Web Content Caching and Distribution (eBook)

Proceedings of the 8th International Workshop

Brian D. Davison, Fred Douglis (Herausgeber)

eBook Download: PDF

2007 | 1. Auflage
363 Seiten
Springer Netherlands (Verlag)
9781402022586 (ISBN)

Infos

Web caching and content delivery technologies provide the infrastructure on which systems are built for the scalable distribution of information. This proceedings of the eighth annual workshop, captures a cross-section of the latest issues and techniques of interest to network architects and researchers in large-scale content delivery. Topics covered include the distribution of streaming multimedia, edge caching and computation, multicast, delivery of dynamic content, enterprise content delivery, streaming proxies and servers, content transcoding, replication and caching strategies, peer-to-peer content delivery, and Web prefetching.

Web Content Caching and Distribution encompasses all areas relating to the intersection of storage and networking for Internet content services. The book is divided into eight parts: mobility, applications, architectures, multimedia, customization, peer-to-peer, performance and measurement, and delta encoding.  

Inhalt

Contents 6
A Message from the Workshop Chairs 10
Credits 12
Contributing Authors 14
Mobility-aware server selection for mobile streaming multimedia content distribution networks 18
1. Introduction and Overview 18
2. Mobility Based Server Selection 19
2.1 Layout of servers in content distribution network 20
2.2 Considerations in mobility based server selection 21
2.3 Measurement of mobility rate and server residence time estimation 21
2.4 Server load and QoS information collection 22
2.5 Server selection algorithm 23
3. Simulation Setup 25
3.1 Mobility simulation 26
3.2 CDN layout 27
3.3 Simulation scenarios 28
4. Results 30
5. Related Work 33
6. Conclusions 33
References 34
Performance of PEPs in cellular wireless networks 36
1. Introduction 36
2. RelatedWork 37
3. Overview of Cellular Networks 38
4. Wireless PEP 39
5. Latency Components 40
6. Transport/Session Optimizations 41
6.1 TCP Tuning 42
6.2 TCP Connection Sharing 45
6.3 Number of TCP connections 46
6.4 Temporal Block Flow Release 48
6.5 Session-level overheads: DNS 49
7. Application Level Optimizations 50
7.1 Compression Results 50
7.2 Acceleration Results 51
7.3 Impact of Pipelining 52
8. Comparison 53
9. Conclusions 54
References 55
Edge caching for directory based Web applications: Algorithms and performance 56
1. Introduction 56
2. Notations 58
3. LDAP Caching Framework 59
4. LDAP Query Containment 60
4.1 Query containment problem 60
4.2 General filter containment 60
4.3 Template based filter containment 61
4.4 Query containment algorithm 62
5. LDAP Caching Algorithms 63
6. Directory Server Extensions 65
7. Application Offload and Prefetching 66
7.1 Directory application modeling: Example 67
7.2 Prefetching 68
8. Performance of Caching Algorithms 68
9. Conclusions 71
References 72
Computing on the edge: A platform for replicating Internet applications 74
1. Introduction 74
2. Issues 75
3. Architecture Overview 76
4. Application Distribution Framework 77
4.1 The metafile 77
4.2 Replica creation 78
4.3 Replica deletion 79
4.4 Consistency maintenance 79
5. Algorithms 80
5.1 Content placement algorithm 81
5.2 Request distribution algorithm 83
6. Performance 85
6.1 Request distribution 85
6.2 Content placement 86
6.3 Redeployment threshold 89
7. RelatedWork 91
8. Conclusions 93
Acknowledgments 93
References 93
Scalable consistency maintenance for edge query caches: Exploiting templates in Web applications 96
1. Introduction 96
2. Semantic caching over theWeb 97
2.1 DBProxy overview 97
2.2 Common Local Store 98
3. Consistency Management 99
3.1 Update propagation approaches 100
4. Basic filtering 100
5. Template-based filtering 102
5.1 Template-based filtering: Single cache case 102
5.2 Template-based filtering: Multiple caches 105
6. Related work 106
7. Conclusions 106
References 107
Proxy+: Simple proxy augmentation for dynamic content processing 108
1. Introduction 108
2. Related Work 109
3. Summary of Previous Result 110
4. Proxy+ Architecture 111
4.1 ASP.NET output caching 112
4.2 Cache key generation 113
4.3 Tag generation and fragment caching 114
4.4 Cache keys notification and page composition 117
4.5 Summary of the protocol 119
5. Application Modifications 120
