http://www.cnn.com/2003/TECH/internet/03/07/speed.record/index.html
Comments folks?
Yeah. Give me a million dollars, plus fiber from here to anywhere,
and let me muck with the TCP algorithm, and I can move a gig-e worth
of traffic, too.
-Dave
... in an unrelated story, the RIAA's Jack Valenti was seen wandering down
Sunset blvd, foaming at the mouth while shopping at a used-backhoe lot....
I can only hope that the researchers actually spent $2000-$4000 on moving
the gigabit of data, pocketed the rest, and are now living in a tropical
foreign country with lots and lots of drugs and women, because anything
else would just be too sad for me to contemplate.
What am I missing here, OC48=2.5Gb, OC192=10Gb, theres native 1GigE, native
10GigE
So whats good about this?
More detailed technical information on the periodic I2 Land Speed
Record contest can be found at http://lsr.internet2.edu/
The answer to "what's good about this" is left as an exercise to the reader.
---Rob
"Stephen J. Wilcox" <steve@telecomplete.co.uk> writes:
This might have something to do with it:
Contest Rules:
1. A minimum of 100 megabytes must be transferred a minimum terrestrial
distance of 100 kilometers with a minimum of two router hops in each
direction between the source node and the destination node across one or
more operational and production-oriented high-performance research and
education networks. Examples of such networks are Abilene, ESnet, CA*net3,
NREN and GEANT.
Production commercial networks need not apply, 'lest someone realize that
they blow away these speed records on a regular basis.
According to CNN:
"Scientists were able to get 93 percent efficiency out of their
record-setting connection because they didn't have to share bandwidth,
they received donated equipment in excess of $1 million and they
changed the setting of Internet protocols to allow faster data
transfers, Newman said."
So, you turn down/off all the parts of TCP that allow you to share
bandwidth properly, crank up the window and packet sizes, and
suddenly, TCP is pretty damn efficient for a one-way transfer.
There's no real "science" here. This is a geek publicity stunt.
-Dave
Quoting Eric Germann <ekgermann@cctec.com>:
CNN.com - Scientists: Internet speed record smashed - Mar. 7, 2003
Comments folks?
I'm going to launch a couple DAT tapes across the parking lot with a spud gun
and see if I can achieve 923 Mb/s!
It would have been nice if the reporter bothered to mention that "Internet
speed records" are measured in terabit meters per second. An article
about "Internet speed records" that doesn't include the actual record, or even
a definition of the term "Internet speed record", is hardly deserving of
placement on the front of cnn.com. Slow news day?
-Adam
What kind of production environment needs a single TCP stream of data
at 1 gigabit/s over a 150ms latency link?
Just the fact that you need a ~20 megabyte TCP window size to achieve this
(feel free to correct me if I'm wrong here) seems kind of unusal to me.
> Production commercial networks need not apply, 'lest someone realize that
> they blow away these speed records on a regular basis.What kind of production environment needs a single TCP stream of data
at 1 gigabit/s over a 150ms latency link?
Probably not many, but it's quite possible. I've done 1 Gbps streams off a
single box before, it's not much harder to take it out 150ms. Heck for
their 60 second test, you could buy some GigE transit ports from someone
with a STM64 across the pond and not even pay for it in 95th percentile.
Just the fact that you need a ~20 megabyte TCP window size to achieve this
(feel free to correct me if I'm wrong here) seems kind of unusal to me.
And you can't afford 20MB of RAM because...?
:
: Quoting Eric Germann <ekgermann@cctec.com>:
:
: > http://www.cnn.com/2003/TECH/internet/03/07/speed.record/index.html
: >
: > Comments folks?
:
: I'm going to launch a couple DAT tapes across the parking lot with a spud gun
: and see if I can achieve 923 Mb/s!
Yer gonna need a big damn spud gun... 
Contest Rules
1.A minimum of 100 megabytes must be transferred a minimum
terrestrial distance of 100 kilometers...
scott
: It would have been nice if the reporter bothered to mention that "Internet
: speed records" are measured in terabit meters per second. An article
: about "Internet speed records" that doesn't include the actual record, or even
: a definition of the term "Internet speed record", is hardly deserving of
: placement on the front of cnn.com. Slow news day?
:
: -Adam
:
On Fri, Mar 07, 2003 at 10:09:51PM +0100, Mikael Abrahamsson quacked:
> Production commercial networks need not apply, 'lest someone realize that
> they blow away these speed records on a regular basis.What kind of production environment needs a single TCP stream of data
at 1 gigabit/s over a 150ms latency link?Just the fact that you need a ~20 megabyte TCP window size to achieve this
(feel free to correct me if I'm wrong here) seems kind of unusal to me.
