Skip to main content


eCommons@Cornell

eCommons@Cornell >
Faculty of Computing and Information Science >
Computing and Information Science >
Computing and Information Science Technical Reports >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1813/8219
Title: Scalable Publish-Subscribe in a Managed Framework
Authors: Ostrowski, Krzysztof
Birman, Ken
Keywords: computer science
Distributed, Parallel, and Cluster Computing
technical report
Issue Date: 10-Jul-2007
Publisher: Cornell University
Citation: http://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cis/TR2007-2086
Abstract: Reliable multicast, publish-subscribe and group communication are highly effective in support of replication and event notification, and could serve as the enabling technologies for new types of applications that are both interac-tive and decentralized. To fully realize this vision, we need a high-performance, scalable, and reliable multicast en-gine as an integral part of the runtime environment. Since the majority of development today is done in managed, strongly-typed environments such as Java or .NET, integration with such environments is of particular importance. What factors limit performance and scalability of a reliable multicast engine in a managed environment? What support from the runtime could improve performance, avoid instabilities, or make such systems easier to build? This paper sheds light on these questions by analyzing the performance of QuickSilver Scalable Multicast (QSM), a new multicast protocol and system built entirely in .NET. Memory-related overheads and scheduling-related phenomena are shown to dominate the behavior of our system. We discuss techniques that helped us alleviate some of these problems, and point to areas where better support from the runtime would be desirable.
URI: http://hdl.handle.net/1813/8219
Appears in Collections:Computing and Information Science Technical Reports

Files in This Item:

File Description SizeFormat
TR2007-2086.pdf1.48 MBAdobe PDFView/Open

Refworks Export

Items in eCommons are protected by copyright, with all rights reserved, unless otherwise indicated.

 

© 2014 Cornell University Library Contact Us