Internet-2, NGI and TEN-155 Lessons for the (European) Academic and Research Community David Williams CERN - IT Division Supercomputer’98 Mannheim [email protected].

Internet-2, NGI and TEN-155Internet-2, NGI and TEN-155

Lessons for the Lessons for the (European)(European)Academic and Research Academic and Research

CommunityCommunity

David WilliamsDavid Williams

CERN - IT DivisionCERN - IT Division

Supercomputer’98 MannheimSupercomputer’98 Mannheim

[email protected]@cern.ch

Slides: Slides: http://nicewww.cern.ch/~davidw/public/Mannheim/Mannheim.pphttp://nicewww.cern.ch/~davidw/public/Mannheim/Mannheim.pp

tt

What about me?What about me?

Other side of the RöstigrabenOther side of the Röstigraben CERNCERN Never a networking specialistNever a networking specialist No longer a managerNo longer a manager ICFA-NTFICFA-NTF EUEU So this talk is all my own views, but not all So this talk is all my own views, but not all

my own workmy own work Too much to tell you aboutToo much to tell you about

Outline of this TalkOutline of this Talk

Does the Internet work?Does the Internet work? ApplicationsApplications Technical changesTechnical changes AmericaAmerica

– Internet-2Internet-2 -- NGI -- NGI EuropeEurope

– TEN-34 and successorsTEN-34 and successors -- 5FP-- 5FP What are the lessons?What are the lessons?

Networks for supercomputer usersNetworks for supercomputer users The (general-purpose) Internet in EuropeThe (general-purpose) Internet in Europe

(How well)(How well) Does the Does the (academic)(academic) Internet work?Internet work?

Not as well as it shouldNot as well as it should

April 1998 Packet Loss (extract)April 1998 Packet Loss (extract)

US universityUS university from Fermifrom Fermi from CERNfrom CERNbrown.edu 16.15 17.29umass.edu 14.92 15.77pitt.edu 10.71 15.52harvard.edu 8.06 9.48uoregon.edu 4.18 0.33washington.edu 2.97 0.30princeton.edu 1.50 5.14cmu.edu 1.49 14.61hawaii.edu 1.18 0.70duke.edu 0.30 6.60umd.edu 0.16 5.07indiana.edu 0.14 15.25mit.edu 0.02 0.27

NSF Awards NLANR Group at UCSD NSF Awards NLANR Group at UCSD $2.08 Million for Measurement and $2.08 Million for Measurement and Analysis of Internet Infrastructure Analysis of Internet Infrastructure

(1/2) (1/2)

UNIVERSITY OF CALIFORNIA, SAN DIEGO -- UNIVERSITY OF CALIFORNIA, SAN DIEGO -- May 27, 1998May 27, 1998

The National Science Foundation has The National Science Foundation has awarded $2.08 million over 30 months to awarded $2.08 million over 30 months to the University of California, San Diego to the University of California, San Diego to monitor and analyze the continent-wide monitor and analyze the continent-wide research network that is a key component research network that is a key component of the next generation of Internet of the next generation of Internet technologies.technologies.

NLANR Award (2/2)NLANR Award (2/2)

The award establishes the Measurement The award establishes the Measurement and Operations Analysis Team (MOAT) as a and Operations Analysis Team (MOAT) as a formal group within the National formal group within the National Laboratory for Applied Networking Laboratory for Applied Networking Research to analyze network traffic Research to analyze network traffic patterns and traffic behavior, evaluate patterns and traffic behavior, evaluate service models, and conduct research to service models, and conduct research to enhance the NSF's very high performance enhance the NSF's very high performance Backbone Network ServiceBackbone Network Service

See http://www.npaci.edu/online/ and See http://www.npaci.edu/online/ and http://moat.nlanr.net/ for more infohttp://moat.nlanr.net/ for more info

CERN to SLAC Monitoring over 1 week in December 1997

Above (left) is Round trip time (about 180 ms)Below (right) is packet loss rate (very low)

CERN to Uni Tokyo - same week

RTT 350-500msBig daily peaks

Packet loss worseSome 20-30% samples

One bad peak

Sat Sun

Things do improve - CERN to Tokyo May 98

RTT at 300-400msDaily peak effect much less

Packet loss quite reasonable

SatSat SunSunSunSun

MonMon

TueTue

WedWed

ThursThurs

FriFri

Daily packet loss structure on a congested route

50% peaks 8 quiet hours at nightFrom ~01.00 to 09.00 CET

Packet loss rate - Fermilab to Brown University - April 98

Performance inside the US can be bad too!

Same period - CERN to Brown University - packet loss

With RTT - same period - CERN to Brown

RTT = 250 to 400+ msecCompare 180 msec to SLAC

CAnet

ESnetDFN

TEN-34

HEP networking seen from HEP networking seen from CanadaCanada

NACSIS

Lessons so far?Lessons so far?

