A Classification Scheme for Evaluating Management Instrumentation in Distributed Middleware Infrastructure

• Published in: 2006 4th IEEE/IFIP Workshop on End-to-End Monitoring Techniques and Services pp. 50 - 57
• Main Authors: Karim, F., Thanneer, H.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2006
• Subjects: Availability; Context-aware services; Debugging; Instruments; Integrated Control and Management; management information model; Middleware; middleware technologies; Mission critical systems; Monitoring; Performance and fault management; Proactive and reactive management; Quality of service; Runtime; Software systems
• ISBN: 1424401453; 9781424401451
• DOI: 10.1109/E2EMON.2006.1651279

Management instrumentation is an integrated capability of a software system that enables an external observer to monitor the system's availability, performance, and reliability during operation. It is highly useful for taking both proactive and reactive actions to keep a software system operational in mission-critical environments where tolerance for an unavailable or poor-performing system is very low. Middleware infrastructure components have taken important positions in distributed software systems due to various benefits related to the development, deployment, and runtime operations. Keeping these components highly available and up to the expected performance requires integrated capabilities that allow regular monitoring of critical functionality, measurement of Quality of Service (QoS), debugging and troubleshooting, and health-checks in the context of actual business processes.. Yet, currently there is no approach that enables systematic evaluation of the relative strengths and weaknesses of a middleware component's management instrumentation. In this paper, we will present an approach to evaluating management instrumentation of middleware infrastructure components. We use a classification-based scheme that has a functional dimension called Capability and two main quality dimensions called Usability and Precision. We further categorize each dimension into smaller, more precise instrumentation features, such as Tracing, Distributed Correlation and Granularity. In presenting our approach, we hope to achieve the following: i) educate middleware users on how to systematically assess or compare the overall manageability of a MidIn component using the classification scheme, and ii) share with middleware researchers on the importance of good integrated manageability in middleware infrastructure.