Re: what does this mean?
On Mon, Sep 09, 2002 at 04:44:07PM -0700, Terry Lambert wrote: It's also a possible message, if you have a serial port disabled in the BIOS, but the hardware probe finds the hardware there, because the BIOS is merely advisory, and you have not disable PnP OS in the BIOS. Something along these lines occured on my notebook in response to a kernel configuraton entry for the second serial port on my notebook. While the port appears to be advertised, it doesn't actually seem to exist. -- christian zander [EMAIL PROTECTED] To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
bge problems (was: gigabit NIC of choice?)
Hi, What's the gigabit ethernet NIC of choice these days? (I've had good experiences with the NetGear G620T, but apparently this card is no longer being sold.) [ discussion followed ] just as this comes up, I have a question. Has anyone had experiences with the bge driver and related cards? We had some weird problems here lately: - bought two 3com 996-SX (fiber) cards and plugged them into ASUS A7M266-D boards with AMD Athlon 1.8GHz CPUs, - brought up FBSD 4.6 and tried some networking -- All packets (to and fro) that where bigger than total IP length of 214 bytes were garbled. To be more specific, it seemed to us that some 8 byte regions haven't been copied correctly from the cards at some point when the packets were larger. (The boards worked fine with normal 100Mbit cards, BTW.) To make matters more interesting, we then put the (Gbit) cards into AMD-Duron-700MHz-Systems with 32bit bus only - as apposed to the A7M266-D which had a 64bit bus: -- The cards worked just fine with all sorts (and sizes) of packets, but performance was - surpise, surprise - limited to 0.25 Gbit. So it seems there is some problem with the bge driver/card/64bit bus. Does the scenario ring a bell to someone of you? Regards, Birger To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: gigabit NIC of choice?
On Fri, 6 Sep 2002, Terry Lambert wrote: Terry Lambert wrote: Dan Ellard wrote: What's the gigabit ethernet NIC of choice these days? (I've had good experiences with the NetGear G620T, but apparently this card is no longer being sold.) The Tigon II has the best performances, but that's because software people rewrote the firmware, instead of hardware engineers moonlighting as programmers. 8-) 8-). Is anyone still making cards with the Tigon II chipset? I'm not finding them for sale anywhere... Thanks, -Dan To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: gigabit NIC of choice?
Dan Ellard wrote: Terry Lambert wrote: Dan Ellard wrote: What's the gigabit ethernet NIC of choice these days? (I've had good experiences with the NetGear G620T, but apparently this card is no longer being sold.) The Tigon II has the best performances, but that's because software people rewrote the firmware, instead of hardware engineers moonlighting as programmers. 8-) 8-). Is anyone still making cards with the Tigon II chipset? I'm not finding them for sale anywhere... See Ken's post. You will basically have to buy them from stock from someone who has them on a shelf somewhere, or you will have to sign NDA and recreate the firmware work on another card. The Tigon III's are *significantly* cheaper, and don't have the firmware-download-each-time-the-IP-changes that the Tigon II driver has, so most people have switches to the Tigon III. I guess the next question is Anyone know a gigabit NIC that is currently in production, which has hack-friendly firmware?... -- Terry To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: PCMCIA questions: mapping attribute and common memory?
Warner, Thanks very much for your help. The driver appears to work perfectly. Expect a whole bunch of smartcard-related ports submissions shortly. BMS To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: PCMCIA questions: mapping attribute and common memory?
