On Saturday 17 October 2009, Frans Pop wrote:

On Saturday 17 October 2009, Mel Gorman wrote:

quoted

Frans, you reported that both patches in combination reduced the
number of failures. Was it in fact just the kswapd change that made
the difference?

I will retest both patches (as I already mailed you privately
yesterday), but not today. The improvement with the combination was
real, but I'm not sure which patch is the reason. I think the second,
but I need to verify.

I've done another 30 boots or so today, mainly in the "akpm" merge, and
I've found new patterns that will help me nail down the regression. But
ATM I can't see straight anymore, so it will have to wait until
tomorrow.

Again sorry for the delay, but I needed to retest these with various 
kernels as the results were inconclusive. AFAICT neither of the two 
patches makes a significant difference for my test case.

Not sure if my initial test was broken or that it was just a case where the 
timings worked out favorably.

Cheers,
FJP

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>