Larry Dowdy

A capacity planning process for performance assurance of component-based distributed systems

For service providers of multi-tiered component-based applications, such as web portals, assuring high performance and availability to their customers without impacting revenue requires effective and careful capacity planning that aims at minimizing the number of resources, and utilizing them efficiently while simultaneously supporting a large customer base and meeting their service level agreements. This paper presents a novel, hybrid capacity planning process that results from a systematic blending of 1) analytical modeling, where traditional modeling techniques are enhanced to overcome their limitations in providing accurate performance estimates; 2) profile-based techniques, which determine performance profiles of individual software components for use in resource allocation and balancing resource usage; and 3) allocation heuristics that determine minimum number of resources to allocate software components. Our results illustrate that using our technique, performance (i.e., bounded response time) can be assured while reducing operating costs by using 25% less resources and increasing revenues by handling 20% more clients compared to traditional approaches.

A Component Assignment Framework for Improved Capacity and Assured Performance in Web Portals

Web portals hosting large-scale internet applications have become popular due to the variety of services they provide to their users. These portals are developed using component technologies. Important design challenges for developers of web portals involve (1) determining the component placement that maximizes the number of users/requests (capacity) without increasing hardware resources and (2) maintaining the performance within certain bounds given by service level agreements (SLAs). The multitude of behavioral patterns presented by users makes it hard to identify the incoming workloads. n nThis paper makes three contributions to the design and evaluation of web portals that address these design challenges. First it introduces an algorithmic framework that combines bin-packing and modeling-based queuing theory to place components onto hardware nodes. This capability is realized by the Component Assignment Framework for multi-tiered internet applications (CAFe). Second, it develops a component-aware queuing model to predict web portal performance. Third, it provides extensive experimental evaluation using the Rice University Bidding System (RUBiS). The results indicate that CAFe can identify opportunities to increase web portal capacity by 25% for a constant amount of hardware resources and typical web application and user workloads.

The Impact of Variability on Soft Real-Time System Scheduling

Soft real-time systems sometimes operate under uncertain and unpredictable environmental conditions which makes event arrival times unreliable and variable. Input to such systems also change from time to time making event processing times variable. Due to such variations, traditional techniques using worst case times to estimate system performance deviate far from actual expected behavior.This paper presents a Method of Stages based Analysis of soft Real Time systems (MoSART). MoSART takes into account variance in both the arrival and execution time and can model the performance of different scheduling algorithms. Sensitivity analysis, experimental validation, and the discovery of state dependent algorithms that outperform popular algorithms are demonstrated.

Experimental sensitivity analysis of wireless protocols in an office environment

This paper provides a methodical experimental evaluation of the 802.11a and 802.11b protocols, presenting an unbiased and independent performance review in a given office environment. Specifically, the bandwidths of the two protocols are compared as a function of distance between the wireless laptops and their access point (AP). In addition, the effects on bandwidth in the presence of interference from competing Bluetooth devices at various distances are also measured. Finally, the performance effects of using two different levels of security (i.e., 64 and 128 bit encryption schemes) are reported.

Performance Modeling of Enterprise Grids

Modeling has long been recognized as an invaluable tool for predicting the performance behavior of computer systems. Modeling software, both commercial and open source, is widely used as a guide for the development of new systems and the upgrading of exiting ones. Tools such as queuing network models, stochastic Petri nets, and event driven simulation are in common use for stand-alone computer systems and networks. Unfortunately, no set of comprehensive tools exists for modeling complex distributed computing environments such as the ones found in emerging grid deployments. With the rapid advance of grid computing, the need for improved modeling tools specific to the grid environment has become evident. This chapter addresses concepts, methodologies, and tools that are useful when designing, implementing, and tuning the performance in grid and cluster environments

Abstract only: a capacity planning process for performance assurance of component-based distributed systems

For service providers of multi-tiered component-based applications, such as web portals, assuring high performance and availability to their customers without impacting revenue requires effective and careful capacity planning that aims at minimizing the number of resources, and utilizing them efficiently while simultaneously supporting a large customer base and meeting their service level agreements. This paper presents a novel, hybrid capacity planning process that results from a systematic blending of 1) analytical modeling, where traditional modeling techniques are enhanced to overcome their limitations in providing accurate performance estimates; 2) profile-based techniques, which determine performance profiles of individual software components for use in resource allocation and balancing resource usage; and 3) allocation heuristics that determine minimum number of resources to allocate software components. Our results illustrate that using our technique, performance (i.e., bounded response time) can be assured while reducing operating costs by using 25% less resources and increasing revenues by handling 20% more clients compared to traditional approaches.

The Identification and Characterization of Workload Classes

In all areas of engineering, it is important to be able to accurately forecast how a system would react to some change. For instance, for a proposed new bridge design, what would be the effect of 10 large trucks simultaneously crossing the bridge? Or, for an existing parallel computer system, what would be the expected response time if three processors failed simultaneously? To be able to answer such performance prediction questions, an engineer needs a correct characterization of the current system.