From: Jesper Juhl <redacted>
Date: Fri, 29 Oct 2010 22:20:12 +0200 (CEST)

Sorry to intrude out of the blue without really understanding the kernel 
side of most of the code in question, but if there's a performance 
regression for applications using poll() shouldn't we address that so we 
get back to the prior performance level rather than requireing all 
userspace apps to switch to epoll() ??

For such a pathological program like Alban's test case, I say
absolutely not.