An Analysis of Internet Content Delivery Systems

Total Page:16

File Type:pdf, Size:1020Kb

An Analysis of Internet Content Delivery Systems An Analysis of Internet Content Delivery Systems S. Saroiu, K. P. Gummadi, R. J. Dunn, S. D. Gribble, and H. M. Levy Department of Computre Science & Engineering University of Washington 2008. 11. 27 Kyusik Kim Wireless Networks lab Contents Introduction Overview of Content Delivery Systems WWW, Content delivery networks (CDNs), peer-to-peer systems (P2P) Measurement Methodology High-Level Data Characteristics Detailed Content Delivery Characteristics objects, clients, servers, scalability of P2P systems The Potential Role of Caching in CDNs and P2P Conclusion 1 Wireless Networks Lab. Introduction (1) Purpose Examining content delivery traffic HTTP web Akamai content delivery network p2p file sharing systems Gnutella, Kazza Providing a detailed characterization and comparison of content delivery systems analyzing a nine day trace (incoming and outgoing Internet traffic at University of Washington) over 500 million transactions and over 20 terabytes of HTTP data 2 Wireless Networks Lab. Introduction (2) Results quantify the extent to which p2p traffic has overwhelmed web traffic as a leading consumer of Internet bandwidth the differences in the characteristics of objects being transferred the impact of the two-way nature of p2p communication the ways in which p2p systems are not scaling, despite their explicitly scalable design 3 Wireless Networks Lab. Content Delivery Systems -WWW The world-wide web (WWW) Simple client-server architecture Using the HTTP protocols Most web objects are small (5~10KB) The number if web objects is enormous and rapidly growing 4 Wireless Networks Lab. Content Delivery Systems - CDNs Content delivery networks (CDNs) Dedicated collection of servers located strategically across the wide- area Internet Content providers contracts with commercial CDNs to host and distribute content Content is replicated across the wide area highly available Clients can access topologically nearby replicas with low latency DNS redirection causes overhead 5 Wireless Networks Lab. CDN example - Akami 6 Wireless Networks Lab. Content Delivery Systems –P2P Peer-to-peer systems (P2P) Peers collaborate to form a distributed system exchanging content Peers behave as both servers and clients Architecture types of P2P systems logically centralized architecture Napster fully distributed architecture Gnutella, Freenet hybird architecture some peers are elected as supernodes Kazaa 7 Wireless Networks Lab. P2P example Distributed Centralized Hybrid 8 Wireless Networks Lab. Measurement Methodology Passive network monitoring collects traces of traffic between the University of Washington(UW) and the Internet UW connects to its IPSs via two border routers one for outbound traffic, the other is for inbound traffic both are fully connected to four switches each switches has a monitoring port sending copies of incoming and outgoing packets to the monitoring hosts Traffic types HTTP traffic WWW, Akamai, Kazza, Gnutella non-HTTP TCP traffic Kazza and Gnutella search traffic 9 Wireless Networks Lab. Classifying traffic types Akamai HTTP traffic on port 80, 8080, 443 WWW HTTP traffic on port 80, 8080, 443 HTTP traffic on port 6346, 6347 Gnutella - inculding file transfer - excluding search, control traffic HTTP traffic on port 1214 Kazza - including file transfer -excluding search, control traffic P2P Gnutella + Kazza any other TCP traffic - NNTP, SMTP, HTTP traffic to other ports Non-HTTP TCP traffic -traffic from other P2P systems - control and search traffic on Gnutella and Kazza 10 Wireless Networks Lab. High-Level Data Characteristics 11 Wireless Networks Lab. HTTP trace summary Exporting 16.65 TB, importing 3.44 TB UW is a net provider rather than consumer of HTTP data P2P systems account for a large percentage of the bytes exported and the total bytes transferred 12 Wireless Networks Lab. TCP Bandwidth All systems show a typical diurnal cycle Bandwidth consumption Akamai - 0.2% Gnutella - 6.04% WWW traffic - 14.3% of TCP traffic Kazaa - 36.99% of TCP bytes other TCP based protocols – 43% 13 Wireless Networks Lab. UW Client and Server TCP Bandwidth Figure (a) – Inbound Data BW (web and P2P downloads from UW clients) WWW peaking in the middle of the day Kazza peaking late at night Figure (b) – Outbound Data BW (web and P2P uploads from UW servers) Peak Kazza BW dominates WWW by a factor of 3 External Kazza clients consume 7.6 times more BW than UW Kazza clients 14 Wireless Networks Lab. Content Types Downloaded by UW Clients GIF & JPEG images 42% of requests, only 16.3% of the bytes transferred AVI & MPEG 0.41% of requests, 29.3% of the bytes transferred Comparison with measurements from study in 1999 HTML traffic : -43%, GIF&JPG traffic : -59% AVI&MPG traffic : 400%, MP3 traffic 300% 15 Wireless Networks Lab. Summary The balance of HTTP traffic has changed dramatically over the last server years P2P traffic overtaking WWW traffic as the largest contributor