Improving ISP Locality in BitTorrent Traffic via Biased Neighbor Selection Ruchir Bindal, Pei Cao, William Chan Stanford University Jan Medved, George

  • View
    212

  • Download
    0

Embed Size (px)

Text of Improving ISP Locality in BitTorrent Traffic via Biased Neighbor Selection Ruchir Bindal, Pei Cao,...

  • Slide 1
  • Improving ISP Locality in BitTorrent Traffic via Biased Neighbor Selection Ruchir Bindal, Pei Cao, William Chan Stanford University Jan Medved, George Suwala, Tony Bates, Amy Zhang Cisco Systems, Inc.
  • Slide 2
  • P2P and ISPs: Not Friends P2P applications are notoriously difficult to traffic engineer P2P applications are notoriously difficult to traffic engineer ISPs: different links have different monetary costs P2P applications: Peers are all equal Peers are all equal Choices made based on measured performance Choices made based on measured performance No regards for underlying ISP topology or preferences No regards for underlying ISP topology or preferences
  • Slide 3
  • P2P and ISPs: Cant Be Foes ISPs: need P2P for customers ISPs: need P2P for customers P2P: need ISPs for bandwidth P2P: need ISPs for bandwidth Current state of affairs: a clumsy co- existence Current state of affairs: a clumsy co- existence ISPs throttle P2P traffic along high-cost links Users suffer
  • Slide 4
  • Can They Be Partners? ISPs inform P2P applications of its preferences ISPs inform P2P applications of its preferences P2P applications schedule traffic in ways that benefit both Users and ISPs P2P applications schedule traffic in ways that benefit both Users and ISPs This paper gives an example for BitTorrent
  • Slide 5
  • Outline Review of BitTorrent Review of BitTorrent Biased Neighbor Selection: Biased Neighbor Selection: Design and Implementations Evaluations Comparison with Alternatives Comparison with Alternatives
  • Slide 6
  • BitTorrent File Sharing Network Goal: replicate K chunks of data among N nodes Form neighbor connection graph Form neighbor connection graph Neighbors exchange data Neighbors exchange data
  • Slide 7
  • BitTorrent: Neighbor Selection Tracker file.torrent 1 Seed Whole file A 5 2 3 4
  • Slide 8
  • BitTorrent: Piece Replication Tracker file.torrent 1 Seed Whole file A 3 2
  • Slide 9
  • BitTorrent: Piece Replication Algorithms Tit-for-tat (choking/unchoking): Tit-for-tat (choking/unchoking): Each peer only uploads to 7 other peers at a time 6 of these are chosen based on amount of data received from the neighbor in the last 20 seconds The last one is chosen randomly, with a 75% bias toward new comers (Local) Rarest-first replication: (Local) Rarest-first replication: When peer 3 unchokes peer A, A selects which piece to download
  • Slide 10
  • Performance of BitTorrent Conclusion from modeling studies: BitTorrent is nearly optimal in idealized, homogeneous networks Conclusion from modeling studies: BitTorrent is nearly optimal in idealized, homogeneous networks Demonstrated by simulation studies Confirmed by theoretical modeling studies Intuition: in a random graph, Intuition: in a random graph, Prob(Peer As content is a subset of Peer Bs) 50%
  • Slide 11
  • Random Neighbor Selection Existing studies all assume random neighbor selection Existing studies all assume random neighbor selection BitTorrent no longer optimal if nodes in the same ISP only connect to each other Random neighbor selection high cross- ISP traffic Random neighbor selection high cross- ISP traffic Q: Can we modify the neighbor selection scheme without affecting performance?
  • Slide 12
  • Biased Neighbor Selection Idea: of N neighbors, choose N-k from peers in the same ISP, and choose k randomly from peers outside the ISP Idea: of N neighbors, choose N-k from peers in the same ISP, and choose k randomly from peers outside the ISP ISP
  • Slide 13
  • Implementing Biased Neighbor Selection By Tracker By Tracker Need ISP affiliations of peers Peer to AS maps Peer to AS maps Public IP address ranges from ISPs Public IP address ranges from ISPs Special X- HTTP header Special X- HTTP header By traffic shaping devices By traffic shaping devices Intercept peer tracker messages and manipulate responses No need to change tracker or client
  • Slide 14
  • Evaluation Methodology Event-driven simulator Event-driven simulator Use actual client and tracker codes as much as possible Calculate bandwidth contention, assume perfect fair- share from TCP Network settings Network settings 14 ISPs, each with 50 peers, 100Kb/s upload, 1Mb/s download Seed node, 400Kb/s upload Optional university nodes (1Mb/s upload) Optional ISP bottleneck to other ISPs
  • Slide 15
  • Limitation of Throttling
  • Slide 16
  • Throttling: Cross-ISP Traffic Redundancy: Average # of times a data chunk enters the ISP
  • Slide 17
  • Biased Neighbor Selection: Download Times
  • Slide 18
  • Biased Neighbor Selection: Cross- ISP Traffic
  • Slide 19
  • Importance of Rarest-First Replication Random piece replication performs badly Random piece replication performs badly Increases download time by 84% - 150% Increase traffic redundancy from 3 to 14 Biased neighbors + Rarest-First More uniform progress of peers Biased neighbors + Rarest-First More uniform progress of peers
  • Slide 20
  • Biased Neighbor Selection: Single-ISP Deployment
  • Slide 21
  • Presence of External High- Bandwidth Peers Biased neighbor selection alone: Biased neighbor selection alone: Average download time same as regular BitTorrent Cross-ISP traffic increases as # of university peers increase Result of tit-for-tat Result of tit-for-tat Biased neighbor selection + Throttling: Biased neighbor selection + Throttling: Download time only increases by 12% Most neighbors do not cross the bottleneck Most neighbors do not cross the bottleneck Traffic redundancy (i.e. cross-ISP traffic) same as the scenario without university peers
  • Slide 22
  • Comparison with Alternatives Gateway peer: only one peer connects to the peers outside the ISP Gateway peer: only one peer connects to the peers outside the ISP Gateway peer must have high bandwidth It is the seed for this ISP It is the seed for this ISP Ends up benefiting peers in other ISPs Caching: Caching: Can be combined with biased neighbor selection Biased neighbor selection reduces the bandwidth needed from the cache by an order of magnitude
  • Slide 23
  • Summary By choosing neighbors well, BitTorrent can achieve high peer performance without increasing ISP cost By choosing neighbors well, BitTorrent can achieve high peer performance without increasing ISP cost Biased neighbor selection: choose initial set of neighbors well Can be combined with throttling and caching P2P and ISPs can collaborate!
  • Slide 24
  • Related Work Many modeling studies of BitTorrent Many modeling studies of BitTorrent Simulation studies Simulation studies Measurements of real torrents Measurements of real torrents
  • Slide 25
  • Future Work Implementation of tracker-side changes and experiments Implementation of tracker-side changes and experiments Theoretical modeling of biased neighbor selection Theoretical modeling of biased neighbor selection Dynamic biased neighbor selection for global congestion avoidance Dynamic biased neighbor selection for global congestion avoidance