LOAD BALANCING IN DISTRIBUTED EXASCALE COMPUTING BASED ON PROCESS REQUIREMENTS

Volume 1 (2), December 2018, Pages 158-167

Shirin Shahrabi1, Faezeh Mollasalehi1, Araz R Aliev2, Ehsan Mousavi Khaneghah1


1Department of Computer Engineering, Faculty of Engineering, Shahed University, Tehran, Iran; This email address is being protected from spambots. You need JavaScript enabled to view it., This email address is being protected from spambots. You need JavaScript enabled to view it., This email address is being protected from spambots. You need JavaScript enabled to view it.;

2Department of General and Applied Mathematics, HPC Advance Research Center, Azerbaijan State Oil and Industry University, Baku, Azerbaijan; This email address is being protected from spambots. You need JavaScript enabled to view it.


Abstract

In distributed Exascale systems, the occurrence of a dynamic and interactive nature changes the workload of the system’s computing elements. Because of this, the load balancer needs to collect information on the system state. Activating the load balancer increases the runtime of the scientific application. While analyzing the impact of the dynamic and interactive nature on the load balancer functionality, this paper also attempts to provide a mathematical definition for load balancer based on the concept of dynamic and interactive nature. This makes it possible to describe and examine the load balancer functionality by considering the impacts of the dynamic and interactive nature. As a result, decisions can be made on the behavior of the load balancer when a dynamic and interactive nature occurs. According to the mentioned operational function, this paper has analyzed the load balancer’s behavior in processes with a dynamic and interactive nature. The introduced operational function for the load balancer in this paper enables the management element to separate the requests of processes with a dynamic and interactive nature and normal processes that leads to redistribution.

Keywords:

distributed exascale computing system, load balancing, dynamic and interactive nature, runtime.

DOI: https://doi.org/10.32010/26166127.2018.1.2.158.167

 

Reference 

[1] Mousavi Khaneghah, E., Noorabad Ghahroodi, R., & Reyhani ShowkatAbad, A. (2018). A mathematical multi-dimensional mechanism to improve process migration efficiency in peer-to-peer computing environments. Cogent Engineering, 5(1), 1458434.

[2] Mirtaheri, S. L., & Grandinetti, L. (2017). Dynamic load balancing in distributed exascale computing systems. Cluster Computing, 20(4), 3677-3689.

[3] Barak, A., Drezner, Z., Levy, E., Lieber, M., & Shiloh, A. (2015). Resilient gossip algorithms for collecting online management information in exascale clusters. Concurrency and Computation: Practice and Experience, 27(17), 4797-4818.

[4] Reyle, C., Richard, J., Cambrésy, L., Deleuil, M., Pécontal, E., & Tresse, L. (2016). Perspectives in numerical astrophysics. In the Annual meeting of the French Society of Astronomy and Astrophysics, SF2A-2016.

[5] Alowayyed, S., Groen, D., Coveney, P. V., & Hoekstra, A. G. (2017). Multiscale computing in the exascale era. Journal of Computational Science, 22, 15-25.

[6] Innocenti, M. E., Johnson, A., Markidis, S., Amaya, J., Deca, J., Olshevsky, V., & Lapenta, G. (2017). Progress towards physics-based space weather forecasting with exascale computing. Advances in Engineering Software, 111, 3-17.

[7] SEVENTH FRAMEWORK PROGRAMME Research Infrastructures. (n.d.). Retrieved from https://www.deep-projects.eu/images/materials/DEEP_ER_D1.1.pdf

[8] Mirtaheri, S. L., Fatemi, S. A., & Grandinetti, L. (2017). Adaptive Load Balancing Dashboard in Dynamic Distributed Systems. Supercomputing Frontiers and Innovations, 4(4), 34-49.

[9] Wang, K., Qiao, K., Sadooghi, I., Zhou, X., Li, T., Lang, M., & Raicu, I. (2016). Load‐balanced and locality‐aware scheduling for data‐intensive workloads at extreme scales. Concurrency and Computation: Practice and Experience, 28(1), 70-94.

[10] Khaneghah, E. M., ShowkatAbad, A. R., & Ghahroodi, R. N. (2018, February). Challenges of Process Migration to Support Distributed Exascale Computing Environment. In Proceedings of the 2018 7th International Conference on Software and Computer Applications (pp. 20-24). ACM.

[11] Amelina, N., Fradkov, A., Jiang, Y., & Vergados, D. J. (2015). Approximate consensus in stochastic networks with application to load balancing. IEEE Transactions on Information Theory, 61(4), 1739-1752.

[12] Klimentov, A., Buncic, P., De, K., Jha, S., Maeno, T., Mount, R., ... & Porter, R. J. (2015). Next generation workload management system for big data on heterogeneous distributed computing. In Journal of Physics: Conference Series (Vol. 608, No. 1, p. 012040). IOP Publishing.

[13] Hussain, H., Malik, S. U. R., Hameed, A., Khan, S. U., Bickler, G., Min-Allah, N., ... & Kolodziej, J. (2013). A survey on resource allocation in high performance distributed computing systems. Parallel Computing, 39(11), 709-736.

