>> On Mon, 2 Feb 2009 21:21:36 -0500, Richard Sims <rbs AT BU DOT EDU> said:

> The symptoms seem like something in the network layer, as though the
> faucet were shut because something thought that was enough data
> already through that single session (service throttling).  You might
> try an artificial FTP of an equivalent amount of data (perhaps to /
> dev/null, as outlined in NETWORK PERFORMANCE in ADSM QuickFacts) to
> see if that gets cut off in much the same way.


Amen, brother.

I have seen this scenario several times; most of these times it was
straightforward to identify problem network hops.  Look very hard at
the net.

And -KEEP DIGGING-.  Trust TSM; it's really pretty good.  The worst of
my cases required several PMRs over a series of years, and four
simultaneuous sniffs.  That ended up with a faulty ASIC in a CISCO;
One particular set of bits would make the thing drop the packet.

Boy that was a pain to find.




- Allen S. Rout