A study of PosDB performance in a distributed environment

George Chernishev, Vyacheslav Galaktionov, Valentin Grigorev, Evgeniy Klyuchikov, Kirill Smirnov

Research output

2 Citations (Scopus)

Abstract

PosDB is a new disk-based distributed column-store relational engine aimed for research purposes. It uses the Volcano pull-based model and late materialization for query processing, and join indexes for internal data representation. In its current state PosDB is capable of both local and distributed processing of all SSB (Star Schema Benchmark) queries. Data, as well as query plans, can be distributed among network nodes in our system. Data distribution is performed by horizontal partitioning. In this paper we experimentally evaluate the performance of our system in a distributed environment. We analyze system performance and report a number of metrics, such as speedup and scaleup. For our evaluation we use the standard benchmark - the SSB.

Original languageEnglish
JournalCEUR Workshop Proceedings
Volume1864
Publication statusPublished - 1 Sep 2017
Event2nd Conference on Software Engineering and Information Management, SEIM 2017 - Saint Petersburg
Duration: 21 Apr 2017 → …

Fingerprint

Stars
Volcanoes
Query processing
Engines
Processing

Scopus subject areas

  • Computer Science(all)

Cite this

Chernishev, G., Galaktionov, V., Grigorev, V., Klyuchikov, E., & Smirnov, K. (2017). A study of PosDB performance in a distributed environment. CEUR Workshop Proceedings, 1864.
Chernishev, George ; Galaktionov, Vyacheslav ; Grigorev, Valentin ; Klyuchikov, Evgeniy ; Smirnov, Kirill. / A study of PosDB performance in a distributed environment. In: CEUR Workshop Proceedings. 2017 ; Vol. 1864.
@article{9630275b437f43f69359da751d022bc4,
title = "A study of PosDB performance in a distributed environment",
abstract = "PosDB is a new disk-based distributed column-store relational engine aimed for research purposes. It uses the Volcano pull-based model and late materialization for query processing, and join indexes for internal data representation. In its current state PosDB is capable of both local and distributed processing of all SSB (Star Schema Benchmark) queries. Data, as well as query plans, can be distributed among network nodes in our system. Data distribution is performed by horizontal partitioning. In this paper we experimentally evaluate the performance of our system in a distributed environment. We analyze system performance and report a number of metrics, such as speedup and scaleup. For our evaluation we use the standard benchmark - the SSB.",
author = "George Chernishev and Vyacheslav Galaktionov and Valentin Grigorev and Evgeniy Klyuchikov and Kirill Smirnov",
year = "2017",
month = "9",
day = "1",
language = "English",
volume = "1864",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "RWTH Aahen University",

}

Chernishev, G, Galaktionov, V, Grigorev, V, Klyuchikov, E & Smirnov, K 2017, 'A study of PosDB performance in a distributed environment', CEUR Workshop Proceedings, vol. 1864.

A study of PosDB performance in a distributed environment. / Chernishev, George; Galaktionov, Vyacheslav; Grigorev, Valentin; Klyuchikov, Evgeniy; Smirnov, Kirill.

In: CEUR Workshop Proceedings, Vol. 1864, 01.09.2017.

Research output

TY - JOUR

T1 - A study of PosDB performance in a distributed environment

AU - Chernishev, George

AU - Galaktionov, Vyacheslav

AU - Grigorev, Valentin

AU - Klyuchikov, Evgeniy

AU - Smirnov, Kirill

PY - 2017/9/1

Y1 - 2017/9/1

N2 - PosDB is a new disk-based distributed column-store relational engine aimed for research purposes. It uses the Volcano pull-based model and late materialization for query processing, and join indexes for internal data representation. In its current state PosDB is capable of both local and distributed processing of all SSB (Star Schema Benchmark) queries. Data, as well as query plans, can be distributed among network nodes in our system. Data distribution is performed by horizontal partitioning. In this paper we experimentally evaluate the performance of our system in a distributed environment. We analyze system performance and report a number of metrics, such as speedup and scaleup. For our evaluation we use the standard benchmark - the SSB.

AB - PosDB is a new disk-based distributed column-store relational engine aimed for research purposes. It uses the Volcano pull-based model and late materialization for query processing, and join indexes for internal data representation. In its current state PosDB is capable of both local and distributed processing of all SSB (Star Schema Benchmark) queries. Data, as well as query plans, can be distributed among network nodes in our system. Data distribution is performed by horizontal partitioning. In this paper we experimentally evaluate the performance of our system in a distributed environment. We analyze system performance and report a number of metrics, such as speedup and scaleup. For our evaluation we use the standard benchmark - the SSB.

UR - http://www.scopus.com/inward/record.url?scp=85025131897&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85025131897

VL - 1864

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -

Chernishev G, Galaktionov V, Grigorev V, Klyuchikov E, Smirnov K. A study of PosDB performance in a distributed environment. CEUR Workshop Proceedings. 2017 Sep 1;1864.