[14] Yang, C. T., Liu, J. C., Hsu, C. H., & Chou, W. L. (2014). On improvement of cloud virtual machine availability with virtualization fault tolerance mechanism. The Journal of Supercomputing, 69(3), 1103-1122.

[15] Kołodziej, J., Khan, S. U., Wang, L., Kisiel-Dorohinicki, M., Madani, S. A., Niewiadomska-Szynkiewicz, E., ... & Xu, C. Z. (2014). Security, energy, and performance-aware resource allocation mechanisms for computational grids. Future Generation Computer Systems, 31, 77-92.

[16] Skinner, B. F. (1953). Science and human behavior (No. 92904). Simon and Schuster.

[17] Fiore, S., Bakhouya, M., & Smari, W. W. (2018). On the road to exascale: Advances in High Performance Computing and Simulations—An overview and editorial. Future Generation Computer Systems, 82, 450-458. doi:10.1016/j.future.2018.01.034

[18] Straatsma, T. P., Antypas, K. B., & Williams, T. J. (2017). Exascale Scientific Applications: Scalability and Performance Portability. Chapman and Hall/CRC.

[19] Ghomi, E. J., Rahmani, A. M., & Qader, N. N. (2017). Load-balancing algorithms in cloud computing: a survey. Journal of Network and Computer Applications, 88, 50-71.

[20] Abraham, E., Bekas, C., Brandic, I., Genaim, S., Johnsen, E. B., Kondov, I., ... & Streit, A. (2015, September). Preparing HPC applications for exascale: Challenges and recommendations. In Network-Based Information Systems (NBiS), 2015 18th International Conference on (pp. 401-406). IEEE.

[21] Eicker, N., Lippert, T., Moschny, T., & Suarez, E. (2013, October). The deep project-pursuing cluster-computing in the many-core era. In 2013 42nd International Conference on Parallel Processing (ICPP) (pp. 885-892). IEEE.

[22] Singh, A., Juneja, D., & Malhotra, M. (2015). Autonomous agent based load balancing algorithm in cloud computing. Procedia Computer Science, 45, 832-841.

[23] Milani, A. S., & Navimipour, N. J. (2016). Load balancing mechanisms and techniques in the cloud environments: Systematic literature review and future trends. Journal of Network and Computer Applications, 71, 86-98.

[24] Xiao, Y., Xue, Y., Nazarian, S., & Bogdan, P. (2017, November). A load balancing inspired optimization framework for exascale multicore systems: a complex networks approach. In Proceedings of the 36th International Conference on Computer-Aided Design (pp. 217-224). IEEE Press.

[25] Márquez, C., César, E., & Sorribes, J. (2015, August). Graph-based automatic dynamic load balancing for HPC agent-based simulations. In European Conference on Parallel Processing (pp. 405-416). Springer, Cham.

[26] Marathe, A., Bailey, P. E., Lowenthal, D. K., Rountree, B., Schulz, M., & de Supinski, B. R. (2015, July). A run-time system for power-constrained HPC applications. In International conference on high performance computing (pp. 394-408). Springer, Cham.

[27] Panchal, B., Smaranika, P. (2018) An Efficient Dynamic Load Balancing Algorithm Using Machine Learning Technique in Cloud Environment. International Journal of Scientific Research in Science, Engineering and Technology, 4(4), 1184-1186.

[28] Jeannot, E., Mercier, G., & Tessier, F. (2016, November). Topology and affinity aware hierarchical and distributed load-balancing in Charm++. In International Workshop on Communication Optimizations in HPC (COMHPC) (pp. 63-72). IEEE.

[29] Soltani, N., & Sharifi, M. (2014). A Load Balancing Algorithm Based on Replication and Movement af Data Items for Dynamic Structured P2P Systems. International Journal of Peer to Peer Networks, 5(3), 15-32. doi:10.5121/ijp2p.2014.5302

[30] Sreenivas, V., Prathap, M., & Kemal, M. (2014, February). Load balancing techniques: Major challenge in Cloud Computing-a systematic review. In 2014 International Conference on Electronics and Communication Systems (ICECS) (pp. 1-6). IEEE.

[31] Rahman, M., Iqbal, S., & Gao, J. (2014, April). Load balancer as a service in cloud computing. In 2014 IEEE 8th international symposium on service oriented system engineering (SOSE) (pp. 204-211). IEEE.

[32] Singh, P., Baaga, P., & Gupta, S. (2016). Assorted Load Balancing Algorithms in Cloud Computing: A Survey. International Journal of Computer Applications, 143(7).

[33] Navimipour, N. J., & Milani, F. S. (2015). A comprehensive study of the resource discovery techniques in peer-to-peer networks. Peer-to-Peer Networking and Applications, 8(3), 474-492.

[34] Rathore, N., & Chana, I. (2014). Load balancing and job migration techniques in grid: a survey of recent trends. Wireless personal communications, 79(3), 2089-2125.