Software Performance Engineering

• Event stream processing (ESP) has recently emerged as a popular paradigm for implementing high-volume data processing applications. • Software aging is a phenomenon consisting of the performance degradation, or the increase of the failure rate of a program, which can affects popular stream processing technology as Apache Storm. • Software rejuvenation is a means to prevent aging-related failures, hence to mitigate the impact of aging in Apache Storm. a b s t r a c t Event stream processing has recently emerged as a popular paradigm for implementing high-volume distributed (near-)real time data processing applications. Several open source systems are today available, supporting the development of such applications, many of which developed with the technologies of the Apache Software Foundation. These so called stream processors are long-running complex software systems which may be affected by software aging, a well-known phenomenon among operation engineers, consisting of a progressive increase in the failure rate or in performance degradation of a software system over time. We address the problem of identifying symptoms and sources of software aging in the Apache Storm event stream processing system; this helps to identify proper strategies to prevent or mitigate anomalous behaviors in production environments. To this aim, we present an experimental study investigating aging manifestations in a popular system, namely Apache Storm. Results show that Storm presents anomalous behaviors in long runs, which prevent some topologies from working continuously. These can be attributed to software aging, due to Storm internal resource management mechanisms influenced by the garbage collector and the memory assigned to worker processes. We discuss the aging-related Apache Storm behaviors, and we experiment rejuvenation actions, showing that they are actually able to remove them.

Software development organizations are increasingly becoming more focused on performance evaluation and improvement of their software applications. An initial process for performance evaluation is proposed and has been studied on a software application under various configurations and workloads. This method, using a combination of threshold analysis and correlation cluster analysis on collected performance measurements, identifies key relationships among different computer performance measurements, as well as existing bottlenecks without detailed knowledge of internal system information.

10th International Conference on Software Engineering & Trends (SE 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Software Engineering. The goal of this conference is to bring together researchers and practitioners from academia and industry to focus on understanding Modern software engineering concepts and establishing new collaborations in these areas.

The International Journal of Software Engineering & Applications (IJSEA) is a bi-monthly open access peer-reviewed journal that publishes articles which contribute new results in all areas of the Software Engineering & Applications. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on understanding Modern software engineering concepts & establishing new collaborations in these areas.

The need for software architecture evaluation is based on the realization that software development, like all engineering disciplines, is a process of continuous modeling and refinement. Detecting architectural problems before the bulk of development work is done allows re-architecting activities to take place in due time, without having to rework what has already been done. At the same time, tuning activities allow software performance to be enhanced and maintained during the software lifetime. When dealing with product families, architectural evaluations have an even more crucial role: the evaluations are targeted to a set of common products. We have tried different approaches to software assessments with our mobile phone software, an embedded real-time software platform, which must support an increasingly large number of different product variants. In this paper, we present a case study and discuss the experiences gained with three different assessment techniques that we have worked on during the past five years. The assessment techniques presented include scenario-based software architecture assessment, software performance assessment and experience-based assessment. The various evaluation techniques are complementary and, when used together, constitute a tool which a software architect must be aware of in order to maintain and evolve a large software intensive system.

When fixing performance problems in new or existing software or determining whether a proposed system will meet its performance objectives, taking an architectural approach can make it possible to achieve performance objectives more quickly and at a lower cost. This paper describes PASA, a method for performance assessment of software architectures. It was developed from our experience in conducting performance assessments of software architectures in a variety of application domains including web-based systems, financial applications, and real-time systems. PASA uses the principles and techniques of software performance engineering (SPE) to determine whether an architecture is capable of supporting its performance objectives. The method may be applied to new development to uncover potential problems when they are easier and less expensive to fix. It may also be used when upgrading legacy systems to decide whether to continue to commit resources to the current architecture or migrat...

This position paper brings together the evaluation of ambient intelligence architectures in context-awareness systems with performance modeling. Thus, firstly appropriate description methods for distributed intelligent applications are summarized. Derived from the system characterization, typical software performance engineering techniques are based on the augmented description of the model regarding performance annotations. However, these annotations are only related with the syntactical view

In today’s scenario, most of the organizations provide the services through the web. This makes the web service an important research area. In addition, early design and building web services, it is necessary to concentrate on the quality of web services. Performance is an important quality attributes that to be considered during the designing of web services. The expected performance can be achieved by proper scheduling of resources and scalability of the system. Scalability is a desirable attribute of a process computer system or network. Poor scalability can result in lacking system performance. Hence, in this paper, we have reviewed the literature available for the quality attributes of performance and scalability and identified the issues that affect the quality attributes related to Web Services.

