with Quantum are steering me clear of them. >>atipa carries a rather limited selection in general, just how they do business. >> I would suggest getting the drive from someplace that carries what you want. A place I have been generall happy with: http://www.basoncomputer.com/. > Does anyone have any recommendations on drives? Or, any drives >in particular I should stick away from? I heard that SeaGate went downhill >for awhile there...anyone have a current opinion of them? The IBM drives appear to be particularly good values at the moment. ----------------------------------------------------------------------------- Michael L. VanLoon michaelv@MindBender.serv.net --< 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... ----------------------------------------------------------------------------- From owner-freebsd-smp Tue Nov 12 10:01:26 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA09684 for smp-outgoing; Tue, 12 Nov 1996 10:01:26 -0800 (PST) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id KAA09538; Tue, 12 Nov 1996 10:00:29 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id KAA29886; Tue, 12 Nov 1996 10:59:11 -0700 Message-Id: <199611121759.KAA29886@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: Cat Okita cc: "Marc G. Fournier" , soward@service1.uky.edu, smp@FreeBSD.org, current@FreeBSD.org, freebsd-hardware@FreeBSD.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-reply-to: Your message of "Tue, 12 Nov 1996 12:32:59 EST." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 12 Nov 1996 10:59:10 -0700 Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi, Last message to -current Lets move this from -current to hardware where it belongs (keep smp, please) -- Steve Passe | powered by smp@csn.net | FreeBSD From owner-freebsd-smp Tue Nov 12 10:18:16 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA10894 for smp-outgoing; Tue, 12 Nov 1996 10:18:16 -0800 (PST) Received: from shadows.aeon.net (bsdcur@shadows.aeon.net [194.100.41.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA10791; Tue, 12 Nov 1996 10:17:16 -0800 (PST) Received: (from bsdcur@localhost) by shadows.aeon.net (8.7.5/8.6.9) id UAA02970; Tue, 12 Nov 1996 20:16:39 +0200 (EET) From: mika ruohotie Message-Id: <199611121816.UAA02970@shadows.aeon.net> Subject: Re: GigaByte GA-586DX-512 Motherboard To: scrappy@ki.net (Marc G. Fournier) Date: Tue, 12 Nov 1996 20:16:39 +0200 (EET) Cc: smp@freebsd.org, current@freebsd.org In-Reply-To: from "Marc G. Fournier" at "Nov 12, 96 00:16:02 am" X-Mailer: ELM [version 2.4ME+ PL22 (25)] 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 > Apparantly they have had a great deal of problems with this board and are not > > Can anyone comment on this? I've always had good dealing with > the ASUS brand of motherboards, but is there an equivalent ASUS motherboard > that ppl would recommend? well. i've used the DX board for a while, but not with dual cpu's... didnt have any reasonable way to get smp part at the time... too bad. and i had no problems whatsoever with it running freebsd... > I'm wondering if their "great deal of problems" might have been > with earlier models, and they just said to hell with carrying it altogether? i have no idea. unless. the board is _very_ picky about what kinds ram you throw into it. if it's edo/true parity ram, expect probs unless it's high quolity ram. example. with poor ram i got easy crashes when the parity check was on, finally it messed up the inodes from sd0a. then i turned that off, and got signal 11's and strange errors with cc... and _all_ that went away right after i changed the ram, now the servers are very happy... and for the record the asus boards are not bug free either. and what makes the said DX interesting is the onboard aic7880, since the board is _cheaper_ than a HX and 2940UW PCI card. atleast here. anyway, i prefer the said board over asus any day coz of the six simm slots and the _easy_ dip switch (only 4) speed configuring... ofcourse, since the latest asus supports these incredible bus speeds, it gets pretty tempting, but. (notice that i havent got my hands on tyans so far) and i _do_ run the servers at work now using the HX version. which is very close to the DX in any ways. while i'm posting, anyone got any information from the TX chipset? since _that_ is something i am interested in testing. gigabyte will have a board out with that chipset very soon after it's out