[56455] in North American Network Operators' Group
Re: 923 Mbps across the Ocean ...
daemon@ATHENA.MIT.EDU (Marshall Eubanks)
Sat Mar 8 16:27:48 2003
Date: Sat, 8 Mar 2003 16:26:38 -0500
Cc: "'nanog@nanog.org'" <nanog@nanog.org>,
"'rich@a3.ph.man.ac.uk'" <rich@a3.ph.man.ac.uk>
To: "Cottrell, Les" <cottrell@SLAC.Stanford.EDU>
From: Marshall Eubanks <tme@multicasttech.com>
In-Reply-To: <2846497B437BF84BAD1A4CC407418D260148EA19@exchange1.slac.stanford.edu>
Errors-To: owner-nanog-outgoing@merit.edu
e-VLBI could easily live with a 1% packet loss rate, so I see no need
for it to use TCP. (Much higher and the correlator hardware
will probably start having trouble staying in sync.)
The 1.8 Gbps igrid2002 demo used UDP, for example.
http://www.hep.man.ac.uk/~rich/VLBI_web/igrid2002_index.html
On Saturday, March 8, 2003, at 03:43 PM, Cottrell, Les wrote:
>
> We have been talking to the radio astronomy people. We are aware they
> have such needs, however, I am unclear whether they have succeeded in
> transmitting single stream TCP application to application throughput of
> 900Mbits/s over 10,000km on a regular basis. Perhaps you could point me
> to whom to talk to. I am aware of the work of Richard Hughes-Jones of
> Manchester
Alan Whitney <awhitney@haystack.mit.edu>
Hans Hinteregger <hhinteregger@haystack.mit.edu>
Hisao Uose <uose.hisao@lab.ntt.co.jp>
Craig Walker < cwalker@nrao.edu>
> University and others and the Radio Astronomy VLBI Data Transmission
> (see for example http://www.hep.man.ac.uk/~rich/VLBI_web/) since we
> have shared notes and talked together a lot on the high performance
> issues. My understanding is that for today they use special high
> performance tapes to ship the data around, and are actively looking at
> using the network.
Today, yes, although the disk drive based Mark 5 system will be rapidly
rolled out, as it will substantially reduce operating costs.
http://web.haystack.mit.edu/e-vlbi/whitney.pdf
(BTW, the Mk5 deployment plan
http://ivscc.gsfc.nasa.gov/program/Mk5plan_disks.pdf
involves buying a metric ton of shippable disk drives.)
Tape shipping for the USNO VLBI correlator is on the order of $ 50K
per month (not counting recorder maintenance), so the
real question is, when will it be possible to ship 1 Gbps data by fiber
cheaper than than by FedEx. As the data are loss tolerant, and as
buffers are cheap, thus the interest in using worse than best effort
bandwidth. (If anyone is interested in the
this, I am trying to have an informal bar bof to discuss it at the SF
IETF.)
I cannot see how this is really relevant to NANOG and would suggest that
it be taken off list.
>
> -----Original Message-----
> From: alex@yuriev.com [mailto:alex@yuriev.com]
> Sent: Saturday, March 08, 2003 12:23 PM
> To: Jason Slagle
> Cc: Richard A Steenbergen; fingers; nanog@merit.edu
> Subject: Re: 923 Mbps across the Ocean ...
>
>
>
>> On Sat, 8 Mar 2003, Richard A Steenbergen wrote:
>>
>>> A) The amount of arrogance it takes to declare a land speed "record"
>>> when
>>> there are people out there doing way more than this on a regular
>>> basis.
>>
>> Single stream at 900mbs over that distance? Where?
>
> Talk to folks that deal with radio telescopes.
>
> Alex
>
Regards
Marshall Eubanks
T.M. Eubanks
Multicast Technologies, Inc.
Phone : 703-293-9601 Fax : 703-293-9609
e-mail : tme@multicasttech.com
http://www.multicasttech.com
Our New Multicast Workshop :
http://www.multicasttech.com/workshop