It's unusual, but it's not completely unheard of. One of the biggest
sources of such data is VLBI (interferometry to measure the movement
of the earth's crust), in which signals from geographically distributed
measurement sites have to be recorded and correlated at a central site:
http://web.haystack.edu/vlbi/vlbisystems.html
The signals are massive. Right now they use specially made tape
drives that can record 1Gb/s:
ftp://web.haystack.edu/pub/mark4/memos/230.2.pdf
ftp://web.haystack.edu/pub/mark4/memos/HDR_concept.PDF
and they send the data around via airplanes. They'd love to be
able to do real-time correlation of the data, but that
involves collecting 6 of these feeds at a central site (more coming).
The feeds must be capable of running unattended for up to 24 hours
(86 terabytes each, or an aggregate of half a petabyte per day).
Yes, backbones push more than a gigabit across links, but not as
for a single flow of data.
-Dave
Doing the 923 Mbps for one stream may be non-trivial (heck, even doing
110 MB per second sustained to/from disk isn't trivial) but the real
challenge would be having two of those setups each try to do 1 Gbps over
a single connecting while sharing the 1 Gbps link without any slowdowns.
(And no fair having 20 MB interface buffers in the routers.)
Or a 400,000pps attack Which we've seen
Hello;
There was a 1.5 Gigabit per second uncompressed HDTV stream that was sent
U Washington to DC.
http://www.washington.edu/hdtv/next-gen.html
True, that was sent RTP over UDP, but if I was
going to send that data rate over a _dedicated_ link, I would use UDP. The
very high bit rate applications I have been involved with could all tolerate
some loss, and for the others, a little FEC could go a long way.
Production commercial networks need not apply, 'lest someone realize that
they blow away these speed records on a regular basis.What kind of production environment needs a single TCP stream of data
at 1 gigabit/s over a 150ms latency link?Just the fact that you need a ~20 megabyte TCP window size to achieve this
(feel free to correct me if I'm wrong here) seems kind of unusal to me.--
Mikael Abrahamsson email: swmike@swm.pp.se
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
Maybe that's why the two endpoints are LA and Amsterdam?
Neither is tropical, but they have plenty of drugs and women.
Andy
xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Andy Dills 301-682-9972
Xecunet, LLC www.xecu.net
xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Dialup * Webhosting * E-Commerce * High-Speed Access
> Production commercial networks need not apply, 'lest someone realize that
> they blow away these speed records on a regular basis.What kind of production environment needs a single TCP stream of data
at 1 gigabit/s over a 150ms latency link?
what kind of production highway sees the kinds of cars that reach the
world land speed records?
why is it that nanog'ers seem to display such aggression at this type of
thing? is it the article itself, the work the researchers are doing, or
the fact that they had the bandwidth and hardware to do it with?
--Rob
On Fri, Mar 07, 2003 at 10:09:51PM +0100, Mikael Abrahamsson quacked:
Production commercial networks need not apply, 'lest someone realize that
they blow away these speed records on a regular basis.What kind of production environment needs a single TCP stream of data
at 1 gigabit/s over a 150ms latency link?Just the fact that you need a ~20 megabyte TCP window size to achieve this
(feel free to correct me if I'm wrong here) seems kind of unusal to me.It's unusual, but it's not completely unheard of. One of the biggest
sources of such data is VLBI (interferometry to measure the movement
of the earth's crust), in which signals from geographically distributed
measurement sites have to be recorded and correlated at a central site:http://web.haystack.edu/vlbi/vlbisystems.html
The signals are massive. Right now they use specially made tape
drives that can record 1Gb/s:ftp://web.haystack.edu/pub/mark4/memos/230.2.pdf
ftp://web.haystack.edu/pub/mark4/memos/HDR_concept.PDF
and they send the data around via airplanes. They'd love to be
able to do real-time correlation of the data, but that
involves collecting 6 of these feeds at a central site (more coming).
The feeds must be capable of running unattended for up to 24 hours
(86 terabytes each, or an aggregate of half a petabyte per day).
VLBI is moving to hard drive replacements for the expensive 1 inch tapes currently
used (known as Mark V). There are active projects for "e-VLBI" - at CRL in Japan
http://www.ntt.co.jp/news/news01e/0107/010706.html
and at Haystack Observatory in Massachusetts
http://web.haystack.edu/e-vlbi/meeting.html
In e-VLBI there is no need for reliable transmission and UDP is the way to go.
I am still involved with this peripherally, especially with the idea that the traffic be sent
"worse than best effort", so as not to collide with regular traffic.
BTW, when I did VLBI for the Navy, we used to move literally tons of tapes around the world
per month and achieved sustained bandwidths > 1 Gbps, albeit with FED-EX, not routers.
Yes, backbones push more than a gigabit across links, but not as
for a single flow of data.-Dave
--
work: dga@lcs.mit.edu me: dga@pobox.com
MIT Laboratory for Computer Science http://www.angio.net/
I do not accept unsolicited commercial email. Do not spam me.
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
It is well established that wide-area networking has become the ego center
of computing.