SCAN: A Dynamic, Scalable, and Efficient Content Distribution Network Yan Chen, Randy H. Katz, John D. Kubiatowicz {yanchen, randy,

Slides:



Advertisements
Similar presentations
Dynamic Replica Placement for Scalable Content Delivery Yan Chen, Randy H. Katz, John D. Kubiatowicz {yanchen, randy, EECS Department.
Advertisements

Tapestry: Decentralized Routing and Location SPAM Summer 2001 Ben Y. Zhao CS Division, U. C. Berkeley.
Alex Cheung and Hans-Arno Jacobsen August, 14 th 2009 MIDDLEWARE SYSTEMS RESEARCH GROUP.
Ion Stoica, Robert Morris, David Karger, M. Frans Kaashoek, Hari Balakrishnan MIT and Berkeley presented by Daniel Figueiredo Chord: A Scalable Peer-to-peer.
Optimizations for Locality-Aware Structured Peer-to-Peer Overlays Jeremy Stribling Collaborators: Kris Hildrum John D. Kubiatowicz The First.
SplitStream by Mikkel Hesselager Blanné Erik K. Aarslew-Jensen.
Small-world Overlay P2P Network
Web Caching Schemes1 A Survey of Web Caching Schemes for the Internet Jia Wang.
1 Clustering Web Content for Efficient Replication Yan Chen, Lili Qiu*, Weiyu Chen, Luan Nguyen, Randy H. Katz EECS Department UC Berkeley *Microsoft Research.
Opportunities and Challenges of Peer-to-Peer Internet Video Broadcast J. Liu, S. G. Rao, B. Li and H. Zhang Proc. of The IEEE, 2008 Presented by: Yan Ding.
Beneficial Caching in Mobile Ad Hoc Networks Bin Tang, Samir Das, Himanshu Gupta Computer Science Department Stony Brook University.
Peer-to-Peer Based Multimedia Distribution Service Zhe Xiang, Qian Zhang, Wenwu Zhu, Zhensheng Zhang IEEE Transactions on Multimedia, Vol. 6, No. 2, April.
1 Clustering Web Content for Efficient Replication Yan Chen, Lili Qiu*, Weiyu Chen, Luan Nguyen, Randy H. Katz EECS Department UC Berkeley *Microsoft Research.
Efficient Content Location Using Interest-based Locality in Peer-to-Peer Systems Presented by: Lin Wing Kai.
Quantitative Characterization of Denial of Service Attacks: A Case Study of Location Services Adam Bargteil David Bindel Yan Chen.
Scalable Adaptive Data Dissemination Under Heterogeneous Environment Yan Chen, John Kubiatowicz and Ben Zhao UC Berkeley.
Application Layer Multicast
ICNP'061 Benefit-based Data Caching in Ad Hoc Networks Bin Tang, Himanshu Gupta and Samir Das Department of Computer Science Stony Brook University.
1 A Distributed Delay-Constrained Dynamic Multicast Routing Algorithm Quan Sun and Horst Langendorfer Telecommunication Systems Journal, vol.11, p.47~58,
1 An Overlay Scheme for Streaming Media Distribution Using Minimum Spanning Tree Properties Journal of Internet Technology Volume 5(2004) No.4 Reporter.
Introspective Replica Management Yan Chen, Hakim Weatherspoon, and Dennis Geels Our project developed and evaluated a replica management algorithm suitable.
CS218 – Final Project A “Small-Scale” Application- Level Multicast Tree Protocol Jason Lee, Lih Chen & Prabash Nanayakkara Tutor: Li Lao.
Dynamic Multicast Tree Construction in OceanStore Puneet Mehra and Satrajit Chatterjee Advanced Topics in Computer Systems Final Project EECS Department,
Adaptive Web Caching Lixia Zhang, Sally Floyd, and Van Jacob-son. In the 2nd Web Caching Workshop, Boulder, Colorado, April 25, System Laboratory,
Component-Based Routing for Mobile Ad Hoc Networks Chunyue Liu, Tarek Saadawi & Myung Lee CUNY, City College.
Locality Optimizations in Tapestry Jeremy Stribling Joint work with: Kris Hildrum Ben Y. Zhao Anthony D. Joseph John D. Kubiatowicz Sahara/OceanStore Winter.
Or, Providing Scalable, Decentralized Location and Routing Network Services Tapestry: Fault-tolerant Wide-area Application Infrastructure Motivation and.
An Evaluation of Scalable Application-level Multicast Using Peer-to-peer Overlays Miguel Castro, Michael B. Jones, Anne-Marie Kermarrec, Antony Rowstron,
Clustering of Web Content for Efficient Replication Yan Chen, Lili Qiu, Wei Chen, Luan Nguyen and Randy H. Katz {yanchen, wychen, luann,
Web Caching and CDNs March 3, Content Distribution Motivation –Network path from server to client is slow/congested –Web server is overloaded Web.
Quantifying Network Denial of Service: A Location Service Case Study Yan Chen, Adam Bargteil, David Bindel, Randy H. Katz and John Kubiatowicz Computer.
World Wide Web Caching: Trends and Technology Greg Barish and Katia Obraczka USC Information Science Institute IEEE Communications Magazine, May 2000 Presented.
1 Algorithms for Bandwidth Efficient Multicast Routing in Multi-channel Multi-radio Wireless Mesh Networks Hoang Lan Nguyen and Uyen Trang Nguyen Presenter:
