Knowledge-based checkpointing strategy for spot instances in cloud computing

Sumit Tomar; Ashish Kumar Mishra; Dharmendra K Yadav

doi:10.59796/jcst.V13N2.2023.1754

Authors

Sumit Tomar Computer Science and Engineering Department, Motilal Nehru National Institute of Technology Allahabad, Prayagraj, U. P. India, 211004
Ashish Kumar Mishra Computer Science and Engineering Department, Motilal Nehru National Institute of Technology Allahabad, Prayagraj, U. P. India, 211004
Dharmendra K Yadav Computer Science and Engineering Department, Motilal Nehru National Institute of Technology Allahabad, Prayagraj, U. P. India, 211004

DOI:

https://doi.org/10.59796/jcst.V13N2.2023.1754

Keywords:

checkpointing, cloud computing, fault tolerance, spot instances

Abstract

The Amazon EC2 offers spot-priced virtual machines (VMs) at a reduced price compared to on-demand and reserved VMs. However, Amazon EC2 can terminate these VMs anytime due to the spot price and demand fluctuation. Using spot VMs results in a longer execution time and disrupts service availability. Users can use fault-tolerant techniques such as checkpointing, migration, and job duplication to mitigate the unreliability of spot VMs. In this paper, a knowledge-based checkpointing strategy is proposed to minimize the overall checkpointing overhead during the execution of jobs. The proposed scheme uses real-time price history to decide when to take a checkpoint. Results show that the proposed approach can significantly reduce the turnaround time by 18% compared to Hourly Checkpointing Strategy and 9% compared to Rising-Edge Checkpointing Strategy. One can also achieve 54% to 78% reliability with a cost saving of 78% for the workload used with the described approach.

References

Agarwal, S., Mishra, A. K., & Yadav, D. K. (2017). Forecasting price of amazon spot instances using neural networks. International Journal of Applied Engineering Research, 12(20), 10276-10283.

Agmon Ben-Yehuda, O., Ben-Yehuda, M., Schuster, A., & Tsafrir, D. (2013). Deconstructing Amazon EC2 spot instance pricing. ACM Transactions on Economics and Computation (TEAC), 1(3), 1-20. https://doi.org/10.1145/2509413.2509416

Alourani, A., & Kshemkalyani, A. D. (2020, July). Provisioning spot instances without employing fault-tolerance mechanisms. In 2020 19th International Symposium on Parallel and Distributed Computing (ISPDC) (pp. 126-133). IEEE. https://doi.org/10.1109/ISPDC51135.2020.00026

Amazon Web Services, Inc. (n.d.a). Secure and resizable cloud compute – Amazon EC2. Retrieved June 28, 2022, from https://aws.amazon.com/ec2/

Amazon Web Services, Inc. (n.d.b). Amazon EC2 Spot – Save up-to 90% on On-Demand Prices. Retrieved June 28, 2022, from https://aws.amazon.com/ec2/spot/

Amazon Web Services. (n.d.c). High-Performance Block Storage Retrieved June 27, 2022, from https://aws.amazon.com/ebs/

Andrzejak, A., Kondo, D., & Yi, S. (2010, August). Decision model for cloud computing under SLA constraints. In 2010 IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (pp. 257-266). IEEE. https://doi.org/10.1109/MASCOTS.2010.34

Buyya, R., Yeo, C. S., Venugopal, S., Broberg, J., & Brandic, I. (2009). Cloud computing and emerging IT platforms: Vision, hype, and reality for delivering computing as the 5th utility. Future Generation computer systems, 25(6), 599-616. https://doi.org/10.1016/j.future.2008.12.001

Calheiros, R. N., Ranjan, R., Beloglazov, A., De Rose, C. A., & Buyya, R. (2011). CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Software: Practice and experience, 41(1), 23-50. https://doi.org/10.1002/spe.995

Cao, J., Simonin, M., Cooperman, G., & Morin, C. (2015). Checkpointing as a Service in Heterogeneous Cloud Environments. https://doi.org/10.1109/ccgrid.2015.160

