Peeking into the Past
Autor: | Dirk Vogt, Andrew S. Tanenbaum, Armando Miraglia, Herbert Bos, Cristiano Giuffrida |
---|---|
Přispěvatelé: | Computer Systems, Systems and Network Security, Network Institute |
Jazyk: | angličtina |
Rok vydání: | 2016 |
Předmět: |
010302 applied physics
Computer science media_common.quotation_subject 020206 networking & telecommunications 02 engineering and technology computer.software_genre 01 natural sciences Kernel (linear algebra) Software bug Debugging Server 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Operating system Overhead (computing) Analysis tools computer media_common |
Zdroj: | Miraglia, A, Vogt, D, Bos, H, Tanenbaum, A & Giuffrida, C 2016, Peeking into the Past : Efficient Checkpoint-Assisted Time-Traveling Debugging . in Proceedings-2016 IEEE 27th International Symposium on Software Reliability Engineering, ISSRE 2016 ., 7774543, ACM, IEEE Computer Society, pp. 455-466, 27th IEEE International Symposium on Software Reliability Engineering, ISSRE 2016, Ottawa, United States, 23/10/16 . https://doi.org/10.1109/ISSRE.2016.9 2016 IEEE 27th International Symposium on Software Reliability Engineering (ISSRE) Proceedings-2016 IEEE 27th International Symposium on Software Reliability Engineering, ISSRE 2016, 455-466 STARTPAGE=455;ENDPAGE=466;TITLE=Proceedings-2016 IEEE 27th International Symposium on Software Reliability Engineering, ISSRE 2016 ISSRE |
Popis: | Debugging long-lived latent software bugs that manifest themselves only long after their introduction in the system is hard. Even state-of-the-artrecord/replay debugging techniques are of limited use to identify the rootcause of long-lived latent bugs in general and event-driven bugs in particular. We propose DeLorean, a new end-to-end solution for time-travelling debugging based on fast memory checkpointing. Our design trades off replay guarantees with efficient support for history-aware debug queries (or time-travelling introspection) and provides novel analysis tools to diagnose event-driven latent software bugs. DeLorean imposes low run-time performance and memory overhead while preserving in memory as much history information as possible by deduplicating and/or compressing the collected data. We evaluate DeLorean byextensive experimentation, exploring the performance-memory tradeoffs in different configurations and comparing our results against state-of-the-art solutions. We show that DeLorean can efficiently support high-frequency checkpoints and store millions of them in memory. |
Databáze: | OpenAIRE |
Externí odkaz: |