BorderPatrol: isolating events for black-box tracing

作者: Eric Koskinen , John Jannotti

DOI: 10.1145/1352592.1352613

关键词:

摘要: Causal request traces are valuable to developers of large concurrent and distributed applications, yet difficult obtain. Traces show how a is processed, can be analyzed by tools detect performance or correctness errors anomalous behavior.We present BorderPatrol, which obtains precise through suystems built from litany unmodified modules. Traced components include Apache, thttpd, PostgreSQL, TurboGears, BIND notably Zeus, closed-source event-driven web server. BorderPatrol using active observation carefully modifies the event stream observed modules, simplifying observation. Protocol processors leverage knowledge about standard protocols, avoiding application-specific instrumentation.BorderPatrol for black-box systems that cannot traced any other technique. We confirm accuracy BorderPatrol's comparing manual instrumentation, compare developer effort required each kind trace. imposes limited overhead on real (approximately 10-15%) it may enabled disabled in at run-time, making viable option deployment production environments.

参考文章(13)
Peter M. Chen, Samuel T. King, Analyzing intrusions using operating system level information flow University of Michigan. ,(2006)
Richard Mortier, Rebecca Isaacs, Austin Donnelly, Paul Barham, Using magpie for request extraction and workload modelling operating systems design and implementation. pp. 18- 18 ,(2004)
Scott Shenker, George Porter, Ion Stoica, Randy H. Katz, Rodrigo Fonseca, X-trace: a pervasive network tracing framework networked systems design and implementation. pp. 20- 20 ,(2007)
David Mazières, A Toolkit for User-Level File Systems usenix annual technical conference. pp. 261- 274 ,(2001)
Anupam Chanda, Alan L. Cox, Khaled Elmeleegy, Willy Zwaenepoel, Causeway: operating system support for controlling and analyzing the execution of distributed programs hot topics in operating systems. pp. 18- 18 ,(2005)
Andrew Ayers, Richard Schooler, Chris Metcalf, Anant Agarwal, Junghwan Rhee, Emmett Witchel, TraceBack: first fault diagnosis by reconstruction of distributed control flow programming language design and implementation. ,vol. 40, pp. 201- 212 ,(2005) , 10.1145/1064978.1065035
Anupam Chanda, Alan L. Cox, Willy Zwaenepoel, Whodunit: transactional profiling for multi-tier applications european conference on computer systems. ,vol. 41, pp. 17- 30 ,(2007) , 10.1145/1272996.1273001
Patrick Reynolds, Janet L. Wiener, Jeffrey C. Mogul, Marcos K. Aguilera, Amin Vahdat, WAP5 Proceedings of the 15th international conference on World Wide Web - WWW '06. pp. 347- 356 ,(2006) , 10.1145/1135777.1135830
Amin Vahdat, Jeffrey C. Mogul, Charles Killian, Mehul A. Shah, Janet L. Wiener, Patrick Reynolds, Pip: detecting the unexpected in distributed systems networked systems design and implementation. pp. 9- 9 ,(2006)
Leland L. Smith, Stardust ACM SIGMETRICS Performance Evaluation Review. ,vol. 34, pp. 3- 14 ,(2006) , 10.1145/1140103.1140280