Skip to main content
USENIX
  • Conferences
  • Students
Sign in
  • FAST '13 Home
  • Organizers
  • Registration Information
  • Registration Discounts
  • At a Glance
  • Calendar
  • Training Program
  • Technical Sessions
  • Purchase the Box Set
  • Posters and WiPs
  • Birds-of-a-Feather Sessions
  • Sponsors
  • Activities
  • Hotel and Travel Information
  • Services
  • Students
  • Questions
  • Help Promote
  • For Participants
  • Call for Papers
  • Past Proceedings

sponsors

Platinum Sponsor
Gold Sponsor
Gold Sponsor
Gold Sponsor
Silver Sponsor
Silver Sponsor
Silver Sponsor
Bronze Sponsor
Bronze Sponsor
Bronze Sponsor
Bronze Sponsor
Bronze Sponsor
General Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Media Sponsor
Industry Partner

twitter

Tweets by @usenix

usenix conference policies

  • Event Code of Conduct
  • Conference Network Policy
  • Statement on Environmental Responsibility Policy

You are here

Home » Building Workload-Independent Storage with VT-Trees
Tweet

connect with us

http://twitter.com/usenix
https://www.facebook.com/usenixassociation
http://www.linkedin.com/groups?home=&gid=49559
http://www.youtube.com/user/USENIXAssociation

Building Workload-Independent Storage with VT-Trees

Authors: 

Pradeep Shetty, Richard Spillane, Ravikant Malpani, Binesh Andrews, Justin Seyster, and Erez Zadok, Stony Brook University

Abstract: 

As the Internet and the amount of data grows, the variability of data sizes grows too—from small MP3 tags to large VM images. With applications using increasingly more complex queries and larger data-sets, data access patterns have become more complex and randomized. Current storage systems focus on optimizing for one band of workloads at the expense of other workloads due to limitations in existing storage system data structures. We designed a novel workload-independent data structure called the VT-tree  which extends the LSM-tree to efficiently handle sequential and file-system workloads. We designed a system based solely on VT-trees which offers concurrent access to data via file system and database APIs, transactional guarantees, and consequently provides efficient and scalable access to both large and small data items regardless of the access pattern. Our evaluation shows that our user-level system has 2–6.6  better performance for random-write workloads and only a small average overhead for other workloads.

Pradeep J. Shetty, Stony Brook University

Richard P. Spillane, Stony Brook University

Ravikant R. Malpani, Stony Brook University

Binesh Andrews, Stony Brook University

Justin Seyster, Stony Brook University

Erez Zadok, Stony Brook University

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {180725,
author = {Pradeep J. Shetty and Richard P. Spillane and Ravikant R. Malpani and Binesh Andrews and Justin Seyster and Erez Zadok},
title = {Building {Workload-Independent} Storage with {VT-Trees}},
booktitle = {11th USENIX Conference on File and Storage Technologies (FAST 13)},
year = {2013},
isbn = {978-1-931971-99-7},
address = {San Jose, CA},
pages = {17--30},
url = {https://www.usenix.org/conference/fast13/technical-sessions/presentation/shetty},
publisher = {USENIX Association},
month = feb
}
Download
Shetty PDF
View the slides

Presentation Video 

Presentation Audio

MP3 Download

Download Audio

  • Log in or    Register to post comments

Platinum Sponsors

Gold Sponsors

Silver Sponsors

Bronze Sponsors

General Sponsors

Media Sponsors & Industry Partners

© USENIX

  • Privacy Policy
  • Contact Us