Not everything is wonderful in the USANot everything is wonderful in the USA A few universities badly connected, even A few universities badly connected, even

some very rich and famous onessome very rich and famous ones Everything depends on the detailed Everything depends on the detailed

routingrouting

InterNet = InterNet = InterInterconnects + connects + NetsNets We know how to build the nets wellWe know how to build the nets well We have not yet learned how to build the We have not yet learned how to build the

interconnects as wellinterconnects as well

Three factors for the futureThree factors for the future

TechnologyTechnology

EconomicsEconomics

OrganisationOrganisation

ApplicationsApplications

Application generationsApplication generations

First = what we are used toFirst = what we are used to Second = what is about to enter general Second = what is about to enter general

productionproduction Third = interesting, but needs lots of Third = interesting, but needs lots of

bandwidthbandwidth

PLUSPLUS Interactive = human intimately in loopInteractive = human intimately in loop

First generation appsFirst generation apps

e-maile-mail– few 10s of packets; tolerant of high packet few 10s of packets; tolerant of high packet

loss; non-interactiveloss; non-interactive Web accessWeb access

– quite similar; not really very interactivequite similar; not really very interactive manually initiated file transfermanually initiated file transfer

– more packets, but not very interactivemore packets, but not very interactive telnet, X-windowtelnet, X-window

– interactive; people start to get very disturbed interactive; people start to get very disturbed with delays ~>5 sec; sensitive to packet loss with delays ~>5 sec; sensitive to packet loss ratesrates

First generation apps (summary)First generation apps (summary)

So far, so goodSo far, so good But not very adventurousBut not very adventurous Fortunately only the interactive telnet and Fortunately only the interactive telnet and

X traffic is very sensitive to packet lossX traffic is very sensitive to packet loss

Second generation apps (1)Second generation apps (1)

streaming video and audio for individualsstreaming video and audio for individuals– lots of datalots of data– quite strong RT constraintsquite strong RT constraints– intolerant of packet loss (esp. audio)intolerant of packet loss (esp. audio)

groupware for collaboration at a distancegroupware for collaboration at a distance– fundamentally important for collaborative fundamentally important for collaborative

sciencescience– shared software development (here or next?)shared software development (here or next?)– brainstorming (shared whiteboards, good access brainstorming (shared whiteboards, good access

to Web, incl. graphics, video and audio, ...)to Web, incl. graphics, video and audio, ...)– weekly meetings (10 people, 5 locations, …)weekly meetings (10 people, 5 locations, …)– must be easy to use, reliable, good performancemust be easy to use, reliable, good performance

Second generation apps (2)Second generation apps (2)

automated data access and transferautomated data access and transfer– contrast with manually initiated file xfercontrast with manually initiated file xfer– automated file transfer systems for ‘production’ automated file transfer systems for ‘production’

– basic remote super-computer servicesbasic remote super-computer services– general client-server systemsgeneral client-server systems

shared file systems (e.g. AFS)shared file systems (e.g. AFS)– form a special subsetform a special subset– starting to become part of the “normally expected” starting to become part of the “normally expected”

infrastructure in HEPinfrastructure in HEP– need reasonable bandwidth and reliabilityneed reasonable bandwidth and reliability– so none to Japan, quite a bit across Atlantic, but so none to Japan, quite a bit across Atlantic, but

less than inside Europe and inside USAless than inside Europe and inside USA

Second generation apps Second generation apps (summary)(summary)

When they can be widely deployed they When they can be widely deployed they will bring fundamental improvements to will bring fundamental improvements to collaborative science on national, collaborative science on national, European, and inter-national levelsEuropean, and inter-national levels

But they do require significant But they do require significant improvements in the reliability of the links improvements in the reliability of the links being used (more bandwidth, lower packet being used (more bandwidth, lower packet loss)loss)

Third generation appsThird generation apps

Collaboratories and Advanced groupwareCollaboratories and Advanced groupware– trying to break the distance barrier for trying to break the distance barrier for

individuals who work togetherindividuals who work together Remote control roomsRemote control rooms

– telescopes or physics experiments or …..telescopes or physics experiments or …..– trying to break the distance barrier for teams trying to break the distance barrier for teams

looking after complex technical equipmentlooking after complex technical equipment Remote VR or other very advanced Remote VR or other very advanced

graphicsgraphics– trying to break the distance barrier for people trying to break the distance barrier for people

working with computersworking with computers

Third generation apps Third generation apps (summary)(summary)

No shortage of interesting ideasNo shortage of interesting ideas Probably? a shortage of bandwidthProbably? a shortage of bandwidth Or of money to pay for itOr of money to pay for it Or of means to make everything work on Or of means to make everything work on

an inter-continental basisan inter-continental basis

Technical changesTechnical changes

Bandwidth (1/2)Bandwidth (1/2)

Presently drive laser signals down fibre optic Presently drive laser signals down fibre optic cablescables

(Optically) amplify them every ~100 km(Optically) amplify them every ~100 km Lay cables under sea, on power lines, in conduits Lay cables under sea, on power lines, in conduits

along roads and railwaysalong roads and railways Fibre itself not expensive -- O(1 DEM/m)Fibre itself not expensive -- O(1 DEM/m) Undersea amplifiers have to consume very little Undersea amplifiers have to consume very little

power, which comes down cable (10 kV DC across power, which comes down cable (10 kV DC across the Atlantic) and operate unattended for 25 years. the Atlantic) and operate unattended for 25 years. So only 4 pairs per cable, cf 24, 48, and more So only 4 pairs per cable, cf 24, 48, and more overland. This is the reason why undersea overland. This is the reason why undersea bandwidth is inherently more expensive today.bandwidth is inherently more expensive today.

Bandwidth (2/2)Bandwidth (2/2)

Signal processing today is electronic. 2.5 Gbps Signal processing today is electronic. 2.5 Gbps is standardly available, 10 Gbps a little is standardly available, 10 Gbps a little expensive, but coming into use.expensive, but coming into use.

Big movement is to use multiple wavelengths. Big movement is to use multiple wavelengths. 4x in regular use by carriers, 32x seems 4x in regular use by carriers, 32x seems almost here, some people guess that 1024x is almost here, some people guess that 1024x is feasiblefeasible

Can you do everything optically?? Who Can you do everything optically?? Who knows? knows?

