Análisis del rendimiento de la paralelización del algoritmo Reed-Solomon
DOI:
https://doi.org/10.18779/ingenio.v4i1.365Palabras clave:
Fiabilidad, tolerancia a los fallos, códigos de control de errores, Reed-SolomonResumen
Los sistemas de almacenamiento distribuido permiten resolver la fuerte demanda de almacenamiento de datos que requiere la sociedad actual. Es por ello que surgen nuevos retos relacionados con la recuperación de datos basada en código de borrado. En este artículo se presenta la paralelización del algoritmo Reed-Solomon a través de hilos. La evaluación se ha realizado en un sistema BLADE, la ejecución del algoritmo se ha realizado en una configuración de 1, 2, 4 y 8 hilos para comprobar el comportamiento del algoritmo. En cuanto a los resultados, se observa que se reducen considerablemente los tiempos requeridos para el procesamiento de los algoritmos tanto para codificación como para decodificación.
Descargas
Citas
Palacios, R. H., Díaz, A. F., Anguita, M., Ortega, J., & Rodríguez-Quintana, C. (2017). High-throughput multi-multicast transfers in data center networks. The Journal of Supercomputing, 73(1), 152-163.
Palacios, R. H., Rodríguez-Quintana, C., Díaz, A. F., Anguita, M., & Ortega, J. (2017). Evaluation of redundant data storage in clusters based on multi-multicast and local storage. The Journal of Supercomputing, 73(1), 576-590.
Aguilera, M. K., Janakiraman, R., & Xu, L. (2005, June). Using erasure codes efficiently for storage in a distributed system. In 2005 International Conference on Dependable Systems and Networks (DSN'05) (pp. 336-345). IEEE.
Hafner, J. L. (2005, December). WEAVER Codes: Highly Fault Tolerant Erasure Codes for Storage Systems. In Fast (Vol. 5, pp. 16-16).
Khan, O., Burns, R. C., Plank, J. S., Pierce, W., & Huang, C. (2012, February). Rethinking erasure codes for cloud file systems: minimizing I/O for recovery and degraded reads. In FAST (p. 20).
Plank, J. S. (2013). Erasure codes for storage systems: A brief primer. ; login:: the magazine of USENIX & SAGE, 38(6), 44-50.
Weatherspoon, H., & Kubiatowicz, J. D. (2002, March). Erasure coding vs. replication: A quantitative comparison. In International Workshop on Peer-to-Peer Systems (pp. 328-337). Springer, Berlin, Heidelberg.
Rashmi, K. V., Shah, N. B., Ramchandran, K., & Kumar, P. V. (2017). Information-theoretically secure erasure codes for distributed storage. IEEE Transactions on Information Theory, 64(3), 1621-1646.
Yiu, M. M., Chan, H. H., & Lee, P. P. (2017, May). Erasure coding for small objects in in-memory kv storage. In Proceedings of the 10th ACM International Systems and Storage Conference (pp. 1-12).
Sobe, P. (2010, May). Parallel reed/solomon coding on multicore processors. In 2010 International Workshop on Storage Network Architecture and Parallel I/Os (pp. 71-80). IEEE.
Chen, R., & Xu, L. (2020). Practical performance evaluation of space optimal erasure codes for high-speed data storage systems. SN Computer Science, 1(1), 1-14.
Jin, H., Wu, C., Xie, X., Li, J., Guo, M., Lin, H., & Zhang, J. (2019, August). Approximate code: a cost-effective erasure coding framework for tiered video storage in cloud systems. In Proceedings of the 48th International Conference on Parallel Processing (pp. 1-10).
Plank, J. S., Simmerman, S., & Schuman, C. D. (2007). Jerasure: A library in C/C++ facilitating erasure coding for storage applications. Technical Report CS-07-603, University of Tennessee.
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2021 Fabricio R. Marcillo, Raúl H. Palacios, Antonio F. Díaz, Jefferson R. Herrera, Ronald D. Camacho
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
Licensing Agreement
This journal provides free access to its content through its website following the principle that making research available free of charge to the public supports a larger exchange of global knowledge.
Web content of the journal is distributed under a Attribution-NonCommercial-ShareAlike 4.0 International.
Authors may adopt other non-exclusive license agreements for the distribution of the version of the published work, provided that the initial publication in this journal is indicated. Authors are allowed and recommended to disseminate their work through the internet before and during the submission process, which can produce interesting exchanges and increase citations of the published work.