Re: [patch] bug fix & TCP networking performance improvements

[Matthias Drochner <M.Drochner%fz-juelich.de@localhost>]

tls%panix.com@localhost said:
> > keep the kauth stuff seperate for now
> You are probably correct about this.

While we are here - there is some TCP RTT calculation change
in tcp_input.c which looks related to the recent thread
on tech-net -- was there some conclusion finally?

And there is the addition of "kinfo_pcb2" to socket.h
which I don't see a use for.

Why can't arp_drain() not be called in interrupt context?
It just does m_freem() which should be safe.

> VTW should be on by default

I agree that maintaining 2 code paths for the same thing
is not desirable. VTW adds ~22kB kernel code on i386
which is not _that_ much.

best regards
Matthias



------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------
Forschungszentrum Juelich GmbH
52425 Juelich
Sitz der Gesellschaft: Juelich
Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498
Vorsitzender des Aufsichtsrats: MinDirig Dr. Karl Eugen Huthmacher
Geschaeftsfuehrung: Prof. Dr. Achim Bachem (Vorsitzender),
Dr. Ulrich Krafft (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt,
Prof. Dr. Sebastian M. Schmidt
------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------

Besuchen Sie uns auf unserem neuen Webauftritt unter www.fz-juelich.de