From owner-freebsd-hardware Sun Sep 15 01:21:54 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id BAA09271 for hardware-outgoing; Sun, 15 Sep 1996 01:21:54 -0700 (PDT) Received: from dns2.noc.best.net (dns2.noc.best.net [206.86.0.21]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id BAA09265; Sun, 15 Sep 1996 01:21:51 -0700 (PDT) Received: from shellx.best.com (shellx.best.com [206.86.0.11]) by dns2.noc.best.net (8.6.12/8.6.5) with SMTP id BAA24785; Sun, 15 Sep 1996 01:21:45 -0700 Date: Sun, 15 Sep 1996 01:21:45 -0700 (PDT) From: Amanda Chou To: "Michael L. VanLoon -- HeadCandy.com" cc: questions@freebsd.org, hackers@freebsd.org, hardware@freebsd.org Subject: Re: Q: Tyan Tomcat I with > 64MB RAM In-Reply-To: <199609140341.UAA04018@MindBender.serv.net> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Fri, 13 Sep 1996, Michael L. VanLoon -- HeadCandy.com wrote: > > >Has anyone used Tyan Tomcat I with more than 64MB RAM? We ran into some > >weird problems; it works fine when we just put 64MB EDO RAM, but it got > >panicked at booting or some other random time when we put more than 64MB > >EDO RAM. We followed the manual and changed its jumper setting, added one > >more 32K X 8K SRAM; we changed the Award BIOS to make it able to recongnize > >the memory up to 512MB; we added an option so it'll work with 128MB RAM. > >Any idea? > > I'm not sure I followed everything you just tried to say. Oh, what I tried to say was that we tried _everything_ to make Tyan TomcatI motherboard to be happy with memory more than 64MB. > However, have you tested the memory by itself to make sure you don't > have a bad chip? Yes, we did; I replaced one bad SIMM. Actually we solved the problem already, and the solution is fairly simple (but not terribly obvious). I got those 8 16MB EDO RAMs from two different places: Fry's and Chip Merchant. Fry's get their chips from different suppliers, while Chip Merchant get theirs only from one place. As soon as we put Fry's RAM in lower banks and Chip Merchant's in the higher banks, bingo, it started working! The lesson we learned is: try to get all your memory made from the same factory if you try to build a system with more than 64MB RAM. Amanda From owner-freebsd-hardware Sun Sep 15 03:54:50 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id DAA13937 for hardware-outgoing; Sun, 15 Sep 1996 03:54:50 -0700 (PDT) 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 DAA13932; Sun, 15 Sep 1996 03:54:45 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id DAA00240; Sun, 15 Sep 1996 03:53:14 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609151053.DAA00240@GndRsh.aac.dev.com> Subject: Re: Q: Tyan Tomcat I with > 64MB RAM In-Reply-To: from Amanda Chou at "Sep 15, 96 01:21:45 am" To: achou@best.com (Amanda Chou) Date: Sun, 15 Sep 1996 03:53:14 -0700 (PDT) Cc: michaelv@MindBender.serv.net, questions@freebsd.org, hackers@freebsd.org, hardware@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-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk ... > > Actually we solved the problem already, and the solution is fairly simple > (but not terribly obvious). I got those 8 16MB EDO RAMs from two different > places: Fry's and Chip Merchant. Fry's get their chips from different > suppliers, while Chip Merchant get theirs only from one place. As soon as > we put Fry's RAM in lower banks and Chip Merchant's in the higher banks, > bingo, it started working! Someone at Chip Merchant is not telling you the whole truth. They may be _buying_ all thier memory from the same memory broker, but it comes from all over the place. Just taking a sample of my last 5 orders of 32MB, 8MBx36-60nS FPM 24 chip modules I show these manufactures: LGS on 3rd party LGS with MT parity on Liteon OKI on 3rd party OKI on 3rd party SEC on 3rd party You have a very slim chance of getting the same memory 2 orders in a row from the Chip Merchant, and realize I am a manufacturer who is order in volume once or twice a week. (Okay, so now all your folks know where AAC gets good memory from :-)). > > The lesson we learned is: try to get all your memory made from the same > factory if you try to build a system with more than 64MB RAM. Let me guess that some of this EDO memory is made by someone other than Micron, yea, let me see if I can put my finger on it... could it possibly be Siemens? If so be wary, there is a huge batch of these chips floating around that appear to be marginal. -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Sun Sep 15 06:50:15 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id GAA19610 for hardware-outgoing; Sun, 15 Sep 1996 06:50:15 -0700 (PDT) Received: from diablo.ppp.de (diablo.ppp.de [193.141.101.34]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id GAA19600 for ; Sun, 15 Sep 1996 06:50:13 -0700 (PDT) Received: from allegro.lemis.de by diablo.ppp.de with smtp (Smail3.1.28.1 #1) id m0v2HaM-000QiyC; Sun, 15 Sep 96 15:50 MET DST From: grog@lemis.de (Greg Lehey) Organisation: LEMIS, Schellnhausen 2, 36325 Feldatal, Germany Phone: +49-6637-919123 Fax: +49-6637-919122 Received: (grog@localhost) by allegro.lemis.de (8.6.9/8.6.9) id OAA00535 for freebsd-hardware@FreeBSD.org; Sun, 15 Sep 1996 14:30:14 +0200 Message-Id: <199609151230.OAA00535@allegro.lemis.de> Subject: Any Pentium boards with more than 4 PCI slots? To: freebsd-hardware@FreeBSD.org (FreeBSD hardware Users) Date: Sun, 15 Sep 1996 14:30:14 +0200 (MET DST) X-Mailer: ELM [version 2.4 PL23] MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Does anybody know of Pentium boards which support more than 4 PCI slots? One of my customers has a requirement for up to 8 or 10 slots. My understanding is that this is only possible with a PCI bridge--is this correct? If so (and even if not, I suppose), how transparent is the PCI bridge to the software? How much slower is it than the direct side of the PCI bus? Are there any other gotchas? Greg From owner-freebsd-hardware Sun Sep 15 10:00:35 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA29465 for hardware-outgoing; Sun, 15 Sep 1996 10:00:35 -0700 (PDT) Received: from kodiak.ucla.edu (kodiak.ucla.edu [164.67.128.11]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA29457 for ; Sun, 15 Sep 1996 10:00:34 -0700 (PDT) Received: from elm.burris.com (elm.cns.ucla.edu [164.67.222.20]) by kodiak.ucla.edu (8.7.4/8.6.9) with SMTP id KAA25110; Sun, 15 Sep 1996 10:00:27 -0700 From: Scott Burris To: "William R. Somsky" cc: freebsd-hardware@FreeBSD.org Subject: Re: Trouble w/ Number Nine Motion 771 -- Any Help? Message-ID: Date: Sun, 15 Sep 1996 10:00:24 -0700 () Priority: NORMAL X-Mailer: Simeon for Win32 Version 4.0.9 X-Authentication: none MIME-Version: 1.0 Content-Type: TEXT/PLAIN; CHARSET=US-ASCII Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Thu, 12 Sep 1996 16:26:28 -0700 (PDT) "William R. Somsky" wrote: > > Can anybody give me any clues/leads to what's going on? Surely, with > the Number Nine's being as popular among FreeBSD'ers as they seemed, > some of you out there must have Motion 771's and succumbed to the > temptation of having a small Win95 partition of to the side to play > games on, so would have some experience w/ it's behavior under Win95. > _Is_ this typical behavior for a Motion 771? Do I need to: Fix my setup? > Get different drivers? Replace the card? Give up on the Motion 771? > Give up on Win95? (But my games!) Please, any help would be appreciated. I'm running a dual boot system with Win 95 and FreeBSD with the Motion 771 card with 4meg vram. Works like a charm. This is with a no-name motherboard Triton chipset with an NCR 825 based SCSI controller. FYI, the Number Nine driver version I'm running is (this from the status section of their control panel): Windows Driver Version: Hawkeye for S3 v1.09p Windows Disk Version: 9FX Motion Ver 2.05 (Dom) I'm not running with the soundblaster, but rather the Gravis Ultrasound PnP Pro. I did have DMA problems with my Soundblaster 16, but no idea if that would relate to your problems or not. Scott ---------------------- Scott Burris UCLA Campus Network Services scott@cns.ucla.edu From owner-freebsd-hardware Sun Sep 15 10:37:27 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA02115 for hardware-outgoing; Sun, 15 Sep 1996 10:37:27 -0700 (PDT) Received: from FileServ1.MI.Uni-Koeln.DE (FileServ1.MI.Uni-Koeln.DE [134.95.212.1]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id KAA02091 for ; Sun, 15 Sep 1996 10:37:13 -0700 (PDT) Received: from x14.mi.uni-koeln.de (annexr3-16.slip.Uni-Koeln.DE) by FileServ1.MI.Uni-Koeln.DE with SMTP id AA00314 (5.67b/IDA-1.5 for ); Sun, 15 Sep 1996 17:58:36 +0200 Received: (from se@localhost) by x14.mi.uni-koeln.de (8.7.5/8.6.9) id RAA00745; Sun, 15 Sep 1996 17:58:32 +0200 (MET DST) Date: Sun, 15 Sep 1996 17:58:32 +0200 (MET DST) Message-Id: <199609151558.RAA00745@x14.mi.uni-koeln.de> From: Stefan Esser To: grog@lemis.de (Greg Lehey) Cc: freebsd-hardware@freebsd.org (FreeBSD hardware Users) Subject: Re: Any Pentium boards with more than 4 PCI slots? In-Reply-To: <199609151230.OAA00535@allegro.lemis.de> References: <199609151230.OAA00535@allegro.lemis.de> Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Greg Lehey writes: > Does anybody know of Pentium boards which support more than 4 PCI Hmmm, I seem to remember there was one with 5, but that's not what you are looking for ... > slots? One of my customers has a requirement for up to 8 or 10 > slots. My understanding is that this is only possible with a PCI > bridge--is this correct? If so (and even if not, I suppose), how Yes, there are PCI bus extension boxes for this purpose. Satoshi uses one for his large disk array. They use TWO PCI to PCI bridge chips, one that sits in any PCI slot of your motherboard, the other is at the other end of the extender cable, and wired to the second back plane. > transparent is the PCI bridge to the software? How much slower is it Once you are through initialization, the PCI to PCI bridge is not visible to any drivers or software. But you'll need a very recent PCI BIOS, in order to get the interrupt to IRQ routing set up correctly: The PCI BIOS has to identify all boards behind the second PCI bus bridge chip, assign them an IRQ, and set up the routing. Then the IRQ number has to be stored into the chip's interrupt number register in configuration space, where the driver will later find it. What we found in the case of Satoshi's original MB was, that his BIOS would only probe one level deep behind the primary PCI bus, and thus would not see any cards in the extender box. The FreeBSD PCI probe will identify the cards, but can't set up the missing PCI interrupt to ISA IRQ routing, since this is chip set specific (and should be done by the BIOS for that reason). (Well, in fact there is a way to initialize the IRQ routing, but it relies on a very recent PCI BIOS, or it will do more harm than good. And with a recent PCI BIOS, you can expect it did its job :) > than the direct side of the PCI bus? Are there any other gotchas? The speed will be nearly identical for large bursts, but latency is much increased. There might be a buffer that needs to be flushed before reversing directions through the PCI bridge, and that may affect accesses to a devices register, while another chip is doing bus-master transfers into the opposite direction. The BIOS has to assign the memory and port maps correctly, or you'll not be able to reach all I/O ports (they are a scarce resource) or will find that card memory has been mapped non-prefetchable, while it in fact is, leading to reduced streaming performance. There are dead-lock issues, when a device can't perform a requested priority transfer, but also can't go on with its previous operation unless it satisfies this request. This has been dealt with in PCI 2.1, and newer PCI to PCI bridge chips are designed to work around this problem. PCI to PCI bridge chips are very common on multi-channel ethernet cards, and on the AH3940, for example. But this is a slightly different environment than an extender box. It is only one level deep and just about every BIOS does the right thing with them. Conclusion: There is not much of a risk, if all the components (motherboard, BIOS, PCI to PCI bridges) are current designs. I wouldn't bother to try it with an one year old motherboard without a BIOS upgrade :) Regards, STefan From owner-freebsd-hardware Sun Sep 15 11:49:37 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA07875 for hardware-outgoing; Sun, 15 Sep 1996 11:49:37 -0700 (PDT) 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 LAA07859 for ; Sun, 15 Sep 1996 11:49:21 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id LAA04679; Sun, 15 Sep 1996 11:46:35 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609151846.LAA04679@GndRsh.aac.dev.com> Subject: Re: Any Pentium boards with more than 4 PCI slots? To: grog@lemis.de (Greg Lehey) Date: Sun, 15 Sep 1996 11:46:35 -0700 (PDT) Cc: freebsd-hardware@FreeBSD.org In-Reply-To: <199609151230.OAA00535@allegro.lemis.de> from Greg Lehey at "Sep 15, 96 02:30:14 pm" X-Mailer: ELM [version 2.4ME+ PL11 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > Does anybody know of Pentium boards which support more than 4 PCI > slots? No, but if you find anything please do let us all know about it! > One of my customers has a requirement for up to 8 or 10 > slots. That would either require 2 host to PCI bridge chips, and I don't know of any Pentium Host to PCI bridge chips that allow more than 1, though in theory you could probably do it with some glue logic and the 82439HX chip since it at least understands 3 devices being on the host bus. Or 2 PCI-PCI bridges giving a primary PCI bus with 2 slots open and 2 secondary buses with 4 slots each. > My understanding is that this is only possible with a PCI > bridge--is this correct? No, that is now the only way it could be done, see above. But this is the most economical way it could be done. > If so (and even if not, I suppose), how transparent is the PCI bridge > to the software? Once configured correctly a PCI-PCI bridge is totally transparent to both the software and the hardware as far as functionality goes. > How much slower is it than the direct side of the PCI bus? Thats a ``Complicated Question'', both sides of the bridge still run at full speed, but when a transaction must cross the bridge the chip must aquire the other bus (and the other bus may be busy due to having multiple masters on it), after the aquire the bridge looks like a 1 clock delay. But then, some of the bridges (DEC DC21050, go dig around on http://www.dec.com for full data sheets, app notes, and even schematics and order numbers for a evaluation board that would add 4 PCI slots to any standard motherboard) have posting buffers that would eliminate or atleast make transparent some of this loss in performance. > Are there any other gotchas? Yea, most chipsets don't have a way to route more than 4 interrupts to PCI slots, thus your going to be forced to share interrupts unless you go with a custom design. How ``important'' is the need for this product, ie, would it be worth the ~$250,000 NRE charges to have a custom solution designed? Remeber with enough money you can have almost anything designed and built that is technically possible to due. -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Sun Sep 15 11:55:31 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA08169 for hardware-outgoing; Sun, 15 Sep 1996 11:55:31 -0700 (PDT) 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 LAA08161 for ; Sun, 15 Sep 1996 11:55:27 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id LAA04704; Sun, 15 Sep 1996 11:52:18 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609151852.LAA04704@GndRsh.aac.dev.com> Subject: Re: Any Pentium boards with more than 4 PCI slots? To: se@ZPR.Uni-Koeln.DE (Stefan Esser) Date: Sun, 15 Sep 1996 11:52:18 -0700 (PDT) Cc: grog@lemis.de, freebsd-hardware@freebsd.org, asami@cs.berkeley.edu In-Reply-To: <199609151558.RAA00745@x14.mi.uni-koeln.de> from Stefan Esser at "Sep 15, 96 05:58:32 pm" X-Mailer: ELM [version 2.4ME+ PL11 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > Greg Lehey writes: > > Does anybody know of Pentium boards which support more than 4 PCI > > Hmmm, I seem to remember there was one with 5, > but that's not what you are looking for ... > > > slots? One of my customers has a requirement for up to 8 or 10 > > slots. My understanding is that this is only possible with a PCI > > bridge--is this correct? If so (and even if not, I suppose), how > > Yes, there are PCI bus extension boxes for this > purpose. Satoshi uses one for his large disk array. > They use TWO PCI to PCI bridge chips, one that sits > in any PCI slot of your motherboard, the other is > at the other end of the extender cable, and wired > to the second back plane. Okay, Satoshi, who makes it? Where did you get it? How much did it cost? Also what MB are you using with this? -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Sun Sep 15 20:51:54 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id UAA07674 for hardware-outgoing; Sun, 15 Sep 1996 20:51:54 -0700 (PDT) Received: from notendur.isholf.is (notendur.isholf.is [194.105.226.2]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id UAA07652; Sun, 15 Sep 1996 20:51:40 -0700 (PDT) Received: from hummer.islandia.is by notendur.isholf.is with ESMTP (8.7.1/1.2-eef) id DAA15719; Mon, 16 Sep 1996 03:48:44 GMT Received: from caliber by hummer.islandia.is (8.7.5/ISnet/12-09-94); Mon, 16 Sep 1996 03:50:12 GMT Message-Id: <3.0b11.32.19960916034918.008f1100@islandia.is> X-Sender: gestur@islandia.is X-Mailer: Windows Eudora Pro Version 3.0b11 (32) Date: Mon, 16 Sep 1996 03:49:18 +0000 To: questions@freebsd.org, hardware@freebsd.org From: "Gestur A. Grjetarsson" Subject: system frequently hangs, and most often automatically reboots on daily basis. Cc: admin@islandia.is Mime-Version: 1.0 Content-Type: text/enriched; charset="iso-8859-1" Content-Transfer-Encoding: 8bit Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Greetings, We are experiencing some drastic failures in our main server wich is the main server for servicing the Internet to our dialup account customers. The failure is in few words: The system frequently hangs, often it reboots automatically without any notice or much workload. We've been running the FreeBSD os in about a year now, and have tolerated this failures, but it seems that they are getting more frequent, almost on daily basis. It's not a good situation having this system for the main server to the ISP we are running here. the system consists of: FreeBSD 2.1.5 cslip and ppp are installed System handles all main services for our ISP, such as: dns server, web server, news server, mail server, ftp server etc etc P5/133 motherboard has 256kb.cache (not pipeline) viatech chipset (same as in hyundai mb's) 64Mb RAM Adaptech AHA2940 bios v.1.21 two Quantum Atlas QI2120 2.1Gig SCSI2 Hdd's one Quantum Atlas QI4300 4.3Gig SCSI3 Hdd external Accton NE2000 compatible 10Mbit Ethernet Combo card Cyclom multiport ISA with two 16port Cyclom multiports = 32ports. 20 microcom descporte 28.8S kbps modems Any hints or questions on what might be the problem cause, is greatly appreciated.Meš kvešju Isl@ndia Sincerely Grensįsvegur 7 PoBox 9147 Gestur A. Grjetarsson 129 Reykjavik kerfisstjori islandia.is islandia.com admin@islandia.is http://www.islandia.is gestur@islandia.is From owner-freebsd-hardware Sun Sep 15 21:22:12 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id VAA09415 for hardware-outgoing; Sun, 15 Sep 1996 21:22:12 -0700 (PDT) Received: from freefall.freebsd.org (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id VAA09396; Sun, 15 Sep 1996 21:22:07 -0700 (PDT) Message-Id: <199609160422.VAA09396@freefall.freebsd.org> To: "Gestur A. Grjetarsson" cc: questions@FreeBSD.org, hardware@FreeBSD.org, admin@islandia.is Subject: Re: system frequently hangs, and most often automatically reboots on daily basis. In-reply-to: Your message of "Mon, 16 Sep 1996 03:49:18 -0000." <3.0b11.32.19960916034918.008f1100@islandia.is> Date: Sun, 15 Sep 1996 21:22:07 -0700 From: "Justin T. Gibbs" Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk >Greetings, > > >We are experiencing some drastic failures in our main server > >wich is the main server for servicing the Internet to our dialup > >account customers. > > >The failure is in few words: > > >The system frequently hangs, often it reboots automatically without > >any notice or much workload. Can you drp into the debugger when it hangs? If so, what does the output of "ps" in the debugger tell you? Whe you say that it reboots, do you know the machine experienced a panic and then simply timed out and rebooted or if the machine simply spontaneously rebooted? If its panicing, that will most likely point right to the problem. Are you running a custom kernel with all unnecessary devices stripped out? Have you tried swapping ram? -- Justin T. Gibbs =========================================== FreeBSD: Turning PCs into workstations =========================================== From owner-freebsd-hardware Sun Sep 15 21:49:01 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id VAA10524 for hardware-outgoing; Sun, 15 Sep 1996 21:49:01 -0700 (PDT) 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 VAA10519; Sun, 15 Sep 1996 21:48:57 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id VAA00565; Sun, 15 Sep 1996 21:48:20 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609160448.VAA00565@GndRsh.aac.dev.com> Subject: Re: system frequently hangs, and most often automatically reboots on daily basis. In-Reply-To: <3.0b11.32.19960916034918.008f1100@islandia.is> from "Gestur A. Grjetarsson" at "Sep 16, 96 03:49:18 am" To: gestur@islandia.is (Gestur A. Grjetarsson) Date: Sun, 15 Sep 1996 21:48:20 -0700 (PDT) Cc: questions@FreeBSD.org, hardware@FreeBSD.org, admin@islandia.is 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-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk [text/enriched is unsupported, treating like TEXT/PLAIN] > Greetings, > > > We are experiencing some drastic failures in our main server > > wich is the main server for servicing the Internet to our dialup > > account customers. > > > The failure is in few words: > > > The system frequently hangs, often it reboots automatically without > > any notice or much workload. We've been running the FreeBSD os in about ... The number one hardware related failure that will cause these symptoms is bad main memory. Do you infact have 60nS memory in that system with a P5/133, if not try that as a first hardware replacement. -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Mon Sep 16 02:15:08 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id CAA22670 for hardware-outgoing; Mon, 16 Sep 1996 02:15:08 -0700 (PDT) Received: from dv.op.dlr.de (dv.op.dlr.de [129.247.188.46]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id CAA22649 for ; Mon, 16 Sep 1996 02:14:59 -0700 (PDT) Received: from havel.robotic.dlr.de (havel.robotic.dlr.de [129.247.189.22]) by dv.op.dlr.de (8.7.5/8.7.3) with SMTP id LAA78484; Mon, 16 Sep 1996 11:14:22 +0200 Received: by havel.robotic.dlr.de (940816.SGI.8.6.9/940406.SGI.AUTO) id LAA08531; Mon, 16 Sep 1996 11:14:07 +0200 From: Joerg.Langwald@dlr.de (Joerg Langwald) Message-Id: <199609160914.LAA08531@havel.robotic.dlr.de> Subject: Re: Any Pentium boards with more than 4 PCI slots? To: rgrimes@gndrsh.aac.dev.com (Rodney W. Grimes) Date: Mon, 16 Sep 96 11:14:06 MDT Cc: se@ZPR.Uni-Koeln.DE, grog@lemis.de, freebsd-hardware@freebsd.org, asami@cs.berkeley.edu In-Reply-To: <199609151852.LAA04704@GndRsh.aac.dev.com>; from "Rodney W. Grimes" at Sep 15, 96 11:52 am X-Mailer: ELM [version 2.3 PL11] Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > > > > Does anybody know of Pentium boards which support more than 4 PCI > > > > Hmmm, I seem to remember there was one with 5, > > but that's not what you are looking for ... > > > > Yes, there are PCI bus extension boxes for this > > purpose. Satoshi uses one for his large disk array. > > They use TWO PCI to PCI bridge chips, one that sits > > in any PCI slot of your motherboard, the other is > > at the other end of the extender cable, and wired > > to the second back plane. > > Okay, Satoshi, who makes it? Look at http://www.bit3.com/expanuni.html . > Where did you get it? > How much did it cost? > > Also what MB are you using with this? > Joerg. From owner-freebsd-hardware Mon Sep 16 02:41:30 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id CAA23909 for hardware-outgoing; Mon, 16 Sep 1996 02:41:30 -0700 (PDT) Received: from silvia.HIP.Berkeley.EDU (silvia.HIP.Berkeley.EDU [136.152.64.181]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id CAA23904 for ; Mon, 16 Sep 1996 02:41:26 -0700 (PDT) Received: (from asami@localhost) by silvia.HIP.Berkeley.EDU (8.7.5/8.6.9) id CAA02756; Mon, 16 Sep 1996 02:39:42 -0700 (PDT) Date: Mon, 16 Sep 1996 02:39:42 -0700 (PDT) Message-Id: <199609160939.CAA02756@silvia.HIP.Berkeley.EDU> To: Joerg.Langwald@dlr.de CC: rgrimes@gndrsh.aac.dev.com, se@ZPR.Uni-Koeln.DE, grog@lemis.de, freebsd-hardware@freebsd.org In-reply-to: <199609160914.LAA08531@havel.robotic.dlr.de> (Joerg.Langwald@dlr.de) Subject: Re: Any Pentium boards with more than 4 PCI slots? From: asami@freebsd.org (Satoshi Asami) Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk * Look at http://www.bit3.com/expanuni.html . Yes, we got ours from Bit3 too. I believe the price for a 7-slot expansion unit is around $800. Be careful about the motherboard though, some BIOSes don't support more than one level of PCI-PCI bridges and won't work at all with expansion boxes. In particular, Award doesn't work (or didn't when we tried it in January or so). Satoshi From owner-freebsd-hardware Mon Sep 16 06:31:57 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id GAA03690 for hardware-outgoing; Mon, 16 Sep 1996 06:31:57 -0700 (PDT) Received: from Kitten.mcs.com (Kitten.mcs.com [192.160.127.90]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id GAA03682 for ; Mon, 16 Sep 1996 06:31:56 -0700 (PDT) Received: from mars.mcs.com (root@Mars.mcs.com [192.160.127.85]) by Kitten.mcs.com (8.8.Beta.3/8.8.Beta.3) with SMTP id IAA06584; Mon, 16 Sep 1996 08:31:54 -0500 (CDT) Received: by mars.mcs.com (/\==/\ Smail3.1.28.1 #28.13) id ; Mon, 16 Sep 96 08:31 CDT Message-Id: Subject: Re: Any Pentium boards with more than 4 PCI slots? To: grog@lemis.de (Greg Lehey) Date: Mon, 16 Sep 1996 08:31:53 -0500 (CDT) From: "Lars Jonas Olsson" Cc: hardware@freebsd.org In-Reply-To: <199609151230.OAA00535@allegro.lemis.de> from "Greg Lehey" at Sep 15, 96 02:30:14 pm X-Mailer: ELM [version 2.4 PL24] Content-Type: text Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk It's not quite a Pentium board with more than 4 PCI slots, but you can get ISA/PCI passive backplanes with more than 4 PCI slots. In Industrial Computer Source's ((800) 523-2320) catalog I find these passive backplanes (Only backplanes, you also need box and passive backplane computer): Model 15013-02 6 ISA, 1 CPU, 6 PCI slots $790 Model 15018-01 11 ISA, 1 CPU, 6 PCI Slots $940 Model 15018-02 8 ISA, 1 CPU, 9 PCI slots $995 These use Digital bridge chips. I got a for passive backplane computer that fit in these backplanes (PICMG standard) from Arista ((510) 226-1800). It was Pentium 166 with 512 kb sync. cache, watchdog timer, Triton II chipset, 64 MB EDO parity RAM , onboard C&T 65545 SVGA, serial and parallel ports, optional onboard SCSI (Adaptec 7880) for $2145. This particular one has Award BIOS and might therefore not work the Digital bridges (see other post). Jonas From owner-freebsd-hardware Mon Sep 16 08:36:32 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA11358 for hardware-outgoing; Mon, 16 Sep 1996 08:36:32 -0700 (PDT) Received: from rock.anchorage.net (guest@rock.anchorage.net [204.17.241.163]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id IAA11334; Mon, 16 Sep 1996 08:36:22 -0700 (PDT) Received: from jabpc.rtfm.com (jabpc.rtfm.com [199.237.0.200]) by rock.anchorage.net (8.6.12/8.6.9) with SMTP id HAA03810; Mon, 16 Sep 1996 07:31:35 -0300 Received: by jabpc.rtfm.com with Microsoft Mail id <01BBA3A2.11B93340@jabpc.rtfm.com>; Mon, 16 Sep 1996 07:38:36 -0800 Message-ID: <01BBA3A2.11B93340@jabpc.rtfm.com> From: Jeffrey Barber To: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Very Slow Ethernet Link Date: Mon, 16 Sep 1996 07:38:33 -0800 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: bash$ ping localhost PING localhost (127.0.0.1): 56 data bytes 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms 64 bytes from 127.0.0.1: icmp_seq=1 ttl=255 time=0.342 ms 64 bytes from 127.0.0.1: icmp_seq=2 ttl=255 time=0.362 ms 64 bytes from 127.0.0.1: icmp_seq=3 ttl=255 time=0.349 ms --- localhost.arctic.net ping statistics --- 6 packets transmitted, 6 packets received, 0% packet loss round-trip min/avg/max = 0.342/0.349/0.362 ms bash$ ifconfig -a lp0: flags=8810 mtu 1500 ep0: flags=863 mtu 1500 inet 19.51.13.1 netmask 0xffffff00 broadcast 19.51.13.255 lo0: flags=8009 mtu 16384 inet 127.0.0.1 netmask 0xff000000 sl0: flags=c010 mtu 552 tun0: flags=8010 mtu 1500 On my Linux box I get a ping response of: PING localhost (127.0.0.1): 56 data bytes 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms 64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.9 ms 64 bytes from 127.0.0.1: icmp_seq=2 ttl=64 time=0.9 ms 64 bytes from 127.0.0.1: icmp_seq=3 ttl=64 time=1.0 ms Big difference here. Please shed some light on this for me. TIA From owner-freebsd-hardware Mon Sep 16 08:53:42 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA12197 for hardware-outgoing; Mon, 16 Sep 1996 08:53:42 -0700 (PDT) Received: from silver.sms.fi (root@silver.sms.fi [194.111.122.