>The article pointed by you justifies that the way ResetEvent is done by >patch is correct. I am not sure, but you can weigh, if there is a need >of >comment so that if we want enhance this part of code (or want to write >something similar) in future, we don't need to rediscover this fact.
I've added a reference in a comment.
Did you have a chance of running the patched versions on windows?
I am planning to do it in next few hours.
I plan to push this sometime today, so I can get on to some performance patches I was planning to look into committing.
have we done testing to ensure that it actually mitigate the impact of performance degradation due to commit ac1d794. I wanted to do that, but unfortunately the hight-end m/c on which this problem is reproducible is down.