Tuning RED for Web Traffic
- M. Christiansen,
K. Jeffay,
D. Ott, and
F.D. Smith
- Proceedings of ACM SIGCOMM 2000, Stockholm, Sweden
- August-September 2000, pages 139-150.
- An expanded version of the paper also appeared in:
- IEEE/ACM Transactions on Networking,
- Volume 9, Number 3, (June 2001), pages 249-264.
ABSTRACT:
We study the effects of RED on the performance of Web browsing
with a novel aspect of our work being the use of a user-centric
measure of performance - response time for HTTP request-response
pairs. We empirically evaluate RED across a range of parameter
settings and offered loads. Our results show that:
- Contrary to expectations, compared to a FIFO queue, RED has a minimal
effect on HTTP response times for offered loads up to 90% of link
capacity,
- Response times at loads in this range are not
substantially effected by RED parameters,
- Between 90% and
100% load, RED can be carefully tuned to yield performance
somewhat superior to FIFO, however, response times are quite
sensitive to the actual RED parameter values selected, and
- In such heavily congested networks, RED parameters that provide the
best link utilization produce poorer response times.
We conclude
that for links carrying only web traffic, RED queue management
appears to provide no clear advantage over tail-drop FIFO for end-
user response times.
Two versions of this paper are available:
- The version as it apeared in the proceedings of ACM SIGCOMM 2000
(in
PostScript - or -
PDF
format), or
- The revised and extended version of the paper
(in
PostScript (compressed) - or -
PDF
format)
that appeared in IEEE/ACM Transactions on Networking.
A copy of the
slides for the talk presented at the conference is also available.
Back to the
Networking Research at UNC page.