Pub Date : 2003-06-23DOI: 10.1109/WIAPP.2003.1210298
George Candea, Mauricio Delgado, Michael Chen, A. Fox
Automatic failure-path inference (AFPI) is an application-generic, automatic technique for dynamically discovering the failure dependency graphs of componentized Internet applications. AFPI's first phase is invasive, and relies on controlled fault injection to determine failure propagation; this phase requires no a priori knowledge of the application and takes on the order of hours to run. Once the system is deployed in production, the second, noninvasive phase of AFPI passively monitors the system, and updates the dependency graph as new failures are observed. This process is a good match for the perpetually-evolving software found in Internet systems; since no performance overhead is introduced, AFPI is feasible for live systems. We applied AFPI to J2EE and tested it by injecting Java exceptions into an e-commerce application and an online auction service. The resulting graphs of exception propagation are more detailed and accurate than what could be derived by time-consuming manual inspection or analysis of readily-available static application descriptions.
{"title":"Automatic failure-path inference: a generic introspection technique for Internet applications","authors":"George Candea, Mauricio Delgado, Michael Chen, A. Fox","doi":"10.1109/WIAPP.2003.1210298","DOIUrl":"https://doi.org/10.1109/WIAPP.2003.1210298","url":null,"abstract":"Automatic failure-path inference (AFPI) is an application-generic, automatic technique for dynamically discovering the failure dependency graphs of componentized Internet applications. AFPI's first phase is invasive, and relies on controlled fault injection to determine failure propagation; this phase requires no a priori knowledge of the application and takes on the order of hours to run. Once the system is deployed in production, the second, noninvasive phase of AFPI passively monitors the system, and updates the dependency graph as new failures are observed. This process is a good match for the perpetually-evolving software found in Internet systems; since no performance overhead is introduced, AFPI is feasible for live systems. We applied AFPI to J2EE and tested it by injecting Java exceptions into an e-commerce application and an online auction service. The resulting graphs of exception propagation are more detailed and accurate than what could be derived by time-consuming manual inspection or analysis of readily-available static application descriptions.","PeriodicalId":179377,"journal":{"name":"Proceedings the Third IEEE Workshop on Internet Applications. WIAPP 2003","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116397671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-06-23DOI: 10.1109/WIAPP.2003.1210295
Nathaniel Leibowitz
Internet traffic is experiencing a shift from Web traffic to file swapping traffic. Today a significant part of Internet traffic is generated by peer-to-peer applications, mostly by the popular Kazaa application. Yet, to date, few studies analyze Kazaa traffic, thus leaving the bulk of Internet traffic in dark. We present a large-scale investigation of Kazaa traffic based on logs collected at a large Israeli ISP, which capture roughly a quarter of all traffic between Israel and US.
{"title":"Deconstructing the Kazaa network","authors":"Nathaniel Leibowitz","doi":"10.1109/WIAPP.2003.1210295","DOIUrl":"https://doi.org/10.1109/WIAPP.2003.1210295","url":null,"abstract":"Internet traffic is experiencing a shift from Web traffic to file swapping traffic. Today a significant part of Internet traffic is generated by peer-to-peer applications, mostly by the popular Kazaa application. Yet, to date, few studies analyze Kazaa traffic, thus leaving the bulk of Internet traffic in dark. We present a large-scale investigation of Kazaa traffic based on logs collected at a large Israeli ISP, which capture roughly a quarter of all traffic between Israel and US.","PeriodicalId":179377,"journal":{"name":"Proceedings the Third IEEE Workshop on Internet Applications. WIAPP 2003","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116364598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-06-23DOI: 10.1109/WIAPP.2003.1210294
A. T. Mizrak, Yuchung Cheng, Vineet Kumar, S. Savage
Peer-to-peer (P2P) systems are typically divided into those that centralize lookup functionality in a single location and those that distribute the lookup operation across the set of participating hosts. The former approach can offer constant time lookup latency, but is more expensive to scale and suffers from single points of failure. In contrast, the fully distributed approach is easier to scale and can be more resilient to failures, but the lookup latency scales as a function of the total number of participants. While the research community has made great progress in improving the latency of distributed lookup, these systems, exemplified by Chord[I. Stoica et al., (2001)] typically require O(logN) hops to locate an object in a system with N hosts. We explore the costs and benefits of a new hybrid approach that partially distributes lookup information among a dynamically adjusted set of high-capacity "superpeers". This design exploits the resource heterogeneity inherent in existing P2P systems to provide many of the advantages of a centralized system, even while avoiding most of the problems associated with such systems. Lookup is performed using superpeers in constant-time, and the system performs well even in the event of simultaneous super-peer failures. Finally, while our gain in performance is potentially at the expense of scalability, we will show that a straightforward implementation should be able to scale to over one million peers with reasonable lookup rates.