In message: [EMAIL PROTECTED] Bruce M Simpson [EMAIL PROTECTED] writes: : Thanks very much for your help. The driver appears to work perfectly. : Expect a whole bunch of smartcard-related ports submissions shortly. Cool! Often for things like this we'll put the driver into the tree (so it doesn't bit rot), and then have a bunch of ports... Warner To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: I climb the mountain seeking wisdom
Greg 'groggy' Lehey wrote: There will always be situations where the debugger can't catch the problem in time. Then it's up to you to guess and put a breakpoint just before it freezes; this can be an interative process. The method requiring the least thought is to single step over function calls until the system freezes. Then you know which function it happened in. Reboot, set a breakpoint in that function, and repeat. What is being a real bear on this one, is the fact that it is not my code that is generating the panic. I assume I'm doing something bad that some other part of the kernel finds objectionable. Makes it hard to know where to set the break point... Debugging hasn't changed much since 4.3BSD. True enough, but *what* I am debugging sure has changed. KLD for example did not exist the last time I did kernel programming. Debugging klds is a little more difficult. You need to use gdb's add-symbol-file command to get the symbols. There are some functions which help, but the good one hasn't been committed yet. Take a look at http://people.freebsd.org/~gallatin/gdbmods. I had found a refrence to the add-symbol-file, but had not tried it, mostly because I can't get a core file... guess I will have to look into the remote debugger. Now I want to do a kldunload and have the driver dettach, the MOD_UNLOAD is called, but the detach() is never called. What do I need to do to get the detach() to be called? Is there an opposite to BUS_ADD_CHILD()? I tried device_delete_child()... gave me a panic and no core and devclass_delete_driver()... returned an error (ENOENT, I think) Hmm, haven't had that particular problem, but my klds don't handle hardware. Have you looked at similar code in other drivers? Well, it turned out that this was a problem caused by the same root problem that was causing my panics in strange places. Once I tracked down my rogue pointer, things became much better behaved. OK, I admit it, I have been programming in Java for the last two years and it is taking my brain a while to adjust to pointers again :-) Moral of the story, don't stomp your device_t, not that I was doing it intentionaly... Now, for a more meaning of life, the universe and device drivers type set of question: For a static driver, we have the config flags that can be used to modify the drivers behaviour, is sysctl the equivalent for KLD modules? If so, should a person support both or are the config flags considered depricated? Is there any naming convention for the MIB or is _driver_._option_ acceptable? -stacy -- If they keep lowering education standards and raising the price of gasoline, there are going to be a lot of stupid people walking around. Stacy Millions [EMAIL PROTECTED] Millions Consulting Limited To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Dell 2650 SMP perf question
Hi All; I'm stumped at how little improvement using an SMP kernel gives in a Dell 2650. System is dual 2400 xeon processors, 2 GB ram. It's intended to be used as a database processor, among other things. A perl process that read and input file and updates simple records in a mysql database actually run much more slowly: processing ~2million records takes 817 seconds with SMP enabled and 262 seconds with it disabled. Simple things like some_program.pl some_big_file | another_program.pl seem to take full advantage of the second processor, but this system is supposed to run mysql. Hyperthreading is turned off, I believe. There aren't any hyperthreading swithes in the bios I could find, but the logical processor option is turned off. Clues why SMP is so much slower very welcome indeed. --- David Nitty Gritty details: FreeBSD is 4.7prerelease, cvsupped 9/9/02. Dmesg output: Copyright (c) 1992-2002 The FreeBSD Project. Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 1994 The Regents of the University of California. All rights reserved. FreeBSD 4.7-PRERELEASE #0: Mon Sep 9 21:23:39 GMT 2002 root@:/usr/src/sys/compile/DBSMP Timecounter i8254 frequency 1193182 Hz CPU: Pentium 4 (2392.26-MHz 686-class CPU) Origin = GenuineIntel Id = 0xf24 Stepping = 4 Features=0x3febfbffFPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,M MX,FXSR,SSE,SSE2,SS,b28,ACC real memory = 2147418112 (2097088K bytes) avail memory = 2088226816 (2039284K bytes) Changing APIC ID for IO APIC #0 from 0 to 3 on chip Changing APIC ID for IO APIC #1 from 0 to 4 on chip Changing APIC ID for IO APIC #2 from 0 to 5 on chip Programming 16 pins in IOAPIC #0 IOAPIC #0 intpin 2 - irq 0 Programming 16 pins in IOAPIC #1 Programming 16 pins in IOAPIC #2 FreeBSD/SMP: Multiprocessor motherboard cpu0 (BSP): apic id: 0, version: 0x00050014, at 0xfee0 cpu1 (AP): apic id: 2, version: 0x00050014, at 0xfee0 io0 (APIC): apic id: 3, version: 0x000f0011, at 0xfec0 io2 (APIC): apic id: 5, version: 0x000f0011, at 0xfec02000 Preloaded elf kernel kernel at 0xc035a000. md0: Malloc disk Using $PIR table, 9 entries at 0xc00fc490 npx0: math processor on motherboard npx0: INT 16 interface pcib0: Host to PCI bridge on motherboard IOAPIC #1 intpin 3 - irq 2 IOAPIC #1 intpin 7 - irq 3 IOAPIC #1 intpin 11 - irq 5 pci0: PCI bus on pcib0 pci0: unknown card (vendor=0x1028, dev=0x000c) at 4.0 irq 2 pci0: unknown card (vendor=0x1028, dev=0x0008) at 4.1 irq 3 pci0: unknown card (vendor=0x1028, dev=0x000d) at 4.2 irq 5 pci0: ATI Mach64-GR graphics accelerator at 14.0 atapci0: ServerWorks CSB5 ATA100 controller port 0x8b0-0x8bf,0x8d8-0x8db,0x8d0-0x8d7,0x8c8-0x8cb,0x8c0-0x8c7 a t device 15.1 on pci0 ata0: at 0x1f0 irq 14 on atapci0 ata1: at 0x170 irq 15 on atapci0 pci0: OHCI USB controller at 15.2 irq 0 isab0: PCI to ISA bridge (vendor=1166 device=0225) at device 15.3 on pci0 isa0: ISA bus on isab0 pcib1: Host to PCI bridge on motherboard pci1: PCI bus on pcib1 pcib2: Host to PCI bridge on motherboard pci2: PCI bus on pcib2 pcib3: Host to PCI bridge on motherboard IOAPIC #1 intpin 12 - irq 7 IOAPIC #1 intpin 13 - irq 10 pci3: PCI bus on pcib3 bge0: Broadcom BCM5701 Gigabit Ethernet mem 0xfcf1-0xfcf1 irq 7 at device 6.0 on pci3 bge0: Ethernet address: 00:06:5b:8c:a5:62 miibus0: MII bus on bge0 brgphy0: BCM5701 10/100/1000baseTX PHY on miibus0 brgphy0: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, 1000baseTX, 1000baseTX-FDX, auto bge1: Broadcom BCM5701 Gigabit Ethernet mem 0xfcf0-0xfcf0 irq 10 at device 8.0 on pci3 bge1: Ethernet address: 00:06:5b:8c:a5:63 miibus1: MII bus on bge1 brgphy1: BCM5701 10/100/1000baseTX PHY on miibus1 brgphy1: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, 1000baseTX, 1000baseTX-FDX, auto pcib4: Host to PCI bridge on motherboard pci4: PCI bus on pcib4 pcib8: PCI to PCI bridge (vendor=8086 device=0309) at device 8.0 on pci4 IOAPIC #1 intpin 14 - irq 11 IOAPIC #1 intpin 15 - irq 13 pci5: PCI bus on pcib8 ahc_pci0: Adaptec aic7899 Ultra160 SCSI adapter port 0xcc00-0xccff mem 0xfccff000-0xfccf irq 11 at device 6.0 on pci5 aic7899: Ultra160 Wide Channel A, SCSI Id=7, 32/253 SCBs ahc_pci1: Adaptec aic7899 Ultra160 SCSI adapter port 0xc800-0xc8ff mem 0xfccfe000-0xfccfefff irq 13 at device 6.1 on pci5 aic7899: Ultra160 Wide Channel B, SCSI Id=7, 32/253 SCBs pcib5: Host to PCI bridge on motherboard pci6: PCI bus on pcib5 pcib6: Host to PCI bridge on motherboard pci7: PCI bus on pcib6 pcib7: Host to PCI bridge on motherboard pci8: PCI bus on pcib7 orm0: Option ROMs at iomem 0xc-0xc7fff,0xc8000-0xcdfff,0xec000-0xe on isa0 fdc0: NEC 72065B or clone at port 0x3f0-0x3f5,0x3f7 irq 6 drq 2 on isa0 fdc0: FIFO enabled, 8 bytes threshold fd0: 1440-KB 3.5 drive on fdc0 drive 0 atkbdc0: Keyboard controller (i8042) at port 0x60,0x64 on isa0 atkbd0: AT Keyboard irq 1 on atkbdc0 kbd0 at atkbd0 vga0: Generic ISA VGA at port
Re: Dell 2650 SMP perf question
On Tue, Sep 10, 2002 at 01:16:40PM -0400, [EMAIL PROTECTED] wrote: Hi All; I'm stumped at how little improvement using an SMP kernel gives in a Dell 2650. System is dual 2400 xeon processors, 2 GB ram. It's intended to be used as a database processor, among other things. A perl process that read and input file and updates simple records in a mysql database actually run much more slowly: processing ~2million records takes 817 seconds with SMP enabled and 262 seconds with it disabled. Simple things like some_program.pl some_big_file | another_program.pl seem to take full advantage of the second processor, but this system is supposed to run mysql. Hyperthreading is turned off, I believe. There aren't any hyperthreading swithes in the bios I could find, but the logical processor option is turned off. Clues why SMP is so much slower very welcome indeed. I believe at some point in the not too distant past their have been many performance problems for people using MySQL on FreeBSD. These problems where mostly related to MySQL's use of threads, I don't know if these problems have been fully resolved but it could be that SMP is aggrevating this. Watching what MySQL is doing with a trace might show some interesting results. I suppose you're running the lastest version of MySQL ? --- David Nitty Gritty details: FreeBSD is 4.7prerelease, cvsupped 9/9/02. Dmesg output: Copyright (c) 1992-2002 The FreeBSD Project. Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 1994 The Regents of the University of California. All rights reserved. FreeBSD 4.7-PRERELEASE #0: Mon Sep 9 21:23:39 GMT 2002 root@:/usr/src/sys/compile/DBSMP Timecounter i8254 frequency 1193182 Hz CPU: Pentium 4 (2392.26-MHz 686-class CPU) Origin = GenuineIntel Id = 0xf24 Stepping = 4 Features=0x3febfbffFPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,M MX,FXSR,SSE,SSE2,SS,b28,ACC real memory = 2147418112 (2097088K bytes) avail memory = 2088226816 (2039284K bytes) Changing APIC ID for IO APIC #0 from 0 to 3 on chip Changing APIC ID for IO APIC #1 from 0 to 4 on chip Changing APIC ID for IO APIC #2 from 0 to 5 on chip Programming 16 pins in IOAPIC #0 IOAPIC #0 intpin 2 - irq 0 Programming 16 pins in IOAPIC #1 Programming 16 pins in IOAPIC #2 FreeBSD/SMP: Multiprocessor motherboard cpu0 (BSP): apic id: 0, version: 0x00050014, at 0xfee0 cpu1 (AP): apic id: 2, version: 0x00050014, at 0xfee0 io0 (APIC): apic id: 3, version: 0x000f0011, at 0xfec0 io2 (APIC): apic id: 5, version: 0x000f0011, at 0xfec02000 Preloaded elf kernel kernel at 0xc035a000. md0: Malloc disk Using $PIR table, 9 entries at 0xc00fc490 npx0: math processor on motherboard npx0: INT 16 interface pcib0: Host to PCI bridge on motherboard IOAPIC #1 intpin 3 - irq 2 IOAPIC #1 intpin 7 - irq 3 IOAPIC #1 intpin 11 - irq 5 pci0: PCI bus on pcib0 pci0: unknown card (vendor=0x1028, dev=0x000c) at 4.0 irq 2 pci0: unknown card (vendor=0x1028, dev=0x0008) at 4.1 irq 3 pci0: unknown card (vendor=0x1028, dev=0x000d) at 4.2 irq 5 pci0: ATI Mach64-GR graphics accelerator at 14.0 atapci0: ServerWorks CSB5 ATA100 controller port 0x8b0-0x8bf,0x8d8-0x8db,0x8d0-0x8d7,0x8c8-0x8cb,0x8c0-0x8c7 a t device 15.1 on pci0 ata0: at 0x1f0 irq 14 on atapci0 ata1: at 0x170 irq 15 on atapci0 pci0: OHCI USB controller at 15.2 irq 0 isab0: PCI to ISA bridge (vendor=1166 device=0225) at device 15.3 on pci0 isa0: ISA bus on isab0 pcib1: Host to PCI bridge on motherboard pci1: PCI bus on pcib1 pcib2: Host to PCI bridge on motherboard pci2: PCI bus on pcib2 pcib3: Host to PCI bridge on motherboard IOAPIC #1 intpin 12 - irq 7 IOAPIC #1 intpin 13 - irq 10 pci3: PCI bus on pcib3 bge0: Broadcom BCM5701 Gigabit Ethernet mem 0xfcf1-0xfcf1 irq 7 at device 6.0 on pci3 bge0: Ethernet address: 00:06:5b:8c:a5:62 miibus0: MII bus on bge0 brgphy0: BCM5701 10/100/1000baseTX PHY on miibus0 brgphy0: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, 1000baseTX, 1000baseTX-FDX, auto bge1: Broadcom BCM5701 Gigabit Ethernet mem 0xfcf0-0xfcf0 irq 10 at device 8.0 on pci3 bge1: Ethernet address: 00:06:5b:8c:a5:63 miibus1: MII bus on bge1 brgphy1: BCM5701 10/100/1000baseTX PHY on miibus1 brgphy1: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, 1000baseTX, 1000baseTX-FDX, auto pcib4: Host to PCI bridge on motherboard pci4: PCI bus on pcib4 pcib8: PCI to PCI bridge (vendor=8086 device=0309) at device 8.0 on pci4 IOAPIC #1 intpin 14 - irq 11 IOAPIC #1 intpin 15 - irq 13 pci5: PCI bus on pcib8 ahc_pci0: Adaptec aic7899 Ultra160 SCSI adapter port 0xcc00-0xccff mem 0xfccff000-0xfccf irq 11 at device 6.0 on pci5 aic7899: Ultra160 Wide Channel A, SCSI Id=7, 32/253 SCBs ahc_pci1: Adaptec aic7899 Ultra160 SCSI adapter port 0xc800-0xc8ff mem 0xfccfe000-0xfccfefff irq 13 at device 6.1 on pci5 aic7899: Ultra160 Wide
Re: Dell 2650 SMP perf question
On Tue, 10 Sep 2002, Dominic Marks wrote: On Tue, Sep 10, 2002 at 01:16:40PM -0400, [EMAIL PROTECTED] wrote: Hi All; Hyperthreading is turned off, I believe. There aren't any hyperthreading swithes in the bios I could find, but the logical processor option is turned off. Clues why SMP is so much slower very welcome indeed. I believe at some point in the not too distant past their have been many performance problems for people using MySQL on FreeBSD. These problems where mostly related to MySQL's use of threads, I don't know if these problems have been fully resolved but it could be that SMP is aggrevating this. Watching what MySQL is doing with a trace might show some interesting results. Threads, mysql, and FreeBSD have been an unsocial group for a while, and running two processes that access the same tables does seem to slow things down a lot. Tracing it might show something of interest to someone, and I'm happy to do it if it will help. I wouldn't have a clue what I was looking at, and couldn't fix it if I did. I suppose you're running the lastest version of MySQL ? I've tried 4.03b, 4.02a, and 3.23.x, all show similar results:( Thanks, --- David To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: Dell 2650 SMP perf question
