[blasdel]

That you didn't say anything about the machines you ran it on was a huge red flag. It looks like jacquesm has you nailed on the localhost testing, I hadn't noticed the link to the code before.

I'll trust that you accurately measured the ATR boundary between poll and epoll in your specific synthetic benchmark. That's then completely undermined by your handwaving in this thread about what ATR looks like in the wild, and the lack of any way for us to relate your microbenchmark with the real world.

[zedshaw]

The original article had the link to the code so don't even try to imply that I was hiding jack squat. He hasn't nailed shit, it's the same test epoll proponents have used for years. It's not a "localhost" test, it's a test that makes a bunch of file descriptors and then compares the poll vs. epoll performance as active vs. total changes.

But hey, you can live in your own little fantasy world where you think you've won some kind of battle of the HN because you listened to some epoll fanatic weirdo and cheered him on.