Messages in this thread | | | Date | Sat, 30 Aug 2008 17:30:00 +0200 | From | "Vegard Nossum" <> | Subject | Re: BUG: kernel-2.6.27-rc5: soft lockup - CPU#X stuck for 61s! |
| |
On Sat, Aug 30, 2008 at 2:46 PM, Thomas Backlund <tmb@mandriva.org> wrote: > Hi, (please cc me as I'm not subscribed) > > thought I would post this right now, I'll try to reproduce it with vanilla > 2.6.27-rc5 as soon as the buildhost is back up... > > (vanilla 2.6.27-rc5 x86_64 also locked up my laptop wich is a > Core2 Duo T8300 during kernel build with make -j3, but > I dont have any logs of that yet) > > Kernel: 2.6.27-rc5 + Mandriva patches > Config: > http://svn.mandriva.com/cgi-bin/viewvc.cgi/packages/cooker/kernel/branches/rebase-to-2.6.27/PATCHES/configs/x86_64.config?revision=276760&view=markup > Arch: x86_64 > > System: Intel Quad Core Q9300 > > getting this with netconsole while building kernel rpms with make -j5:
Hi,
I tried your recipe. Well, not exactly. But I also got this during a kernel build. Notice that the kernel version is a clean v2.6.27-rc5 (i.e. latest Linus -git):
BUG: soft lockup - CPU#1 stuck for 61s! [swapper:0] irq event stamp: 3585444 hardirqs last enabled at (3585443): [<c015927b>] trace_hardirqs_on+0xb/0x10 hardirqs last disabled at (3585444): [<c0290614>] trace_hardirqs_off_thunk+0xc/8 softirqs last enabled at (3585438): [<c0139fb1>] __do_softirq+0xe1/0x100 softirqs last disabled at (3585427): [<c013a075>] do_softirq+0xa5/0xb0
Pid: 0, comm: swapper Not tainted (2.6.27-rc5-00006-gbef69ea #3) EIP: 0060:[<c011eb55>] EFLAGS: 00000202 CPU: 1 EIP is at native_safe_halt+0x5/0x10 EAX: 0036b5a3 EBX: c2161b80 ECX: 00000000 EDX: 00000000 ESI: 00000001 EDI: c090fb80 EBP: f7855f80 ESP: f7855f80 DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 CR0: 8005003b CR2: 0807a0b0 CR3: 3695d000 CR4: 000006d0 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: ffff0ff0 DR7: 00000400 [<c010ad80>] default_idle+0x50/0x70 [<c01029c8>] cpu_idle+0x68/0x130 [<c059e120>] start_secondary+0x160/0x1c0 =======================
c011eb50 <native_safe_halt>: c011eb50: 55 push %ebp c011eb51: 89 e5 mov %esp,%ebp c011eb53: fb sti c011eb54: f4 hlt c011eb55: 5d pop %ebp c011eb56: c3 ret c011eb57: 89 f6 mov %esi,%esi c011eb59: 8d bc 27 00 00 00 00 lea 0x0(%edi),%edi
...there's not many clues here as to what went wrong. Curious.
(Yes, I played with CPU hotplug and hibernate as well.)
Vegard
-- "The animistic metaphor of the bug that maliciously sneaked in while the programmer was not looking is intellectually dishonest as it disguises that the error is the programmer's own creation." -- E. W. Dijkstra, EWD1036
| |