6. Experimental Results 122
7. Security aspect 124
8. Conclusions 124
References 125
Multicast cloud with integrated multicast and unicast content distribution routing 126
1. Introduction 126
3. Multicast Cloud 129
4. Integrated Channel Routing 130
5. Application-layer Traffic Control 132
6. Related Work 133
7. Conclusion 134
8. References 135
A large enterprise content distribution network: Design, implementation and operation 136
1. Introduction 136
2. Service Perspective and Network Infrastructure 137
3. CDN Architecture 138
3.1 Redirection System 140
4. CDN Operation and Lessons Learned 142
5. Related work 144
6. Conclusion and Future work 144
References 145
Architectural choices for video-on-demand systems 146
1. Introduction 146
2. Contribution and RelatedWork 147
3. The distribution network 148
4. Evaluation of Architectural Choices 148
4.1 Analytical model 148
4.2 Set-top box at the client side for pre.x storage 149
4.3 Use of satellite for suf.x transmission 152
5. Conclusion and FutureWork 153
References 155
Dynamic cache reconfiguration strategies for a cluster-based streaming proxy 156
1. Introduction 156
2. Architecture of cluster-based streaming proxy 158
3. Optimal Cache Placement 159
3.1 Optimal Cache Placement: Problem Formulation 159
3.2 Cache Placement Heuristics 160
4. Dynamic Cache Recon.guration 161
4.1 MWPM cache recon.guration 162
4.2 Swapping-based cache recon.guration 162
5. Performance Evaluation 164
5.1 Simulation setting 165
5.2 Evaluation of cache placement algorithms 165
5.3 Evaluation of cache reconfiguration algorithms 168
6. RelatedWork 172
7. Conclusions and future work 173
References 173
Stream engine: A new kernel interface for high-performance Internet 176
1. Introduction 176
2. Characteristics of Internet Streaming Protocols 177
3. Implementation Experience 178
3.1 Initial prototype 178
3.2 Identifying performance bottlenecks 179
4. The Stream Engine Interface 181
4.1 Definitions of a stream engine 181
4.2 Performance improvements from stream engine 183
5. Implications for TCP Offloading Hardware 183
6. RelatedWork 185
7. Conclusion and FutureWork 186
References 186
Streaming flow analyses for prefetching in segment-based proxy caching to improve delivery quality 188
1. Background and Motivation 188
2. Prefetching Methods for Segment-based Proxy Caching 190
2.1 Look-ahead window based prefetching method 191
2.2 Active prefetching method 193
3. Segment-based Proxy Caching Strategies with Least Proxy Jitter 196
3.1 Minimum number of segments cached for proxy jitter free 196
3.2 Trade-off between low proxy jitter and high byte hit ratio 197
4. Performance Evaluation 197
4.1 Workload summary 198
4.2 Exponential segmentation strategy 199
4.3 Uniform segmentation strategy 200
5. Conclusion 202
References 202
Subscription-enhanced content delivery 204
1. Introduction 204
2. Subscription-based content delivery 206
2.1 Access-based caching: the baseline approach 207
2.2 Single cache and single replacement method 207
2.3 Dual-caches approaches 209
3. Simulator and workload 210
3.1 Simulator and workload for news delivery 210
3.2 Generating subscription information 211
3.3 Tagging accesses as notification- driven or not 212
4. Experimental results 212
4.1 Metric and experimental setup 212
4.2 Comparing RSG2 and HUG 213
4.3 Behavior of DC- TA 214
4.4 Comparing SG1, HUG and DC 216
5. Related work 218
6. Conclusion 220
References 220
Cooperative architectures and algorithms for discovery and transcoding of multi-version content 222
1. Introduction 222
2. Related work 224
3. Main features of the intermediate infrastructure 225
4. Hierarchical topologies 226
5. Flat topologies 227
5.1 Cooperative discovery 227
5.2 Cooperative transcoding algorithms 228
6. Workload model 230
7. Experimental results 231
7.1 Comparison of the architectures 231
7.2 Cooperative transcoding algorithms 235
8. Conclusions 237
Acknowledgements 237
References 237
User specific request redirection in a content delivery network 240
1. Introduction 240
2. User Specific Request Redirection 241
2.1 Service differentiation based on user specific information 241
2.2 IP address based redirection 242
3. Implementing user specific request redirection 243
4. Request Defection 244
4.1 Step 1: A priori transformation of embedded URLs 244
4.2 Step 2: On-the-fly HTTP response header modification 245
4.3 Wire-speed request de.ection 246
