[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: pf(4) schemantics

On Fri, Mar 21, 2003 at 06:39:49PM +0100, Srebrenko Sehic wrote:
> On Thu, Mar 20, 2003 at 04:13:04PM -0700, [email protected] wrote: 
> > > I assume that 'pass out all keep state' makes pf(4), at least, do a
> > > state lookup in the table? AFAIK, that's, in worst case scenario, 16
> > > searches down the binary tree? That ought to eat a few cycles.
> > I really doubt there is a performance issue here, or really, that this
> > would be the bottleneck. If it is, show the facts, and we (I use the
> > royal we here, meaning Daniel or Henning) can address it then.
> Hmm? It might not be a major bottleneck, but keeping state for nothing
> and on _two_ interfaces, must cost something. Let's not forget about
> memory cost also.
380000 state table entries in 128MB memory.
wanna talk about memory cost?
15000 packets/s on a duron 700 at 10% CPU.
wanna talk about performance impact?
pah humbug.
Profile, don't speculate.
Henning Brauer, BS Web Services, http://bsws.de
[email protected] - [email protected]
Unix is very simple, but it takes a genius to understand the simplicity.
(Dennis Ritchie)