Geomancy: Automated Performance Enhancement through Data Layout Optimization

The size and complexity of large storage systems, such as high-performance computing (HPC) systems, inhibit rapid effective restructuring of data layouts to maintain performance as workloads shift. To address this issue, we have developed Geomancy, a tool that models the placement of data within a d...

Descripción completa

Detalles Bibliográficos
Autores principales: Bel, Oceane, Chang, Kenneth, Tallent, Nathan R., Duellmann, Dirk, Miller, Ethan L., Nawab, Faisal, Long, Darrell D. E.
Publicado: 2020
Acceso en línea:https://dx.doi.org/10.1109/ISPASS48437.2020.00025
http://cds.cern.ch/record/2799930
_version_ 1780972598385967104
author Bel, Oceane
Chang, Kenneth
Tallent, Nathan R.
Duellmann, Dirk
Miller, Ethan L.
Nawab, Faisal
Long, Darrell D. E.
author_facet Bel, Oceane
Chang, Kenneth
Tallent, Nathan R.
Duellmann, Dirk
Miller, Ethan L.
Nawab, Faisal
Long, Darrell D. E.
author_sort Bel, Oceane
collection CERN
description The size and complexity of large storage systems, such as high-performance computing (HPC) systems, inhibit rapid effective restructuring of data layouts to maintain performance as workloads shift. To address this issue, we have developed Geomancy, a tool that models the placement of data within a distributed storage system and reacts to drops in performance. Our approach to optimizing throughput offers benefits for storage systems such as avoiding potential bottlenecks and increasing overall I/O throughput from 11% to 30%.
id cern-2799930
institution Organización Europea para la Investigación Nuclear
publishDate 2020
record_format invenio
spelling cern-27999302022-01-19T21:36:06Zdoi:10.1109/ISPASS48437.2020.00025http://cds.cern.ch/record/2799930Bel, OceaneChang, KennethTallent, Nathan R.Duellmann, DirkMiller, Ethan L.Nawab, FaisalLong, Darrell D. E.Geomancy: Automated Performance Enhancement through Data Layout OptimizationThe size and complexity of large storage systems, such as high-performance computing (HPC) systems, inhibit rapid effective restructuring of data layouts to maintain performance as workloads shift. To address this issue, we have developed Geomancy, a tool that models the placement of data within a distributed storage system and reacts to drops in performance. Our approach to optimizing throughput offers benefits for storage systems such as avoiding potential bottlenecks and increasing overall I/O throughput from 11% to 30%.oai:cds.cern.ch:27999302020
spellingShingle Bel, Oceane
Chang, Kenneth
Tallent, Nathan R.
Duellmann, Dirk
Miller, Ethan L.
Nawab, Faisal
Long, Darrell D. E.
Geomancy: Automated Performance Enhancement through Data Layout Optimization
title Geomancy: Automated Performance Enhancement through Data Layout Optimization
title_full Geomancy: Automated Performance Enhancement through Data Layout Optimization
title_fullStr Geomancy: Automated Performance Enhancement through Data Layout Optimization
title_full_unstemmed Geomancy: Automated Performance Enhancement through Data Layout Optimization
title_short Geomancy: Automated Performance Enhancement through Data Layout Optimization
title_sort geomancy: automated performance enhancement through data layout optimization
url https://dx.doi.org/10.1109/ISPASS48437.2020.00025
http://cds.cern.ch/record/2799930
work_keys_str_mv AT beloceane geomancyautomatedperformanceenhancementthroughdatalayoutoptimization
AT changkenneth geomancyautomatedperformanceenhancementthroughdatalayoutoptimization
AT tallentnathanr geomancyautomatedperformanceenhancementthroughdatalayoutoptimization
AT duellmanndirk geomancyautomatedperformanceenhancementthroughdatalayoutoptimization
AT millerethanl geomancyautomatedperformanceenhancementthroughdatalayoutoptimization
AT nawabfaisal geomancyautomatedperformanceenhancementthroughdatalayoutoptimization
AT longdarrellde geomancyautomatedperformanceenhancementthroughdatalayoutoptimization

Ejemplares similares