MacroDB: Scaling Database Engines on Multicores

João Manuel dos Santos Lourenço; Nuno Manuel Ribeiro Preguiça

doi:10.1007/978-3-642-40047-6_61

MacroDB: Scaling Database Engines on Multicores

João Manuel dos Santos Lourenço, Nuno Manuel Ribeiro Preguiça

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Multicore processors are available for over a decade, but general purpose database management systems (DBMS) still cannot fully explore the computational resources of these platforms. This paper explores a simple and easy to deploy approach for improving DBMS performance in multicore platforms, by maintaining multiple database engines running in parallel, rather than a single instance, thus circumventing the increase in contention due to load interactions. Unlike previous works, we focus on in-memory DBMS, exploring different design solutions that combine distributed systems and concurrent programming techniques. We show that we are able to improve performance over standalone solutions, without modifying either database or application code, by up to 3 times while minimizing response times.

Original language	Unknown
Title of host publication	Lecture Notes in Computer Science
Editors	F Wolf, B Mohr, D Mey
Publisher	Springer Berlin Heidelberg
Pages	607-619
Volume	8097
ISBN (Print)	978-3-642-40046-9
DOIs	https://doi.org/10.1007/978-3-642-40047-6_61
Publication status	Published - 1 Jan 2013
Event	Euro-Par - International European Conference on Parallel and Distributed Computing - Duration: 1 Jan 2013 → …

Conference

Conference	Euro-Par - International European Conference on Parallel and Distributed Computing
Period	1/01/13 → …

Access to Document

10.1007/978-3-642-40047-6_61

http://dx.doi.org/10.1007/978-3-642-40047-6_61

Cite this

@inproceedings{7383f8d05cef4f91a3beedda3623a25e,

title = "MacroDB: Scaling Database Engines on Multicores",

abstract = "Multicore processors are available for over a decade, but general purpose database management systems (DBMS) still cannot fully explore the computational resources of these platforms. This paper explores a simple and easy to deploy approach for improving DBMS performance in multicore platforms, by maintaining multiple database engines running in parallel, rather than a single instance, thus circumventing the increase in contention due to load interactions. Unlike previous works, we focus on in-memory DBMS, exploring different design solutions that combine distributed systems and concurrent programming techniques. We show that we are able to improve performance over standalone solutions, without modifying either database or application code, by up to 3 times while minimizing response times.",

author = "Louren{\c c}o, {Jo{\~a}o Manuel dos Santos} and Pregui{\c c}a, {Nuno Manuel Ribeiro}",

year = "2013",

month = jan,

day = "1",

doi = "10.1007/978-3-642-40047-6_61",

language = "Unknown",

isbn = "978-3-642-40046-9",

volume = "8097",

pages = "607--619",

editor = "F Wolf and B Mohr and D Mey",

booktitle = "Lecture Notes in Computer Science",

publisher = "Springer Berlin Heidelberg",

note = "null ; Conference date: 01-01-2013",

}

TY - GEN

T1 - MacroDB: Scaling Database Engines on Multicores

AU - Lourenço, João Manuel dos Santos

AU - Preguiça, Nuno Manuel Ribeiro

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Multicore processors are available for over a decade, but general purpose database management systems (DBMS) still cannot fully explore the computational resources of these platforms. This paper explores a simple and easy to deploy approach for improving DBMS performance in multicore platforms, by maintaining multiple database engines running in parallel, rather than a single instance, thus circumventing the increase in contention due to load interactions. Unlike previous works, we focus on in-memory DBMS, exploring different design solutions that combine distributed systems and concurrent programming techniques. We show that we are able to improve performance over standalone solutions, without modifying either database or application code, by up to 3 times while minimizing response times.

AB - Multicore processors are available for over a decade, but general purpose database management systems (DBMS) still cannot fully explore the computational resources of these platforms. This paper explores a simple and easy to deploy approach for improving DBMS performance in multicore platforms, by maintaining multiple database engines running in parallel, rather than a single instance, thus circumventing the increase in contention due to load interactions. Unlike previous works, we focus on in-memory DBMS, exploring different design solutions that combine distributed systems and concurrent programming techniques. We show that we are able to improve performance over standalone solutions, without modifying either database or application code, by up to 3 times while minimizing response times.

U2 - 10.1007/978-3-642-40047-6_61

DO - 10.1007/978-3-642-40047-6_61

M3 - Conference contribution

SN - 978-3-642-40046-9

VL - 8097

SP - 607

EP - 619

BT - Lecture Notes in Computer Science

A2 - Wolf, F

A2 - Mohr, B

A2 - Mey, D

PB - Springer Berlin Heidelberg

Y2 - 1 January 2013

ER -