Optimizing checkpoint data placement with guaranteed burst buffer endurance in large-scale hierarchical storage systems

Open Webpage

Lipeng Wan, Qing Cao, Feiyi Wang, Sarp Oral

Published: 2017, Last Modified: 19 Mar 2026J. Parallel Distributed Comput. 2017EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A thorough analysis of both failure patterns and runtime characteristics of HPC systems.•A new checkpoint placement model for optimizing large-scale hierarchical storage systems’ usage.•A novel adaptive algorithm that can dynamically optimize the checkpoint placement.