i've been told. > Marc G. Fournier scrappy@ki.net > Systems Administrator @ ki.net scrappy@freebsd.org mickey -- mika ruohotie mika@aeon.net From owner-freebsd-smp Tue Nov 12 10:21:20 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA11390 for smp-outgoing; Tue, 12 Nov 1996 10:21:20 -0800 (PST) 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 KAA11321; Tue, 12 Nov 1996 10:20:49 -0800 (PST) Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id LAA20558; Tue, 12 Nov 1996 11:09:20 -0700 From: Terry Lambert Message-Id: <199611121809.LAA20558@phaeton.artisoft.com> Subject: Re: GigaByte GA-586DX-512 Motherboard To: cat@uunet.ca (Cat Okita) Date: Tue, 12 Nov 1996 11:09:20 -0700 (MST) Cc: scrappy@ki.net, soward@service1.uky.edu, smp@FreeBSD.org, current@FreeBSD.org In-Reply-To: from "Cat Okita" at Nov 12, 96 12:32:59 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 > For end users, ATX means better designed systems > that are quieter, more reliable, easier to upgrade > and easier to service. The improved layout gives the > end user easy access to key components like memory > and CPU sites, making upgrades much easier. Since all > expansion slots in ATX systems are full length, end > users need have no worries on fitting the latest full > length multimedia upgrade boards in their systems. Unless their systems have standard cases... (sorry, couldn't resist). 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 Tue Nov 12 11:26:14 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA15624 for smp-outgoing; Tue, 12 Nov 1996 11:26:14 -0800 (PST) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id LAA15537; Tue, 12 Nov 1996 11:25:41 -0800 (PST) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id UAA27223; Tue, 12 Nov 1996 20:15:46 +0100 (MET) Received: from localhost (localhost [127.0.0.1]) by klemm.gtn.com (8.8.2/8.8.2) with SMTP id SAA13298; Tue, 12 Nov 1996 18:56:42 +0100 (MET) Date: Tue, 12 Nov 1996 18:56:42 +0100 (MET) From: Andreas Klemm To: "Rodney W. Grimes" cc: scrappy@ki.net, smp@csn.net, smp@FreeBSD.org, current@FreeBSD.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: <199611121629.IAA15688@GndRsh.aac.dev.com> Message-ID: X-try-apsfilter: ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz X-Fax: +49 2137 2018 X-Phone: +49 2137 2020 MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Tue, 12 Nov 1996, Rodney W. Grimes wrote: > > Quantum Atlas 2GB, the 4GB modell is too loud for a home environment. > > Both drives have 1 MB cache ! > > I'll correct that, the 4GB model has a 2MB cache on it... Oh wow ! Thanks for correcting me. BTW, the German PC magazine C't made a harddisk test, they also gave information about the noise, the several disks produce (in DB and a sone factor). Be careful if you want to get a 4GB harddisk with 7200 U/min for home environment. I successfully sold a Grand Prix 4GB and bought 2 2GB IBM DORS 32160. ;) -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-smp Tue Nov 12 13:26:50 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA28070 for smp-outgoing; Tue, 12 Nov 1996 13:26:50 -0800 (PST) Received: from GndRsh.aac.dev.com (GndRsh.aac.dev.com [198.145.92.241]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id NAA28039; Tue, 12 Nov 1996 13:26:29 -0800 (PST) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id NAA17321; Tue, 12 Nov 1996 13:24:27 -0800 (PST) From: "Rodney W. Grimes" Message-Id: <199611122124.NAA17321@GndRsh.aac.dev.com> Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: <199611121756.JAA06618@MindBender.serv.net> from "Michael L. VanLoon -- HeadCandy.com" at "Nov 12, 96 09:56:09 am" To: michaelv@MindBender.serv.net (Michael L. VanLoon -- HeadCandy.com) Date: Tue, 12 Nov 1996 13:24:27 -0800 (PST) Cc: scrappy@ki.net, smp@csn.net, smp@freebsd.org, current@freebsd.org X-Mailer: ELM [version 2.4ME+ PL25 (25)] 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 > > >>I recommend 64meg of parity. Don't really have direct knowledge of EDO vs not. > > > Hrmmm...I had thought that EDO RAM was better because it had > >'on chip' cache or something like that ... > > Uh, no. EDO RAM simply takes less clock cycles per access than > standard (or FPM) RAM. You should go read some technical specifications before you make such statements. The actual access time changes very very little between EDO (``Extended Data Out'') and FPM (``Fast Page Mode''). The only real effective difference is that