Making the most of what you pay for by delaying tasks to improve overall cloud instance performance
Resumo
Resource elasticity and server consolidation have long been among two of cloud computing’s most relevant management tools. Yet, exemplified with a scientific application use case, this paper highlights how judicious scheduling of tasks can help maximize resource utilization and improve performance and costs for both users and cloud providers. Developing an efficient cloud service for DNA sequence comparisons is adopted as a motivating use case. Using the bioinformatics tool MASA that finds an optimal pair-wise sequence alignment, we propose a model for co-scheduling multiple alignments on a single cloud instance. The resulting, practically optimal, non-preemptive schedule can effectively double the throughput of MASA-based sequence alignment workflows.
Referências
Calatrava, A., Romero, E., Moltó, G., Caballer, M., and Alonso, J. M. (2016). Self-managed cost-efficient virtual elastic clusters on hybrid cloud infrastructures. Future Generation Computer Systems, 61:13-25.
Carvalho, L., Melo, A., and Araujo, A. (2021). A framework for executing protein sequence alignment in cloud computing services. In Anais do XXII Simpósio em Sistemas Computacionais de Alto Desempenho, pages 48-59, Porto Alegre, RS, Brasil. SBC.
De O. Sanders, E. F., Miranda, G., Martorell, X., Ayguade, E., Teodoro, G., and De Melo, A. C. M. A. (2016). MASA: A multiplatform architecture for sequence aligners with block pruning. ACM Transactions on Parallel Computing, 2(4).
Myers, E. W. and Miller, W. (1988). Optimal alignments in linear space. Bioinformatics, 4(1):11-17.
Nicodemus, C. H. Z., Boeres, C., and Rebello, V. E. F. (2020). Managing vertical memory elasticity in containers. In 2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing (UCC), pages 132-142. IEEE.
Qazi, K. (2019). Vertelas Automated user-controlled vertical elasticity in commercial clouds. In 2019 4th Int. Conf. on Computing, Comm. and Security (ICCCS), pages 1-8.
Teylo, L., Nunes, A. L., Melo, A. C. M. A., Boeres, C., de A. Drummond, L. M., and Martins, N. F. (2021). Comparing SARS-CoV-2 sequences using a commercial cloud with a spot instance based dynamic scheduler. In 2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid), pages 247-256.