Switches and routersSwitches and routers

These are basically specialised computers, These are basically specialised computers, and benefit from the overall improvement and benefit from the overall improvement in computer technologyin computer technology

Critical functions being incorporated in Critical functions being incorporated in specialised electronicsspecialised electronics

High bandwidth backplanes/switching High bandwidth backplanes/switching fabricsfabrics

There There seemseem to be no barriers to progress to be no barriers to progress And a lot of very smart people and And a lot of very smart people and

companies hoping to make money from companies hoping to make money from Tbps routersTbps routers

Service levelsService levels

Perhaps the next “religious war”Perhaps the next “religious war” Telecoms people talk about “quality of Telecoms people talk about “quality of

service” and know that ATM provides it, while service” and know that ATM provides it, while Internet fans now talk about “differentiated Internet fans now talk about “differentiated service” (instead of “integrated services”), service” (instead of “integrated services”), and are thinking about who can tell what and are thinking about who can tell what makes a service different, and how you can makes a service different, and how you can profit from the knowledgeprofit from the knowledge

Internet-2Internet-2

Some historySome history

Agencies and universitiesAgencies and universities NSFnet and 1994-95NSFnet and 1994-95 No NRNNo NRN UCAIDUCAID

Agencies and universitiesAgencies and universities

It is important (for Europeans) to understand It is important (for Europeans) to understand that in the USA the financing of the various that in the USA the financing of the various agencies of the federal government (such as agencies of the federal government (such as NSF, DoE, DOD, NIH,..) is entirely separate NSF, DoE, DOD, NIH,..) is entirely separate from the funding of the universities, which is from the funding of the universities, which is either on a private or state basis.either on a private or state basis.

Although you can find some parallels in Although you can find some parallels in Europe (Germany in particular) the Europe (Germany in particular) the separation in the US seems to be very separation in the US seems to be very strong.strong.

This all means that until now there has been This all means that until now there has been no national A&R networkno national A&R network in the US in the US

NSFnet and 1994-95NSFnet and 1994-95

The NSFnet played a key role in the The NSFnet played a key role in the development of the Internet during the development of the Internet during the period from ~1986 until 1994/95. It was period from ~1986 until 1994/95. It was effectively the overall backbone, effectively the overall backbone, interconnecting the various agency interconnecting the various agency networks, and its capacity was upgraded networks, and its capacity was upgraded from 56 kbps to 1.5 Mbps to 45 Mbps during from 56 kbps to 1.5 Mbps to 45 Mbps during that time.that time.

It was decided to “privatise” this function, It was decided to “privatise” this function, and that took place during 1994/95, and and that took place during 1994/95, and NSFnet had been decommissioned by 31 NSFnet had been decommissioned by 31 March 1995.March 1995.

No NRNNo NRN

The NSFnet backbone was “replaced” by The NSFnet backbone was “replaced” by whichever Internet Service Provider (ISP) the whichever Internet Service Provider (ISP) the university took its business to.university took its business to.

Most (and essentially all of the research Most (and essentially all of the research universities) chose the InternetMCI service of universities) chose the InternetMCI service of MCI, who had run the NSFnet.MCI, who had run the NSFnet.

95 and 96 were years of very fast growth of 95 and 96 were years of very fast growth of the general purpose Internet in the US the general purpose Internet in the US (home and business use was booming).(home and business use was booming).

Lots of congestion and frustration, leading in Lots of congestion and frustration, leading in October 1996 to the first Internet-2 meetingsOctober 1996 to the first Internet-2 meetings

Internet-2Internet-2

This statement may not be PC (in the US), but This statement may not be PC (in the US), but Internet-2 is a good approximation to the Internet-2 is a good approximation to the NRN that the US has never hadNRN that the US has never had

Though Internet-2 Though Internet-2 per se per se has no (direct) has no (direct) relations with or connection to the national relations with or connection to the national labslabs

Top priority is on Top priority is on production servicesproduction services, and , and notnot on on research into networkingresearch into networking

Though they do have plans to encourage Though they do have plans to encourage advanced apps and to investigate and deploy advanced apps and to investigate and deploy QoS featuresQoS features

UCAIDUCAID

The University Corporation for Advanced The University Corporation for Advanced Internet Development is, to all intents and Internet Development is, to all intents and purposes, the supervisory board of a purposes, the supervisory board of a national university networknational university network

Responsible for Internet-2Responsible for Internet-2 122 (research) universities are members122 (research) universities are members 14 corporate partners (AT&T, 3Com, ANS, 14 corporate partners (AT&T, 3Com, ANS,

Bay, Cabletron, Cisco, Fore, IBM, Lucent, Bay, Cabletron, Cisco, Fore, IBM, Lucent, MCI, Newbridge, Nortel, Qwest, StarBurst)MCI, Newbridge, Nortel, Qwest, StarBurst)

Chief executive is Doug van HouwelingChief executive is Doug van Houweling

GigaPoPs (1/2)GigaPoPs (1/2)

One theme of Internet-2, which I personally find One theme of Internet-2, which I personally find very interesting, is to construct GigaPoPs (which very interesting, is to construct GigaPoPs (which officially stands for Gbps point-of-presence)officially stands for Gbps point-of-presence)

All sites wanting to connect in a given region All sites wanting to connect in a given region (city, state, …) connect to a commonly located, (city, state, …) connect to a commonly located, operated and funded Point of Presenceoperated and funded Point of Presence

Makes it far simpler, and far more competitive, for Makes it far simpler, and far more competitive, for different backbone providers to connect up different backbone providers to connect up GigaPopsGigaPops

Also simplifies inter-connection with “other Also simplifies inter-connection with “other networks” (such as ESnet) with decent networks” (such as ESnet) with decent performance performance

