Elias Drakopoulos

Performance analysis of client-server storage systems

The performance analysis of a system in which storage is provided by a file server node on a network of client processors is discussed. The server controls a hierarchy of storage devices, and provides all the necessary file management functions. The clients are large mainframe systems that have their own local storage devices. The movement of files among the various storage levels is managed by a hierarchical storage management system. A closed queuing network model of the client-server storage system is used to analyze the performance of the system for various file movement criteria and to study the tradeoffs between recalling a file and accessing it by a distributed file system. Several network topologies (Ethernet, token ring, channel-to-channel) and their effect on performance are considered. >

A two-phase inter-switch handoff scheme for wireless ATM networks

Supporting mobility in wireless ATM networks poses a number of technical issues. An important issue is the ability to reroute on-going virtual connections during handoff as mobile users move among base stations. We propose a two-phase inter-switch handoff scheme using permanent virtual paths reserved between adjacent mobility enhanced switches (MES). The virtual paths are used in the first phase to rapidly reroute user connections. In the second phase, a distributed optimization process is initiated to optimally reroute handoff connections. The proposed handoff scheme yields small handoff latency and optimal routes while decreasing system cost and complexity. The paper also describes wireless control and ATM signaling capabilities required for supporting this scheme. Specific ATM UNI/NNI protocol extensions are presented. Using analysis, we calculate and study the bandwidth requirement for the reserved virtual paths. We also study the second-phase optimization process overhead as well as the effect of other system design parameters.

Performance study of client-server storage systems

The authors study the performance of a system in which mass storage is provided by a file server node on a network of client processors. The server controls a hierarchy of storage devices and provides all necessary file management functions. The clients are large mainframe UNIX systems that have their own local storage devices. The movement of files among the various storage levels is managed by a hierarchical storage management system. The authors develop and solve a closed queuing network model of the client-server storage system, which is used to analyze the performance of the system for various file movement criteria, and to study the tradeoffs between recalling a file and accessing it by a distributed file system. Several network topologies (Ethernet, FDDI, Channel-to-Channel) and their effect on performance are considered.<<ETX>>

Research: Performance and traffic analysis of a network-based distributed system

In this paper we study the performance of a distributed computing system that consists of a number of clients and a server, interconnected by a carrier-sense multiple-access with collision detection (CSMA/CD) LAN. Each client represents a single-user discless workstation, or an intelligent terminal, and generates application workload using either a conventional Unix file system or the Network File System (NFS). To characterize the application workload we perform a series of measurement experiments in a controlled environment. During each experiment the traffic on the network, and the activity on the various system resources are monitored. The measurements obtained from the experiments are used to parameterize a queueing network model of the system, which is then used to project the performance of the system under various load conditions, to identify system bottlenecks, and to compare design alternatives. The results obtained from the queueing network analysis are used to determine the maximum number of clients that can be supported by the system without violating system performance requirements.

Analysis of a local computer network with workstations and X terminals

The performance of a network based computing system that consists of a number of clients and a server, interconnected by a local area network, is studied. Each client represents a diskless or swapful workstation, or an X terminal, and generates application workload using either a conventional UNIX file system or the Network File System (NFS). To characterize the application workload and the effect of the protocol (login, rlogin, NFS), the user interface (workstation, X terminal) and its configuration (memory size, disk storage), a series of measurement experiments was performed in a controlled environment. During each experiment the traffic on the network and the activity on the various system resources were monitored. The measurements obtained are used to parameterize a queuing network model of the system, which is then used to project the performance of the system under various load conditions, to identify system bottlenecks, and to compare design alternatives.<<ETX>>

Periodic route optimization for handed-off connections in wireless ATM networks

In wireless ATM networks, user connections need to be rerouted during handoff as mobile users move among base stations. The rerouting of connections must be done quickly with minimal disruption to traffic. In addition, the resulting routes must be optimal. A reasonable approach is to implement handoff in two phases. In the first phase connections are rapidly rerouted and in the second phase a periodic route optimization procedure is executed. The route optimization should impose minimal signaling and processing load on the ATM switches. In this paper, we propose and study a periodic execution of route optimization for a two-phase handoff scheme. We study two types of execution: non-adaptive and adaptive. For the adaptive optimization, we consider two adaptation schemes that are dependent on network conditions. A simulation model is developed to study system performance. The adaptive route optimization is shown to minimize signaling and processing load while maximizing utilization of reserved resources.

Performance modeling and analysis of a distributed computing environment

The paper studies the performance of computing environment design alternatives for an application workload associated with a large software product generation process. A number of configurations based on shared memory multiprocessor computing platforms and network file servers are considered in the study. The various computing environment configurations are differentiated based on the location of the devices that provide physical storage for the input and output files of the software product generation process, and the characteristics of the computing platforms that are used to provide compute and file services. The evaluation of the design alternatives is based on a multiclass priority queuing network model that is used to analyze system performance under various load conditions, identify potential bottlenecks and study design tradeoffs.

Design issues in data networks

The paper describes the network design and analysis of a multi-protocol application environment characterized by a client/server architecture, integration of legacy and distributed database structures, frame relay wide area network, and token ring local area networks. Detailed workload characterization and performance modeling of the application environment is presented, and network design issues are addressed. The model is used to study network performance under various load conditions, identify bottlenecks and compare design alternatives.