News for hackers. Stuff that matters.

A comment on Why Events Are A Bad Idea For High-Concurrency Servers (2003).

Re:Why Events Are A Bad Idea For High-Concurrency Servers (2... by timdoug on Friday May 02, 2014 @01:21AM (#7684247)
A bit of historical context: this paper came out in 2003, the same year NPTL (in RH9) and Linux 2.6.0 (first stable kernel with epoll, 2.5.44 introduced it in 2002) were released.
[ Parent | on HN ]
Re:Why Events Are A Bad Idea For High-Concurrency Servers (2... by stormbrew on Friday May 02, 2014 @03:50AM (#7684541)
It is worth noting that kqueue was introduced in FreeBSD 4.1 in 2000, /dev/poll in Solaris 8 at about the same time, and though somewhat different in nature, IOCP and Overlapped I/O were in Windows NT from before even that.

So there was already experience with high performance event driven mechanisms before epoll.

That said, the examples presented in this paper do appear to be linux examples.

[ Parent | on HN ]