On Tue, Sep 10, 2002 at 01:30:23PM -0400, [EMAIL PROTECTED] wrote: On Tue, 10 Sep 2002, Dominic Marks wrote: On Tue, Sep 10, 2002 at 01:16:40PM -0400, [EMAIL PROTECTED] wrote: Hi All; Hyperthreading is turned off, I believe. There aren't any hyperthreading swithes in the bios I could find, but the logical processor option is turned off. Clues why SMP is so much slower very welcome indeed. I believe at some point in the not too distant past their have been many performance problems for people using MySQL on FreeBSD. These problems where mostly related to MySQL's use of threads, I don't know if these problems have been fully resolved but it could be that SMP is aggrevating this. Watching what MySQL is doing with a trace might show some interesting results. Threads, mysql, and FreeBSD have been an unsocial group for a while, and running two processes that access the same tables does seem to slow things down a lot. Tracing it might show something of interest to someone, and I'm happy to do it if it will help. I wouldn't have a clue what I was looking at, and couldn't fix it if I did. I suppose you're running the lastest version of MySQL ? I've tried 4.03b, 4.02a, and 3.23.x, all show similar results:( Thanks, --- David My very small pool of knowledge about MySQL+FreeBSD is now exhausted. It's not answering the question to ask if you see any better or worse results with different software. But you might like to try with another Database (Postgres ?) to see if the poor performance on SMP appears with it too. Good Luck, -- Dominic Marks Computer Politics Geek [work]::[npl.co.uk] dominic.marks at npl.co.uk [educ]::[umist.ac.uk] notyet-known at umist.ac.uk [home]::[btinternet] dominic_marks at btinternet.com To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
unsubscribe
To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: gigabit NIC of choice?
Terry Lambert writes: I guess the next question is Anyone know a gigabit NIC that is currently in production, which has hack-friendly firmware?... I think our products are the only game in town. http://www.myri.com/myrinet/product_list.html http://www.myri.com/myrinet/performance/index.html Yes, they are a little pricy, but quite hackable. And the link speed is twice gig ethers's (ie, 2Gb/sec full duplex, rather than 1Gb/sec full duplex). Sorry for the shameless plug ;) Drew To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: Dell 2650 SMP perf question
In the last episode (Sep 10), [EMAIL PROTECTED] said: I'm stumped at how little improvement using an SMP kernel gives in a Dell 2650. System is dual 2400 xeon processors, 2 GB ram. It's intended to be used as a database processor, among other things. A perl process that read and input file and updates simple records in a mysql database actually run much more slowly: processing ~2million records takes 817 seconds with SMP enabled and 262 seconds with it disabled. Simple things like some_program.pl some_big_file | another_program.pl seem to take full advantage of the second processor, but this system is supposed to run mysql. Mysql is a threaded database, and FreeBSD's pthreads are user-space. This means that mysql will only ever use one CPU, and disk I/O in one thread will block all other threads. You can try: * Rebuilding the mysql port with USE_LINUXTHREADS=yes. This will help lots if your mysql process is CPU-bound, and will help some if you are heavily I/O bound. * Switching to InnoDB tables, which cache much better than MyISAM tables so you are more likely to get your data from RAM instead of a blocking disk read. * Splitting your single perl program into multiple ones that hit the database simultaneously. You might be seeing a synchronization effect where your perl and mysql processes are competing for a SMP lock or something and the wrong one always wins. -- Dan Nelson [EMAIL PROTECTED] To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: gigabit NIC of choice?
