Abstract
With the increase of system scale, the inherent reliability of supercomputers becomes lower and lower. The cost of fault handling and task recovery increases so rapidly that the reliability issue will soon harm the usability of supercomputers. This issue is referred to as the “reliability wall”, which is regarded as a critical problem for current and future supercomputers. To address this problem, we propose an autonomous fault-tolerant system, named Iaso, in MilkyWay-2 system. Iaso introduces the concept of autonomous management in supercomputers. By autonomous management, the computer itself, rather than manpower, takes charge of the fault management work. Iaso automatically manage the whole lifecycle of faults, including fault detection, fault diagnosis, fault isolation, and task recovery. Iaso endows the autonomous features with MilkyWay-2 system, such as self-awareness, self-diagnosis, self-healing, and self-protection. With the help of Iaso, the cost of fault handling in supercomputers reduces from several hours to a few seconds. Iaso greatly improves the usability and reliability of MilkyWay-2 system.
Similar content being viewed by others
References
Yang X, Wang Z, Xue J, Zhou Y. The reliability wall for exascale supercomputing. IEEE Transactions on Computers, 2012, 61(6): 767–779
Li Y, Lan Z. Proactive fault manager for high performance computing. In: Proceedings of the 35th International Conference on Dependable Systems and Networks (Fast Abstract). 2005
Shapiro MW. Self-healing in modern operating systems. Queue, 2004, 2(9): 66–75
Oliner A, Stearley J. What supercomputers say: A study of five system logs. In: Proceedings of the 37th Annual IEEE/IFIP International Conference on Dependable Systems and Networks. 2007, 575–584
Sun X H, Lan Z, Li Y, Jin H, Zheng Z. Towards a faultaware computing environment. High Availability and Performance Computing Workshop, 2008
Lan Z, Li Y, Gujrati P, Zheng Z, Thakur R, White J. A fault diagnosis and prognosis service for teragrid clusters. In: Proceedings of Tera-Grid, 2007
Wang X, Luo J, Liu Y, Li S, Dong D. Component-based localization in sparse wireless networks. IEEE/ACM Transactions on Networking (ToN), 2011, 19(2): 540–548
Takemiya H, Tanaka Y, Sekiguchi S, Ogata S, Kalia R K, Nakano A, Vashishta P. Sustainable adaptive grid supercomputing: multiscale simulation of semiconductor processing across the pacific. In: Proceedings of the ACM/IEEE SuperComputing. 2006, 23
Wang X, Liu Y, Yang Z, Lu K, Luo J. OFA: an optimistic approach to conquer flip ambiguity in network localization. Computer Networks, 2013, 57(6): 1529–1544
Santosd T, Santosd L, Farinon F, Homma R, Andraded R, Khairalla I, Lemos F. Integrating heterogenous applications in control centers based on smart grid concepts. In: Proceedings of the 2013 IEEE PES Conference on Innovative Smart Grid Technologies Latin America (ISGT LA). 2013, 1–6
Wang X, Yang Z, Luo J, Shen C. Beyond rigidity: obtain localisability with noisy ranging measurement. International Journal of Ad Hoc and Ubiquitous Computing, 2011, 8(1): 114–124
Valverde L, Rosa F, Bordons C. Design, planning and management of a hydrogen-based microgrid. IEEE Transactions on Industrial Informatics, 2013, 9(3): 1398–1404
Zhang X, Zhou F, Zhu X, Sun H, Perrig A, Vasilakos A V, Guan H. DFL: Secure and practical fault localization for datacenter networks. IEEE/ACM Transactions on Networking, 2013
Huebscher M C, McCann J A. A survey of autonomic computing—degrees, models, and applications. ACM Computing Surveys (CSUR), 2008, 40(3): 7:1–7:28
Author information
Authors and Affiliations
Corresponding author
Additional information
Kai Lu, PhD, professor, Deputy Dean of College of Computer Science, National University of Defense Technology, China. His research interests include parallel and distributed system software, operating system, parallel tool suites and fault-tolerant computing technology.
Xiaoping Wang, PhD, assistant professor, National University of Defense Technology, China. His research interests include parallel computing, system software, and distributed computing.
Gen Li, PhD, assistant professor, National University of Defense Technology, China. His research interests include operating system and system security.
Ruibo Wang, PhD, assistant professor, National University of Defense Technology, China. His research interests include operating system and transactional memory.
Wanqing Chi, associate professor, National University of Defense Technology, China. His research interests include operating system, system software, and high performance computing.
Yongpeng Liu, PhD, assistant professor, National University of Defense Technology, China. His research interests include power management, fault tolerance, and high performance computing.
Hongwei Tang, assistant professor, National University of Defense Technology, China. His research interests include operating system, system firmware, high performance computing, distributed computing and computer architecture.
Hua Feng, associate professor, National University of Defense Technology, China. His research interests include operating system, system software, and computer architecture.
Yinghui Gao, PhD, associated professor, National University of Defense Technology, China. Her research interests include artificial intelligent, machine learning and pattern recognition.
Rights and permissions
About this article
Cite this article
Lu, K., Wang, X., Li, G. et al. Iaso: an autonomous fault-tolerant management system for supercomputers. Front. Comput. Sci. 8, 378–390 (2014). https://doi.org/10.1007/s11704-014-3503-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11704-014-3503-1