No abstract

Exponential growth in data production and a prominent trend in data center design architecture -a shift from expensive hardware towards a multitude of simple servers -pose new tasks and demand the use of different strategies for data center architects. In this work, a new solutions to distributed systems design are discussed, which are based on Plan9 operating system model. We first overview application and research projects including project of porting Plan9 to the IBM Blue Gene/L supercomputer, project of the Plan9 use in data centers and cloud systems, and projects aimed at distributed embedded systems. Then we introduce a Cloud/IX operating system for the ARM-based server platforms that also follows the Plan9 model and is implemented on top of one of Plan 9 derivatives called 9front -a free software distributed operating system. We also present the experimental testbed setup and results of experimental study of the Cloud/IX on multi-computer server farm in actual data center environment.

In this paper, we present results of a computational evaluation of goMapReduce parallel programming model approach for solving distributed data processing problems. In some applications, particularly data center problems, including text processing the programming models can aggregate significant number of parallel processes. We first discuss the implementation of these approaches using both Linux and Plan9 operating system and conduct a comparative scalability study of the both. From these results, we empirically show that, in practical implementation and evaluation of a goMapReduce model, the degree of OS's support for distributed processing encountered in solving the resulting word counting problem is crucial. We conclude that the goMapReduce approach under Plan9 may be useful in developing a heuristic approach for the data center problems.

No abstract

No abstract