Andrew Gallatin wrote: I guess the next question is Anyone know a gigabit NIC that is currently in production, which has hack-friendly firmware?... I think our products are the only game in town. http://www.myri.com/myrinet/product_list.html http://www.myri.com/myrinet/performance/index.html Yes, they are a little pricy, but quite hackable. And the link speed is twice gig ethers's (ie, 2Gb/sec full duplex, rather than 1Gb/sec full duplex). Sorry for the shameless plug ;) I'm a bit confused about these cards. Are they Gigabit ethernet cards, or are they 2 gigabit ethernet cards, which can only talk to other Myrinet cards, like ARCNet is not the same thing as ethernet? Are the FDX through a Cisco or Extreme Networks Gigabit switch, getting 2Gbit, and you are just defining 2G as total over the wire transfer rate in *both* directions, requiring that data go both ways (i.e. 2G is an aggregate number, but it's still standards compliant Gigabit)??? -- Terry To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: gigabit NIC of choice?
On Tue, 10 Sep 2002, Terry Lambert wrote: Andrew Gallatin wrote: I think our products are the only game in town. http://www.myri.com/myrinet/product_list.html http://www.myri.com/myrinet/performance/index.html I'm a bit confused about these cards. Terry, put down the pipe and visit the URLs. ;-) They're not Ethernet at all. They're Myrinet. They're 2 GB/s full duplex. Saying that they are 4GB/s would be misleading, but they are most definitely capable of 2GB/s+2GB/s if your bus can pump that much data. Myrinet is currently only useful in specialized applications because it can't be bridged onto a standard Ethernet network without running it through a computer (AFAIK). There are rumors afloat of Gigabit Ethernet linecards for Myrinet switch hardware on the horizon though. The technology is great and the folks at myri.com are some of the most competent and helpful support staff I've ever had the pleasure of dealing with. Oh yeah, and it's f'ing fast. Brandon D. Valentine -- http://www.geekpunk.net [EMAIL PROTECTED] ++[++-][++-].[+-][+-]+.+++..++ +.+[++-]++.+++..+++.--..+. To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: Dell 2650 SMP perf question
Another item we've done is to run multiple mysqld against the same filesystem tables. This requires you to have the filesystem locking enabled when you build mysql (but I think that's the default on FreeBSD). Also, you need to have multiple clients to connect to the multiple ports (or use a load-balancer of some sort). This allowed us to more fully utilize the I/O capacity of our RAID arrays. The primary issue, and it's a very big one, is that there are a number of SQL commands which are dangerous. OPTIMIZE, ALTER, DELETE without a WHERE clause, and generally any command which unlinks the existing table file and creates a new table file are dangerous. The problem is that the processes other than the one doing the command retain an open file descriptor on the original table file. The process running the command deletes that file, and creates a new one, and thus gets out of sync with the other processes. Later, scott On Tue, 10 Sep 2002, Dan Nelson wrote: In the last episode (Sep 10), [EMAIL PROTECTED] said: I'm stumped at how little improvement using an SMP kernel gives in a Dell 2650. System is dual 2400 xeon processors, 2 GB ram. It's intended to be used as a database processor, among other things. A perl process that read and input file and updates simple records in a mysql database actually run much more slowly: processing ~2million records takes 817 seconds with SMP enabled and 262 seconds with it disabled. Simple things like some_program.pl some_big_file | another_program.pl seem to take full advantage of the second processor, but this system is supposed to run mysql. Mysql is a threaded database, and FreeBSD's pthreads are user-space. This means that mysql will only ever use one CPU, and disk I/O in one thread will block all other threads. You can try: * Rebuilding the mysql port with USE_LINUXTHREADS=yes. This will help lots if your mysql process is CPU-bound, and will help some if you are heavily I/O bound. * Switching to InnoDB tables, which cache much better than MyISAM tables so you are more likely to get your data from RAM instead of a blocking disk read. * Splitting your single perl program into multiple ones that hit the database simultaneously. You might be seeing a synchronization effect where your perl and mysql processes are competing for a SMP lock or something and the wrong one always wins. To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: gigabit NIC of choice?
