Skip to Main content Skip to Navigation
Master thesis

Minimizing Cluster Under-use using a Control-Based Approach

Quentin Guilloteau 1, 2
1 DATAMOVE - Data Aware Large Scale Computing
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
2 CTRL-A - Control for Autonomic computing systems
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : High Performance Computing (HPC) systems have become increasingly more complex in the last decade. Their behavior concerning their performance and power consumption make them less predictable. This unpredictability requires more and more runtime management. We believe that the field of Control Theory can bring a new approach to the administration of such complex systems. This project integrates an autonomic approach to the CiGri middleware, a grid application to manage large sets of multi-parametric tasks. This work presents two distinct contributions. In a first time, we present a solution to minimize cluster under-utilization while controlling the load of the fileserver. We then investigate the case of reproducibility for our studied distributed system.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03167242
Contributor : Quentin Guilloteau <>
Submitted on : Friday, March 12, 2021 - 10:17:45 AM
Last modification on : Monday, April 26, 2021 - 8:58:54 AM

File

M2_report_Quentin_Guilloteau.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03167242, version 1

Citation

Quentin Guilloteau. Minimizing Cluster Under-use using a Control-Based Approach. Distributed, Parallel, and Cluster Computing [cs.DC]. 2020. ⟨hal-03167242⟩

Share

Metrics

Record views

170