Improving ISP Locality Improving ISP Locality in BitTorrent Traffic in BitTorrent Traffic via Biased Neighbor via Biased Neighbor Selection Selection Ruchir Bindal, Ruchir Bindal, Pei Cao Pei Cao , , William Chan William Chan Stanford University Stanford University Jan Medved, George Suwala, Jan Medved, George Suwala, Tony Bates, Amy Zhang Tony Bates, Amy Zhang Cisco Systems, Inc. Cisco Systems, Inc.
25
Embed
Improving ISP Locality in BitTorrent Traffic via Biased Neighbor Selection Ruchir Bindal, Pei Cao, William Chan Stanford University Jan Medved, George.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Improving ISP Locality in Improving ISP Locality in BitTorrent Traffic via Biased BitTorrent Traffic via Biased
Neighbor SelectionNeighbor Selection
Ruchir Bindal, Ruchir Bindal, Pei CaoPei Cao, William , William ChanChan
Stanford UniversityStanford UniversityJan Medved, George Suwala, Tony Jan Medved, George Suwala, Tony
Bates, Amy ZhangBates, Amy ZhangCisco Systems, Inc.Cisco Systems, Inc.
P2P and ISPs: Not FriendsP2P and ISPs: Not Friends
• P2P applications are notoriously P2P applications are notoriously difficult to “traffic engineer”difficult to “traffic engineer”– ISPs: different links have different ISPs: different links have different
•Choices made based on measured Choices made based on measured performanceperformance
•No regards for underlying ISP topology or No regards for underlying ISP topology or preferencespreferences
P2P and ISPs: Can’t Be FoesP2P and ISPs: Can’t Be Foes
• ISPs: need P2P for customersISPs: need P2P for customers
• P2P: need ISPs for bandwidthP2P: need ISPs for bandwidth
• Current state of affairs: a clumsy co-Current state of affairs: a clumsy co-existenceexistence– ISPs “throttle” P2P traffic along high-cost ISPs “throttle” P2P traffic along high-cost
linkslinks– Users sufferUsers suffer
Can They Be Partners?Can They Be Partners?
• ISPs inform P2P applications of its ISPs inform P2P applications of its preferencespreferences
• P2P applications schedule traffic in P2P applications schedule traffic in ways that benefit both Users and ISPsways that benefit both Users and ISPs
This paper gives an example for This paper gives an example for BitTorrentBitTorrent
OutlineOutline
• Review of BitTorrent Review of BitTorrent
• Biased Neighbor Selection: Biased Neighbor Selection: – Design and ImplementationsDesign and Implementations– EvaluationsEvaluations
• Comparison with AlternativesComparison with Alternatives
• ““Tit-for-tat” (choking/unchoking):Tit-for-tat” (choking/unchoking):– Each peer only uploads to 7 other peers at a timeEach peer only uploads to 7 other peers at a time– 6 of these are chosen based on amount of data 6 of these are chosen based on amount of data
received from the neighbor in the last 20 secondsreceived from the neighbor in the last 20 seconds– The last one is chosen randomly, with a 75% bias The last one is chosen randomly, with a 75% bias
toward new comerstoward new comers
• (Local) Rarest-first replication:(Local) Rarest-first replication:– When peer 3 unchokes peer A, A selects which When peer 3 unchokes peer A, A selects which
piece to downloadpiece to download
Performance of BitTorrentPerformance of BitTorrent
• Conclusion from modeling studies: Conclusion from modeling studies: BitTorrent is nearly optimal in BitTorrent is nearly optimal in idealized, homogeneous networksidealized, homogeneous networks– Demonstrated by simulation studiesDemonstrated by simulation studies– Confirmed by theoretical modeling Confirmed by theoretical modeling
studiesstudies• Intuition: in a random graph, Intuition: in a random graph,
Prob(Peer A’s content is a subset of Peer B’s) ≤ Prob(Peer A’s content is a subset of Peer B’s) ≤ 50%50%
Random Neighbor SelectionRandom Neighbor Selection
• Existing studies all assume random Existing studies all assume random neighbor selectionneighbor selection– BitTorrent no longer optimal if nodes in BitTorrent no longer optimal if nodes in
the same ISP only connect to each otherthe same ISP only connect to each other
• Random neighbor selection Random neighbor selection high high cross-ISP trafficcross-ISP traffic
Q: Can we modify the neighbor selection Q: Can we modify the neighbor selection scheme without affecting scheme without affecting performance?performance?
• Idea: of N neighbors, choose N-k from Idea: of N neighbors, choose N-k from peers in the same ISP, and choose k peers in the same ISP, and choose k randomly from peers outside the ISPrandomly from peers outside the ISP
Importance of Rarest-First Importance of Rarest-First ReplicationReplication
• Random piece replication performs Random piece replication performs badlybadly– Increases download time by 84% - 150%Increases download time by 84% - 150%– Increase traffic redundancy from 3 to 14Increase traffic redundancy from 3 to 14
• Biased neighbors + Rarest-First Biased neighbors + Rarest-First More uniform progress of peersMore uniform progress of peers
Presence of External High-Presence of External High-Bandwidth PeersBandwidth Peers
• Biased neighbor selection alone: Biased neighbor selection alone: – Average download time same as regular Average download time same as regular
BitTorrentBitTorrent– Cross-ISP traffic increases as # of “university” Cross-ISP traffic increases as # of “university”
peers increasepeers increase• Result of tit-for-tatResult of tit-for-tat
• Biased neighbor selection + Throttling: Biased neighbor selection + Throttling: – Download time only increases by 12%Download time only increases by 12%
• Most neighbors do not cross the bottleneckMost neighbors do not cross the bottleneck
– Traffic redundancy (i.e. cross-ISP traffic) same Traffic redundancy (i.e. cross-ISP traffic) same as the scenario without “university” peersas the scenario without “university” peers
Comparison with Comparison with AlternativesAlternatives• Gateway peer: only one peer connects to Gateway peer: only one peer connects to
the peers outside the ISPthe peers outside the ISP– Gateway peer must have high bandwidthGateway peer must have high bandwidth
• It is the “seed” for this ISPIt is the “seed” for this ISP
– Ends up benefiting peers in other ISPsEnds up benefiting peers in other ISPs
• Caching:Caching:– Can be combined with biased neighbor selectionCan be combined with biased neighbor selection– Biased neighbor selection reduces the Biased neighbor selection reduces the
bandwidth needed from the cache by an order bandwidth needed from the cache by an order of magnitudeof magnitude
SummarySummary
• By choosing neighbors well, BitTorrent By choosing neighbors well, BitTorrent can achieve high peer performance can achieve high peer performance without increasing ISP costwithout increasing ISP cost– Biased neighbor selection: choose initial Biased neighbor selection: choose initial
set of neighbors wellset of neighbors well– Can be combined with throttling and Can be combined with throttling and
cachingcaching
P2P and ISPs can collaborate!P2P and ISPs can collaborate!
Related WorkRelated Work
• Many modeling studies of BitTorrentMany modeling studies of BitTorrent
• Simulation studiesSimulation studies
• Measurements of real torrentsMeasurements of real torrents
Future WorkFuture Work
• Implementation of tracker-side Implementation of tracker-side changes and experimentschanges and experiments
• Theoretical modeling of biased Theoretical modeling of biased neighbor selectionneighbor selection