Massey Documents by Type

Permanent URI for this communityhttps://mro.massey.ac.nz/handle/10179/294

Browse

Filters

2005 - 20082

Settings

Subject: search.filters.subject.Beowulf clusters (Computer systems)

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A scalable application server on Beowulf clusters : a thesis presented in partial fulfilment of the requirement for the degree of Master of Information Science at Albany, Auckland, Massey University, New Zealand
    (Massey University, 2005) Zhou, Michael Zhiyong
    Application performance and scalability of a large distributed multi-tiered application is a core requirement for most of today's critical business applications. I have investigated the scalability of a J2EE application server using the standard ECperf benchmark application in the Massey Beowulf Clusters namely the Sisters and the Helix. My testing environment consists of Open Source software: The integrated JBoss-Tomcat as the application server and the web server, along with PostgreSQL as the database. My testing programs were run on the clustered application server, which provide replication of the Enterprise Java Bean (EJB) objects. I have completed various centralized and distributed tests using the JBoss Cluster. I concluded that clustering of the application server and web server will effectively increase the performance of the application running on them given sufficient system resources. The application performance will scale to a point where a bottleneck has occurred in the testing system, the bottleneck could be any resources included in the testing environment: the hardware, software, network and the application that is running. Performance tuning for a large-scale J2EE application is a complicated issue, which is related to the resources available. However, by carefully identifying the performance bottleneck in the system with hardware, software, network, operating system and application configuration. I can improve the performance of the J2EE applications running in a Beowulf Cluster. The software bottleneck can be solved by changing the default settings, on the other hand, hardware bottlenecks are harder unless more investment are made to purchase higher speed and capacity hardware.
  • Thumbnail Image
    Item
    Concurrent Viola Jones classifiers on a portable Beowulf cluster : a thesis presented in partial fulfilment of the requirements for the degree of Master of Engineering in Mechatronics at Massey University
    (Massey University, 2008) Chemudugunta, Ravi Kiran
    Real-time Computer Vision is an interesting application for supercomputing, real-time applications (vision processing in particular) employ special purpose hardware such as DSPs to achieve high performance. This thesis explores parallel computers particularly commodity general purpose hardware. We also build a prototype to better understand the economics of supercomputing, specifically related to mobile computing - low power, rugged design by building a mobile computer. A new communication layer is built, where by the nature of the locality of the nodes allows one to optimise the protocols to reduce the latency comparably. Finally a study and in depth results of the algorithm, the Viola Jones Object detector in parallel are presented followed by reflection and future work based on the current results and platform.