Mailing List Archive

Temporary freeze in 2.2.5 on SMP box.
My linux box just froze for ~ 15 seconds. I was in X. The pointer
froze, the capslock key didn't toggle the capslock light, etc... It
seems to be fine now that it's warmed up again. The logs showed:
Sep 2 11:46:41 blinky kernel: stuck on TLB IPI wait (CPU#0)
Sep 2 11:46:41 blinky last message repeated 23 times
This is in kernel 2.2.5 from a stock RH6.0 setup.
Is this a known bug? If not, should I start running a more recent
kernel (possibly with debug mods) & see if it happens again? If so,
has it been fixed in a newer kernel?
Here's some additional info (from /var/log/messages during bootup):
Aug 31 10:56:02 blinky kernel: Linux version 2.2.5-15smp (root@porky.devel.redhat.com) (gcc version egcs-2.91.66 19990314/Linux (egc
s-1.1.2 release)) #1 SMP Mon Apr 19 22:43:28 EDT 1999
Aug 31 10:56:02 blinky kernel: Intel MultiProcessor Specification v1.1
Aug 31 10:56:02 blinky kernel: Virtual Wire compatibility mode.
Aug 31 10:56:02 blinky kernel: OEM ID: OEM00000 Product ID: PROD00000000 APIC at: 0xFEE00000
Aug 31 10:56:02 blinky kernel: Processor #1 Pentium(tm) Pro APIC version 17
Aug 31 10:56:02 blinky kernel: Processor #0 Pentium(tm) Pro APIC version 17
Aug 31 10:56:02 blinky kernel: I/O APIC #2 Version 17 at 0xFEC00000.
Aug 31 10:56:02 blinky kernel: Processors: 2
Aug 31 10:56:02 blinky kernel: mapped APIC to ffffe000 (fee00000)
Aug 31 10:56:02 blinky kernel: mapped IOAPIC to ffffd000 (fec00000)
Aug 31 10:56:02 blinky kernel: Detected 501149595 Hz processor.
Aug 31 10:56:02 blinky kernel: Console: colour VGA+ 80x25
Aug 31 10:56:02 blinky kernel: Calibrating delay loop... 499.71 BogoMIPS
Aug 31 10:56:02 blinky kernel: Memory: 127548k/131008k available (1044k kernel code, 416k reserved, 1608k data, 68k init)
Aug 31 10:56:02 blinky kernel: VFS: Diskquotas version dquot_6.4.0 initialized
Aug 31 10:56:02 blinky kernel: Checking 386/387 coupling... OK, FPU using exception 16 error reporting.
Aug 31 10:56:02 blinky kernel: Checking 'hlt' instruction... OK.
Aug 31 10:56:02 blinky kernel: POSIX conformance testing by UNIFIX
Aug 31 10:56:02 blinky kernel: mtrr: v1.26 (19981001) Richard Gooch (rgooch@atnf.csiro.au)
Aug 31 10:56:02 blinky kernel: per-CPU timeslice cutoff: 100.02 usecs.
Aug 31 10:56:02 blinky kernel: CPU1: Intel 00/07 stepping 02
Aug 31 10:56:02 blinky kernel: calibrating APIC timer ...
Aug 31 10:56:02 blinky kernel: ..... CPU clock speed is 501.1667 MHz.
Aug 31 10:56:02 blinky kernel: ..... system bus clock speed is 100.2331 MHz.
Aug 31 10:56:02 blinky kernel: Booting processor 0 eip 2000
Aug 31 10:56:02 blinky kernel: Calibrating delay loop... 499.71 BogoMIPS
Aug 31 10:56:02 blinky kernel: OK.
Aug 31 10:56:02 blinky kernel: CPU0: Intel 00/07 stepping 02
Aug 31 10:56:02 blinky kernel: Total of 2 processors activated (999.42 BogoMIPS).
Aug 31 10:56:02 blinky kernel: enabling symmetric IO mode... ...done.
Aug 31 10:56:02 blinky kernel: ENABLING IO-APIC IRQs
Aug 31 10:56:02 blinky kernel: init IO_APIC IRQs
Aug 31 10:56:02 blinky kernel: IO-APIC pin 0, 5, 10, 11, 13, 18, 20, 21, 22, 23 not connected.
Aug 31 10:56:02 blinky kernel: number of MP IRQ sources: 15.
Aug 31 10:56:02 blinky kernel: number of IO-APIC registers: 24.
Aug 31 10:56:02 blinky kernel: testing the IO APIC.......................
