Real-time problem localization for synchronous transactions in HTTP-based composite enterprise applications

Loosely-coupled composite enterprise applications based on modern Web technologies are becoming increasingly popular. While composing such applications is appealing for a number of reasons, the distributed nature of the applications makes problem determination difficult. Stringent service level agreements in these environments require rapid localization of failing and poorly performing services. We present in this paper a method that performs real-time transaction level problem determination by tracking synchronous transaction flows in HTTP based composite enterprise applications. Our method relies on instrumentation of service requests and responses to transmit downstream path and monitoring information in realtime. Further, our method applies change-point based techniques on monitored information at the point of origin of a transaction, and quickly detects anomalies in the performance of invoked services. Since our method performs transaction level monitoring, it avoids the pitfalls associated with techniques that use aggregate performance metrics. Additionally, since we use change-point based techniques to detect problems, our method is more robust than error-prone static threshold based techniques.