Raúl Peña-Ortiz

Dweb model: Representing Web 2.0 dynamism

Due to the increase in the number and popularity of applications such as e-commerce or on-line booking systems, typical of the Web 2.0, dynamic contents are becoming more and more frequent. This trend suggests the review of widely accepted paradigms and models for the World Wide Web. As a system that is continuously changing, both in the offered applications and in its infrastructure, performance evaluation studies are a main concern to provide sound proposals when designing new web-related systems. Although the dynamism in the workload characterization has also been tackled in previous research, it has not been modeled in a precise way yet because of its complex nature. In this paper we propose the Dweb model which represents the dynamism of current web applications in the workload characterization. Dweb is based on three main concepts that allow to model dynamic workload: navigation, workload test and workload distribution. In addition, a dynamic workload generator has been implemented to show the practical application of the proposed model, which has been illustrated through a case study.

Analyzing web server performance under dynamic user workloads

The increasing popularity of web applications has introduced a new paradigm where users are no longer passive web consumers but they become active contributors to the web, specially in the contexts of social networking, blogs, wikis or e-commerce. In this new paradigm, contents and services are even more dynamic, which consequently increases the level of dynamism in users behavior. Moreover, this trend is expected to rise in the incoming web. This dynamism is a major adversity to define and model representative web workload, in fact, this characteristic is not fully represented in the most of the current web workload generators. This work proves that the web users dynamic behavior is a crucial point that must be addressed in web performance studies in order to accurately estimate system performance indexes. In this paper, we analyze the effect of using a more realistic dynamic workload on the web performance metrics. To this end, we evaluate a typical e-commerce scenario and compare the results obtained using different levels of dynamic workload instead of traditional workloads. Experimental results show that, when a more dynamic and interactive workload is taken into account, performance indexes can widely differ and noticeably affect the stress borderline on the server. For instance, the processor usage can increase 30% due to dynamism, affecting negatively average response time perceived by users, which can also turn in unwanted effects in marketing and fidelity policies.

The Impact of User's Dynamic Behavior on Web Performance

The increasing popularity of web applications has introduced a new paradigm where users are no longer passive web consumers but they become active contributors to the Web, specially in the contexts of social networking, blogs, wikis or e-commerce. In this new paradigm, contents and services are even more dynamic, which consequently increases the level of dynamism in users behavior. Moreover, this trend is expected to rise in the incoming Web. This dynamism is a major adversity to define and model representative web workload, in fact, this characteristic is not fully represented in the most of the current web workload generators. This work proves that the web users dynamic behavior is a crucial point that must be addressed in web performance studies in order to accurately estimate system performance indexes. In this paper, we analyze the effect of using a more realistic dynamic workload on the web performance metrics. To this end, we evaluate a typical e-commerce scenario and compare the results obtained using dynamic workload instead of traditional workloads. Experimental results show that, when a more dynamic and interactive workload is taken into account, performance indexes can widely differ and noticeably affect the stress borderline on the server. For instance, the processor usage can increase 20% due to dynamism, affecting negatively average response time perceived by users, which can also turn in unwanted effects in marketing and fidelity policies.

The impact of user-browser interaction on web performance

The user interaction with the current web contents is a major concern when defining web workloads in order to precisely estimate system performance. However, the intrinsic difficulty to represent this behavior in a workload model leads many research works to still use workloads non representative of the current web navigations. In contrast, in previous works we demonstrated that the use of an accurate workload model that considers users dynamism when navigating the web clearly affects system performance metrics. In this paper we analyze, for the first time, the effect of considering the User-Browser Interaction (UBI) as a part of users dynamic behavior on web workload characterization in performance studies. To this end, we evaluate a typical e-commerce scenario and compare the obtained results for different UBI behaviors, such as the use of the back button and parallel browsing originated by using browser tabs or opening new windows when surfing a website.

An approach for economic evaluation of cloud-based applications

This paper links the economic cost of the cloud infrastructure to the business model of an internet-based company in order to evaluate costs and benefits of web applications. To this end, performance models and indexes related to the usage of the main system resources (i.e. processor, memory, storage and network bandwidth) have been reformulated to include new useful metrics for business management, such as customer abandonments and service costs. With the aim of showing practical application of the proposed evaluation study, a typical e-commerce scenario has been considered. Experimental results show that, our approach allows internet-based companies to estimate more accurately the cost of adopting a particular cloud configuration, both in terms of cost of infrastructure and cost of losing customers due to performance degradation. Consequently, it permits to appraise the viability of business decisions, such as promotions and expansion strategies.

