The storage system for a multimedia data manager kernel
Autor(a) principal: | |
---|---|
Data de Publicação: | 2014 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/PDCAT.2013.41 http://hdl.handle.net/11449/177250 |
Resumo: | One way to boost the performance of a Database Management System (DBMS) is by fetching data in advance of their use, a technique known as prefetching. However, depending on the resource being used (file, disk partition, memory, etc.), the way prefetching is done might be different or even not necessary, forcing a DBMS to be aware of the underlying Storage System. In this paper we propose a Storage System that frees the DBMS of this task by exposing the database through a unique interface, no matter what kind of resource hosts it. We have implemented a file resource that recognizes and exploits sequential access patterns that emerge over time to prefetch adjacent blocks to the requested ones. Our approach is speculative because it considers past accesses, but it also considers hints from the upper layers of the DBMS, which must specify the access context in which a read operation takes place. The informed access context is then mapped to one of the available channels in the file resource, which is equipped with a set of internal buffers, one per channel, for the management of fetched and prefetched data. Prefetched data are moved to the main cache of the DBMS only if really requested by the application, which helps to avoid cache pollution. So, we slightly introduced a two level cache hierarchy without any intervention of the DBMS kernel. We ran the tests with different buffer settings and compared the results against the OBL policy, which showed that it is possible to get a read time up to two times faster in a highly concurrent environment without sacrificing the performance when the system is not under intensive workloads. |
id |
UNSP_71d17801dbd1c9fa7fd61dd2feeed8ad |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/177250 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
The storage system for a multimedia data manager kernelAccess contextbuffer managementcache pollutionchanneldatabase management systemmultimedia databaseobject databaseperformanceprefetchingsequential access patternstorage systemOne way to boost the performance of a Database Management System (DBMS) is by fetching data in advance of their use, a technique known as prefetching. However, depending on the resource being used (file, disk partition, memory, etc.), the way prefetching is done might be different or even not necessary, forcing a DBMS to be aware of the underlying Storage System. In this paper we propose a Storage System that frees the DBMS of this task by exposing the database through a unique interface, no matter what kind of resource hosts it. We have implemented a file resource that recognizes and exploits sequential access patterns that emerge over time to prefetch adjacent blocks to the requested ones. Our approach is speculative because it considers past accesses, but it also considers hints from the upper layers of the DBMS, which must specify the access context in which a read operation takes place. The informed access context is then mapped to one of the available channels in the file resource, which is equipped with a set of internal buffers, one per channel, for the management of fetched and prefetched data. Prefetched data are moved to the main cache of the DBMS only if really requested by the application, which helps to avoid cache pollution. So, we slightly introduced a two level cache hierarchy without any intervention of the DBMS kernel. We ran the tests with different buffer settings and compared the results against the OBL policy, which showed that it is possible to get a read time up to two times faster in a highly concurrent environment without sacrificing the performance when the system is not under intensive workloads.Departamento de Ciéncias de Computação e Estatística, São Paulo State University - UNESPDepartamento de Computação, Federal University of São Carlos - UFSCarDepartamento de Ciéncias de Computação e Estatística, São Paulo State University - UNESPUniversidade Estadual Paulista (Unesp)Universidade Federal de São Carlos (UFSCar)Valěncio, Carlos Roberto [UNESP]De Almeida, Fábio Renato [UNESP]Machado, Jose Marcio [UNESP]Colombini, Angelo CesarNeves, Leandro Alves [UNESP]De Souza, Rogeria Cristiane Gratao [UNESP]2018-12-11T17:24:38Z2018-12-11T17:24:38Z2014-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject219-225http://dx.doi.org/10.1109/PDCAT.2013.41Parallel and Distributed Computing, Applications and Technologies, PDCAT Proceedings, p. 219-225.http://hdl.handle.net/11449/17725010.1109/PDCAT.2013.412-s2.0-84907986006464481225387583221390538148793120000-0002-9325-3159Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengParallel and Distributed Computing, Applications and Technologies, PDCAT Proceedingsinfo:eu-repo/semantics/openAccess2021-10-23T21:47:03Zoai:repositorio.unesp.br:11449/177250Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T21:47:03Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
