Messages in this thread | | | From | Raphael Manfredi <> | Subject | Re: memory tester and BP6 problems | Date | Fri, 10 Mar 2000 08:22:55 +0100 |
| |
Quoting John Newman: :Can anyone recommend a good app to stress test the memory in my :Linux box? I'm getting these strange lockups in a BP6 where :the box locks hard, usually emitting a constant beep when it's :locked. When I reboot it it usually doesn't come up for about :five minutes but instead makes a beep pattern that is alternating :a high and lower pitch beep continuously.
Funny you mention this, because it happened to me this morning for the first time in 6 months, with 2.2.14.
:usually stays up for anywhere from a day to a week. Not :overclocked, happens with any kernel config and I've got my ram :settings at the most conservative. Also, the temperature stays :anywhere from 29C - 34C on the CPU's and in the system as reported :by lm_sensors and looking at logs of the temps it is never overly :hot when it dies.
Dual Celeron config, not overclocked. I don't have lm_sensors installed, but when I rebooted I went to the BIOS and looked at the temperature. It was 50C, as usual (I have 2 fans on the Celerons, but no thermal glue, so I guess the heat does not dissipate properly--it's stable though).
I have put mem=288M in my loadlin paramerters, which is correct. I rebooted with mem=287M, and we'll see if I get new lockups.
It's not the first time I see those lockups, and they always happen when my machine is having many windows opened for a while (4,5 Netscape windows, VMWare running with 96 Mb configured, around 20 xterms).
Usually nothing in the logs, but this morning, I saw this (not on my SMP machine, but on a remote syslog) -- the SMP machine is called "nice", after the French town Nice, not the English adjective.
------ nice kernel: Unable to handle kernel NULL pointer dereference at nice kernel: current->tss.cr3 = 0d7e1000, %cr3 = 0d7e1000 nice kernel: *pde = 00000000 nice kernel: Oops: 0000 nice kernel: CPU: 1 nice kernel: EIP: 0010:[smp_call_function_interrupt+8/64] nice kernel: EFLAGS: 00013046 nice kernel: eax: 00000000 ebx: 0000006a ecx: 08259384 edx: 00000018 nice kernel: esi: 00000000 edi: 082fcdf0 ebp: bffff614 esp: cd793fbc nice kernel: ds: 0018 es: 0018 ss: 0018 nice kernel: Process vmware (pid: 22828, process nr: 68, stackpage=cd793000) nice kernel: Stack: 082fcdf0 c010ad5e 0000006a 08259384 08259384 00000000 082fcdf0 bffff614 nice kernel: 63c4be29 0000002b 0000002b ffffffff 080d10d1 00000023 00003246 bffff568 nice kernel: 0000002b nice kernel: Call Trace: [call_function_interrupt+26/32] nice kernel: Code: 8b 30 8b 58 04 8b 78 10 e8 ab fa ff ff 8b 15 cc a0 20 c0 8d nice kernel: PI wait (CPU#0) nice kernel: stuck on TLB IPI wait (CPU#0) ------
And that's it. The machine locked up, because I don't see any new indication of periodic cron jobs ("rmmod -a") being run on the machine past that date, on the syslog server.
It looks like a spinlock deadlock problem happened, after the initial oops.
Raphael
- 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/
| |