NSF/Mideast Workshop Future Internet Architectures Panel Convener: - PowerPoint PPT Presentation

NSF/Mideast Workshop Future Internet Architectures Panel Convener: Zhi-Li Zhang University of Minnesota

Panelists • Jeff Chase, Duke University • Sonia Fahmy, Purdue University • George Kesidis, Penn State University • Taieb Znati, Pittsburgh University • Zhi-Li Zhang, University of Minnesota

Internet: Past & Now • From the original 4-node ARPANet (in 1969) – underwent a few transformations • to today’s “hourglass” Internet architecture – based on TCP/IP (+ DNS & BGP) as the core networking protocols • Original Internet Design Goals: David Clark [Sigcomm88] In the order of importance: 0 Connect existing networks 1. Survivability 2. Support multiple types of services 3. Must accommodate a variety of networks 4. Allow distributed management 5. Allow host attachment with a low level of effort 6. Be cost effective 7. Allow resource accountability

What Has Become of Internet • Information Service Platform – deliver all kinds of information (web, iTune, YouTube, Netflix, …) • Global Information Repository – store and search for all kinds of information (e.g., Dropbox) • Cyberspace and Virtual Communities – keep in touch with friends and strangers (e.g., Facebook, Twitter) • Enormous Super-Computer – cloud & mobile computing and services • What’s coming: Internet of Things Ø … we increasingly depend on it!

Diverging Trends … • Internet Core: concentration – high bandwidth, dense connectivity – data centers: computing, storage, networking, … • Internet Edges: diversification – “smart” to “dumb” devices • PCs with significant processing and storage capacities • small or mobile devices with limited computing, memory, power, … – broadband to narrowband – “always on” to intermittent connectivity Challenges and Opportunities! overcome heterogeneity, seamlessly integrate • new services & “disruptive” technologies •

Within the Internet Core • Large ISPs with large geographical span and • Large content providers with huge data centers • High capacity, dense and rich topology • Cloud Computing/Services and Mobile Computing

On the Internet Edge … Games • Large number of mobile users Multimedia Online TV Streaming Web/emails • Large number of “dumb” or “smart” devices and appliances, some resource constrained Internet ¡ Home users • Intermittent connectivity dumb & with varying bandwidth smart phones Surveillance Banking & • Diverse applications and & Security VoIP e-commerce services POTS • Heterogeneous technologies

Challenges Facing Today’s Internet • Scalability: capability to connect tens of thousands, millions or more users and devices – routing table size, constrained by router memory, lookup speed • Availability & Reliability: must be resilient to failures – need to be “proactive” instead of reactive; need to localize effect of failures • Mobility: users and hosts/servers are more mobile – need to separate location (“addressing”) and identity (“naming”) • Manageability: ease of deployment, “plug-&-play” – need to minimize manual configuration – self-configure, self-organize, while ensuring security and trust • Security & Privacy: – in addition to encryption, etc, how to distinguish “good” guys from “bad” guys à need a “social, behavioral & economic” perspectives! • Economic Viability – various stakeholders, often with shared but also competing interests

Challenges Facing Today’s Internet • Scalability: capability to connect tens of thousands, millions or more users and devices – routing table size, constrained by router memory, lookup speed • Availability & Reliability: must be resilient to failures Internet: – need to be “proactive” instead of reactive; need to localize effect of failures • Mobility: users and hosts/servers are more mobile critical global information infrastructure, – need to separate location (“addressing”) and identity (“naming”) big, complex, massively distributed, and changing! • Manageability: ease of deployment, “plug-&-play” – need to minimize manual configuration – self-configure, self-organize, while ensuring security and trust • Security & Privacy: – in addition to encryption, etc, how to distinguish “good” guys from “bad” guys à need a “social, behavioral & economic” perspectives! • Economic Viability – various stakeholders, often with shared but also competing interests

US NSF “Future Internet Architectures” Initiatives Started circa 2006, two phases • Phase I: FIND (Future Internet Network Design) Initiative – A number of small and medium-size projects funded – See http://www.nets-find.net • Phase 2: FIA (Future Integrative Architectures) Initiative – Four large multi-institution projects funded • eXpressive Internet Architecture (PI: Peter Steenkiste, CMU) • MobilityFirst (PI: Dipankar Raychaudhuri, Rutgers U.) • Named Data Networking (PI: Lixia Zhang, UCLA) • NEBULA (PI: Jonathan Smith, U. of Pennsylvania) – See http://www.nets-fia.net • Separately, GENI Initiative (serving as testbed?)

Why Research on “Future/New Internet Architectures” My personal perspective: • Many short-term “fixes/patches” have been developed/applied – fix some problems but introduce others; e.g., NAT, firewalls – also make things more complex and error-prone (esp. net config.) • Certain limitations of the Internet architecture require radical changes and long-term solutions – need “out-of-the-box” re-thinking of network architectures – where the (academic) research community can play a significant role! • “Clean-slate” (re-)designs of Internet architectures – unconstrained by the current Internet’s “idiosyncrasies” – unencumbered by “conventional wisdoms”

Panelists • Jeff Chase, Duke University • Sonia Fahmy, Purdue University • George Kesidis, Penn State University • Taieb Znati, Pittsburgh University • Zhi-Li Zhang, University of Minnesota

NSF/Mideast Workshop New Internet Architectures Panel VIRO: Scalable, Robust & Name-Independent V irtual I d Ro uting for (future) Large-scale, Dynamic Networks Zhi-Li Zhang Qwest Chair Professor Department of Computer Science and Engineering University of Minnesota Email: zhzhang@cs.umn.edu

Designed to Meet Challenges posed by Large, Dynamic Networks (e.g., Data Center Networks) • Scalability: capability to connect tens of thousands, millions or more users and devices – routing table size, constrained by router memory, lookup speed • Mobility: hosts are more mobile – need to separate location (“addressing”) and identity (“naming”) • Availability & Reliability: must be resilient to failures – need to be “proactive” instead of reactive – need to localize effect of failures • Manageability: ease of deployment, “plug-&-play” – need to minimize manual configuration – self-configure, self-organize, while ensuring security and trust – Agility: dynamically adapt to demand • ......

Pros & Cons of Existing Technologies • (Layer-2) Ethernet/Wireless q (Layer-3) IPv4/IPv6 LANs ¤ Pluses: u Pluses: • better data plane scalability , more • plug-&-play , minimal “ optimal ” routing, … configuration, better ¤ Minuses: mobility • control plane flooding , global effect of u Minuses: network failures • (occasional) data plane • poor support for mobility flooding , sub-optimal • difficulty/complexity in “network routing (using spanning renaming” tree), not robust to failures • Esp., changing addressing schemes • Not scalable to large (& (IPv4 -> IPv6 transition) requires wide-area) networks modifications in routing and other – IETF TRILL network protocols

Meeting the Challenges: VIRO: A Scalable, Robust, Namespace- Independent, “Plug-&-Play” Routing Architecture • Decoupling routing from naming/”addressing” – “native” naming/address-independent • “future-proof” & capable of supporting multiple namespaces • Introduce a “self-organizing” virtual id (vid) layer – a layer 2 (LLC)/layer-3 convergence layer – subsume layer-2/layer-3 routing/forwarding functionality • except for first/last hop: host to switch or switch to host • layer-3 addresses (or higher layer names): global addressing or naming for inter-networking and “persistent” identifiers DHT-style routing using a topology-aware, structured vid space l • highly scalable and robust: going beyond shortest-path routing, with built- in multi-path & fast rerouting capabilities, – O(log N) routing table size, localize failures, enable fast rerouting • support multiple topologies or virtualized network services