University of Nevada, Reno Virtual Direction Multicast for Overlay Networks Suat Mercan & Dr. Murat Yuksel HOTP2P’11.
SCAN: a Scalable, Adaptive, Secure and Network-aware Content Distribution Network Yan Chen CS Department Northwestern University.
Overcast: Reliable Multicasting with an Overlay Network CS294 Paul Burstein 9/15/2003.
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.
World Wide Web Caching: Trends and Technologys Gerg Barish & Katia Obraczka USC Information Sciences Institute, USA,2000.
Overlay Network Physical LayerR : router Overlay Layer N R R R R R N.
Resilient Peer-to-Peer Streaming Presented by: Yun Teng.
Higashino Lab. Maximizing User Gain in Multi-flow Multicast Streaming on Overlay Networks Y.Nakamura, H.Yamaguchi and T.Higashino Graduate School of Information.
1 On the Placement of Web Server Replicas Lili Qiu, Microsoft Research Venkata N. Padmanabhan, Microsoft Research Geoffrey M. Voelker, UCSD IEEE INFOCOM’2001,
Streaming over Subscription Overlay Networks Department of Computer Science Iowa State University.
A Scalable, Adaptive, Network-aware Infrastructure for Efficient Content Delivery Yan Chen Ph.D. Status Talk EECS Department UC Berkeley.
Live Streaming over Subscription Overlay Networks CS587x Lecture Department of Computer Science Iowa State University.
TOMA: A Viable Solution for Large- Scale Multicast Service Support Li Lao, Jun-Hong Cui, and Mario Gerla UCLA and University of Connecticut Networking.
1 On the Placement of Web Server Replicas Lili Qiu, Microsoft Research Venkata N. Padmanabhan, Microsoft Research Geoffrey M. Voelker, UCSD IEEE INFOCOM’2001,
Adaptive Web Caching CS411 Dynamic Web-Based Systems Flying Pig Fei Teng/Long Zhao/Pallavi Shinde Computer Science Department.
An IP Address Based Caching Scheme for Peer-to-Peer Networks Ronaldo Alves Ferreira Joint work with Ananth Grama and Suresh Jagannathan Department of Computer.
Energy-Efficient Shortest Path Self-Stabilizing Multicast Protocol for Mobile Ad Hoc Networks Ganesh Sridharan
1 Evaluation of Cooperative Web Caching with Web Polygraph Ping Du and Jaspal Subhlok Department of Computer Science University of Houston presented at.
A Membership Management Protocol for Mobile P2P Networks Mohamed Karim SBAI, Emna SALHI, Chadi BARAKAT.
PROP: A Scalable and Reliable P2P Assisted Proxy Streaming System Computer Science Department College of William and Mary Lei Guo, Songqing Chen, and Xiaodong.
A P2P-Based Architecture for Secure Software Delivery Using Volunteer Assistance Purvi Shah, Jehan-François Pâris, Jeffrey Morgan and John Schettino IEEE.
Towards a Transparent and Proactively-Managed Internet Ehab Al-Shaer School of Computer Science DePaul University Yan Chen EECS Department Northwestern.
NUS.SOC.CS5248 Ooi Wei Tsang Course Matters. NUS.SOC.CS5248 Ooi Wei Tsang Deadlines 11 Oct: Survey Paper Due 18 Oct: Paper Reviews Due.
Plethora: Infrastructure and System Design. Introduction Peer-to-Peer (P2P) networks: –Self-organizing distributed systems –Nodes receive and provide.
Energy-Conserving Data Placement and Asynchronous Multicast in Wireless Sensor Networks Sagnik Bhattacharya, Hyung Kim, Shashi Prabh, Tarek Abdelzaher.
Peer-to-Peer Result Dissemination in High-Volume Data Filtering Shariq Rizvi and Paul Burstein CS 294-4: Peer-to-Peer Systems.
Efficient and Adaptive Replication using Content Clustering Yan Chen EECS Department UC Berkeley.
CS 6401 Overlay Networks Outline Overlay networks overview Routing overlays Resilient Overlay Networks Content Distribution Networks.
Content Delivery Networks: Status and Trends Speaker: Shao-Fen Chou Advisor: Dr. Ho-Ting Wu 5/8/
Dynamic Replica Placement for Scalable Content Delivery Yan Chen, Randy H. Katz, John D. Kubiatowicz {yanchen, randy, EECS Department.
An overlay for latency gradated multicasting Anwitaman Datta SCE, NTU Singapore Ion Stoica, Mike Franklin EECS, UC Berkeley
On the Placement of Web Server Replicas Yu Cai. Paper On the Placement of Web Server Replicas Lili Qiu, Venkata N. Padmanabhan, Geoffrey M. Voelker Infocom.
1 Evaluation of Cooperative Web Caching with Web Polygraph Ping Du and Jaspal Subhlok Department of Computer Science University of Houston presented at.
Efficient and Adaptive Replication using Content Clustering Yan Chen EECS Department UC Berkeley.
Cost-Effective Video Streaming Techniques Kien A. Hua School of EE & Computer Science University of Central Florida Orlando, FL U.S.A.
SCOPE: Scalable Consistency in Structured P2P Systems
Dynamic Replica Placement for Scalable Content Delivery
Presentation transcript:

