Uma Política de Escalonamento Orientada à Redução do Tempo de Resposta de Aplicações Paralelas
Resumo
Este artigo apresenta uma nova política de escalonamento para aplicações do tipo Bag-of-Tasks denominada Dynamic Max-Min2x. Essa política visa reduzir o tempo de resposta de aplicações em grids computacionais. Experimentos utilizando a Dynamic Max-Min2x apontam significativos ganhos de desempenho dessa política quando comparada a outras propostas na literatura. A análise dos experimentos demonstra que a atribuição de tarefas no grid está fortemente ligada ao tamanho das tarefas a serem submetidas e à taxa de chegada das mesmas.
Referências
M. CALZAROSSA and S. GIUSEPPE. A characterization of the variation in time of workload arrival patterns. In IEEE 160 Transactions on Computers, volume C-34, pages 156-162, Fevereiro 1985.
H. CASANOVA, A. LEGRAND, D. ZAGORODNOV, and F. BERMAN. Heuristics for scheduling parameter sweep applications in grid environments. In 9th Heterogeneous Computing Workshop (HCW), pages 349-363, Cancun, Mexico, Maio2000.
CIRNE, W. Computational Grids: Architectures, Tecnologies and Applications. In Terceiro Workshop em Sistemas Computacionais de Alto Desempenho. Vitória, Brasil, Outubro 2002.
R. F. de Mello and L. J. Senger. A new migration model based on the evaluation of processes load and lifetime on heterogeneous computing environments. In International Symposium on Computer Architecture and High Performance Computing- SBAC-PAD, page 6, 2004.
R. F. de Mello and L. J. Senger. A new slowdown model for heterogeneous multicomputers environments. page li, 2005.
A. B. DOWNEY. A parallel workload model and its implications for processor allocation. Cluster Computing, 1(1): 133-145, 1998.
D. G. Feitelson and M. A. Jette. Improved utilization and responsiveness with gang scheduling. In D. G. Feitelson and L. Rudolph, editors, Job Scheduling Strategies for Parallel Processing, pages 238-261. Springer, 1997. Lect. Notes Comput. Sci. vol. 1291.
D. G. FEITELSON and L. RUDOLPH. Metrics and benchmarking for parallel job scheduling. In IPPSISPDP '98: Proceedings of the Workshop on Job Scheduling Strategies for Parallel Processing, volume 1459, pages 1-24, London, UK, 1998. Springer-Verlag.
I. FOSTER and C. KESSELMAN. The Grid: Blueprint for a New Computing Infrastructure, chapter Computational Grids. Morgan-Kaufman, 1999.
A. H. JAMES, H. A. K., and D. P. CODDlNGTON. Scheduling independent tasks on metacomputing systems. In Paraliei and Distributed Computing Systems (PDCS'99), pages 156-162, Fort Lauderdale, Florida, USA, Agosto 1999.
V. LO, J. MACHE, and K. WINDISCH. A comparative study of real workload traces and synthetic workload models for parallel job scheduling. In D. G. Feitelson and L. Rudolph, editors, Job Scheduling Strategies for Parallel Processing, pages 25-46. Springer Verlag, 1998. Lect. Notes Comput. Sei. vol. 1459.
M. MAHESWARAN, S. ALI, H. J. SIEGEL, D. A. HENSGEN, and R. F. FREUND. Dynamic matching and scheduling of a class of independent tasks onto heterogeneous computing systems. In 8th Heterogeneous Computing Workshop, pages 30-44, Abril 1999.
D. P. SILVA. Usando Replicações para Escalonar Tarefas Bag-of-Tasks em Grids Computacionais. Master's thesis, Universidade Federal de Campina Grande (UFCG), Campina Grande, Brasil. Fevereiro 2003.
H. CASANOVA, A. LEGRAND, D. ZAGORODNOV, and F. BERMAN. Heuristics for scheduling parameter sweep applications in grid environments. In 9th Heterogeneous Computing Workshop (HCW), pages 349-363, Cancun, Mexico, Maio2000.
CIRNE, W. Computational Grids: Architectures, Tecnologies and Applications. In Terceiro Workshop em Sistemas Computacionais de Alto Desempenho. Vitória, Brasil, Outubro 2002.
R. F. de Mello and L. J. Senger. A new migration model based on the evaluation of processes load and lifetime on heterogeneous computing environments. In International Symposium on Computer Architecture and High Performance Computing- SBAC-PAD, page 6, 2004.
R. F. de Mello and L. J. Senger. A new slowdown model for heterogeneous multicomputers environments. page li, 2005.
A. B. DOWNEY. A parallel workload model and its implications for processor allocation. Cluster Computing, 1(1): 133-145, 1998.
D. G. Feitelson and M. A. Jette. Improved utilization and responsiveness with gang scheduling. In D. G. Feitelson and L. Rudolph, editors, Job Scheduling Strategies for Parallel Processing, pages 238-261. Springer, 1997. Lect. Notes Comput. Sci. vol. 1291.
D. G. FEITELSON and L. RUDOLPH. Metrics and benchmarking for parallel job scheduling. In IPPSISPDP '98: Proceedings of the Workshop on Job Scheduling Strategies for Parallel Processing, volume 1459, pages 1-24, London, UK, 1998. Springer-Verlag.
I. FOSTER and C. KESSELMAN. The Grid: Blueprint for a New Computing Infrastructure, chapter Computational Grids. Morgan-Kaufman, 1999.
A. H. JAMES, H. A. K., and D. P. CODDlNGTON. Scheduling independent tasks on metacomputing systems. In Paraliei and Distributed Computing Systems (PDCS'99), pages 156-162, Fort Lauderdale, Florida, USA, Agosto 1999.
V. LO, J. MACHE, and K. WINDISCH. A comparative study of real workload traces and synthetic workload models for parallel job scheduling. In D. G. Feitelson and L. Rudolph, editors, Job Scheduling Strategies for Parallel Processing, pages 25-46. Springer Verlag, 1998. Lect. Notes Comput. Sei. vol. 1459.
M. MAHESWARAN, S. ALI, H. J. SIEGEL, D. A. HENSGEN, and R. F. FREUND. Dynamic matching and scheduling of a class of independent tasks onto heterogeneous computing systems. In 8th Heterogeneous Computing Workshop, pages 30-44, Abril 1999.
D. P. SILVA. Usando Replicações para Escalonar Tarefas Bag-of-Tasks em Grids Computacionais. Master's thesis, Universidade Federal de Campina Grande (UFCG), Campina Grande, Brasil. Fevereiro 2003.
Publicado
24/10/2005
Como Citar
REIS, Valéria Quadros dos; SANTANA, Marcos José; MELLO, Rodrigo Fernandes de; SANTANA, Regina Helena Carlucci.
Uma Política de Escalonamento Orientada à Redução do Tempo de Resposta de Aplicações Paralelas. In: SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 6. , 2005, Rio de Janeiro.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2005
.
p. 153-160.
DOI: https://doi.org/10.5753/wscad.2005.18988.