GigaPoPs (2/2)GigaPoPs (2/2)

Instead of universities and research institutes Instead of universities and research institutes needing to get to each carrier’s Point of needing to get to each carrier’s Point of Presence, GigaPoPs allow the universities to Presence, GigaPoPs allow the universities to specify where the carriers must come tospecify where the carriers must come to

It would be a good idea (according to me) for It would be a good idea (according to me) for the (A&R community in) European countries, the (A&R community in) European countries, regions and cities to invest in such EuroPoPs regions and cities to invest in such EuroPoPs or UserPoPsor UserPoPs

vBNS backbonevBNS backbone

Until recently the Until recently the de factode facto backbone for I2 backbone for I2 was the NSF’s vBNS, provided by MCIwas the NSF’s vBNS, provided by MCI

The very-high-performance Backbone The very-high-performance Backbone Network Service was initially created as a Network Service was initially created as a fast interconnect between NSF’s fast interconnect between NSF’s Supercomputer CentresSupercomputer Centres

It basically provides 622 Mbps linksIt basically provides 622 Mbps links During 1997/98 it has been transformed During 1997/98 it has been transformed

into the Connections Program and some into the Connections Program and some 100? universities are now connected to it 100? universities are now connected to it

More competitionMore competition

Recently (15 April 98) UCAID announced Recently (15 April 98) UCAID announced that Abilene will form an alternative that Abilene will form an alternative backbone for Internet-2backbone for Internet-2

Abilene is based on the use of the Qwest Abilene is based on the use of the Qwest fibre optic network, with equipment from fibre optic network, with equipment from Cisco and Nortel (Northern Telecom)Cisco and Nortel (Northern Telecom)

I have seen essentially no discussion of I have seen essentially no discussion of the financial terms, but it is clear that the financial terms, but it is clear that some of this is supported financially by the some of this is supported financially by the three companies concernedthree companies concerned

More on QwestMore on Qwest

Qwest Teams with Cisco to Build the Next Generation of Qwest Teams with Cisco to Build the Next Generation of High-Speed Voice/Data NetworksHigh-Speed Voice/Data Networks

Dr. Shafei explained that Qwest's network starts with 48 Dr. Shafei explained that Qwest's network starts with 48 fibers (with the capability to add ten times as many fibers (with the capability to add ten times as many fibers through additional in-place conduits), bidirectional, fibers through additional in-place conduits), bidirectional, line switching OC-192 ring SONET nationwide network. line switching OC-192 ring SONET nationwide network. Each fiber can carry 8 wave division multiplexing (WDM) Each fiber can carry 8 wave division multiplexing (WDM) windows, where each WDM window has a bandwidth of windows, where each WDM window has a bandwidth of 10 gigabits per second, providing Qwest with the 10 gigabits per second, providing Qwest with the potential of a multi terabit-per-second capability. potential of a multi terabit-per-second capability.

From a 30 Sept 1997 Press ReleaseFrom a 30 Sept 1997 Press Release

Next Generation InternetNext Generation Internet(NGI)(NGI)

Overview (1/2)Overview (1/2)

NGI initiative = multi-agency federal agency R&D NGI initiative = multi-agency federal agency R&D programme for:-programme for:-– developing advanced network technologiesdeveloping advanced network technologies– developing revolutionary apps needing advanced netsdeveloping revolutionary apps needing advanced nets– demonstrating via testbeds 100x-1000x faster end-to-demonstrating via testbeds 100x-1000x faster end-to-

end than today’s Internetend than today’s Internet i.e. not the universities (directly)i.e. not the universities (directly) Started 1 October 1997 (FY’98)Started 1 October 1997 (FY’98) Normally said to be 3-year program (I have seen Normally said to be 3-year program (I have seen

5)5) DARPA, NASA, NIH, NIST, NSF all involvedDARPA, NASA, NIH, NIST, NSF all involved DoE from FY’99??DoE from FY’99??

Overview (2/2)Overview (2/2)

This is the real place where the “leading-This is the real place where the “leading-edge” R&D is being performededge” R&D is being performed

But… insofar as NSF and hence vBNS are part But… insofar as NSF and hence vBNS are part of NGI, the project plays an important role in of NGI, the project plays an important role in getting Internet-2 off the groundgetting Internet-2 off the ground

Impressive (to me) how far the politicians Impressive (to me) how far the politicians (Gore (Gore et al, et al, but not only him) have but not only him) have understood the economic importance of understood the economic importance of Internet evolutionInternet evolution

One of my worries in Europe….One of my worries in Europe….

A first NGI visionA first NGI vision

The Next Generation Internet will:The Next Generation Internet will:– Accelerate mission-critical and time-sensitive Accelerate mission-critical and time-sensitive

research for Federal technology programsresearch for Federal technology programs– Expedite the introduction of advanced networking Expedite the introduction of advanced networking

services and applicationsservices and applications– Ensure and strengthen the technological and Ensure and strengthen the technological and

scientific leadership of the United Statesscientific leadership of the United States– Foster stronger technology research partnerships Foster stronger technology research partnerships

among government, academia and industryamong government, academia and industry

(From talk by Toole on 13 June 97, at (From talk by Toole on 13 June 97, at www.ngi.gov/talks)www.ngi.gov/talks)

A second NGI visionA second NGI vision

Imagine an Internet a thousand times faster than Imagine an Internet a thousand times faster than todaytoday– An Internet so ubiquitous that it interconnects all An Internet so ubiquitous that it interconnects all

Americans regardless of location, age, income or healthAmericans regardless of location, age, income or health– An Internet so safe and reliable that Americans An Internet so safe and reliable that Americans

confidently use it for most of their important confidently use it for most of their important communicationscommunications

