P4P : Provider Portal for (P2P) Applications

Transcription

1 P4P : Provider Portal for (P2P) Applications Haiyong Xie Laboratory of Networked Systems Yale University Laird Popkin Pando Networks, Inc

2 P2P : Bandwidth Usage Traffic: Internet Protocol Breakdown File-Types: Major P2P Networks Up to 50-70% of Internet traffic is contributed by P2P applications Cache logic research: Internet protocol breakdown ; Velocix: File-types on major P2P networks.

3 A Fundamental Problem Network-oblivious P2P applications may not be network efficient 50%-90% of existing local pieces in active users are downloaded externally Average P2P bit traverses 1000 miles / 5.5 metro hops in Verizon network Traditional Internet architectural feedback to applications is limited: routing (hidden) rate control through coarse-grained TCP congestion feedback Emerging applications such as P2P can have tremendous flexibility in shaping how data is communicated more information and feedback are needed to most effectively utilize this flexibility, and for improving network efficiency

4 P4P Mission Design a framework to enable better providers and applications cooperation ISP perspective: guide applications to achieve more efficient network usage P2P perspective: better user experiences P4P: provider portal for (P2P) applications a provider can be a traditional ISP (e.g., AT&T, Verizon) or a content distribution provider (e.g., Akamai), or a caching provider (e.g., PeerApp)

5 The P4P Framework: Control Plane itracker: a portal for each network resource provider (iportal) An itracker provides multiple interfaces Static topology / policy Provider capability Virtual cost itracker of a provider can be identified in multiple ways e.g., through DNS SRV records; whois itracker can be run by trusted third parties itracker access protected by access control

6 Virtual Cost Interface: Network Internal View Terms PIDs: set of nodes each called a PID E: set of links connecting PIDs p e : the virtual cost of link e Benefit: simplicity and flexibility Usage of virtual cost can be used to rank peers, or converted to peering weights reflects both network status and policy, e.g., OSPF weights PID6 higher prices on links with highest util. or higher than a threshold congestion volume (Briscoe) 30 PID1 PID5 70 PID2 PID PID3

7 Virtual Cost Interface: Applications View 70 PID PID2 ISP computes the cost from one PID to another - link cost and routing PID-pair costs are perturbed to increase privacy PID6 PID3 PID5 PID4 Applications query costs of related PID pairs, adjust traffic patterns to place less load on more expensive pairs

8 Interdomain: Application External View Application obtains cost for top (ASN, PID) pairs Intradomain cost + interdomain cost From AS 1 s point view (AS1, PID1) (AS2, PID2) Intradomain cost + interdomain cost From AS 2 s point view

9 Example: P4P Protocol for BT Information flow: ptracker 1 4 peer 2 3 itracker ISP A 1. peer queries ptracker 2/3. ptracker asks itracker for virtual cost (occasionally) 4. ptracker selects and returns a set of active peers, according to both the virtual prices and its own P2P objective

10 Complete Set: Feb 21 to April 2008 FTTH 209% faster!

11 Current P4P-WG: 70+ Members ISPs, P2Ps, Researchers. Scope includes business processes, protocols, education, etc. Core! Group! AT&T! Bezeq Intl! BitTorrent! Cisco Systems! Comcast! Grid Networks! Joost! LimeWire! Manatt! Oversi! Pando Networks! PeerApp! Solid State! Telefonica Group! Velocix! VeriSign! Telecom Italia! Verizon! Vuze! University of Toronto! Univ of Washington! Yale University! Observers! Abacast! AHT Intl! AjauntySlant! Akamai! Alcatel Lucent! CableLabs! Cablevision! Cox Comm! Exa Networks! Juniper Networks! Lariat Network! Level 3 Communications! Limelight Networks! Microsoft! MPAA! NBC Universal! Nokia! Orange! Princeton University! RawFlow! RSUC/GweepNet! SaskTel! Solana Networks! Speakeasy Network! Stanford University! Thomson! Time Warner Cable! Turner Broadcasting! UCLA!

12 Acknowledgements Joint work with Y. Richard Yang (Yale) Arvind Krishnamurthy (University of Washington) Avi Silberschatz (Yale) Extremely grateful to Members of Yale Laboratory of Networked Systems (LANS): Richard Alimi, Hao Wang, Ye Wang, Glenn Thrope Charles Kalmanek (AT&T Labs) Marty Lafferty (DCIA) Doug Pasko (Verizon) Laird Popkin (Pando) Rich Woundy (Comcast) Members of the P4P working group

13 Discussions I: Possible modifications to/uses of IETF protocols Trackerless p2p use a mechanism to locate itrackers (e.g. DNS) Tracker-based p2p A mechanism for clients to find their (ASN, PID) (i.e. easier than IP mapping) A lookup mechanism for finding the itracker for a given ASN. Enable P2P to "play nice" with ISPs A mechanism for determining the ISPs usage policies, and the user's usage against quota. Imagine using a cell phone without being able to tell how many minutes you've used. A standard mechanism for marking "bulk data" (i.e. not time sensitive).

14 Discussion II: Usage of Virtual Cost ISP Application Rank peers the lower the cost from (ASNi, PIDi) to (ASNj, PIDj), the higher the ranking of peers in (ASNj, PIDj) when selecting peers for a node in (ASNi, PIDi) Manual virtual cost configuration Virtual cost by Primal-Dual Virtual cost as ranking Blackbox usage Peer Selection Weight Matrix Issues interpreting the virtual cost as ranking is too coarse-grained P2P applications use structured peer selection, e.g., achieve certain connectivity, select one super peer,

15 Discussions III: P4P Data Plane ISP A b ISP B a Routers mark packets to provide faster, fine-grained feedbacks, e.g., virtual capacity to optimize multihoming cost and performance - applications adjust traffic rates according to feedbacks Applications mark importance of traffic