4.4 Resolving server IP addresses 247
5. Conclusions 248
References 249
Friendships that last: Peer lifespan and its role in P2P protocols 250
1. Introduction 250
2. Background 251
2.1 Related work 252
3. Peer Lifespan Distribution 253
3.1 Collecting observed peers’ lifespans 253
3.2 Peer lifespan distribution 254
4. Peer Lifespan and P2P Protocols 256
4.1 Lifespan-based friend selection 256
4.2 Lifespan-based friend selection and recommendation 257
4.3 Taking available connections into consideration 257
5. Evaluation 257
5.1 Experimental setup 258
5.2 Comparison 260
6. Conclusions and FutureWork 261
Acknowledgments 262
References 262
A fine-grained peer sharing technique for delivering large media files over the Internet 264
1. Introduction 264
2. Fine-Grained Peer Sharing in CDNs 265
2.1 Peer sharing in CDNs 265
2.2 Fine-grained peer sharing 266
3. Communication Protocol and Scheduling Algorithm 267
3.1 Communication protocol 268
3.2 Scheduling algorithm 269
4. Performance Evaluation 270
5. RelatedWork 273
6. Concluding Remarks 273
References 273
Proxy-cache aware object bundling for Web access acceleration 274
1. Introduction 274
2. Existing Methods to Retrieve Embedded Objects 276
3. Traffic Characteristics of Embedded Objects 277
3.1 Number of embedded objects per page 277
3.2 Content of embedded objects 278
3.3 Sizes of embedded objects 278
3.4 Retrieval latency of embedded objects 279
4. Proxy-Cache Aware PC-Bundle Transfer of HTTP Messages 280
4.1 Basic mechanism 280
4.2 Assumptions 281
4.3 Detailed Specifications of Modifications to HTTP for 282
5. Experimental Results on PC-Bundle Mechanism 284
5.1 Environment of simulation 284
5.2 Results with respect to cache size 285
5.3 Results with respect to cache replacement policy 287
5.4 Results with respect to degree of parallelism 288
6. Conclusions 289
References 290
A case for dynamic selection of replication and caching strategies 292
1. Introduction 292
2. Evaluation methodology 293
2.1 Simulation model 293
2.2 Adaptation mechanisms 294
3. The Need for Dynamic Adaptation 295
4. Strategy Selection Heuristics 296
4.1 Performance evaluation metrics 296
4.2 Selection heuristics 297
5. Related work 298
6. Conclusions and FutureWork 299
References 299
Link prefetching in Mozilla: A server-driven approach 300
1. Introduction 300
2. Prefetching Directives 301
3. Determining When To Prefetch 303
4. Browser Imposed Restrictions 304
5. Identifying Prefetch Requests 305
6. Practical Limitations 305
7. Applications and Results 306
8. Conclusion 306
Acknowledgments 307
References 307
A generalized model for characterizing content modi.cation dynamics of Web objects 310
1. Introduction 310
2. Related Work 311
3. Modeling Content Modification Dynamics of Web Objects 312
3.1 Quantity matrix for content modification dynamics 312
3.2 Calculation of quantity matrix 313
4. Verification of Quantity Matrix for Content Modification Dynamics of Objects 316
5. Conclusions 317
References 317
Server-friendly delta compression for efficient Web access 320
1. Introduction 320
1.1 Delta compression for Web access 321
1.2 Discussion of known approaches 322
1.3 Our approach and contributions 323
2. Delta Compression Schemes for Site Visits 324
2.1 Reference file selection policies 324
2.2 Experimental setup 325
2.3 Experimental evaluation of policies 326
2.4 An efficient and nearly optimal protocol 330
2.5 Impact of duplicates 332
2.6 Summary of observations 333
3. Utility of rsync for Web Access 333
3.1 Experiments for related pages 334
3.2 Experiments for versions of a page 335
3.3 Discussion and a generalized approach 336
4. Concluding Remarks 338
Acknowledgements 338
References 338
Evaluation of ESI and class-based delta encoding 340
1. Introduction 340
2. ESI 341
3. A Page Content Model 342
4. The System Model 344
5. Simulation 345
6. ESI Simulation Results 346
6.1 Simulation Results - Online Bookstore’s Book Pages 346
6.2 Simulation Results - Other Resources 349
7. Class-Based Delta Encoding 351
7.1 System Model 351
8. Delta Encoding Simulation 352
8.1 Simulation Results - Online Bookstore 352
8.2 Simulation Results - My Page 353
8.3 Same-Base reply for Online Bookstore 353
9. Comparison of ESI and Class-Based DE 355
9.1 My Page Resource 355
9.2 Online Bookstore Resource 357
10. Additional Considerations 358
Acknowledgments 359
References 359
Author Index 362
More eBooks at www.ciando.com 0

