عنوان مقاله
تحلیل عملکرد تعادل و توازن بار ایستا در گرید
فهرست مطالب
مقدمه
الگوریتم های توازن بار ایستا
سیستم مانیتورینگ گرید پیشنهاد شده
نتایج ارزیابی
نتیجه گیری
بخشی از مقاله
سیستم کانیتورینگ گرید پیشنهاد شده
کلیات
اکثر خدمات اطلاعاتی و مانیتورینگ گرید دارای موانعی بوده و استفاده از آنها راحت نمی باشد. اولاً اینکه آنها بسیار بزرگ بوده و نصب ، پیکره بندی و آرایش آنهابسیار سخت و دشوار می باشد. ثانیاً، برخی از توابع مهیا شده از سوی آنها به برخی از پروژه های خاص محدود می شوند. این توابع ممکن است برای پروژه دیگر بلااستفاده بوده و عملکرد این پروژه را کاهش دهند.
کلمات کلیدی:
Abstract— Monitoring is the act of collecting information concerning the characteristics and status of resources of interest. The Grid Monitoring Architecture (GMA) based on simple Consumer/ Producer architecture with an integrated system registry and distinguishes transmission of monitoring data and data discovery logically. We propose grid monitoring system based on GMA. The proposed grid monitoring system consists of producers, registry, consumers, and failover registry. The registry is used to match the consumer with one or more producers, so it is the main monitoring tool. The failover registry is used to recover any failure in the main registry. The structure of proposed grid monitoring system depends on java Servlet and SQL query language. Load balancing (LB) should be added to the system to overcome the message overloaded. Load balancing algorithms can be static or dynamic. This paper evaluates the four types of static load balancing algorithms; Randomized, Round Robin, Threshold, and Central Manager algorithms. We evaluate the performance of the system by measuring the response time, and throughput. Central Manager algorithm introduces the smallest response time and the highest throughput. Index Terms— Grid computing, monitoring system, load balancing, response time, Security, throughput. I. INTRODUCTION rid computing has emerged as an important new field. It focuses on large-scale resource sharing, innovative applications, and high-performance orientation. The distinguished advantage of Grid against traditional distributed computing is that it can integrate a large number of computing resources as well as data resources to solve some kind of challenges. As more and more web service applications, Grid computing has extended its territory from traditional computing Grid to public and provides Grid services. The purpose of Grid is to realize coordinated resource sharing and problem in dynamic virtual organizations (VOs) [1]. In this environment, the security problem is a hot topic in Grid research due to the dynamics and uncertainty of Grid system. The Grid security issues can be categorized into three main categories: architecture related issues, infrastructure related issues, and management related issues [8]. This paper is focused on Grid management. The different 1,3 Graduate School of Advanced Integration Science, Chiba University, Japan 263-8522 2 Faculty of Computers and Information, Mansoura University, Egypt Emails: 1,2sherihan@graduate.chiba-u.jp, 3 kitakami@faculty.chiba-u.jp management issues that Grid administrators are worried about are credential management, trust management, and monitoring related issues. The ability to monitor and manage distributed computing components is critical for enabling high performance distributed computing. Monitoring data is needed to determine the source of performance problems and to tune the system for better performance [9]. Monitoring is the act of collecting information concerning the characteristics and status of resources of interest. Monitoring is also crucial in a variety of cases such as scheduling, data replication, accounting, performance analysis and optimization of distributed systems or individual applications, self-tuning applications, and many more [8]. The functions of monitoring are correctness checking, performance enhancement, dependability or fault tolerance, performance evaluation, debugging and testing, control or management, and security. Most existing monitoring systems work with network or cluster systems. There are several research systems implementing the Grid Monitoring Architecture (GMA) [6]: Autopilot, R-GMA, MDS, etc. Autopilot [11] is a framework for enabling applications to dynamically adapt to changing environments. It aims to facilitate end-users in the development of application. R-GMA [12] combines grid monitoring and information services based on the relational model. Although the robustness of R-GMA, it has three drawbacks: flow of data, loss of control message, and single point of failure. The Monitoring and Discovery System (MDS) [3] of the Globus Toolkit (GT) is a suite of components for monitoring and discovering Grid resources and services. It has many problems such as it is too difficult to install. In this paper, we focus on monitoring management in Grid system. The proposed Grid monitoring system is also based on the GMA [6]. GMA is the basis of most of monitoring system. The goal of GMA is to provide a minimal specification that will support required functionality and allow interoperability. We design a simple Grid monitoring system. The proposed system components are producers, registry, consumers, and failover registry. The goals of this system are to provide a way for consumers to obtain information about Grid resources as quickly as possible, and to recover any faults in the system. There is no direct relationship between producer and consumer. The monitoring tool is registry. It manages and controls the relationship between all producers and consumers existing Performance Analysis of Static Load Balancing
