DOI QR코드

DOI QR Code

Analysis of Checkpointing Model with Instantaneous Error Detection

즉각적 오류 감지가 가능한 경우의 체크포인팅 모형 분석

  • Lee, Yutae (Department of Information and Communications Engineering, Dong-eui University)
  • Received : 2021.11.17
  • Accepted : 2021.11.23
  • Published : 2022.01.31

Abstract

Reactive failure management techniques are required to mitigate the impact of errors in high performance computing. Checkpoint is the standard recovery technique for coping with errors. An application employing checkpoints periodically saves its state, so that when an error occurs while some task is executing, the application is rolled back to its last checkpointed task and resumes execution from that task onward. In this paper, assuming the time-to-errors are independent each other and generally distributed, we analyze the checkpointing model with instantaneous error detection. The conventional assumption that two or more errors do not take place between two consecutive checkpoints is removed. Given the checkpointing time, down-time, and recovery time, we derive the reliability of the checkpointing model. When the time-to-error follows an exponential distribution, we obtain the optimal checkpointing interval to achieve the maximum reliability.

고성능 컴퓨팅 분야에서 오류의 영향을 완화하기 위해 사후 장애 관리 기법이 필요하다. 일반적인 오류 복구 기법은 체크포인트 기법이다. 이 기법은 체크포인트를 설정해서 주기적으로 응용 프로그램의 상태를 저장했다가, 오류가 발생했을 때 오류 발생 이전 상태로 시스템을 복구하는 것이다. 본 논문에서는 오류 발생 시간이 독립이고 동일한 일반적인 분포를 따른다는 가정에서 즉각적으로 오류를 감지하는 경우의 체크포인팅 모형을 분석한다. 두 체크포인트 사이에 많아야 하나의 오류만 발생한다는 가정을 제거한다. 체크포인트 발생 시간, 고장 시간, 복구 시간 등이 주어질 때, 시스템의 신뢰도를 유도한다. 또한, 오류 발생 시간이 지수 분포를 따르는 경우에 최적의 체크 포인팅 시간 간격을 구한다.

Keywords

References

  1. A. Benoit, A. Cavelan, Y. Robert, and H. Sun, "Multi-level checkpointing and silent error detection for linear workflows," Journal of Computational Science, vol. 28, pp. 398-415, Arp. 2017. https://doi.org/10.1016/j.jocs.2017.03.024
  2. Y. Du, L. Marchal, G. Pallez, and Y. Robert, "Optimal checking strategies for iterative applications," IEEE Transactions on Parallel and Distributed Systems, vol. 33, no. 3, pp. 507-522, Mar. 2022. https://doi.org/10.1109/TPDS.2021.3099440
  3. A. Benoit, A. Cavelan, F. Cappello, P. Raghavan, Y. Robert, and H. Sun, "Coping with silent and fail-stop errors at scale by combining replication and checkpointing," Journal of Parallel and Distributed Computing, vol. 122, no. 1, pp. 209-225, Aug. 2018. https://doi.org/10.1016/j.jpdc.2018.08.002
  4. Y. Lee, "Reliability analysis of checkpointing model with multiple verification mechanism," Bulletin of the Korean Mathematical Society, vol. 56, no. 6, pp. 1435-1445, Nov. 2019. https://doi.org/10.4134/bkms.b181068
  5. J. W. Young, "A first order approximation to the optimal checkpoint interval," Communications of the ACM, vol. 17, no. 9, pp. 530-531, Sept. 1974. https://doi.org/10.1145/361147.361115
  6. J. T. Daly, "A higher order estimate of the optimum checkpoint interval for restart dumps," Future Generation Computer Systems, vol. 22, no. 3, pp. 303-312, 2004. https://doi.org/10.1016/j.future.2004.11.016
  7. M. S. Bouguerra, D. Trystram, and F. Wagner, "Complexity analysis of checkpoint scheduling with variable costs," IEEE Transactions on Computers, vol. 62, no. 6, pp. 1269-1275, Mar. 2013. https://doi.org/10.1109/TC.2012.57