Multiclass P2P Networks: Static Resource Allocation for Service Differentiation and Bandwidth Diversity Florence Clévenot-Perronnin, Philippe Nain and.

Slides:



Advertisements
Similar presentations
1 Coupon Replication Systems Laurent Massoulié & Milan Vojnović Microsoft Research Cambridge, UK.
Advertisements

Network Resource Broker for IPTV in Cloud Computing Lei Liang, Dan He University of Surrey, UK OGF 27, G2C Workshop 15 Oct 2009 Banff,
P2P Streaming Protocol Pro- incentive Parameters draft-zeng-ppsp-protocol-pro-incentive-para-01 IETF79 Meeting Wenjun (Kevin) Zeng & Yingjie Gu Huawei.
Layered Video for Incentives in P2P Live Streaming
Xia Zhou*, Stratis Ioannidis ♯, and Laurent Massoulié + * University of California, Santa Barbara ♯ Technicolor Research Lab, Palo Alto + Technicolor Research.
Optimal Scheduling in Peer-to-Peer Networks Lee Center Workshop 5/19/06 Mortada Mehyar (with Prof. Steven Low, Netlab)
Rarest First and Choke Algorithms Are Enough
Rarest First and Choke Algorithms are Enough Arnaud LEGOUT INRIA, Sophia Antipolis France G. Urvoy-Keller and P. Michiardi Institut Eurecom France.
The BitTorrent Protocol. What is BitTorrent?  Efficient content distribution system using file swarming. Does not perform all the functions of a typical.
The BitTorrent protocol A peer-to-peer file sharing protocol.
Incentives Build Robustness in BitTorrent Bram Cohen.
Presented by: Su Yingbin. Outline Introduction SocialSwam Design Notations Algorithms Evaluation Conclusion.
Agenda Introduction BT + Multimedia Experimental Conclusion 2.
X stream Project proposal. Project goals: Students Students: Academic Supervisor Academic Supervisor: Advisors: Developing and Implementing a large scale.
Playback delay in p2p streaming systems with random packet forwarding Viktoria Fodor and Ilias Chatzidrossos Laboratory for Communication Networks School.
Peer-assisted On-demand Streaming of Stored Media using BitTorrent-like Protocols Authors: Niklas Carlsson & Derek L. Eager Published in: Proc. IFIP/TC6.
1 Communication Networks Kolja Eger, Prof. Dr. U. Killat 1 From Packet-level to Flow-level Simulations of P2P Networks Kolja Eger, Ulrich Killat Hamburg.
Stochastic Analysis of File Swarming Systems The Chinese University of Hong Kong John C.S. Lui Collaborators: D.M. Chiu, M.H. Lin, B. Fan.
1 Analysis of BitTorrent-like Protocols for On-Demand Stored Media Streaming Khandoker Nadim Parvez Carey Williamson Anirban Mahanti Niklas Carlsson.
Seed Scheduling for Peer-to-Peer Networks Flavio Esposito Ibrahim Matta Pietro Michiardi Nobuyuki Mitsutake Damiano Carra.
Short-Term Fairness and Long- Term QoS Lei Ying ECE dept, Iowa State University, Joint work with Bo Tan, UIUC and R. Srikant, UIUC.
Load Balancing of Elastic Traffic in Heterogeneous Wireless Networks Abdulfetah Khalid, Samuli Aalto and Pasi Lassila
Queueing Models for P2P Systems.  Extend classical queuing theory for P2P systems.  Develop taxonomy for different variations of these queuing models.
Resource Pooling A system exhibits complete resource pooling if it behaves as if there was a single pooled resource. The Internet has many mechanisms for.
Modelling and Performance Analysis of BitTorrent-Like Peer-to-Peer Networks.
Analyzing and Improving BitTorrent Ashwin R. Bharambe ( Carnegie Mellon University ) Cormac Herley ( Microsoft Research, Redmond ) Venkat Padmanabhan (
CompSci 356: Computer Network Architectures Lecture 21: Content Distribution Chapter 9.4 Xiaowei Yang
A Game Theoretic Approach to Provide Incentive and Service Differentiation in P2P Networks John C.S. Lui The Chinese University of Hong Kong Joint work.
Alex Sherman Jason Nieh Cliff Stein.  Lack of fairness in bandwidth allocation in P2P systems:  Users are not incentivized to contributed bandwidth.
Network Coding for Large Scale Content Distribution Christos Gkantsidis Georgia Institute of Technology Pablo Rodriguez Microsoft Research IEEE INFOCOM.
Improving ISP Locality in BitTorrent Traffic via Biased Neighbor Selection Ruchir Bindal, Pei Cao, William Chan Stanford University Jan Medved, George.
Peer-Assisted Content Distribution Networks: Techniques and Challenges Pei Cao Stanford University.
Service Differentiated Peer Selection An Incentive Mechanism for Peer-to-Peer Media Streaming Ahsan Habib, Member, IEEE, and John Chuang, Member, IEEE.
