On Mon, 2006-02-20 at 01:41 +0100, Roberto Nibali wrote:
Increasing the time to 20000 usec cuts CPU in half again - to about 1/8 of the original consumption. It's now using ~10-15% of a CPU under the same heavy log load from ~750 connections. Granted, this increases latency, but I don't think 10 or 20 msec delays will kill anything.
The idea is cool, although I have to admit it is really a hack :)
What's wrong/the issue with adding epoll? Besides non-portability? Also 20msec may not hurt on 2.4.x kernels regarding latency however, 2.6.x kernels busy loop with HZ>100. Reducing HZ to something sensible like 100 is better for servers anyway. Could the OP also put his .config online somewhere?
The problem with epoll is that syslog-ng uses glib for its main loop, and it does not support epoll, and it does not seem to be trivial to add either. -- Bazsi