[Beowulf] High Performance SSH/SCP

[Mark Hahn]

> Hopefully the PSC folks (or other parties) can convince the OpenSSH
> maintainers to allow some options (dynamic buffers, disabled encryption
> of the non-handshake payload, etc.) that result in higher-bandwidth
> transfers.

the switch-to-none feature is a good one.  I'm a bit skeptical about
the buffering changes, since you can accomplish the same thing with 
sysctls.  (has anyone ever experienced a real case where too-large 
sysctl net memory settings caused problems?  obviously, attempting 
to do long-fat-pipe transfers to a heavily used web server might 
be a problem, since the latter wants tight controls on sock mem use.)

the really cool thing would be if you could associate a default 
setting for socket buffers with a _route_.  heck, a round-port combo.
it seems crazy for apps to be messing with these issues.

> ps - For ssh transfers over long distances (high-bandwith and high
>     latency) one can break the data up into pieces and run multiple
>     ssh transfers in parallel.  Transmitting terabyte data sets from
>     the West Coast to the East Coast over Abilene I've seen >10X
>     speedups (that is, >10X the overall throughput) when running
>     15--20 simultaneous ssh sessions.

this implies inappropriate buffer size settings, no?  what's the bw*delay
product for that path?