@article{FelgentreffPerscheidHirschfeld2017,
  author    = {Felgentreff, Tim and Perscheid, Michael and Hirschfeld, Robert},
  title     = {Implementing record and refinement for debugging timing-dependent communication},
  series = {Science of computer programming},
  volume    = {134},
  journal   = {Science of computer programming},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0167-6423},
  doi       = {10.1016/j.scico.2015.11.006},
  pages     = {4 -- 18},
  year      = {2017},
  abstract  = {Distributed applications are hard to debug because timing-dependent network communication is a source of non-deterministic behavior. Current approaches to debug non deterministic failures include post-mortem debugging as well as record and replay. However, the first impairs system performance to gather data, whereas the latter requires developers to understand the timing-dependent communication at a lower level of abstraction than they develop at. Furthermore, both approaches require intrusive core library modifications to gather data from live systems. In this paper, we present the Peek-At-Talk debugger for investigating non-deterministic failures with low overhead in a systematic, top-down method, with a particular focus on tool-building issues in the following areas: First, we show how our debugging framework Path Tools guides developers from failures to their root causes and gathers run-time data with low overhead. Second, we present Peek-At-Talk, an extension to our Path Tools framework to record non-deterministic communication and refine behavioral data that connects source code with network events. Finally, we scope changes to the core library to record network communication without impacting other network applications.},
  language  = {en}
}