Re: [patch] Real-Time Preemption, -RT-2.6.12-rc6-V0.7.48-00

[K.R. Foley]

Ingo Molnar wrote:
> * Ingo Molnar <mingo@xxxxxxx> 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@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/