EDO memory holds it's data outputs valid after CAS goes back high, allowing a wider and slopper data latching. This _can_ lead to elimination of wait states in poor designs, but does zilch in good designs, since good designs don't need the added 15nS of valid data out as they latch the data in the 5 to 6nS window you get when running FPM at minimum timings. Note that the cycle time for EDO vs FPM is IDENTICAL for every manufactures data sheet I have looked at. Real memory bandwidth is a direct function of cycle time, and has nothing to do with access times. Access times are for wimps, real memory designers work with cycle times :-) :-). You can not transfer 1MB of data out of EDO memory any faster than you can transfer 1MB of data out of FPM. Period. Look over the data sheets, study memory design, _know_ before you speak. Also note that the ``access'' time difference is usually less than 5nS and due to other timing constraints you can rarely if ever take advantage of this. -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation, Inc. Reliable computers for FreeBSD From owner-freebsd-smp Tue Nov 12 22:47:17 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id WAA28474 for smp-outgoing; Tue, 12 Nov 1996 22:47:17 -0800 (PST) Received: from mx.serv.net (mx.serv.net [199.201.191.10]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id WAA28469; Tue, 12 Nov 1996 22:47:11 -0800 (PST) Received: from MindBender.serv.net by mx.serv.net (8.7.5/SERV Revision: 2.30) id WAA11475; Tue, 12 Nov 1996 22:47:17 -0800 (PST) Received: from localhost.HeadCandy.com (michaelv@localhost.HeadCandy.com [127.0.0.1]) by MindBender.serv.net (8.7.5/8.7.3) with SMTP id WAA08610; Tue, 12 Nov 1996 22:47:02 -0800 (PST) Message-Id: <199611130647.WAA08610@MindBender.serv.net> X-Authentication-Warning: MindBender.serv.net: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: "Rodney W. Grimes" cc: scrappy@ki.net, smp@csn.net, smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard In-reply-to: Your message of Tue, 12 Nov 96 13:24:27 -0800. <199611122124.NAA17321@GndRsh.aac.dev.com> Date: Tue, 12 Nov 1996 22:47:01 -0800 From: "Michael L. VanLoon -- HeadCandy.com" Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >> >>I recommend 64meg of parity. Don't really have direct knowledge of EDO vs not. >> > Hrmmm...I had thought that EDO RAM was better because it had >> >'on chip' cache or something like that ... >> Uh, no. EDO RAM simply takes less clock cycles per access than >> standard (or FPM) RAM. >You should go read some technical specifications before you make such >statements. The actual access time changes very very little between >EDO (``Extended Data Out'') and FPM (``Fast Page Mode''). The only >real effective difference is that EDO memory holds it's data outputs [...] No thank you. I have enough to keep me very busy already. I am not a hardware engineer. I understand the _effect_ of running EDO RAM, and that is that cycle times can generally be shorter, in typical modern motherboards. You can argue about the electical intricacies if you want, but I have better things to do. I'm sure you know what you're talking about, and I may get around to looking at this info some time in the future (I am always curious about the intricacies of the hardware, and generally understand it fairly well). But right now, I don't have the time. How am I wrong in stating that "the effect of running EDO RAM in a typical modern motherboard is that you can run with shorter cycle times"? ----------------------------------------------------------------------------- Michael L. VanLoon michaelv@MindBender.serv.net --< 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... ----------------------------------------------------------------------------- From owner-freebsd-smp Wed Nov 13 00:20:31 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA02224 for smp-outgoing; Wed, 13 Nov 1996 00:20:31 -0800 (PST) Received: from trapdoor.aracnet.com (trapdoor.aracnet.com [204.188.47.