{"title":"Structured superpeers: leveraging heterogeneity to provide constant-time lookup","authors":"A. T. Mizrak, Yuchung Cheng, Vineet Kumar, S. Savage","doi":"10.1109/WIAPP.2003.1210294","DOIUrl":"https://doi.org/10.1109/WIAPP.2003.1210294","url":null,"abstract":"Peer-to-peer (P2P) systems are typically divided into those that centralize lookup functionality in a single location and those that distribute the lookup operation across the set of participating hosts. The former approach can offer constant time lookup latency, but is more expensive to scale and suffers from single points of failure. In contrast, the fully distributed approach is easier to scale and can be more resilient to failures, but the lookup latency scales as a function of the total number of participants. While the research community has made great progress in improving the latency of distributed lookup, these systems, exemplified by Chord[I. Stoica et al., (2001)] typically require O(logN) hops to locate an object in a system with N hosts. We explore the costs and benefits of a new hybrid approach that partially distributes lookup information among a dynamically adjusted set of high-capacity \"superpeers\". This design exploits the resource heterogeneity inherent in existing P2P systems to provide many of the advantages of a centralized system, even while avoiding most of the problems associated with such systems. Lookup is performed using superpeers in constant-time, and the system performs well even in the event of simultaneous super-peer failures. Finally, while our gain in performance is potentially at the expense of scalability, we will show that a straightforward implementation should be able to scale to over one million peers with reasonable lookup rates.","PeriodicalId":179377,"journal":{"name":"Proceedings the Third IEEE Workshop on Internet Applications. WIAPP 2003","volume":"586 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132508894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-06-23DOI: 10.1109/WIAPP.2003.1210299
Shi-Cho Cha, Yuh-Jzer Joung, Y. Lue
We propose personal data backbone (PDB) to provide universal profile services over peer-to-peer networks. The main objective is to bring the control of personal data back to their owners. By using peer-to-peer technology, people can collaborate with one another to establish the services without resorting to a centralized mechanism or corporation, thereby removing concerns such as privacy, security, and monopoly. The peer-to-peer technology also achieves better trust, availability, accountability, and reliability, as compared to the centralized ones.
{"title":"Building universal profile systems over a peer-to-peer network","authors":"Shi-Cho Cha, Yuh-Jzer Joung, Y. Lue","doi":"10.1109/WIAPP.2003.1210299","DOIUrl":"https://doi.org/10.1109/WIAPP.2003.1210299","url":null,"abstract":"We propose personal data backbone (PDB) to provide universal profile services over peer-to-peer networks. The main objective is to bring the control of personal data back to their owners. By using peer-to-peer technology, people can collaborate with one another to establish the services without resorting to a centralized mechanism or corporation, thereby removing concerns such as privacy, security, and monopoly. The peer-to-peer technology also achieves better trust, availability, accountability, and reliability, as compared to the centralized ones.","PeriodicalId":179377,"journal":{"name":"Proceedings the Third IEEE Workshop on Internet Applications. WIAPP 2003","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115383885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-06-23DOI: 10.1109/WIAPP.2003.1210282
A. Broido, E. Nemeth, K. Claffy
We study attempts to dynamically update DNS records for private (RFC1918) addresses, by analyzing the frequency spectrum of updates observed at an authoritative nameserver for these addresses. We developed a binary autocorrelation algorithm and discovered that updates come in infinite series with periods of 60 or 75 minutes. We identify both periods as default settings of out-of-the-box Microsoft Windows 2000 and XP DNS software. Identifying this common property of end-user environments helps to understand users' behavior on the Internet. To our knowledge this is the first study of the global impact of dynamic DNS.