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id IAA12192; Mon, 16 Sep 1996 08:53:35 -0700 (PDT) Received: (from pete@localhost) by silver.sms.fi (8.7.5/8.6.9) id SAA12091; Mon, 16 Sep 1996 18:50:53 +0300 (EET DST) Date: Mon, 16 Sep 1996 18:50:53 +0300 (EET DST) Message-Id: <199609161550.SAA12091@silver.sms.fi> From: Petri Helenius To: Jeffrey Barber Cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Very Slow Ethernet Link In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> References: <01BBA3A2.11B93340@jabpc.rtfm.com> Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Excuse me, but last time I checked, 0.350 milliseconds is much less than a millisecond? So your LinSux is three times slower to respond to a ping to loopback address. (which is to be expected from the 'design' of the network code) Pete Jeffrey Barber writes: > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > bash$ ping localhost > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=255 time=0.342 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=255 time=0.362 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=255 time=0.349 ms > > --- localhost.arctic.net ping statistics --- > 6 packets transmitted, 6 packets received, 0% packet loss > round-trip min/avg/max = 0.342/0.349/0.362 ms > > bash$ ifconfig -a > > lp0: flags=8810 mtu 1500 > ep0: flags=863 mtu 1500 > inet 19.51.13.1 netmask 0xffffff00 broadcast 19.51.13.255 > lo0: flags=8009 mtu 16384 > inet 127.0.0.1 netmask 0xff000000 > sl0: flags=c010 mtu 552 > tun0: flags=8010 mtu 1500 > > > On my Linux box I get a ping response of: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=64 time=1.0 ms > > Big difference here. Please shed some light on this for me. > > TIA > From owner-freebsd-hardware Mon Sep 16 08:56:35 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA12378 for hardware-outgoing; Mon, 16 Sep 1996 08:56:35 -0700 (PDT) Received: from rocky.mt.sri.com (rocky.mt.sri.com [206.127.76.100]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id IAA12366; Mon, 16 Sep 1996 08:56:28 -0700 (PDT) Received: (from nate@localhost) by rocky.mt.sri.com (8.7.5/8.7.3) id JAA02862; Mon, 16 Sep 1996 09:54:47 -0600 (MDT) Date: Mon, 16 Sep 1996 09:54:47 -0600 (MDT) Message-Id: <199609161554.JAA02862@rocky.mt.sri.com> From: Nate Williams To: Jeffrey Barber Cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Re: Very Slow Ethernet Link In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> References: <01BBA3A2.11B93340@jabpc.rtfm.com> Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Jeffrey Barber writes: > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > bash$ ping localhost > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms vs. > On my Linux box I get a ping response of: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms Hmm, it looks like the Linux box is about 3X slower than FreeBSD. I'm not sure, but in my math class .1 ms is faster than 1ms. Nate From owner-freebsd-hardware Mon Sep 16 09:00:27 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA12635 for hardware-outgoing; Mon, 16 Sep 1996 09:00:27 -0700 (PDT) Received: from dyson.iquest.net (dyson.iquest.net [198.70.144.127]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA12605; Mon, 16 Sep 1996 09:00:19 -0700 (PDT) Received: (from root@localhost) by dyson.iquest.net (8.7.5/8.6.9) id LAA01123; Mon, 16 Sep 1996 11:00:01 -0500 (EST) From: John Dyson Message-Id: <199609161600.LAA01123@dyson.iquest.net> Subject: Re: Very Slow Ethernet Link To: jab@rock.anchorage.net (Jeffrey Barber) Date: Mon, 16 Sep 1996 11:00:01 -0500 (EST) Cc: freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> from "Jeffrey Barber" at Sep 16, 96 07:38:33 am Reply-To: dyson@FreeBSD.org X-Mailer: ELM [version 2.4 PL24 ME8] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > bash$ ping localhost > FreeBSD number: > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms Linux number: > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms Looks like Linux is slower to me... John From owner-freebsd-hardware Mon Sep 16 09:11:12 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA13204 for hardware-outgoing; Mon, 16 Sep 1996 09:11:12 -0700 (PDT) Received: from fullfeed.msn.fullfeed.com (fullfeed.msn.fullfeed.com [199.184.182.42]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id JAA13199; Mon, 16 Sep 1996 09:11:06 -0700 (PDT) Received: from sumatra.americantv.com by fullfeed.msn.fullfeed.com (8.6.9/FF-1.1) id LAA26698; Mon, 16 Sep 1996 11:10:43 -0500 Received: (from uucp@localhost) by sumatra.americantv.com (8.6.12/8.6.12) with UUCP id KAA07019; Mon, 16 Sep 1996 10:38:28 -0500 Received: (jlemon@localhost) by right.PCS (8.6.13/8.6.4) id QAA12775; Mon, 16 Sep 1996 16:07:58 GMT From: Jonathan Lemon Message-Id: <199609161607.QAA12775@right.PCS> Subject: Re: Very Slow Ethernet Link To: jab@rock.anchorage.net (Jeffrey Barber) Date: Mon, 16 Sep 1996 11:07:57 -0500 (CDT) Cc: freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> from "Jeffrey Barber" at Sep 16, 96 07:38:33 am X-Mailer: ELM [version 2.4 PL21] Content-Type: text Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=255 time=0.342 ms > On my Linux box I get a ping response of: > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.9 ms Umm, 0.342ms < 0.9ms, isn't it? If your question is "why is Linux ~3x slower", then that question might be better asked on a linux mailing list. This assumes similar hardware. Note that different hardware also affects the ping rate: 386/20 w/4MB running 2.2-960612-SNAP: 64 bytes from 127.0.0.1: icmp_seq=4 ttl=255 time=6.563 ms 586/133 w/32M running 2.1.0-RELEASE: 64 bytes from 127.0.0.1: icmp_seq=4 ttl=255 time=0.158 ms -- Jonathan From owner-freebsd-hardware Mon Sep 16 09:12:57 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA13412 for hardware-outgoing; Mon, 16 Sep 1996 09:12:57 -0700 (PDT) Received: from gatekeeper.fsl.noaa.gov (gatekeeper.fsl.noaa.gov [137.75.131.181]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA13387; Mon, 16 Sep 1996 09:12:50 -0700 (PDT) Received: from emu.fsl.noaa.gov (kelly@emu.fsl.noaa.gov [137.75.60.32]) by gatekeeper.fsl.noaa.gov (8.7.5/8.7.3) with ESMTP id QAA20759; Mon, 16 Sep 1996 16:12:49 GMT Message-Id: <199609161612.QAA20759@gatekeeper.fsl.noaa.gov> Received: by emu.fsl.noaa.gov (1.40.112.4/16.2) id AA284420392; Mon, 16 Sep 1996 10:13:12 -0600 Date: Mon, 16 Sep 1996 10:13:12 -0600 From: Sean Kelly To: jab@rock.anchorage.net Cc: freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> (message from Jeffrey Barber on Mon, 16 Sep 1996 07:38:33 -0800) Subject: Re: Very Slow Ethernet Link Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk >>>>> Jeffrey Barber writes: > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > On my Linux box I get a ping response of: > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 > Big difference here. Please shed some light on this for me. Yes, there is a big difference: 0.356 ms < 1.1 ms, so your FreeBSD host is faster when ping'ing localhost. Are you saying even though it's faster than Linux, it's still too slow? -- Sean Kelly NOAA Forecast Systems Laboratory kelly@fsl.noaa.gov Boulder Colorado USA http://www-sdd.fsl.noaa.gov/~kelly/ From owner-freebsd-hardware Mon Sep 16 09:19:47 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA14087 for hardware-outgoing; Mon, 16 Sep 1996 09:19:47 -0700 (PDT) Received: from home.winc.com (root@home.winc.com [204.178.182.2]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA14046; Mon, 16 Sep 1996 09:19:37 -0700 (PDT) Received: from phoenix.aristar.com (slip125.winc.com [204.178.182.125]) by home.winc.com (8.7.1/8.7.3) with SMTP id MAA21070; Mon, 16 Sep 1996 12:18:51 -0400 Message-ID: <323D7E23.31DFF4F5@aristar.com> Date: Mon, 16 Sep 1996 12:19:47 -0400 From: "Matthew A. Gessner" Organization: Aristar, Inc. X-Mailer: Mozilla 3.0b8Gold (X11; I; FreeBSD 2.1.0-RELEASE i386) MIME-Version: 1.0 To: Nate Williams CC: Jeffrey Barber , "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Enough (was Re: Very Slow Ethernet Link) References: <01BBA3A2.11B93340@jabpc.rtfm.com> <199609161554.JAA02862@rocky.mt.sri.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Nate Williams wrote: > > Jeffrey Barber writes: > > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > > > bash$ ping localhost > > > > PING localhost (127.0.0.1): 56 data bytes > > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > > vs. > > > On my Linux box I get a ping response of: > > > > PING localhost (127.0.0.1): 56 data bytes > > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms > > Hmm, it looks like the Linux box is about 3X slower than FreeBSD. I'm > not sure, but in my math class .1 ms is faster than 1ms. > > Nate Hey, all, by this time, he probably got the hint. -- Matthew Gessner, Computer Scientist, Aristar, Inc. 302 N. Cleveland-Massillon Rd. Akron, OH 44333 Voice (330) 668-2267, Fax (330) 668-2961 From owner-freebsd-hardware Mon Sep 16 09:26:42 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA14520 for hardware-outgoing; Mon, 16 Sep 1996 09:26:42 -0700 (PDT) Received: from zwei.siemens.at (zwei.siemens.at [193.81.246.12]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA14499; Mon, 16 Sep 1996 09:26:36 -0700 (PDT) Received: from sol1.gud.siemens.co.at (root@[10.1.143.100]) by zwei.siemens.at (8.7.5/8.7.3) with SMTP id SAA28112; Mon, 16 Sep 1996 18:25:30 +0200 (MET DST) Received: from ws2301.gud.siemens.co.at by sol1.gud.siemens.co.at with smtp (Smail3.1.28.1 #7 for ) id m0v2gUl-000218C; Mon, 16 Sep 96 18:26 MET DST Received: by ws2301.gud.siemens.co.at (1.37.109.16/1.37) id AA232580878; Mon, 16 Sep 1996 18:21:18 +0200 From: "Hr.Ladavac" Message-Id: <199609161621.AA232580878@ws2301.gud.siemens.co.at> Subject: Re: Very Slow Ethernet Link To: jab@rock.anchorage.net (Jeffrey Barber) Date: Mon, 16 Sep 1996 18:21:18 +0200 (MESZ) Cc: freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> from "Jeffrey Barber" at Sep 16, 96 07:38:33 am X-Mailer: ELM [version 2.4 PL24 ME8a] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk E-mail message from Jeffrey Barber contained: > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > bash$ ping localhost > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=255 time=0.342 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=255 time=0.362 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=255 time=0.349 ms > > --- localhost.arctic.net ping statistics --- > 6 packets transmitted, 6 packets received, 0% packet loss > round-trip min/avg/max = 0.342/0.349/0.362 ms > > bash$ ifconfig -a > > lp0: flags=8810 mtu 1500 > ep0: flags=863 mtu 1500 > inet 19.51.13.1 netmask 0xffffff00 broadcast 19.51.13.255 > lo0: flags=8009 mtu 16384 > inet 127.0.0.1 netmask 0xff000000 > sl0: flags=c010 mtu 552 > tun0: flags=8010 mtu 1500 > > > On my Linux box I get a ping response of: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=64 time=1.0 ms > > Big difference here. Please shed some light on this for me. What would be your point, please? 1) Localhost doesn't even reach the wire; 2) localhost pings on freebsd seem to be 3 times faster than the linux ones (according to your data.) What did you want to ask? Perplexed minds wish to know. BTW, tcpblast on loopback device (localhost) is slow on 2.1 because of the slightly bogus mtu of 16K. Set it to something more reasonable like 1500 /Marino > > TIA > > From owner-freebsd-hardware Mon Sep 16 09:34:10 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA14970 for hardware-outgoing; Mon, 16 Sep 1996 09:34:10 -0700 (PDT) Received: from freefall.freebsd.org (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA14952; Mon, 16 Sep 1996 09:34:06 -0700 (PDT) Message-Id: <199609161634.JAA14952@freefall.freebsd.org> To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Re: Very Slow Ethernet Link In-reply-to: Your message of "Mon, 16 Sep 1996 07:38:33 -0800." <01BBA3A2.11B93340@jabpc.rtfm.com> Date: Mon, 16 Sep 1996 09:34:05 -0700 From: "Justin T. Gibbs" Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk >Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > >bash$ ping localhost >64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > >On my Linux box I get a ping response of: > >PING localhost (127.0.0.1): 56 data bytes >64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms > >Big difference here. Please shed some light on this for me. > >TIA Last I checked, .356ms was faster than 1.1ms. I think you missed the decimal point. -- Justin T. Gibbs =========================================== FreeBSD: Turning PCs into workstations =========================================== From owner-freebsd-hardware Mon Sep 16 09:36:56 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA15368 for hardware-outgoing; Mon, 16 Sep 1996 09:36:56 -0700 (PDT) Received: (from hsu@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA15362 for hardware; Mon, 16 Sep 1996 09:36:55 -0700 (PDT) Date: Mon, 16 Sep 1996 09:36:55 -0700 (PDT) From: Jeffrey Hsu Message-Id: <199609161636.JAA15362@freefall.freebsd.org> To: hardware Subject: passive backplane (was Re: Any Pentium boards with more than 4 PC) slots? Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Speaking of passive backplanes, I have a question. What are they used for? The hardware engineer I asked a while ago didn't give a satisfying answer. In fact, I've forgotten what it was. But it must be good for something, because I keep seeing passive backplanes advertised in embedded systems magazines. From owner-freebsd-hardware Mon Sep 16 09:39:56 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA15480 for hardware-outgoing; Mon, 16 Sep 1996 09:39:56 -0700 (PDT) Received: from fore.com (mailhub.fore.com [192.88.243.4]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA15475; Mon, 16 Sep 1996 09:39:47 -0700 (PDT) Received: from dolphin.fore.com ([192.88.243.27]) by fore.com (8.7.3/8.6.11) with ESMTP id MAA15894; Mon, 16 Sep 1996 12:35:30 -0400 (EDT) Received: from lamprey.fore.com (lamprey.fore.com [169.144.1.113]) by dolphin.fore.com (8.7.5/8.7.3) with SMTP id MAA27610; Mon, 16 Sep 1996 12:39:00 -0400 (EDT) Message-Id: <199609161639.MAA27610@dolphin.fore.com> To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Re: Very Slow Ethernet Link In-reply-to: Message from Jeffrey Barber of "Mon, 16 Sep 1996 07:38:33 -0800." <01BBA3A2.11B93340@jabpc.rtfm.com> Reply-to: rv@fore.com X-Mailer: MH v6.8.3 Date: Mon, 16 Sep 1996 12:38:57 -0400 From: Rajesh Vaidheeswarran Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk unless I don't understand, .356 ms << .9 ms (slightly more than a third) -- using MH template repl.format -- In a previous message, Jeffrey Barber writes: > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > bash$ ping localhost > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=255 time=0.342 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=255 time=0.362 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=255 time=0.349 ms > > --- localhost.arctic.net ping statistics --- > 6 packets transmitted, 6 packets received, 0% packet loss > round-trip min/avg/max = 0.342/0.349/0.362 ms > > bash$ ifconfig -a > > lp0: flags=8810 mtu 1500 > ep0: flags=863 mtu 1500 > inet 19.51.13.1 netmask 0xffffff00 broadcast 19.51.13.255 > lo0: flags=8009 mtu 16384 > inet 127.0.0.1 netmask 0xff000000 > sl0: flags=c010 mtu 552 > tun0: flags=8010 mtu 1500 > > > On my Linux box I get a ping response of: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=64 time=1.0 ms > > Big difference here. Please shed some light on this for me. > > TIA > From owner-freebsd-hardware Mon Sep 16 09:42:35 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA15719 for hardware-outgoing; Mon, 16 Sep 1996 09:42:35 -0700 (PDT) Received: from www.hsc.wvu.edu (www.hsc.wvu.edu [157.182.105.122]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id JAA15713; Mon, 16 Sep 1996 09:42:30 -0700 (PDT) Received: (from jsigmon@localhost) by www.hsc.wvu.edu (8.6.12/8.6.12) id MAA13035; Mon, 16 Sep 1996 12:44:30 -0400 Date: Mon, 16 Sep 1996 12:44:28 -0400 (EDT) From: Jeremy Sigmon To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Re: Very Slow Ethernet Link In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=255 time=0.349 ms > > On my Linux box I get a ping response of: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.9 ms > Isn't .349 << .9 ???? =) My FBSD box: PING at-ga1.hsc.wvu.edu (157.182.105.124): 56 data bytes 64 bytes from 157.182.105.124: icmp_seq=0 ttl=255 time=0.305 ms 64 bytes from 157.182.105.124: icmp_seq=1 ttl=255 time=0.177 ms 64 bytes from 157.182.105.124: icmp_seq=2 ttl=255 time=0.169 ms 64 bytes from 157.182.105.124: icmp_seq=3 ttl=255 time=0.165 ms 64 bytes from 157.182.105.124: icmp_seq=4 ttl=255 time=0.166 ms 64 bytes from 157.182.105.124: icmp_seq=5 ttl=255 time=0.167 ms 64 bytes from 157.182.105.124: icmp_seq=6 ttl=255 time=0.168 ms ====================================================================== Jeremy Sigmon B.S. ChE | Web Developer of the Robert C. Byrd Health | Use Sciences Center of West Virginia University | FreeBSD WWW.HSC.WVU.EDU | Now Graduate Student in Computer Science | Office : 293-1060 | From owner-freebsd-hardware Mon Sep 16 09:49:46 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA16111 for hardware-outgoing; Mon, 16 Sep 1996 09:49:46 -0700 (PDT) Received: from solar.os.com (craigs@solar.os.com [199.232.136.65]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA16106; Mon, 16 Sep 1996 09:49:42 -0700 (PDT) Received: (from craigs@localhost) by solar.os.com (8.7/8.7.0) id MAA28827; Mon, 16 Sep 1996 12:54:26 -0400 Date: Mon, 16 Sep 1996 12:54:26 -0400 From: Craig Shrimpton Subject: Re: Very Slow Ethernet Link To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Mon, 16 Sep 1996, Jeffrey Barber wrote: > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > bash$ ping localhost > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=255 time=0.342 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=255 time=0.362 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=255 time=0.349 ms You got it backwards. The FreeBSD box is much faster than the Linux box. A return time of .349 is faster than a return time of .9 - Craig +------------------------------------+--------------------------------------+ | Craig Shrimpton | e-mail: craigs@os.com | | Orbit Systems | information: info@os.com | | Worcester, MA 508.753.8776 | http://www.os.com/ | +------------------------------------+--------------------------------------+ _/_/_/_/ _/_/_/_/ _/_/_/_/ _/_/_/_/ _/_/_/_/ _/ _/ _/ _/ _/ _/ _/ _/ _/ _/ _/_/_/ _/_/_/_/ _/ _/ _/ _/ _/ _/ _/ _/ _/ _/ _/_/_/_/ _/ _/ _/_/_/_/ _/_/_/_/ _/ Strategic Systems From owner-freebsd-hardware Mon Sep 16 09:54:32 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA16578 for hardware-outgoing; Mon, 16 Sep 1996 09:54:32 -0700 (PDT) Received: from genesis.atrad.adelaide.edu.au (genesis.atrad.adelaide.edu.au [129.127.96.120]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA16573 for ; Mon, 16 Sep 1996 09:54:30 -0700 (PDT) Received: from msmith@localhost by genesis.atrad.adelaide.edu.au (8.6.12/8.6.9) id CAA26362; Tue, 17 Sep 1996 02:24:20 +0930 From: Michael Smith Message-Id: <199609161654.CAA26362@genesis.atrad.adelaide.edu.au> Subject: Re: Very Slow Ethernet Link To: jab@rock.anchorage.net (Jeffrey Barber) Date: Tue, 17 Sep 1996 02:24:19 +0930 (CST) Cc: freebsd-hardware@FreeBSD.org In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> from "Jeffrey Barber" at Sep 16, 96 07:38:33 am MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Jeffrey Barber stands accused of saying: > > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: Firstly, please note that 2.1 is more than half a year old. 2.1.5 contains significant improvements and is generally worth the effort. > bash$ ping localhost > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms ... > On my Linux box I get a ping response of: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms ... > Big difference here. Please shed some light on this for me. Linux networking is slower contemplating its navel? You can't read decimal numbers? How should I know? Talking over the loopback interface basically tells you very little; if you get down and dirty with the BSD box, you'll find that it's often better than 3x faster like above... > TIA -- ]] Mike Smith, Software Engineer msmith@atrad.adelaide.edu.au [[ ]] Genesis Software genesis@atrad.adelaide.edu.au [[ ]] High-speed data acquisition and (GSM mobile) 0411-222-496 [[ ]] realtime instrument control (ph/fax) +61-8-267-3039 [[ ]] Collector of old Unix hardware. "Where are your PEZ?" The Tick [[ From owner-freebsd-hardware Mon Sep 16 10:14:14 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA18307 for hardware-outgoing; Mon, 16 Sep 1996 10:14:14 -0700 (PDT) Received: from Gatekeeper.Lamb.net (ulf@cat-food.Melmac.org [206.169.44.2]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA18289; Mon, 16 Sep 1996 10:14:08 -0700 (PDT) Received: (from ulf@localhost) by Gatekeeper.Lamb.net (8.7.5/8.7.3) id KAA02093; Mon, 16 Sep 1996 10:14:46 -0700 (PDT) From: Ulf Zimmermann Message-Id: <199609161714.KAA02093@Gatekeeper.Lamb.net> Subject: Re: Very Slow Ethernet Link To: jab@rock.anchorage.net (Jeffrey Barber) Date: Mon, 16 Sep 1996 10:14:45 -0700 (PDT) Cc: freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> from Jeffrey Barber at "Sep 16, 96 07:38:33 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-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > bash$ ping localhost > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=255 time=0.342 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=255 time=0.362 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=255 time=0.349 ms > > --- localhost.arctic.net ping statistics --- > 6 packets transmitted, 6 packets received, 0% packet loss > round-trip min/avg/max = 0.342/0.349/0.362 ms > > bash$ ifconfig -a > > lp0: flags=8810 mtu 1500 > ep0: flags=863 mtu 1500 > inet 19.51.13.1 netmask 0xffffff00 broadcast 19.51.13.255 > lo0: flags=8009 mtu 16384 > inet 127.0.0.1 netmask 0xff000000 > sl0: flags=c010 mtu 552 > tun0: flags=8010 mtu 1500 > > > On my Linux box I get a ping response of: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=64 time=1.0 ms > > Big difference here. Please shed some light on this for me. > > TIA > > And it seems you can't read ;-) the FreeBSD is faster then your Linux. Your Linux box gives you ping times of 1 ms and 0.9 ms, while FreeBSD gives you an average of 0.349 ms, since then is that slow ? Ulf. -------------------------------------------------------------------------- Ulf Zimmermann, 1525 Pacific Ave., Alameda, CA-94501, #: 510-865-0204 Lamb Art Internet Services | http://www.Lamb.net/ | http://www.Alameda.net From owner-freebsd-hardware Mon Sep 16 10:30:22 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA19913 for hardware-outgoing; Mon, 16 Sep 1996 10:30:22 -0700 (PDT) Received: from critter.tfs.com ([140.145.230.177]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA19874; Mon, 16 Sep 1996 10:30:08 -0700 (PDT) Received: from critter.tfs.com (localhost.tfs.com [127.0.0.1]) by critter.tfs.com (8.7.5/8.7.3) with ESMTP id TAA16559; Mon, 16 Sep 1996 19:29:38 +0200 (MET DST) To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Re: Very Slow Ethernet Link In-reply-to: Your message of "Mon, 16 Sep 1996 07:38:33 -0800." <01BBA3A2.11B93340@jabpc.rtfm.com> Date: Mon, 16 Sep 1996 19:29:38 +0200 Message-ID: <16557.842894978@critter.tfs.com> From: Poul-Henning Kamp Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk In message <01BBA3A2.11B93340@jabpc.rtfm.com>, Jeffrey Barber writes: >Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > >bash$ ping localhost > >PING localhost (127.0.0.1): 56 data bytes > >round-trip min/avg/max = 0.342/0.349/0.362 ms > >On my Linux box I get a ping response of: > >PING localhost (127.0.0.1): 56 data bytes >64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms >64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.9 ms >64 bytes from 127.0.0.1: icmp_seq=2 ttl=64 time=0.9 ms >64 bytes from 127.0.0.1: icmp_seq=3 ttl=64 time=1.0 ms > >Big difference here. Please shed some light on this for me. Seems to me that FreeBSD is 3 times >faster< on this completely silly benchmark... -- 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-hardware Mon Sep 16 10:46:25 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA21020 for hardware-outgoing; Mon, 16 Sep 1996 10:46:25 -0700 (PDT) Received: from saguaro.flyingfox.com (saguaro.flyingfox.com [204.188.109.253]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id KAA20998; Mon, 16 Sep 1996 10:46:21 -0700 (PDT) Received: (from jas@localhost) by saguaro.flyingfox.com (8.6.12/8.6.10) id KAA07081; Mon, 16 Sep 1996 10:44:55 -0700 Date: Mon, 16 Sep 1996 10:44:55 -0700 From: Jim Shankland Message-Id: <199609161744.KAA07081@saguaro.flyingfox.com> To: jab@rock.anchorage.net, kelly@fsl.noaa.gov Subject: Re: Very Slow Ethernet Link Cc: freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk OK, so several correspondents have pointed out that 0.356ms (ping RTT for 127.0.0.1 on FreeBSD) is less than 1.1 ms (ping RTT for 127.0.0.1) on Linux. On the assumption that the original mail was not a mis-timed April Fool's prank, let me make two small, additional observations: (1) Packets to 127.0.0.1 will go through the loopback interface, so Ethernet has nothing to do with it. (2) It is possible that jab@rock.anchorage.net was looking at the ttl value rather than the RTT. The ttl was 64 for Linux, 255 for FreeBSD. This has nothing to do with ping times, but rather with the maximum number of hops that a packet can make before it is discarded on the assumption that there is some routing loop. It needs to be larger than the largest number of hops that a packet could legitimately make en route from its source to its destination. 64 is probably sufficient in today's Internet; 255 works, too, and may be a better choice. If ttl is to be the measure of performance, then sysctl -W net.inet.ip.ttl=32 will cause FreeBSD to run circles around Linux :-). Jim Shankland Flying Fox Computer Systems, Inc. From owner-freebsd-hardware Mon Sep 16 10:53:34 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA21624 for hardware-outgoing; Mon, 16 Sep 1996 10:53:34 -0700 (PDT) Received: from persprog.com (persprog.com [204.215.255.203]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA21597; Mon, 16 Sep 1996 10:53:24 -0700 (PDT) Received: by persprog.com (8.7.5/4.10) id MAA26137; Mon, 16 Sep 1996 12:44:13 -0500 Received: from dasa(192.2.2.199) by cerberus.ppi.com via smap (V1.3) id sma026135; Mon Sep 16 13:43:57 1996 Received: from DASA/SpoolDir by dasa.ppi.com (Mercury 1.21); 16 Sep 96 13:43:59 +0500 Received: from SpoolDir by DASA (Mercury 1.30); 16 Sep 96 13:43:43 +0500 From: "David Alderman" Organization: Personalized Programming, Inc To: John Dyson , freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org, jab@rock.anchorage.net Date: Mon, 16 Sep 1996 13:43:40 +0500 Subject: Re: Very Slow Ethernet Link Priority: normal X-mailer: Pegasus Mail for Windows (v2.42a) Message-ID: Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > From: John Dyson > Reply-to: dyson@FreeBSD.org > > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > > > bash$ ping localhost > > > FreeBSD number: > > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > > Linux number: > > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms > > Looks like Linux is slower to me... > > John > Is the ping code the same on both Linux and FreeBSD? On older SCO boxes it always says 0ms (and their TCP/IP is not all that great). I would think ftp (or anything else) would be a better test of the TCP/IP stack. I didn't see the original post so please accept my apologies if I'm just blathering. ====================================== When philosophy conflicts with reality, choose reality. Dave Alderman -- dave@persprog.com ====================================== From owner-freebsd-hardware Mon Sep 16 11:11:45 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA23686 for hardware-outgoing; Mon, 16 Sep 1996 11:11:45 -0700 (PDT) Received: from night.primate.wisc.edu (night.primate.wisc.edu [144.92.43.19]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id LAA23648; Mon, 16 Sep 1996 11:11:37 -0700 (PDT) Received: by night.primate.wisc.edu; id NAA28776; 8.6.10/41.8; Mon, 16 Sep 1996 13:12:54 -0500 From: Paul DuBois Message-Id: <199609161812.NAA28776@night.primate.wisc.edu> Subject: Re: Enough (was Re: Very Slow Ethernet Link) To: mgessner@aristar.com (Matthew A. Gessner) Date: Mon, 16 Sep 1996 13:12:54 -0500 (CDT) Cc: freebsd-hardware@freebsd.org, freebsd-hackers@freebsd.org In-Reply-To: <323D7E23.31DFF4F5@aristar.com> from "Matthew A. Gessner" at Sep 16, 96 12:19:47 pm X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >Hey, all, by this time, he probably got the hint. I figured all the respondents were trying to demonstrate that NO question is too difficult for this list. :-) From owner-freebsd-hardware Mon Sep 16 11:24:47 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA24998 for hardware-outgoing; Mon, 16 Sep 1996 11:24:47 -0700 (PDT) Received: from brasil.moneng.mei.com (brasil.moneng.mei.com [151.186.109.160]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id LAA24974; Mon, 16 Sep 1996 11:24:41 -0700 (PDT) Received: (from jgreco@localhost) by brasil.moneng.mei.com (8.7.Beta.1/8.7.Beta.1) id NAA05966; Mon, 16 Sep 1996 13:23:24 -0500 From: Joe Greco Message-Id: <199609161823.NAA05966@brasil.moneng.mei.com> Subject: Re: Very Slow Ethernet Link To: nate@mt.sri.com (Nate Williams) Date: Mon, 16 Sep 1996 13:23:24 -0500 (CDT) Cc: jab@rock.anchorage.net, freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: <199609161554.JAA02862@rocky.mt.sri.com> from "Nate Williams" at Sep 16, 96 09:54:47 am X-Mailer: ELM [version 2.4 PL24] Content-Type: text Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > Jeffrey Barber writes: > > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > > > bash$ ping localhost > > > > PING localhost (127.0.0.1): 56 data bytes > > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > > > On my Linux box I get a ping response of: > > > > PING localhost (127.0.0.1): 56 data bytes > > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms > > Hmm, it looks like the Linux box is about 3X slower than FreeBSD. I'm > not sure, but in my math class .1 ms is faster than 1ms. You guys aren't touching on an important point: This is NOT Ethernet traffic. This is loopback traffic! (see Subject:) Given the same hardware, FreeBSD will generally go faster than Linux for most real networking tests (ok, fine, _all_ of them that _I_ have seen that were executed in an unbiased manner). However, the difference in speed seems to be magnified somewhat on the loopback interface :-) Anyways, the fix to this fellow's problem is obvious: Press the Turbo switch or set your CMOS configuration to start the machine up in non-Turbo mode. Then your FreeBSD box will (probably?) go slower than your Linux box. ( all sorts of :-)'s ) ... JG From owner-freebsd-hardware Mon Sep 16 12:05:02 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA28534 for hardware-outgoing; Mon, 16 Sep 1996 12:05:02 -0700 (PDT) Received: from Kitten.mcs.com (Kitten.mcs.com [192.160.127.90]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id MAA28511 for ; Mon, 16 Sep 1996 12:04:59 -0700 (PDT) Received: from mercury.mcs.com (root@Mercury.mcs.com [192.160.127.80]) by Kitten.mcs.com (8.8.Beta.3/8.8.Beta.3) with SMTP id OAA27119; Mon, 16 Sep 1996 14:04:58 -0500 (CDT) Received: by mercury.mcs.com (/\==/\ Smail3.1.28.1 #28.13) id ; Mon, 16 Sep 96 14:04 CDT Message-Id: Subject: Re: passive backplane (was Re: Any Pentium boards with more than 4 PC) slots? To: hsu@freefall.freebsd.org (Jeffrey Hsu) Date: Mon, 16 Sep 1996 14:04:57 -0500 (CDT) From: "Lars Jonas Olsson" Cc: hardware@freebsd.org In-Reply-To: <199609161636.JAA15362@freefall.freebsd.org> from "Jeffrey Hsu" at Sep 16, 96 09:36:55 am X-Mailer: ELM [version 2.4 PL24] Content-Type: text Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk The passive backplane computers are supposed to be better quality and the cases that fit them definately are more robust than most standard PC cases. We (AccuMed International Inc.) are using them in medical devices were we want: 1. reliable PC/case 2. easy service/upgrades (pulling computer board is much simpler than replacing a motherboard) 3. compact design (Our computer case is 11x21x43 cm. The backplane is 1 ISA, 1 CPU, and 2 PCI. I have yet to see a motherboard that can fit these slots in 11 cm width (external case dimension). 