SCAN: A Dynamic, Scalable, and Efficient Content Distribution Network Yan Chen, Randy H. Katz, John D. Kubiatowicz {yanchen, randy, EECS Department UC Berkeley

Outlines Motivation Goal and Challenges Previous Work SCAN Architecture and Components Evaluation Methodology Results Conclusions

Motivation Scenario: World Cup 2002

Goal and Challenges Dynamic choice of number and location of replicas –Clients’ QoS constraints: latency, staleness –Servers’ capacity constraints Efficient resource consumption –Small delay, bandwidth consumption for replica update –Small replica management cost Scalability: millions of objects, clients and servers No global network topology knowledge Provide content distribution to clients with good latency and staleness, while retaining efficient and balanced resource consumption of the underlying infrastructure

Previous Work Replica Placement –Research communities: optimal static replica placement Assume clients’ distributions, access patterns & IP topology No consideration for clients’ QoS or servers’ capacity constraints –CDN operators: un-cooperative, ad hoc placement Centralized CDN name server cannot record replica locations – place many more than necessary (ICNP ’02) Update Multicast –No inter-domain IP multicast –Most application-level multicast (ALM) unscalable Split root as common solution, suffers consistency overhead

adaptive coherence data plane network plane data source Web content server CDN server client replica always update cache SCAN: Scalable Content Access Network DOLR mesh