Chen, C., Lee, B. S., & Tang, X. (2014, December). Improving hadoop monetary efficiency in the cloud using spot instances. In 2014 IEEE 6th International Conference on Cloud Computing Technology and Science (pp. 312-319). IEEE. https://doi.org/10.1109/CloudCom.2014.35

Chohan, N., Castillo, C., Spreitzer, M., Steinder, M., Tantawi, A. N., & Krintz, C. (2010). See spot run: using spot instances for mapreduce workflows. HotCloud, 10, 1-7. https://dl.acm.org/doi/10.5555/1863103.1863110

Cloud Infrastructure Solutions | IBM. (n.d.). Retrieved June 25, 2022, from https://www.ibm.com/in-en/cloud/infrastructure

Compute Engine: Virtual Machines (VMs) | Google Cloud. (n.d.). Google Cloud. Retrieved June 27, 2022, from https://cloud.google.com/compute/

Dawoud, W., Takouna, I., & Meinel, C. (2012, June). Increasing spot instances reliability using dynamic scalability. In 2012 IEEE Fifth International Conference on Cloud Computing (pp. 959-961). IEEE. http://dx.doi.org/10.1109/CLOUD.2012.58

Deldari, A., & Salehan, A. (2021). A survey on preemptible IaaS cloud instances: challenges, issues, opportunities, and advantages. Iran Journal of Computer Science, 4(3), 1-24. https://doi.org/10.1007/s42044-020-00071-1

Di, S., Robert, Y., Vivien, F., Kondo, D., Wang, C. L., & Cappello, F. (2013, November). Optimization of cloud task processing with checkpoint-restart mechanism. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (pp. 1-12). http://doi.acm.org/10.1145/2503210.2503217

Goiri, Í., Julia, F., Guitart, J., & Torres, J. (2010, April). Checkpoint-based fault-tolerant infrastructure for virtualized service providers. In 2010 IEEE network operations and management symposium-NOMS 2010 (pp. 455-462). IEEE. https://doi.org/10.1109/NOMS.2010.5488493

Hussain, Z., Znati, T., & Melhem, R. (2019, May). Optimal placement of in-memory checkpoints under heterogeneous failure likelihoods. In 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS) (pp. 900-910). IEEE. https://doi.org/10.1109/IPDPS.2019.00098

Jangjaimon, I., & Tzeng, N. F. (2015). Effective cost reduction for elastic clouds under spot instance pricing through adaptive checkpointing. IEEE Transactions on Computers, 64(2), 396-409. https://doi.org/10.1109/TC.2013.225

Jangjaimon, I., & Tzeng, N. F. (2013, May). Adaptive incremental checkpointing via delta compression for networked multicore systems. In 2013 IEEE 27th International Symposium on Parallel and Distributed Processing (pp. 7-18). IEEE. http://dx.doi.org/10.1109/IPDPS.2013.33

Javadi, B., Thulasiram, R. K., & Buyya, R. (2013). Characterizing spot price dynamics in public cloud environments. Future Generation Computer Systems, 29(4), 988-999. http://dx.doi.org/10.1016/j.future.2012.06.012

Javadi, B., Thulasiramy, R. K., & Buyya, R. (2011, December). Statistical modeling of spot instance prices in public cloud environments. In 2011 fourth IEEE international conference on utility and cloud computing (pp. 219-228). IEEE. https://doi.org/10.1109/UCC.2011.37

Jung, D., Chin, S., Chung, K., Yu, H., & Gil, J. (2011). An efficient checkpointing scheme using price history of spot instances in cloud computing environment. In Network and Parallel Computing: 8th IFIP International Conference, NPC 2011, Changsha, China, October 21-23, 2011. Proceedings 8 (pp. 185-200). Springer Berlin Heidelberg. http://dx.doi.org/10.1007/978-3-642-24403-2_16

Liu, W., Wang, P., Meng, Y., Zhao, C., & Zhang, Z. (2020). Cloud spot instance price prediction using kNN regression. Human-centric Computing and Information Sciences, 10(1), 1-14. https://doi.org/10.1186/s13673-020-00239-5

Mattess, M., Vecchiola, C., & Buyya, R. (2010, September). Managing peak loads by leasing cloud infrastructure services from a spot market. In 2010 IEEE 12th International Conference on High Performance Computing and Communications (HPCC) (pp. 180-188). IEEE. https://doi.org/10.1109/HPCC.2010.77