Brandon D. Valentine writes: running it through a computer (AFAIK). There are rumors afloat of Gigabit Ethernet linecards for Myrinet switch hardware on the horizon Slightly more than rumours -- http://www.myri.com/news/02512/slides/Seitz_roadmap.pdf http://www.myri.com/news/02512/slides/Seizovic_lanai.pdf Cheers, Drew To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: what does this mean?
In message: [EMAIL PROTECTED] Julian Elischer [EMAIL PROTECTED] writes: : sio1: configured irq 3 not in bitmap of probed irqs 0 : what on earth is this trying to tell me? : WHAT bitmap? Bitmap of probed irqs of '0' means that the driver put the card into an interrupt 'state', yet no interrupts were asserted. Warner To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: I climb the mountain seeking wisdom
In message: [EMAIL PROTECTED] Stacy Millions [EMAIL PROTECTED] writes: : For a static driver, we have the config flags that can be used to : modify the drivers behaviour, is sysctl the equivalent for KLD : modules? If so, should a person support both or are the config : flags considered depricated? Is there any naming convention for : the MIB or is _driver_._option_ acceptable? hints.name.unit#.parameter=string You can then use the full weight of the hints system to get these parameters on a per instance basis. hw.driver.parameter: String For global parameters. Warner To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: Dell 2650 SMP perf question
Random notes: On Tue, 10 Sep 2002 [EMAIL PROTECTED] wrote: Hyperthreading is turned off, I believe. There aren't any hyperthreading swithes in the bios I could find, but the logical processor option is turned off. HyperThreading is not supported on FreeBSD at current. It requires some ACPI work which hasn't happened yet. -- Doug White| FreeBSD: The Power to Serve [EMAIL PROTECTED] | www.FreeBSD.org To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: what does this mean?
On Tue, 10 Sep 2002, M. Warner Losh wrote: In message: [EMAIL PROTECTED] Julian Elischer [EMAIL PROTECTED] writes: : sio1: configured irq 3 not in bitmap of probed irqs 0 : what on earth is this trying to tell me? : WHAT bitmap? Bitmap of probed irqs of '0' means that the driver put the card into an interrupt 'state', yet no interrupts were asserted. thanks.. It appears it may be some 'Dummy' uart that is the front-end to a software modem of some sort. We were looking at a toshiba tecra 8100 and tryinmg to see if the modem was usable from BSD.. We've given up.. We think it may be some kind of Winmodem thingy. Warner To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: bge problems (was: gigabit NIC of choice?)
At 12:51 PM +0200 9/10/02, Birger Toedtmann wrote: So it seems there is some problem with the bge driver/card/64bit bus. Does the scenario ring a bell to someone of you? Yes, the bge driver in 4.6 is broken. John Polstra put fixes into -stable which will show up in 4.7. Mark To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: Dell 2650 SMP perf question
On Tue, 10 Sep 2002, Dan Nelson wrote: In the last episode (Sep 10), [EMAIL PROTECTED] said: I'm stumped at how little improvement using an SMP kernel gives in a Dell 2650. System is dual 2400 xeon processors, 2 GB ram. It's intended to be used as a database processor, among other things. A perl process that read and input file and updates simple records in a mysql database actually run much more slowly: processing ~2million records takes 817 seconds with SMP enabled and 262 seconds with it disabled. Simple things like some_program.pl some_big_file | another_program.pl seem to take full advantage of the second processor, but this system is supposed to run mysql. Mysql is a threaded database, and FreeBSD's pthreads are user-space. This means that mysql will only ever use one CPU, and disk I/O in one thread will block all other threads. I'd be happy to see perl running on one CPU and mysqld on the other. What I understand that mysql is thread based and that it will only run on one CPU at a time. What I don't understand is why it take 3.5 times as long to run the same job when I enable SMP. You can try: * Rebuilding the mysql port with USE_LINUXTHREADS=yes. This will help lots if your mysql process is CPU-bound, and will help some if you are heavily I/O bound. It's definately CPU bound. I'm building mysql independently of the ports, but I can figure out what that does. * Switching to InnoDB tables, which cache much better than MyISAM tables so you are more likely to get your data from RAM instead of a blocking disk read. That's not a problem - disk IO is on the order of tens per second, tops. * Splitting your single perl program into multiple ones that hit the database simultaneously. You might be seeing a synchronization effect where your perl and mysql processes are competing for a SMP lock or something and the wrong one always wins. Now that would be interesting. Running multiple tasks on a single CPU system always slowed things down, but it's worth a try:) Thanks for the suggestions! --- David To Unsubscribe: send mail to [EMAIL PROTECTED] with unsubscribe freebsd-hackers in the body of the message
Re: Updating bsd.cpu.mk (Re: -fomit-frame-pointer for the world build)
On Fri, Sep 06, 2002 at 06:08:23PM -0700, Maxime Henrion wrote:
Forgot that one. Here is an updated patch. I'm quite sure that on the
Intel side, only the pentium 4 have sse2, but I don't know if any AMD
chip supports it yet. The attached patch only adds it for p4's.
