1 / 7

CS 268: Project Ideas

CS 268: Project Ideas. Kevin Lai Feb 6, 2002. Announcements. Summary submission method cp laik.jac88.html ~cs268/reviews chmod 755 ~cs268/reviews/laik.jac88.html No email summary submissions accepted after today. Simulation Benchmark. Motivation

nico
Télécharger la présentation

CS 268: Project Ideas

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. CS 268: Project Ideas Kevin Lai Feb 6, 2002

  2. Announcements • Summary submission method • cp laik.jac88.html ~cs268/reviews • chmod 755 ~cs268/reviews/laik.jac88.html • No email summary submissions accepted after today laik@cs.berkeley.edu

  3. Simulation Benchmark • Motivation • No standard benchmark for many classes of networking protocols: • e.g. transport protocols, active queue management, multicast, mobility • Prevents understanding of consequences of various approaches • Solution • Survey existing papers on a class of network protocols • Synthesize benchmark from previous experiments • Show validity of benchmark by replicating previous results laik@cs.berkeley.edu

  4. Applying Link Bandwidth Measurement to TCP seq seq loss retransmission Slow Start Slow Start Time Time regular TCP exit slow start early laik@cs.berkeley.edu

  5. Applying Link Bandwidth Measurement to TCP • Two problems with TCP slow start • can take a long time if bandwidth and/or latency are high • May loose entire window’s worth of packets at end of slow start • Solution • Use bottleneck link bandwidth measurement techniques to determine bottleneck link bandwidth • Skip slow start, open window to bandwidth • Don’t allow window to exceed bandwidth laik@cs.berkeley.edu

  6. Using FEC and Congestion Control • Motivation • Congestion losses and delays harm real time applications • Forward Error Correction allows trading bandwidth for reduction in loss • Congestion control allows hosts to safely consume more bandwidth • Solution • Do FEC over congestion control • Compare to router based solutions like Fair Queueing laik@cs.berkeley.edu

  7. Multipath Transport Protocols • Motivation • Many paths between host A and B in current Internet (multiple base stations, multihoming) • Don’t know characteristics of paths • Which one to use? • Use all of them • Must do so with congestion control • For n independent paths, get n speedup ? laik@cs.berkeley.edu

More Related