* Ingo Molnar [off-list ref] wrote:

* Gregory Haskins [off-list ref] wrote:

quoted

I may have found the issue: It looks like the hunk that initially 
disables interrupts in load_balance_newidle() was inadvertently 
applied to load_balance() instead during the merge to linux-tip.  If 
you fold the following patch into my original patch, it should set 
things right again.

ah, sorry - indeed! I've reactivated your patch and i'm testing it 
now.

-tip testing found that it still hangs at:

 Intel machine check architecture supported.
 Intel machine check reporting enabled on CPU#1.
 x86 PAT enabled: cpu 1, old 0x7040600070406, new 0x7010600070106
 CPU1: AMD Athlon(tm) 64 X2 Dual Core Processor 3800+ stepping 02
 Brought up 2 CPUs
 Total of 2 processors activated (8044.97 BogoMIPS).
 [...]

with this config:

  http://redhat.com/~mingo/misc/config-Thu_Jul__3_16_49_53_CEST_2008.bad

on 3 separate test-systems.

I've again reverted both your fixup and the original commit. I've pushed 
out the failing tree to the tmp.sched/devel.fe6149f5e82 -tip branch, you 
should be able to reproduce it.

	Ingo