Skip to main content
Back to USENIX
  • Conferences
  • Students
Sign in

USENIX Conference Policies

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

Partial Prefetch for Faster Surfing in Composite Hypermedia

In this paper we present a prefetch technique, which incorporates a scheme similar to data streaming to minimize the response-lag. Unlike previous all or none techniques, we propose partial prefetch where the size of the lead segment is computed optimally so that only a minimum but sufficient amount of data is prefetched and buffered. The remaining segment is fetched if and only when the media is traversed. Thus, it delivers content without any increase in perceived response delay, and at the same time drastically minimizes unnecessary pre-load. The paper presents the scheme in the context of surfing in composite multimedia documents. It presents the technique and optimization scheme used for stream segmentation backed by analytical model and statistical simulation. We report remarkable increase in the responsiveness of web systems by a factor of 2-15 based on the specific situation.

Javed I. Khan, Kent State University

Qingping Tao, Kent State University

BibTeX
@inproceedings {271042,
author = {Javed I. Khan and Qingping Tao},
title = {Partial Prefetch for Faster Surfing in Composite Hypermedia},
booktitle = {3rd USENIX Symposium on Internet Technologies and Systems (USITS 01)},
year = {2001},
address = {San Francisco, CA},
url = {https://www.usenix.org/conference/usits-01/partial-prefetch-faster-surfing-composite-hypermedia},
publisher = {USENIX Association},
month = mar
}
Download

Links

Paper: 
http://www.usenix.org/events/usits01/full_papers/khan/khan.pdf
Paper (HTML): 
http://www.usenix.org/events/usits01/full_papers/khan/khan_html/index.html
  • Log in or register to post comments

© USENIX
EIN 13-3055038

  • Privacy Policy
  • Contact Us