Abstract
Increasing the size and complexity of modern HPC systems also increases the probability of various types of failures. Failures may disrupt application execution and waste valuable system resources due to failed executions. In this work, we explore the effect of node failures on the completion times of MPI parallel jobs. We introduce a simulation environment that generates synthetic traces of node failures, assuming that the times between failures for each node are independently distributed, following the same distribution but with different parameters. To highlight the importance of failure-awareness for resource allocation, we compare two failure-oblivious resource allocation approaches with one that considers node failure probabilities before assigning a partition to a job: a heuristic that randomly selects the partition for a job, and Slurm’s linear resource allocation policy. We present results for a case study that assumes a 4D-torus topology and a Weibull distribution for each node’s time between failures, and considers several different traces of node failures, capturing different failure patterns. For the synthetic traces explored, the benefit is more prominent for longer jobs, up to 82% depending on the trace, when compared with Slurm and a failure-oblivious heuristic. For shorter jobs, benefits are noticeable for systems with more frequent failures.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cappello, F., Al, G., Gropp, W., Kale, S., Kramer, B., Snir, M.: Toward exascale resilience: 2014 update. Supercomput. Front. Innov.: Int. J. 1(1), 5–28 (2014)
Casanova, H., Giersch, A., Legrand, A., Quinson, M., Suter, F.: Versatile, scalable, and accurate simulation of distributed applications and platforms. J. Parallel Distrib. Comput. 74(10), 2899–2917 (2014)
Dogan, A., Ozguner, F.: Matching and scheduling algorithms for minimizing execution time and failure probability of applications in heterogeneous computing. IEEE Trans. Parallel Distrib. Syst. 13(3), 308–323 (2002)
El-Sayed, N., Zhu, H., Schroeder, B.: Learning from failure across multiple clusters: a trace-driven approach to understanding, predicting, and mitigating job terminations. In: 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS), pp. 1333–1344 (2017)
Elnozahy, E.N.: System resilience at extreme scale. Technical report. Defense Advanced Research Project Agency (2008)
Engelmann, C., Lauer, F.: Facilitating co-design for extreme-scale systems through lightweight simulation. In: 2010 IEEE International Conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS), pp. 1–8 (2010)
Engelmann, C., Naughton, T.: Toward a performance/resilience tool for hardware/software co-design of high-performance computing systems. In: 2013 42nd International Conference on Parallel Processing, pp. 960–969 (2013)
ETP4HPC-SRA 4: Strategic Research Agenda for High Performance Computing in Europe. https://www.etp4hpc.eu/pujades/files/ETP4HPC_SRA4_2020_web.pdf
Fu, S.: Failure-aware resource management for high-availability computing clusters with distributed virtual machines. J. Parallel Distrib. Comput. 70(4), 384–393 (2010)
Gottumukkala, N.R., Leangsuksun, C.B., Taerat, N., Nassar, R., Scott, S.L.: Reliability-aware resource allocation in HPC systems. In: 2007 IEEE International Conference on Cluster Computing, pp. 312–321 (2007)
Gottumukkala, N.R., Nassar, R., Paun, M., Leangsuksun, C.B., Scott, S.L.: Reliability of a system of k nodes for high performance computing applications. IEEE Trans. Reliab. 59(1), 162–169 (2010)
Hakem, M., Butelle, F.: Reliability and scheduling on systems subject to failures. In: 2007 International Conference on Parallel Processing (ICPP 2007), pp. 38–38 (2007)
Heien, E., LaPine, D., Kondo, D., Kramer, B., Gainaru, A., Cappello, F.: Modeling and tolerating heterogeneous failures in large parallel systems. In: SC 2011: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1–11 (2011)
Choo, H., Yoo, S.-M., Youn, H.Y.: Processor scheduling and allocation for 3D torus multicomputer systems. IEEE Trans. Parallel Distrib. Syst. 11(5), 475–484 (2000)
