advertisement

icdcs99

50 %
50 %
advertisement
Information about icdcs99
Entertainment

Published on June 26, 2007

Author: JJMiller

Source: authorstream.com

advertisement

Fault Tolerant Video-On-Demand Services:  Fault Tolerant Video-On-Demand Services Tal Anker, Danny Dolev, Idit Keidar, The Transis Project VoD Service:  VoD Service VoD: Full VCR control 1 video stream per client Client C1 VoD Service provider Requests Video Stream Movies disk(s) High Availability:  High Availability Multiple servers at different sites Fault tolerance: servers can crash Managing the load: new servers can be brought up / down load should be re-distributed 'on the fly' migration of clients The challenges:  The challenges Low overhead Transparency How do clients know whom to connect to? 'abstract' service Clients should be unaware of migration Buffer Management andFlow Control:  Buffer Management and Flow Control Overcome jitter, message re-ordering and migration periods Re-fill buffers quickly after migration avoid buffer overflow Minimize buffers minimize pre-fetch bandwidth Dynamically adjust transmission rate to client capabilities Re-negotiation of QoS Features of our solution:  Features of our solution Use group communication in the control plane connection establishment fault tolerance and migration Flow control explicitly handles migration Low overhead ~1/1000 of the bandwidth Negligible memory and CPU overhead Commodity hardware and publicly available network technologies Environment:  Environment Implementation UDP/IP over 10 Mbit/s switched ethernet Transis Sun Sparc and BSDI PC’s as video servers Win NT machines as video clients MPEG1 andamp; 2 hardware decoders Machine and Network Failures Implementing the abstract service:  Implementing the abstract service Use group communication clients communicate with a well known group name (logical entity) unaware of the number and identity of the servers in the group Servers periodically share information about clients (every 1/2sec) If a server crashes (or is overloaded), another server transparently takes over Group Communication:  Group Communication Reliable Group Multicast (Group Abstraction) Message Ordering Dynamic Reconfiguration Membership with Strong Semantics (Virtual Synchrony) Systems: Transis, Horus, Ensemble, Totem, Newtop, RMP, ISIS, Psync, Relacs The group layout of the VoD service:  The group layout of the VoD service Transis Allows Simple Design:  Transis Allows Simple Design Group abstraction for connection establishment and transparent migration Reliable group multicast allows servers to consistently share information Membership services detects conditions for migration Reliable messages for control Server takes ~2500 C++ code lines Client takes ~4000 C code lines (excluding GUI and display) VoD Client: Multi Threaded Design:  VoD Client: Multi Threaded Design Client buffer accounts for jitter period when migration occurs Obviously, Flow-Control and Buffer management were needed Flow Control:  Flow Control Feedback based flow-control (sparse): FC messages are sent to the logical server (session group) Clients determines the changes in the flow: Emergency Flow Control:  Emergency Flow Control When the server receives an emergency message: The server change the fps rate: fps = latest-known-fps + emergency quantity The emergency quantity decays every second (by a factor) While the quantity is above zero, the server ignores FC messages from the client Performance Measurements :  Performance Measurements On HUJI Network (LAN) Servers at TAU and clients at HUJI (WAN) The measurements show the system is robust and support our transparency claims Software Buffers:  Software Buffers Hardware Buffers:  Hardware Buffers Skipped Frames on LAN:  Skipped Frames on LAN Skipped Frames on WAN:  Skipped Frames on WAN Summary:  Summary Scalable VoD service Load balancing Tolerating machine and network failure All the above are achieved practically for free: ~1/1000 of the total bandwidth Negligible memory and CPU overhead Thanks to ...:  Thanks to ... Gregory Chockler The other members of the Transis project

Add a comment

Related presentations

Related pages

dblp: 19. ICDCS 1999: Austin, TX, USA

Bibliographic content of 19. ICDCS 1999: Austin, TX, USA. default search action. combined dblp search; author search; venue search; publication search;
Read more

icdcs99 - Ace Recommendation Platform - 1

Design Considerations for Distributed Caching on the Internet#03Renu Tewari Michael Dahlin, Harrick M. Vin Jonathan S. KayIBM T.J. Watson Research Center ...
Read more

icdcs99 - Ace Recommendation Platform - 1

In Proceedings of the 19th IEEE International Conference on Distributed Computing Systems, Austin, TX, June 1999.Proxy Cache Coherency and Replacement ...
Read more

Incorporating Transaction Semantics to Reduce Reprocessing ...

Incorporating Transaction Semantics to Reduce Reprocessing Overhead in Replicated Mobile Data Applications Peng Liu Paul Ammann Sushil Jajodia Center for ...
Read more

Design Considerations for Distributed Caching on the Internet

Design Considerations for Distributed Caching on the Internet Renu Tewari Michael Dahlin, Harrick M. Vin Jonathan S. Kay IBM T.J. Watson Research Center ...
Read more

Con tract T e Negotiation - CMU Computer Science

Con tract T yp e Sequencing for Reallo cativ e Negotiation Martin Andersson and T uomas Sandholm f mra, sandholm g @cs.wustl.edu Departmen t of Computer ...
Read more

Proxy Cache Coherency and Replacement—T owards a More ...

In Proceedings of the 19th IEEE International Conference on Distributed Computing Systems, Austin, TX, June 1999. Proxy Cache Coherency and Replacement—T ...
Read more

An Advanced Communication Toolkit for Implementing the ...

An Advanced Communication Toolkit for Implementing the Broker Pattern Cristian Francu and Ivan Marsic Center for Computer Aids for Industrial Productivity ...
Read more

Fault Tolerant Video on Demand Services - MIT CSAIL

Fault Tolerant Video on Demand Services Tal Anker Danny Dolev Idit Keidar Institute of Computer Science Laboratory for Computer Science The Hebrew ...
Read more

- A QoS-enabled Customizable Middleware Framework for

CompOSE j Q - A QoS-enabled Customizable Middleware Framework for Distributed Computing Nalini Venkatasubramanian Dept. of Information and Computer Science ...
Read more