On Wed, Feb 17, 2010 at 08:37:14PM +1100, Anton Blanchard wrote:

 
Hi Nick,

quoted

Cool. How does it go when there are significant amount of instructions
between the lock and the unlock? A real(ish) workload, like dbench on
ramdisk (which should hit the dcache lock).

Good question, I'll see if we can see a difference on dbench.

Well I misread your benchmark. Your test is using pthread mutexes in
order to basically exercise kernel's syscall and context switching and
futex code. Wheras I thought it was just a trivial lock/unlock
sequence being tested.

So I'm much more impressed with your numbers :) dbench would still
be interesting though.