CROWNBench: A Grid Performance Testing System Using Customizable Synthetic Workload

نویسندگان

  • Xing Yang
  • Xiang Li
  • Yipeng Ji
  • Mo Sha
چکیده

The Grid middleware must be developed iteratively and incrementally, so Grid performance testing is critical for middleware developers of Grid system. Considering the special characters of Grid system, in order to gain meaningful and comprehensive results of performance testing, it is necessary to implement testing on real Grid environment with various types of workload. CROWNBench, as described in this paper, is a system for helping Grid middleware developers to evaluate middleware design and implement using customizable synthetic workload. Middleware developers can customize testing workload basing on the model of Grid workload derived from real workload traces, including its structure and parameters, and then workload is synthesized automatically and contained jobs will be submitted by CROWNBench in a distributed manner. CROWNBench defines several metrics for measuring Grid performance as automatic testing results. The experiment, which used CROWNBench to test the performance of Grid system with CROWN Grid middleware, shows that the system already finished have accomplished its prospective goal. It can implement Grid performance testing in an efficient, flexible, controllable, replayable and automatic way to help middleware developers evaluate and improve their products effectively.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Performance Prediction of Multi-Agent Based Simulation Applications on the Grid

A major requirement for Grid application developers is ensuring performance and scalability of their applications. Predicting the performance of an application demands understanding its specific features. This paper discusses performance modeling and prediction of multi-agent based simulation (MABS) applications on the Grid. An experiment conducted using a synthetic MABS workload explains the k...

متن کامل

Workload Generation for Trace Based Grid Simulations

Testing Grid models and their resource management components is a critical part of efficient Grid development. There are two ways to experimentally assess the performance of Grid models: benchmarking and using synthetic grid workloads. Workload generation for Grids has become more problematic than for independent supercomputers. It requires standardization of the activity of thousand simultaneo...

متن کامل

Synthetic Grid Workloads with Ibis, KOALA, and GrenchMark

Grid computing is becoming the natural way to aggregate and share large sets of heterogeneous resources. However, grid development and acceptance hinge on proving that grids reliably support real applications. A step in this direction is to combine several grid components into a demonstration and testing framework. This paper presents such an integration effort, in which three research prototyp...

متن کامل

Performance Evaluation of MySQL 5.0 and Berkeley DB XML as a Grid Resource Information Manager (GRIM) with a Benchmark/Workload

A challenge in the distributed middleware that implements a grid envisioned to span the world, is the management of information about the resources available to the Grid. This paper describes an experimental study we undertook to better understanding the performance of the native XML database Berkeley DB XML, as a grid resource information manager system compare to MySQL 5.0. We run a benchmark...

متن کامل

On Grid Performance Evaluation Using Synthetic Workloads

Grid computing is becoming a common platform for solving large scale computing tasks. However, a number of major technical issues, including the lack of adequate performance evaluation approaches, hinder the grid computing’s further development. The requirements herefore are manifold; adequate approaches must combine appropriate performance metrics, realistic workload models, and flexible tools...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008