4. longer product life. Things don't change as fast as for motherboards. 5. contain BIOS that don't need keyboard or video card (embedded application). Other people might need the large number of slots you can get. This tends to be true for computer telephony applications (up to 24 ISA slots in one case) and some control applications. Jonas > > Speaking of passive backplanes, I have a question. What are they > used for? The hardware engineer I asked a while ago didn't give > a satisfying answer. In fact, I've forgotten what it was. But it > must be good for something, because I keep seeing passive backplanes > advertised in embedded systems magazines. > From owner-freebsd-hardware Mon Sep 16 12:37:24 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA01789 for hardware-outgoing; Mon, 16 Sep 1996 12:37:24 -0700 (PDT) Received: from lserver.infoworld.com (root@lserver.infoworld.com [192.216.48.4]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id MAA01768; Mon, 16 Sep 1996 12:37:19 -0700 (PDT) From: BRETT_GLASS@ccgate.infoworld.com Received: from ccgate.infoworld.com (ccgate.infoworld.com [192.216.49.101]) by lserver.infoworld.com (8.7.5/8.7.3) with SMTP id MAA04022; Mon, 16 Sep 1996 12:37:16 -0700 (PDT) Received: from ccMail by ccgate.infoworld.com (SMTPLINK V2.11) id AA842902427; Mon, 16 Sep 96 14:23:42 PST Date: Mon, 16 Sep 96 14:23:42 PST Message-Id: <9608168429.AA842902427@ccgate.infoworld.com> To: hardware@freebsd.org, questions@freebsd.org Subject: PCMCIA, APM, 3C562 Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Have given up on OS/2 for my laptop.... It seems to be crashing and failing big-time under the Merlin gamma, and my bug reports have been utterly ignored. So, I'd like to try FreeBSD on it. But first, some questions: How good is the PCMCIA support in FreeBSD? Will I be able to swap cards? Is APM supported? Will the system (including PCMCIA) be able to survive a suspend/resume cycle without "freaking out" or getting too busy to use due to missed items in /etc/crontab? (Come to think of it, how DOES it handle missed items in /etc/crontab?) Is there a sync on suspend? If the battery dies during a suspend (common on many laptops that suspend when the battery gets low), is the filesystem left "clean" and ready for a reboot? Finally, there doesn't appear to be a driver for my 3C562 Modem/Ethernet combo card. As I understand it, this card is really just a 3Com Ethernet adapter and a modem (with standard UART) sharing an IRQ. Is there a driver available? Would it be possible to construct one by creating a "hybrid" driver that probed for the card, grabbed the one interrupt, and linked to routines from the existing sio and 3Com PCMCIA Ethernet drivers? --Brett From owner-freebsd-hardware Mon Sep 16 12:43:58 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA02174 for hardware-outgoing; Mon, 16 Sep 1996 12:43:58 -0700 (PDT) Received: from alpo.whistle.com (s205m1.whistle.com [207.76.205.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id MAA02152; Mon, 16 Sep 1996 12:43:51 -0700 (PDT) Received: from current1.whistle.com (current1.whistle.com [207.76.205.22]) by alpo.whistle.com (8.7.5/8.7.3) with SMTP id MAA18330; Mon, 16 Sep 1996 12:38:31 -0700 (PDT) Message-ID: <323DAC5D.ABD322C@whistle.com> Date: Mon, 16 Sep 1996 12:37:01 -0700 From: Julian Elischer Organization: Whistle Communications X-Mailer: Mozilla 3.0b6 (X11; I; FreeBSD 2.2-CURRENT i386) MIME-Version: 1.0 To: Jeffrey Barber CC: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Re: Very Slow Ethernet Link References: <01BBA3A2.11B93340@jabpc.rtfm.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Jeffrey Barber wrote: > > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: OK for a start your FreeBSD times are approximatly 1/3 the times of the linux ones.. 0.3mS vs 1mS secondly, pinging the loopback interface doesn't test the ethernet as the packet never goes anywhere NEAR the ethernet. thirdly, if the ethernet is slow, and you haven't showed that it is, you need to give your hardware configuration. maybe FreeBSD is configured for the wrong interrupt.. that tends to make it slow.. lastly, 2.1 is way old.. you should install 2.1.5 becasue 2.1 is hard to support as everyone has moved on. > > bash$ ping localhost > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=255 time=0.342 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=255 time=0.362 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=255 time=0.349 ms > > --- localhost.arctic.net ping statistics --- > 6 packets transmitted, 6 packets received, 0% packet loss > round-trip min/avg/max = 0.342/0.349/0.362 ms > > bash$ ifconfig -a > > lp0: flags=8810 mtu 1500 > ep0: flags=863 mtu 1500 > inet 19.51.13.1 netmask 0xffffff00 broadcast 19.51.13.255 > lo0: flags=8009 mtu 16384 > inet 127.0.0.1 netmask 0xff000000 > sl0: flags=c010 mtu 552 > tun0: flags=8010 mtu 1500 > > On my Linux box I get a ping response of: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=64 time=1.0 ms > > Big difference here. Please shed some light on this for me. > > TIA From owner-freebsd-hardware Mon Sep 16 13:44:50 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA07040 for hardware-outgoing; Mon, 16 Sep 1996 13:44:50 -0700 (PDT) Received: from rah.star-gate.com (rah.star-gate.com [204.188.121.18]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id NAA07016; Mon, 16 Sep 1996 13:44:40 -0700 (PDT) Received: from rah.star-gate.com (localhost.star-gate.com [127.0.0.1]) by rah.star-gate.com (8.7.5/8.7.3) with ESMTP id NAA14600; Mon, 16 Sep 1996 13:44:14 -0700 (PDT) Message-Id: <199609162044.NAA14600@rah.star-gate.com> X-Mailer: exmh version 1.6.9 8/22/96 to: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Wait and then Post! (Re: Very Slow Ethernet Link ) In-reply-to: Your message of "Mon, 16 Sep 1996 12:37:01 PDT." <323DAC5D.ABD322C@whistle.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 16 Sep 1996 13:44:14 -0700 From: Amancio Hasty Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Is there a way to throttle responses to dumb posts ? 8) If the answer is obvious, try to wait a little bit before posting a response mostly because I am sure that some will not be able to resist answering the post 8) Cheers, Amancio From owner-freebsd-hardware Mon Sep 16 15:33:54 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id PAA15588 for hardware-outgoing; Mon, 16 Sep 1996 15:33:54 -0700 (PDT) Received: from panda.hilink.com.au (panda.hilink.com.au [203.2.144.5]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id PAA15543; Mon, 16 Sep 1996 15:33:35 -0700 (PDT) Received: (from danny@localhost) by panda.hilink.com.au (8.7.5/8.7.3) id IAA01117; Tue, 17 Sep 1996 08:32:52 +1000 (EST) Date: Tue, 17 Sep 1996 08:32:51 +1000 (EST) From: "Daniel O'Callaghan" To: "Gestur A. Grjetarsson" cc: questions@freebsd.org, hardware@freebsd.org, admin@islandia.is Subject: Re: system frequently hangs, and most often automatically reboots on daily basis. In-Reply-To: <3.0b11.32.19960916034918.008f1100@islandia.is> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Mon, 16 Sep 1996, Gestur A. Grjetarsson wrote: > The failure is in few words: > The system frequently hangs, often it reboots automatically without > any notice or much workload. We've been running the FreeBSD os in about > a year now, and have tolerated this failures, but it seems that they are > > the system consists of: > FreeBSD 2.1.5 > > cslip and ppp are installed Hmm, I suffered this with 2.0.5 for a while, but I have not had a crash/hang since switching to 2.1.5. I have a feeling that it is caused by problems in the SLIP code erroneously expanding bad CSLIP headers. Switching to PPP only stopped the problem completely. The CSLIP problem has been fixed in 2.1.5 by David Greenman, which is why I'm surprised you are still suffering. Try switching everyone possible over to PPP and see if that reduces the problem. DG, did however express doubt as to the cause of my problems, and suggested that I was running out of mbuf clusters. Try rebuilding a kernel with options "NMBCLUSTERS=2048" (4096 etc) or options MAXUSERS 64 Danny From owner-freebsd-hardware Mon Sep 16 15:58:05 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id PAA18149 for hardware-outgoing; Mon, 16 Sep 1996 15:58:05 -0700 (PDT) Received: from zeus.xtalwind.net (h-advance.x31.infi.net [206.27.115.54]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id PAA18117; Mon, 16 Sep 1996 15:57:51 -0700 (PDT) Received: from localhost (localhost [127.0.0.1]) by zeus.xtalwind.net (8.7.5/8.7.3) with SMTP id SAA01171; Mon, 16 Sep 1996 18:57:26 -0400 (EDT) Date: Mon, 16 Sep 1996 18:57:26 -0400 (EDT) From: jack To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Re: Very Slow Ethernet Link In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Mon, 16 Sep 1996, Jeffrey Barber wrote: > Ok, I just installed FreeBSD 2.1 and boy this is slow, Really? >Example: > > bash$ ping localhost > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=255 time=0.342 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=255 time=0.362 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=255 time=0.349 ms > > --- localhost.arctic.net ping statistics --- > 6 packets transmitted, 6 packets received, 0% packet loss > round-trip min/avg/max = 0.342/0.349/0.362 ms > > > On my Linux box I get a ping response of: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=64 time=1.0 ms > > Big difference here. Please shed some light on this for me. FreeBSD averages 0 POINT 349ms Linux averages 0 POINT 95ms. FreeBSD's SLOWEST was 0 POINT 362 ms Linux's FASTEST was 0 POINT 9ms. Let's round FBSD's numbers to the same number of significant digits. FBSD Linux 0.4ms 1.1ms 0.3ms 0.9ms 0.4ms 0.9ms 0.3ms 1.0ms Which one is slow? -------------------------------------------------------------------------- Jack O'Neill Finger jacko@onyx.xtalwind.net or jack@xtalwind.net http://www.xtalwind.net/~jacko/pubpgp.html #include for my PGP key. PGP Key fingerprint = F6 C4 E6 D4 2F 15 A7 67 FD 09 E9 3C 5F CC EB CD -------------------------------------------------------------------------- From owner-freebsd-hardware Mon Sep 16 15:58:21 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id PAA18205 for hardware-outgoing; Mon, 16 Sep 1996 15:58:21 -0700 (PDT) Received: from rock.rtfm.com (guest@rock.anchorage.net [204.17.241.163]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id PAA18181; Mon, 16 Sep 1996 15:58:13 -0700 (PDT) Received: from jabpc.rtfm.com (jabpc.rtfm.com [199.237.0.200]) by rock.rtfm.com (8.6.12/8.6.9) with SMTP id OAA05494; Mon, 16 Sep 1996 14:53:31 -0300 Received: by jabpc.rtfm.com with Microsoft Mail id <01BBA3DF.D5124740@jabpc.rtfm.com>; Mon, 16 Sep 1996 15:00:43 -0800 Message-ID: <01BBA3DF.D5124740@jabpc.rtfm.com> From: Jeffrey Barber To: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Slow Etherlink Date: Mon, 16 Sep 1996 15:00:41 -0800 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk OK, If we can get past all the sarcasim bull shit! I realize that the = ping I showed for Linux seems to be slower than FreeBSD but the point is = that I have faster telnet response from Linux than I do FreeBSD. For the = more serious ppl who want to help. Let me rephrase my question: Why = would pinging and telneting to FreeBSD be slower than that of a Linux = box? FreeBSD: bash$ ifconfig -a lp0: flags=3D8810 mtu 1500 ep0: flags=3D863 mtu 1500 inet 19.51.13.1 netmask 0xffffff00 broadcast 19.51.13.255 lo0: flags=3D8009 mtu 16384 inet 127.0.0.1 netmask 0xff000000=20 sl0: flags=3Dc010 mtu 552 tun0: flags=3D8010 mtu 1500 PING localhost (127.0.0.1): 56 data bytes 64 bytes from 127.0.0.1: icmp_seq=3D0 ttl=3D255 time=3D0.356 ms 64 bytes from 127.0.0.1: icmp_seq=3D1 ttl=3D255 time=3D0.342 ms 64 bytes from 127.0.0.1: icmp_seq=3D2 ttl=3D255 time=3D0.362 ms 64 bytes from 127.0.0.1: icmp_seq=3D3 ttl=3D255 time=3D0.349 ms Linux: PING localhost (127.0.0.1): 56 data bytes 64 bytes from 127.0.0.1: icmp_seq=3D0 ttl=3D64 time=3D1.1 ms 64 bytes from 127.0.0.1: icmp_seq=3D1 ttl=3D64 time=3D0.9 ms 64 bytes from 127.0.0.1: icmp_seq=3D2 ttl=3D64 time=3D0.9 ms 64 bytes from 127.0.0.1: icmp_seq=3D3 ttl=3D64 time=3D1.0 ms I have never seen the SIMPLEX entries before on other OS's. Can this be = the problem or no? I have a 3com Etherlink III isa card installed the = FreeBSD system of which I had in a Linux box previously. Comments on trouble shooting this would be nice. Thanks From owner-freebsd-hardware Mon Sep 16 16:21:46 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id QAA19568 for hardware-outgoing; Mon, 16 Sep 1996 16:21:46 -0700 (PDT) Received: from rah.star-gate.com (rah.star-gate.com [204.188.121.18]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id QAA19547; Mon, 16 Sep 1996 16:21:42 -0700 (PDT) Received: from rah.star-gate.com (localhost.star-gate.com [127.0.0.1]) by rah.star-gate.com (8.7.5/8.7.3) with ESMTP id QAA18099; Mon, 16 Sep 1996 16:21:05 -0700 (PDT) Message-Id: <199609162321.QAA18099@rah.star-gate.com> X-Mailer: exmh version 1.6.9 8/22/96 To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Re: Slow Etherlink In-reply-to: Your message of "Mon, 16 Sep 1996 15:00:41 -0800." <01BBA3DF.D5124740@jabpc.rtfm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 16 Sep 1996 16:21:05 -0700 From: Amancio Hasty Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk >From The Desk Of Jeffrey Barber : > OK, If we can get past all the sarcasim bull shit! I realize that the = > ping I showed for Linux seems to be slower than FreeBSD but the point is = Try not to post bull shit posts. If indeed the FreeBSD box is slower than the Linux box I would start by posting the actual measurements which show the results indicating your assumptions. Also, state the configuration of both the Linux box and the FreeBSD box. Amancio From owner-freebsd-hardware Mon Sep 16 16:30:56 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id QAA20023 for hardware-outgoing; Mon, 16 Sep 1996 16:30:56 -0700 (PDT) Received: from tibet.stepnet.com (tibet.stepnet.com [206.14.120.100]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id QAA20018 for ; Mon, 16 Sep 1996 16:30:50 -0700 (PDT) Received: (from ping@localhost) by tibet.stepnet.com (8.7.5/8.7.3) id QAA25264 for freebsd-hardware@freebsd.org; Mon, 16 Sep 1996 16:39:54 -0700 (PDT) From: Ping Mai Message-Id: <199609162339.QAA25264@tibet.stepnet.com> Subject: is matrox millenium support? To: freebsd-hardware@freebsd.org Date: Mon, 16 Sep 1996 16:39:53 -0700 (PDT) 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-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, is the matrox millennium support by xfree? ping From owner-freebsd-hardware Mon Sep 16 16:47:09 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id QAA20636 for hardware-outgoing; Mon, 16 Sep 1996 16:47:09 -0700 (PDT) Received: from orion.webspan.net (root@orion.webspan.net [206.154.70.41]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id QAA20614; Mon, 16 Sep 1996 16:47:02 -0700 (PDT) Received: from localhost (gpalmer@localhost [127.0.0.1]) by orion.webspan.net (8.7.5/8.6.12) with SMTP id TAA28206; Mon, 16 Sep 1996 19:46:27 -0400 (EDT) X-Authentication-Warning: orion.webspan.net: Host gpalmer@localhost [127.0.0.1] didn't use HELO protocol To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" From: "Gary Palmer" Subject: Re: Slow Etherlink In-reply-to: Your message of "Mon, 16 Sep 1996 15:00:41 -0800." <01BBA3DF.D5124740@jabpc.rtfm.com> Date: Mon, 16 Sep 1996 19:46:27 -0400 Message-ID: <28202.842917587@orion.webspan.net> Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Jeffrey Barber wrote in message ID <01BBA3DF.D5124740@jabpc.rtfm.com>: > OK, If we can get past all the sarcasim bull shit! Perhaps you should phrase your questions better and provide more relevant information in that case. Complaining about network speed, and then including results which contradict your problem is BOUND to get sarcastic responses! > I realize that the > ping I showed for Linux seems to be slower than FreeBSD but the point is > that I have faster telnet response from Linux than I do FreeBSD. For the > more serious ppl who want to help. Let me rephrase my question: Why > would pinging and telneting to FreeBSD be slower than that of a Linux > box? Why ask about ethernet speed / response times and provide lo0 (loopback) response times? They are two TOTALLY different interfaces, and are TOTALLY unrelated! (well, not totally, but they follow different code paths in the kernel after a certain point) > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=3D0 ttl=3D255 time=3D0.356 ms > 64 bytes from 127.0.0.1: icmp_seq=3D1 ttl=3D255 time=3D0.342 ms > 64 bytes from 127.0.0.1: icmp_seq=3D2 ttl=3D255 time=3D0.362 ms > 64 bytes from 127.0.0.1: icmp_seq=3D3 ttl=3D255 time=3D0.349 ms > > Linux: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=3D0 ttl=3D64 time=3D1.1 ms > 64 bytes from 127.0.0.1: icmp_seq=3D1 ttl=3D64 time=3D0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=3D2 ttl=3D64 time=3D0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=3D3 ttl=3D64 time=3D1.0 ms > I have never seen the SIMPLEX entries before on other OS's. Can this be = > the problem or no? I have a 3com Etherlink III isa card installed the = > FreeBSD system of which I had in a Linux box previously. AHA! USEFUL INFORMATION ALERT!!!!! >From the file /sys/i386/conf/LINT: # ep: 3Com 3C509 (buggy) (3c509 == EtherLink III) The driver in FreeBSD isn't up to much I'm afraid, and has been slated for a re-write for a while. Unfortunately, issues such as kernel stability tend to take precidence. Gary -- Gary Palmer FreeBSD Core Team Member FreeBSD: Turning PC's into workstations. See http://www.FreeBSD.ORG/ for info From owner-freebsd-hardware Mon Sep 16 17:29:09 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id RAA23489 for hardware-outgoing; Mon, 16 Sep 1996 17:29:09 -0700 (PDT) Received: from solar.os.com (craigs@solar.os.com [199.232.136.65]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id RAA23480; Mon, 16 Sep 1996 17:29:03 -0700 (PDT) Received: (from craigs@localhost) by solar.os.com (8.7/8.7.0) id UAA30316; Mon, 16 Sep 1996 20:31:05 -0400 Date: Mon, 16 Sep 1996 20:31:04 -0400 From: Craig Shrimpton Subject: Re: Slow Etherlink To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" In-Reply-To: <01BBA3DF.D5124740@jabpc.rtfm.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Mon, 16 Sep 1996, Jeffrey Barber wrote: > OK, If we can get past all the sarcasim bull shit! I realize that the ping >I showed for Linux seems to be slower than FreeBSD but the point is that I >have faster telnet response from Linux than I do FreeBSD. For the more >serious ppl who want to help. Let me rephrase my question: Why would >pinging and telneting to FreeBSD be slower than that of a Linux box? Do you mean slower on start up or just plain slower. A ping to the localhost will not tell you anything about telnet performance. They don't even use the same protocols (ICMP vs. TCP). If you mean slower to start, try looking at your IN-ADDR.ARPA setup. Improperly configured reverse DNS can make telnet crawl. One thing I will say about Linux is that it has superior screen display performance. So, if what you are complaining about is screen redraw speed, Linux is much faster than FreeBSD. However, the redraw slowness of FreeBSD does not show up under xterm. Maybe it's the syscons driver, try the other driver and see if that's faster. Do remember though, for routing functions and raw data transfers, FreeBSD blows the doors off of Linux. (and Cisco for that matter) Good Luck, Craig +------------------------------------+--------------------------------------+ | Craig Shrimpton | e-mail: craigs@os.com | | Orbit Systems | information: info@os.com | | Worcester, MA 508.753.8776 | http://www.os.com/ | +------------------------------------+--------------------------------------+ _/_/_/_/ _/_/_/_/ _/_/_/_/ _/_/_/_/ _/_/_/_/ _/ _/ _/ _/ _/ _/ _/ _/ _/ _/ _/_/_/ _/_/_/_/ _/ _/ _/ _/ _/ _/ _/ _/ _/ _/ _/_/_/_/ _/ _/ _/_/_/_/ _/_/_/_/ _/ Strategic Systems From owner-freebsd-hardware Mon Sep 16 17:34:38 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id RAA23927 for hardware-outgoing; Mon, 16 Sep 1996 17:34:38 -0700 (PDT) Received: from saguaro.flyingfox.com (saguaro.flyingfox.com [204.188.109.253]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id RAA23867; Mon, 16 Sep 1996 17:34:22 -0700 (PDT) Received: (from jas@localhost) by saguaro.flyingfox.com (8.6.12/8.6.10) id RAA07558; Mon, 16 Sep 1996 17:32:55 -0700 Date: Mon, 16 Sep 1996 17:32:55 -0700 From: Jim Shankland Message-Id: <199609170032.RAA07558@saguaro.flyingfox.com> To: gpalmer@FreeBSD.org, jab@rock.anchorage.net Subject: Re: Slow Etherlink Cc: freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > > I have never seen the SIMPLEX entries before on other OS's. Can this be = > > the problem or no? I have a 3com Etherlink III isa card installed the = > > FreeBSD system of which I had in a Linux box previously. > > AHA! USEFUL INFORMATION ALERT!!!!! > > >From the file /sys/i386/conf/LINT: > > # ep: 3Com 3C509 (buggy) > > (3c509 == EtherLink III) > > The driver in FreeBSD isn't up to much I'm afraid, and has been slated > for a re-write for a while. Unfortunately, issues such as kernel > stability tend to take precidence. On the other hand, I've been running 4 3C509's in an old 486-DX2/66 box running 2.1.0 for about a year now, and it's been rock-solid. I no longer even have a monitor or keyboard plugged in to the box. >From time to time, it gets unplugged. We just plug it back in, and 45 seconds or so later, it's routing again. To call it stable would be an understatement. No sarcasm here; but I'm still waiting for a coherent description of the problem .... Jim Shankland Flying Fox Computer Systems, Inc. From owner-freebsd-hardware Mon Sep 16 17:53:24 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id RAA24850 for hardware-outgoing; Mon, 16 Sep 1996 17:53:24 -0700 (PDT) Received: from genesis.atrad.adelaide.edu.au (genesis.atrad.adelaide.edu.au [129.127.96.120]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id RAA24844; Mon, 16 Sep 1996 17:53:19 -0700 (PDT) Received: from msmith@localhost by genesis.atrad.adelaide.edu.au (8.6.12/8.6.9) id KAA27601; Tue, 17 Sep 1996 10:23:10 +0930 From: Michael Smith Message-Id: <199609170053.KAA27601@genesis.atrad.adelaide.edu.au> Subject: Re: passive backplane (was Re: Any Pentium boards with more than 4 PC) slots? To: hsu@freefall.freebsd.org (Jeffrey Hsu) Date: Tue, 17 Sep 1996 10:23:10 +0930 (CST) Cc: hardware@freefall.freebsd.org In-Reply-To: <199609161636.JAA15362@freefall.freebsd.org> from "Jeffrey Hsu" at Sep 16, 96 09:36:55 am MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Jeffrey Hsu stands accused of saying: > > Speaking of passive backplanes, I have a question. What are they > used for? The hardware engineer I asked a while ago didn't give > a satisfying answer. In fact, I've forgotten what it was. But it > must be good for something, because I keep seeing passive backplanes > advertised in embedded systems magazines. Some good things about PB's : - Easy motherboard replacement (dike the card and drop in a new one). - Space efficiency (no footprint area that's not covered by plugins). - Small footprints (3xISA16 is not uncommon). - Huge footprints (20xISA16 is not uncommon). - Robustness (board flex on card insertion/removal is a non-problem). Take a 20xISA16 PB, a small 486, ethernet and 18 dual-8255 cards and you have 864 digital I/O lines. You can do a hell of a lot of machine control with that 8) -- ]] Mike Smith, Software Engineer msmith@atrad.adelaide.edu.au [[ ]] Genesis Software genesis@atrad.adelaide.edu.au [[ ]] High-speed data acquisition and (GSM mobile) 0411-222-496 [[ ]] realtime instrument control (ph/fax) +61-8-267-3039 [[ ]] Collector of old Unix hardware. "Where are your PEZ?" The Tick [[ From owner-freebsd-hardware Mon Sep 16 18:07:32 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA25417 for hardware-outgoing; Mon, 16 Sep 1996 18:07:32 -0700 (PDT) Received: from Gatekeeper.Lamb.net (ulf@cat-food.Melmac.org [206.169.44.2]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id SAA25394; Mon, 16 Sep 1996 18:07:25 -0700 (PDT) Received: (from ulf@localhost) by Gatekeeper.Lamb.net (8.7.5/8.7.3) id SAA03263; Mon, 16 Sep 1996 18:08:00 -0700 (PDT) From: Ulf Zimmermann Message-Id: <199609170108.SAA03263@Gatekeeper.Lamb.net> Subject: Re: Slow Etherlink To: jab@rock.anchorage.net (Jeffrey Barber) Date: Mon, 16 Sep 1996 18:08:00 -0700 (PDT) Cc: freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: <01BBA3DF.D5124740@jabpc.rtfm.com> from Jeffrey Barber at "Sep 16, 96 03:00:41 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-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > OK, If we can get past all the sarcasim bull shit! I realize that the ping I >showed for Linux seems to be slower than FreeBSD but the point is that I have >faster telnet response from Linux than I do FreeBSD. For the more serious ppl >who want to help. Let me rephrase my question: Why would pinging and telneting >to FreeBSD be slower than that of a Linux box? Again, you show only pinging localhost, which is on the FreeBS host faster then on the shown Linux host. Again, pinging localhost DOESN'T go onto the Ethernet cable. > > FreeBSD: > bash$ ifconfig -a > > lp0: flags=8810 mtu 1500 > ep0: flags=863 mtu 1500 > inet 19.51.13.1 netmask 0xffffff00 broadcast 19.51.13.255 > lo0: flags=8009 mtu 16384 > inet 127.0.0.1 netmask 0xff000000 > sl0: flags=c010 mtu 552 > tun0: flags=8010 mtu 1500 > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=255 time=0.342 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=255 time=0.362 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=255 time=0.349 ms > > Linux: > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms > 64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=2 ttl=64 time=0.9 ms > 64 bytes from 127.0.0.1: icmp_seq=3 ttl=64 time=1.0 ms > > I have never seen the SIMPLEX entries before on other OS's. Can this be the problem or no? I have a 3com Etherlink III isa card installed the FreeBSD system of which I had in a Linux box previously. > > Comments on trouble shooting this would be nice. How should we help you, if you don't tell what is the real problem ? > > Thanks > > Ulf. -------------------------------------------------------------------------- Ulf Zimmermann, 1525 Pacific Ave., Alameda, CA-94501, #: 510-865-0204 Lamb Art Internet Services | http://www.Lamb.net/ | http://www.Alameda.net From owner-freebsd-hardware Mon Sep 16 18:10:01 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA25560 for hardware-outgoing; Mon, 16 Sep 1996 18:10:01 -0700 (PDT) Received: from Gatekeeper.Lamb.net (ulf@cat-food.Melmac.org [206.169.44.2]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id SAA25539 for ; Mon, 16 Sep 1996 18:09:58 -0700 (PDT) Received: (from ulf@localhost) by Gatekeeper.Lamb.net (8.7.5/8.7.3) id SAA03277; Mon, 16 Sep 1996 18:10:47 -0700 (PDT) From: Ulf Zimmermann Message-Id: <199609170110.SAA03277@Gatekeeper.Lamb.net> Subject: Re: is matrox millenium support? To: ping@stepnet.com (Ping Mai) Date: Mon, 16 Sep 1996 18:10:47 -0700 (PDT) Cc: freebsd-hardware@freebsd.org In-Reply-To: <199609162339.QAA25264@tibet.stepnet.com> from Ping Mai at "Sep 16, 96 04:39:53 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-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > Hi, > > is the matrox millennium support by xfree? > > ping > This is answered by Xfree86.org: No, because Matrox doesn't give programming documents without a NDA (Non Disclosure Aggrement). AcceleratedX from Xinside.com has a X11 server, which supports the Matrox. It is also faster then the server from xfree. Ulf. -------------------------------------------------------------------------- Ulf Zimmermann, 1525 Pacific Ave., Alameda, CA-94501, #: 510-865-0204 Lamb Art Internet Services | http://www.Lamb.net/ | http://www.Alameda.net From owner-freebsd-hardware Mon Sep 16 18:28:38 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA26384 for hardware-outgoing; Mon, 16 Sep 1996 18:28:38 -0700 (PDT) Received: from genesis.atrad.adelaide.edu.au (genesis.atrad.adelaide.edu.au [129.127.96.120]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id SAA26360; Mon, 16 Sep 1996 18:28:28 -0700 (PDT) Received: from msmith@localhost by genesis.atrad.adelaide.edu.au (8.6.12/8.6.9) id KAA27718; Tue, 17 Sep 1996 10:56:58 +0930 From: Michael Smith Message-Id: <199609170126.KAA27718@genesis.atrad.adelaide.edu.au> Subject: Re: PCMCIA, APM, 3C562 To: BRETT_GLASS@ccgate.infoworld.com Date: Tue, 17 Sep 1996 10:56:57 +0930 (CST) Cc: hardware@freebsd.org, questions@freebsd.org In-Reply-To: <9608168429.AA842902427@ccgate.infoworld.com> from "BRETT_GLASS@ccgate.infoworld.com" at Sep 16, 96 02:23:42 pm MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk BRETT_GLASS@ccgate.infoworld.com stands accused of saying: > > How good is the PCMCIA support in FreeBSD? Will I be able to swap cards? PCC support is actually getting along pretty well. You can certainly swap cards, and with certain caveats (routes, NFS mounts, open serial ports) you'll be just fine. > Is APM supported? Will the system (including PCMCIA) be able to survive a > suspend/resume cycle without "freaking out" or getting too busy to use due > to missed items in /etc/crontab? (Come to think of it, how DOES it handle > missed items in /etc/crontab?) Is there a sync on suspend? If the battery > dies during a suspend (common on many laptops that suspend when the > battery gets low), is the filesystem left "clean" and ready for a reboot? APM is supported, although many laptop APM implementations make a lot of assumptions. I can enable APM and lid-suspend my Sharp, but trying to talk to the APM interface causes it to trap (the fault address is in the BIOS, so I don't think it's the APM driver's fault per se.) The system syncs on suspend, and snaps the clock when it resumes, so that missed cron jobs are just lost. Filesystems aren't marked clean, as that requires an unmount. Some PCC's require reinitialisation coming out of a suspend (and removing a card while suspended can cause grief), and support for that is in place but not implemented. > Finally, there doesn't appear to be a driver for my 3C562 Modem/Ethernet > combo card. As I understand it, this card is really just a 3Com Ethernet > adapter and a modem (with standard UART) sharing an IRQ. Is there a driver > available? Would it be possible to construct one by creating a "hybrid" > driver that probed for the card, grabbed the one interrupt, and linked to > routines from the existing sio and 3Com PCMCIA Ethernet drivers? You could probably do that, yes. > --Brett -- ]] Mike Smith, Software Engineer msmith@atrad.adelaide.edu.au [[ ]] Genesis Software genesis@atrad.adelaide.edu.au [[ ]] High-speed data acquisition and (GSM mobile) 0411-222-496 [[ ]] realtime instrument control (ph/fax) +61-8-267-3039 [[ ]] Collector of old Unix hardware. "Where are your PEZ?" The Tick [[ From owner-freebsd-hardware Mon Sep 16 19:03:21 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id TAA28123 for hardware-outgoing; Mon, 16 Sep 1996 19:03:21 -0700 (PDT) Received: from phaeton.artisoft.com (phaeton.Artisoft.COM [198.17.250.211]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id TAA28108; Mon, 16 Sep 1996 19:03:16 -0700 (PDT) Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id TAA03421; Mon, 16 Sep 1996 19:02:04 -0700 From: Terry Lambert Message-Id: <199609170202.TAA03421@phaeton.artisoft.com> Subject: Re: Slow Etherlink To: jab@rock.anchorage.net (Jeffrey Barber) Date: Mon, 16 Sep 1996 19:02:04 -0700 (MST) Cc: freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: <01BBA3DF.D5124740@jabpc.rtfm.com> from "Jeffrey Barber" at Sep 16, 96 03:00:41 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-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > OK, If we can get past all the sarcasim bull shit! I realize that the = > ping I showed for Linux seems to be slower than FreeBSD but the point is = > that I have faster telnet response from Linux than I do FreeBSD. For the = > more serious ppl who want to help. Let me rephrase my question: Why = > would pinging and telneting to FreeBSD be slower than that of a Linux = > box? It shouldn't be. By "slower", do you mean: 1) Slower to make a TCP connection for Telnet? a) Check your rarp setup b) Check your DNS setup c) Check your hosts file d) Back off a version or two of BIND e) Back off a version of sendmail, or reset the sendmail option to prevent it verifying source addresses 2) Slower to fail in the no route to host case? a) Yes, this is because FreeBSD retries rather than giving up. For transient initial loss, this seems slower. The fix is to correct your circuit so you don't get transientinitial loss. b) In the case of a transient failure, the BSD behaviour will not lose the connection, where the Linux will. 3) Slower to respond to pings? a) This could be your source host b) Check your TCP extensions. If you have a bogus TCP/IP implementation that doesn't understand RFC 1323 or RFC 1644, or can't correctly ignore them if they are used, then you should turn them off. 4) Slower to start pinging? a) There is an option that controls "time to live" on packets. Man sysctl. > bash$ ifconfig -a > > lp0: flags=3D8810 mtu 1500 > ep0: flags=3D863 mtu 1500 > inet 19.51.13.1 netmask 0xffffff00 broadcast 19.51.13.255 > > I have never seen the SIMPLEX entries before on other OS's. Can this be = > the problem or no? I have a 3com Etherlink III isa card installed the = > FreeBSD system of which I had in a Linux box previously. It means it can't transmit and receive at the same time. This is a card "feature", and if you haven't seen it before, your other OS has been lying to you (or it's one of the drivers that needs updated). In general, SIMPLEX, if capable of being fixed via a driver interface (usually it is not, as noted above), will only affect unidirectional throughput, generally out of the machine, and generally only for real data transferred (ie: it's not your "ping" problem, whatever your "ping" problem is -- you haven't supplied enough information for us to know). 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-hardware Mon Sep 16 19:05:57 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id TAA28298 for hardware-outgoing; Mon, 16 Sep 1996 19:05:57 -0700 (PDT) Received: from genesis.atrad.adelaide.edu.au (genesis.atrad.adelaide.edu.au [129.127.96.120]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id TAA28290 for ; Mon, 16 Sep 1996 19:05:51 -0700 (PDT) Received: from msmith@localhost by genesis.atrad.adelaide.edu.au (8.6.12/8.6.9) id LAA28148; Tue, 17 Sep 1996 11:35:33 +0930 From: Michael Smith Message-Id: <199609170205.LAA28148@genesis.atrad.adelaide.edu.au> Subject: Re: is matrox millenium support? To: ulf@Lamb.net (Ulf Zimmermann) Date: Tue, 17 Sep 1996 11:35:33 +0930 (CST) Cc: ping@stepnet.com, freebsd-hardware@freebsd.org In-Reply-To: <199609170110.SAA03277@Gatekeeper.Lamb.net> from "Ulf Zimmermann" at Sep 16, 96 06:10:47 pm MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Ulf Zimmermann stands accused of saying: > > AcceleratedX from Xinside.com has a X11 server, which supports the Matrox. > It is also faster then the server from xfree. Speaking of this "faster" X server, I've noticed that Tcl/Tk applications running remotely (ie. on another machine), display _atrociously_ slowly on the Xinside server, but very quickly (ie. as expected) on the XFree server on the same hardware. Anyone else seen this? > Ulf Zimmermann, 1525 Pacific Ave., Alameda, CA-94501, #: 510-865-0204 -- ]] Mike Smith, Software Engineer msmith@atrad.adelaide.edu.au [[ ]] Genesis Software genesis@atrad.adelaide.edu.au [[ ]] High-speed data acquisition and (GSM mobile) 0411-222-496 [[ ]] realtime instrument control (ph/fax) +61-8-267-3039 [[ ]] Collector of old Unix hardware. "Where are your PEZ?" The Tick [[ From owner-freebsd-hardware Mon Sep 16 19:08:23 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id TAA28443 for hardware-outgoing; Mon, 16 Sep 1996 19:08:23 -0700 (PDT) Received: from terra.Sarnoff.COM (terra.sarnoff.com [130.33.11.203]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id TAA28428 for ; Mon, 16 Sep 1996 19:08:19 -0700 (PDT) Received: (from rminnich@localhost) by terra.Sarnoff.COM (8.6.12/8.6.12) id WAA00698; Mon, 16 Sep 1996 22:06:47 -0400 Date: Mon, 16 Sep 1996 22:06:47 -0400 (EDT) From: "Ron G. Minnich" X-Sender: rminnich@terra To: Ulf Zimmermann cc: Ping Mai , freebsd-hardware@FreeBSD.org Subject: Re: is matrox millenium support? In-Reply-To: <199609170110.SAA03277@Gatekeeper.Lamb.net> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Mon, 16 Sep 1996, Ulf Zimmermann wrote: > This is answered by Xfree86.org: No, because Matrox doesn't give > programming documents without a NDA (Non Disclosure Aggrement). this situation is now changing. Somebody at matrox has woken up, smelled coffee, and is changing things for the better. And i've lost the URL with the copies of the letters from matrox (sorry!). But, it does appear taht a real matrox driver may happen in the next few months. do a search and you may find the page with the relevant info. ron From owner-freebsd-hardware Mon Sep 16 19:40:37 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id TAA00721 for hardware-outgoing; Mon, 16 Sep 1996 19:40:37 -0700 (PDT) Received: from root.com (implode.root.com [198.145.90.17]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id TAA00696; Mon, 16 Sep 1996 19:40:25 -0700 (PDT) Received: from localhost (localhost [127.0.0.1]) by root.com (8.7.5/8.6.5) with SMTP id TAA08641; Mon, 16 Sep 1996 19:40:57 -0700 (PDT) Message-Id: <199609170240.TAA08641@root.com> X-Authentication-Warning: implode.root.com: Host localhost [127.0.0.1] didn't use HELO protocol To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Re: Slow Etherlink In-reply-to: Your message of "Mon, 16 Sep 1996 15:00:41 -0800." <01BBA3DF.D5124740@jabpc.rtfm.com> From: David Greenman Reply-To: dg@root.com Date: Mon, 16 Sep 1996 19:40:57 -0700 Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk >OK, If we can get past all the sarcasim bull shit! I realize that the = >ping I showed for Linux seems to be slower than FreeBSD but the point is = >that I have faster telnet response from Linux than I do FreeBSD. For the = >more serious ppl who want to help. Let me rephrase my question: Why = >would pinging and telneting to FreeBSD be slower than that of a Linux = >box? I'm going to assume that there is a real problem (which can't be infered from the data you provided). One of the common problems with the 3c509 is that it is easy to misconfigure the irq and yet still have the card appear to sort of work. The result is 0-1 _second_ round-trip times. Try pinging another host on your ethernet, and if this is the case, then you have a irq mismatch or conflict. -DG David Greenman Core-team/Principal Architect, The FreeBSD Project From owner-freebsd-hardware Mon Sep 16 20:26:11 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id UAA03572 for hardware-outgoing; Mon, 16 Sep 1996 20:26:11 -0700 (PDT) Received: from solar.os.com (craigs@solar.os.com [199.232.136.65]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id UAA03567; Mon, 16 Sep 1996 20:26:03 -0700 (PDT) Received: (from craigs@localhost) by solar.os.com (8.7/8.7.0) id XAA31028; Mon, 16 Sep 1996 23:33:07 -0400 Date: Mon, 16 Sep 1996 23:33:07 -0400 From: Craig Shrimpton Subject: Re: Slow Etherlink To: Terry Lambert cc: Jeffrey Barber , freebsd-hardware@FreeBSD.ORG, hackers@FreeBSD.ORG In-Reply-To: <199609170202.TAA03421@phaeton.artisoft.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Mon, 16 Sep 1996, Terry Lambert wrote: > > It means it can't transmit and receive at the same time. This is a card > "feature", and if you haven't seen it before, your other OS has been > lying to you (or it's one of the drivers that needs updated). > > In general, SIMPLEX, if capable of being fixed via a driver interface > (usually it is not, as noted above), will only affect unidirectional > throughput, generally out of the machine, and generally only for real > data transferred (ie: it's not your "ping" problem, whatever your "ping" > What cards are "synchronous?" I use SMC EtherPower PCI cards (de0) because they are basically plug and play under FreeBSD. I put 3 in a FBSD router box and they all worked first try automagically! Any idea if the SMC drivers are updateable? Craig +------------------------------------+--------------------------------------+ | Craig Shrimpton | e-mail: craigs@os.com | | Orbit Systems | information: info@os.com | | Worcester, MA 508.753.8776 | http://www.os.com/ | +------------------------------------+--------------------------------------+ From owner-freebsd-hardware Mon Sep 16 20:28:31 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id UAA03872 for hardware-outgoing; Mon, 16 Sep 1996 20:28:31 -0700 (PDT) Received: from genesis.atrad.adelaide.edu.au (genesis.atrad.adelaide.edu.au [129.127.96.120]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id UAA03865 for ; Mon, 16 Sep 1996 20:28:26 -0700 (PDT) Received: from msmith@localhost by genesis.atrad.adelaide.edu.au (8.6.12/8.6.9) id MAA28840 for hardware@freebsd.org; Tue, 17 Sep 1996 12:58:18 +0930 From: Michael Smith Message-Id: <199609170328.MAA28840@genesis.atrad.adelaide.edu.au> Subject: RAM timings for Triton chipsets? To: hardware@freebsd.org Date: Tue, 17 Sep 1996 12:58:18 +0930 (CST) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Just a quick question for anyone familiar with the jargon that Award use in their older Triton BIOSsen. I just had to reboot my system here (to clear an NFS mount that's now in Japan 8), and stuck my nose into the "Chipset Setup" option in the BIOS for a poke around. I thought I'd try changing a couple of the memory timing options from "x2222" to "x4444", there being no explanation of what these mean. And lo and behold, the system _seems_ much faster. It could just be that it's just been rebooted after being up for months, but at the same time I'm wondering if the changes could be significant. FreeBSD 2.1-STABLE #0: Wed Mar 20 11:07:43 CST 1996 root@cain.atrad.adelaide.edu.au:/local1/2.1.0-STABLE/src/sys/compile/CAIN CPU: 100-MHz Pentium 815\\100 (Pentium-class CPU) Origin = "GenuineIntel" Id = 0x525 Stepping=5 Features=0x1bf real memory = 33554432 (32768K bytes) avail memory = 31301632 (30568K bytes) pcibus_setup(1): mode1res=0x80000000 (0x80000000), mode2res=0xff (0x0e) pcibus_setup(2): mode1res=0x80000000 (0x80000000) pcibus_check: device 0 is there (id=122d8086) Probing for devices on PCI bus 0: configuration mode 1 allows 32 devices. chip0 rev 1 on pci0:0 chip1 rev 2 on pci0:7 (Apologies for the ancient kernel, it's just so STABLE that I've had no call for a new one. This and 'genesis' : FreeBSD 2.1-STABLE #0: Wed Nov 1 15:35:25 CST 1995 are two excellent advertisements for FreeBSD.) -- ]] Mike Smith, Software Engineer msmith@atrad.adelaide.edu.au [[ ]] Genesis Software genesis@atrad.adelaide.edu.au [[ ]] High-speed data acquisition and (GSM mobile) 0411-222-496 [[ ]] realtime instrument control (ph/fax) +61-8-267-3039 [[ ]] Collector of old Unix hardware. "Where are your PEZ?" The Tick [[ From owner-freebsd-hardware Mon Sep 16 20:56:28 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id UAA05307 for hardware-outgoing; Mon, 16 Sep 1996 20:56:28 -0700 (PDT) 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 UAA05294; Mon, 16 Sep 1996 20:56:15 -0700 (PDT) Received: from MindBender.serv.net by mx.serv.net (8.7.5/SERV Revision: 2.30) id UAA07939; Mon, 16 Sep 1996 20:50:45 -0700 (PDT) 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 UAA19977; Mon, 16 Sep 1996 20:36:33 -0700 (PDT) Message-Id: <199609170336.UAA19977@MindBender.serv.net> X-Authentication-Warning: MindBender.serv.net: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: Jeffrey Hsu cc: hardware@freefall.freebsd.org Subject: Re: passive backplane (was Re: Any Pentium boards with more than 4 PC) slots? In-reply-to: Your message of Mon, 16 Sep 96 09:36:55 -0700. <199609161636.JAA15362@freefall.freebsd.org> Date: Mon, 16 Sep 1996 20:36:33 -0700 From: "Michael L. VanLoon -- HeadCandy.com" Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk >Speaking of passive backplanes, I have a question. What are they >used for? The hardware engineer I asked a while ago didn't give >a satisfying answer. In fact, I've forgotten what it was. But it >must be good for something, because I keep seeing passive backplanes >advertised in embedded systems magazines. Two things, primarily: 1) Creating a computer where you can just "swap-out" the CPU, and "swap-in" a better one. I. e. put the entire motherboard electronics on a PCI-ish board, and plug it into a back-plane. Then, when you want something better, yank the card and plug in a new one. In reality, this has never been cheaper than buying a new motherboard. Usually the companies that make something this cool end up charging twice as much for the technology. 2) Extending your bus so you can have fifteen or twenty cards plugged in. ----------------------------------------------------------------------------- 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-hardware Mon Sep 16 22:04:00 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id WAA08473 for hardware-outgoing; Mon, 16 Sep 1996 22:04:00 -0700 (PDT) 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 WAA08462 for ; Mon, 16 Sep 1996 22:03:49 -0700 (PDT) Received: from MindBender.serv.net by mx.serv.net (8.7.5/SERV Revision: 2.30) id WAA09311; Mon, 16 Sep 1996 22:01:23 -0700 (PDT) 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 WAA21788; Mon, 16 Sep 1996 22:00:59 -0700 (PDT) Message-Id: <199609170500.WAA21788@MindBender.serv.net> X-Authentication-Warning: MindBender.serv.net: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: Michael Smith cc: hardware@freebsd.org Subject: Re: RAM timings for Triton chipsets? In-reply-to: Your message of Tue, 17 Sep 96 12:58:18 +0930. <199609170328.MAA28840@genesis.atrad.adelaide.edu.au> Date: Mon, 16 Sep 1996 22:00:41 -0700 From: "Michael L. VanLoon -- HeadCandy.com" Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >Just a quick question for anyone familiar with the jargon that Award >use in their older Triton BIOSsen. [...] >I thought I'd try changing a couple of the memory timing options from >"x2222" to "x4444", there being no explanation of what these mean. >And lo and behold, the system _seems_ much faster. It could just be that >it's just been rebooted after being up for months, but at the same time >I'm wondering if the changes could be significant. It must be, because you just made it much slower... :-) x2222 and x4444 mean how many cycles it takes to access memory for each cycle of a burst read or write. The x means that the first access is longer (typically something like 6 cycles). After the first access, it can burst at a word for every 2 bus cycles (or as the case is now, for ever 4 bus cycles). ----------------------------------------------------------------------------- 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-hardware Mon Sep 16 22:08:17 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id WAA08745 for hardware-outgoing; Mon, 16 Sep 1996 22:08:17 -0700 (PDT) Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.19]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id WAA08721; Mon, 16 Sep 1996 22:08:08 -0700 (PDT) Received: (from bde@localhost) by godzilla.zeta.org.au (8.6.12/8.6.9) id OAA10729; Tue, 17 Sep 1996 14:56:00 +1000 Date: Tue, 17 Sep 1996 14:56:00 +1000 From: Bruce Evans Message-Id: <199609170456.OAA10729@godzilla.zeta.org.au> To: craigs@os.com, jab@rock.anchorage.net Subject: Re: Slow Etherlink Cc: freebsd-hardware@freebsd.org, hackers@freebsd.org Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >One thing I will say about Linux is that it has superior screen display >performance. So, if what you are complaining about is screen redraw >speed, Linux is much faster than FreeBSD. Really? Linux was 6-12 times slower last time I worked on speeding up syscons. >However, the redraw slowness >of FreeBSD does not show up under xterm. Perhaps you are noticing the redraw fastness of FreeBSD. Redraws for running vi over ethernet connections _seem_ to be very slow because there is a long pause after the data in the first packet is written. The pause is actually caused by delayed ACKs and may be avoided using the undocumented option TCP_ACK_HACK. This option was standard in FreeBSD-2.0 and in FreeBSD-current up to just before the release of 2.0.5. It was disabled because it caused problems with T/TCP. Linux has a similar option CONFIG_TCP_NAGLE_OFF. >Maybe it's the syscons driver, >try the other driver and see if that's faster. ... pcvt is much slower than syscons. Bruce Test notes and output: --- The test simply writes 2000 bytes of printable characters 1000 times. Other methods of writing to the screen are inherently slower (several lines can be written in the time that it takes to format and parse one escape sequence). ISA ET4000: 2.4MB/sec read, 5.9MB/sec write VLB ET4000/W32i: 6.8MB/sec read, 25.5MB/sec write PCI S3/868: 3.5MB/sec read, 23.1MB/sec write -o means stty flag -opost No-scroll: machine video O/S where real user sys speed --------- ------- -------------- --------- ----- ---- ----- ----- DX2/66 VLB ET4000/W32i FreeBSD-rcurrent offscreen-o 1.18 0.01 1.16 1.69 DX2/66 VLB ET4000/W32i FreeBSD-rcurrent onscreen-o 1.19 0.00 1.18 1.68 486/33 ISA ET4000 minix-1.6.25++ offscreen 2 0.01 1.45 1.37 486/33 ISA ET4000 minix-1.6.25++ onscreen 2 0.01 1.60 1.24 DX2/66 VLB ET4000/W32i FreeBSD-bcurrent offscreen 1.62 0.00 1.59 1.23 DX2/66 VLB ET4000/W32i FreeBSD-bcurrent onscreen 1.62 0.02 1.58 1.23 486/33 ISA ET4000 FreeBSD-bcurrent offscreen-o 2.28 0.03 2.24 0.88 486/33 ISA ET4000 FreeBSD-bcurrent onscreen-o 2.34 0.01 2.26 0.85 486/33 ISA ET4000 FreeBSD-current offscreen-o 2.50 0.00 2.46 0.80 486/33 ISA ET4000 FreeBSD-current onscreen-o 2.55 0.02 2.49 0.78 486/33 ISA ET4000 FreeBSD-bcurrent offscreen 3.17 0.00 3.15 0.63 486/33 ISA ET4000 FreeBSD-bcurrent onscreen 3.23 0.03 3.11 0.62 486/33 ISA ET4000 FreeBSD-current offscreen 3.48 0.03 3.41 0.57 486/33 ISA ET4000 FreeBSD-current onscreen 3.55 0.02 3.45 0.56 486/33 ISA ET4000 linux-1.1.36 offscreen 20.80 0.00 20.80 0.10 486/33 ISA ET4000 linux-1.1.36 onscreen 38.34 0.02 38.38 0.05 Scroll: machine video O/S where real user sys speed --------- ------- -------------- --------- ----- ---- ----- ----- 486/33 ISA ET4000 minix-1.6.25++ offscreen 2 0.00 1.70 1.18 486/33 ISA ET4000 minix-1.6.25++ onscreen 2 0.00 1.81 1.10 DX2/66 VLB ET4000/W32i FreeBSD-bcurrent offscreen-o 3.24 0.01 3.21 0.62 DX2/66 VLB ET4000/W32i FreeBSD-bcurrent onscreen-o 3.40 0.01 3.33 0.59 DX2/66 VLB ET4000/W32i FreeBSD-bcurrent offscreen 3.68 0.02 3.63 0.54 DX2/66 VLB ET4000/W32i FreeBSD-bcurrent onscreen 3.97 0.01 3.93 0.50 486/33 ISA ET4000 FreeBSD-bcurrent offscreen-o 5.38 0.02 5.32 0.37 486/33 ISA ET4000 FreeBSD-bcurrent onscreen-o 5.50 0.02 5.38 0.36 486/33 ISA ET4000 FreeBSD-current offscreen-o 5.71 0.02 5.64 0.35 486/33 ISA ET4000 FreeBSD-current onscreen-o 5.72 0.00 5.62 0.35 486/33 ISA ET4000 FreeBSD-bcurrent offscreen 6.42 0.03 6.36 0.31 486/33 ISA ET4000 FreeBSD-bcurrent onscreen 6.39 0.03 6.17 0.31 486/33 ISA ET4000 FreeBSD-current offscreen 6.68 0.02 6.62 0.30 486/33 ISA ET4000 FreeBSD-current onscreen 6.73 0.03 6.54 0.30 486/33 ISA ET4000 linux-1.1.36 offscreen 23.56 0.03 23.60 0.08 486/33 ISA ET4000 linux-1.1.36 onscreen 40.26 0.00 40.27 0.05 From owner-freebsd-hardware Mon Sep 16 22:26:45 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id WAA09627 for hardware-outgoing; Mon, 16 Sep 1996 22:26:45 -0700 (PDT) Received: from genesis.atrad.adelaide.edu.au (genesis.atrad.adelaide.edu.au [129.127.96.120]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id WAA09618 for ; Mon, 16 Sep 1996 22:26:35 -0700 (PDT) Received: from msmith@localhost by genesis.atrad.adelaide.edu.au (8.6.12/8.6.9) id OAA29451; Tue, 17 Sep 1996 14:55:25 +0930 From: Michael Smith Message-Id: <199609170525.OAA29451@genesis.atrad.adelaide.edu.au> Subject: Re: RAM timings for Triton chipsets? To: michaelv@MindBender.serv.net (Michael L. VanLoon -- HeadCandy.com) Date: Tue, 17 Sep 1996 14:55:24 +0930 (CST) Cc: msmith@atrad.adelaide.edu.au, hardware@freebsd.org In-Reply-To: <199609170500.WAA21788@MindBender.serv.net> from "Michael L. VanLoon -- HeadCandy.com" at Sep 16, 96 10:00:41 pm MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Michael L. VanLoon -- HeadCandy.com stands accused of saying: > > x2222 and x4444 mean how many cycles it takes to access memory for > each cycle of a burst read or write. The x means that the first > access is longer (typically something like 6 cycles). After the first > access, it can burst at a word for every 2 bus cycles (or as the case > is now, for ever 4 bus cycles). Hmm. It certainly isn't behaving 'much slower'... What sort of 'much' would you expect from that sort of change? > Michael L. VanLoon michaelv@MindBender.serv.net -- ]] Mike Smith, Software Engineer msmith@atrad.adelaide.edu.au [[ ]] Genesis Software genesis@atrad.adelaide.edu.au [[ ]] High-speed data acquisition and (GSM mobile) 0411-222-496 [[ ]] realtime instrument control (ph/fax) +61-8-267-3039 [[ ]] Collector of old Unix hardware. "Where are your PEZ?" The Tick [[ From owner-freebsd-hardware Mon Sep 16 22:28:57 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id WAA09743 for hardware-outgoing; Mon, 16 Sep 1996 22:28:57 -0700 (PDT) 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 WAA09721 for ; Mon, 16 Sep 1996 22:28:43 -0700 (PDT) Received: from MindBender.serv.net by mx.serv.net (8.7.5/SERV Revision: 2.30) id WAA09885; Mon, 16 Sep 1996 22:28:34 -0700 (PDT) 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 WAA22129; Mon, 16 Sep 1996 22:28:15 -0700 (PDT) Message-Id: <199609170528.WAA22129@MindBender.serv.net> X-Authentication-Warning: MindBender.serv.net: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: Michael Smith cc: hardware@freebsd.org Subject: Re: RAM timings for Triton chipsets? In-reply-to: Your message of Tue, 17 Sep 96 14:55:24 +0930. <199609170525.OAA29451@genesis.atrad.adelaide.edu.au> Date: Mon, 16 Sep 1996 22:28:14 -0700 From: "Michael L. VanLoon -- HeadCandy.com" Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >Michael L. VanLoon -- HeadCandy.com stands accused of saying: >> x2222 and x4444 mean how many cycles it takes to access memory for >> each cycle of a burst read or write. The x means that the first >> access is longer (typically something like 6 cycles). After the first >> access, it can burst at a word for every 2 bus cycles (or as the case >> is now, for ever 4 bus cycles). >Hmm. It certainly isn't behaving 'much slower'... What sort of >'much' would you expect from that sort of change? Small things that fit nicely in your cache probably won't be noticably slower. Stuff that will are big processes that touch a lot of memory. Like piggy GCC doing a large build. Try doing a clean kernel compile with the settings each way and see what you get. ----------------------------------------------------------------------------- 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-hardware Tue Sep 17 01:36:06 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id BAA20788 for hardware-outgoing; Tue, 17 Sep 1996 01:36:06 -0700 (PDT) Received: from genesis.atrad.adelaide.edu.au (genesis.atrad.adelaide.edu.au [129.127.96.120]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id BAA20783 for ; Tue, 17 Sep 1996 01:36:03 -0700 (PDT) Received: from msmith@localhost by genesis.atrad.adelaide.edu.au (8.6.12/8.6.9) id SAA00100; Tue, 17 Sep 1996 18:04:21 +0930 From: Michael Smith Message-Id: <199609170834.SAA00100@genesis.atrad.adelaide.edu.au> Subject: Re: RAM timings for Triton chipsets? To: michaelv@MindBender.serv.net (Michael L. VanLoon -- HeadCandy.com) Date: Tue, 17 Sep 1996 18:04:21 +0930 (CST) Cc: msmith@atrad.adelaide.edu.au, hardware@freebsd.org In-Reply-To: <199609170528.WAA22129@MindBender.serv.net> from "Michael L. VanLoon -- HeadCandy.com" at Sep 16, 96 10:28:14 pm MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Michael L. VanLoon -- HeadCandy.com stands accused of saying: > > Try doing a clean kernel compile with the settings each way and see > what you get. Moot point; I wasn't willing to take the risk, so it's back to x2222 and working just as well 8) Now I have an 0612-SNAP box that can't build the world to worry about (I think the hardware is rooted 8( ) > Michael L. VanLoon michaelv@MindBender.serv.net -- ]] Mike Smith, Software Engineer msmith@atrad.adelaide.edu.au [[ ]] Genesis Software genesis@atrad.adelaide.edu.au [[ ]] High-speed data acquisition and (GSM mobile) 0411-222-496 [[ ]] realtime instrument control (ph/fax) +61-8-267-3039 [[ ]] Collector of old Unix hardware. "Where are your PEZ?" The Tick [[ From owner-freebsd-hardware Tue Sep 17 04:31:18 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id EAA28331 for hardware-outgoing; Tue, 17 Sep 1996 04:31:18 -0700 (PDT) Received: from diablo.ppp.de (diablo.ppp.de [193.141.101.34]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id EAA28319; Tue, 17 Sep 1996 04:31:12 -0700 (PDT) Received: from allegro.lemis.de by diablo.ppp.de with smtp (Smail3.1.28.1 #1) id m0v2yMs-000QjzC; Tue, 17 Sep 96 13:31 MET DST From: grog@lemis.de (Greg Lehey) Organisation: LEMIS, Schellnhausen 2, 36325 Feldatal, Germany Phone: +49-6637-919123 Fax: +49-6637-919122 Received: (grog@localhost) by allegro.lemis.de (8.6.9/8.6.9) id MAA08085; Tue, 17 Sep 1996 12:42:43 +0200 Message-Id: <199609171042.MAA08085@allegro.lemis.de> Subject: Re: Slow Etherlink To: gpalmer@FreeBSD.org (Gary Palmer) Date: Tue, 17 Sep 1996 12:42:43 +0200 (MET DST) Cc: freebsd-hardware@FreeBSD.org (FreeBSD hardware Users), hackers@FreeBSD.org (FreeBSD Hackers) In-Reply-To: <28202.842917587@orion.webspan.net> from "Gary Palmer" at Sep 16, 96 07:46:27 pm X-Mailer: ELM [version 2.4 PL23] MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Gary Palmer writes: > > Jeffrey Barber wrote in message ID > <01BBA3DF.D5124740@jabpc.rtfm.com>: >> OK, If we can get past all the sarcasim bull shit! > > Perhaps you should phrase your questions better and provide more > relevant information in that case. Complaining about network speed, > and then including results which contradict your problem is BOUND to > get sarcastic responses! I agree that the original poster gave no useful information and made a claim that would raise many FreeBSD users' hackles even if it were proven true, but all this correspondence hasn't done much to identify whether there is a performance problem. Let's summarize: 1. Ping localhost is a nice way to show the length of some of the internal paths through the kernel. Jeffrey seemed to confuse it with Ethernet. 