An efficient logging algorithm for incremental replay of message-passing applications

@article{Zambonelli1999AnEL,
  title={An efficient logging algorithm for incremental replay of message-passing applications},
  author={F. Zambonelli},
  journal={Proceedings 13th International Parallel Processing Symposium and 10th Symposium on Parallel and Distributed Processing. IPPS/SPDP 1999},
  year={1999},
  pages={392-398}
}
  • F. Zambonelli
  • Published 1999
  • Computer Science
  • Proceedings 13th International Parallel Processing Symposium and 10th Symposium on Parallel and Distributed Processing. IPPS/SPDP 1999
  • To support incremental replay of message-passing applications, processes must periodically checkpoint and the content of some messages must be logged, to break dependencies of the current state of the execution on past events. The paper presents a new adaptive logging algorithm that dynamically decides whether to log a message based on dependencies the incoming message introduces on past events of the execution. The paper discusses the implementation issues of the algorithm and evaluates its… CONTINUE READING
    24 Citations

    Figures, Tables, and Topics from this paper.

    Deadlock-Free Incremental Replay of Message-Passing Programs
    • 5
    Constant Execution Time Recording for Replay of Sporadic Real-Time Systems
    Shortcut Replay: A Replay Technique for Debugging Long-Running Parallel Programs
    • 9
    Fault Reproduction for Multithreaded Applications
    Robust non-intrusive record-replay with processor extraction
    • 7
    • PDF
    Preparing for replay
    • 3
    • PDF
    Debugging Large-Scale, Long-Running Parallel Programs
    • 2
    • PDF

    References

    SHOWING 1-10 OF 21 REFERENCES
    Adaptive message logging for incremental program replay
    • R. Netzer, J. Xu
    • Computer Science
    • IEEE Parallel & Distributed Technology: Systems & Applications
    • 1993
    • 40
    • Highly Influential
    Critical-path-based message logging for incremental replay of message-passing programs
    • 21
    Replaying distributed programs without message logging
    • R. Netzer, Y. Xu
    • Computer Science
    • Proceedings. The Sixth IEEE International Symposium on High Performance Distributed Computing (Cat. No.97TB100183)
    • 1997
    • 20
    On the effectiveness of distributed checkpoint algorithms for domino-free recovery
    • F. Zambonelli
    • Computer Science
    • Proceedings. The Seventh International Symposium on High Performance Distributed Computing (Cat. No.98TB100244)
    • 1998
    • 19
    • PDF
    Preventing useless checkpoints in distributed computations
    • 78
    • PDF
    Optimal tracing and replay for debugging message-passing parallel programs
    • 72
    • PDF
    On-the-fly replay: a practical paradigm and its implementation for distributed debugging
    • 18
    • PDF
    Necessary and Sufficient Conditions for Consistent Global Snapshots
    • R. Netzer, J. Xu
    • Computer Science
    • IEEE Trans. Parallel Distributed Syst.
    • 1995
    • 278
    Debugging Parallel Programs with Instant Replay
    • 806
    • PDF
    Consistent global states of distributed systems: fundamental concepts and mechanisms
    • 317
    • PDF