Research
Publications
Software Engineering
Performance Engineering | Software Engineering
Performance Engineering
Performance Engineering and Global Software Development
Sohel Aziz, Gaurav Caprishan, Kingshuk Dasgupta, and Stephen Lane
The need to achieve system performance in a way that reduces risk and improves cost-effectiveness and time-to-market for performance-critical systems is one of the principal goals of IS organizations. This requires a holistic and quantitative approach to performance, without compromising on other system qualities like flexibility, maintainability, reliability, and usability. Infosys has put into practice such an approach by combining recently developed practices in performance engineering with client delivery experience. Adapted to ensure collaboration among globally distributed application development teams, it combines performance modeling with benchmarking, tuning, and optimization to deliver high-performance systems.
Should performance be an integral part of the SDLC?
Vaidyanatha Siva and Sridhar Sharma
Poorly performing IT apps are bleeding corporations~$60B/year. Diagnosing, fine tuning and fixing poorly performing applications is both a science and an art, that can provide great dividends.
This article appears in the SETLabs Briefings on ‘Enterprise IT Perspectives’ (Oct - Dec, 2006).
Read the complete issue
Enterprise Application Performance Management: An End-to-End Perspective
Vishy Narayan
Performance management of enterprise applications is the key to maximising return on IT investment. With rapidly evolving technology, continued improvements in performance management and establishing baseline metrics is important to the sustenance of key infrastructure elements
This article appears in the SETLabs Briefings on ‘Enterprise IT Perspectives’ (Oct - Dec, 2006).
Read the complete issue
Design of a Performance Diagnosis tool for .NET applications
Ram Kumar C, Sachin Ashok Wagh
Dr. Dobbs Journal, August 2005
Our approach to diagnosis begins with the creation of a knowledge base comprising of several performance signatures or performance patterns, which are symptomatic evidences for detecting bottlenecks.
Software Infrastructure Bottlenecks in J2EE
Deepak Goel
ONJava.com, January 2005
Scalability is one of the most important non-functional requirements of a system. But there could be several bottlenecks within a system, which might prevent it from being scalable. In this article, we try to analyze the case in which the software infrastructure becomes a bottleneck, long before any of the hardware resources (such as CPU, memory, disk space, and network speed) are fully consumed. This is a tricky problem whose solution is explored below.
Performance modeling for the Grid
Sengupta S.
06/01/2004
As Grid computing gets mainstream, more applications are getting Gridenabled to achieve high performance. However, running on Grid does not automatically ensure uniform speedup and scalability for an application.
Experiences with Memory Access Issues in RTOS
Narendra Ramanna
Based on the architecture of the operating system as well as the nature of the software defect, memory access issues often encountered on Real-Timer Operating Systems [RTOS] may be either very simple or a cryptic puzzle. This article presents some of the memory access issues often noticed on "simpler" models of soft Real-Time Operating Systems. Software Reliability Assessment of High Volume Web Systems
Rupal Chachra, Surendra Babu, Rajeshwari G.
Accepted in WSEAS Transaction on Systems and ISA`04 Conference proceedings, April 2004
04/07/2004
Software reliability is crucial for high volume Web based systems, where outages can result in loss of revenue and dissatisfied customers. Here we advocate a simple, but elegant approach based on construction of a Customer Behavior Model Graph to capture.
(
The paper you are trying to access is not available as a free download. Please contact us to know more about how you can obtain a copy of the same.)Software Scalability Analysis with Surrogate Delay
Rajeshwari G.
11/01/2003
This note introduces the notion of software utilization limit, and proposes an approximate solution for analyzing software scalability for distributed systems.
Characterizing Web Workloads - a Transaction Oriented View
JSengupta S.
Accepted and to be presented in IEEE / IFIP 5th International Workshop on Distributed Computing (IWDC 2003) to be held in Calcutta in December 2003.
10/09/2003
In this paper, we present a technique for characterizing Web workloads in a transaction-oriented manner through offline analysis of Web server logs.
(
The paper you are trying to access is not available as a free download. Please contact us to know more about how you can obtain a copy of the same.)Workload Modeling for Web-based Systems
Sengupta S., Rajeshwari G.
Accepted in advanced session of modeling, maths and statistics in CMG`s up-coming conference (CMG 03) to be held in Dallas in December.
09/03/2003
Web-based systems mostly have arrivals other than Poisson; this renders the standard analytical methods of workload modeling inapplicable. In this paper we examine real-life sites that had self-similar or fractal arrival.
(
The paper you are trying to access is not available as a free download. Please contact us to know more about how you can obtain a copy of the same.)
Event
Infosys at the CMG'08 International Conference
More
Media Mentions
Fortune ranks Infosys 10 among Top Companies for Leaders 2007 More
In the News
Sourcing at your fingertips:
Global Sourcing Essentials
Everything you wanted to know about global sourcing, in five easy parts.
Download your copy