to HTTP bytes transferred Although UW is large publisher of web documents, P2P traffic makes the University an even larger exporter of data The mixture of object types downloaded by UW clients has changed video and audio accounting for a substantially larger fraction of traffic than three years ago 16 Wireless Networks Lab. Detailed Content Delivery Characteristics 17 Wireless Networks Lab. Objects Object size: P2P (median: 4MB)> WWW (median: 2KB) & Akamai Top bandwidth consuming Objects Gnutella relatively large number of objects account for a large portion of the transferred bytes 18 Wireless Networks Lab. Top 10 bandwidth consuming objects WWW – The top 10 objects are a mix of extremely small objects Akamai – 8 out of the top 10 objects are larger and unpopular Kazaa – Export objects are larger than import objects 19 Wireless Networks Lab. Downloaded bytes by object type 20 Wireless Networks Lab. Top UW bandwidth consuming clients Figure (a) – Top Bandwidth Consuming UW Clients WWW - Top 200 clients (0.5%) 13% of WWW traffic Kazza - Top 200 clients (4%) 50% of Kazza traffic Figure (b) Kazza: 200 clients 20% of the total HTTP bytes downloaded (worst offender) 21 Wireless Networks Lab. Clients - Request rates over time Figure (a) – WWW + Akamai Request Rates inbound request rate peaks at 1100 request per second outbound request rate peaks under 200 request per second Figure (b) – Kazza Request Rates at a high level request rate: two orders of magnitude lower than the web Kazza consumes median object size: three orders of magnitude higher than the web more bandwidth 22 Wireless Networks Lab. Client – Concurrent HTTP transactions Despite the order of magnitude request-rate advantage of WWW over Kazza the number of simultaneous open Kazza connections is about twice the number of simultaneous open WWW + Akamai connections Tue 0:00 Kazza generates only 23 requests per second up to almost 1000 open requests at a time due to its long transfers 23 Wireless Networks Lab. Top UW-internal servers to external clients Figure (a) – Top Bandwidth Consuming UW Servers Gnutella: All of the bytes first 10 servers WWW: steep curve several major servers provide documents to the web Kazza: 80% of the bytes top 334 servers Figure (b) WWW: 20 servers 20% of all HTTP bytes output Kazza: 170 server 50% of all HTTP bytes output 24 Wireless Networks Lab. The UW-external servers to internal clients Figure (a) WWW: 938 external servers 50% of the bytes Kazza: 600 external servers 26% of the bytes Figure (b) Kazza: Top 500 external Kazza peers 10% of the bytes WWW: Top 500 servers 22% of the bytes 25 Wireless Networks Lab. Scalability of P2P Systems Whether P2P Systems like Kazaa can scale in environments such as UW ? Every peer in P2P system consumes bandwidth in both directions Each new P2P client added becomes a server for the entire P2P structure Kazaa object is huge, so a small number of peers can consume an enormous amount of total net. Bandwidth The bandwidth cost of each P2P peer is 90 times that of the web client It seems questionable whether any organization can supports a service with these characteristics 26 Wireless Networks Lab. Summary Peer-to-peer, which now accounts for over three quarters of HTTP traffic A small number of P2P users are consuming a disproportionately high fraction of bandwidth While the P2P request rate is quite low, the transfer last long While the design of P2P overlay structures focuses on spreading the workload for scalability, our measurements show that a small number of servers are taking the majority of the burden 27 Wireless Networks Lab. The Potential Role of Caching in CDNs Akamai requests achieve an 88% ideal hit rate and a 50% practical hit rate, noticeably higher than www requests (77% and 36%) Our analysis shows that akamai requests are more skewed towards the most popular documents than are WWW requests We know that most bytes fetched from Akamai are from images and videos This implies that much of Akamai's content is in fact static and could be cached We would expect that widely deployed proxy caches would significantly reduce the need for a separate content delivery network 28 Wireless Networks Lab. The Potential Role of Caching in P2P The potential impact of caching in P2P systems may exceed the benefits seen in the web Inbound cache byte hit rate = 35%, Outbound cache byte hit rate = 85% Hit rate increases with client population size for outbound traffic. (1000 client - 40%, 500,000 client - 85%) Reverse P2P cache saves the most bandwidth 29 Wireless Networks Lab. Conclusion P2P traffic now accounts for the majority of HTTP bytes transferred P2P documents are three orders of magnitude larger than web objects leading to a 1000-fold increase in transfer time A small number of extremely large objects account for an enormous fraction of observed P2P traffic A small number of clients and servers are responsible for the majority of the traffic we saw in the P2P systems Each P2P client creates a significant bandwidth load in both directions 30 Wireless Networks Lab.