Generating realistic workload for web performance studies

This chapter presents the current state of the art in characterizing and generating workloads for Web performance evaluation. First, it reviews a representative subset of the most relevant perspectives to define Web workloads, and analyzes the main drawbacks that we have to tackle in order to obtain representative workloads for current Web applications. After that, we evaluate and classify the most commonly used software tools proposed in the open literature according to their main features and ability to generate workloads for the dynamic Web. Finally, the chapter presents the Dynamic WEB workload model (DWEB) with the aim of characterizing a more realistic workload when evaluating the performance of current Web applications. DWEB tackles in a progressive way the main challenges when modeling the user’s behavior on representative workloads. To this end, it defines a couple of new concepts: user’s navigations and user’s roles. These concepts characterize different levels of dynamism in the workload definition by means of modeling Web users’ behaviors.

A Methodology for Economic Evaluation of Cloud-Based Web Applications

Cloud technology is an attractive infrastructure solution to optimize the scalability and performance of web applications. The workload of these applications typically fluctuates between peak and valley loads and sometimes in an unpredictable way. Cloud systems can easily deal with this fluctuation because they provide customers with an almost unlimited on-demand infrastructure capacity using a pay-per-use model, which enables internet-based companies to pay for the actual consumption instead of peak capacity. In this paradigm, this paper links the business model of an internet-based company to the performance evaluation of the infrastructure. To this end, the paper develops a new methodology for assessing the costs and benefits of implementing web-based applications in the cloud. Traditional performance models and indexes related to usage of the main system resources (such as processor, memory, storage, and bandwidth) have been reformulated to include new metrics (such as customer losses and service costs) that are useful for business managers. Additionally, the proposed methodology has been illustrated with a case study of a typical e-commerce scenario. Experimental results show that the proposed metrics enable internet-based companies to estimate the cost of adopting a particular cloud configuration more accurately in terms of the infrastructure cost and the cost of losing customers due to performance degradation. Consequently, the methodology can be a useful tool to assess the feasibility of business plans.

A new testbed for web performance evaluation

Together with the evolution of the WWW, the behavior of WWW users has changed to include an increased dynamism. This makes traditional ways of conducting performance evaluation studies obsolete. In this chapter we devise a new testbed that has the ability of reproducing different types of web workloads. After the validation process, the testbed will be used to analyze the effect of applying dynamic workloads on the web performance metrics, instead of traditional workloads. The chapter introduces the workload generator used, the testbed design and describes the validation process.

The impact of dynamic user workloads on web performance: The e-commerce case study

The chapter proves that the web user’s dynamic behavior is a crucial issue that must be addressed in web performance studies in order to accurately estimate system performance indexes. To this end, in a first step we analyze and measure the effect of considering different levels of dynamic workload on web performance evaluation, instead of traditional (static) workloads. The more realistic workloads show that processor utilization is not uniformly balanced along time, but overloaded peaks rise when considering user’s dynamic behavior. As a consequence, the probability of a long response time is higher, and the number of user abandonments can increase (up to 40% according to technical studies). Then, in a second step we analyze and measure the effect of considering the User-Browser Interaction (UBI) as a part of user’s dynamic behavior on web workload characterization in performance studies. To this end, we evaluate a typical e-commerce scenario and compare the obtained results for different behaviors that take the user’s interaction with browser interface facilities into account, such as the use of the back button and parallel browsing originated by browser tabs or opening new windows when surfing a website. Experimental results show that these interaction patterns allow users to achieve their navigation objectives sooner than when browsing in a sequential way, so increasing their productivity up to 200% when surfing the website. In addition, results prove that when these types of behavior are taken into account, performance indexes can widely differ and relax the stress borderline of the server. For instance, the server utilization drops as much as 45% due to parallel browsing behavior, permitting the system either to devote more resources to other applications or to serve more users.The chapter proves that the web user’s dynamic behavior is a crucial issue that must be addressed in web performance studies in order to accurately estimate system performance indexes. To this end, in a first step we analyze and measure the effect of considering different levels of dynamic workload on web performance evaluation, instead of traditional (static) workloads. The more realistic workloads show that processor utilization is not uniformly balanced along time, but overloaded peaks rise when considering user’s dynamic behavior. As a consequence, the probability of a long response time is higher, and the number of user abandonments can increase (up to 40% according to technical studies). Then, in a second step we analyze and measure the effect of considering the User-Browser Interaction (UBI) as a part of user’s dynamic behavior on web workload characterization in performance studies. To this end, we evaluate a typical e-commerce scenario and compare the obtained results for different behaviors that take the user’s interaction with browser interface facilities into account, such as the use of the back button and parallel browsing originated by browser tabs or opening new windows when surfing a website. Experimental results show that these interaction patterns allow users to achieve their navigation objectives sooner than when browsing in a sequential way, so increasing their productivity up to 200% when surfing the website. In addition, results prove that when these types of behavior are taken into account, performance indexes can widely differ and relax the stress borderline of the server. For instance, the server utilization drops as much as 45% due to parallel browsing behavior, permitting the system either to devote more resources to other applications or to serve more users.