Transcript PPT
On the Effect of Server Adaptation
for Web Content Delivery
Yin Zhang (AT&T)
Joint work with
Balachander Krishnamurthy (AT&T)
Craig Wills (WPI)
IMW ’02, Marseille, Nov. 2002
Motivation
Web sites have a strong
incentive to reduce
time-to-glass
Challenge
Internet
Natural solution –
server adaptation
foobar.com
11/8/2002
client connectivity is
heterogeneous
IMW 2002
client connectivity +
content characteristics +
client capability +
server load + …
action to take
2
Study: What?
Basic question – What exactly is the
performance impact of server adaptation?
When and how much can server adaptation help?
Which action should the server take?
Lots of previous work … but typically
focusing on one individual action
This study –
Provides a unified framework for assessing the
impact of different server actions
Obtains useful insights through multi-site widearea measurements
11/8/2002
IMW 2002
3
Factors Considered
Client connectivity
Latency, bandwidth
Content characteristics
Criteria: total bytes, container bytes, #objects
3x3x3 = 27 buckets
derived from large proxy logs
further justified by examining popular Websites’ pages
Server actions
Altering the content
Altering the location of the content
compression, bundling
Altering protocol options
using a Content Distribution Network (CDN)
Altering manner of delivery
reducing number of images, reducing image size
using persistent connections
Combination of different actions
11/8/2002
IMW 2002
4
Experiment Methodology
350 uk.icir
uk.wpi
300
A multi-site study
Server: Apache
Round-Trip Time (ms)
250
modem.icir
au.wpi
Client: httperf
200
au.icir
modem.wpi
150
de.icir
isdn.icir
100
att.icir de.wpi
0
20
11/8/2002
40
100
80
60
Throughput (KB/sec)
att.wpi(462.6)
140
120
IMW 2002
US: att, modem, isdn
Intl: de, au, uk
Canonical content served
at each site
isdn.wpi
50
0
West coast: icir
East coast: wpi
covering the space of
buckets
Experiments repeated at
different times of day
5
Results
Compression of HTML is not universally useful
Persistent connections alone has limited benefit
Exception: bandwidth-constrained clients
Bundling gives significant improvement
Little improvement for all client/server combo
Pipelining gives significant improvement
It only works for bandwidth-constrained clients
Bundling alone is similar to pipelining
Compressed bundles help a lot under all conditions
CDN-served bundles – good idea for well-connected clients
Reducing image size by half has little benefit
Reducing the number of objects by half helps a lot
under most conditions
Baseline: 4 parallel HTTP/1.0 connections
11/8/2002
IMW 2002
6
Contribution and Further Work
Contribution
A unified framework for evaluating the impact
of server adaptation
Can be applied by individual Web site
Insights we gained can be useful for improving
client performance
Further work
Evaluation of the feasibility of online client
classification and server adaptation through
real implementation
11/8/2002
Our results are encouraging
IMW 2002
7
Acknowledgments
People who gave us accounts / logs
11/8/2002
IMW 2002
8