Recommended publications
  • Uila Supported Apps
    Uila Supported Applications and Protocols updated Oct 2020 Application/Protocol Name Full Description 01net.com 01net website, a French high-tech news site. 050 plus is a Japanese embedded smartphone application dedicated to 050 plus audio-conferencing. 0zz0.com 0zz0 is an online solution to store, send and share files 10050.net China Railcom group web portal. This protocol plug-in classifies the http traffic to the host 10086.cn. It also 10086.cn classifies the ssl traffic to the Common Name 10086.cn. 104.com Web site dedicated to job research. 1111.com.tw Website dedicated to job research in Taiwan. 114la.com Chinese web portal operated by YLMF Computer Technology Co. Chinese cloud storing system of the 115 website. It is operated by YLMF 115.com Computer Technology Co. 118114.cn Chinese booking and reservation portal. 11st.co.kr Korean shopping website 11st. It is operated by SK Planet Co. 1337x.org Bittorrent tracker search engine 139mail 139mail is a chinese webmail powered by China Mobile. 15min.lt Lithuanian news portal Chinese web portal 163. It is operated by NetEase, a company which 163.com pioneered the development of Internet in China. 17173.com Website distributing Chinese games. 17u.com Chinese online travel booking website. 20 minutes is a free, daily newspaper available in France, Spain and 20minutes Switzerland. This plugin classifies websites. 24h.com.vn Vietnamese news portal 24ora.com Aruban news portal 24sata.hr Croatian news portal 24SevenOffice 24SevenOffice is a web-based Enterprise resource planning (ERP) systems. 24ur.com Slovenian news portal 2ch.net Japanese adult videos web site 2Shared 2shared is an online space for sharing and storage.
    [Show full text]
  • What Is Peer-To-Peer File Transfer? Bandwidth It Can Use
    sharing, with no cap on the amount of commonly used to trade copyrighted music What is Peer-to-Peer file transfer? bandwidth it can use. Thus, a single NSF PC and software. connected to NSF’s LAN with a standard The Recording Industry Association of A peer-to-peer, or “P2P,” file transfer 100Mbps network card could, with KaZaA’s America tracks users of this software and has service allows the user to share computer files default settings, conceivably saturate NSF’s begun initiating lawsuits against individuals through the Internet. Examples of P2P T3 (45Mbps) internet connection. who use P2P systems to steal copyrighted services include KaZaA, Grokster, Gnutella, The KaZaA software assesses the quality of material or to provide copyrighted software to Morpheus, and BearShare. the PC’s internet connection and designates others to download freely. These services are set up to allow users to computers with high-speed connections as search for and download files to their “Supernodes,” meaning that they provide a How does use of these services computers, and to enable users to make files hub between various users, a source of available for others to download from their information about files available on other create security issues at NSF? computers. users’ PCs. This uses much more of the When configuring these services, it is computer’s resources, including bandwidth possible to designate as “shared” not only the and processing capability. How do these services function? one folder KaZaA sets up by default, but also The free version of KaZaA is supported by the entire contents of the user’s computer as Peer to peer file transfer services are highly advertising, which appears on the user well as any NSF network drives to which the decentralized, creating a network of linked interface of the program and also causes pop- user has access, to be searchable and users.
