Aliasing occurs in Web transactions when requests containing different URLs elicit replies containing identical data payloads. Aliasing can cause cache misses, and there is reason to suspect that offthe-shelf Web authoring tools might increase aliasing on the Web. Existing research literature, however, says little about the prevalence of aliasing in user-initiated transactions or its impact on endto-end performance in large multi-level cache hierarchies. This paper quantifies the performance impact and extent of aliasing using a large client trace from WebTV Networks. Fewer than 5 % of reply payloads are aliased (referenced via multiple URLs) but over 54 % of successful transactions involve aliased payloads. Aliased payloads account for under 3.1 % of the trace’s “working set size ” (sum of payload sizes) but over 36 % of bytes transferred. Aliasing accounts for roughly 10 % of browser cache misses and 12–23 % of proxy misses in the workload studied, assuming infinite-capacity caches. The performance impact of aliasing is similar in a large proxy trace from Compaq Corporation. Aliasing does not entirely explain the large number of redundant proxy-to-browser payload transfers previously reported in the WebTV system. We consider other possible causes of redundant transfers (e.g., reply metadata and browser cache management policies) and discuss a simple hop-by-hop protocol extension that completely eliminates all redundant transfers, regardless of cause.
|
666
|
The Art of Computer Systems Performance Analysis
– Jain
- 1991
|
|
557
|
Generating Representative Web Workloads for Network and Server Performance Evaluation
– Barford, Crovella
- 1998
|
|
554
|
Web Caching and Zipf-like Distributions: Evidence and Implications
– Breslau, Cao, et al.
- 1999
|
|
255
|
Characteristics of WWW Client-based Traces
– Cunha, Bestavros, et al.
- 1995
|
|
251
|
Syntactic clustering of the Web
– Broder
- 1997
|
|
221
|
On the Scale and Performance of Cooperative Web Proxy Caching
– Wolman, Voelker, et al.
- 1999
|
|
206
|
System design issues for Internet middleware services: Deductions from a large client trace
– Gribble, Brewer
- 1997
|
|
199
|
Potential Benefits of Delta-encoding and Data Compression for HTTP
– Mogul, Douglis, et al.
- 1997
|
|
189
|
Rate of Change and other Metrics: a Live Study of the World Wide Web
– Douglis, Feldmann, et al.
- 1997
|
|
146
|
A low-bandwidth network file system
– Muthitacharoen, Chen, et al.
- 2001
|
|
124
|
Improving Web Server Performance by Caching Dynamic Data
– Iyengar, Challenger
- 1997
|
|
95
|
Characterizing Browsing Strategies
– Catledge, Pitkow
- 1995
|
|
91
|
How Dynamic is the Web
– Brewington, Cybenko
- 2000
|
|
82
|
Performance of web proxy caching in heterogeneous bandwidth environments
– Feldmann, Caceres, et al.
- 1999
|
|
79
|
Organization-based analysis of web-object sharing and caching
– Wolman, Voelker, et al.
- 1999
|
|
59
|
A ProtocolIndependent Technique for Eliminating Redundant Network Traffic
– Spring, Wetherall
- 2000
|
|
54
|
Towards a better understanding of web resources and server responses for improved caching
– Wills, C, et al.
- 1999
|
|
46
|
A comparison of techniques to find mirrored hosts on the WWW
– Bharat, Broder, et al.
- 2000
|
|
44
|
Finding near-replicas of documents on the web
– Shivakumar, Garcia-Molina
- 1998
|
|
43
|
Studying the impact of more complete server information on Web caching
– Wills, Mikhailov
- 2000
|
|
39
|
Workload characterization of a web proxy in a cable modem environment
– Arlitt, Friedrich, et al.
- 1999
|
|
36
|
Rfc 2616: Hypertext transfer protocol
– Fielding, Gettys, et al.
- 1999
|
|
35
|
mirror on the web: a study of host pairs with replicated content
– Mirror
- 1999
|
|
26
|
Thin-client Web access patterns: measurements from a cache-busting proxy
– Kelly
- 2001
|
|
25
|
Continuous online extraction of HTTP traces from packet traces
– Feldmann
- 1998
|
|
25
|
M.: Examining the cacheability of user-requested Web resources
– Wills, Mikhailov
- 1999
|
|
23
|
Web traffic logs: An imperfect resource for evaluation
– Davison
- 1999
|
|
21
|
The Medusa proxy: A tool for exploring user-perceived web performance
– Koletsou, Voelker
- 2001
|
|
18
|
Squeezing more bits out of http caches
– Mogul
- 2000
|
|
16
|
Increasing effective link bandwidth by suppressing replicated data
– Santos, Wetherall
- 1998
|
|
15
|
Errors in timestamp-based HTTP header values
– Mogul
- 1999
|
|
11
|
Replica-Aware Caching for Web Proxies
– Bahn, Lee, et al.
- 2002
|
|
11
|
PRO-COW: Protocol Compliance on the Web—A Longitudinal Study
– Krishnamurthy, Arlitt
- 2001
|
|
11
|
The HTTP distribution and replication protocol
– Hoff, Giannandrea, et al.
- 1997
|
|
10
|
Change and relationship-driven content caching, distribution and assembly
– Mikhailov, Wills
- 2001
|
|
9
|
A trace-based analysis of duplicate suppression in HTTP
– Mogul
- 1999
|
|
6
|
Observation of changing information sources
– Brewington
- 2000
|
|
6
|
HTTP 1.0 logs considered harmful
– Cáceres, Krishnamurthy, et al.
- 1998
|
|
6
|
The content and access dynamics of a busy Web server: Findings and implications
– Padmanabhan, Qiu
- 2000
|
|
5
|
Cachability of web objects
– Zhang
- 2000
|
|
4
|
Analyzing Web Robots and their Impact on Caching
– Almeida, Menasce, et al.
- 2001
|
|
4
|
Patent #6,292,880: “Alias-free content-indexed object cache
– S
- 2001
|
|
3
|
Improving proxy cache performance—analyzing three cache replacement policies
– Dilley, Arlitt
- 1999
|
|
2
|
White paper: Creating a cache-friendly Web site
– Corporation
- 2001
|
|
2
|
Squid cache revalidation and metadata updates. Posting tosquid-dev mailing list
– Nordstrom
- 2001
|
|
2
|
The third cache-off: The official report
– Rousskov, Wessels
- 2000
|
|
2
|
Exploiting result equivalence in caching dynamic content
– Smith, Acharya, et al.
- 1999
|
|
1
|
RFC 3143: Known HTTP proxy/caching problems
– Cooper, Dilley
- 2001
|
|
1
|
RFC 3229: Delta encoding in HTTP
– Mogul, Krishnamurthy, et al.
- 2002
|
