On Thursday 21 March 2002 00:51, Adrian Chadd wrote:
> Linux seems to suffer from the "NIH" syndrome. Ie, if its not
> invented or implemented here, we don't like it.
So does most of this world..
> Search the linux-kernel list archives for the discussions
> about /dev/poll and kqueue, and see what people have to say.
> Whether its the "best" or not really isn't relevant - its
> a step in the right direction. A very big step. :)
Both methods are about the same step with slightly different approach
and different drawbacks. Also, /dev/poll is the natural evolution of
poll, RT signals are "cool" but somewhat messy to deal with.
Neither are the best way to solve the problem. A correct solution
requires a far more radical approach on I/O in general and some
improvements in memory management.
Regards
Henrik
Received on Wed Mar 20 2002 - 17:06:28 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:14:52 MST