Messages in this thread | | | Date | Sat, 15 Apr 2006 16:28:23 -0700 | From | "Martin J. Bligh" <> | Subject | Re: Clear performance regression on reaim7 in 2.6.15-git6 |
| |
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@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |