CPU profiler: make code events handling scalable.

CPU profiler: make code events handling scalable.

I changed the implementation of a queue between the VM and processor
thread to be unbounded and lock-free, using Herb Sutter's example from
DDJ article: http://www.ddj.com/high-performance-computing/210604448
This had brought back profiling overhead to a minimum for the page
from Chromium's issue 16184.

BUG=714
Committed: http://code.google.com/p/v8/source/detail?r=4706

[Søren Thygesen Gjesse, 2010-05-21 06:44:08]

LGTM

Nice and simple - I like it!

http://codereview.chromium.org/2091019/diff/1/12
File src/unbound-queue.h (right):

http://codereview.chromium.org/2091019/diff/1/12#newcode36
src/unbound-queue.h:36: // transferring small records between a single producer
and a single
Maybe emphasize single.

[mnaganov (inactive), 2010-05-22 05:26:44]

Thanks!

http://codereview.chromium.org/2091019/diff/1/12
File src/unbound-queue.h (right):

http://codereview.chromium.org/2091019/diff/1/12#newcode36
src/unbound-queue.h:36: // transferring small records between a single producer
and a single
On 2010/05/21 06:44:08, Søren Gjesse wrote:
> Maybe emphasize single.

Capitalized 'Single' -- now easier to spot.