– An Internet so intelligent that it can be used effortlessly An Internet so intelligent that it can be used effortlessly to help us preserve our environment, improve our to help us preserve our environment, improve our productivity, and get first rate medical careproductivity, and get first rate medical care

(From talk by Howell on 9 April 98, same location) (From talk by Howell on 9 April 98, same location)

First NGI testbedFirst NGI testbed

At least 100 sites (universities, federal At least 100 sites (universities, federal labs, other research partners) connected labs, other research partners) connected with end-to-end speeds 100x faster than with end-to-end speeds 100x faster than today’s Internettoday’s Internet

Today’s end-to-end speed (such as Today’s end-to-end speed (such as available between two workstations) is available between two workstations) is assessed as 10 Mbps at mostassessed as 10 Mbps at most

Led by NSF, NASA and DoE (from FY 99)Led by NSF, NASA and DoE (from FY 99)

Second NGI testbedSecond NGI testbed

About 10 sites with end-to-end speeds About 10 sites with end-to-end speeds 1000x faster than today’s Internet1000x faster than today’s Internet

Development of ultra-high speed switching Development of ultra-high speed switching and transmission technologies, and end-and transmission technologies, and end-to-end speeds of 1+ Gbpsto-end speeds of 1+ Gbps

Speaks of laying groundwork for Tbps, Speaks of laying groundwork for Tbps, with net management, control and QoS with net management, control and QoS guaranteesguarantees

Led by DARPA, with participation by NASA, Led by DARPA, with participation by NASA, NSF, DoE (from FY 99) etc. NSF, DoE (from FY 99) etc.

AlsoAlso

Experimental research for advanced Experimental research for advanced network technologiesnetwork technologies

Developments of “revolutionary” Developments of “revolutionary” applicationsapplications

Everything will, as far as possible, be Everything will, as far as possible, be tested on the testbedstested on the testbeds

SuperNet (1/2)SuperNet (1/2)

SuperNet will lay the groundwork for Tbps SuperNet will lay the groundwork for Tbps networksnetworks

Coordinated by DARPA IT OfficeCoordinated by DARPA IT Office Wide-Area Broadband CoreWide-Area Broadband Core

– It is DARPA’s intention that one or more It is DARPA’s intention that one or more metropolitan networks with links capable of at least metropolitan networks with links capable of at least 40 Gbps transmission rates be deployed.40 Gbps transmission rates be deployed.

– In addition some or all of the metro nets will be In addition some or all of the metro nets will be connected to form a national ultra-high-capacity netconnected to form a national ultra-high-capacity net

– The elements in these nets will be largely all-optical The elements in these nets will be largely all-optical with no electronic conversionwith no electronic conversion

(from www.darpa.mil/ito/Solicitations)(from www.darpa.mil/ito/Solicitations)

SuperNet (2/2)SuperNet (2/2)

Broadband Local TrunkingBroadband Local Trunking– Searching for cost-effective ways for delivering Searching for cost-effective ways for delivering

really high-performance services to users, really high-performance services to users, everywhereeverywhere

– Near-transparent (?) and service-independent Near-transparent (?) and service-independent connectivity from customer premises to all-connectivity from customer premises to all-optical backboneoptical backbone

– 20-40 Gbps fibre-based access? or20-40 Gbps fibre-based access? or– Gbps RF access (including satellite access)Gbps RF access (including satellite access)

Timetable (selected items)Timetable (selected items)

Starting in 1999Starting in 1999– First testbed with >100 sites connected to 622 First testbed with >100 sites connected to 622

Mbps infrastructure over 155 Mbps connectionsMbps infrastructure over 155 Mbps connections Starting in 2000Starting in 2000

– Second testbed connecting ~10 sites with 2.5 Second testbed connecting ~10 sites with 2.5 Gbps connectionsGbps connections

Starting in 2001Starting in 2001– Integrate QoS over a variety of technologies and Integrate QoS over a variety of technologies and

carrierscarriers Starting in 2002Starting in 2002

– Tbps packet switching demo. Advanced apps Tbps packet switching demo. Advanced apps tested over second testbedtested over second testbed

Budgets FY’98 and FY’99 Budgets FY’98 and FY’99 (proposal)(proposal)

AgencyAgency FY’98FY’98 FY’99FY’99

DARPA 4242 (All in MUSD) 40 (All in MUSD) 40NSF 2323 2525DoE 00 2525NASA 1010 1010NIST 55 55NIH 55 5 5

Total 8585 110 110

The relationship betweenThe relationship betweenInternet-2 and NGIInternet-2 and NGI

Not easy to understand … (1/2)Not easy to understand … (1/2)

Some aspects of telling politicians what they want Some aspects of telling politicians what they want to hearto hear

Internet-2 grew out of university frustration with Internet-2 grew out of university frustration with poor Internet performance. Above all it is about a poor Internet performance. Above all it is about a better production network for universities.better production network for universities.

The federal agencies have had their own The federal agencies have had their own networks, with little or nothing to be frustrated networks, with little or nothing to be frustrated aboutabout

NGI is basically advanced R&D triggered and NGI is basically advanced R&D triggered and largely funded by the US government, with the largely funded by the US government, with the aim of keeping US industry in a dominant position aim of keeping US industry in a dominant position in Internet technologiesin Internet technologies

Not easy to understand … (2/2)Not easy to understand … (2/2)

Internet-2 and NGI do not intrinsically have much Internet-2 and NGI do not intrinsically have much to do with each otherto do with each other

But, as I already pointed out, Internet-2 starts out But, as I already pointed out, Internet-2 starts out by depending on vBNS for its backboneby depending on vBNS for its backbone

What change does Abilene make??What change does Abilene make?? The first NGI testbed looks awfully like Internet-2 The first NGI testbed looks awfully like Internet-2

with good connections from the various federal with good connections from the various federal nets via vBNS??nets via vBNS??

