Rethinking DRAM caching for LSMs in an NVRAM environment

Research output: Contribution to book/conference proceedings/anthology/reportConference contributionContributedpeer-review

Contributors

  • Lucas Lersch - , Chair of Databases, SAP Research (Author)
  • Ismail Oukid - , TUD Dresden University of Technology, SAP Research (Author)
  • Ivan Schreter - , SAP Research (Author)
  • Wolfgang Lehner - , Chair of Databases (Author)

Abstract

The rise of NVRAM technologies promises to change the way we think about system architectures. In order to fully exploit its advantages, it is required to develop systems specially tailored for NVRAM devices. Not only this imposes great challenges, but also developing full system architectures from scratch is undesirable in many scenarios due to prohibitive development costs. Instead, we analyze in this paper the behavior of an existing log-structured persistent key-value store, namely LevelDB, when run on top of an emulated NVRAM device. We investigate initial opportunities for improvement when adapting a system tailored for HDD/SSDs to run on top of an NVRAM environment. Furthermore, we analyze the behavior of the DRAM caching components of LevelDB and whether more suitable caching policies are required.

Details

Original languageEnglish
Title of host publicationAdvances in Databases and Information Systems - 21st European Conference, ADBIS 2017, Proceedings
EditorsMarite Kirikova, Kjetil Norvag, George A. Papadopoulos
PublisherSpringer, Berlin [u. a.]
Pages326-340
Number of pages15
ISBN (print)9783319669168
Publication statusPublished - 2017
Peer-reviewedYes

Publication series

SeriesLecture Notes in Computer Science, Volume 10509
ISSN0302-9743

Conference

Title21st European Conference on Advances in Databases and Information Systems
Abbreviated titleADBIS 2017
Conference number21
Duration24 - 27 September 2017
Website
LocationHilton Cyprus Hotel
CityNicosia
CountryCyprus

External IDs

ORCID /0000-0001-8107-2775/work/142253519

Keywords

Keywords

  • Caching, Log-structured merge-tree, Persistent memory, Storage

Library keywords