[PATCH 6/6] powerpc: Use lwsync for acquire barrier if CPU supports it

Benjamin Herrenschmidt benh at kernel.crashing.org
Tue Feb 16 15:19:03 EST 2010


On Mon, 2010-02-15 at 22:22 -0600, Olof Johansson wrote:
> 
> Turns out this one hurts PA6T performance quite a bit, lwsync seems to be
> significantly more expensive there. I see a 25% drop in the microbenchmark
> doing pthread_lock/unlock loops on two cpus.
> 
> Taking out the CPU_FTR_LWSYNC will solve it, it's a bit unfortunate since
> the sync->lwsync changes definitely still can, and should, be done. 

So we should use a different feature bit. No biggie. If needed we can
split them more anyways.

Cheers,
Ben.




More information about the Linuxppc-dev mailing list