TTCP/RFC1644 problem

[Andre Oppermann]

Danny Braniss wrote:
> 
> > Danny Braniss wrote:
> > > hi,
> > >     im running some experiments, and it seems to me that
> > > setting net.inet.tcp.rfc1644 has the reverse effect.
> > > with sysctl net.inet.tcp.rfc1644 = 0, the transaction uses only 6 packets
> > > and it's less than 1 sec, setting net.inet.tcp.rfc1644 to 1 uses
> > > 8 packets and takes more than 1 sec.
> >
> > The first tcp session in an TTCP connection doesn't gain anything, only
> > subsequent session can go faster.
> >
> 
> i have tried many. ( > 1), btw, your statement and what my reading of Stevens
> don't 'coincide' :-), but then my experiment is not working either.
> 
> > You see in the second case that it tries to send data in the packet which
> > is not ACKed for the first connection and has to be retransmitted.
> >
> > You should check out the second and third connection to the server and
> > look how they behave.
> >
> > Did you enable rfc1644 on server and client?
> 
> yes!
> 
> what puzzels me is that with rfc1644 on on both ends it's slower than without
> it.
> 
> from Colin's answer i assume that my client is doing the right thing, the
> server
> is not.

I have been the last one fuzz around in the TTCP code areas.  However
there could be problems that were lurking there before in other code
parts (syncache maybe).  TTCP isn't used in production by anyone (AFAIK)
and only minimally tested.

What FreeBSD version are you using?

-- 
Andre