🚀 go-pugleaf

hanc...@bbs.cpcn.com writes:
> That is surprising, since early on in satellite communications
> they discovered the problem with latency in both voice and data
> transmission.  Indeed, by 1960, they knew the characteristics of
> voice and data were different enough to require different line
> treatments ("conditioning") to accommodate higher data speeds
> on landlines.
>
> I'm not sure when SNA was developed, but I would guess by that
> point overseas computer data transmission was already in place
> via cable, as well as transcontinental data transmission via
> microwave, which has latency, too.
>
> Some of that is touched on in the following:
> http://massis.lcs.mit.edu/telecom-archives/archives/technical/western-union-tech-review/21-4/p174.htm

mid-70s as Future System was imploded, my wife was co-author of AWP39
... peer-to-peer networking architecture ... about the same time as SNA
... which specified dumb terminal communication control system ... "not"
a system, "not" a network, and "not" an archiecture (i.e. fancy TCAM)
... but because they used "network" (when it wasn't a network), AWP39
had to qualify with peer-to-peer.
htpt://www.garlic.com/~lynn/submain.html#futuresys

She was then in the gburg JES group and one of the catchers that turned
ASP into JES3 and co-author of JESUS (JES unified system) ... all the
stuff in JES2 & JES3 that the respective customers couldn't live w/o
... then was con'ed into going to POK to be in charge of
"loosely-coupled" architecture (mainframe for "cluster) and did
"peer-coupled shared data architecture" ... some past posts
http://www.garlic.com/~lynn/subnetwork.html#shareddata

She didn't remain long because 1) little uptake (except for IMS
hot-standby ... until sysplex and parallel sysplex much later) and 2)
constant battles with communication group trying to force her into using
SNA/VTAM for loosely-coupled operation.

SBS satellite communication provided much higher bandwidth with distance
insensitive charges (stationary orbit satellite footprint). SNA/VTAM had
window pacing implementation that would allow small (very limited)
number of small fixed-sized packets to be transmitted (waiting for
outstanding packet acknowledgements) and it also had maximum time-out if
it didn't get response. Double-hop 56kbit satellite link latency
exceeded both the maximum time-out case as well as the maximum window of
outstanding packets. Terrestrial T1 latency and speed would exceeded the
maxium window/number of outstanding packets ... at which point VTAM
stops transmitting until it gets ACKs back for earlier transmitted
packets (aka acknowledgements that previously transmitted packets had
been received), so even with terrestrial latency, majority of the T1
bandwidth was idle ... late 80s resulted in the 3237 spoofing CTCA
(local channel-to-channel with no latency) for T1 links ... still
couldn't get over 2mbits/sec aggregate. some old email
http://www.garlic.com/~lynn/2011g.html#email880130
http://www.garlic.com/~lynn/2011g.html#email880606
http://www.garlic.com/~lynn/2011g.html#email881005
in these posts
http://www.garlic.com/~lynn/2011g.html#75 We list every company in the world that has a mainframe computer
http://www.garlic.com/~lynn/2011g.html#77 Is the magic and romance killed by Windows (and Linux)?

cira 1979 or 1980, there is inframous case where STL (west coast, now
silicon valley lab) and Hursely (Englan lab) datacenters were trying to
setup to use each others "off-shift" time for their respective 1st shift
throughput. They had double hop satellite 56kbit link (much, much
cheaper than terrestrial plus undersea cable) and initially tested with
VM370 VNET connection and everything worked fine. Then (MVS-bigot)
insisted that it be setup for MVS JES2 (SNA/VTAM) and it was completely
dead. The MVS-bigot tried to claim it was a bad link and VM370 VNET was
too dumb to realize it. The problem was the double-hop round trip
latency was greater than the MVS SNA/VTAM time-out value ... so wouldn't
establish a operational link.

HSDT even got a dedicated transponder to play with when SBS4
http://space.skyrocket.de/doc_sdat/sbs-1.htm
STS-41-D (I was invited to VIP launch party at cape)
https://en.wikipedia.org/wiki/STS-41-D
I think SBS4 was their first KU-band ... previous having been C-band
https://en.wikipedia.org/wiki/Ku_band

hsdt posts
http://www.garlic.com/~lynn/subnetwork.html#hsdt
HSDT did dynamic rate-based pacing (rather than window-based ... aka max
number of outstanding packets waiting for acknowledgement). I was also
on the XTP technical advisory board ... past posts
http://www.garlic.com/~lynn/subnetwork.html#xtphsp
and wrote up (dynammic) rate-based pacing for XTP specification
http://www.garlic.com/~lynn/xtprate.html