Components of SCAN Decentralized Object Location & Routing (DOLR) –Properties needed Scalable location with guaranteed success Search with locality –Improve the scalability of d-tree: each member only maintains states for its parent and direct children Simultaneous Dynamic Replica Placement and d- tree Construction –Replica search: Singular, Localized or Exhaustive –Replica placement on DOLR path: Lazy or Eager

parent candidate data plane network plane c s DOLR path Replica Search proxy DOLR mesh Singular Search

Replica Search parent candidates Localized search data plane network plane c s parent sibling server child proxy DOLR path client child Greedy load distribution DOLR mesh

data plane network plane c s proxy DOLR path first placement choice Replica Placement: Eager DOLR mesh

Replica Placement: Lazy data plane network plane c s proxy DOLR path client child first placement choice DOLR mesh

Evaluation of Alternatives Two dynamic overlay approaches –Overlay_naïve: Singular search + Eager placement –Overlay_smart: Localized search + Lazy placement Compared with static placement + IP multicast –Overlay_static: With global overlay topology –IP_static: With global IP topology (ideal) Metrics –Number of replicas deployed, load distribution –Multicast performance: Relative Delay Penalty (RDP) and bandwidth consumption –Tree construction traffic (packets and bandwidth)

Methodology Network Topology –5000-node network with GT-ITM transit-stub model –SCAN nodes placed randomly or on transit nodes NS-like Packet-level Network Simulations Workloads –Synthetic flash crowd: all clients access a hot object in random order –Real Web server traces: NASA and MSNBC Web SitePeriodDuration# Requests# Clients# objects MSNBC8/2/199910–11am1.6M140K4186 NASA7/1/1995All day64K

Methodology: Sensitivity Analysis Various Client/Server Ratio Various Server Density Various Latency & Capacity Constraints Various Network Topologies –Average over 5 topologies with different setup All Have Similar Trend of Results –Overlay_smart has close-to-optimal (IP_static) number of replicas, load distribution, multicast performance with reasonable amount of tree construction traffic

Number of Replicas Deployed and Load Distribution Overlay_smart uses only 30-60% of replicas than overlay_naïve and very close to IP_static Overlay_smart has two times better load distribution than od_naïve, overlay_static and very close to IP_static

Multicast Performance 85% of overlay_smart Relative Delay Penalty (RDP) less than 4 Bandwidth consumed by overlay_smart is very close to IP_static, and is only 1/3 of bandwidth by overlay_naive

Tree Construction Traffic Including “join” requests, “ping” messages, replica placement and parent/child registration Overlay_smart consumes times of traffic than overlay_naïve, and the traffic of overlay_naïve is quite close to IP_static Far less frequent event than access & update dissemination

Conclusions P2P networks can be used to construct CDNs SCAN: Scalable Content Access Network with good QoS, efficiency and load balancing –Simultaneous dynamic replica placement & d-tree construction –Leverage DOLR to improve scalability and locality In particular, overlay_smart recommended –Localized search + Lazy placement –Close to optimal number of replicas, good load distribution, low multicast delay and bandwidth penalty at the price of reasonable construction traffic

Results on Web Server Traces Limited simulations, most URLs have very few requests Overlay_smart uses only one third to half replicas than overlay_naïve for hot objects

data plane network plane data source Web content server CDN server client replica always update cache SCAN: Scalable Content Access Network adaptive coherence DOLR mesh

parent candidate data plane network plane c s DOLR path Replica Search proxy DOLR mesh Singular Search

Replica Search parent candidates Localized search data plane network plane c s parent sibling server child proxy DOLR path client child Greedy load distribution

data plane network plane c s proxy Tapestry overlay path first placement choice parent candidate Dynamic Replica Placement: naïve Tapestry mesh Singular Search Eager Placement

Dynamic Replica Placement: smart Localized search Lazy placement Greedy load distribution data plane parent candidates network plane c s parent sibling server child proxy Tapestry overlay path client child first placement choice