Bandwidth sharing: objectives and algorithms Jim Roberts France Télécom - CNET Laurent Massoulié Microsoft Research.
Modeling and analysis of BitTorrent-like P2P network Fan Bin Oct,1 st,2004.
Modeling and Performance Analysis of Bitorrent-Like Peer-to-Peer Networks Dongyu Qiu and R. Srikant University of Illinois, 2004 Presented by : Ran Zivhon.
Understanding Mesh-based Peer-to-Peer Streaming Nazanin Magharei Reza Rejaie.
A P2P file distribution system ——BitTorrent Fan Bin Sep,25,2004.
High Performance Cooperative Data Distribution [J. Rick Ramstetter, Stephen Jenks] [A scalable, parallel file distribution model conceptually based on.
Optimal peer-to-peer broadcasting schemes Laurent Massoulié Thomson Research, Paris Joint work with A. Twigg, C. Gkantsidis and P. Rodriguez.
Peer-To-Peer Multimedia Streaming Using BitTorrent Purvi Shah, Jehan-François Pâris University of Houston Houston, TX.
Exploring VoD in P2P Swarming Systems By Siddhartha Annapureddy, Saikat Guha, Christos Gkantsidis, Dinan Gunawardena, Pablo Rodriguez Presented by Svetlana.
University of Bologna, Italy How to cheat BitTorrent and why nobody does Simon Patarin and David Hales University of Bologna ECCS 2006,
BitTorrent Under a Microscope: Towards Static QoS Provision in Dynamic Peer-to-Peer Networks Tom H. Luan*, Xuemin (Sherman) Shen* and Danny H. K. Tsang.
GPS: A General Peer-to-Peer Simulator and its Use for Modeling BitTorrent Weishuai Yang Nael Abu-Ghazaleh
A P2P file distribution system ——BitTorrent Pegasus Team CMPE 208.
1 BitHoc: BitTorrent for wireless ad hoc networks Jointly with: Chadi Barakat Jayeoung Choi Anwar Al Hamra Thierry Turletti EPI PLANETE 28/02/2008 MAESTRO/PLANETE.
2: Application Layer1 Chapter 2: Application layer r 2.1 Principles of network applications r 2.2 Web and HTTP r 2.3 FTP r 2.4 Electronic Mail  SMTP,
Do incentives build robustness in BitTorrent? Michael Piatek, Tomas Isdal, Thomas Anderson, Arvind Krishnamurthy, Arun Venkataramani.
1 Insertion of ISP-owned Peer & Locality Awareness in BitTorrent Ioanna Papafili, George D. Stamoulis, Sergios Soursos AUEB EuroNF workshop, Athens October.
1 Towards Cinematic Internet Video-on-Demand Bin Cheng, Lex Stein, Hai Jin and Zheng Zhang HUST and MSRA Huazhong University of Science & Technology Microsoft.
1 Performance Analysis of Coexisting Secondary Users in Heterogeneous Cognitive Radio Network Xiaohua Li Dept. of Electrical & Computer Engineering State.
P2P Traffic Localization by Alias Tracker for Tracker-based P2P applications (ATTP) draft-zhang-alto-attp-02 Yunfei Zhang China Mobile.
MULTI-TORRENT: A PERFORMANCE STUDY Yan Yang, Alix L.H. Chow, Leana Golubchik Internet Multimedia Lab University of Southern California.
Application Layer 2-1 Chapter 2 Application Layer Computer Networking: A Top Down Approach 6 th edition Jim Kurose, Keith Ross Addison-Wesley March 2012.
Impact of Incentives in BitTorrent By Jenny Liu and Seth Cooper.
A Simple Model for Analyzing P2P Streaming Protocols Zhou Yipeng Chiu DahMing John, C.S. Lui The Chinese University of Hong Kong.
2: Application Layer 1 Chapter 2 Application Layer Computer Networking: A Top Down Approach, 5 th edition. Jim Kurose, Keith Ross Addison-Wesley, April.
A simple model for analyzing P2P streaming protocols. Seminar on advanced Internet applications and systems Amit Farkash. 1.
14 th INFORMS Applied Probability Conference, Eindhoven July 9, 2007 Yoni Nazarathy Gideon Weiss University of Haifa Yoni Nazarathy Gideon Weiss University.
Analyzing and Improving BitTorrent Ashwin R. Bharambe ( Carnegie Mellon University ) Cormac Herley ( Microsoft Research, Redmond ) Venkat Padmanabhan (
Bit Torrent Nirav A. Vasa. Topics What is BitTorrent? Related Terms How BitTorrent works Steps involved in the working Advantages and Disadvantages.
Traffic Localization with Information Guidance of Pseudo Peer Agent on BT-P2P Network 學生 : 楊宏昌 指導教授 : 曾黎明教授 在 BT 同儕通訊上利用參與者訊息引導對外流量之區域化節約.
An example of peer-to-peer application
BitTyrant.
The Impact of Replacement Granularity on Video Caching
Queue Dynamics with Window Flow Control
The BitTorrent Protocol
Fluid Modeling Abstracting a discrete-valued system (e.g., packets, customers, users) into a continuous-valued model Writing equations to model system.
Presentation transcript:

Multiclass P2P Networks: Static Resource Allocation for Service Differentiation and Bandwidth Diversity Florence Clévenot-Perronnin, Philippe Nain and Keith Ross Performance 2005 Juan-les-Pins, October

2 Outline File Dissemination Systems Resource Allocation Problem Generic Multiclass Model Application : Service Differentiation Application : Bandwidth diversity Summary and Open Problems

3 File Dissemination Systems Introduction Example: BitTorrent Peer-to-peer file diffusion –Server points on a tracker –Published file is split into N chunks –Downloaders share (upload) the chunks they already have Upload capacity scales with downloader population

4 File Dissemination Systems BitTorrent principle Tracker ? S B D C A E 1,2,3, Downloader Seed

5 File Dissemination Systems BitTorrent principle Tracker S B D C A E S, C B D A ,2,3, Downloader Seed

6 File Dissemination Systems BitTorrent principle Tracker S B D C A E B D A ,2,3, Downloader Seed

7 Resource Allocation Problem Problem description Number of uploads capped (4) Tit-for-tat mechanism Optimistic unchoke Possible secondary criteria: –Missing chunks [Felber and Biersack 04] –Available bandwidth –Subscribed QoS

8 Resource Allocation Problem Objective Goals: –Determine stability conditions –Optimize individual resource allocation policy for various problems: Constraints: –Independently of seed connection time

9 Resource Allocation Problem Main Assumptions 2 classes of users In each class : Upload rate ≤ download rate (ex: ADSL) Users cooperate (i.e. send at full upload capacity)

10 Generic Multiclass Fluid Model Original model [Qiu & Srikant 04] Number of downloaders = x(t) (regardless how many chunks they have) Number of seeds = y(t) Download abort  x(t) y(t) min( cx,  (  x + y ))  

11 Generic Multiclass Fluid Model Two-Class Simplified Model Based on [Qiu and Srikant 04] –Number of downloaders = fluid x i, i =1,2 Allocation Policy: –P (class i selects class i peer) =  i –P (class i selects class j ≠ i peer) = 1 –  i Download abort  i Simplification : No seeds (  i = ∞)

12 Generic Multiclass Fluid Model Performance metric Sojourn time T i ? Complete download probability P i ?  Download cost:  i = T i / P i (Download time given that the download is complete)

13 Applications Model specialization Service differentiation: –Classes = QoS classes (1 st and 2 nd class) –Both classes have the same bandwidth –Allocation policy:  1 = 1-  2 =  Bandwidth diversity: –Classes = bandwidth classes –Both classes have same QoS subscription –Allocation policy:  1 =  2 = 

14 Application: Service Differentiation Specialized multiclass model x (t)  1 1     min(cx 1, μηα(x 1 +x 2 ))min(cx 2, μη(1-α) ( x 1 +x 2 ))

15 Application: Service Differentiation Transitory regime Linear switched system:

16 Local stability proved Unique stable equilibrium Allocation policy  determines: –Type of equilibrium –Download Cost  i for each class Closed-form expression for  i Application: Service Differentiation Results

17 Application: Service Differentiation Type of equilibrium Type 2 (resp.3) : –Download bottleneck for class 1 (resp.2) –Upload bottleneck for class 2 (resp.1) Type 4 : –Upload bottleneck in both classes  Type 3 Type 4 Type 2

18 Application: Service Differentiation Achieving a service differentiation ratio We can solve  2 = k  1 in  for a given k

19 Application: Bandwidth Diversity Results Results: –Local stability proved –Several expressions for download cost –Steady-state : (graphical) optimization of  Problems : –Steady-state may depend on initial conditions –Analysis depends on parameters

20 Application: Bandwidth Diversity Maximum Download Cost

21 Conclusion Summary Proposed a multi-class model for resource allocation problem in P2P networks Obtained closed-form expression for service differentiation in a practical “worst case” Proposed numerical optimization in heterogeneous systems

22 Conclusion Open issues Global stability Validate model through simulations Extend model to any number of classes Dynamic policies Implementation of allocation policies

23 Thank you!