The storage system for a multimedia data manager kernel |
title |
The storage system for a multimedia data manager kernel |
spellingShingle |
The storage system for a multimedia data manager kernel Valěncio, Carlos Roberto [UNESP] Access context buffer management cache pollution channel database management system multimedia database object database performance prefetching sequential access pattern storage system |
title_short |
The storage system for a multimedia data manager kernel |
title_full |
The storage system for a multimedia data manager kernel |
title_fullStr |
The storage system for a multimedia data manager kernel |
title_full_unstemmed |
The storage system for a multimedia data manager kernel |
title_sort |
The storage system for a multimedia data manager kernel |
author |
Valěncio, Carlos Roberto [UNESP] |
author_facet |
Valěncio, Carlos Roberto [UNESP] De Almeida, Fábio Renato [UNESP] Machado, Jose Marcio [UNESP] Colombini, Angelo Cesar Neves, Leandro Alves [UNESP] De Souza, Rogeria Cristiane Gratao [UNESP] |
author_role |
author |
author2 |
De Almeida, Fábio Renato [UNESP] Machado, Jose Marcio [UNESP] Colombini, Angelo Cesar Neves, Leandro Alves [UNESP] De Souza, Rogeria Cristiane Gratao [UNESP] |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Universidade Federal de São Carlos (UFSCar) |
dc.contributor.author.fl_str_mv |
Valěncio, Carlos Roberto [UNESP] De Almeida, Fábio Renato [UNESP] Machado, Jose Marcio [UNESP] Colombini, Angelo Cesar Neves, Leandro Alves [UNESP] De Souza, Rogeria Cristiane Gratao [UNESP] |
dc.subject.por.fl_str_mv |
Access context buffer management cache pollution channel database management system multimedia database object database performance prefetching sequential access pattern storage system |
topic |
Access context buffer management cache pollution channel database management system multimedia database object database performance prefetching sequential access pattern storage system |
description |
One way to boost the performance of a Database Management System (DBMS) is by fetching data in advance of their use, a technique known as prefetching. However, depending on the resource being used (file, disk partition, memory, etc.), the way prefetching is done might be different or even not necessary, forcing a DBMS to be aware of the underlying Storage System. In this paper we propose a Storage System that frees the DBMS of this task by exposing the database through a unique interface, no matter what kind of resource hosts it. We have implemented a file resource that recognizes and exploits sequential access patterns that emerge over time to prefetch adjacent blocks to the requested ones. Our approach is speculative because it considers past accesses, but it also considers hints from the upper layers of the DBMS, which must specify the access context in which a read operation takes place. The informed access context is then mapped to one of the available channels in the file resource, which is equipped with a set of internal buffers, one per channel, for the management of fetched and prefetched data. Prefetched data are moved to the main cache of the DBMS only if really requested by the application, which helps to avoid cache pollution. So, we slightly introduced a two level cache hierarchy without any intervention of the DBMS kernel. We ran the tests with different buffer settings and compared the results against the OBL policy, which showed that it is possible to get a read time up to two times faster in a highly concurrent environment without sacrificing the performance when the system is not under intensive workloads. |
publishDate |
2014 |
dc.date.none.fl_str_mv |
2014-01-01 2018-12-11T17:24:38Z 2018-12-11T17:24:38Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1109/PDCAT.2013.41 Parallel and Distributed Computing, Applications and Technologies, PDCAT Proceedings, p. 219-225. http://hdl.handle.net/11449/177250 10.1109/PDCAT.2013.41 2-s2.0-84907986006 4644812253875832 2139053814879312 0000-0002-9325-3159 |
url |
http://dx.doi.org/10.1109/PDCAT.2013.41 http://hdl.handle.net/11449/177250 |
identifier_str_mv |
Parallel and Distributed Computing, Applications and Technologies, PDCAT Proceedings, p. 219-225. 10.1109/PDCAT.2013.41 2-s2.0-84907986006 4644812253875832 2139053814879312 0000-0002-9325-3159 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Parallel and Distributed Computing, Applications and Technologies, PDCAT Proceedings |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
219-225 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1803649386675175424 |