In this paper, we describe the ClusterProbe, an open, flexible, scalable, and Java-based tool for monitoring large clusters of workstations. The tool provides an open environment by developing a multiple-protocol communication interface that can be connected to various types of external accesses from the clients. The design of ClusterProbe allows it to scale up to commodious capacity with its cascading hierarchical architecture. In addition, ClusterProbe is flexible that the monitoring tool can be easily extended to adapt to the resource changes by using the Java-RMI mechanism. Several useful services are implemented based on ClusterProbe, including the visualization of cluster resources information in various forms and cluster fault management. The tool has been used to assist the execution of a cluster-based search engine and a distributed N-body application. All experiments demonstrate high efficiency and good performance improvement. 1. Introduction Using workstation clusters for...

As the system size of Beowulf-Class cluster system scale up, system administration becomes challenging due to the increases complexity of the system. The lack of powerful tools for the administrative tasks even make the matter worse. This paper presents a proposed framework for system management of large Beowulf cluster that divided the management task into well defined layers of service. A cluster management tools called SCMS (SMILE Cluster Management System) has been developed according to this framework. SCMS provides a rich set of services and tools for large cluster administration. The current implementation of SCMS is discussed referenced to the proposed framework. The software is now freely available on Internet. 1 Introduction and Motivation One of the important class of cluster system is BeowulfClass cluster[10] which emphasis on the use of commodity hardware technology and opensource software to deliver a very high-performance at extremely low cost. Many organizations has s...

: The QUT's Gardens project aims to create a virtual parallel machine out of a network of nondedicated computers (workstations/PCs). These systems are interconnected through low latency and high bandwidth communication links such as Myrinet. Gardens is an integrated programming language and system designed to utilize the idle workstation's CPU cycles to support adaptive parallel computing. A Gardens computation consists of a network of communicating tasks, dynamically mapped onto a network of processors. Tasks are created dynamically and each task consists of a stack and a collection of heap segments in which dynamic data structures are stored. We designed and developed a Gardens cluster monitoring system called Gardmon. It is a portable, flexible, interactive, scalable, locationtransparent, and comprehensive environment for monitoring of Gardens runtime activities. It follows client-server methodology and provides transparent access to all nodes to be monitored from a monitoring mach...