Re: Clear performance regression on reaim7 in 2.6.15-git6

From: Martin J. Bligh
Date: Sat Apr 15 2006 - 19:28:48 EST


Martin J. Bligh wrote:
It's still broken in 17-rc1 ... will send you a patch in a sec.



I already have kconfigdebug-set-debug_mutex-to-off-by-default.patch queued up.


OK. That explains why -mm2 bounced back at the end of this graph:
http://test.kernel.org/perf/reaim.moe.png

But ... it's still way below what 2.6.15 was. There's another thunk
down between 2.6.16 and 2.6.16-git18, AFAICS.

OK, I futzed with the graphs a bit. -git2 to -git3 definitely drops
off. I think -git6 to git7 does as well, though that's much more
difficult to discern amongst the noise. I'll take a look more.

Andy, if there's any way you could rerun all the -git ones on moe
with the CONFIG_DEBUG_MUTEXES stuff disabled, might be easier to see ...

M.
-
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/