Re: HEADSUP: Committing new interrupt code, tree will be broken
John Baldwin wrote: I'm committing the new i386 interrupt and SMP code, so buckle your seat belts. :) I'll be intentionally breaking the kernel build at the start and re-enable it with the last commit when I am done. Is this *only* for SMP systems, or will the interrupt code also affect UNIprocessor boxes (like my laptop)? I'm suspecting some interrupt loss here, so I might give this new code a spin around the block. /Eirik ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: HEADSUP: Committing new interrupt code, tree will be broken
On Mon, 3 Nov 2003, Scott Long wrote: > > My Dell PE1750 hangs up solid under network load. > > > > Its a serverworks of some recent variation, 2x2.4GHz xeons. BIOS A05. bge > > ethernet x2. Apachebench will mash it dead in a few seconds. > > > > Sam just discovered some locking problems in the IPv4 stack. Can you > update to his recent commit and retry? With the new interrupt routing > code, you can either get your interrupts or you can't. High load > should not be affected by it. (for the record) Tried turning off mpsafenet, no luck. Will try disabling ACPI tomorrow. I'm hoping its not some silly bge bug that happens to manifest only in -current. I ran some extensive load testing with this and another single-proc box on 4.9 without any issues, but thats obviously not directly comparable. -- Doug White| FreeBSD: The Power to Serve [EMAIL PROTECTED] | www.FreeBSD.org ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: HEADSUP: Committing new interrupt code, tree will be broken
On Mon, 3 Nov 2003, Doug White wrote:> On Mon, 3 Nov 2003, Peter Wemm wrote: > > > John Baldwin wrote: > > > > > > On 03-Nov-2003 John Baldwin wrote: > > > > I'm committing the new i386 interrupt and SMP code, so buckle your > > > > seat belts. :) I'll be intentionally breaking the kernel build at > > > > the start and re-enable it with the last commit when I am done. > > > > > > I've finished committing everything but am waiting for some kernel > > > compiles on virgin trees to finish to make sure I didn't miss anything. > > > The -current waters should be safe again though. > > My Dell PE1750 hangs up solid under network load. > > Its a serverworks of some recent variation, 2x2.4GHz xeons. BIOS A05. bge > ethernet x2. Apachebench will mash it dead in a few seconds. > Sam just discovered some locking problems in the IPv4 stack. Can you update to his recent commit and retry? With the new interrupt routing code, you can either get your interrupts or you can't. High load should not be affected by it. Scott ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: HEADSUP: Committing new interrupt code, tree will be broken
On Mon, 3 Nov 2003, Peter Wemm wrote: > John Baldwin wrote: > > > > On 03-Nov-2003 John Baldwin wrote: > > > I'm committing the new i386 interrupt and SMP code, so buckle your > > > seat belts. :) I'll be intentionally breaking the kernel build at > > > the start and re-enable it with the last commit when I am done. > > > > I've finished committing everything but am waiting for some kernel > > compiles on virgin trees to finish to make sure I didn't miss anything. > > The -current waters should be safe again though. My Dell PE1750 hangs up solid under network load. Its a serverworks of some recent variation, 2x2.4GHz xeons. BIOS A05. bge ethernet x2. Apachebench will mash it dead in a few seconds. -- Doug White| FreeBSD: The Power to Serve [EMAIL PROTECTED] | www.FreeBSD.org ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: HEADSUP: Committing new interrupt code, tree will be broken
John Baldwin wrote: > > On 03-Nov-2003 John Baldwin wrote: > > I'm committing the new i386 interrupt and SMP code, so buckle your > > seat belts. :) I'll be intentionally breaking the kernel build at > > the start and re-enable it with the last commit when I am done. > > I've finished committing everything but am waiting for some kernel > compiles on virgin trees to finish to make sure I didn't miss anything. > The -current waters should be safe again though. JFYI: ref5.freebsd.org updated ok (no MADT or mptable in bios) builder.freebsd.org updated ok (no MADT or mptable in bios) the quad xeon-550 at work updated fine.. multiple IO apics and all. (I had to make a PAE fix for i386/acpica/madt.c though) ... ACPI APIC Table: CPU: Pentium III/Pentium III Xeon/Celeron (549.44-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0x673 Stepping = 3 Features=0x387fbff real memory = 6442450944 (6144 MB) avail memory = 5828734976 (5558 MB) FreeBSD/SMP: Multiprocessor System Detected: 4 CPUs cpu0 (BSP): APIC ID: 3 cpu1 (AP): APIC ID: 0 cpu2 (AP): APIC ID: 1 cpu3 (AP): APIC ID: 2 ioapic0 irqs 0-15 on motherboard ioapic1 irqs 16-31 on motherboard ... Cheers, -Peter -- Peter Wemm - [EMAIL PROTECTED]; [EMAIL PROTECTED]; [EMAIL PROTECTED] "All of this is for nothing if we don't go to the stars" - JMS/B5 ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "[EMAIL PROTECTED]"
RE: HEADSUP: Committing new interrupt code, tree will be broken
On 03-Nov-2003 John Baldwin wrote: > > On 03-Nov-2003 John Baldwin wrote: >> I'm committing the new i386 interrupt and SMP code, so buckle your >> seat belts. :) I'll be intentionally breaking the kernel build at >> the start and re-enable it with the last commit when I am done. > > I've finished committing everything but am waiting for some kernel > compiles on virgin trees to finish to make sure I didn't miss anything. > The -current waters should be safe again though. My GENERIC build finished ok, so it should at least be workable for most people. By the way, if anyone has a machine with 8 or more CPUs (John Cagle, I know you are out there. :)) feel free to test the new code out and post a boot -v dmesg log to the smp@ list. Thanks. -- John Baldwin <[EMAIL PROTECTED]> <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "[EMAIL PROTECTED]"
RE: HEADSUP: Committing new interrupt code, tree will be broken
On 03-Nov-2003 John Baldwin wrote: > I'm committing the new i386 interrupt and SMP code, so buckle your > seat belts. :) I'll be intentionally breaking the kernel build at > the start and re-enable it with the last commit when I am done. I've finished committing everything but am waiting for some kernel compiles on virgin trees to finish to make sure I didn't miss anything. The -current waters should be safe again though. -- John Baldwin <[EMAIL PROTECTED]> <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "[EMAIL PROTECTED]"
HEADSUP: Committing new interrupt code, tree will be broken
I'm committing the new i386 interrupt and SMP code, so buckle your seat belts. :) I'll be intentionally breaking the kernel build at the start and re-enable it with the last commit when I am done. -- John Baldwin <[EMAIL PROTECTED]> <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "[EMAIL PROTECTED]"
