![]() | |||||||||||||
Messages in this thread |
Ingo Molnar wrote: > * Ingo Molnar <mingo@elte.hu> wrote: > > >>>There doesn't seem to be any actual lockups, just messages. I will try >>>disabling the above when I get home this evening. Can't get to the >>>system right now. >> >>i tweaked the softlockup detector in the last patch a bit (to fix >>false positives under very high loads), might have broken it on SMP. > > > yeah - found a bug that could explain the symptoms on your system. > Called softlockup_tick() from the global timer interrupt, instead of the > per-CPU timer interrupt. So on SMP the other CPUs would not see any > softlockup ticks at all, and would incorrectly report soft lockups. > This bug is fixed in the -48-36 patch i just uploaded. > > Ingo > Yes I noticed the softlockup_tick() in some stack traces that I generated with -48-35 last night. Just downloaded and starting to compile -48-36. Will report back the results. Also will turn of the CONFIG_DEBUG_RT_LOCKING_MODE mentioned in your previous mail. thanks. -- kr - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ | ||||||||||||
| Last update: 2005-06-17 14:17 [W:2.691 / U:0.250 seconds] ©2003-2008 Jasper Spaans | |||||||||||||