Aug 31 10:56:02 blinky kernel: .... register #00: 02000000
Aug 31 10:56:02 blinky kernel: ....... : physical APIC id: 02
Aug 31 10:56:02 blinky kernel: .... register #01: 00170011
Aug 31 10:56:02 blinky kernel: ....... : max redirection entries: 0017
Aug 31 10:56:02 blinky kernel: ....... : IO APIC version: 0011
Aug 31 10:56:02 blinky kernel: .... register #02: 00000000
Aug 31 10:56:02 blinky kernel: ....... : arbitration: 00
Aug 31 10:56:02 blinky kernel: .... IRQ redirection table:
Aug 31 10:56:02 blinky kernel: NR Log Phy Mask Trig IRR Pol Stat Dest Deli Vect:
Aug 31 10:56:02 blinky kernel: 00 000 00 1 0 0 0 0 0 0 00
Aug 31 10:56:02 blinky kernel: 01 000 00 0 0 0 0 0 1 1 59
Aug 31 10:56:02 blinky kernel: 02 0FF 0F 0 0 0 0 0 1 1 51
Aug 31 10:56:02 blinky kernel: 03 000 00 0 0 0 0 0 1 1 61
Aug 31 10:56:02 blinky kernel: 04 000 00 0 0 0 0 0 1 1 69
Aug 31 10:56:02 blinky kernel: 05 000 00 1 0 0 0 0 0 0 00
Aug 31 10:56:02 blinky kernel: 06 000 00 0 0 0 0 0 1 1 71
Aug 31 10:56:02 blinky kernel: 07 000 00 0 0 0 0 0 1 1 79
Aug 31 10:56:02 blinky kernel: 08 000 00 0 0 0 0 0 1 1 81
Aug 31 10:56:02 blinky kernel: 09 000 00 0 0 0 0 0 1 1 89
Aug 31 10:56:02 blinky kernel: 0a 000 00 1 0 0 0 0 0 0 00
Aug 31 10:56:02 blinky kernel: 0b 000 00 1 0 0 0 0 0 0 00
Aug 31 10:56:02 blinky atd: atd startup succeeded
Aug 31 10:56:02 blinky kernel: 0c 000 00 0 0 0 0 0 1 1 91
Aug 31 10:56:02 blinky kernel: 0d 000 00 1 0 0 0 0 0 0 00
Aug 31 10:56:02 blinky kernel: 0e 000 00 0 0 0 0 0 1 1 99
Aug 31 10:56:02 blinky kernel: 0f 000 00 0 0 0 0 0 1 1 A1
Aug 31 10:56:02 blinky kernel: 10 0FF 0F 1 1 0 1 0 1 1 A9
Aug 31 10:56:02 blinky kernel: 11 0FF 0F 1 1 0 1 0 1 1 B1
Aug 31 10:56:02 blinky kernel: 12 000 00 1 0 0 0 0 0 0 00
Aug 31 10:56:02 blinky kernel: 13 0FF 0F 1 1 0 1 0 1 1 B9
Aug 31 10:56:02 blinky kernel: 14 000 00 1 0 0 0 0 0 0 00
Aug 31 10:56:02 blinky kernel: 15 000 00 1 0 0 0 0 0 0 00
Aug 31 10:56:02 blinky kernel: 16 000 00 1 0 0 0 0 0 0 00
Aug 31 10:56:02 blinky kernel: 17 000 00 1 0 0 0 0 0 0 00
Aug 31 10:56:02 blinky kernel: .................................... done.
Aug 31 10:56:02 blinky kernel: PCI: PCI BIOS revision 2.10 entry at 0xf0730
Aug 31 10:56:02 blinky kernel: PCI: Using configuration type 1
Aug 31 10:56:02 blinky kernel: PCI: Probing PCI hardware
Thanks,
Harvey Stein
Bloomberg LP
hjstein@bfr.co.il
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
Re: Temporary freeze in 2.2.5 on SMP box. [ In reply to ]
> Sep 2 11:46:41 blinky kernel: stuck on TLB IPI wait (CPU#0)
> Sep 2 11:46:41 blinky last message repeated 23 times
> This is in kernel 2.2.5 from a stock RH6.0 setup.
I could be very wrong but that usually happens when one of the CPUs "falls off
the bus", be it improper cooling, overclocking, hardware failure.
--
Which is worse, ignorance or apathy? Who knows? Who cares?
I'm not a perfectionist, but I'm working on it.
Buckcherry in 10 years: "I love the Rogaine. I love the Rogaine."
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/