我们研究了动态更新私有(RFC1918)地址的DNS记录的尝试，通过分析在权威名称服务器上观察到的这些地址的更新频谱。我们开发了一种二值自相关算法，发现更新以无限级数出现，周期为60或75分钟。我们将这两个时期确定为开箱即用的Microsoft Windows 2000和XP DNS软件的默认设置。识别最终用户环境的这一共同属性有助于理解用户在Internet上的行为。据我们所知，这是第一次对动态DNS的全球影响进行研究。
{"title":"Spectroscopy of private DNS update sources","authors":"A. Broido, E. Nemeth, K. Claffy","doi":"10.1109/WIAPP.2003.1210282","DOIUrl":"https://doi.org/10.1109/WIAPP.2003.1210282","url":null,"abstract":"We study attempts to dynamically update DNS records for private (RFC1918) addresses, by analyzing the frequency spectrum of updates observed at an authoritative nameserver for these addresses. We developed a binary autocorrelation algorithm and discovered that updates come in infinite series with periods of 60 or 75 minutes. We identify both periods as default settings of out-of-the-box Microsoft Windows 2000 and XP DNS software. Identifying this common property of end-user environments helps to understand users' behavior on the Internet. To our knowledge this is the first study of the global impact of dynamic DNS.","PeriodicalId":179377,"journal":{"name":"Proceedings the Third IEEE Workshop on Internet Applications. WIAPP 2003","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122899256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-06-23DOI: 10.1109/WIAPP.2003.1210285
G. Pierre, M. van Steen
Replicating Web documents at a worldwide scale can help reduce user-perceived latency and wide-area network traffic. We present the design and implementation of Globule, a platform that allows Web server administrators to organize a decentralized replication service by trading Web hosting resources with each other. Globule automates all aspects of such replication: document replication, selection of the most appropriate replication strategies on a per-document basis, consistency management and transparent redirection of clients to replicas. To facilitate the transition from a nonreplicated server to a replicated one, we designed Globule as a module for the Apache Web server. Therefore, converting Web documents should require no more than compiling a new module into Apache and editing a configuration file.
{"title":"Design and implementation of a user-centered content distribution network","authors":"G. Pierre, M. van Steen","doi":"10.1109/WIAPP.2003.1210285","DOIUrl":"https://doi.org/10.1109/WIAPP.2003.1210285","url":null,"abstract":"Replicating Web documents at a worldwide scale can help reduce user-perceived latency and wide-area network traffic. We present the design and implementation of Globule, a platform that allows Web server administrators to organize a decentralized replication service by trading Web hosting resources with each other. Globule automates all aspects of such replication: document replication, selection of the most appropriate replication strategies on a per-document basis, consistency management and transparent redirection of clients to replicas. To facilitate the transition from a nonreplicated server to a replicated one, we designed Globule as a module for the Apache Web server. Therefore, converting Web documents should require no more than compiling a new module into Apache and editing a configuration file.","PeriodicalId":179377,"journal":{"name":"Proceedings the Third IEEE Workshop on Internet Applications. WIAPP 2003","volume":"239 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133690377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-06-23DOI: 10.1109/WIAPP.2003.1210288
V. Cardellini, M. Colajanni, R. Lancellotti, P. Yu
The large variety of devices that are gaining access to the Internet requires novel server functionalities to tailor Web content at run-time, namely transcoding. Traditional schemes assign transcoding operations to the Web server or single edge proxies. We propose an alternative architecture consisting of cooperative proxy servers which collaborate in discovering and transcoding multiple versions of Web objects. The transcoding functionality opens an entirely new space of investigation in the research area of cache cooperation, because it transforms the proxy servers from content repositories into pro-active network elements providing computation and adaptive delivery. We investigate and evaluate experimentally different schemes for cooperative discovery of multiversion content and transcoding in the context of a flat topology of edge servers.
{"title":"A distributed architecture of edge proxy servers for cooperative transcoding","authors":"V. Cardellini, M. Colajanni, R. Lancellotti, P. Yu","doi":"10.1109/WIAPP.2003.1210288","DOIUrl":"https://doi.org/10.1109/WIAPP.2003.1210288","url":null,"abstract":"The large variety of devices that are gaining access to the Internet requires novel server functionalities to tailor Web content at run-time, namely transcoding. Traditional schemes assign transcoding operations to the Web server or single edge proxies. We propose an alternative architecture consisting of cooperative proxy servers which collaborate in discovering and transcoding multiple versions of Web objects. The transcoding functionality opens an entirely new space of investigation in the research area of cache cooperation, because it transforms the proxy servers from content repositories into pro-active network elements providing computation and adaptive delivery. We investigate and evaluate experimentally different schemes for cooperative discovery of multiversion content and transcoding in the context of a flat topology of edge servers.","PeriodicalId":179377,"journal":{"name":"Proceedings the Third IEEE Workshop on Internet Applications. WIAPP 2003","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127233764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-06-23DOI: 10.1109/WIAPP.2003.1210292
Jiang Lan, Xiaotao Liu, P. Shenoy, K. Ramamritham
While the current generation of peer-to-peer networks share predominantly static files, future peer-to-peer networks will support sharing of files that are modified frequently by their users. We present techniques to maintain temporal consistency of replicated files in a peer-to-peer network. We consider the Gnutella P2P network and present techniques for maintaining consistency in Gnutella even when peers containing replicated files dynamically join and leave the network. An experimental evaluation of our techniques shows that: (i) a hybrid approach based on push and pull achieves high fidelity in highly dynamic P2P networks and (ii) the run-time overheads of our techniques are small, making them a practical choice for P2P networks.
