Abstract
A centralized scheduler can become a bottleneck for placing the tasks of a many-task application on heterogeneous cloud resources. We have previously demonstrated that a decentralized vector scheduling approach based on performance measurements can be used successfully for this task placement scenario. We then extended this approach to task placement based on latency measurements. Each node collects the performance measurements from its neighbors on an overlay graph, measures the communication latency, and then makes local decisions on where to move tasks. Our recent experiments in CloudLab with nodes allocated on multiple cloud sites demonstrate that using latency in our vector scheduling approach results in better performance and resource utilization. While our algorithm for configuring the overlay graph based on latency measurements was beneficial with simulated communication delays, it was not beneficial in the multi-cloud environment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abramson, D., Giddy, J., Kotler, L.: High performance parametric modeling with Nimrod/G: killer application for the global grid? In: Proceedings of 14th International Parallel and Distributed Processing Symposium (IPDPS 2000), pp. 520–528 (2000). https://doi.org/10.1109/IPDPS.2000.846030
Barsness, E.L., Darrington, D.L., Lucas, R.L., Santosuosso, J.M.: Distributed job scheduling in a multi-nodal environment. US Patent 8,645,745 (2014)
Baumgartner, G., et al.: Synthesis of high-performance parallel programs for a class of ab initio quantum chemistry models. Proc. IEEE 93, 276–292 (2005)
Buaklee, D., Tracy, G., Vernon, M., Wright, S.: Near-optimal adaptive control of a large grid application. In: Proceedings of the 16th International Conference on Supercomputing, pp. 315–326 (2002)
Chakravarti, A.J., Baumgartner, G., Lauria, M.: The Organic Grid: self-organizing computation on a peer-to-peer network. IEEE Trans. Syst. Man Cybern.-Part A: Syst. Hum. 35(3), 373–384 (2005)
Chakravarti, A.J., Baumgartner, G., Lauria, M.: Self-organizing scheduling on the Organic Grid. Int. J. High Perform. Comput. Appl. 20(1), 115–130 (2006)
Chen, J., et al.: Beeflow: a workflow management system for in situ processing across HPC and cloud systems. In: 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS), pp. 1029–1038 (2018). https://doi.org/10.1109/ICDCS.2018.00103
Chien, A., Calder, B., Elbert, S., Bhatia, K.: Entropia: architecture and performance of an enterprise desktop grid system. J. Parallel Distrib. Comput. 63(5), 597–610 (2003)
Dean, J., Ghemawat, S.: Mapreduce: simplified data processing on large clusters. Commun. ACM 51(1), 107–113 (2008)
Duplyakin, D., et al.: The design and operation of CloudLab. In: Proceedings of the USENIX Annual Technical Conference (ATC), pp. 1–14 (2019). https://www.flux.utah.edu/paper/duplyakin-atc19
Evangelinos, C., Hill, C.: Cloud computing for parallel scientific HPC applications: feasibility of running coupled atmosphere-ocean climate models on Amazon EC2. Ratio 2(2.40), 2–34 (2008)
Gutierrez-Estevez, D.M., Luo, M.: Multi-resource schedulable unit for adaptive application-driven unified resource management in data centers. In: 2015 International Telecommunication Networks and Applications Conference (ITNAC), pp. 261–268. IEEE (2015)
Luo, M., Li, L., Chou, W.: ADARM: an application-driven adaptive resource management framework for data centers. In: 2017 IEEE International Conference on AI & Mobile Services, pp. 76–84 (2017)
Maheswaran, M., Ali, S., Siegel, H.J., Hensgen, D., Freund, R.F.: Dynamic mapping of a class of independent tasks onto heterogeneous computing systems. J. Parallel Distrib. Comput. 59(2), 107–131 (1999)
Mithila, S.P.: Scheduling Many-Task Computing Applications for a Hybrid Cloud. LSU doctoral dissertation. 5928, Louisiana State University and Agricultural and Mechanical College (2022)
Mithila, S.P., Baumgartner, G.: Latency-based vector scheduling of many-task applications for a hybrid cloud. In: 2022 IEEE 15th International Conference on Cloud Computing (CLOUD), pp. 257–262 (2022). https://doi.org/10.1109/CLOUD55607.2022.00047
Mohammadzadeh, A., Masdari, M., Gharehchopogh, F.S.: Energy and cost-aware workflow scheduling in cloud computing data centers using a multi-objective optimization algorithm. J. Netw. Syst. Manag. 29(3), 1–34 (2021)
Peterson, B.: Decentralized Scheduling for Many-Task Applications in the Hybrid Cloud. LSU doctoral dissertation. 4223, Louisiana State University and Agricultural and Mechanical College (2017)
Peterson, B., Fazlalizadeh, Y., Baumgartner, G., Wang, Q.: A vector-scheduling approach for running many-task applications in the cloud. In: Luo, M., Zhang, L.-J. (eds.) CLOUD 2018. LNCS, vol. 10967, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-94295-7_1
Raicu, I., Foster, I.T., Zhao, Y.: Many-task computing for grids and supercomputers. In: 2008 Workshop on Many-Task Computing on Grids and Supercomputers, pp. 1–11. IEEE (2008)
Rajbhandari, S., Nikam, A., Lai, P., Stock, K., Krishnamoorthy, S., Sadayappan, P.: A communication-optimal framework for contracting distributed tensors. In: SC 2014: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 375–386. IEEE (2014)
Taylor, I., Shields, M., Wang, I.: Resource management for the triana peer-to-peer services. In: Nabrzyski, J., Schopf, J.M., Weglarz, J. (eds.) Grid Resource Management, pp. 451–462. Springer, Boston (2004). https://doi.org/10.1007/978-1-4615-0509-9_27
Vannikkarasan, H.: Decentralized scheduling in cloud with variable size tasks. Technical report, Louisiana State University (2021)
Walker, E.: Benchmarking Amazon EC2 for high-performance scientific computing. Mag. USENIX SAGE 33(5), 18–23 (2008)
Wikipedia: Grid computing (2023). https://en.wikipedia.org/wiki/Grid_computing
Xin, R., Gonzalez, J., Franklin, M., Stoica, I.: Graphx: a resilient distributed graph system on spark. In: First International Workshop on Graph Data Management Experiences and Systems, pp. 1–6 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mithila, S.P., Franz, P., Baumgartner, G. (2023). Scheduling Many-Task Applications on Multi-clouds and Hybrid Clouds. In: Diehl, P., Thoman, P., Kaiser, H., Kale, L. (eds) Asynchronous Many-Task Systems and Applications. WAMTA 2023. Lecture Notes in Computer Science, vol 13861. Springer, Cham. https://doi.org/10.1007/978-3-031-32316-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-32316-4_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-32315-7
Online ISBN: 978-3-031-32316-4
eBook Packages: Computer ScienceComputer Science (R0)