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id AAA02198; Wed, 13 Nov 1996 00:20:25 -0800 (PST) Received: from cbrowni2-home (ppp-u20.aracnet.com [204.188.47.149]) by trapdoor.aracnet.com (8.7.4/8.6.9) with SMTP id AAA05424; Wed, 13 Nov 1996 00:13:46 -0800 Message-ID: <3289833E.571F@aracnet.com> Date: Wed, 13 Nov 1996 00:13:50 -0800 From: Chris Browning Reply-To: cbrown@aracnet.com X-Mailer: Mozilla 3.01 (WinNT; U) MIME-Version: 1.0 To: "Michael L. VanLoon -- HeadCandy.com" CC: "Rodney W. Grimes" , scrappy@ki.net, smp@csn.net, smp@freebsd.org, current@freebsd.org Subject: Re: GigaByte GA-586DX-512 Motherboard References: <199611130647.WAA08610@MindBender.serv.net> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Michael L. VanLoon -- HeadCandy.com wrote: > > >> >>I recommend 64meg of parity. Don't really have direct knowledge of EDO vs not. > > >> > Hrmmm...I had thought that EDO RAM was better because it had > >> >'on chip' cache or something like that ... > > >> Uh, no. EDO RAM simply takes less clock cycles per access than > >> standard (or FPM) RAM. > > >You should go read some technical specifications before you make such > >statements. The actual access time changes very very little between > >EDO (``Extended Data Out'') and FPM (``Fast Page Mode''). The only > >real effective difference is that EDO memory holds it's data outputs > [...] > > No thank you. I have enough to keep me very busy already. > > I am not a hardware engineer. I understand the _effect_ of running > EDO RAM, and that is that cycle times can generally be shorter, in > typical modern motherboards. > > You can argue about the electical intricacies if you want, but I have > better things to do. I'm sure you know what you're talking about, and > I may get around to looking at this info some time in the future (I am > always curious about the intricacies of the hardware, and generally > understand it fairly well). But right now, I don't have the time. > > How am I wrong in stating that "the effect of running EDO RAM in a > typical modern motherboard is that you can run with shorter cycle > times"? Ok, I will try to answer this. I recommend that we take any future replies off the list. What the previous gentleman was telling you is correct. Both of your statements are incorrect. The cycle time and # of clock cycles to access EDO and FP RAM is approximately the same. Maybe there is confusion here because you are using some very specific terms used to spec memory but I don't think that is what you are intending to say. The cycle time of memory is how fast you can access the same cell of memory sequentially. This is pretty much the same for EDO & FP. The number of clocks that it takes to access memory will be about the same for EDO & FP. Both of these items are determined by the technology used to implement the chips on the S(D)IMMS, which will be the same for both EDO & FP. Both of these really don't talk about the differences between EDO and FP. What makes EDO RAM attractive is the fact that once you have paid the penality to get to memory, you can get a whole row without much additional overhead. This is a kind of "bursting", if you will. This way, if you are getting a lot of sequential bytes, then you pay one large delay to get to memory and a small subsequent delay to get to the adjacent bytes. With FP, on the other hand, you would incur the same large delay to get all the bytes (assuming no interleaving). Unfortunately, some of the advantage of EDO is hidden by the cache. If you have to go to memory, the processor will get the byte (word, etc) that it wanted and the EDO fill will all go to the cache. This makes for faster cache fills, but the processor didn't really see any of the advantage. Well, I hope this help. Again, lets take this off the list. Thanks, Chris From owner-freebsd-smp Wed Nov 13 10:45:37 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA05341 for smp-outgoing; Wed, 13 Nov 1996 10:45:37 -0800 (PST) Received: from shadows.aeon.net (bsdcur@shadows.aeon.net [194.100.41.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA05302; Wed, 13 Nov 1996 10:45:16 -0800 (PST) Received: (from bsdcur@localhost) by shadows.aeon.net (8.7.5/8.6.9) id UAA12163; Wed, 13 Nov 1996 20:40:32 +0200 (EET) From: mika ruohotie Message-Id: <199611131840.UAA12163@shadows.aeon.net> Subject: Re: GigaByte GA-586DX-512 Motherboard To: cat@uunet.ca (Cat Okita) Date: Wed, 13 Nov 1996 20:40:31 +0200 (EET) Cc: smp@csn.net, gwh@spiders.com, soward@service1.uky.edu, smp@FreeBSD.org, current@FreeBSD.org, scrappy@ki.net In-Reply-To: from Cat Okita at "Nov 12, 96 12:33:58 pm" X-Mailer: ELM [version 2.4ME+ PL22 (25)] 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 > > If anyone knows of a good source of ATX cases please speak up. > I've just gotten a case from 'Procase' - I'll forward more once I've got > the thing out of