Download:
by Pascal Felber
In Proceedings of the 23rd IEEE Symposium on Reliable Distributed Systems (SRDS’04
http://members.unine.ch/pascal.felber/publications/SRDS-04a.pdf
Add To MetaCart
Abstract:
Flash crowds, which result from the sudden increase in popularity of some online content, are among the most important problems that plague today’s Internet. Affected servers are overloaded with requests and quickly become “hot spots. ” They usually suffer from severe performance failures or stop providing service altogether, as there are scarcely any effective techniques to scalably deliver content under hot spot conditions to all requesting clients. In this paper, we propose and evaluate collaborative techniques to detect and proactively avoid the occurrence of hot spots. Using our mechanisms, groups of small- to medium-sized Web servers can team up to withstand unexpected surges of requests in a cost-effective manner. Once a Web server detects a sudden increase in request traffic, it replicates onthe-fly the affected content on other Web servers; subsequent requests are transparently redirected to the copies to offload the primary server. Each server acts both as a primary source for its own content, and as a secondary source for other servers ’ content in the event of a flash-crowd; scalability and dependability are therefore achieved in a peerto-peer fashion, with each peer contributing to, and benefiting from, the service. Our proactive hot spot avoidance techniques are implemented as a module for the popular Apache Web server. We have conducted a comprehensive experimental evaluation, which demonstrates that our techniques are effective at dealing with flash crowds and scaling to very high request loads. 1.
Citations
|
283
|
Cooperative Caching: Using Remote Client Memory to Improve File System Performance
– Dahlin, Wang, et al.
- 1994
|
|
264
|
SEDA: an architecture for well-conditioned, scalable Internet services
– Welsh, Culler, et al.
- 2001
|
|
220
|
Flash: An efficient and portable Web server
– Pai, Druschel, et al.
- 1999
|
|
140
|
Flash Crowds and Denial of Service Attacks: Characterization and Implications for CDNs and Web Sites
– Jung, Krishnamurthy, et al.
- 2002
|
|
118
|
Squirrel: A decentralized peer-to-peer web cache
– Iyer, Rowstron, et al.
- 2002
|
|
86
|
Resource overbooking and application profiling in shared hosting platforms
– Urgaonkar, Shenoy, et al.
- 2002
|
|
77
|
Oceano - SLA Based Management of a Computing Utility
– Appleby, Fakhouri, et al.
- 2001
|
|
69
|
Peer-to-peer caching schemes to address flash crowds
– Stading, Maniatis, et al.
- 2002
|
|
60
|
A lightweight, robust p2p system to handle flash crowds
– Stavrou, Rubenstein, et al.
- 2002
|
|
45
|
httperf—a tool for measuring web server performance
– Mosberger, Jin
- 1998
|
|
44
|
The SlashDot Effect: An Analysis of Three Internet
– Adler
- 1999
|
|
33
|
The vMatrix: A network of virtual machine monitors for dynamic content distribution
– Awadallah, Rosenblum
- 2002
|
|
24
|
Globule: a platform for self-replicating Web documents
– Pierre, Steen
- 2001
|
|
20
|
World Wide Web Caching: The Application-Level View of the Internet
– Baentsch, Baum, et al.
- 1997
|
|
16
|
OnCall: Defeating Spikes with a Free-Market Application Cluster
– Norris, Coleman, et al.
- 2004
|
|
16
|
Topology-Centric Look-Up Service
– Garces-Erice, Ross, et al.
- 2003
|
|
15
|
JAWS: A Framework for High Performance Web Servers
– Hu, Schmidt
- 1999
|
|
15
|
Dynamic Surge Protection: An Approach to Handling Unexpected Workload Surges with Resource Actions that have Lead Times
– Lassettre, Coleman, et al.
- 2003
|
|
12
|
Managing Flash Crowds on the Internet
– Ari, Hong, et al.
- 2003
|
|
3
|
Experimental Evaluation of an Adaptive Flash Crowd Protection System
– Chen, Heidemann
- 2003
|
|
2
|
Adaptive Replicated Web Documents
– Pierre, Kuz, et al.
- 2000
|
|
2
|
Predicting the Upper Bound of Web Traffic Volume Using a Multiple Time Scale Approach
– Zhao, Schulzrinne
- 2003
|