Performance models assist capacity management and planning for large-scale enterprise applications by predicting their performance for different workloads and hardware environments. Manually creating these models often outweighs their benefits. Automatic performance model generators have been introduced to facilitate the model creation. These generators often use custom monitoring solutions to generate the required input data for the model creation. In contrast, standardized application performance management (APM) solutions are used in industry to control performance metrics for productive systems. This work presents the integration of industry standard APM solutions with a performance model generation framework. We apply the integration concepts using the APM solution Dynatrace and a performance model generation framework for Palladio Component Models (PCM).

Responsiveness and scalability are important quality-of-service attributes for Web applications. Web sites that are slow, either because of poor responsiveness or lack of scalability, can produce customer dissatisfaction, loss of revenue and/or productivity, and potentially more serious consequences. To avoid these problems, it is important to know whether users will be able to access information in a timely fashion, whether the hardware will be able to handle the load, and whether the system will scale to meet projected demand before the system is deployed. This paper describes how to apply the techniques of Software Performance Engineering (SPE) to Web applications. We focus on using the SPE models to provide decision support during the software architectural design phase because the decisions made at that time have the largest effect on performance and scalability. A case study illustrates the application of these techniques to a typical Web application.

As an important element of the Smart Grid, Advanced Metering Infrastructure (AMI) systems have been implemented and deployed throughout the world in the past several years. An AMI system connects millions of end devices (e.g., smart meters and sensors in the residential level) with utility control centers via an efficient two-way communication infrastructure. AMI systems are able to exchange substantial meter data and control information between utilities and end devices in real-time or near real-time. The major challenge our research was to scale ABB’s Meter Data Management System (MDMS) to manage data that originates from millions of smart meters. We designed a lightweight architecture capable of collect ever-increasing large amount of meter data from various metering systems, clean, analyze, and aggregate the meter data to support various smart grid applications. To meet critical high performance requirements, various concurrency processing techniques were implemented and integrated in our prototype. Our experiments showed that on average the implemented data file parser took about 42 minutes to complete parsing, cleaning, and aggregating 5.184 billion meter reads on a single machine with the hardware configuration of 12-core CPU, 32G RAM, and SSD Hard Drives. The throughput is about 7.38 billion meter reads (206.7GB data) per hour (i.e., 1811TB/year). In addition, well-designed publish/subscribe and communication infrastructures ensure the scalability and flexibility of the system.

Software performance is an important non-functional quality attribute and software performance evaluation is an essential activity in the software development process. Especially in embedded real-time systems, software design and evaluation are driven by the needs to optimize the limited resources, to respect time deadlines and, at the same time, to produce the best experience for end-users. Software product family architectures add additional requirements to the evaluation process. In this case, the evaluation includes the analysis of the optimizations and tradeoffs for the whole products in the family. Performance evaluation of software product family architectures requires knowledge and a clear understanding of different domains: software architecture assessments, software performance and software product family architecture. We have used a scenario-driven approach to evaluate performance and dynamic memory management efficiency in one Nokia software product family architecture. In this paper we present two case studies. Furthermore, we discuss the implications and tradeoffs of software performance against evolvability and maintenability in software product family architectures.

Software systems are today one of the most complex artifacts, they are simultaneously used by hundred-thousand of people sometimes in risk real time operations, such as auctions or electronic commerce. Nevertheless, it is a common practice to deploy them without the expected performance. Software Performance Engineering has emerged as a discipline to complement Software Engineering research in order to address this kind of problems. In this work, we survey some recent contributions in the field of Software Performance ...

In distributed environment the changes and challenges faced by composite web services in their network environment are enormous. The primary issue in these systems is to distribute the load among various components of the composite web services to improve the performance through minimizing the response time. In this paper, we present a methodology to estimate the load sharing among composite web services using traditional workflow concept combined with game theory approach. In addition, we have developed a simulation model and observed that the results are promising for a better understanding of workload sharing among individual web services. We obtained the stable solution for ensuring the cooperation of the web services which further helps in capacity planning in composite web services network environment.

Cloud computing facilitates service providers to rent their computing capabilities for deploying applications depending on user requirements. Applications of cloud have diverse composition, configuration and deployment requirements. Quantifying the performance of applications in Cloud computing environments is a challenging task. In this paper, we try to identify various parameters associated with performance of cloud applications and analyse the impact of resource management and scalability among them.

