@inproceedings{chen2004path-based,
author = {Chen, Mike Y. and Accardi, Anthony and Kiciman, Emre and Lloyd, Jim and Patterson, Dave and Fox, Armando and Brewer, Eric},
title = {Path-Based Failure and Evolution Management},
booktitle = {The 1st USENIX/ACM Symposium on Networked Systems Design and Implementation (NSDI '04)},
year = {2004},
month = {March},
abstract = {We present a new approach to managing failures and evolution in large, complex distributed systems using runtime paths. We use the paths that requests follow as they move through the system as our core abstraction, and our "macro" approach focuses on component interactions rather than the details of the components themselves. Paths record component performance and interactions, are user- and request-centric, and occur in sufficient volume to enable statistical analysis, all in a way that is easy reusable across applications. Automated statistical analysis of multiple paths allows for the detection and diagnosis of complex failures and the assessment of evolution issues. In particular, our approach enables significantly stronger capabilities in failure detection, failure diagnosis, impact analysis, and understanding system evolution. We explore these capabilities with three real implementations, two of which service millions of requests per day. Our contributions include the approach; the maintainable, extensible, and reusable architecture; the various statistical analysis engines; and the discussion of our experience with a high-volume production service over several years.},
publisher = {Association for Computing Machinery, Inc.},
url = {http://approjects.co.za/?big=en-us/research/publication/path-based-failure-and-evolution-management/},
edition = {The 1st USENIX/ACM Symposium on Networked Systems Design and Implementation (NSDI '04)},
}