    [Show full text]
  • The Effects of Digital Music Distribution" (2012)
    Southern Illinois University Carbondale OpenSIUC Research Papers Graduate School Spring 4-5-2012 The ffecE ts of Digital Music Distribution Rama A. Dechsakda [email protected] Follow this and additional works at: http://opensiuc.lib.siu.edu/gs_rp The er search paper was a study of how digital music distribution has affected the music industry by researching different views and aspects. I believe this topic was vital to research because it give us insight on were the music industry is headed in the future. Two main research questions proposed were; “How is digital music distribution affecting the music industry?” and “In what way does the piracy industry affect the digital music industry?” The methodology used for this research was performing case studies, researching prospective and retrospective data, and analyzing sales figures and graphs. Case studies were performed on one independent artist and two major artists whom changed the digital music industry in different ways. Another pair of case studies were performed on an independent label and a major label on how changes of the digital music industry effected their business model and how piracy effected those new business models as well. I analyzed sales figures and graphs of digital music sales and physical sales to show the differences in the formats. I researched prospective data on how consumers adjusted to the digital music advancements and how piracy industry has affected them. Last I concluded all the data found during this research to show that digital music distribution is growing and could possibly be the dominant format for obtaining music, and the battle with piracy will be an ongoing process that will be hard to end anytime soon.
    [Show full text]
  • Piratez Are Just Disgruntled Consumers Reach Global Theaters That They Overlap the Domestic USA Blu-Ray Release
    Moviegoers - or perhaps more accurately, lovers of cinema - are frustrated. Their frustrations begin with the discrepancies in film release strategies and timing. For example, audiences that saw Quentin Tarantino’s1 2 Django Unchained in the United States enjoyed its opening on Christmas day 2012; however, in Europe and other markets, viewers could not pay to see the movie until after the 17th of January 2013. Three weeks may not seem like a lot, but some movies can take months to reach an international audience. Some take so long to Piratez Are Just Disgruntled Consumers reach global theaters that they overlap the domestic USA Blu-Ray release. This delay can seem like an eternity for ultiscreen is at the top of the entertainment a desperate fan. This frustrated enthusiasm, combined industry’s agenda for delivering digital video. This with a lack of timely availability, leads to the feeling of M is discussed in the context of four main screens: being treated as a second class citizen - and may lead TVs, PCs, tablets and mobile phones. The premise being the over-anxious fan to engage in piracy. that multiscreen enables portability, usability and flexibility for consumers. But, there is a fifth screen which There has been some evolution in this practice, with is often overlooked – the cornerstone of the certain films being released simultaneously to a domestic and global audience. For example, Avatar3 was released entertainment industry - cinema. This digital video th th ecosystem is not complete without including cinema, and in theaters on the 10 and 17 of December in most it certainly should be part of the multiscreen discussion.
    [Show full text]
  • Informed Content Delivery Across Adaptive Overlay Networks
    Informed Content Delivery Across Adaptive Overlay Networks John Byers Jeffrey Considine Michael Mitzenmacher Stanislav Rost [email protected] [email protected] [email protected] [email protected] Dept. of Computer Science EECS MIT Laboratory for Boston University Harvard University Computer Science Boston, Massachusetts Cambridge, Massachusetts Cambridge, Massachusetts Abstract Categories and Subject Descriptors C.2 [Computer Systems Organization]: Computer- Overlay networks have emerged as a powerful and highly flexible Communication Networks method for delivering content. We study how to optimize through- put of large transfers across richly connected, adaptive overlay net- General Terms works, focusing on the potential of collaborative transfers between Algorithms, Measurement, Performance peers to supplement ongoing downloads. First, we make the case for an erasure-resilient encoding of the content. Using the digital Keywords fountain encoding approach, end-hosts can efficiently reconstruct Overlay, peer-to-peer, content delivery, digital fountain, erasure ¡ the original content of size ¡ from a subset of any symbols drawn correcting code, min-wise summary, Bloom filter, reconciliation, from a large universe of encoded symbols. Such an approach af- collaboration. fords reliability and a substantial degree of application-level flex- ibility, as it seamlessly accommodates connection migration and 1 Introduction parallel transfers while providing resilience to packet loss. How- ever, since the sets of encoded symbols acquired by peers during Consider the problem of distributing a large new file across a downloads may overlap substantially, care must be taken to enable content delivery network of several thousand geographically dis- them to collaborate effectively. Our main contribution is a collec- tributed machines.