2. The numbers he gave were irrelevant anyway. 3. He claims there are performance problems with telnet and ping. How about ftp? That's usually the clearest indication of ethernet throughput. 4. Gary thinks it might be due to the driver. Possibly that depends on the release, but just by chance I did some tests on Sunday, after installing Slowaris on my Sparc 2. *Those* results are interesting. Here are my results. They weren't really designed to show anything on FreeBSD, and since I only have one FreeBSD box up and running at the moment, they're only an indication. I ftp'd a 9 MB file (kernel with debugging symbols, FWIW) between 3 boxes: a P133 running FreeBSD 2.2-current, a P133 running BSD/OS 2.1, and the SparcStation 2 running SunOS 4.1.3 and Solaris 2.5. Here the results: copy to -> /dev/null /tmp/junk FreeBSD - SunOS 4 1020 kb/s 1020 kb/s FreeBSD - BSD/OS 1030 kb/s 930 kb/s FreeBSD - Solaris 2.5 462 kb/s 462 kb/s I wouldn't complain about the throughput of any of the BSD systems, though it's interesting how badly BSD/OS fared with a copy to a file. This was also the only result which varied significantly (between 835 and 960 kb/s) and may be related to the fact that this machine was also running X and the console on which I did the tests. The real surprise is Solaris 2.5. The SS2 only has 16 MB of memory, but all it was doing was receiving the file, so you'd think it could handle things better than that. Does anybody have any ideas? From owner-freebsd-hardware Tue Sep 17 04:41:12 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id EAA28887 for hardware-outgoing; Tue, 17 Sep 1996 04:41:12 -0700 (PDT) Received: from critter.tfs.com ([140.145.230.252]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id EAA28866; Tue, 17 Sep 1996 04:41:06 -0700 (PDT) Received: from critter.tfs.com (localhost.tfs.com [127.0.0.1]) by critter.tfs.com (8.7.5/8.7.3) with ESMTP id NAA01102; Tue, 17 Sep 1996 13:40:35 +0200 (MET DST) To: grog@lemis.de (Greg Lehey) cc: gpalmer@FreeBSD.org (Gary Palmer), freebsd-hardware@FreeBSD.org (FreeBSD hardware Users), hackers@FreeBSD.org (FreeBSD Hackers) Subject: Re: Slow Etherlink In-reply-to: Your message of "Tue, 17 Sep 1996 12:42:43 +0200." <199609171042.MAA08085@allegro.lemis.de> Date: Tue, 17 Sep 1996 13:40:35 +0200 Message-ID: <1100.842960435@critter.tfs.com> From: Poul-Henning Kamp Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk In message <199609171042.MAA08085@allegro.lemis.de>, Greg Lehey writes: >I ftp'd a 9 MB file (kernel with >debugging symbols, FWIW) between 3 boxes: a P133 running FreeBSD >2.2-current, a P133 running BSD/OS 2.1, and the SparcStation 2 running >SunOS 4.1.3 and Solaris 2.5. Here the results: > > copy to -> /dev/null /tmp/junk > >FreeBSD - SunOS 4 1020 kb/s 1020 kb/s >FreeBSD - BSD/OS 1030 kb/s 930 kb/s >FreeBSD - Solaris 2.5 462 kb/s 462 kb/s > >The real surprise is Solaris 2.5. The SS2 only has 16 MB of memory, >but all it was doing was receiving the file, so you'd think it could >handle things better than that. Does anybody have any ideas? You should try a ss1000 then :-) Luckily it >can< be used as a boat-anchor. -- 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-hardware Tue Sep 17 06:27:24 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id GAA05866 for hardware-outgoing; Tue, 17 Sep 1996 06:27:24 -0700 (PDT) Received: from gallup.cia-g.com (root@gallup.cia-g.com [206.206.162.10]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id GAA05858 for ; Tue, 17 Sep 1996 06:27:22 -0700 (PDT) Received: from gallup.cia-g.com (lithium@gallup.cia-g.com [206.206.162.10]) by gallup.cia-g.com (8.7.5/8.6.12) with SMTP id HAA19329; Tue, 17 Sep 1996 07:26:51 -0600 (MDT) Date: Tue, 17 Sep 1996 07:26:51 -0600 (MDT) From: Stephen Fisher To: Michael Smith cc: "Michael L. VanLoon -- HeadCandy.com" , hardware@freebsd.org Subject: Re: RAM timings for Triton chipsets? In-Reply-To: <199609170834.SAA00100@genesis.atrad.adelaide.edu.au> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Here is an excellent hardware information guide I found: http://www.u-net.com/sysdoc/guide.html It has descriptions of timings and what they mean. On Tue, 17 Sep 1996, Michael Smith wrote: > Michael L. VanLoon -- HeadCandy.com stands accused of saying: > > > > Try doing a clean kernel compile with the settings each way and see > > what you get. > > Moot point; I wasn't willing to take the risk, so it's back to x2222 and > working just as well 8) > > Now I have an 0612-SNAP box that can't build the world to worry about > (I think the hardware is rooted 8( ) From owner-freebsd-hardware Tue Sep 17 08:39:42 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA17976 for hardware-outgoing; Tue, 17 Sep 1996 08:39:42 -0700 (PDT) Received: from rock.rtfm.com (guest@rock.anchorage.net [204.17.241.163]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id IAA17946; Tue, 17 Sep 1996 08:39:31 -0700 (PDT) Received: from jabpc.rtfm.com (jabpc.rtfm.com [199.237.0.200]) by rock.rtfm.com (8.6.12/8.6.9) with SMTP id HAA03125; Tue, 17 Sep 1996 07:34:23 -0300 Received: by jabpc.rtfm.com with Microsoft Mail id <01BBA46B.C28E9240@jabpc.rtfm.com>; Tue, 17 Sep 1996 07:42:21 -0800 Message-ID: <01BBA46B.C28E9240@jabpc.rtfm.com> From: Jeffrey Barber To: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Very Slow Ethernet Link (FreeBSD v. Linux) Date: Tue, 17 Sep 1996 07:40:28 -0800 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Thanks for all the responses but still no luck. I had to put linux on = the system instead. But I did run a ftp test comparing FreeBSD to Linux. = The results: Using FreeBSD 2.1.0: ftp transfer with freebsd 1927427 bytes @ 4.2e+02 seconds 4.4kb/s Removing FreeBSD and Installed Linux 2.0 ftp transfer with Linux 1927427 bytes @ 3.05 seconds (6.2e+02 kb/s) = Wooo Wooo :) Using the exact same configuration and computer, the reults are in the = Linux favor by far. Don't know what the problem was. Thanks again. From owner-freebsd-hardware Tue Sep 17 09:35:45 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA21347 for hardware-outgoing; Tue, 17 Sep 1996 09:35:45 -0700 (PDT) Received: from silver.sms.fi (root@silver.sms.fi [194.111.122.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA21341; Tue, 17 Sep 1996 09:35:39 -0700 (PDT) Received: (from pete@localhost) by silver.sms.fi (8.7.5/8.6.9) id TAA14831; Tue, 17 Sep 1996 19:35:17 +0300 (EET DST) Date: Tue, 17 Sep 1996 19:35:17 +0300 (EET DST) Message-Id: <199609171635.TAA14831@silver.sms.fi> From: Petri Helenius To: Jeffrey Barber Cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Very Slow Ethernet Link (FreeBSD v. Linux) In-Reply-To: <01BBA46B.C28E9240@jabpc.rtfm.com> References: <01BBA46B.C28E9240@jabpc.rtfm.com> Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Jeffrey Barber writes: > Thanks for all the responses but still no luck. I had to put linux on the system instead. But I did run a ftp test comparing FreeBSD to Linux. The results: > > Using FreeBSD 2.1.0: > > ftp transfer with freebsd 1927427 bytes @ 4.2e+02 seconds 4.4kb/s > > Removing FreeBSD and Installed Linux 2.0 > > ftp transfer with Linux 1927427 bytes @ 3.05 seconds (6.2e+02 kb/s) Wooo Wooo :) > > Using the exact same configuration and computer, the reults are in the Linux favor by far. > Don't know what the problem was. > You did a ftp to the loopback-address? This is a known problem with the MTU if you did. Set the MTU to 1500 or something more reasonable. Pete From owner-freebsd-hardware Tue Sep 17 10:22:38 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA23512 for hardware-outgoing; Tue, 17 Sep 1996 10:22:38 -0700 (PDT) Received: from phaeton.artisoft.com (phaeton.Artisoft.COM [198.17.250.211]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id KAA23493; Tue, 17 Sep 1996 10:22:33 -0700 (PDT) Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id KAA04369; Tue, 17 Sep 1996 10:21:18 -0700 From: Terry Lambert Message-Id: <199609171721.KAA04369@phaeton.artisoft.com> Subject: Re: Slow Etherlink To: craigs@os.com (Craig Shrimpton) Date: Tue, 17 Sep 1996 10:21:17 -0700 (MST) Cc: terry@lambert.org, jab@rock.anchorage.net, freebsd-hardware@FreeBSD.ORG, hackers@FreeBSD.ORG In-Reply-To: from "Craig Shrimpton" at Sep 16, 96 11:33:07 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-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > > It means it can't transmit and receive at the same time. This is a card > > "feature", and if you haven't seen it before, your other OS has been > > lying to you (or it's one of the drivers that needs updated). > > > > In general, SIMPLEX, if capable of being fixed via a driver interface > > (usually it is not, as noted above), will only affect unidirectional > > throughput, generally out of the machine, and generally only for real > > data transferred (ie: it's not your "ping" problem, whatever your "ping" > > > > > What cards are "synchronous?" I use SMC EtherPower PCI cards (de0) > because they are basically plug and play under FreeBSD. I put 3 in a > FBSD router box and they all worked first try automagically! > > Any idea if the SMC drivers are updateable? The drivers are *always* updtatable. However, if the card simply does not have enough memory on board to hold both an inbound and an outbound buffer simultaneously, it *must* remain "simplex" no matter who writes the driver or how well. Just because other OS's don't report the fact doesn't make it any less a fact. 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-hardware Tue Sep 17 10:54:40 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA25219 for hardware-outgoing; Tue, 17 Sep 1996 10:54:40 -0700 (PDT) Received: from zwei.siemens.at (zwei.siemens.at [193.81.246.12]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA25190; Tue, 17 Sep 1996 10:54:34 -0700 (PDT) Received: from sol1.gud.siemens.co.at (root@[10.1.143.100]) by zwei.siemens.at (8.7.5/8.7.3) with SMTP id TAA21102; Tue, 17 Sep 1996 19:53:26 +0200 (MET DST) Received: from ws2301.gud.siemens.co.at by sol1.gud.siemens.co.at with smtp (Smail3.1.28.1 #7 for ) id m0v34LQ-000218C; Tue, 17 Sep 96 19:54 MET DST Received: by ws2301.gud.siemens.co.at (1.37.109.16/1.37) id AA133682555; Tue, 17 Sep 1996 19:49:15 +0200 From: "Hr.Ladavac" Message-Id: <199609171749.AA133682555@ws2301.gud.siemens.co.at> Subject: Re: Very Slow Ethernet Link (FreeBSD v. Linux) To: jab@rock.anchorage.net (Jeffrey Barber) Date: Tue, 17 Sep 1996 19:49:15 +0200 (MESZ) Cc: freebsd-hardware@FreeBSD.ORG, hackers@FreeBSD.ORG In-Reply-To: <01BBA46B.C28E9240@jabpc.rtfm.com> from "Jeffrey Barber" at Sep 17, 96 07:40:28 am X-Mailer: ELM [version 2.4 PL24 ME8a] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk E-mail message from Jeffrey Barber contained: > Thanks for all the responses but still no luck. I had to put linux on the system instead. But I did run a ftp test comparing FreeBSD to Linux. The results: > > Using FreeBSD 2.1.0: > > ftp transfer with freebsd 1927427 bytes @ 4.2e+02 seconds 4.4kb/s > > Removing FreeBSD and Installed Linux 2.0 > > ftp transfer with Linux 1927427 bytes @ 3.05 seconds (6.2e+02 kb/s) Wooo Wooo :) > > Using the exact same configuration and computer, the reults are in the Linux favor by far. > Don't know what the problem was. This is usually symptomatic for a misconfigured 3com509 where the kernel does not receive the interrupts (and then it times out and sends a packet per second.) Under FreeBSD these cards have been known to achieve >1000 KB/s, *iff* correctly configured (i.e. PnP turned off, interrupts on the channel where the kernel expects them, no irq conflicts, that sort of things.) /Marino > > Thanks again. > > From owner-freebsd-hardware Tue Sep 17 11:33:58 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA04279 for hardware-outgoing; Tue, 17 Sep 1996 11:33:58 -0700 (PDT) Received: from home.winc.com (root@home.winc.com [204.178.182.2]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id LAA04274 for ; Tue, 17 Sep 1996 11:33:54 -0700 (PDT) Received: from phoenix.aristar.com (slip125.winc.com [204.178.182.125]) by home.winc.com (8.7.1/8.7.3) with SMTP id OAA28601; Tue, 17 Sep 1996 14:33:31 -0400 Message-ID: <323EEF3D.167EB0E7@aristar.com> Date: Tue, 17 Sep 1996 14:34:37 -0400 From: "Matthew A. Gessner" Organization: Aristar, Inc. X-Mailer: Mozilla 3.0b8Gold (X11; I; FreeBSD 2.1.0-RELEASE i386) MIME-Version: 1.0 To: FreeBSD Hardware group Subject: ppp/pap Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hello, all, My ISP is telling me I need to use ppp with PAP authorization. Unfortunately, the man page for ppp covers this only in passing and doesn't say what other parts of ppp.conf I will need. Can someone please help me out with this? TIA, -- Matthew Gessner, Computer Scientist, Aristar, Inc. 302 N. Cleveland-Massillon Rd. Akron, OH 44333 Voice (330) 668-2267, Fax (330) 668-2961 From owner-freebsd-hardware Tue Sep 17 11:38:34 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA04586 for hardware-outgoing; Tue, 17 Sep 1996 11:38:34 -0700 (PDT) Received: from home.winc.com (root@home.winc.com [204.178.182.2]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id LAA04581 for ; Tue, 17 Sep 1996 11:38:32 -0700 (PDT) Received: from phoenix.aristar.com (slip125.winc.com [204.178.182.125]) by home.winc.com (8.7.1/8.7.3) with SMTP id OAA28634; Tue, 17 Sep 1996 14:38:27 -0400 Message-ID: <323EF066.2781E494@aristar.com> Date: Tue, 17 Sep 1996 14:39:34 -0400 From: "Matthew A. Gessner" Organization: Aristar, Inc. X-Mailer: Mozilla 3.0b8Gold (X11; I; FreeBSD 2.1.0-RELEASE i386) MIME-Version: 1.0 To: freebsd-hardware@freebsd.org Subject: Weird messages on boot-up Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, all, I'm getting two new strange messages on bootup. Can anyone give me a little insight into these? Sep 17 14:21:50 phoenix /kernel: arp_rtrequest: bad gateway value Sep 17 14:21:50 phoenix /kernel: rtinit: wrong ifa (0xf072c780) was (0xf072c380) I've recently changed /etc/sysconfig: I removed the -q30m flag from sendmail config, and I was added tun0 to test it but I've since commented it back out. TIA -- Matthew Gessner, Computer Scientist, Aristar, Inc. 302 N. Cleveland-Massillon Rd. Akron, OH 44333 Voice (330) 668-2267, Fax (330) 668-2961 From owner-freebsd-hardware Tue Sep 17 11:51:21 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA05465 for hardware-outgoing; Tue, 17 Sep 1996 11:51:21 -0700 (PDT) Received: from rah.star-gate.com (rah.star-gate.com [204.188.121.18]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id LAA05446; Tue, 17 Sep 1996 11:51:16 -0700 (PDT) Received: from rah.star-gate.com (localhost.star-gate.com [127.0.0.1]) by rah.star-gate.com (8.7.5/8.7.3) with ESMTP id LAA07005; Tue, 17 Sep 1996 11:50:37 -0700 (PDT) Message-Id: <199609171850.LAA07005@rah.star-gate.com> X-Mailer: exmh version 1.6.9 8/22/96 To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Re: Very Slow Ethernet Link (FreeBSD v. Linux) In-reply-to: Your message of "Tue, 17 Sep 1996 07:40:28 -0800." <01BBA46B.C28E9240@jabpc.rtfm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 17 Sep 1996 11:50:37 -0700 From: Amancio Hasty Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk >From The Desk Of Jeffrey Barber : > Thanks for all the responses but still no luck. I had to put linux on = > the system instead. But I did run a ftp test comparing FreeBSD to Linux. = > The results:> > Using FreeBSD 2.1.0: > > ftp transfer with freebsd 1927427 bytes @ 4.2e+02 seconds 4.4kb/s > > Removing FreeBSD and Installed Linux 2.0 > > ftp transfer with Linux 1927427 bytes @ 3.05 seconds (6.2e+02 kb/s) = > Wooo Wooo :) > > Using the exact same configuration and computer, the reults are in the = > Linux favor by far. > Don't know what the problem was. > > Thanks again. > > Not welcome... Really, a couple of invididuals have requested your hardware configuration and your kernel configuration. Additionally, it was pointed out that FreeBSD-2.1.0's 3c509 driver was buggy so why are you posting ?? I would have tried a different ethernet card or upgraded the driver or would have indicated an attempt to verify the settings on the 3c509 and ensure that the kernel has the apropiate settings. Go ahead Jeffrey smile , as someone stated they have seen 1000kb/sec on a 3c509 which means that you are at least 1/3 slower than on a properly configured FreeBSD. The only remaining question now is on which CPU or darn we don't know your hardware configuration. So in summary it looks to me like : Jeffrey still has "Very Slow Ethernet" 8) Amancio From owner-freebsd-hardware Tue Sep 17 12:39:18 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA08751 for hardware-outgoing; Tue, 17 Sep 1996 12:39:18 -0700 (PDT) Received: (from jmb@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA08743; Tue, 17 Sep 1996 12:39:16 -0700 (PDT) From: "Jonathan M. Bresler" Message-Id: <199609171939.MAA08743@freefall.freebsd.org> Subject: Re: Very Slow Ethernet Link (FreeBSD v. Linux) To: jab@rock.anchorage.net (Jeffrey Barber) Date: Tue, 17 Sep 1996 12:39:16 -0700 (PDT) Cc: freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: <01BBA46B.C28E9240@jabpc.rtfm.com> from "Jeffrey Barber" at Sep 17, 96 07:40:28 am X-Mailer: ELM [version 2.4 PL24] Content-Type: text Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Jeffrey Barber wrote: > > Thanks for all the responses but still no luck. I had to put linux on = > the system instead. But I did run a ftp test comparing FreeBSD to Linux. = Jeff, you have to provide us some information about your system in order for us to help you. if you do not provide information on your system, we must conclude that you are not interested in trying to solve your configuration problem. we routinely get 2.5MB/s (thats bytes, not bits) thru a 100BaseT ethernet connection from wcarchive.cdrom.com to a core router on the internet. jmb -- Jonathan M. Bresler FreeBSD Postmaster jmb@FreeBSD.ORG FreeBSD--4.4BSD Unix for PC clones, source included. http://www.freebsd.org/ PGP 2.6.2 Fingerprint: 31 57 41 56 06 C1 40 13 C5 1C E3 E5 DC 62 0E FB From owner-freebsd-hardware Tue Sep 17 13:08:46 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA11127 for hardware-outgoing; Tue, 17 Sep 1996 13:08:46 -0700 (PDT) Received: from dyson.iquest.net (dyson.iquest.net [198.70.144.127]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id NAA11112; Tue, 17 Sep 1996 13:08:39 -0700 (PDT) Received: (from root@localhost) by dyson.iquest.net (8.7.5/8.6.9) id PAA03119; Tue, 17 Sep 1996 15:08:18 -0500 (EST) From: John Dyson Message-Id: <199609172008.PAA03119@dyson.iquest.net> Subject: Re: Very Slow Ethernet Link (FreeBSD v. Linux) To: jmb@freefall.freebsd.org (Jonathan M. Bresler) Date: Tue, 17 Sep 1996 15:08:18 -0500 (EST) Cc: jab@rock.anchorage.net, freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: <199609171939.MAA08743@freefall.freebsd.org> from "Jonathan M. Bresler" at Sep 17, 96 12:39:16 pm Reply-To: dyson@FreeBSD.org X-Mailer: ELM [version 2.4 PL24 ME8] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > > Jeffrey Barber wrote: > > > > Thanks for all the responses but still no luck. I had to put linux on = > > the system instead. But I did run a ftp test comparing FreeBSD to Linux. = > > Jeff, you have to provide us some information about your system > in order for us to help you. > > if you do not provide information on your system, we must conclude > that you are not interested in trying to solve your configuration > problem. > > we routinely get 2.5MB/s (thats bytes, not bits) thru a 100BaseT > ethernet connection from wcarchive.cdrom.com to a core router > on the internet. BTW, that perf is on a machine doing LOTS of ftp's under signficant load. That is certainly not a static test of a single ftp (that being a very degenerate and simple test.) John From owner-freebsd-hardware Tue Sep 17 14:18:47 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA15063 for hardware-outgoing; Tue, 17 Sep 1996 14:18:47 -0700 (PDT) Received: from gargoyle.bazzle.com ([206.103.246.190]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id OAA15037; Tue, 17 Sep 1996 14:18:38 -0700 (PDT) Received: from gargoyle.bazzle.com (localhost [127.0.0.1]) by gargoyle.bazzle.com (8.7.5/8.6.12) with SMTP id RAA15582; Tue, 17 Sep 1996 17:17:16 -0400 (EDT) Date: Tue, 17 Sep 1996 17:17:15 -0400 (EDT) From: "Eric J. Chet" To: Jeffrey Barber cc: "'freebsd-hardware@FreeBSD.org'" , "'hackers@FreeBSD.ORG'" Subject: Re: Very Slow Ethernet Link In-Reply-To: <01BBA3A2.11B93340@jabpc.rtfm.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hello Take a look at your numbers again, I see them a FreeBSD being 3x faster than Linux on a localhost ping. Eric J. Chet - ejc@bazzle.com On Mon, 16 Sep 1996, Jeffrey Barber wrote: > Ok, I just installed FreeBSD 2.1 and boy this is slow, Example: > > bash$ ping localhost > > PING localhost (127.0.0.1): 56 data bytes > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=255 time=0.356 ms > > 64 bytes from 127.0.0.1: icmp_seq=0 ttl=64 time=1.1 ms From owner-freebsd-hardware Tue Sep 17 14:39:21 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA16004 for hardware-outgoing; Tue, 17 Sep 1996 14:39:21 -0700 (PDT) Received: from who.cdrom.com (who.cdrom.com [204.216.27.3]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id OAA15999 for ; Tue, 17 Sep 1996 14:39:19 -0700 (PDT) Received: from persprog.com (persprog.com [204.215.255.203]) by who.cdrom.com (8.7.5/8.6.11) with ESMTP id OAA22216 for ; Tue, 17 Sep 1996 14:39:16 -0700 (PDT) Received: by persprog.com (8.7.5/4.10) id QAA23580; Tue, 17 Sep 1996 16:22:38 -0500 Received: from dasa(192.2.2.199) by cerberus.ppi.com via smap (V1.3) id sma023578; Tue Sep 17 17:22:25 1996 Received: from DASA/SpoolDir by dasa.ppi.com (Mercury 1.21); 17 Sep 96 17:22:31 +0500 Received: from SpoolDir by DASA (Mercury 1.30); 17 Sep 96 17:22:15 +0500 From: "David Alderman" Organization: Personalized Programming, Inc To: freebsd-hardware@FreeBSD.org Date: Tue, 17 Sep 1996 17:22:06 +0500 Subject: Triton I Triton II boot problem Priority: normal X-mailer: Pegasus Mail for Windows (v2.42a) Message-ID: Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk SCO and Adaptec have been less than helpful on this problem so I though I might ask here since the level of hardware knowledge is very high in this group. At work, we were trying to move an Adaptec 2940 w. hard disk from an ASUS Triton I based motherboard to an ASUS P55T2P4 (HX chipset). We are getting the following error messages: > not a directory > > boot not found > Cannot open > Stage 1 boot failure: error loading hd(40)/boot Note that both the controller and hard disk are the same - only the motherboard has changed. DOS > 1 GIG is off on both configurations. An identical drive with SCO loaded from this machine works fine. Any ideas? I suspect it is a geometry problem but why does it change if the adapter BIOS (and setup) is the same. Is this some spawned-in-hell PnP "feature"? Please don't flame me - you know I do not use this OS by choice. I'm FreeBSD friendly 8) Thanks. ====================================== When philosophy conflicts with reality, choose reality. Dave Alderman -- dave@persprog.com ====================================== From owner-freebsd-hardware Tue Sep 17 15:37:46 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id PAA18730 for hardware-outgoing; Tue, 17 Sep 1996 15:37:46 -0700 (PDT) Received: from gargoyle.bazzle.com ([206.103.246.190]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id PAA18722 for ; Tue, 17 Sep 1996 15:37:42 -0700 (PDT) Received: from gargoyle.bazzle.com (localhost [127.0.0.1]) by gargoyle.bazzle.com (8.7.5/8.6.12) with SMTP id SAA16302; Tue, 17 Sep 1996 18:37:34 -0400 (EDT) Date: Tue, 17 Sep 1996 18:37:34 -0400 (EDT) From: "Eric J. Chet" To: Amanda Chou cc: hardware@FreeBSD.org Subject: Re: Dual Pentium motherboards In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Wed, 28 Aug 1996, Amanda Chou wrote: > Hello everyone, > > I got some questions for you FreeBSD experts: =) > > 1. Does FreeBSD support dual Pentium motherboards? > 2. Have anyone tried to install FreeBSD by using any of the motherboards: > o ASUS P55T2P4D > o Tyan S1562 Tomcat I > o Supermicro P55T2S > and if you have, what are your opinions about them? > > Thanks a bunch!! > > Amanda > ------ > achou@best.com > http://www.best.com/~achou/ > Hello I have read good things about the GigaByte GA586DX Dual pentium mainboard on the smp@freebsd.org list. Eric J. Chet - ejc@bazzle.com From owner-freebsd-hardware Tue Sep 17 21:13:09 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id VAA29466 for hardware-outgoing; Tue, 17 Sep 1996 21:13:09 -0700 (PDT) Received: from lserver.infoworld.com (root@lserver.infoworld.com [192.216.48.4]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id VAA29445 for ; Tue, 17 Sep 1996 21:13:06 -0700 (PDT) Received: from ccgate.infoworld.com (ccgate.infoworld.com [192.216.49.101]) by lserver.infoworld.com (8.7.5/8.7.3) with SMTP id VAA02961 for ; Tue, 17 Sep 1996 21:13:03 -0700 (PDT) From: BRETT_GLASS@infoworld.com Received: from ccMail by ccgate.infoworld.com (SMTPLINK V2.11) id AA843019634; Tue, 17 Sep 96 23:00:46 PST Date: Tue, 17 Sep 96 23:00:46 PST Message-Id: <9608178430.AA843019634@ccgate.infoworld.com> To: hardware@freebsd.org Subject: VIA Apollo chipset: Any experience yet? Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Does anyone have experience with VIA's Apollo chipset, which is directly competitive with Intel's Natoma? From owner-freebsd-hardware Tue Sep 17 21:47:17 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id VAA13308 for hardware-outgoing; Tue, 17 Sep 1996 21:47:17 -0700 (PDT) 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 VAA13262 for ; Tue, 17 Sep 1996 21:47:10 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id VAA01722; Tue, 17 Sep 1996 21:47:03 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609180447.VAA01722@GndRsh.aac.dev.com> Subject: Re: VIA Apollo chipset: Any experience yet? In-Reply-To: <9608178430.AA843019634@ccgate.infoworld.com> from "BRETT_GLASS@infoworld.com" at "Sep 17, 96 11:00:46 pm" To: BRETT_GLASS@infoworld.com Date: Tue, 17 Sep 1996 21:47:02 -0700 (PDT) Cc: hardware@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-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > Does anyone have experience with VIA's Apollo chipset, which is directly > competitive with Intel's Natoma? No, but have you found a motherboard using this chipset? I have been wanting to bring it in for evaluation but have not had the time to hunt down a board using it. -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Tue Sep 17 22:51:50 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id WAA11578 for hardware-outgoing; Tue, 17 Sep 1996 22:51:50 -0700 (PDT) Received: from lserver.infoworld.com (root@lserver.infoworld.com [192.216.48.4]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id WAA11200 for ; Tue, 17 Sep 1996 22:51:09 -0700 (PDT) Received: from ccgate.infoworld.com (ccgate.infoworld.com [192.216.49.101]) by lserver.infoworld.com (8.7.5/8.7.3) with SMTP id WAA06491; Tue, 17 Sep 1996 22:50:55 -0700 (PDT) From: BRETT_GLASS@infoworld.com Received: from ccMail by ccgate.infoworld.com (SMTPLINK V2.11) id AA843025677; Tue, 17 Sep 96 23:56:51 PST Date: Tue, 17 Sep 96 23:56:51 PST Message-Id: <9608178430.AA843025677@ccgate.infoworld.com> To: "Rodney W. Grimes" Cc: hardware@freebsd.org Subject: Re: VIA Apollo chipset: Any experience yet? Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >> Does anyone have experience with VIA's Apollo chipset, which is >> directly competitive with Intel's Natoma? > No, but have you found a motherboard using this chipset? I have been > wanting to bring it in for evaluation but have not had the time to hunt > down a board using it. The people to call are FIC. They and VIA are wholly-owned subsidiaries of the same Taiwanese company. --Brett From owner-freebsd-hardware Wed Sep 18 00:01:49 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA18168 for hardware-outgoing; Wed, 18 Sep 1996 00:01:49 -0700 (PDT) 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 AAA18147 for ; Wed, 18 Sep 1996 00:01:45 -0700 (PDT) Received: from MindBender.serv.net by mx.serv.net (8.7.5/SERV Revision: 2.30) id AAA09728; Wed, 18 Sep 1996 00:01:50 -0700 (PDT) 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 AAA27511; Wed, 18 Sep 1996 00:01:32 -0700 (PDT) Message-Id: <199609180701.AAA27511@MindBender.serv.net> X-Authentication-Warning: MindBender.serv.net: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: "Eric J. Chet" cc: Amanda Chou , hardware@freebsd.org Subject: Re: Dual Pentium motherboards In-reply-to: Your message of Tue, 17 Sep 96 18:37:34 -0400. Date: Wed, 18 Sep 1996 00:01:31 -0700 From: "Michael L. VanLoon -- HeadCandy.com" Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >> 1. Does FreeBSD support dual Pentium motherboards? Not by default. There is an experimental SMP project apart from normal FreeBSD development. >> 2. Have anyone tried to install FreeBSD by using any of the motherboards: >> o ASUS P55T2P4D There are tons of people running FreeBSD and NetBSD on all sorts of Asus boards. I'm typing to you from a P55TP4N (the model just before that one). ----------------------------------------------------------------------------- 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-hardware Wed Sep 18 00:15:16 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA24913 for hardware-outgoing; Wed, 18 Sep 1996 00:15:16 -0700 (PDT) Received: from relay.philips.nl (ns.philips.nl [130.144.65.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id AAA24857 for ; Wed, 18 Sep 1996 00:15:10 -0700 (PDT) Received: (from smap@localhost) by relay.philips.nl (8.6.9/8.6.9-950414) id JAA09841 for ; Wed, 18 Sep 1996 09:14:31 +0200 Received: from unknown(192.26.173.32) by ns.philips.nl via smap (V1.3+ESMTP) with ESMTP id sma009613; Wed Sep 18 09:13:10 1996 Received: from aonc01.nym.sc.philips.com (aonc01.nym.sc.philips.com [130.144.70.193]) by smtp.nl.cis.philips.com (8.6.10/8.6.10-0.9z-02May95) with ESMTP id JAA23930 for ; Wed, 18 Sep 1996 09:15:46 +0200 Received: from NLNMG01.nym.sc.philips.com (nlnmg01 [130.144.80.6]) by aonc01.nym.sc.philips.com (8.6.10/8.6.10-1.2a-960822) with ESMTP id JAA06570 for ; Wed, 18 Sep 1996 09:13:17 +0200 Received: from NLNMG01/MAILQUEUE by NLNMG01.nym.sc.philips.com (Mercury 1.21); 18 Sep 96 09:13:20 +0100 Received: from MAILQUEUE by NLNMG01 (Mercury 1.21); 18 Sep 96 09:13:15 +0100 From: "Kees Jan Koster" Organization: Philips Semiconductors Nijmegen To: hardware@freebsd.org Date: Wed, 18 Sep 1996 09:13:08 GMT+0100 Subject: Re: Triton I Triton II boot problem Reply-to: Kees.Koster@nym.sc.philips.com Priority: normal X-mailer: Pegasus Mail v3.22 Message-ID: <271C3813231@NLNMG01.nym.sc.philips.com> Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > Van: "David Alderman" > Organisatie: Personalized Programming, Inc > Aan: freebsd-hardware@FreeBSD.org > Datum verzending: Tue, 17 Sep 1996 17:22:06 +0500 > Onderwerp: Triton I Triton II boot problem > Prioriteit: normal Well... It may not be helpful, but I noticed that when I tried to overclock my cpu, one of the symptoms of a failing clock setting was that the BOIS failed to probe my (onboard) IDE and (53C810) SCSI controller correctly. Putting the cpu back at its specified speed (and proper voltage <:-] ) cured the problem. Also I had to disable all PnP to actually get the BIOS to assign my SCSI card an irq. Not much, but maybe it helps? Groetjes, Kees Jan > SCO and Adaptec have been less than helpful on this problem so I > though I might ask here since the level of hardware knowledge is very > high in this group. > > At work, we were trying to move an Adaptec 2940 w. hard disk from an > ASUS Triton I based motherboard to an ASUS P55T2P4 (HX chipset). We > are getting the following error messages: > > > > not a directory > > > > boot not found > > Cannot open > > Stage 1 boot failure: error loading hd(40)/boot > > Note that both the controller and hard disk are the same - only the > motherboard has changed. DOS > 1 GIG is off on both configurations. > An identical drive with SCO loaded from this machine works fine. > > > Any ideas? I suspect it is a geometry problem but why does it change > if the adapter BIOS (and setup) is the same. Is this some > spawned-in-hell PnP "feature"? > > Please don't flame me - you know I do not use this OS by choice. > I'm FreeBSD friendly 8) > > Thanks. > ====================================== > When philosophy conflicts with reality, choose reality. > Dave Alderman -- dave@persprog.com > ====================================== > From owner-freebsd-hardware Wed Sep 18 00:56:34 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA19945 for hardware-outgoing; Wed, 18 Sep 1996 00:56:34 -0700 (PDT) Received: from sdev.blaze.net.au (sdev.blaze.net.au [203.17.53.11]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id AAA19206; Wed, 18 Sep 1996 00:55:01 -0700 (PDT) Received: from localhost (davidn@localhost) by sdev.blaze.net.au (8.7.5/8.6.9) with SMTP id RAA05069; Wed, 18 Sep 1996 17:48:57 GMT Date: Wed, 18 Sep 1996 17:48:55 +0000 () From: David Nugent To: Bruce Evans cc: craigs@os.com, jab@rock.anchorage.net, freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org Subject: Re: Slow Etherlink In-Reply-To: <199609170456.OAA10729@godzilla.zeta.org.au> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk On Tue, 17 Sep 1996, Bruce Evans wrote: >>One thing I will say about Linux is that it has superior screen display >>performance. So, if what you are complaining about is screen redraw >>speed, Linux is much faster than FreeBSD. > >Really? Linux was 6-12 times slower last time I worked on speeding up >syscons. I can only agree to this. I recently switched from RedHat Linux (running kernel 2.0.10) to FreeBSD on exactly the same hardware, and without having benchmarks at all I'd rate syscons quite noticably faster than Linux's console. When the scree scrolls, for example, I often missed screens of output in the blink of an eye (I'd rarely even see them scroll by!), whereas on Linux I'd have the opportunity to hit ^S to stop the display. Well, at least I learned to use more, more (and more - sic! :-)). One problem I do have with the syscons driver, however, is the cursor. I'm not one who things much of the blocky cursor, especially since porting Crisp as an editor with it's neat ability to change the cursor size over virtual/real spaces - it needs to have the hardware cursor enabled (e.g. vidcontrol -c destructive) so the cursor size can change. The problem is, the screen updates are affected by enabling that, such that when typing at the shell prompt, you often don't see characters that are typed until you hit enter. Is this a known problem? I'm running 2.2-CURRENT if that is relevent, although I noticed the same when I ran 2.1.5-RELEASE as well. Right now I just have the editor enable the destructive cursor while editing, and switch it back off when exiting via the appropriate ANSI sequences. Unfortunately, while that's fine while within that vt (Crisp itself seems unaffected by this 'bug' - it seems only to happen with cooked stdio enabled, or maybe if termios echo enabled since it occurs with tcsh as well; I haven't really experimented all that much) - but the destructive cursor is system wide, so switching to another vt while editing brings the destructive cursor with it. David Nugent, Unique Computing Pty Ltd - Melbourne, Australia Voice +61-3-791-9547 Data/BBS +61-3-792-3507 3:632/348@fidonet davidn@blaze.net.au http://www.blaze.net.au/~davidn From owner-freebsd-hardware Wed Sep 18 01:36:28 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id BAA06307 for hardware-outgoing; Wed, 18 Sep 1996 01:36:28 -0700 (PDT) Received: from ra.dkuug.dk (ra.dkuug.dk [193.88.44.193]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id BAA06221; Wed, 18 Sep 1996 01:36:12 -0700 (PDT) Received: (from sos@localhost) by ra.dkuug.dk (8.6.12/8.6.12) id KAA13230; Wed, 18 Sep 1996 10:33:03 +0200 Message-Id: <199609180833.KAA13230@ra.dkuug.dk> Subject: Re: Slow Etherlink To: davidn@sdev.blaze.net.au (David Nugent) Date: Wed, 18 Sep 1996 10:33:02 +0200 (MET DST) Cc: bde@zeta.org.au, craigs@os.com, jab@rock.anchorage.net, freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: from "David Nugent" at Sep 18, 96 05:48:55 pm From: sos@FreeBSD.org Reply-to: sos@FreeBSD.org X-Mailer: ELM [version 2.4 PL24] Content-Type: text Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk In reply to David Nugent who wrote: > > On Tue, 17 Sep 1996, Bruce Evans wrote: > > >>One thing I will say about Linux is that it has superior screen display > >>performance. So, if what you are complaining about is screen redraw > >>speed, Linux is much faster than FreeBSD. > > > >Really? Linux was 6-12 times slower last time I worked on speeding up > >syscons. Syscons is nearly as fast as the PC architecture allows for :) It uses a totally different method of updating the screen than all the other console driver in the "free" world (minix excluded) > One problem I do have with the syscons driver, however, is the > cursor. I'm not one who things much of the blocky cursor, especially > since porting Crisp as an editor with it's neat ability to change > the cursor size over virtual/real spaces - it needs to have the > hardware cursor enabled (e.g. vidcontrol -c destructive) so the > cursor size can change. The problem is, the screen updates are > affected by enabling that, such that when typing at the shell > prompt, you often don't see characters that are typed until you > hit enter. > > Is this a known problem? I'm running 2.2-CURRENT if that is Yes, it is, and it is on my TODO list... -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- Soren Schmidt (sos@FreeBSD.org) FreeBSD Core Team So much code to hack -- so little time. From owner-freebsd-hardware Wed Sep 18 02:01:09 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id CAA15081 for hardware-outgoing; Wed, 18 Sep 1996 02:01:09 -0700 (PDT) Received: from sovcom.kiae.su (sovcom.kiae.su [193.125.152.1]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id CAA14856; Wed, 18 Sep 1996 02:00:36 -0700 (PDT) Received: by sovcom.kiae.su id AA08329 (5.65.kiae-1 ); Wed, 18 Sep 1996 11:55:17 +0300 Received: by sovcom.KIAE.su (UUMAIL/2.0); Wed, 18 Sep 96 11:55:17 +0300 Received: (from ache@localhost) by nagual.ru (8.7.5/8.7.3) id MAA00462; Wed, 18 Sep 1996 12:39:45 +0400 (MSD) Message-Id: <199609180839.MAA00462@nagual.ru> Subject: Re: (was Slow Etherlink) Syscons In-Reply-To: from "David Nugent" at "Sep 18, 96 05:48:55 pm" To: davidn@sdev.blaze.net.au (David Nugent) Date: Wed, 18 Sep 1996 12:39:45 +0400 (MSD) Cc: bde@zeta.org.au, craigs@os.com, jab@rock.anchorage.net, freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org, sos@FreeBSD.org (Soren Schmidt) From: =?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?= (Andrey A. Chernov) Organization: self X-Class: Fast 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-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > One problem I do have with the syscons driver, however, is the > cursor. I'm not one who things much of the blocky cursor, especially > since porting Crisp as an editor with it's neat ability to change > the cursor size over virtual/real spaces - it needs to have the > hardware cursor enabled (e.g. vidcontrol -c destructive) so the > cursor size can change. The problem is, the screen updates are > affected by enabling that, such that when typing at the shell > prompt, you often don't see characters that are typed until you > hit enter. > > Is this a known problem? I'm running 2.2-CURRENT if that is > relevent, although I noticed the same when I ran 2.1.5-RELEASE as > well. Right now I just have the editor enable the destructive > cursor while editing, and switch it back off when exiting via the > appropriate ANSI sequences. Unfortunately, while that's fine > while within that vt (Crisp itself seems unaffected by this 'bug' > - it seems only to happen with cooked stdio enabled, or maybe if > termios echo enabled since it occurs with tcsh as well; I > haven't really experimented all that much) - but the destructive > cursor is system wide, so switching to another vt while editing > brings the destructive cursor with it. Yes, it is known bug, I already report Soren about this thing. It was broken about month ago. The next manifistation of this bug is that scrolling not always occurse when answering to 'rm -i' response at the last line, but it is very hard to catch it. -- Andrey A. Chernov http://www.nagual.ru/~ache/ From owner-freebsd-hardware Wed Sep 18 08:49:38 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA21291 for hardware-outgoing; Wed, 18 Sep 1996 08:49:38 -0700 (PDT) Received: from glacier.cold.org (glacier.sunrem.com [206.81.134.54]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id IAA21265 for ; Wed, 18 Sep 1996 08:49:35 -0700 (PDT) Received: (from brandon@localhost) by glacier.cold.org (8.7.5/8.7.3) id JAA07331; Wed, 18 Sep 1996 09:50:31 -0600 (MDT) Date: Wed, 18 Sep 1996 09:50:31 -0600 (MDT) From: Brandon Gillespie To: freebsd-hardware@freebsd.org Subject: RAID solutions? Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk We are looking to put a RAID array onto a server, and were wondering which solution would be the best/most cost effective. We have daily incremental backups, so I doubt the powers that be would be willing to go for a full blown RAID system--so at this time we are likely looking at a card which will do a RAID array through the hardware (preferably Level 5). Has anybody had any experience with this? Any suggestions on which card (and drives) to get? I'm not exploring the hardware (just fishing for helpful hints :), but the guy who is mentioned something about an adaptec RAID card--comments on it? Enjoy; -Brandon Gillespie From owner-freebsd-hardware Wed Sep 18 10:40:18 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA12960 for hardware-outgoing; Wed, 18 Sep 1996 10:40:18 -0700 (PDT) Received: from eldorado.net-tel.co.uk ([193.122.171.253]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id KAA12840 for ; Wed, 18 Sep 1996 10:40:07 -0700 (PDT) From: Andrew.Gordon@net-tel.co.uk Received: (from root@localhost) by eldorado.net-tel.co.uk (8.6.12/8.6.10) id SAA21202; Wed, 18 Sep 1996 18:38:06 +0100 Received: from "/PRMD=NET-TEL/ADMD=GOLD 400/C=GB/" by net-tel.co.uk (Route400-RFCGate); Wed, 18 Sep 96 18:33:10 +0100 X400-Received: by mta "eldorado" in "/PRMD=net-tel/ADMD=gold 400/C=gb/"; Relayed; Wed, 18 Sep 96 18:33:10 +0100 X400-Received: by mta "net-tel cambridge" in "/PRMD=net-tel/ADMD=gold 400/C=gb/"; Relayed; Wed, 18 Sep 96 17:33:07 +0000 X400-Received: by "/PRMD=NET-TEL/ADMD=Gold 400/C=GB/"; Relayed; Wed, 18 Sep 96 17:33:07 +0000 X400-MTS-Identifier: ["/PRMD=NET-TEL/ADMD=Gold 400/C=GB/";hst:8389-960918173307-0B7D] X400-Content-Type: P2-1984 (2) X400-Originator: Andrew.Gordon@net-tel.co.uk Original-Encoded-Information-Types: IA5-Text X400-Recipients: non-disclosure:; Date: Wed, 18 Sep 96 17:33:07 +0000 X400-Content-Identifier: Re: dail back mo Message-Id: <"28729-960918154318-B6B1*/G=Andrew/S=Gordon/O=NET-TEL Computer Systems Ltd/PRMD=NET-TEL/ADMD=Gold 400/C=GB/"@MHS> To: graichen@axp5.physik.fu-berlin.de Cc: hardware@FreeBSD.org In-Reply-To: <199609140727.JAA00994@mordillo> Subject: Re: dail back modems (or dialing back with modems) Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > does anyone here know about hardware dial back modems (you call them and > then > they call directly back to you) - if yes - whats the price for them > compared > to a normal modem ? Among others, the USR Courier supports this. "Compared to a normal modem" depends what you think a normal modem is; compared to a cheapest-possible modem, maybe double the price - but so far as I am concerned my USR Courier is my "normal modem".... HOWEVER, this may not be what you want. Depending on your local phone system, dial-back with a single line/modem may not offer you the security that you hope for. Certainly in the UK "calling party clears" applies to most phone lines - this means that if you make a call and the answering end hangs up, the call remains open and if they pick up again the incoming call is still there. The call is only cleared if the calling party hangs up (or after a timeout). This allows the following exploit with simple dialback systems: Intruder dials in and requests dialback Answering modem hangs up ready to dial back Intruder does not hang up when carrier is lost, so call remains open Answering modem picks up expecting dialtone Intruder simulates dialtone on the still-open call Answering modem dials number, but as call is open it has no effect at all Intruder simulates ringing and answer Call is connected, even though Intruder is not calling from the number dialled back. This makes the "dial back" no more secure than a simple password scheme. Of course, your phone system might not have calling-party-clears, or it might provide polarity reversals that a clever modem can use to detect the difference between a real connect and a fake one, but you require detailed knowledge of both modem and phone system to be sure. The safe way to do dial-back is to use two modems, connected to two phone lines, and dial back on the other line. Round here, we use Caller-ID for secure dial-in, which has the advantage of being much faster as well as (probably) more secure. It is also quite cheap here. In your case, ISDN may be a better bet. From owner-freebsd-hardware Wed Sep 18 10:42:45 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA14523 for hardware-outgoing; Wed, 18 Sep 1996 10:42:45 -0700 (PDT) Received: from Gatekeeper.Lamb.net (ulf@cat-food.Melmac.org [206.169.44.2]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA14490 for ; Wed, 18 Sep 1996 10:42:41 -0700 (PDT) Received: (from ulf@localhost) by Gatekeeper.Lamb.net (8.7.5/8.7.3) id KAA07560; Wed, 18 Sep 1996 10:42:58 -0700 (PDT) From: Ulf Zimmermann Message-Id: <199609181742.KAA07560@Gatekeeper.Lamb.net> Subject: Re: RAID solutions? To: brandon@glacier.cold.org (Brandon Gillespie) Date: Wed, 18 Sep 1996 10:42:57 -0700 (PDT) Cc: freebsd-hardware@FreeBSD.org In-Reply-To: from Brandon Gillespie at "Sep 18, 96 09:50:31 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-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > We are looking to put a RAID array onto a server, and were wondering which > solution would be the best/most cost effective. We have daily incremental > backups, so I doubt the powers that be would be willing to go for a full > blown RAID system--so at this time we are likely looking at a card which > will do a RAID array through the hardware (preferably Level 5). Has > anybody had any experience with this? Any suggestions on which card (and > drives) to get? I'm not exploring the hardware (just fishing for helpful > hints :), but the guy who is mentioned something about an adaptec RAID > card--comments on it? > > Enjoy; > > -Brandon Gillespie > The Adaptec card you talk about is the AHA-3985[W] and Adaptec has not released a handbook for one important chip on that card. I would suggest you look into a SCSI-2-SCSI solution like from CMD or Mylex (and other) Ulf. -------------------------------------------------------------------------- Ulf Zimmermann, 1525 Pacific Ave., Alameda, CA-94501, #: 510-865-0204 Lamb Art Internet Services | http://www.Lamb.net/ | http://www.Alameda.net From owner-freebsd-hardware Wed Sep 18 11:09:11 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA28167 for hardware-outgoing; Wed, 18 Sep 1996 11:09:11 -0700 (PDT) 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 LAA28146 for ; Wed, 18 Sep 1996 11:09:08 -0700 (PDT) Received: from MindBender.serv.net by mx.serv.net (8.7.5/SERV Revision: 2.30) id KAA19690; Wed, 18 Sep 1996 10:59:52 -0700 (PDT) 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 KAA04117; Wed, 18 Sep 1996 10:40:43 -0700 (PDT) Message-Id: <199609181740.KAA04117@MindBender.serv.net> X-Authentication-Warning: MindBender.serv.net: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: Brandon Gillespie cc: freebsd-hardware@freebsd.org Subject: Re: RAID solutions? In-reply-to: Your message of Wed, 18 Sep 96 09:50:31 -0600. Date: Wed, 18 Sep 1996 10:40:16 -0700 From: "Michael L. VanLoon -- HeadCandy.com" Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >We are looking to put a RAID array onto a server, and were wondering which >solution would be the best/most cost effective. We have daily incremental >backups, so I doubt the powers that be would be willing to go for a full >blown RAID system--so at this time we are likely looking at a card which >will do a RAID array through the hardware (preferably Level 5). Has >anybody had any experience with this? Any suggestions on which card (and >drives) to get? I'm not exploring the hardware (just fishing for helpful >hints :), but the guy who is mentioned something about an adaptec RAID >card--comments on it? Your best bet for "RAID" right now would be software RAID, using the ccd. Man ccd and man ccdconfig for more info. As far as I know, FreeBSD (and NetBSD) don't currently support any hardware RAID controllers. A final alternative is to get something that does RAID on the drive side, transparently from the SCSI controller (i. e. uses a regular SCSI controller and hides the fact that it's doing RAID). I don't know who makes these, but people have posted about a couple of them in the past, here. ----------------------------------------------------------------------------- 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-hardware Wed Sep 18 11:56:47 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA23003 for hardware-outgoing; Wed, 18 Sep 1996 11:56:47 -0700 (PDT) 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 LAA22958 for ; Wed, 18 Sep 1996 11:56:41 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id LAA03843; Wed, 18 Sep 1996 11:55:23 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609181855.LAA03843@GndRsh.aac.dev.com> Subject: Re: RAID solutions? In-Reply-To: <199609181742.KAA07560@Gatekeeper.Lamb.net> from Ulf Zimmermann at "Sep 18, 96 10:42:57 am" To: ulf@Lamb.net (Ulf Zimmermann) Date: Wed, 18 Sep 1996 11:55:23 -0700 (PDT) Cc: brandon@glacier.cold.org, freebsd-hardware@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-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > > We are looking to put a RAID array onto a server, and were wondering which > > solution would be the best/most cost effective. We have daily incremental > > backups, so I doubt the powers that be would be willing to go for a full > > blown RAID system--so at this time we are likely looking at a card which > > will do a RAID array through the hardware (preferably Level 5). Has > > anybody had any experience with this? Any suggestions on which card (and > > drives) to get? I'm not exploring the hardware (just fishing for helpful > > hints :), but the guy who is mentioned something about an adaptec RAID > > card--comments on it? > > > > Enjoy; > > > > -Brandon Gillespie > > > > The Adaptec card you talk about is the AHA-3985[W] and Adaptec has not > released a handbook for one important chip on that card. I would suggest > you look into a SCSI-2-SCSI solution like from CMD or Mylex (and other) Or wait 60 to 90 says and get a host based solution from me... -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Wed Sep 18 12:48:34 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA19990 for hardware-outgoing; Wed, 18 Sep 1996 12:48:34 -0700 (PDT) Received: from zit1.zit.th-darmstadt.de (root@zit1.zit.th-darmstadt.de [130.83.63.20]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id MAA19958; Wed, 18 Sep 1996 12:48:31 -0700 (PDT) Received: from localhost (petzi@localhost) by zit1.zit.th-darmstadt.de (8.7.5/8.6.9) with SMTP id VAA14169; Wed, 18 Sep 1996 21:48:00 +0200 (MET DST) Date: Wed, 18 Sep 1996 21:48:00 +0200 (MET DST) From: Michael Beckmann To: "S(pork)" cc: isp@FreeBSD.org, hardware@FreeBSD.org Subject: Re: INN history file and disk I/O In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk Hi there, > We'll be building a new news server here rather soon, and I was wondering > if anyone in on this discussion has any preferences in motherboards and > dealers... Our usual supplier is having some trouble coming up with a > recommendation on a RAM-packed motherboard... I have made very good experiences with the Gigabyte 586 HX mainboard. I have built several machines with it. It has 6 SIMM slots. I have only used it with 32 MB SIMMs so far, and it works very well. According to a test in a very reputable German computer magazine, it performs slightly better than the Asus counterpart, which has only 4 SIMM slots. The test also says that this board is among the few that boot with 64 MB SIMMs installed. If you equip the board with a 16 kbyte Tag RAM it will extend the L2 cacheable area to 512 MB. The cacheable area becomes important when you have that much RAM. Almost all motherboards do not L2 cache more than 64 megabytes. I think that 6 x 64 MB = 384 MB will make a good newsserver :-) With a P 166 or P 200 it outperforms e.g. a SPARC 20 easily. Another option is the Asus Double Pentium board, which has 8 SIMM slots. The second Pentium is not supported by FreeBSD (and you don't need it for a news server), but I would still consider it because of the 8 SIMM slots and the good Asus support and quality. Hope this helps. Don't buy crap. Michael From owner-freebsd-hardware Wed Sep 18 13:49:32 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA17920 for hardware-outgoing; Wed, 18 Sep 1996 13:49:32 -0700 (PDT) Received: from vector.jhs.no_domain (slip139-92-42-167.ut.nl.ibm.net [139.92.42.167]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id NAA17701 for ; Wed, 18 Sep 1996 13:48:59 -0700 (PDT) Received: from vector.jhs.no_domain (localhost [127.0.0.1]) by vector.jhs.no_domain (8.7.5/8.6.9) with ESMTP id BAA18058 for ; Wed, 18 Sep 1996 01:00:33 +0200 (MET DST) Message-Id: <199609172300.BAA18058@vector.jhs.no_domain> To: freebsd-hardware@freebsd.org Subject: Re: Slow Etherlink From: "Julian H. Stacey" Reply-To: "Julian H. Stacey" Organization: Vector Systems Ltd. Mailer: EXMH 1.6.7, PGP available X-Address: Holz Strasse 27d, 80469 Munich, Germany X-Phone: +49.89.268616 X-Fax: +49.89.2608126 X-Web: http://www.freebsd.org/~jhs/ In-reply-to: Your message of "Tue, 17 Sep 1996 12:42:43 +0200." <199609171042.MAA08085@allegro.lemis.de> Date: Wed, 18 Sep 1996 01:00:32 +0200 Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Whoever cross posted the low traffic list: freebsd-hardware@FreeBSD.org with the high traffic list: hackers@FreeBSD.org on the `Ping' thread, Subject: Re: Slow Etherlink managed to swamp the hardware@ list :-( Please don't do that again, Thanks ! Seperate mail lists exist to control traffic, Cross posting defeats that aim. EG I don't subscribe hackers, specifically to avoid the mass response traffic that just hit hardware@ I haven't cross posted this to hackers@, to avoid further flooding hardware@, but I have bcc'd the person I think probably initiated the first post, in case he's not on hardware@. Julian -- Julian H. Stacey jhs@freebsd.org http://www.freebsd.org/~jhs/ From owner-freebsd-hardware Wed Sep 18 14:06:16 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA24106 for hardware-outgoing; Wed, 18 Sep 1996 14:06:16 -0700 (PDT) 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 OAA24059; Wed, 18 Sep 1996 14:06:08 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id OAA04861; Wed, 18 Sep 1996 14:04:27 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609182104.OAA04861@GndRsh.aac.dev.com> Subject: Re: INN history file and disk I/O In-Reply-To: from Michael Beckmann at "Sep 18, 96 09:48:00 pm" To: petzi@zit.th-darmstadt.de (Michael Beckmann) Date: Wed, 18 Sep 1996 14:04:26 -0700 (PDT) Cc: spork@super-g.com, isp@freebsd.org, hardware@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-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > Hi there, > > > We'll be building a new news server here rather soon, and I was wondering > > if anyone in on this discussion has any preferences in motherboards and > > dealers... Our usual supplier is having some trouble coming up with a > > recommendation on a RAM-packed motherboard... > > I have made very good experiences with the Gigabyte 586 HX mainboard. I > have built several machines with it. It has 6 SIMM slots. I have only used Buyer beware, Gigabyte is playing games with the specifications and register usage of the Triton-I and Triton-II chipsets to get away with these 6 SIMM slots. These chip sets have 8 programmable DRAM row size registers, each _SIDE_ of a SIMM requires one of them to be programmed, you can _ONLY_ run 4 double sided simms with these chip sets. Gigabyte dirty little move is to _ONLY_ allow single sided SIMMS in 2 of the sockets, thus the max memory is REALLY 4 * 32MB + 2 * 16MB == 160MB for Triton-I and 64MB * 6 == 384MB for Triton-II (64MB simms are single row simms if they use 64MB technology chips on them). > it with 32 MB SIMMs so far, and it works very well. According to a test in > a very reputable German computer magazine, it performs slightly better > than the Asus counterpart, which has only 4 SIMM slots. The test also says > that this board is among the few that boot with 64 MB SIMMs installed. > If you equip the board with a 16 kbyte Tag RAM it will extend the > L2 cacheable area to 512 MB. The cacheable area becomes important when you It's not 16kbyte of tag you need, it is 11 bit wide tags you need, see the Intel 439HX databooks. ASUS also supports this, but it is a little trickier to do and I am trying to accertain some optional ways of doing it. > have that much RAM. Almost all motherboards do not L2 cache more than 64 > megabytes. I think that 6 x 64 MB = 384 MB will make a good newsserver :-) > With a P 166 or P 200 it outperforms e.g. a SPARC 20 easily. > > Another option is the Asus Double Pentium board, which has 8 SIMM slots. > The second Pentium is not supported by FreeBSD (and you don't need it for > a news server), but I would still consider it because of the 8 SIMM slots > and the good Asus support and quality. My experience with the PCI/E-P55T2P4D is that it won't reliably run more than 6 simms unless they happen to be single sided 12 chip or less simm modules. :-(. > > Hope this helps. Don't buy crap. And as a final note, AAC has disqualified Gigabyte as a MB supplier 4 times. Every time a new board comes out from them my local distributor swears it is the best thing since sliced bread, so I bring in a couple of them for my 2 week eval process... welll... Gigabyte has never made it to my qualified parts list :-( Oh, and of course YMMV... -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Wed Sep 18 14:27:38 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA01516 for hardware-outgoing; Wed, 18 Sep 1996 14:27:38 -0700 (PDT) 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 OAA01483 for ; Wed, 18 Sep 1996 14:27:32 -0700 (PDT) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id PAA00944; Wed, 18 Sep 1996 15:26:58 -0600 Message-Id: <199609182126.PAA00944@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: "Rodney W. Grimes" cc: freebsd-hardware@freebsd.org Subject: Re: RAID solutions? In-reply-to: Your message of "Wed, 18 Sep 1996 11:55:23 PDT." <199609181855.LAA03843@GndRsh.aac.dev.