6th IEEE Workshop on Future Trends of Distributed Computing Systems (FTDCS '97)
Impact of rollback recovery to program locality of reference and page replacement policies
Tunis, TUNISIA
October 29-October 31
ISBN: 0-8186-8153-5
Y. Lin, Dept. of Comput. Sci. & Eng., Arizona State Univ., Tempe, AZ, USA
S. Bhattacharya, Dept. of Comput. Sci. & Eng., Arizona State Univ., Tempe, AZ, USA
We study the impact of checkpointing-based fault tolerance on the program locality of reference and memory page (or cache block) replacement policies. We demonstrate that the current research in page/block replacement algorithms may not operate well with fault-tolerant programs. We include the identification of this critical research topic, and the development of an analytical model for fault propagation in a checkpointed program. This model is corroborated using simulation, and we propose a new page/block replacement algorithm that takes into account fault-triggered rollback(s). Performance is shown by an example study.
Index Terms:
system recovery; rollback recovery; locality of reference; page replacement policies; checkpointing; fault tolerance; cache block replacement policies; research; fault propagation; simulation; fault-triggered rollback; performance; memory management
Citation:
Y. Lin, S. Bhattacharya, "Impact of rollback recovery to program locality of reference and page replacement policies," ftdcs, pp.104, 6th IEEE Workshop on Future Trends of Distributed Computing Systems (FTDCS '97), 1997