Memory-intensive scheduling policies for distributed applications / Políticas de escalonamento memory-intensive para aplicações distribuídas

AUTOR(ES)
DATA DE PUBLICAÇÃO

2008

RESUMO

This dissertation approaches the process scheduling on clusters of computers, on both homogeneous and heterogeneous platforms. The heterogeneities considered include processor computational power, system main memory quantity and the average disk access time. In this work are proposed four novel policies aimed at realizing the work load sharing on these environments, considering workloads with applications varying between CPU-bound and memory-intensive. Among the four policies, one of them uses only CPU indices, while the others also use memory indices. The results were obtained by means of trace-based simulations and show a significant reduction on the performance losses observed on the results obtained with the proposed scheduling policies. As references were used traditional scheduling policies found in the literature

ASSUNTO(S)

processes scheduling memory-intensive applications and simulation cluster de computadores escalonamento de processos avaliação de desempenho sistemas de imagem única single-system image performance evaluation aplicações memory-intensive e simulação computer clusters

ACESSO AO ARTIGO

Documentos Relacionados