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 18 Sep 1996 15:26:58 -0600 Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, Rod said: > > We are looking to put a RAID array onto a server, and were wondering which > > ... > Or wait 60 to 90 says and get a host based solution from me... are we talking about a hardware/software product you will be selling or a freeBSD driver? -- Steve Passe | powered by smp@csn.net | FreeBSD From owner-freebsd-hardware Wed Sep 18 14:41:14 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA08271 for hardware-outgoing; Wed, 18 Sep 1996 14:41:14 -0700 (PDT) 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 OAA08183 for ; Wed, 18 Sep 1996 14:41:03 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id OAA04943; Wed, 18 Sep 1996 14:40:26 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609182140.OAA04943@GndRsh.aac.dev.com> Subject: Re: RAID solutions? In-Reply-To: <199609182126.PAA00944@clem.systemsix.com> from Steve Passe at "Sep 18, 96 03:26:58 pm" To: smp@csn.net (Steve Passe) Date: Wed, 18 Sep 1996 14:40:26 -0700 (PDT) Cc: freebsd-hardware@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-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > Hi, > > Rod said: > > > We are looking to put a RAID array onto a server, and were wondering which > > > ... > > Or wait 60 to 90 says and get a host based solution from me... > > are we talking about a hardware/software product you will be selling > or a freeBSD driver? A FreeBSD driver that will be imported into the sources that supports several cards from a major manufacture of host RAID controllers. This will be hardware RAID support. -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Wed Sep 18 14:59:38 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA16724 for hardware-outgoing; Wed, 18 Sep 1996 14:59:38 -0700 (PDT) Received: from lserver.infoworld.com (root@lserver.infoworld.com [192.216.48.4]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id OAA16701 for ; Wed, 18 Sep 1996 14:59:35 -0700 (PDT) Received: from ccgate.infoworld.com (ccgate.infoworld.com [192.216.49.101]) by lserver.infoworld.com (8.7.5/8.7.3) with SMTP id OAA23982 for ; Wed, 18 Sep 1996 14:59:31 -0700 (PDT) From: BRETT_GLASS@infoworld.com Received: from ccMail by ccgate.infoworld.com (SMTPLINK V2.11) id AA843083789; Wed, 18 Sep 96 16:29:40 PST Date: Wed, 18 Sep 96 16:29:40 PST Message-Id: <9608188430.AA843083789@ccgate.infoworld.com> To: hardware@freebsd.org Subject: More or fewer IRQs? Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I'm setting up a FreeBSD system with a buncha serial ports, and the cards will allow me to share IRQs between ports. There are 5 available IRQs and 10 ports; in other words, there aren't enough IRQs to allow every port to have one of its own, so some sharing is necessary. With the hardware I have here, I have two choices. I can use up every IRQ in the machine and put two UARTS on each, or I can lump more together (there are three ISA cards, so that means I could get away with using 3 out of the 5). The latter approach has the advantage that I can add another peripheral in the remaining vacant PCI slot and would have an IRQ for it. But which would yield better performance? It seems to me that the high overhead of taking an interrupt MIGHT make it better to put many ports on one IRQ, since polling each port on the card probably still costs less than a context switch on an Intel CPU (a truly ugly process ;-). On the other hand, the source code suggests that the driver turns off interrupts as it services serial ports, so there MIGHT be a chance of starving otner devices (in particular, the system's cantankerous IDE interface) if there were many UARTs on an IRQ. What say ye? --Brett From owner-freebsd-hardware Wed Sep 18 16:48:14 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id QAA07145 for hardware-outgoing; Wed, 18 Sep 1996 16:48:14 -0700 (PDT) Received: from mail.crl.com (mail.crl.com [165.113.1.22]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id QAA07125 for ; Wed, 18 Sep 1996 16:48:11 -0700 (PDT) Received: from rocky.mt.sri.com by mail.crl.com with SMTP id AA15174 (5.65c/IDA-1.5 for ); Wed, 18 Sep 1996 16:47:54 -0700 Received: (from nate@localhost) by rocky.mt.sri.com (8.7.5/8.7.3) id RAA15102; Wed, 18 Sep 1996 17:39:19 -0600 (MDT) Date: Wed, 18 Sep 1996 17:39:19 -0600 (MDT) Message-Id: <199609182339.RAA15102@rocky.mt.sri.com> From: Nate Williams To: "Rodney W. Grimes" Cc: smp@csn.net (Steve Passe), freebsd-hardware@freebsd.org Subject: Re: RAID solutions? In-Reply-To: <199609182140.OAA04943@GndRsh.aac.dev.com> References: <199609182126.PAA00944@clem.systemsix.com> <199609182140.OAA04943@GndRsh.aac.dev.com> Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Rodney W. Grimes writes: > > Hi, > > > > Rod said: > > > > We are looking to put a RAID array onto a server, and were wondering which > > > > ... > > > Or wait 60 to 90 says and get a host based solution from me... > > > > are we talking about a hardware/software product you will be selling > > or a freeBSD driver? > > A FreeBSD driver that will be imported into the sources that supports > several cards from a major manufacture of host RAID controllers. This > will be hardware RAID support. Would I be close if I guessed that the vendor was DPT? ;) Nate From owner-freebsd-hardware Wed Sep 18 18:09:40 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA25763 for hardware-outgoing; Wed, 18 Sep 1996 18:09:40 -0700 (PDT) Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.19]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id SAA25702 for ; Wed, 18 Sep 1996 18:09:33 -0700 (PDT) Received: (from bde@localhost) by godzilla.zeta.org.au (8.6.12/8.6.9) id LAA20566; Thu, 19 Sep 1996 11:04:24 +1000 Date: Thu, 19 Sep 1996 11:04:24 +1000 From: Bruce Evans Message-Id: <199609190104.LAA20566@godzilla.zeta.org.au> To: BRETT_GLASS@infoworld.com, hardware@freebsd.org Subject: Re: More or fewer IRQs? Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >I'm setting up a FreeBSD system with a buncha serial ports, and the cards >will allow me to share IRQs between ports. There are 5 available IRQs and >10 ports; in other words, there aren't enough IRQs to allow every port to >have one of its own, so some sharing is necessary. >With the hardware I have here, I have two choices. I can use up every IRQ >in the machine and put two UARTS on each, or I can lump more together >(there are three ISA cards, so that means I could get away with using 3 out >of the 5). The latter approach has the advantage that I can add another >peripheral in the remaining vacant PCI slot and would have an IRQ for it. >But which would yield better performance? Try it and see. "Some sharing" forces you to use the inefficient COM_MULTIPORT options for all ports (even ones on an unshared IRQ), so many of the advantages of not sharing aren't available. The main advantage of putting all the ports on one IRQ gives less unfair sharing but probably costs more. On machines with fast CPUs and cache, approximately: (1) per-interrupt cost for _each_ additional shared port = 1.5 * time for one inb(0x3fa) = about 2 uS for 8MHz ISA bus (2) per-interrupt cost = time for one outb(0x20, 0x20) (if !AUTO_EOI_1 option) + time for one outb(0xa0, 0x20) (if IRQ >= 8 && !AUTO_EOI_2 option) + about 1-10 uS for CPU overheads (1 uS on P90, 10 uS on 386) + time for cache misses + more for lots of output completions and modem status changes = it depends >It seems to me that the high >overhead of taking an interrupt MIGHT make it better to put many ports on >one IRQ, since polling each port on the card probably still costs less than >a context switch on an Intel CPU (a truly ugly process ;-). On the other Interrupt overheads are only relatively high. They are only a couple of times more than the overhead for one inb() to poll one port, at least if inb()s to access the ICU are avoided. Interrupts aren't context switches, so the higher overheads and uglyness for context switches don't apply. >hand, the source code suggests that the driver turns off interrupts as >it services serial ports, so there MIGHT be a chance of starving otner >devices (in particular, the system's cantankerous IDE interface) if >there were many UARTs on an IRQ. What say ye? The other devices would starve anyway, since (sio and cy) serial devices have priority. IDE doesn't mind starving for hours. However, the serial drivers try to be fast, since they would starve their own 8250 devices if they took more than 86 uS. They do take more than 86 uS if there is a lot of activty on a lot of ports. The maximum is about 1000 uS for 16 ports at 115200 bps. 2000 uS for 32 ports at 115200 bps can't work because the next batch of input will arrive after about 14 * 87 = 1218 uS. Bruce From owner-freebsd-hardware Wed Sep 18 18:22:02 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA02948 for hardware-outgoing; Wed, 18 Sep 1996 18:22:02 -0700 (PDT) Received: from monk.via.net (monk.via.net [140.174.204.10]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id SAA02914 for ; Wed, 18 Sep 1996 18:21:58 -0700 (PDT) Received: (from joe@localhost) by monk.via.net (8.6.11/8.6.12) id SAA10248 for hardware@freebsd.org; Wed, 18 Sep 1996 18:28:36 -0700 Date: Wed, 18 Sep 1996 18:28:36 -0700 From: Joe McGuckin Message-Id: <199609190128.SAA10248@monk.via.net> To: hardware@freebsd.org Subject: DEC PCI CHIP QUESTION X-Sun-Charset: US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Can't the Dec PCI chip operate full duplex? Are software changes or ifconfig flags needed? We just bought an ethernet switch that can configure it's ports as full duplex. -joe From owner-freebsd-hardware Wed Sep 18 18:26:48 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA05787 for hardware-outgoing; Wed, 18 Sep 1996 18:26:48 -0700 (PDT) Received: from zit1.zit.th-darmstadt.de (root@zit1.zit.th-darmstadt.de [130.83.63.20]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id SAA05748; Wed, 18 Sep 1996 18:26:44 -0700 (PDT) Received: from localhost (petzi@localhost) by zit1.zit.th-darmstadt.de (8.7.5/8.6.9) with SMTP id DAA05761; Thu, 19 Sep 1996 03:26:10 +0200 (MET DST) Date: Thu, 19 Sep 1996 03:26:10 +0200 (MET DST) From: Michael Beckmann To: "Rodney W. Grimes" cc: spork@super-g.com, isp@freebsd.org, hardware@freebsd.org Subject: Re: INN history file and disk I/O In-Reply-To: <199609182104.OAA04861@GndRsh.aac.dev.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, > Buyer beware, Gigabyte is playing games with the specifications and > register usage of the Triton-I and Triton-II chipsets to get away with > these 6 SIMM slots. These chip sets have 8 programmable DRAM row size > registers, each _SIDE_ of a SIMM requires one of them to be programmed, > you can _ONLY_ run 4 double sided simms with these chip sets. According to the HX manual you can use 6 SIMMs with 8 MB each in it, and these are double-sided. OTOH, who cares whether one can put 6 double sided SIMMs in it. There are so many valid combinations that I don't see this as a problem. The 586 ATE and HX mainboards I have used work just fine, I haven't seen one fail yet. That's just my personal experience. I'm not religious about mainboards, but I don't have the impression that Asus boards have significantly fewer bugs and problems. Gigabyte definitely belongs to the good equipment. > Gigabyte dirty little move is to _ONLY_ allow single sided SIMMS in 2 Wow, you make it sound as if Gigabyte were posessed by the wicked one ;-) Cheers, Michael From owner-freebsd-hardware Wed Sep 18 18:33:58 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA09740 for hardware-outgoing; Wed, 18 Sep 1996 18:33:58 -0700 (PDT) Received: from monk.via.net (monk.via.net [140.174.204.10]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id SAA09723 for ; Wed, 18 Sep 1996 18:33:55 -0700 (PDT) Received: (from joe@localhost) by monk.via.net (8.6.11/8.6.12) id SAA10273; Wed, 18 Sep 1996 18:40:14 -0700 Date: Wed, 18 Sep 1996 18:40:14 -0700 From: Joe McGuckin Message-Id: <199609190140.SAA10273@monk.via.net> To: nate@mt.sri.com Subject: Re: RAID solutions? Cc: freebsd-hardware@FreeBSD.org X-Sun-Charset: US-ASCII Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk **WHEN** will support for a raid controller card be released? I want to build a dedicated news machine with FreeBSD - I'm just waiting for RAID support... -joe From owner-freebsd-hardware Wed Sep 18 20:29:36 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id UAA00917 for hardware-outgoing; Wed, 18 Sep 1996 20:29:36 -0700 (PDT) Received: from mail.crl.com (mail.crl.com [165.113.1.22]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id UAA00891 for ; Wed, 18 Sep 1996 20:29:31 -0700 (PDT) Received: from root.com (implode.root.com) by mail.crl.com with SMTP id AA01497 (5.65c/IDA-1.5 for ); Wed, 18 Sep 1996 20:30:04 -0700 Received: from localhost (localhost [127.0.0.1]) by root.com (8.7.5/8.6.5) with SMTP id UAA01140; Wed, 18 Sep 1996 20:28:19 -0700 (PDT) Message-Id: <199609190328.UAA01140@root.com> X-Authentication-Warning: implode.root.com: Host localhost [127.0.0.1] didn't use HELO protocol To: Joe McGuckin Cc: hardware@freebsd.org Subject: Re: DEC PCI CHIP QUESTION In-Reply-To: Your message of "Wed, 18 Sep 1996 18:28:36 PDT." <199609190128.SAA10248@monk.via.net> From: David Greenman Reply-To: dg@root.com Date: Wed, 18 Sep 1996 20:28:19 -0700 Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >Can't the Dec PCI chip operate full duplex? Are software changes or ifconfig >flags needed? It's possible, but it may require some driver changes. >We just bought an ethernet switch that can configure it's ports as full >duplex. I'll be getting a 100BASE-TX switch in a few days and I'll be working on full duplex support in the fxp driver for the Intel Pro/100B. I've heard that Matt Thomas has patches for the de driver and I intend to pursue this, too. -DG David Greenman Core-team/Principal Architect, The FreeBSD Project From owner-freebsd-hardware Wed Sep 18 21:30:52 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id VAA28757 for hardware-outgoing; Wed, 18 Sep 1996 21:30:52 -0700 (PDT) Received: from mail.crl.com (mail.crl.com [165.113.1.22]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id VAA28725 for ; Wed, 18 Sep 1996 21:30:46 -0700 (PDT) Received: from GndRsh.aac.dev.com by mail.crl.com with SMTP id AA13090 (5.65c/IDA-1.5 for ); Wed, 18 Sep 1996 21:31:13 -0700 Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id VAA05560; Wed, 18 Sep 1996 21:27:57 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609190427.VAA05560@GndRsh.aac.dev.com> Subject: Re: DEC PCI CHIP QUESTION In-Reply-To: <199609190128.SAA10248@monk.via.net> from Joe McGuckin at "Sep 18, 96 06:28:36 pm" To: joe@via.net (Joe McGuckin) Date: Wed, 18 Sep 1996 21:27:57 -0700 (PDT) Cc: hardware@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-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > > Can't the Dec PCI chip operate full duplex? Yes, the DEC PCI ethernet chips (DC21x4x) can operate in full duplex mode. > Are software changes or ifconfig flags needed? Software changes are needed. The current driver does not have full duplex support in it. I have seen private email from the author that shows the card doing a FD negotiation with a switch. I do now know the current status of that set of changes though. > We just bought an ethernet switch that can configure it's ports as full > duplex. And so did I... :-) -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Wed Sep 18 22:59:31 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id WAA04993 for hardware-outgoing; Wed, 18 Sep 1996 22:59:31 -0700 (PDT) Received: from lserver.infoworld.com (root@lserver.infoworld.com [192.216.48.4]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id WAA04979 for ; Wed, 18 Sep 1996 22:59:29 -0700 (PDT) Received: from ccgate.infoworld.com (ccgate.infoworld.com [192.216.49.101]) by lserver.infoworld.com (8.7.5/8.7.3) with SMTP id WAA29248; Wed, 18 Sep 1996 22:58:58 -0700 (PDT) From: BRETT_GLASS@infoworld.com Received: from ccMail by ccgate.infoworld.com (SMTPLINK V2.11) id AA843112557; Thu, 19 Sep 96 00:44:45 PST Date: Thu, 19 Sep 96 00:44:45 PST Message-Id: <9608188431.AA843112557@ccgate.infoworld.com> To: Bruce Evans , hardware@freebsd.org Subject: Re: More or fewer IRQs? Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Bruce: If what you say is true, the only place I can be sure to save time (this is on a 486DX4/100) is at the ICU by setting those AUTO_EOI flags. But how safe are these? I was getting missed IDE completion interrupts with a kernel that had AUTO_EOI_1 on, but don't know if that was the only source of the problem. (I've changed a LOT of options in more recent kernels.) --Brett From owner-freebsd-hardware Wed Sep 18 23:58:22 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id XAA05699 for hardware-outgoing; Wed, 18 Sep 1996 23:58:22 -0700 (PDT) Received: from mail.crl.com (mail.crl.com [165.113.1.22]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id XAA05679 for ; Wed, 18 Sep 1996 23:58:19 -0700 (PDT) Received: from godzilla.zeta.org.au by mail.crl.com with SMTP id AA05269 (5.65c/IDA-1.5 for ); Wed, 18 Sep 1996 23:58:52 -0700 Received: (from bde@localhost) by godzilla.zeta.org.au (8.6.12/8.6.9) id QAA30028; Thu, 19 Sep 1996 16:27:46 +1000 Date: Thu, 19 Sep 1996 16:27:46 +1000 From: Bruce Evans Message-Id: <199609190627.QAA30028@godzilla.zeta.org.au> To: bde@zeta.org.au, BRETT_GLASS@infoworld.com, hardware@freebsd.org Subject: Re: More or fewer IRQs? Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >If what you say is true, the only place I can be sure to save time (this is >on a 486DX4/100) is at the ICU by setting those AUTO_EOI flags. But how >safe are these? I was getting missed IDE completion interrupts with a >kernel that had AUTO_EOI_1 on, but don't know if that was the only source >of the problem. (I've changed a LOT of options in more recent kernels.) For my hardware, they either fail completely (AUTO_EOI_2 fails for one system) or are completely safe. A missing EOI is probably unrecoverable - the software doesn't send one because it expects the hardware to, and the hardware only sends for the next interrupt which never occurs. If the IDE timeout fixed the missing IDE interrupts, then they probably weren't missed because of the EOI configuration. Bruce From owner-freebsd-hardware Thu Sep 19 00:23:55 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA16477 for hardware-outgoing; Thu, 19 Sep 1996 00:23:55 -0700 (PDT) Received: from mail.crl.com (mail.crl.com [165.113.1.22]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id AAA16399; Thu, 19 Sep 1996 00:23:39 -0700 (PDT) Received: from GndRsh.aac.dev.com by mail.crl.com with SMTP id AA12790 (5.65c/IDA-1.5); Wed, 18 Sep 1996 21:29:10 -0700 Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id VAA05547; Wed, 18 Sep 1996 21:23:44 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609190423.VAA05547@GndRsh.aac.dev.com> Subject: Re: INN history file and disk I/O In-Reply-To: from Michael Beckmann at "Sep 19, 96 03:26:10 am" To: petzi@zit.th-darmstadt.de (Michael Beckmann) Date: Wed, 18 Sep 1996 21:23:44 -0700 (PDT) Cc: spork@super-g.com, isp@freebsd.org, hardware@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-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > Hi, > > > Buyer beware, Gigabyte is playing games with the specifications and > > register usage of the Triton-I and Triton-II chipsets to get away with > > these 6 SIMM slots. These chip sets have 8 programmable DRAM row size > > registers, each _SIDE_ of a SIMM requires one of them to be programmed, > > you can _ONLY_ run 4 double sided simms with these chip sets. > > According to the HX manual you can use 6 SIMMs with 8 MB each in it, and > these are double-sided. Then Gigabytes HX manual is in conflict with the Intel 82439HX databook, and somehow I trust the databook far more than I do Gigabyte MB manual. > OTOH, who cares whether one can put 6 double sided SIMMs in it. Anyone who is buying this board thinking they can load it with 6 32MB simms for a total memory capacity of 192MB, thats who cares!! > There are > so many valid combinations that I don't see this as a problem. Trust me, as a system builder, it _IS_ a problem. Both at initial machine configuration time (if I preload the system with 4 32MB simms there is no way to field expand the memory without tossing what is already in it away). Now your clone a day shop down the street wouldn't think twice about doing that because he usually doesn't really care about the customer 3 to 6 months down the road. I do care, and don't like to give customers false senses of upgradeabiliy. > The 586 ATE and HX mainboards I have used work just fine, I haven't > seen one fail yet. The 586ATE board does infact run just fine, and I can't recall exactly what it was about it that stopped me from adding it to my product line, perhaps that it offered nothing over my current product line. > That's just my personal experience. I'm not religious about mainboards, > but I don't have the impression that Asus boards have significantly fewer > bugs and problems. Gigabyte definitely belongs to the good equipment. I can agree that buying Gigabyte would be better than buying a lot of other boards out there. > > > Gigabyte dirty little move is to _ONLY_ allow single sided SIMMS in 2 > > Wow, you make it sound as if Gigabyte were posessed by the wicked one ;-) I consider miss leading datasheets to be wicked, yes I do consider Gigabytes marking department to be ``posessed by the wicked one'' for the particular way the use the 6 simm trick to fool people into thinking they can get more memory on there boards than any one elses. -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Thu Sep 19 00:40:49 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA22774 for hardware-outgoing; Thu, 19 Sep 1996 00:40:49 -0700 (PDT) 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 AAA22759 for ; Thu, 19 Sep 1996 00:40:45 -0700 (PDT) Received: from MindBender.serv.net by mx.serv.net (8.7.5/SERV Revision: 2.30) id AAA09202; Thu, 19 Sep 1996 00:40:53 -0700 (PDT) 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 AAA07812; Thu, 19 Sep 1996 00:40:34 -0700 (PDT) Message-Id: <199609190740.AAA07812@MindBender.serv.net> X-Authentication-Warning: MindBender.serv.net: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: Joe McGuckin cc: nate@mt.sri.com, freebsd-hardware@freebsd.org Subject: Re: RAID solutions? In-reply-to: Your message of Wed, 18 Sep 96 18:40:14 -0700. <199609190140.SAA10273@monk.via.net> Date: Thu, 19 Sep 1996 00:40:33 -0700 From: "Michael L. VanLoon -- HeadCandy.com" Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >**WHEN** will support for a raid controller card be released? I want >to build a dedicated news machine with FreeBSD - I'm just waiting for >RAID support... WHEN someone gets around to writing a driver for one. Have you considered using ccd? ----------------------------------------------------------------------------- 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-hardware Thu Sep 19 00:43:15 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA24029 for hardware-outgoing; Thu, 19 Sep 1996 00:43:15 -0700 (PDT) Received: from tulpi.interconnect.com.au (tulpi.interconnect.com.au [192.189.54.18]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id AAA23088; Thu, 19 Sep 1996 00:41:27 -0700 (PDT) Received: (from ahill@localhost) by tulpi.interconnect.com.au id RAA24913 (8.7.6/IDA-1.6); Thu, 19 Sep 1996 17:40:35 +1000 (EST) Date: Thu, 19 Sep 1996 17:40:34 +1000 (EST) From: Anthony Hill To: qusetions@freebsd.org cc: hardware@freebsd.org Subject: Adaptec Parallel to SCSI converter Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Adaptec has released a EPP (enhanced parallel port) to SCSI converter with a cable that goes from the parallel port directly to a SCSI device. The thing costs $229 Aus (under $300 US) Software is included, although I have heard of no support for any UNIX platform. Has anyone looked into drivers for this product ? Anthony Hill ahill@connect.com.au From owner-freebsd-hardware Thu Sep 19 01:03:42 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id BAA05197 for hardware-outgoing; Thu, 19 Sep 1996 01:03:42 -0700 (PDT) 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 BAA05176 for ; Thu, 19 Sep 1996 01:03:36 -0700 (PDT) Received: from MindBender.serv.net by mx.serv.net (8.7.5/SERV Revision: 2.30) id BAA09505; Thu, 19 Sep 1996 01:03:44 -0700 (PDT) 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 BAA08004; Thu, 19 Sep 1996 01:03:24 -0700 (PDT) Message-Id: <199609190803.BAA08004@MindBender.serv.net> X-Authentication-Warning: MindBender.serv.net: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: BRETT_GLASS@infoworld.com cc: Bruce Evans , hardware@freebsd.org Subject: Re: More or fewer IRQs? In-reply-to: Your message of Thu, 19 Sep 96 00:44:45 -0800. <9608188431.AA843112557@ccgate.infoworld.com> Date: Thu, 19 Sep 1996 01:03:24 -0700 From: "Michael L. VanLoon -- HeadCandy.com" Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >If what you say is true, the only place I can be sure to save time (this is >on a 486DX4/100) is at the ICU by setting those AUTO_EOI flags. But how >safe are these? I was getting missed IDE completion interrupts with a >kernel that had AUTO_EOI_1 on, but don't know if that was the only source >of the problem. (I've changed a LOT of options in more recent kernels.) I have run a kernel with AUTO_EOI_1 and AUTO_EOI_2 both enabled, with two IDE drives, and I didn't have a single problem. This was on an ALR 386 EISA motherboard. ----------------------------------------------------------------------------- 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-hardware Thu Sep 19 07:40:43 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id HAA05983 for hardware-outgoing; Thu, 19 Sep 1996 07:40:43 -0700 (PDT) Received: from mail.id.net (mail.id.net [199.125.1.6]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id HAA05949; Thu, 19 Sep 1996 07:40:38 -0700 (PDT) Received: from server.id.net (rls@server.id.net [199.125.1.10]) by mail.id.net (8.7.5/ID-Net) with ESMTP id KAA02961; Thu, 19 Sep 1996 10:43:11 -0400 (EDT) Received: (from rls@localhost) by server.id.net (8.7.5/8.7.3) id KAA09105; Thu, 19 Sep 1996 10:40:39 -0400 (EDT) From: Robert Shady Message-Id: <199609191440.KAA09105@server.id.net> Subject: Re: Very Slow Ethernet Link (FreeBSD v. Linux) In-Reply-To: <199609171635.TAA14831@silver.sms.fi> from Petri Helenius at "Sep 17, 96 07:35:17 pm" To: pete@sms.fi (Petri Helenius) Date: Thu, 19 Sep 1996 10:40:39 -0400 (EDT) Cc: jab@rock.anchorage.net, freebsd-hardware@FreeBSD.org, hackers@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-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk >> Using FreeBSD 2.1.0: >> >> ftp transfer with freebsd 1927427 bytes @ 4.2e+02 seconds 4.4kb/s >> >> Removing FreeBSD and Installed Linux 2.0 >> >> ftp transfer with Linux 1927427 bytes @ 3.05 seconds (6.2e+02 kb/s) Wooo Wooo :) >> >> Using the exact same configuration and computer, the reults are in the >> Linux favor by far. >> Don't know what the problem was. > You did a ftp to the loopback-address? This is a known problem with > the MTU if you did. Set the MTU to 1500 or something more reasonable. I *HOPE* this wasn't to the loopback address, my tests show ftp> get ids local: ids remote: ids 200 PORT command successful. 150 Opening BINARY mode data connection for ids (1152582 bytes). 226 Transfer complete. 