Rozšíření HDF5 o ukládání časových řad

Thumbnail Image

Files

MOU0011_FEI_N2647_2612T025_2016.pdf (16.39 MB)
MOU0011_FEI_N2647_2612T025_2016_priloha.zip (288.25 KB)
MOU0011_FEI_N2647_2612T025_2016_posudek_vedouci_Martinovic_Jan.pdf (48.85 KB)
MOU0011_FEI_N2647_2612T025_2016_posudek_oponent_Slaninova_Katerina.pdf (50.83 KB)

Downloads

3

Date issued

2016

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Vysoká škola báňská - Technická univerzita Ostrava

Location

Signature

Abstract

This thesis deals with storing of big data, mostly with storing big time series. There are mentioned different approaches to their storing, NoSQL databases, Adios library and Scientific Data formats HDF5, CDF and NetCDF. After that, it describes Lustre file system and its influence on paralel data access. Then it deals with creating extension on HDF5 for storing time series data and describes usage of this extension. Finally this extension is tested on HPC compute nodes.

Description

Import 03/11/2016

Subject(s)

Big data, Time series, NoSQL, Adios, HDF5, CDF, NetCDF, HPC

Citation

Item identifier

http://hdl.handle.net/10084/115906

Collections

Vysokoškolské kvalifikační práce Fakulty elektrotechniky a informatiky / Theses and dissertations of Faculty of Electrical Engineering and Computer Science (FEI)