Ken Yokoyama

Performance problem analysis method for Web systems using multiple decision trees

It is a common task for many system managers to analyze performance problems to keep the system response time small, but it is difficult to identify the characteristics of the situations in which performance problems occur. To solve this problem, we developed an analysis method that uses a decision tree approach for Web system performance problems. In order to output simpler and more understandable results, we developed an original evaluation function for tree construction rather than using an existing one. In addition, to construct an appropriate decision tree from a huge number of parameters, we developed an algorithm which repeats decision tree construction and evaluation with a changing set of construction parameters and chooses the best tree. We implemented and evaluated our algorithm in an actual Web system and we found that our approach is much better than extant decision tree algorithms in terms of accuracy, simplicity, and computational time

Delay estimation method for n-tier architecture

These days, the majority of large systems serving large numbers of users prefer N-tier architecture because of its scalability and flexibility. To maintain the quality of service in these systems, we need to understand how much delay is generated in each tier. However, the structure and the behavior of this architecture is so complicated that it is difficult to analyze these delays without installing special software or hardware – improvements that might change the servers behavior or result in significant additional costs. To solve these problems, we developed a practical method for estimating the delays generated in each tier of N-tier architecture that uses only easily obtainable parameters. In this paper, we first discuss what these easily obtainable parameters are. We then construct a performance model of the N-tier architecture using these parameters and analyze the delays in the model. Finally, we describe the experiments we conducted to evaluate our approach.