If things go well, there might be a big opportunity If things go well, there might be a big opportunity for the US universities and federal agencies (and for the US universities and federal agencies (and industry) to make progress fast together……industry) to make progress fast together……

TEN-34 and Ten-155TEN-34 and Ten-155

What is TEN-34?What is TEN-34?

Trans-European Network at 34 MbpsTrans-European Network at 34 Mbps A distributed switch interconnecting Europe’s A distributed switch interconnecting Europe’s

national A&R networks (NRNs)national A&R networks (NRNs) A true A true InterInterNet (remember I said that building Net (remember I said that building

these Interthese InterConnectsConnects is the hardest job) is the hardest job) A truly major technical and political A truly major technical and political

achievementachievement Started (after almost two years preparatory Started (after almost two years preparatory

work) in ~April 97work) in ~April 97 Funded 40% by EU and 60% by NRNsFunded 40% by EU and 60% by NRNs 4FP project which formally ends 31 July 19984FP project which formally ends 31 July 1998

Some commentsSome comments

You can see that in fact not many of the lines You can see that in fact not many of the lines in TEN-34 are operated at 34 Mbpsin TEN-34 are operated at 34 Mbps

And that there are in fact two basic networks And that there are in fact two basic networks - an IP network from Unisource and an ATM - an IP network from Unisource and an ATM network from various PTTs. There was no network from various PTTs. There was no credible single supplier in mid-96. credible single supplier in mid-96.

Administrative structure is very complexAdministrative structure is very complex

More commentsMore comments

Slightly more capacity installed between Slightly more capacity installed between Europe and US than between European Europe and US than between European countriescountries

About 100 Mbps added (to ~380 Mbps) About 100 Mbps added (to ~380 Mbps) to/from the US in the last 2 monthsto/from the US in the last 2 months

The US capacity is very heavily used, so The US capacity is very heavily used, so total volume of A&R traffic transmitted total volume of A&R traffic transmitted from Europe to US is much higher than from Europe to US is much higher than inside Europeinside Europe

Moving to TEN-155Moving to TEN-155

Formal decisions will be made during the coming Formal decisions will be made during the coming weeks. The following information is believed to weeks. The following information is believed to be accurate, but should be treated as provisionalbe accurate, but should be treated as provisional

Arrangements have been made to extend the Arrangements have been made to extend the TEN-34 project, so that it can run down until 31 TEN-34 project, so that it can run down until 31 December 98, at the same time as TEN-155 runs December 98, at the same time as TEN-155 runs upup

TEN-155 may/might be the name of the TEN-155 may/might be the name of the production network which forms part of the production network which forms part of the Quantum Project, one of the last projects to be Quantum Project, one of the last projects to be funded from the 4FP. Quantum also involves R&D funded from the 4FP. Quantum also involves R&D into QoS issuesinto QoS issues

TEN-155 (more)TEN-155 (more)

Should be “fully” operational by 1 Jan 99Should be “fully” operational by 1 Jan 99 Likely to last about 1 year, when an FP5 Likely to last about 1 year, when an FP5

takes over (see below)takes over (see below) Many of the major countries will have 155 Many of the major countries will have 155

Mbps access to the TEN-155 backboneMbps access to the TEN-155 backbone

The Fifth Framework ProgrammeThe Fifth Framework Programme

Fifth Framework ProgrammeFifth Framework Programme

What is it?What is it? When will it happen?When will it happen? What is the structure?What is the structure? What about A&R networkingWhat about A&R networking

Caveat 1: FP5 has not yet been finally Caveat 1: FP5 has not yet been finally defined or approved. Everything we say defined or approved. Everything we say about it has to be taken conditionally.about it has to be taken conditionally.

Caveat 2: My information may be out-of-Caveat 2: My information may be out-of-datedate

What are Framework What are Framework Programmes?Programmes?

My explanationMy explanation

Every 5 years (in principle) the EU makes a Every 5 years (in principle) the EU makes a plan concerning all of the research and plan concerning all of the research and technical development which it intends to technical development which it intends to carry outcarry out

These plans are called Framework These plans are called Framework ProgrammesProgrammes

The basic idea is that the EU only does The basic idea is that the EU only does things which cannot be done better things which cannot be done better nationallynationally

The planning exercise is quite complexThe planning exercise is quite complex

What is it?What is it?(from EU documentation)(from EU documentation)

Framework programmes are instruments which reflect the scientific Framework programmes are instruments which reflect the scientific and technological priorities of their particular period, as well as the and technological priorities of their particular period, as well as the prevailing economic and political circumstances.prevailing economic and political circumstances.

Taking the form of a European Community legislative decision, Taking the form of a European Community legislative decision, framework programmes set out, for their period of application, the framework programmes set out, for their period of application, the global objectives of Community RTD activities, the specific priorities global objectives of Community RTD activities, the specific priorities and research themes to be addressed, the rules and procedures for and research themes to be addressed, the rules and procedures for implementation, the general conditions for participation, the implementation, the general conditions for participation, the indicative budget and the allocation of financial resources to the indicative budget and the allocation of financial resources to the various research themes.various research themes.

The research themes identified in the framework programme The research themes identified in the framework programme decision are then implemented by a number of "specific decision are then implemented by a number of "specific programmes" (e.g. Biomedicine and Health, Telematics programmes" (e.g. Biomedicine and Health, Telematics Applications, Innovation, etc.)Applications, Innovation, etc.)