its box *grin* we use macase, the ztx box took a while to come out but looks really good... unlike the _all_ others i've seen, it has space for disks, still is not huge, and most of all the power switch allows either the "atx power" type or "baby-at power" type of powers... anyone know what i mean? well, ok... so i thought... but anyway. > Cat mickey From owner-freebsd-smp Wed Nov 13 13:24:02 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA17239 for smp-outgoing; Wed, 13 Nov 1996 13:24:02 -0800 (PST) Received: from troll.uunet.ca (troll.uunet.ca [142.77.1.10]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id NAA17215; Wed, 13 Nov 1996 13:23:40 -0800 (PST) Received: from localhost by troll.uunet.ca with SMTP id <21006-23369>; Wed, 13 Nov 1996 16:23:20 -0500 Date: Wed, 13 Nov 1996 16:23:19 -0500 From: Cat Okita To: mika ruohotie cc: smp@csn.net, gwh@spiders.com, soward@service1.uky.edu, smp@FreeBSD.org, current@FreeBSD.org, scrappy@ki.net Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: <199611131840.UAA12163@shadows.aeon.net> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Wed, 13 Nov 1996, mika ruohotie wrote: > > I've just gotten a case from 'Procase' - I'll forward more once I've got > > the thing out of its box *grin* > we use macase, the ztx box took a while to come out but looks really > good... unlike the _all_ others i've seen, it has space for disks, > still is not huge, and most of all the power switch allows either > the "atx power" type or "baby-at power" type of powers... The Procase box isn't bad: 3 5.25 bays 4 3.5 bays ATX power reasonable ammount of power plugs (had to add one splitter) 230W power supply Medium tower case The only thing that I don't like about this case is not having the removable side - mounting the MB was simple (and would have been simpler if I'd read the stuff on the face plate :<), and the clip ins were nice. The 3.5" 'bays' can be removed, for ease of installation, and they ship faceplates and 'tailplates' for all of the bays. There's plenty of room to work in, and room for an extra fan, if you want one :> Cat From owner-freebsd-smp Wed Nov 13 13:37:22 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA18061 for smp-outgoing; Wed, 13 Nov 1996 13:37:22 -0800 (PST) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id NAA18026; Wed, 13 Nov 1996 13:37:02 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id OAA07786; Wed, 13 Nov 1996 14:34:52 -0700 Message-Id: <199611132134.OAA07786@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: Cat Okita cc: mika ruohotie , gwh@spiders.com, soward@service1.uky.edu, smp@FreeBSD.org, hardware@FreeBSD.org, scrappy@ki.net Subject: Re: GigaByte GA-586DX-512 Motherboard In-reply-to: Your message of "Wed, 13 Nov 1996 16:23:19 EST." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 13 Nov 1996 14:34:52 -0700 Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi, > The Procase box isn't bad: > ... > side - mounting the MB was simple (and would have been simpler if I'd read > the stuff on the face plate :<), and the clip ins were nice. are the motherboard mount points the traditional "nylon + 2 metal studs", or are they all metal? -- Steve Passe | powered by smp@csn.net | FreeBSD -----BEGIN PGP PUBLIC KEY BLOCK----- Version: 2.6.2 mQCNAzHe7tEAAAEEAM274wAEEdP+grIrV6UtBt54FB5ufifFRA5ujzflrvlF8aoE 04it5BsUPFi3jJLfvOQeydbegexspPXL6kUejYt2OeptHuroIVW5+y2M2naTwqtX WVGeBP6s2q/fPPAS+g+sNZCpVBTbuinKa/C4Q6HJ++M9AyzIq5EuvO0a8Rr9AAUR tBlTdGV2ZSBQYXNzZSA8c21wQGNzbi5uZXQ+ =ds99 -----END PGP PUBLIC KEY BLOCK----- From owner-freebsd-smp Wed Nov 13 13:38:53 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA18165 for smp-outgoing; Wed, 13 Nov 1996 13:38:53 -0800 (PST) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id NAA18140; Wed, 13 Nov 1996 13:38:32 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id OAA07797; Wed, 13 Nov 1996 14:35:04 -0700 Message-Id: <199611132135.OAA07797@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: Cat Okita cc: mika ruohotie , gwh@spiders.com, soward@service1.uky.edu, smp@FreeBSD.org, hardware@FreeBSD.org, scrappy@ki.net Subject: Re: GigaByte GA-586DX-512 Motherboard In-reply-to: Your message of "Wed, 13 Nov 1996 16:23:19 EST." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 13 Nov 1996 14:35:04 -0700 Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi, > The Procase box isn't bad: > ... > side - mounting the MB was simple (and would have been simpler if I'd read > the stuff on the face plate :<), and the clip ins were nice. are the motherboard mount points the traditional "nylon + 2 metal studs", or are they all metal? -- Steve Passe | powered by smp@csn.net | FreeBSD -----BEGIN PGP PUBLIC KEY BLOCK----- Version: 2.6.2 mQCNAzHe7tEAAAEEAM274wAEEdP+grIrV6UtBt54FB5ufifFRA5ujzflrvlF8aoE 04it5BsUPFi3jJLfvOQeydbegexspPXL6kUejYt2OeptHuroIVW5+y2M2naTwqtX WVGeBP6s2q/fPPAS+g+sNZCpVBTbuinKa/C4Q6HJ++M9AyzIq5EuvO0a8Rr9AAUR tBlTdGV2ZSBQYXNzZSA8c21wQGNzbi5uZXQ+ =ds99 -----END PGP PUBLIC KEY BLOCK----- From owner-freebsd-smp Wed Nov 13 13:44:38 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA18639 for smp-outgoing; Wed, 13 Nov 1996 13:44:38 -0800 (PST) Received: from troll.uunet.ca (troll.uunet.ca [142.77.1.10]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id NAA18615; Wed, 13 Nov 1996 13:44:24 -0800 (PST) Received: from localhost by troll.uunet.ca with SMTP id <21006-22792>; Wed, 13 Nov 1996 16:44:18 -0500 Date: Wed, 13 Nov 1996 16:44:15 -0500 From: Cat Okita To: Steve Passe cc: mika ruohotie , gwh@spiders.com, soward@service1.uky.edu, smp@FreeBSD.org, hardware@FreeBSD.org, scrappy@ki.net Subject: Re: GigaByte GA-586DX-512 Motherboard In-Reply-To: <199611132135.OAA07797@clem.systemsix.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 On Wed, 13 Nov 1996, Steve Passe wrote: > are the motherboard mount points the traditional "nylon + 2 metal studs", > or are they all metal? They're coloured silver, but are way too light to be most metals. Basically, they just clip into the appropriate point on the board (much nicer than the silly nylong things), and you then screw the MB into them. Hope this helps, Cat From owner-freebsd-smp Sat Nov 16 14:11:25 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA23613 for smp-outgoing; Sat, 16 Nov 1996 14:11:25 -0800 (PST) Received: from critter.tfs.com ([140.145.230.177]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id OAA23606 for ; Sat, 16 Nov 1996 14:11:16 -0800 (PST) Received: from critter.tfs.com (localhost.phk.dk [127.0.0.1]) by critter.tfs.com (8.8.2/8.8.2) with ESMTP id XAA06616 for ; Sat, 16 Nov 1996 23:11:19 +0100 (MET) To: smp@freebsd.org Subject: ctm warning Reply-to: phk@freebsd.org Date: Sat, 16 Nov 1996 23:11:18 +0100 Message-ID: <6614.848182278@critter.tfs.com> From: Poul-Henning Kamp Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I moved the smp CTM generation to the new mkCTM and promptly found a bug in it. In delta #50 you will find that CVSROOT/val-tags is being sent to you, if you already have that file, remove it before you apply #50. Peter can tell you if this is horrible. Sorry about this. -- 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 Sat Nov 16 14:26:03 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA24012 for smp-outgoing; Sat, 16 Nov 1996 14:26:03 -0800 (PST) Received: from spinner.DIALix.COM (root@spinner.DIALix.COM [192.203.228.67]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id OAA24003; Sat, 16 Nov 1996 14:25:31 -0800 (PST) Received: from spinner.DIALix.COM (peter@localhost.DIALix.oz.au [127.0.0.1]) by spinner.DIALix.COM (8.8.2/8.8.2) with ESMTP id GAA15211; Sun, 17 Nov 1996 06:24:57 +0800 (WST) Message-Id: <199611162224.GAA15211@spinner.DIALix.COM> X-Mailer: exmh version 1.6.9 8/22/96 To: phk@freebsd.org cc: smp@freebsd.org Subject: Re: ctm warning In-reply-to: Your message of "Sat, 16 Nov 1996 23:11:18 +0100." <6614.848182278@critter.tfs.com> Date: Sun, 17 Nov 1996 06:24:56 +0800 From: Peter Wemm Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Poul-Henning Kamp wrote: > > I moved the smp CTM generation to the new mkCTM and promptly found a > bug in it. In delta #50 you will find that CVSROOT/val-tags is > being sent to you, if you already have that file, remove it before > you apply #50. > > Peter can tell you if this is horrible. > > Sorry about this. No real problem, just do as suggested.. cvs creates this file as a cache to avoid unnecessary scans of the cvs tree. If you get rid of it, it's no big deal. Cheers, -Peter From owner-freebsd-smp Sat Nov 16 17:28:59 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id RAA02996 for smp-outgoing; Sat, 16 Nov 1996 17:28:59 -0800 (PST) Received: from uruk.org (root@ns.uruk.org [198.145.95.253]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id RAA02989 for ; Sat, 16 Nov 1996 17:28:47 -0800 (PST) Received: from uruk.org [127.0.0.1] (erich) by uruk.org with esmtp (Exim 0.53 #1) id E0vOw7F-0004Hy-00; Sat, 16 Nov 1996 17:33:45 -0800 To: smp@freebsd.org Subject: Can test again... Date: Sat, 16 Nov 1996 17:33:44 -0800 From: Erich Boleyn Message-Id: Sender: owner-smp@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi all. FreeBSD's PCI code and the support for the EISA network card I have didn't work for a while, but I just got the 2.2-ALPHA distribution, and it works great (kudos to those who have been working on it). I grabbed the SMP tree, and have been hacking on it a bit. What I've noticed so far are: -- mptable-2.0.2.c AND the kernel : Both do the MPS floating pointer probe wrong. They are searching on 4-byte boundaries (it should be 16-byte boundaries), and search too many areas. This caused my test machine to not be recognized correctly. The proper probe sequence is to search (again, on 16-byte boundaries): (1) If the EBDA is defined: -- The first kilobyte of the EBDA else: -- The last kilobyte of system base memory. (2) ROM space between 0xF0000 and 0xFFFFF. If you find it anywhere else, it might be a false report (as mentioned, it did on my test box). -- If you have more than NCPU cpus it dies instead of just ignoring the other CPUs. -- If NCPU is greater than 2, then it dies trying to activate the 3rd CPU. I've hacked it so that can only activate 2 CPUs, and that seems to work for the moment. I'll try out the IO APIC stuff and see about getting EISA interrupts. -- Erich Stefan Boleyn \_ E-mail (preferred): Mad Genius wanna-be, CyberMuffin \__ (finger me for other stats) Web: http://www.uruk.org/~erich/ Motto: "I'll live forever or die trying" From owner-freebsd-smp Sat Nov 16 18:31:00 1996 Return-Path: owner-smp Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA16318 for smp-outgoing; Sat, 16 Nov 1996 18:31:00 -0800 (PST) Received: from clem.systemsix.com (clem.systemsix.com [198.99.86.131]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id SAA16289 for ; Sat, 16 Nov 1996 18:30:55 -0800 (PST) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id TAA00833; Sat, 16 Nov 1996 19:30:13 -0700 Message-Id: <199611170230.TAA00833@clem.systemsix.com> X-Authentication-Warning: clem.systemsix.com: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.5 12/11/95 From: Steve Passe To: Erich Boleyn cc: smp@FreeBSD.org Subject: Re: Can test again... In-reply-to: Your message of "Sat, 16 Nov 1996 17:33:44 PST." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sat, 16 Nov 1996 19:30:13 -0700 Sender: owner-smp@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi, >I grabbed the SMP tree, and have been hacking on it a bit. > >What I've noticed so far are: > > -- mptable-2.0.2.c AND the kernel : Both do the MPS floating pointer > probe wrong. They are searching on 4-byte boundaries (it should > be 16-byte boundaries), and search too many areas. This caused > my test machine to not be recognized correctly. > > The proper probe sequence is to search (again, on 16-byte > boundaries): > > If you find it anywhere else, it might be a false report (as > mentioned, it did on my test box). You may be right about the 16-byte boundaries, I'll think about that a little. mptable purposely searches areas it shouldn't. Unfortunately there is the MP spec, and there is the way various manufactures have implimented it. I would have to review my collection of mptable outputs to verify that it can indeed be that strict in search areas. This is the 1st report of a found "false" area, usual problem is not finding it at all. Please give me info about: what board are you using? which area was probed, finding a "false" MP fps? --- > -- If you have more than NCPU cpus it dies instead of just ignoring > the other CPUs. are you saying that when you set NCPU==2, but there are 3/4 actual CPUs that this happens? > -- If NCPU is greater than 2, then it dies trying to activate the > 3rd CPU. is this a restatement of the previous statement? It is known that 3/4 CPUs are not supported. Peter was last working on that, I'm not sure what the current status is... --- > I've hacked it so that can only activate 2 CPUs, and that seems to work for the moment. send the patch when you can. also please send your mptable output: mptable -verbose -dmesg --- > I'll try out the IO APIC stuff and see about getting EISA interrupts. any insight here would be most appreciated! -- Steve Passe | powered by smp@csn.net | FreeBSD