Tapestry : An Infrastructure for Fault-tolerant Wide-area Location and Routing Presenter : Lee Youn Do Oct 5, 2005 Ben Y.Zhao, John Kubiatowicz, and Anthony.

Slides:



Advertisements
Similar presentations
Brocade: Landmark Routing on Peer to Peer Networks Ben Y. Zhao Yitao Duan, Ling Huang, Anthony Joseph, John Kubiatowicz IPTPS, March 2002.
Advertisements

Dynamic Replica Placement for Scalable Content Delivery Yan Chen, Randy H. Katz, John D. Kubiatowicz {yanchen, randy, EECS Department.
Qualifying Examination A Decentralized Location and Routing Infrastructure for Fault-tolerant Wide-area Applications John Kubiatowicz (Chair)Satish Rao.
Tapestry: Scalable and Fault-tolerant Routing and Location Stanford Networking Seminar October 2001 Ben Y. Zhao
Tapestry: Decentralized Routing and Location SPAM Summer 2001 Ben Y. Zhao CS Division, U. C. Berkeley.
Peter Druschel, Rice University Antony Rowstron, Microsoft Research UK
Optimizations for Locality-Aware Structured Peer-to-Peer Overlays Jeremy Stribling Collaborators: Kris Hildrum John D. Kubiatowicz The First.
1 Accessing nearby copies of replicated objects Greg Plaxton, Rajmohan Rajaraman, Andrea Richa SPAA 1997.
Rapid Mobility via Type Indirection Ben Y. Zhao, Ling Huang, Anthony D. Joseph, John D. Kubiatowicz Computer Science Division, UC Berkeley IPTPS 2004.
Common approach 1. Define space: assign random ID (160-bit) to each node and key 2. Define a metric topology in this space,  that is, the space of keys.
Using Overlay Networks for Proximity-based Discovery Steven Czerwinski Anthony Joseph Sahara Winter Retreat January 13, 2004.
The Oceanstore Regenerative Wide-area Location Mechanism Ben Zhao John Kubiatowicz Anthony Joseph Endeavor Retreat, June 2000.
Small-world Overlay P2P Network
Scribe: A Large-Scale and Decentralized Application-Level Multicast Infrastructure Miguel Castro, Peter Druschel, Anne-Marie Kermarrec, and Antony L. T.
Brocade Landmark Routing on Structured P2P Overlays Ben Zhao, Yitao Duan, Ling Huang Anthony Joseph and John Kubiatowicz (IPTPS 2002) Goals Improve routing.
A Scalable Content-Addressable Network Authors: S. Ratnasamy, P. Francis, M. Handley, R. Karp, S. Shenker University of California, Berkeley Presenter:
Scalable Adaptive Data Dissemination Under Heterogeneous Environment Yan Chen, John Kubiatowicz and Ben Zhao UC Berkeley.
Each mesh represents a single hop on the route to a given root. Sibling nodes maintain pointers to each other. Each referrer has pointers to the desired.
Overlay Networks EECS 122: Lecture 18 Department of Electrical Engineering and Computer Sciences University of California Berkeley.
Tapestry: Wide-area Location and Routing Ben Y. Zhao John Kubiatowicz Anthony D. Joseph U. C. Berkeley.
Tapestry : An Infrastructure for Fault-tolerant Wide-area Location and Routing Presenter: Chunyuan Liao March 6, 2002 Ben Y.Zhao, John Kubiatowicz, and.
SCALLOP A Scalable and Load-Balanced Peer- to-Peer Lookup Protocol for High- Performance Distributed System Jerry Chou, Tai-Yi Huang & Kuang-Li Huang Embedded.
Weaving a Tapestry Distributed Algorithms for Secure Node Integration, Routing and Fault Handling Ben Y. Zhao (John Kubiatowicz, Anthony Joseph) Fault-tolerant.
1 CS 194: Distributed Systems Distributed Hash Tables Scott Shenker and Ion Stoica Computer Science Division Department of Electrical Engineering and Computer.
CITRIS Poster Supporting Wide-area Applications Complexities of global deployment  Network unreliability.
Locality Optimizations in Tapestry Jeremy Stribling Joint work with: Kris Hildrum Ben Y. Zhao Anthony D. Joseph John D. Kubiatowicz Sahara/OceanStore Winter.
Decentralized Location Services CS273 Guest Lecture April 24, 2001 Ben Y. Zhao.
Or, Providing High Availability and Adaptability in a Decentralized System Tapestry: Fault-resilient Wide-area Location and Routing Issues Facing Wide-area.
Or, Providing Scalable, Decentralized Location and Routing Network Services Tapestry: Fault-tolerant Wide-area Application Infrastructure Motivation and.
1/17/01 Changing the Tapestry— Inserting and Deleting Nodes Kris Hildrum, UC Berkeley Joint work with John Kubiatowicz, Satish.
CMPE 150- Introduction to Computer Networks 1 CMPE 150 Fall 2005 Lecture 21 Introduction to Computer Networks.