    [Show full text]
  • The Robustness of Content-Based Search in Hierarchical Peer to Peer Networks
    The Robustness of Content-Based Search in Hierarchical Peer to Peer Networks ∗ M. Elena Renda Jamie Callan I.S.T.I. – C.N.R. Language Technologies Institute and School of Computer Science Scuola Superiore Sant’Anna Carnegie Mellon University I-56100 Pisa, Italy Pittsburgh, PA 15213, US [email protected] [email protected] ABSTRACT Keywords Hierarchical peer to peer networks with multiple directory services Peer to Peer, Hierarchical, Search, Retrieval, Content-based, Ro- are an important architecture for large-scale file sharing due to their bustness effectiveness and efficiency. Recent research argues that they are also an effective method of providing large-scale content-based federated search of text-based digital libraries. In both cases the 1. INTRODUCTION directory services are critical resources that are subject to attack Peer to peer (P2P) networks have emerged in recent years as a or failure, but the latter architecture may be particularly vulnera- popular method of sharing information, primarily popular music, ble because content is less likely to be replicated throughout the movies, and software, among large numbers of networked com- network. puters. Computers (‘nodes’) in P2P networks can be information This paper studies the robustness, effectiveness and efficiency providers and information consumers, and may provide network of content-based federated search in hierarchical peer to peer net- services such as message routing and regional directory services. works when directory services fail unexpectedly. Several recovery A single node may play several roles at once, for example, posting methods are studied using simulations with varying failure rates. queries, sharing files, and relaying messages.
    [Show full text]
  • Instart Logic TWITTER LINKEDIN
    Instart Logic TWITTER LINKEDIN MOBILE VIDEO AND APPS WEBSITE Who we are Our advantage Instart Logic is a platform designed to make the delivery of It is a fully responsive platform, offering both flexibility and websites and applications fast, secure and easy. It’s the world’s control. It provides: first endpoint-aware application delivery solution. Performance – Helps improve site-wide performance, especially on mobile through image, code and network Instart’s intelligent architecture provides a new way to optimisation techniques. accelerate web and mobile application performance, based on the user’s specific device, browser, and network conditions. Ad Security – Ability to recover lost advertising revenue from ad-blockers. This new breed of technology goes beyond a traditional Security – Helps protect from harmful bots that flood the site, content delivery network (CDN) to enable businesses to deliver skew data and warp search algorithms and shield from rapid customer-centric website and mobile application Distributed Denial of Service (DDoS), brute-force entry, and experiences. other cyber attacks Agility – Use a DevOps first infrastructure allowed for self-sufficient management and deployment of new content and applications throughout network. Our partnership How does our solution work? Telstra will be using Instart Logic to optimise, monetise and AppSpeed: Instart Logic’s endpoint-aware application delivery deliver managed websites and web applications. Those that are solution provides a new way to accelerate web and mobile application performance. It’s intelligent architecture optimises currently on trial include: images, HTML, JavaScript and other page elements based on • Australian Football League (AFL) each user’s specific device, browser, and network conditions.