Jauk, D., Yang, D., Schulz, M.: Predicting faults in high performance computing systems: an in-depth survey of the state-of-the-practice. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2019, pp. 30:1–30:13. ACM, New York (2019)
Levy, S., Topp, B., Ferreira, K.B., Arnold, D., Hoefler, T., Widener, P.: Using simulation to evaluate the performance of resilience strategies at scale. In: Jarvis, S.A., Wright, S.A., Hammond, S.D. (eds.) PMBS 2013. LNCS, vol. 8551, pp. 91–114. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10214-6_5
Machida, F., Kawato, M., Maeno, Y.: Redundant virtual machine placement for fault-tolerant consolidated server clusters. In: 2010 IEEE Network Operations and Management Symposium - NOMS 2010, pp. 32–39 (2010)
Martino, C.D., Kramer, W., Kalbarczyk, Z., Iyer, R.: Measuring and understanding extreme-scale application resilience: a field study of 5,000,000 HPC application runs. In: 2015 45th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, pp. 25–36 (2015)
Oliner, A.J., Sahoo, R.K., Moreira, J.E., Gupta, M., Sivasubramaniam, A.: Fault-aware job scheduling for BlueGene/L systems. In: Proceedings of the 18th International Parallel and Distributed Processing Symposium, p. 64 (2004)
Schroeder, B., Gibson, G.: Understanding failures in Petascale computers. J. Phys.: Conf. Ser. 78 (2007)
Schroeder, B., Gibson, G.A.: A large-scale study of failures in high-performance computing systems. IEEE Trans. Depend. Secure Comput. 7(4), 337–350 (2010)
Slurm Resource Selection Plugin. https://slurm.schedmd.com/selectplugins.html
Snir, M., et al.: Addressing failures in exascale computing. In: ICiS Workshop ANL/MCS-TM-332, April 2013
Tikotekar, A., Vallee, G., Naughton, T., Scott, S.L., Leangsuksun, C.: Evaluation of fault-tolerant policies using simulation. In: 2007 IEEE International Conference on Cluster Computing, pp. 303–311 (2007)
Tiwari, D., Gupta, S., Vazhkudai, S.S.: Lazy checkpointing: exploiting temporal locality in failures to mitigate checkpointing overheads on extreme-scale systems. In: 2014 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, pp. 25–36 (2014)
Vardas, I., Ploumidis, M., Marazakis, M.: Towards communication profile, topology and node failure aware process placement. In: 2020 IEEE 32nd International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), pp. 241–248 (2020)
Li, Y., Lan, Z.: Exploit failure prediction for adaptive fault-tolerance in cluster computing. In: Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGRID 2006), vol. 1, pp. 8 p. 538 (2006)
Yigitbasi, N., Gallet, M., Kondo, D., Iosup, A., Epema, D.: Analysis and modeling of time-correlated failures in large-scale distributed systems. In: 2010 11th IEEE/ACM International Conference on Grid Computing, pp. 65–72 (2010)
Yoo, A.B., Jette, M.A., Grondona, M.: SLURM: simple Linux utility for resource management. In: Feitelson, D., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2003. LNCS, vol. 2862, pp. 44–60. Springer, Heidelberg (2003). https://doi.org/10.1007/10968987_3
Zhang, Y., Squillante, M.S., Sivasubramaniam, A., Sahoo, R.K.: Performance implications of failures in large-scale cluster scheduling. In: Feitelson, D.G., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2004. LNCS, vol. 3277, pp. 233–252. Springer, Heidelberg (2005). https://doi.org/10.1007/11407522_13
Acknowledgments
This research has received funding from the European Union’s Horizon 2020/EuroHPC research and innovation programme under grant agreements 955606 (DEEP-SEA) and 754337 (EuroEXA). National contributions from the involved state members match the EuroHPC funding.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Vardas, I., Ploumidis, M., Marazakis, M. (2022). Exploring the Impact of Node Failures on the Resource Allocation for Parallel Jobs. In: Chaves, R., et al. Euro-Par 2021: Parallel Processing Workshops. Euro-Par 2021. Lecture Notes in Computer Science, vol 13098. Springer, Cham. https://doi.org/10.1007/978-3-031-06156-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-06156-1_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06155-4
Online ISBN: 978-3-031-06156-1
eBook Packages: Computer ScienceComputer Science (R0)