{"title":"Consistency maintenance in peer-to-peer file sharing networks","authors":"Jiang Lan, Xiaotao Liu, P. Shenoy, K. Ramamritham","doi":"10.1109/WIAPP.2003.1210292","DOIUrl":"https://doi.org/10.1109/WIAPP.2003.1210292","url":null,"abstract":"While the current generation of peer-to-peer networks share predominantly static files, future peer-to-peer networks will support sharing of files that are modified frequently by their users. We present techniques to maintain temporal consistency of replicated files in a peer-to-peer network. We consider the Gnutella P2P network and present techniques for maintaining consistency in Gnutella even when peers containing replicated files dynamically join and leave the network. An experimental evaluation of our techniques shows that: (i) a hybrid approach based on push and pull achieves high fidelity in highly dynamic P2P networks and (ii) the run-time overheads of our techniques are small, making them a practical choice for P2P networks.","PeriodicalId":179377,"journal":{"name":"Proceedings the Third IEEE Workshop on Internet Applications. WIAPP 2003","volume":"267 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133713674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-06-23DOI: 10.1109/WIAPP.2003.1210283
R. Doshi, P. Cao
Despite the rising popularity of streaming media in corporations, there is little understanding of how streaming traffic interacts with other corporate network traffic over low-bandwidth WAN links. We used simulations to study the issue, and found that the buffer-based rate adaptation algorithms used in popular streaming applications is effective at making the streaming traffic behave in a fair manner, even when UDP is used as the transport. The congestion control is affected by the buffer size: small buffers make the streaming application timid and large buffers make it more aggressive. However, regardless of the buffer size, the streaming traffic can be adversely affected by multisession TCP traffic such as Web traffic, and other QoS mechanisms are needed to preserve streaming quality in this case.
{"title":"Streaming traffic fairness over low bandwidth WAN links","authors":"R. Doshi, P. Cao","doi":"10.1109/WIAPP.2003.1210283","DOIUrl":"https://doi.org/10.1109/WIAPP.2003.1210283","url":null,"abstract":"Despite the rising popularity of streaming media in corporations, there is little understanding of how streaming traffic interacts with other corporate network traffic over low-bandwidth WAN links. We used simulations to study the issue, and found that the buffer-based rate adaptation algorithms used in popular streaming applications is effective at making the streaming traffic behave in a fair manner, even when UDP is used as the transport. The congestion control is affected by the buffer size: small buffers make the streaming application timid and large buffers make it more aggressive. However, regardless of the buffer size, the streaming traffic can be adversely affected by multisession TCP traffic such as Web traffic, and other QoS mechanisms are needed to preserve streaming quality in this case.","PeriodicalId":179377,"journal":{"name":"Proceedings the Third IEEE Workshop on Internet Applications. WIAPP 2003","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114622079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-06-23DOI: 10.1109/WIAPP.2003.1210287
Vikrant Mastoli, V. Desai, Weisong Shi
The increasing mismatch between the low-bandwidth, resource characteristics of wireless mobile devices and the high-bandwidth expectations of many content-rich services drives the demand for deploying content-oriented services along the data path between the end users and the content servers. We argue that the idea of extending existing caching proxies to support these services is promising. This suggests extending the proxy caches for more than just their original intended purpose, that is the creation of an execution environment within them, which allows the execution of services locally and remotely. We describe the design, implementation and evaluation of a service execution environment (SEE) in the context of the CONCA proxy cache. We also compare the performance of Simple Object Access Protocol (SOAP) and Internet Content Adaptation Protocol (ICAP) by using them as call-out protocols between SEE and the service providers.
{"title":"SEE: a service execution environment for edge services","authors":"Vikrant Mastoli, V. Desai, Weisong Shi","doi":"10.1109/WIAPP.2003.1210287","DOIUrl":"https://doi.org/10.1109/WIAPP.2003.1210287","url":null,"abstract":"The increasing mismatch between the low-bandwidth, resource characteristics of wireless mobile devices and the high-bandwidth expectations of many content-rich services drives the demand for deploying content-oriented services along the data path between the end users and the content servers. We argue that the idea of extending existing caching proxies to support these services is promising. This suggests extending the proxy caches for more than just their original intended purpose, that is the creation of an execution environment within them, which allows the execution of services locally and remotely. We describe the design, implementation and evaluation of a service execution environment (SEE) in the context of the CONCA proxy cache. We also compare the performance of Simple Object Access Protocol (SOAP) and Internet Content Adaptation Protocol (ICAP) by using them as call-out protocols between SEE and the service providers.","PeriodicalId":179377,"journal":{"name":"Proceedings the Third IEEE Workshop on Internet Applications. WIAPP 2003","volume":"1995 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122217265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：