Tapestry: A Resilient Global-scale Overlay for Service Deployment Ben Y. Zhao, Ling Huang, Jeremy Stribling, Sean C. Rhea, Anthony D. Joseph, and John.
ICTTA'04Arwa zabian1 On The Latency of BFS Interval Cooperation Web Caching Arwa Zabian Maurizio Bonuccelli Department of Computer Science University of.
Tapestry An off-the-wall routing protocol? Presented by Peter, Erik, and Morten.
Internet Indirection Infrastructure (i3) Ion Stoica, Daniel Adkins, Shelley Zhuang, Scott Shenker, Sonesh Surana UC Berkeley SIGCOMM 2002.
ROUTING PROTOCOLS Rizwan Rehman. Static routing  each router manually configured with a list of destinations and the next hop to reach those destinations.
1 A scalable Content- Addressable Network Sylvia Rathnasamy, Paul Francis, Mark Handley, Richard Karp, Scott Shenker Pirammanayagam Manickavasagam.
Tapestry GTK Devaroy (07CS1012) Kintali Bala Kishan (07CS1024) G Rahul (07CS3009)
1 Plaxton Routing. 2 Introduction Plaxton routing is a scalable mechanism for accessing nearby copies of objects. Plaxton mesh is a data structure that.
Arnold N. Pears, CoRE Group Uppsala University 3 rd Swedish Networking Workshop Marholmen, September Why Tapestry is not Pastry Presenter.
CS An Overlay Routing Scheme For Moving Large Files Su Zhang Kai Xu.
HERO: Online Real-time Vehicle Tracking in Shanghai Xuejia Lu 11/17/2008.
Overcast: Reliable Multicasting with an Overlay Network CS294 Paul Burstein 9/15/2003.
Brocade Landmark Routing on P2P Networks Gisik Kwon April 9, 2002.
Chord: A Scalable Peer-to-peer Lookup Protocol for Internet Applications Xiaozhou Li COS 461: Computer Networks (precept 04/06/12) Princeton University.
Vincent Matossian September 21st 2001 ECE 579 An Overview of Decentralized Discovery mechanisms.
Tapestry:A Resilient Global- Scale Overlay for Service Deployment Zhao, Huang, Stribling, Rhea, Joseph, Kubiatowicz Presented by Rebecca Longmuir.
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.
1 More on Plaxton routing There are n nodes, and log B n digits in the id, where B = 2 b The neighbor table of each node consists of - primary neighbors.
SIGCOMM 2001 Lecture slides by Dr. Yingwu Zhu Chord: A Scalable Peer-to-peer Lookup Service for Internet Applications.
Tapestry: A Resilient Global-scale Overlay for Service Deployment 1 Ben Y. Zhao, Ling Huang, Jeremy Stribling, Sean C. Rhea, Anthony D. Joseph, and John.
Plethora: Infrastructure and System Design. Introduction Peer-to-Peer (P2P) networks: –Self-organizing distributed systems –Nodes receive and provide.
Peer to Peer Network Design Discovery and Routing algorithms
Algorithms and Techniques in Structured Scalable Peer-to-Peer Networks
LOOKING UP DATA IN P2P SYSTEMS Hari Balakrishnan M. Frans Kaashoek David Karger Robert Morris Ion Stoica MIT LCS.
Spring 2000CS 4611 Routing Outline Algorithms Scalability.
Scribe: A Large-Scale and Decentralized Application-Level Multicast Infrastructure Miguel Castro, Peter Druschel, Anne-Marie Kermarrec, and Antony I.T.
Dynamic Replica Placement for Scalable Content Delivery Yan Chen, Randy H. Katz, John D. Kubiatowicz {yanchen, randy, EECS Department.
Spring Routing: Part I Section 4.2 Outline Algorithms Scalability.
1 Plaxton Routing. 2 History Greg Plaxton, Rajmohan Rajaraman, Andrea Richa. Accessing nearby copies of replicated objects, SPAA 1997 Used in several.
Plethora: A Locality Enhancing Peer-to-Peer Network Ronaldo Alves Ferreira Advisor: Ananth Grama Co-advisor: Suresh Jagannathan Department of Computer.
Incrementally Improving Lookup Latency in Distributed Hash Table Systems Hui Zhang 1, Ashish Goel 2, Ramesh Govindan 1 1 University of Southern California.
CS791Aravind Elango Maintenance-Free Global Data Storage Sean Rhea, Chris Wells, Patrick Eaten, Dennis Geels, Ben Zhao, Hakim Weatherspoon and John Kubiatowicz.
Accessing nearby copies of replicated objects
Dynamic Routing and OSPF
John D. Kubiatowicz UC Berkeley
Object Location Problem: Find a close copy of an object in a large network Solution should: Find object if it exists Find a close copy of the object (no.
Locality Optimizations in Tapestry Sahara/OceanStore Winter Retreat
Rapid Mobility via Type Indirection
Tapestry: Scalable and Fault-tolerant Routing and Location
Presentation transcript:

Tapestry : An Infrastructure for Fault-tolerant Wide-area Location and Routing Presenter : Lee Youn Do Oct 5, 2005 Ben Y.Zhao, John Kubiatowicz, and Anthony D,Josephetc. Computer Science Division University of California, Berkeley

-2/20- Contents Motivation System Overview Operations Measurements Summary

-3/20- Motivation Today’s dynamic nature of the computing environment stresses in many ways traditional approaches to providing object name service, consistency, location and routing. I’m old now.. Scaling current solutions – A house of cards built from many individual houses-of-cards Tapestry!

-4/20- System Overview Tapestry I have object O I want object O Query with Object-ID(O) 3. Query with Object-ID(O) 4. Sending Object O

-5/20- Contents Motivation System Overview Operations – Routing – Surrogate Routing – Node Insertion Measurements Summary – Publishing & Location – Fault Handling – Node Deletion

-6/20- Routing(1/3) Each node can be server, router, and client Objects/Nodes names – Random fixed-length bit-sequence (e.g., B4F8, 9098) – Evenly distributed in namespace – Independent of their locations Using local routing maps – Called neighbor maps

-7/20- Routing(2/3) Suffix matching ( similar to CIDR ) – Incrementally routing digital by digital – Maximum hops : log b (N) 6789 B4F Msg to 4598 B437

-8/20- Routing(3/3) Neighbor Map A table with b*log b (N) entries Entry( i, j ) - Pointer to the neighbor “ j” + (i- 1) suffix 2 Secondary neighbors Back Pointers Soft state

-9/20- Publishing 1. Map the object ID to a virtual node ID 2. Server send the message with the object id and server id 3. Find the surrogate node as the “root” for the object 4. Save the related info there, such as Server :B F734 B Surrogate Routing Location Pointers

-10/20- Locating Client : B4F8 Server : B A Surrogate Routing 1. Client send the query with the object id 2. Route the query to the root node for the object 3. Forward the query to the server

-11/20- Surrogate Routing each nonexistent ID is mapped to some live node with a similar ID Looks for a “close” digit in the neighbor maps Ensuring that arrive at the same unique root node from any location in the Tapestry network The expected number of additional hops is 2

-12/20- Fault Handling Fault-tolerant Routing – Detecting link and server failures Relying on TCP timeouts Using back pointers to send periodic heartbeats – Operation under faults 2 secondary neighbors Second chance Fault-tolerant Location – Multiple root nodes – Republish location information at regular intervals

-13/20- Node Insertion 1. Get an Node ID 2. Begin with a “Gateway node” G (Assuming that knows of a gateway node) 3. Pretends to route to itself 4. Get the neighbor maps from the nodes on route and optimize it 5. Go to the root node for new node ID and moves data meant for new node 6. Send a “hello” message to all neighbors and secondary neighbors Gateway node : B4F F734 B Surrogate Routing New node : 1234 : Neighbor map transfer : Data transfer

-14/20- Node Deletion Trivial problem Informing the relevant parties of its departure using its back pointers Relying on soft state

-15/20- Contents Motivation System Overview Operations Measurements Summary

-16/20- Measurements(1/3) Experiments on a packet level simulator using unit-distance hop topologies Metric – Location Relative Delay Penalty (RDP) The ration of distance traveled via Tapestry, versus that traveled via direct routing to the object – Latency Topologies – TIERS – Transit-stub (generated by GT-ITM)

-17/20- Measurement(2/3) The effect of location pointers

-18/20- Measurement(3/3) The effect of multiple root nodes

-19/20- Summary Tapestry is presented due to need for new Routing/Location scheme Tapestry is – Self-organizing – Scalable – Robust – Adaptable – Distributed

-20/20- Thank you, any question?