Re: My planned work on networking stack

On Monday 01 March 2004 14:18, Andre Oppermann wrote:
> Hi all,
>
> I put this up for coordination and cooperation in my planned work on the
> FreeBSD networking system.  This is my todo list of things I want to do
> from now through summer 04.  If you are or intend to work on one of these
> please step forward so we can coordinate.  :-)
>
>  [] move ARP out of the routing table and instantiate it once per
> ethernet broadcast domain.  (started)

Yay!

>  [] automatically sizing TCP send buffers to achieve optimal performance
>     over a wide range of bw*delay situations.  (in progress)

What a wonderful idea.  Can't wait for the bikesheds...

>  [] establish a testbed for testing and qualification of TCP performance
>     and optimizations over a wide range of network conditions (types,
>     speeds, packet loss ratios, out of order, etc).  (started)

Be sure to coordinate with the donations officer for help in getting 
equipment you may need.

>  [] update and write more documentation for the network stack and related
>     code.  (started)

Yay!

>  [] adjust or rewrite the IPFW API to use the PFIL_HOOKS instead of being
>     woven directly into ip input/output.  (unless someone else does it)
>
>  [] move IPv4 routing to its own optimized routing table structure and
>     add multi-path and policy-routing options.  (planned)

Will the table code in PF be helpful in this area?  They seem to have 
developed a reasonably small notation for CIDR-type address ranges and code 
that does best-fit matching.

>  [] profile (don't speculate) common network server usages overall and
>     in specific detail in depth in the network code.  (planned)
>
>  [] write a network statistics (only local, no sniffing) gathering daemon
>     that collects vital real world IP and TCP behaviourial statistics.
>     (planned)
>
>  [] rewrite (or port over NetBSDs) tcp_reass() function which is
> currently rather inefficient.  (planned)
>
>  [] remove TTCP complexity and replace it with something along the lines
>     of TCP_MD5SIG to continue to allow fast connection setups but simpler
>     in implementation.  (Nothing fixed yet, up for discussion)
>
>  [] other stuff that I happen to stumble over... ;-)

Wowsers.  I can't wait to hear more.  When do you expect to have a design 
for the ARP stuff and TCP buffer sizing, since they are underway?

-- 
         "Where am I, and what am I doing in this handbasket?"

Wes Peters                                              wes_at_softweyr.com