Re: benchmarking squid on solaris/x86

From: Adrian Chadd <adrian@dont-contact.us>
Date: Wed, 20 Mar 2002 16:51:28 -0700

On Wed, Mar 20, 2002, Henrik Nordstrom wrote:

> The RT signal approach also seems to getting into shape. The RT
> scheme provides some quite interesting aspects even if a good
> /dev/poll probably would have been more useful as it is a lot simpler
> to make correct use of, and to debug..
>
> To me it is a bit odd that Linux do have RT signal I/O, but not a
> working /dev/poll. But I guess RT signal I/O was more fun to
> implement..

Linux seems to suffer from the "NIH" syndrome. Ie, if its not
invented or implemented here, we don't like it.

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. :)

Adrian
Received on Wed Mar 20 2002 - 16:51:30 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:14:52 MST