internet2 background aarnet-internet2 workshop :: sydney guy almes 10 october 2001

Post on 06-Jan-2018

227 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

DESCRIPTION

Internet2 Engineering Objectives Provide our universities with superlative networking: Performance Functionality Understanding Make superlative networking strategic for university research and education

TRANSCRIPT

Internet2 Background

AARnet-Internet2 Workshop :: SydneyGuy Almes <almes@internet2.edu>

10 October 2001

Outline• Historical Context• Internet2: Organization and Membership• Emphases

• Network infrastructure• Engineering• Applications• Middleware

• International Relationships

Internet2 Engineering Objectives

• Provide our universities with superlative networking:• Performance• Functionality• Understanding

• Make superlative networking strategic for university research and education

Historical Context

• NSFnet Experience• 1985-1995 NSFnet program• Created pervasive Internet among universities• From 56 kb/s to 45 Mb/s performance• Intense university-government-industry cooperation

• Transition to Commercial Internet• 1995 growing pains• Lack of focus on university needs

What did we miss?

• Focus on needs of universities• University-government-industry

partnership• Stagnation of technical advances

What did we miss?• Focus on needs of universities

• Disproportionate need to support collaboration• Collaboration structures do not align with

organizational structures• Remote instrument access• New resource-intensive applications needed

• University-government-industry partnership

• Stagnation of technical advances

What did we miss?• Focus on needs of universities• University-government-industry

partnership• In late 1980s NSF could lead national Internet policy

direction• By the mid-1990s, this was not practical• Key parts of industry and government continue to

see value in partnering with universities• Stagnation of technical advances

What did we miss?

• Focus on needs of universities• University-government-industry

partnership• Stagnation of technical advances

• Commercial emphases on residential Internet, on eCommerce, etc.

• No specific continuing improvement in wide-area performance or on solidification of multicast, QoS, etc., as key parts of the Internet

Internet2

• Created as a project: Oct-96• 34 members; synergy with federal NGI program• Reliance on NSF/MCI vBNS program for backbone

• Incorporated Oct-97• Staff mostly at Ann Arbor, Armonk, Washington• 187 university members, plus corporate/affiliate

members• Announcement of Abilene Backbone spring 1998

Emphasis: Network Infrastructure

• Existing vBNS: 620 Mb/s IP-over-ATM• Creation of gigaPoPs

• MREN, MERIT, MCNC, SURA, CENIC• New others and focused local energy on all• Recent creation of The Quilt organization

• 1998-2003: Abilene• 2.4 Gb/s IP-over-Sonet• Qwest, Nortel, Cisco, Indiana University

Key Attributes• 12 Router Nodes

• Cisco 12008 Routers• Qwest collocation

• OC48 Interior Circuits connect them• Packet over Sonet in all cases

• Access: 54 total• OC3, OC12, and some OC48• via any Qwest Sonet PoPs (Access Nodes)• ATM and POS both supported

Abilene core

Seattle

Kansas City

Denver

Cleveland

New York

Atlanta

Houston

Sunnyvale

Los Angeles

Indianapolis Washington

Chicago

Abilene Connectionsby (roughly) October 2001

Emphasis: Engineering

• Advanced Services• Multicast• Quality of Service (QoS)• IPv6• Measurements

• Advanced Performance• End-to-end Performance Initiative

Engineering: Multicast• By 1998,

• Routing protocols existed• Deployment of native IP multicast quite rare• Early ‘MBone’ no longer scalable• Considered key to advanced conferencing and streaming

applications• Emphases on

• Deployment and support for operations• Applications• Working to make it scalable

Engineering: QoS

• What if best-efforts networking will not meet the needs of advanced applications?

• Stress of Interoperability

• Stress of Application needs

• Preserve core Internet values

Engineering: IPv6

• Clarify motivation for IPv6

• Support deployment and engineering expertise on networks, especially on campus

• Anticipate need for first-class support

Engineering: Measurements

• Utilization

• Performance

• Characterization of network usage

• Think global – act local

Engineering:End-to-End Performance

The Current Situation• Our universities have access to an

infrastructure of considerable capacity• examples of 240 Mb/s flows

• End-to-end performance varies widely• but 40 Mb/s flows not always predictable• users don't know what their expectations should be

• Note the mismatch

What are our Aspirations?• Candidate Answer #1:

Switched 100BaseT + Well-provisioned Internet2 networking at 80 Mb/s

• But user expectations and experiences vary widely

What are our Aspirations?• Candidate Answer #2:

Lower user expectations and minimize complaining phone calls

• There is a certain appeal I suppose...

What are our Aspirations?• Candidate Answer #3:

Raise expectations, encourage aggressive use, deliver on performance/functionality to key constituencies.

• Not the easy way, but necessary for success

Threats toEnd to End Performance

• BW = C x packet-size / ( delay x sqrt(packet-loss ))(Mathis, Semke, Mahdavi, and Ott, CCR, July 1997)

• Context:• Network capacity• Geographical distance• Aggressive application

Threats toEnd to End Performance

• Fiber problems• dirty fiber• dim lighting• 'not quite right' connectors

Threats toEnd to End Performance

• Fiber problems• Switches

• horsepower• full vs half-duplex• head-of-line blocking

Threats toEnd to End Performance

• Fiber problems• Switches• Inadvertently stingy provisioning

• mostly communication• happens also in international settings

Threats toEnd to End Performance

• Fiber problems• Switches• Inadvertently stingy provisioning• Wrong Routing

• asymmetric• best use of Internet2• distance

Threats toEnd to End Performance

• Fiber problems• Switches• Inadvertently stingy provisioning• Wrong Routing• Host issues

• NIC• OS / TCP stack• CPU

Perverse Result• 'Users' think the network is congested or

that the Internet2 infrastructure cannot help them

• 'Planners' think the network is underutilized, no further investment needed, or that users don't need high performance networks

Internet2 End-to-End Performance Initiative

• Very recently hired / deployed staff• Cheryl Munn-Fremon, initiative director• Russ Hobby, chief technical architect• George Brett, chief information architect

• $1.5M budgeted by Internet2

Internet2 End-to-End Performance Initiative

• Distributed measurement infrastructure• Enable rapid effective understanding of why an

instance of end-to-end performance is limited• Make the work of PERF participants rewarding• Enable initiation of tests by PERF participants

• Teams of performance analysis specialists (PERF)• Dissemination of best practices

Internet2 End-to-End Performance Initiative

• Distributed measurement infrastructure

• Teams of performance analysis specialists (PERF)• members at campuses, gigaPoPs, backbones• socially and technically coordinated• committed to effecting radical change

• Dissemination of best practices

Internet2 End-to-End Performance Initiative

• Distributed measurement infrastructure• Teams of performance analysis specialists (PERF)

• Dissemination of best practices• Identify key techniques, tools, and 'best practices'• Make them common• Work toward widespread / routine excellent user

experiences• Improve the reputation / status of network

engineers

Anticipated Partners• NLANR: DAST, MOAT, and NCNE• Web100 Project• Abilene partners• Leading campuses and gigaPoPs• Internet2 corporate members

Access to Key Resources• Optical telescopes in Hawaii

• CRAFT Project

• PACI Supercomputer Facilities

• CERN

top related