On Fri 3 Jan, 1997, Nigel Metheringham <Nigel.Metheringham@theplanet.net> wrote:
>I think that having the acl stuff as a separate process need not
>significantly slow things down. If given a nice API, it does allow you to
It depends what your workload is. It will be introducing at least two
extra context switches for each request which might be significant
for some. This is a problem for the redirector, too, of course.
I think I prefer improving the hashing scheme; and using something like
the BSD radix tree does mean that networks and their sizes can be
readily recorded and matched against, caching recent lookups a useful
optimisation.
James.
Received on Sun Jan 05 1997 - 14:27:02 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:33:59 MST