SQL-On-Hadoop Systems: Evaluting Performance of Polybase for Big Data Processing

performance of the bridge PolyBase SQL Server for working with hybrid data stores has been investigated. The analysis of the existing bridges for joint processing of SQL-and NoSQL data with using of a Hadoop cluster has been carried out. Technologies for query optimization when using PolyBase have b...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2018 International Scientific-Practical Conference Problems of Infocommunications. Science and Technology (PIC S&T) s. 591 - 594
Hlavní autoři: Minukhin, Sergii, Fedko, Victor, Sitnikov, Dmytro
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.10.2018
Témata:
Apach Hadoop
Big Data
Bridges
Data warehouses
HDFS
Measurement
PDW
performance metrics
polyBase SQL Server
Servers
split processing
Structured Query Language
ISBN:9781538666098, 153866609X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:performance of the bridge PolyBase SQL Server for working with hybrid data stores has been investigated. The analysis of the existing bridges for joint processing of SQL-and NoSQL data with using of a Hadoop cluster has been carried out. Technologies for query optimization when using PolyBase have been represented. The paradigm of data splitting and applying the pushdown procedure has been considered. Results of using the procedure predicate pushdown for the suggested metrics of PolyBase-Hadoop system performance have been considered for examples of processing test data of large volumes.
ISBN:9781538666098
153866609X
DOI:10.1109/INFOCOMMST.2018.8632143