Textauszug

SERVER-FRIENDLY DELTA COMPRESSION FOR EFFICIENT WEB ACCESS (p. 303-304)

Anubhav Savant and Torsten Suel
CIS Department, Polytechnic University


Abstract

A number of researchers have studied delta compression techniques for improving the efficiency of web page accesses over slow communication links. Most of these schemes exploit the fact that updated web pages often change only very slightly, thus resulting in very small sizes for the transmitted deltas. However, these schemes are only applicable to a minority of page accesses, and require web or proxy servers to retain potentially many different outdated versions of pages for use as reference files in the encoding. Another approach, studied by Chan and Woo [4], encodes a page with respect to similar files located on the same web server that are already in the client’s browser cache. Based on the latter approach, we study different delta compression policies for web access. Our emphasis is on web and proxy server-friendly policies that do not require the maintenance of multiple older versions of a page, but only use reference files accessed by the client within the last few minutes. We compare several policies for identifying appropriate reference files and evaluate their performance on a set of traces. We show that there are very simple policies that achieve significant benefits over gzip compression on most web accesses, and that can be efficiently implemented at web or proxy servers. We also study the potential of file synchronization techniques such as rsync [28] for web access.


1. Introduction

Delta compression (delta encoding) is the process of encoding a target file with respect to one or several, usually similar, referenceles. This encoding, called a delta, describes the target file in terms of the reference files, and a recipient that receives the encoding and already knows the reference files can thus efficiently reconstruct the target. Delta compression has numerous applications in scenarios where there are several versions of a file or many similar files, such as software revision control systems, distribution of software updates, content distribution networks, or efficient storage of related files. Several tools for delta compression, such as bdiff, vcdiff [10, 13], Xdelta [14], and zdelta [25], are freely available. We refer to [23] for an overview of delta compression techniques and applications.


1.1 Delta compression for Web access

A number of authors have proposed the use of delta compression techniques to improve the ef.ciency of web access [1, 4, 7, 9, 16, 17, 21, 27, 29]. In particular, when web pages are updated, they typically do not change by much, and thus delta compression can be used to very succinctly encode the difference between a new version of a web page and an outdated version already in the client’s browser cache. Most proposals focus on encodings between different versions located at the same URL, which results in small sizes for the deltas but is restricted to pages that have been previously visited by the client. One exception is the work by Chan andWoo [4], which proposes to use as reference files other pages on the same site recently visited by the client, which tend to have a significant degree of similarity due to common layout features and HTML structure. In general, delta compression schemes for web access can be distinguished along the following axes.

Produkt-Details

• Erscheint lt. Verlag: 8.5.2007
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Informatik ► Betriebssysteme / Server
• Themenwelt: Mathematik / Informatik ► Informatik ► Netzwerke
• Themenwelt: Mathematik / Informatik ► Informatik ► Theorie / Studium
• Themenwelt: Mathematik / Informatik ► Informatik ► Web / Internet
• Themenwelt: Informatik ► Weitere Themen ► Hardware
• Themenwelt: Technik ► Elektrotechnik / Energietechnik
• ISBN-13: 9781402022586 / 9781402022586