Mishra, A. K., Kesarwani, A., & Yadav, D. K. (2019a, March). Short term price prediction for preemptible vm instances in cloud computing. In 2019 IEEE 5th International Conference for Convergence in Technology (I2CT) (pp. 1-9). IEEE. https://doi.org/10.1109/I2CT45611.2019.9033677

Mishra, A. K., Umrao, B. K., & Yadav, D. K. (2018). A survey on optimal utilization of preemptible VM instances in cloud computing. The Journal of Supercomputing, 74, 5980-6032. https://doi.org/10.1007/s11227-018-2509-0

Mishra, A. K., Yadav, D. K., Kumar, Y., & Jain, N. (2019b). Improving reliability and reducing cost of task execution on preemptible VM instances using machine learning approach. The Journal of Supercomputing, 75, 2149-2180. https://doi.org/10.1007/s11227-018-2717-7

Popovici, F. I., & Wilkes, J. (2005, November). Profitable services in an uncertain world. In SC'05: Proceedings of the 2005 ACM/IEEE conference on Supercomputing (pp. 36-36). IEEE. https://doi.org/10.1109/SC.2005.58

Ramesh, A., Pradhan, V., & Lamkuche, H. (2021, July). Understanding and analysing resource utilization, costing strategies and pricing models in cloud computing. In Journal of Physics: Conference Series, 1964(4), Article 042049. https://doi.org/10.1088/1742- 6596/1964/4/042049

Sharma, P., Irwin, D. E., & Shenoy, P. J. (2016). How Not to Bid the Cloud. In A. Clements & T. Condie (Eds.), 8th {USENIX} Workshop on Hot Topics in Cloud Computing, HotCloud 2016, Denver, CO, USA, June 20-21, 2016. {USENIX} Association. https://www.usenix.org/conference/hotcloud16/workshop-program/presentation/sharma

Song, Y., Zafer, M., & Lee, K. W. (2012, March). Optimal bidding in spot instance market. In 2012 Proceedings IEEE Infocom (pp. 190-198). IEEE. https://doi.org/10.1109/INFCOM.2012.6195567

Toosi, A. N., Vanmechelen, K., Khodadadi, F., & Buyya, R. (2016). An auction mechanism for cloud spot markets. ACM Transactions on Autonomous and Adaptive Systems (TAAS), 11(1), 1-33. https://doi.org/10.1145/2843945

Voorsluys, W., & Buyya, R. (2012, March). Reliable provisioning of spot instances for compute-intensive applications. In 2012 IEEE 26th international conference on advanced information networking and applications (pp. 542-549). IEEE. https://doi.org/10.1109/AINA.2012.106

Wang, Y. M., Huang, Y., Vo, K. P., Chung, P. Y., & Kintala, C. (1995, June). Checkpointing and its applications. In Twenty-fifth International Symposium on fault-tolerant Computing. Digest of papers (pp. 22-31). IEEE. https://doi.org/10.1109/FTCS.1995.466999

Wu, L., Garg, S. K., & Buyya, R. (2012). SLA-based admission control for a Software-as-a-Service provider in Cloud computing environments. Journal of Computer and System Sciences, 78(5), 1280-1299. https://doi.org/10.1016/j.jcss.2011.12.014

Yang, S., Khuller, S., Choudhary, S., Mitra, S., & Mahadik, K. (2021, December). Scheduling ML training on unreliable spot instances. In Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion (Article 29, pp. 1-8). https://doi.org/10.1145/3492323.3495594

Yi, S., Andrzejak, A., & Kondo, D. (2012). Monetary cost-aware checkpointing and migration on amazon cloud spot instances. IEEE Transactions on Services Computing, 5(4), 512-524. https://doi.org/10.1109/TSC.2011.44

Yi, S., Kondo, D., & Andrzejak, A. (2010, July). Reducing costs of spot instances via checkpointing in the amazon elastic compute cloud. In 2010 IEEE 3rd International Conference on Cloud Computing (pp. 236-243). IEEE. https://doi.org/10.1109/CLOUD.2010.35