Skip to main content
USENIX
  • Conferences
  • Students
Sign in
  • Overview
  • Workshop Organizers
  • Workshop Program
  • Sponsorship
  • Instructions for Participants
  • Call for Papers
  • Past Workshops

sponsors

Bronze Sponsor
Bronze Sponsor
Bronze Sponsor

connect with us


  •  Twitter
  •  Facebook
  •  LinkedIn
  •  Google+
  •  YouTube

twitter

Tweets by @usenix

usenix conference policies

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

You are here

Home » Scalability! But at what COST?
Tweet

connect with us

Scalability! But at what COST?

Tuesday, May 19, 2015 - 9:30am-10:00am
Authors: 

Frank McSherry; Michael Isard; Derek G. Murray

Abstract: 

We offer a new metric for big data platforms, COST, or the Configuration that Outperforms a Single Thread. The COST of a given platform for a given problem is the hardware configuration required before the platform outperforms a competent single-threaded implementation. COST weighs a system’s scalability against the overheads introduced by the system, and indicates the actual performance gains of the system, without rewarding systems that bring substantial but parallelizable overheads.

We survey measurements of data-parallel systems recently reported in SOSP and OSDI, and find that many systems have either a surprisingly large COST, often hundreds of cores, or simply underperform one thread for all of their reported configurations.

Frank McSherry[node:field-speakers-institution]

Michael Isard[node:field-speakers-institution]

Derek G. Murray[node:field-speakers-institution]

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.

McSherry PDF
View the slides
  • Log in or    Register to post comments

Bronze Sponsors

© USENIX

  • Privacy Policy
  • Contact Us