In this paper, we present an evaluation methodology to validate the performance of a UML model, representing a software architecture. The proposed approach is based on open and well-known standards: UML for software modeling and the OMG Profile for Schedulability, Performance, and Time Specification for the performance annotations into UML models. Such specifications are collected in an intermediate model, called the Performance Context Model (PCM). The intermediate model is translated into a performance model which is subsequently evaluated. The paper is focused on the mapping from the PCM to the performance domain. More specifically, we adopt Petri nets as the performance domain, specifying a mapping process based on a compositional approach we have entirely implemented in the ArgoPerformance tool. All of the rules to derive a Petri net from a PCM and the performance measures assessable from the former are carefully detailed. To validate the proposed technique, we provide an in-depth analysis of a web application for music streaming.

Quantitative analysis of software systems has been recognized to be important and useful for requirements and design, and, specifically, performance analysis should be integrated in the software development life cycle from the early stages. To this aim, several approaches have been recently proposed to integrate or combine performance analysis and software architecture specification. In this paper we present a brief review and a comparison of some approaches that derive performance models from SA specification. We focus on the generality of the proposed methodologies, the required constraints and assumptions, the type of performance model, the separation of performance model and specification language, the implementation, and how easily the obtained performance results can provide a feedback to the software designer.

In distributed environment the changes and challenges faced by composite web services in their network environment are enormous. The primary issue in these systems is to distribute the load among various components of the composite web services to improve the performance through minimizing the response time. In this paper, we present a methodology to estimate the load sharing among composite web services using traditional workflow concept combined with game theory approach. In addition, we have developed a simulation model and observed that the results are promising for a better understanding of workload sharing among individual web services. We obtained the stable solution for ensuring the cooperation of the web services which further helps in capacity planning in composite web services network environment.

The success of a software product is not only measured by the achievement of functional requirements rather it embodies a wide range of critical aspects such as the fulfillment of quality attributes which can be achieved through a focus given to every development lifecycle. With the increase in size and complexity the need for software performance and balanced trade-offs are becoming very intensive. Furthermore, software products with poor performance or an unbalanced trade-offs have a diverse effect on businesses, stakeholder relationships, budget, schedule etc. This thesis proposes a three layered framework for performance and collaborative trade-off analysis aimed at primarily incorporating performance and trade-off considerations at every step of development lifecycle that can be adopted to different process models, lifecycles, application domains and development methodologies. Additionally, a selection/decision support model is proposed to assist the framework in order to conduct a collaborative trade-off analysis and evaluation. The design of the framework and selection model follows a layered approach derived from a preliminary model and generic process outlines with entities that are integrated. The feasibility and effectiveness of the framework is simulated and evaluated by focusing on the core part of the framework. A standalone desktop application developed using .NET Framework using MS VS C# and SQL Server as a backend and a web based system designed with CMS powered by PHP 5.0 and MySQL server as a backend under ZEND framework is used for the implementation process. The findings of the implementation were concrete which assures the ability of this research to address issues related with performance and trade-offs of software products. The result of this work is believed to be adequate to enhance a software development process to have an efficient performance and balanced trade-offs. Furthermore, this work has determined the ability of the framework and the selection model to be integrated with various process models, application domains and frameworks.

Attribute-based Workload Characterization (AWC) combines qualitative models for performance with quantitative analysis of relationships between workloads and performance measures. The qualitative aspects document performance attributes, clarifying dimensions of application usage and raising important questions about the architecture. Quantitative analysis validates the choice of attributes with traditional statistical techniques. Preliminary results for our case study show all workload factors were identified by AWC and there is good correlation of the workloads with measured performance.

This paper presents the results of a software performance evaluation of a client/server application in an Open Systems environment. Some interesting features of the design and the graphical user interface are described and their performance characteristics are evaluated. The evaluation uses a new Software Performance Engineering (SPE) tool to create software models and evaluate design alternatives. INTRODUCTION

Web Service is an interface which implements business logic. Performance is an important quality aspect of Web services because of their distributed nature. Predicting the performance of web services during early stages of software development is ...

This presentation covers system and application performance engineering. Developed and shared with a partner team at the Tata Consulting team in Chennai, India, this talk outlines the essentials of performance engineering from its motivations, approaches, core models, and applications. Topics included are queuing, performance modeling, the performance analysis process, speed-up, scale-up, Little’s Law, the Universal Scalability Model, Performance SDLC and Maturity, a detailed example of applied application performance engineering, and a set of recommendations. Finally, a set of references are provided for further research.