When will it happen?When will it happen?

FP4 covers the period 1994-1998. It was originally FP4 covers the period 1994-1998. It was originally allocated funding of 12.3 Gecu (for the five years), allocated funding of 12.3 Gecu (for the five years), which has since been increased to 13.2 Gecu.which has since been increased to 13.2 Gecu.

FP5 should cover the period 1999-2002. Present FP5 should cover the period 1999-2002. Present proposal is that the funding should be 16.3 Gecu proposal is that the funding should be 16.3 Gecu (for the four years). Of this 3.925 Gecu, or 1 Gecu (for the four years). Of this 3.925 Gecu, or 1 Gecu annually, would be allocated to “Creating a user-annually, would be allocated to “Creating a user-friendly information society”. This is about 0.12‰ friendly information society”. This is about 0.12‰ of Europe’s GDP.of Europe’s GDP.

Pessimists expect the approval process for FP5 to Pessimists expect the approval process for FP5 to last into 1999, whereas optimists hope that Calls last into 1999, whereas optimists hope that Calls for Proposals for specific programmes will already for Proposals for specific programmes will already be issued by end-1998.be issued by end-1998.

Structure of FP5 - ThematicStructure of FP5 - Thematic

There are four Thematic Programmes, one of There are four Thematic Programmes, one of which is “Creating a user-friendly Information which is “Creating a user-friendly Information Society”.Society”.

This should have four “key actions”:-This should have four “key actions”:-– Systems and services for the citizenSystems and services for the citizen– New methods of work and electronic commerceNew methods of work and electronic commerce– Multimedia content and toolsMultimedia content and tools– Essential technologies and infrastructuresEssential technologies and infrastructures

These activities are all about R&D (and These activities are all about R&D (and nothing to do with production services)nothing to do with production services)

Structure of FP5 - HorizontalStructure of FP5 - Horizontal

There are also three Horizontal Programmes, There are also three Horizontal Programmes, one of which is “Improving Human Potential”.one of which is “Improving Human Potential”.

This has a “general objective, to be realised This has a “general objective, to be realised in concert with related actions elsewhere in in concert with related actions elsewhere in the FP”the FP”– Support for research infrastructuresSupport for research infrastructures

Among other things, this is the label under Among other things, this is the label under which support for “TEN-155” and successors, which support for “TEN-155” and successors, including better connections to/from outside including better connections to/from outside Europe, might be provided.Europe, might be provided.

The Information Society The Information Society Technologies (IST) ProgrammeTechnologies (IST) Programme

The “convergence” of computing, The “convergence” of computing, telecommunications and consumer electronics is telecommunications and consumer electronics is well recognised in Brussels.well recognised in Brussels.

The EU has woken up to the importance of the The EU has woken up to the importance of the Internet. It is starting to understand both the speed Internet. It is starting to understand both the speed of change and the economic impact, and wants to of change and the economic impact, and wants to put in place a programme for Internet development put in place a programme for Internet development in Europe which has some cohesion and identity.in Europe which has some cohesion and identity.

In FP4, ESPRIT, ACTS and Telematics were separate In FP4, ESPRIT, ACTS and Telematics were separate programmes. In FP5, they will be defined as part of programmes. In FP5, they will be defined as part of the same programme (the IST Programme) and the same programme (the IST Programme) and coordinated through a single EU management coordinated through a single EU management structure.structure.

Networking in FP5Networking in FP5

Funding levels available will depend on Funding levels available will depend on discussions about whether A&R discussions about whether A&R networking should be funded networking should be funded only only by the by the IST programme, or IST programme, or alsoalso by the other FP5 by the other FP5 programmesprogrammes

Intention is to keep working on the Intention is to keep working on the interconnection of the NRNs, as long as interconnection of the NRNs, as long as there is a need, and as long as that need there is a need, and as long as that need cannot be met sensibly by commercial cannot be met sensibly by commercial servicesservices

What are the lessons?What are the lessons?

Need for coherent A&R Need for coherent A&R networkingnetworking

A&R community forms a natural groupingA&R community forms a natural grouping It needs reliable high-bandwidth services, It needs reliable high-bandwidth services,

both nationally and internationallyboth nationally and internationally At the moment the needs and the traffic At the moment the needs and the traffic

are differentiated enough to keep them are differentiated enough to keep them separate from business, commercial, separate from business, commercial, school or home useschool or home use

[Good interconnections assumed][Good interconnections assumed] Basically we need NRNsBasically we need NRNs

Need for coherent European Need for coherent European networkingnetworking

Complexity - countries are different - different Complexity - countries are different - different structures for A&R - different ideas on structures for A&R - different ideas on industrial policyindustrial policy

But all of the countries need to interconnect But all of the countries need to interconnect their NRNs well (besides getting good their NRNs well (besides getting good connectivity to the US)connectivity to the US)

Organisationally we need projects like TEN-Organisationally we need projects like TEN-34, TEN-155 and successors34, TEN-155 and successors

They will change over time - involving more They will change over time - involving more open competition for the supply of open competition for the supply of infrastructure and servicesinfrastructure and services

Internet and the European Internet and the European economyeconomy

It is going to change society in many waysIt is going to change society in many ways It is going to be economically very important - It is going to be economically very important -

both for the telecoms suppliers, but also for both for the telecoms suppliers, but also for “normal” business“normal” business

I believe that it will change the whole I believe that it will change the whole economics of voice telephony and faxeconomics of voice telephony and fax

