On Fri, Oct 10, 2008 at 10:31 AM, Greg Ames <[EMAIL PROTECTED]> wrote:
> > I will take a look at the APR atomics and see if the operations that > Event's fdqueue is using are less supported than the atomics used in > worker. > No difference in support on ia32 + gcc; both worker and event use two mutex based apr_atomic_* calls per connection without --enable-nonportable-atomics. So it doesn't matter for this thread. It might be a worthwhile topic for [EMAIL PROTECTED] if there is a significant performance difference. Greg