1152582 bytes received in 1.41 seconds (797.68 Kbytes/s) 800KB/second to the loopback on a heavily loaded machine.. -- Rob === _/_/_/_/_/ _/_/_/_/ _/_/ _/ _/_/_/_/_/ _/_/_/_/_/ _/ _/ _/ _/_/_/ _/ _/ _/ _/_/_/_/ _/ _/_/_/_/_/ _/_/_/_/ _/ _/ _/_/_/_/_/ _/ Innovative Data Services Serving South-Eastern Michigan Internet Service Provider / Hardware Sales / Consulting Services Voice: (810)855-0404 / Fax: (810)855-3268 / Web: http://www.id.net From owner-freebsd-hardware Thu Sep 19 08:11:25 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA17216 for hardware-outgoing; Thu, 19 Sep 1996 08:11:25 -0700 (PDT) Received: from dyson.iquest.net (dyson.iquest.net [198.70.144.127]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id IAA17145; Thu, 19 Sep 1996 08:11:13 -0700 (PDT) Received: (from root@localhost) by dyson.iquest.net (8.7.5/8.6.9) id KAA08270; Thu, 19 Sep 1996 10:10:15 -0500 (EST) From: "John S. Dyson" Message-Id: <199609191510.KAA08270@dyson.iquest.net> Subject: Re: Very Slow Ethernet Link (FreeBSD v. Linux) To: rls@mail.id.net (Robert Shady) Date: Thu, 19 Sep 1996 10:10:15 -0500 (EST) Cc: pete@sms.fi, jab@rock.anchorage.net, freebsd-hardware@FreeBSD.org, hackers@FreeBSD.org In-Reply-To: <199609191440.KAA09105@server.id.net> from "Robert Shady" at Sep 19, 96 10:40:39 am Reply-To: dyson@FreeBSD.org X-Mailer: ELM [version 2.4 PL24 ME8] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > >> Using FreeBSD 2.1.0: > >> > >> ftp transfer with freebsd 1927427 bytes @ 4.2e+02 seconds 4.4kb/s > >> > >> Removing FreeBSD and Installed Linux 2.0 > >> > >> ftp transfer with Linux 1927427 bytes @ 3.05 seconds (6.2e+02 kb/s) Wooo Wooo :) > >> > >> Using the exact same configuration and computer, the reults are in the > >> Linux favor by far. > >> Don't know what the problem was. > > > You did a ftp to the loopback-address? This is a known problem with > > the MTU if you did. Set the MTU to 1500 or something more reasonable. > > I *HOPE* this wasn't to the loopback address, my tests show > > ftp> get ids > local: ids remote: ids > 200 PORT command successful. > 150 Opening BINARY mode data connection for ids (1152582 bytes). > 226 Transfer complete. > 1152582 bytes received in 1.41 seconds (797.68 Kbytes/s) > > 800KB/second to the loopback on a heavily loaded machine.. > I think that the loopback buffer size "feature" has been fixed in 2.2 for quite a while??? John From owner-freebsd-hardware Thu Sep 19 08:44:57 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA01312 for hardware-outgoing; Thu, 19 Sep 1996 08:44:57 -0700 (PDT) Received: from lserver.infoworld.com (root@lserver.infoworld.com [192.216.48.4]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id IAA01276; Thu, 19 Sep 1996 08:44:53 -0700 (PDT) Received: from ccgate.infoworld.com (ccgate.infoworld.com [192.216.49.101]) by lserver.infoworld.com (8.7.5/8.7.3) with SMTP id IAA17250; Thu, 19 Sep 1996 08:44:44 -0700 (PDT) From: BRETT_GLASS@infoworld.com Received: from ccMail by ccgate.infoworld.com (SMTPLINK V2.11) id AA843147695; Thu, 19 Sep 96 10:29:19 PST Date: Thu, 19 Sep 96 10:29:19 PST Message-Id: <9608198431.AA843147695@ccgate.infoworld.com> To: Anthony Hill , qusetions@freebsd.org Cc: hardware@freebsd.org Subject: Adaptec Parallel to SCSI converter Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk This is the Trantor product that's been out for about 5 years. It is very useful, but is slow. --Brett From owner-freebsd-hardware Thu Sep 19 09:05:05 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA10727 for hardware-outgoing; Thu, 19 Sep 1996 09:05:05 -0700 (PDT) Received: from rocky.mt.sri.com (rocky.mt.sri.com [206.127.76.100]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA10688; Thu, 19 Sep 1996 09:05:00 -0700 (PDT) Received: (from nate@localhost) by rocky.mt.sri.com (8.7.5/8.7.3) id KAA18441; Thu, 19 Sep 1996 10:04:52 -0600 (MDT) Date: Thu, 19 Sep 1996 10:04:52 -0600 (MDT) Message-Id: <199609191604.KAA18441@rocky.mt.sri.com> From: Nate Williams To: BRETT_GLASS@infoworld.com Cc: Anthony Hill , qusetions@freebsd.org, hardware@freebsd.org Subject: Re: Adaptec Parallel to SCSI converter In-Reply-To: <9608198431.AA843147695@ccgate.infoworld.com> References: <9608198431.AA843147695@ccgate.infoworld.com> Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk BRETT GLASS writes: > This is the Trantor product that's been out for about 5 years. > > It is very useful, but is slow. I'm pretty sure Adaptec's model is *NOT* the trantor model. However, it is still pretty slow. I've also got one recommended by IOmega for their ZIP drives, but it only has M$ OS software. Nate From owner-freebsd-hardware Thu Sep 19 09:14:17 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA14497 for hardware-outgoing; Thu, 19 Sep 1996 09:14:17 -0700 (PDT) Received: from persprog.com (persprog.com [204.215.255.203]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id JAA14468 for ; Thu, 19 Sep 1996 09:14:12 -0700 (PDT) Received: by persprog.com (8.7.5/4.10) id LAA00800; Thu, 19 Sep 1996 11:00:12 -0500 Received: from dasa(192.2.2.199) by cerberus.ppi.com via smap (V1.3) id sma000793; Thu Sep 19 11:59:54 1996 Received: from DASA/SpoolDir by dasa.ppi.com (Mercury 1.21); 19 Sep 96 12:00:05 +0500 Received: from SpoolDir by DASA (Mercury 1.30); 19 Sep 96 12:00:00 +0500 From: "David Alderman" Organization: Personalized Programming, Inc To: "Rodney W. Grimes" , hardware@freebsd.org Date: Thu, 19 Sep 1996 11:59:57 +0500 Subject: Re: DEC PCI CHIP QUESTION Priority: normal X-mailer: Pegasus Mail for Windows (v2.42a) Message-ID: Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > From: "Rodney W. Grimes" > > We just bought an ethernet switch that can configure it's ports as full > > duplex. > > And so did I... :-) > > Which one did you get? I just love new toys! ====================================== When philosophy conflicts with reality, choose reality. Dave Alderman -- dave@persprog.com ====================================== From owner-freebsd-hardware Thu Sep 19 10:01:16 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA01992 for hardware-outgoing; Thu, 19 Sep 1996 10:01:16 -0700 (PDT) Received: from persprog.com (persprog.com [204.215.255.203]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA01627; Thu, 19 Sep 1996 10:00:12 -0700 (PDT) Received: by persprog.com (8.7.5/4.10) id LAA01187; Thu, 19 Sep 1996 11:50:18 -0500 Received: from dasa(192.2.2.199) by cerberus.ppi.com via smap (V1.3) id sma001183; Thu Sep 19 12:50:13 1996 Received: from DASA/SpoolDir by dasa.ppi.com (Mercury 1.21); 19 Sep 96 12:50:24 +0500 Received: from SpoolDir by DASA (Mercury 1.30); 19 Sep 96 12:50:17 +0500 From: "David Alderman" Organization: Personalized Programming, Inc To: Nate Williams , Anthony Hill , qusetions@FreeBSD.org, hardware@FreeBSD.org, BRETT_GLASS@infoworld.com Date: Thu, 19 Sep 1996 12:50:10 +0500 Subject: Re: Adaptec Parallel to SCSI converter Priority: normal X-mailer: Pegasus Mail for Windows (v2.42a) Message-ID: Sender: owner-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > From: Nate Williams > BRETT GLASS writes: > > This is the Trantor product that's been out for about 5 years. > > > > It is very useful, but is slow. > > I'm pretty sure Adaptec's model is *NOT* the trantor model. However, it > is still pretty slow. I've also got one recommended by IOmega for their > ZIP drives, but it only has M$ OS software. > > > Nate > Actually, Adaptec acquired Trantor several years ago. I'm sure the product has changed since then. So, you're BOTH right (sort of) ;) ====================================== When philosophy conflicts with reality, choose reality. Dave Alderman -- dave@persprog.com ====================================== From owner-freebsd-hardware Thu Sep 19 10:36:30 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA10842 for hardware-outgoing; Thu, 19 Sep 1996 10:36:30 -0700 (PDT) Received: from Gatekeeper.Lamb.net (ulf@cat-food.Melmac.org [206.169.44.2]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA10815; Thu, 19 Sep 1996 10:36:25 -0700 (PDT) Received: (from ulf@localhost) by Gatekeeper.Lamb.net (8.7.5/8.7.3) id KAA11832; Thu, 19 Sep 1996 10:36:36 -0700 (PDT) From: Ulf Zimmermann Message-Id: <199609191736.KAA11832@Gatekeeper.Lamb.net> Subject: Re: Adaptec Parallel to SCSI converter To: nate@mt.sri.com (Nate Williams) Date: Thu, 19 Sep 1996 10:36:36 -0700 (PDT) Cc: BRETT_GLASS@infoworld.com, ahill@interconnect.com.au, qusetions@FreeBSD.org, hardware@FreeBSD.org In-Reply-To: <199609191604.KAA18441@rocky.mt.sri.com> from Nate Williams at "Sep 19, 96 10:04:52 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-hardware@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > BRETT GLASS writes: > > This is the Trantor product that's been out for about 5 years. > > > > It is very useful, but is slow. > > I'm pretty sure Adaptec's model is *NOT* the trantor model. However, it > is still pretty slow. I've also got one recommended by IOmega for their > ZIP drives, but it only has M$ OS software. > > Nate > Why are you so sure ? As adaptec bought Trantor even before Future Domain. The Trantor stuff was longer time even listed with Trantors part numbers. Ulf. -------------------------------------------------------------------------- Ulf Zimmermann, 1525 Pacific Ave., Alameda, CA-94501, #: 510-865-0204 Lamb Art Internet Services | http://www.Lamb.net/ | http://www.Alameda.net From owner-freebsd-hardware Thu Sep 19 10:48:06 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA15657 for hardware-outgoing; Thu, 19 Sep 1996 10:48:06 -0700 (PDT) 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 KAA15620 for ; Thu, 19 Sep 1996 10:48:02 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id KAA07089; Thu, 19 Sep 1996 10:47:36 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609191747.KAA07089@GndRsh.aac.dev.com> Subject: Re: DEC PCI CHIP QUESTION In-Reply-To: from David Alderman at "Sep 19, 96 11:59:57 am" To: dave@persprog.com (David Alderman) Date: Thu, 19 Sep 1996 10:47:35 -0700 (PDT) Cc: hardware@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-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > > From: "Rodney W. Grimes" > > > > We just bought an ethernet switch that can configure it's ports as full > > > duplex. > > > > And so did I... :-) > > > > > > Which one did you get? I just love new toys! A D-Link FlexSwitch DES-3205, seems to be working happily, but a one man shop has a hard time streasing a 100MB/s switch very much :-). Nice thing is that it is a 10/100MB/s switch so I don't have to route between my 2 segments anymore :-) There is currently a product promotion on these for those who are interested that includes the DES-3205 switch and 5 DFE-500TX 10/100MB/s ethernet cards (DC21140 based, FreeBSD certified by AAC) going for the grand old price of $2017 until 9/30/1996. You should be able to find full product details at http://www.dlink.com. -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Thu Sep 19 11:34:48 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA06104 for hardware-outgoing; Thu, 19 Sep 1996 11:34:48 -0700 (PDT) Received: from persprog.com (persprog.com [204.215.255.203]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id LAA06067 for ; Thu, 19 Sep 1996 11:34:37 -0700 (PDT) Received: by persprog.com (8.7.5/4.10) id NAA02173; Thu, 19 Sep 1996 13:27:44 -0500 Received: from dasa(192.2.2.199) by cerberus.ppi.com via smap (V1.3) id sma002168; Thu Sep 19 14:27:36 1996 Received: from DASA/SpoolDir by dasa.ppi.com (Mercury 1.21); 19 Sep 96 14:27:47 +0500 Received: from SpoolDir by DASA (Mercury 1.30); 19 Sep 96 14:27:32 +0500 From: "David Alderman" Organization: Personalized Programming, Inc To: "Rodney W. Grimes" Date: Thu, 19 Sep 1996 14:27:29 +0500 Subject: Re: DEC PCI CHIP QUESTION CC: hardware@freebsd.org Priority: normal X-mailer: Pegasus Mail for Windows (v2.42a) Message-ID: Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > From: "Rodney W. Grimes" > A D-Link FlexSwitch DES-3205, seems to be working happily, but a one > man shop has a hard time streasing a 100MB/s switch very much :-). Nice > thing is that it is a 10/100MB/s switch so I don't have to route between > my 2 segments anymore :-) > > There is currently a product promotion on these for those who are > interested that includes the DES-3205 switch and 5 DFE-500TX 10/100MB/s > ethernet cards (DC21140 based, FreeBSD certified by AAC) going for the > grand old price of $2017 until 9/30/1996. You should be able to find > full product details at http://www.dlink.com. > For this price, I could probably swing one for my house! ====================================== When philosophy conflicts with reality, choose reality. Dave Alderman -- dave@persprog.com ====================================== From owner-freebsd-hardware Thu Sep 19 11:44:20 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id LAA09736 for hardware-outgoing; Thu, 19 Sep 1996 11:44:20 -0700 (PDT) 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 LAA09688 for ; Thu, 19 Sep 1996 11:44:15 -0700 (PDT) Received: from localhost (localhost [127.0.0.1]) by clem.systemsix.com (8.6.12/8.6.12) with SMTP id MAA07822; Thu, 19 Sep 1996 12:43:16 -0600 Message-Id: <199609191843.MAA07822@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: "Rodney W. Grimes" cc: hardware@freebsd.org Subject: Re: DEC PCI CHIP QUESTION In-reply-to: Your message of "Thu, 19 Sep 1996 10:47:35 PDT." <199609191747.KAA07089@GndRsh.aac.dev.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Thu, 19 Sep 1996 12:43:15 -0600 Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi, >A D-Link FlexSwitch DES-3205, seems to be working happily, but a one >man shop has a hard time streasing a 100MB/s switch very much :-). Nice >thing is that it is a 10/100MB/s switch so I don't have to route between >my 2 segments anymore :-) Is DLink a good brand? The DLink DFE-808TX 100base-TX 8-port Hub can be had quite cheaply, and I (also a 1 man shop) can't justify the cost of a switch. As I have a dedicated P5-75 freeBSD box for a router/firewall, using 2 segments is no problem. -- Steve Passe | powered by smp@csn.net | FreeBSD From owner-freebsd-hardware Thu Sep 19 12:22:10 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA00730 for hardware-outgoing; Thu, 19 Sep 1996 12:22:10 -0700 (PDT) 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 MAA00685 for ; Thu, 19 Sep 1996 12:22:06 -0700 (PDT) Received: (from rgrimes@localhost) by GndRsh.aac.dev.com (8.7.5/8.7.3) id MAA07413; Thu, 19 Sep 1996 12:21:53 -0700 (PDT) From: "Rodney W. Grimes" Message-Id: <199609191921.MAA07413@GndRsh.aac.dev.com> Subject: Re: DEC PCI CHIP QUESTION In-Reply-To: <199609191843.MAA07822@clem.systemsix.com> from Steve Passe at "Sep 19, 96 12:43:15 pm" To: smp@csn.net (Steve Passe) Date: Thu, 19 Sep 1996 12:21:53 -0700 (PDT) Cc: hardware@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-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > Hi, > > >A D-Link FlexSwitch DES-3205, seems to be working happily, but a one > >man shop has a hard time streasing a 100MB/s switch very much :-). Nice > >thing is that it is a 10/100MB/s switch so I don't have to route between > >my 2 segments anymore :-) > > Is DLink a good brand? I have been happy with the few products of thiers I have used over the years. > The DLink DFE-808TX 100base-TX 8-port Hub > can be had quite cheaply, and I (also a 1 man shop) can't justify the > cost of a switch. As I have a dedicated P5-75 freeBSD box for a > router/firewall, using 2 segments is no problem. I don't have any first hand experience with this hub, I think David Greenman has one of the DFE-812TX+, which is a 12 port version. If you can't get it for less than $648.00, come see me on it, I'll stand behind it and take it back within the first 15 days if it does not work up to your expectations. -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD From owner-freebsd-hardware Thu Sep 19 12:55:27 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA17991 for hardware-outgoing; Thu, 19 Sep 1996 12:55:27 -0700 (PDT) Received: from monk.via.net (monk.via.net [140.174.204.10]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id MAA17914 for ; Thu, 19 Sep 1996 12:55:20 -0700 (PDT) Received: (from joe@localhost) by monk.via.net (8.6.11/8.6.12) id NAA12278; Thu, 19 Sep 1996 13:00:18 -0700 Date: Thu, 19 Sep 1996 13:00:18 -0700 From: Joe McGuckin Message-Id: <199609192000.NAA12278@monk.via.net> To: dave@persprog.com Subject: Re: DEC PCI CHIP QUESTION Cc: hardware@freebsd.org X-Sun-Charset: US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > From: "Rodney W. Grimes" > > We just bought an ethernet switch that can configure it's ports as full > > duplex. > > And so did I... :-) > > Which one did you get? I just love new toys! ====================================== When philosophy conflicts with reality, choose reality. Dave Alderman -- dave@persprog.com ====================================== ----- End Included Message ----- We got the USR (formerly AmberWave?) etherswitch. PROS: Inexpensive buyin: Ports come on plug-in cards. So we started out with 8 10-base-t ports. Fiber, 10-base-2 and 10-base-100 cards are available also. CONS: The unit is not as compact as some of the others we've looked at (e.g. Linkswitch 1000). For some of our POPs where leased rack space is at a premium we may go with a 3com. On our network here at the office, we saw ping times to a neighboring network go from 150ms to 50ms or below. We have a heavily loaded web server being fed from here and collisions of this network are a problem. We put one at another POP that has problems. We saw some improvement, but not as dramatic. Out conclusion was that although collisions a a factor there the real problem is that we've run out of bandwidth. These boxes can't perform miracles. From owner-freebsd-hardware Thu Sep 19 15:05:23 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id PAA16205 for hardware-outgoing; Thu, 19 Sep 1996 15:05:23 -0700 (PDT) Received: from lserver.infoworld.com (root@lserver.infoworld.com [192.216.48.4]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id PAA16177; Thu, 19 Sep 1996 15:05:19 -0700 (PDT) Received: from ccgate.infoworld.com (ccgate.infoworld.com [192.216.49.101]) by lserver.infoworld.com (8.7.5/8.7.3) with SMTP id PAA03345; Thu, 19 Sep 1996 15:04:42 -0700 (PDT) From: BRETT_GLASS@infoworld.com Received: from ccMail by ccgate.infoworld.com (SMTPLINK V2.11) id AA843170493; Thu, 19 Sep 96 03:49:38 PST Date: Thu, 19 Sep 96 03:49:38 PST Message-Id: <9608198431.AA843170493@ccgate.infoworld.com> To: Nate Williams Cc: ahill@interconnect.com.au, qusetions@freebsd.org, hardware@freebsd.org Subject: Re: Adaptec Parallel to SCSI converter Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > I'm pretty sure Adaptec's model is *NOT* the trantor model. I'd be surprised. Adaptec acquired Trantor, and the adapter looks absolutely identical to what Trantor sold. From the look of it, they just changed the decal. --Brett From owner-freebsd-hardware Thu Sep 19 19:43:10 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id TAA14398 for hardware-outgoing; Thu, 19 Sep 1996 19:43:10 -0700 (PDT) Received: from wong.rogerswave.ca (a17b32.rogerswave.ca [204.92.17.32]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id TAA14351 for ; Thu, 19 Sep 1996 19:43:03 -0700 (PDT) Received: (from wong@localhost) by wong.rogerswave.ca (8.7.5/8.7.3) id WAA00485; Thu, 19 Sep 1996 22:30:28 -0400 (EDT) Date: Thu, 19 Sep 1996 22:30:27 -0400 (EDT) From: Ken Wong Reply-To: wong@rogerswave.ca To: "Rodney W. Grimes" cc: BRETT_GLASS@infoworld.com, hardware@FreeBSD.ORG Subject: Re: VIA Apollo chipset: Any experience yet? In-Reply-To: <199609180447.VAA01722@GndRsh.aac.dev.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Tue, 17 Sep 1996, Rodney W. Grimes wrote: > > Does anyone have experience with VIA's Apollo chipset, which is directly > > competitive with Intel's Natoma? > > No, but have you found a motherboard using this chipset? I have been > wanting to bring it in for evaluation but have not had the time to hunt > down a board using it. > First International Computer ( http://www.fic.com.tw ) is the VIA chipset and motherboard producer. PA-2005 motherboard seems to use VIA apollo. Ken From owner-freebsd-hardware Thu Sep 19 20:20:59 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id UAA01575 for hardware-outgoing; Thu, 19 Sep 1996 20:20:59 -0700 (PDT) Received: from po1.glue.umd.edu (po1.glue.umd.edu [129.2.128.44]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id UAA01550 for ; Thu, 19 Sep 1996 20:20:54 -0700 (PDT) Received: from skipper.eng.umd.edu (skipper.eng.umd.edu [129.2.103.24]) by po1.glue.umd.edu (8.7.5/8.7.3) with ESMTP id XAA19181; Thu, 19 Sep 1996 23:20:50 -0400 (EDT) Received: from localhost (chuckr@localhost) by skipper.eng.umd.edu (8.7.5/8.7.3) with SMTP id XAA11943; Thu, 19 Sep 1996 23:20:50 -0400 (EDT) X-Authentication-Warning: skipper.eng.umd.edu: chuckr owned process doing -bs Date: Thu, 19 Sep 1996 23:20:49 -0400 (EDT) From: Chuck Robey X-Sender: chuckr@skipper.eng.umd.edu To: wong@rogerswave.ca cc: "Rodney W. Grimes" , BRETT_GLASS@infoworld.com, hardware@FreeBSD.ORG Subject: Re: VIA Apollo chipset: Any experience yet? In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Thu, 19 Sep 1996, Ken Wong wrote: > > > On Tue, 17 Sep 1996, Rodney W. Grimes wrote: > > > > Does anyone have experience with VIA's Apollo chipset, which is directly > > > competitive with Intel's Natoma? > > > > No, but have you found a motherboard using this chipset? I have been > > wanting to bring it in for evaluation but have not had the time to hunt > > down a board using it. > > > First International Computer ( http://www.fic.com.tw ) is the VIA chipset > and motherboard producer. PA-2005 motherboard seems to use VIA apollo. Yeah, that's available on the web from Tom's page, but where to get price/availability on these is the question. Like to see performance figures, using DIMMs too. BTW, I _think_ the number is PA-6010. ----------------------------+----------------------------------------------- Chuck Robey | Interests include any kind of voice or data chuckr@eng.umd.edu | communications topic, C programming, and Unix. 9120 Edmonston Ct #302 | Greenbelt, MD 20770 | I run Journey2 and n3lxx, both FreeBSD (301) 220-2114 | version 2.2 current -- and great FUN! ----------------------------+----------------------------------------------- From owner-freebsd-hardware Fri Sep 20 04:20:34 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id EAA13585 for hardware-outgoing; Fri, 20 Sep 1996 04:20:34 -0700 (PDT) Received: from relay.philips.nl (ns.philips.nl [130.144.65.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id EAA13538 for ; Fri, 20 Sep 1996 04:20:25 -0700 (PDT) Received: (from smap@localhost) by relay.philips.nl (8.6.9/8.6.9-950414) id NAA22919 for ; Fri, 20 Sep 1996 13:19:57 +0200 Received: from unknown(192.26.173.32) by ns.philips.nl via smap (V1.3+ESMTP) with ESMTP id smanc6715; Fri Sep 20 12:45:03 1996 Received: from aonc01.nym.sc.philips.com (aonc01.nym.sc.philips.com [130.144.70.193]) by smtp.nl.cis.philips.com (8.6.10/8.6.10-0.9z-02May95) with ESMTP id KAA14091 for ; Fri, 20 Sep 1996 10:52:31 +0200 Received: from NLNMG01.nym.sc.philips.com (nlnmg01 [130.144.80.6]) by aonc01.nym.sc.philips.com (8.6.10/8.6.10-1.2a-960822) with ESMTP id KAA15122 for ; Fri, 20 Sep 1996 10:50:04 +0200 Received: from NLNMG01/MAILQUEUE by NLNMG01.nym.sc.philips.com (Mercury 1.21); 20 Sep 96 10:50:10 +0100 Received: from MAILQUEUE by NLNMG01 (Mercury 1.21); 20 Sep 96 10:50:01 +0100 From: "Kees Jan Koster" Organization: Philips Semiconductors Nijmegen To: hardware@freebsd.org Date: Fri, 20 Sep 1996 10:49:54 GMT+0100 Subject: lmbench results for AMD 5k86-P100 Reply-to: Kees.Koster@nym.sc.philips.com Priority: normal X-mailer: Pegasus Mail for Windows (v2.23) Message-ID: <2A363AB4B4F@NLNMG01.nym.sc.philips.com> Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk I did a little benchmarking on my machine, as Stefan requested (are you on this list?). I haven't had the time to do the bytebench yet. Maybe later. Machine: Exp8661 mainboard, 512kb PB cache, 32Mb EDO, AMD 5k86-P100 @ 100MHz (overclocking doesn't work :). Could someone shed some light on the 'bad MHz' messages below? It worries me a little, because I had some touble before. Unix worked like it always has: sweet as honey, and MS-DOS kept tripping over its feet: random hangs and crashes, missed sequences on the soundcard, etc. Both Unix and MS-DOS work, altough MS-DOS still feels kind'a fragile. Thanks in advance, Kees Jan Koster L M B E N C H 1 . 0 S U M M A R Y ------------------------------------ Processor, Processes - times in microseconds -------------------------------------------- Host OS Mhz Null Null Simple /bin/sh Mmap 2-proc 8-proc Syscall Process Process Process lat ctxsw ctxsw --------- ------------- ---- ------- ------- ------- ------- ---- ------ ------ LikeEver FreeBSD 2.1.5 100 6 3.8K 14.2K 24K 123 35 44 LikeEver. FreeBSD 2.1.5 100 6 3.9K 14.1K 26K 123 36 46 LikeEver. FreeBSD 2.1.5 100 6 3.9K 14.0K 24K 124 36 46 pentium Linux 1.1.54 91 3 3.3K 15.4K 49K 33 25 42 *Local* Communication latencies in microseconds ----------------------------------------------- Host OS Pipe UDP RPC/ TCP RPC/ UDP TCP --------- ------------- ------- ------- ------- ------- ------- LikeEver FreeBSD 2.1.5 101 204 421 251 568 LikeEver. FreeBSD 2.1.5 103 214 427 268 594 LikeEver. FreeBSD 2.1.5 103 208 430 260 579 pentium Linux 1.1.54 157 658 1030 1164 1591 *Local* Communication bandwidths in megabytes/second ---------------------------------------------------- Host OS Pipe TCP File Mmap Bcopy Bcopy Mem Mem reread reread (libc) (hand) read write -------- ------------- ---- ---- ------ ------ ------ ------ ---- ----- LikeEver FreeBSD 2.1.5 14 9.6 23.1 58.6 29 28 81 42 LikeEver FreeBSD 2.1.5 14 9.6 23.1 57.7 29 28 81 42 LikeEver FreeBSD 2.1.5 14 9.7 23.1 58.4 29 28 81 42 pentium Linux 1.1.54 13 2.4 9.8 4.7 18 18 48 32 Memory latencies in nanoseconds (WARNING - may not be correct, check graphs) -------------------------------------------- Host OS Mhz L1 $ L2 $ Main mem TLB Guesses --------- ------------- --- ---- ---- -------- --- ------- LikeEver FreeBSD 2.1.5 100 - - - - Bad mhz? LikeEver. FreeBSD 2.1.5 100 - - - - Bad mhz? LikeEver. FreeBSD 2.1.5 100 - - - - Bad mhz? pentium Linux 1.1.54 90 11 294 439 1254 L M B E N C H 1 . 0 S U M M A R Y ------------------------------------ Comparison to best of the breed ------------------------------- (Best numbers are starred, i.e., *123) Processor, Processes - factor slower than the best -------------------------------------------------- Host OS Mhz Null Null Simple /bin/sh Mmap 2-proc 8-proc Syscall Process Process Process lat ctxsw ctxsw --------- ------------- ---- ------- ------- ------- ------- ---- ------ ------ LikeEver FreeBSD 2.1.5 100 2.0 1.9 2.5 1.4 3.7 1.8 1.5 LikeEver. FreeBSD 2.1.5 100 2.0 2.0 2.5 1.6 3.7 1.8 1.6 LikeEver. FreeBSD 2.1.5 100 2.0 2.0 2.5 1.4 3.8 1.8 1.6 pentium Linux 1.1.54 91 *3 1.7 2.7 3.0 *33 1.2 1.4 *Local* Communication latencies - factor slower than the best ------------------------------------------------------------- Host OS Pipe UDP RPC/ TCP RPC/ UDP TCP --------- ------------- ------- ------- ------- ------- ------- LikeEver FreeBSD 2.1.5 *101 *204 *421 *251 *568 LikeEver. FreeBSD 2.1.5 1.0 1.0 1.0 1.1 1.0 LikeEver. FreeBSD 2.1.5 1.0 1.0 1.0 1.0 1.0 pentium Linux 1.1.54 1.6 3.2 2.4 4.6 2.8 *Local* Communication bandwidths - percentage of the best --------------------------------------------------------- Host OS Pipe TCP File Mmap Bcopy Bcopy Mem Mem reread reread (libc) (hand) read write --------- ------------- ---- ---- ------ ------ ------ ------ ---- ----- LikeEver FreeBSD 2.1.5 36% 27% 30% 93% 35% 23% 82% 25% LikeEver. FreeBSD 2.1.5 36% 27% 30% 91% 35% 23% 82% 25% LikeEver. FreeBSD 2.1.5 35% 27% 30% 92% 35% 23% 82% 25% pentium Linux 1.1.54 32% 6% 12% 7% 22% 14% 48% 19% Memory latencies in nanoseconds - factor slower than the best (WARNING - may not be correct, check graphs) ------------------------------------------------------------- Host OS Mhz L1 $ L2 $ Main mem TLB Guesses --------- ------------- --- ---- ---- -------- --- ------- LikeEver FreeBSD 2.1.5 100 - - - - Bad mhz? LikeEver. FreeBSD 2.1.5 100 - - - - Bad mhz? LikeEver. FreeBSD 2.1.5 100 - - - - Bad mhz? -------------------------------------------v- Kees Jan Koster tel. NL-24-3555870 Hatertseweg 468 6533 GV Nijmegen Thi*&@s_sIg*nATure m(&#$@ay-aPp@#*ear gAr(&bled_to-*$M%ailba$rf(tm)_im*&$paired --------------------------------------------- From owner-freebsd-hardware Fri Sep 20 18:41:43 1996 Return-Path: owner-hardware Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA19199 for hardware-outgoing; Fri, 20 Sep 1996 18:41:43 -0700 (PDT) Received: from aeffle.Stanford.EDU (sequence.Stanford.EDU [171.65.76.7]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id SAA19043 for ; Fri, 20 Sep 1996 18:41:28 -0700 (PDT) Received: (from hlew@localhost) by aeffle.Stanford.EDU (8.6.10/8.6.6) id SAA04797; Fri, 20 Sep 1996 18:38:36 -0700 Date: Fri, 20 Sep 1996 18:38:35 -0700 (PDT) From: Howard Lew To: BRETT_GLASS@infoworld.com cc: hardware@freebsd.org Subject: Re: VIA Apollo chipset: Any experience yet? In-Reply-To: <9608178430.AA843019634@ccgate.infoworld.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hardware@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Tue, 17 Sep 1996 BRETT_GLASS@infoworld.com wrote: > Does anyone have experience with VIA's Apollo chipset, which is directly > competitive with Intel's Natoma? > We have seen the FreeTech F66 Motherboard with the Pentium Pro and it uses Intel's Natoma chipset and seems to offer very good blazing performance especially for Windows 95. It should do miracles for FreeBSD. I do not know about the VIA Apollo chipsets for Pentium Pros, but the ones for the Pentium/Cyrix/AMD are okay. ---- || Shoppers Network BEST PRICES, FULLY x86 COMPATIBLE & FAST!!! || PO BOX 16627 Cyrix 686s now available! || San Francisco, CA 94116 Email - info@shoppersnet.com | ------------------------------> WWW - http://www2.shoppersnet.com -------------------------------> WWW - http://www.shoppersnet.com/shopping