Athlon-{X,M}P support SSE[1]. AMD x86-64 will be the first AMD processor
to support SSE2.
To Unsubscribe: send mail to [EMAIL PROTECTED]
with unsubscribe freebsd-hackers in the body of the message
Re: Updating bsd.cpu.mk (Re: -fomit-frame-pointer for the world build)
On Fri, Sep 06, 2002 at 01:30:26PM -0700, Kris Kennaway wrote:
`-mcpu=CPU-TYPE'
Tune to CPU-TYPE everything applicable about the generated code,
except for the ABI and the set of available instructions. The
choices for CPU-TYPE are `i386', `i486', `i586', `i686',
`pentium', `pentium-mmx', `pentiumpro', `pentium2', `pentium3',
`pentium4', `k6', `k6-2', `k6-3', `athlon', `athlon-tbird',
`athlon-4', `athlon-xp' and `athlon-mp'.
You can also add -msse, -msse2, -m3dnow to use those extensions. It would
appear that our bsd.cpu.mk file is out of date and is missing the newer
cpu types.
How about the following patch (I've only tested 'pentium3'):
I'd like to commit these Athlon changes. I find this much easier to
understand.
Index: bsd.cpu.mk
===
RCS file: /home/ncvs/src/share/mk/bsd.cpu.mk,v
retrieving revision 1.18
diff -u -r1.18 bsd.cpu.mk
--- bsd.cpu.mk 7 Sep 2002 01:26:10 - 1.18
+++ bsd.cpu.mk 8 Sep 2002 23:25:51 -
@@ -42,16 +42,8 @@
# http://gcc.gnu.org/onlinedocs/gcc/RS-6000-and-PowerPC-Options.html
. if ${MACHINE_ARCH} == i386
-. if ${CPUTYPE} == athlon-mp
-_CPUCFLAGS = -march=athlon-mp
-. elif ${CPUTYPE} == athlon-xp
-_CPUCFLAGS = -march=athlon-xp
-. elif ${CPUTYPE} == athlon-4
-_CPUCFLAGS = -march=athlon-4
-. elif ${CPUTYPE} == athlon-tbird
-_CPUCFLAGS = -march=athlon-tbird
-. elif ${CPUTYPE} == athlon
-_CPUCFLAGS = -march=athlon
+. if ${CPUTYPE} == athlon-mp || ${CPUTYPE} == athlon-xp || ${CPUTYPE} ==
+athlon-4 || ${CPUTYPE} == athlon
+_CPUCFLAGS = -march=${CPUTYPE}
. elif ${CPUTYPE} == k6-3
_CPUCFLAGS = -march=k6-3
. elif ${CPUTYPE} == k6-2
@@ -105,16 +97,10 @@
# presence of a CPU feature.
.if ${MACHINE_ARCH} == i386
-. if ${CPUTYPE} == athlon-mp
-MACHINE_CPU = sse k7 3dnow mmx k6 k5 i586 i486 i386
-. elif ${CPUTYPE} == athlon-xp
-MACHINE_CPU = sse k7 3dnow mmx k6 k5 i586 i486 i386
-. elif ${CPUTYPE} == athlon-4
-MACHINE_CPU = sse k7 3dnow mmx k6 k5 i586 i486 i386
-. elif ${CPUTYPE} == athlon-tbird
-MACHINE_CPU = k7 3dnow mmx k6 k5 i586 i486 i386
-. elif ${CPUTYPE} == athlon
-MACHINE_CPU = k7 3dnow mmx k6 k5 i586 i486 i386
+. if ${CPUTYPE} == athlon-mp || ${CPUTYPE} == athlon-xp || ${CPUTYPE} ==
+athlon-4
+MACHINE_CPU = athlon-xp k7 3dnow see mmx k6 k5 i586 i486 i386
+. elif ${CPUTYPE} == athlon || ${CPUTYPE} == athlon-tbird
+MACHINE_CPU = athlon k7 3dnow mmx k6 k5 i586 i486 i386
. elif ${CPUTYPE} == k6-3
MACHINE_CPU = 3dnow mmx k6 k5 i586 i486 i386
. elif ${CPUTYPE} == k6-2
To Unsubscribe: send mail to [EMAIL PROTECTED]
with unsubscribe freebsd-hackers in the body of the message
