packet reordering at exchange points

Tue Apr 9 01:31:17 UTC 2002

Paul-

> more to the point, does anybody still care about packet reordering
> at exchange points?  we (paix) go through significant effort to
> prevent it, and interswitch trunking with round robin would be a
> lot easier.  are we chasing an urban legend here, or would
> reordering still cause pain?

Yep.  Reordering causes pain to TCP performance.  The basic idea is
that if packets get jumbled up they trigger duplicate ACKs from the
receiver.  If things are badly enough reordered we end up with >= 3
duplicate ACKs arriving at the sender.  According to the fast
retransmit algorithm 3 duplicate ACKs are taken by the TCP as an
indication of packet loss -- and, hence, congestion.  So, we end up
needlessly cutting our congestion window in half.

Ethan Blanton and I just published a paper on what might be done
to make TCP more robust to paths that reorder segments (which would,
in turn, make such paths be less problematic).  The paper is:

    Ethan Blanton, Mark Allman. On Making TCP More Robust to Packet
    Reordering}.  ACM Computer Communication Review, 32(1), January
    2002. 
    http://roland.grc.nasa.gov/~mallman/papers/tcp-reorder-ccr.ps

You might not necessarily be interested in the entire paper.  But,
the first part shows the performance problems caused by packet
reordering. 

allman

--
Mark Allman -- NASA GRC/BBN -- http://roland.grc.nasa.gov/~mallman/