As a group we understand quite a bit about As a group we understand quite a bit about this and have a duty to explain it to our this and have a duty to explain it to our governments and fellow citizensgovernments and fellow citizens

Understanding Internet betterUnderstanding Internet better

We need better factsWe need better facts About traffic, performance, reliabilityAbout traffic, performance, reliability Who is using our networks - what for - Who is using our networks - what for -

whether they are hppy (getting their job whether they are hppy (getting their job done)done)

We (users, NRNs, ISPs) must be more open We (users, NRNs, ISPs) must be more open about these factsabout these facts

QoS and traffic flow separationQoS and traffic flow separation

Differentiated services offer a big Differentiated services offer a big opportunity to understand which opportunity to understand which community generates which sort of trafficcommunity generates which sort of traffic

Might be useful for all sorts of reasonsMight be useful for all sorts of reasons Including sending critical flows over Including sending critical flows over

separate lines (physically separate - separate lines (physically separate - maybe separately funded)maybe separately funded)

Networks for supercomputer Networks for supercomputer usersusers

BasicsBasics

Supercomputers can generate information Supercomputers can generate information faster than “normal” computersfaster than “normal” computers

Their users do not (normally) want or need Their users do not (normally) want or need to live close to the supercomputerto live close to the supercomputer

They need shared file systems to prepare They need shared file systems to prepare programs and dataprograms and data

Plus collaborative software development Plus collaborative software development environmentsenvironments

But … more info == more bandwidthBut … more info == more bandwidth How much (semi) interaction??How much (semi) interaction??

We all need ...We all need ...

Like all serious network users, Like all serious network users, supercomputer users need:-supercomputer users need:-– More bandwidthMore bandwidth– Smooth reliable operationSmooth reliable operation– No boundaries (between countries, between No boundaries (between countries, between

service providers)service providers) When they obtain those they will be able When they obtain those they will be able

to do better science and engineeringto do better science and engineering

The (general-purpose) Internet The (general-purpose) Internet in Europein Europe

Everything so farEverything so far

Was about A&R networkingWas about A&R networking But the Internet is also about people, But the Internet is also about people,

companies, economics, and society as a companies, economics, and society as a wholewhole

Europe has a tendency to treat the academic Europe has a tendency to treat the academic and commercial worlds as quite distinctand commercial worlds as quite distinct

Carried to extremes this can be dangerousCarried to extremes this can be dangerous

Reasons for European pessimism Reasons for European pessimism (1/2)(1/2)

Others (in this context, especially Americans) are at least Others (in this context, especially Americans) are at least as smart as we are.as smart as we are.

And they have 2-3 years more experience than us in And they have 2-3 years more experience than us in understanding the impact of the Internet on the economy understanding the impact of the Internet on the economy in particular, and society in general. That is a long time!in particular, and society in general. That is a long time!

The worlds of European business, commerce and banking The worlds of European business, commerce and banking completely fail (in my opinion) to understand the speed completely fail (in my opinion) to understand the speed with which the Internet is transforming our basic with which the Internet is transforming our basic economic assumptions.economic assumptions.

There are not many signs that the ex-PTTs will be able to There are not many signs that the ex-PTTs will be able to meet the double challenge of privatisation, and the meet the double challenge of privatisation, and the Internet revolution, hitting them at the same time. There Internet revolution, hitting them at the same time. There is a strong risk that they will stay national in their is a strong risk that they will stay national in their thinking for far too long.thinking for far too long.

Reasons for European pessimism Reasons for European pessimism (2/2)(2/2)

We never (really) created a strong European We never (really) created a strong European computing industrycomputing industry

We lack the venture capital “philosophy”???We lack the venture capital “philosophy”??? In Europe we did not succeed to build the alliance In Europe we did not succeed to build the alliance

between universities, research laboratories, the IT between universities, research laboratories, the IT industry, telecoms carriers, and politicians which, industry, telecoms carriers, and politicians which, in the USA, moved the Internet out from the labs in the USA, moved the Internet out from the labs and into a mass market. Fuelling a complete and and into a mass market. Fuelling a complete and virtuous economic cycle from research through to virtuous economic cycle from research through to production deployment and back to researchproduction deployment and back to research

Or, where we built the alliance in Europe, it was Or, where we built the alliance in Europe, it was not based around IPnot based around IP

Reasons for European optimism Reasons for European optimism (1/2)(1/2)

We are at least as smart as anyone elseWe are at least as smart as anyone else We can boast of many really excellent world We can boast of many really excellent world

class companiesclass companies Both in general, and in particular in Both in general, and in particular in

(traditional) telecoms equipment supply(traditional) telecoms equipment supply We have a vibrant mobile telephony industry We have a vibrant mobile telephony industry We (largely) liberalised the European We (largely) liberalised the European

telecoms market in January 1998. Even telecoms market in January 1998. Even Greece liberalises at end 2000. Greece liberalises at end 2000.

At this moment in time our national telecoms At this moment in time our national telecoms carriers are cash-richcarriers are cash-rich

Reasons for European optimism Reasons for European optimism (2/2)(2/2)

Many (not all) of our national A&R networks Many (not all) of our national A&R networks are excellentare excellent

So is TEN-34 (if still too expensive)So is TEN-34 (if still too expensive) (You can argue that) we have been good, (You can argue that) we have been good,

historically, at understanding the need for historically, at understanding the need for infrastructures, at planning for their infrastructures, at planning for their implementation, and at keeping them in good implementation, and at keeping them in good repair. [Roads, rail, airports, TGV et. al., repair. [Roads, rail, airports, TGV et. al., motorways, city centre transport, schools, motorways, city centre transport, schools, health care, mobile telephony,…]health care, mobile telephony,…]