SwingDB: An Embedded In-memory DBMS Enabling Instant Snapshot Sharing

  • Qingzhong Meng
  • Xuan Zhou
  • Shiping Chen
  • Shan Wang
Conference paper

DOI: 10.1007/978-3-319-56111-0_8

Part of the Lecture Notes in Computer Science book series (LNCS, volume 10195)
Cite this paper as:
Meng Q., Zhou X., Chen S., Wang S. (2017) SwingDB: An Embedded In-memory DBMS Enabling Instant Snapshot Sharing. In: Blanas S., Bordawekar R., Lahiri T., Levandoski J., Pavlo A. (eds) Data Management on New Hardware. IMDM 2016, ADMS 2016. Lecture Notes in Computer Science, vol 10195. Springer, Cham

Abstract

Data transmission between an in-memory DBMS and a data analytical program is usually slow, partially due to the inadequate IPC support of modern operating systems. In this paper, we present SWING, a novel inter-process data sharing mechanism of OS, which allows processes to share physical memory through an instant system call. Based on SWING, we develop an embedded in-memory DBMS called SwingDB, which enables data analytical applications to access databases in their own memory space, instead of resorting to traditional inter-process communication. Extensive experiments were conducted to demonstrate the advantage of such a DBMS-OS co-design.

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Qingzhong Meng
    • 1
  • Xuan Zhou
    • 1
  • Shiping Chen
    • 2
  • Shan Wang
    • 1
  1. 1.MOE Key Laboratory of DEKERenmin University of ChinaBeijingChina
  2. 2.CSIRO Data61EppingAustralia

Personalised recommendations