    [Show full text]
  • A Peer-To-Peer Internet Measurement Platform and Its Applications in Content Delivery Networks
    A PEER-TO-PEER INTERNET MEASUREMENT PLATFORM AND ITS APPLICATIONS IN CONTENT DELIVERY NETWORKS BY SIPAT TRIUKOSE Submitted in partial fulfillment of the requirements for the degree of Doctor Of Philosophy DISSERTATION ADVISOR: DR. MICHAEL RABINOVICH DEPARTMENT OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE CASE WESTERN RESERVE UNIVERSITY JANUARY 2014 CASE WESTERN RESERVE UNIVERSITY SCHOOL OF GRADUATE STUDIES We hereby approve the dissertation of SIPAT TRIUKOSE candidate for the Doctor of Philosophy degree *. MICHAEL RABINOVICH TEKIN OZSOYOGLU SHUDONG JIN VIRA CHANKONG MARK ALLMAN (date) December 1st, 2010 *We also certify that written approval has been obtained for any proprietary material contained therein. Contents List of Tables . vi List of Figures . ix List of Abbreviations . x Abstract . xi 1 Introduction 1 1.1 Internet Measurements . 1 1.2 Content Delivery Network (CDN) . 4 1.2.1 Akamai and Limelight . 6 1.2.2 Coral . 7 1.3 Outline . 7 1.4 Acknowledgement . 9 2 Related Work 10 2.1 On-demand Network Measurements . 10 2.2 Content Delivery Network (CDN) Research . 12 2.2.1 Performance Assessment . 12 2.2.2 Security . 13 2.2.3 Performance Improvement . 14 3 DipZoom: Peer-to-Peer Internet Measurement Platform 17 3.1 System Overview . 17 i 3.2 The DipZoom Measuring Point (MP) . 21 3.2.1 MP-Loader, MP-Class, and MP Configurations . 25 3.2.2 Authentication . 30 3.2.3 Keep Alive . 37 3.2.4 Measurement . 39 3.3 The DipZoom Client and API . 43 3.4 Security . 44 3.5 Performance . 47 3.5.1 Scalability: Measuring Point Fan-Out .
    [Show full text]
  • Content Distribution in P2P Systems Manal El Dick, Esther Pacitti
    Content Distribution in P2P Systems Manal El Dick, Esther Pacitti To cite this version: Manal El Dick, Esther Pacitti. Content Distribution in P2P Systems. [Research Report] RR-7138, INRIA. 2009. inria-00439171 HAL Id: inria-00439171 https://hal.inria.fr/inria-00439171 Submitted on 6 Dec 2009 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUE Content Distribution in P2P Systems Manal El Dick — Esther Pacitti N° 7138 Décembre 2009 Thème COM apport de recherche ISSN 0249-6399 ISRN INRIA/RR--7138--FR+ENG Content Distribution in P2P Systems∗ Manal El Dick y, Esther Pacittiz Th`emeCOM | Syst`emescommunicants Equipe-Projet´ Atlas Rapport de recherche n° 7138 | D´ecembre 2009 | 63 pages Abstract: The report provides a literature review of the state-of-the-art for content distribution. The report's contributions are of threefold. First, it gives more insight into traditional Content Distribution Networks (CDN), their re- quirements and open issues. Second, it discusses Peer-to-Peer (P2P) systems as a cheap and scalable alternative for CDN and extracts their design challenges. Finally, it evaluates the existing P2P systems dedicated for content distribution according to the identified requirements and challenges.
    [Show full text]
  • Online Piracy
    Online Piracy Christian Helmers 16 April 2015 1 / 31 Online piracy • Digital technologies: • Create, transform, copy data • Digital technologies: transmission, display and analysis of data through copying • Enabled large-scale online piracy • Piracy: illegal copying of copyrighted material online • Music • Movies • Ebooks/audiobooks • Software • Note: [Piracy] is not an offense of timeless character, universally definable by a priori criteria. It is far richer and trickier than that. (Johns, 2009:4) • Beware: often very ideological debate 2 / 31 P2P: Napster 3 / 31 P2P: The Pirate Bay 4 / 31 P2P: LimeWire Pirate Edition (\Not an equivalent, not a replacement, but the exact same thing") 5 / 31 P2P: More BitTorrent sites 6 / 31 Direct downloads: Megaupload 7 / 31 Direct downloads: many anonymous options 8 / 31 Cracking devices: Amazon's MOBI 9 / 31 Online piracy • Digital technologies: • P2P music sharing software: Napster, KaZaa, Morpheus, Grokster, BitTorrent sites, etc. • Direct downloads, file repositories • Cracking software • Enabled large-scale online piracy • Importance of digital platforms for sharing • File sharing market organized in private groups with tightly controlled access (non-profit) • Filehosters often for-profit 10 / 31 The economics of piracy (Klein et al., 2002) • Negative effect on copyright owner: • Pirated copies substitutes for legal downloads (but lower quality files may limit substitution) • Inability to price-discriminate • Inability to control prices • Positive effect on copyright owner: • Sampling (learning) • Space
    [Show full text]
  • Title: P2P Networks for Content Sharing
    Title: P2P Networks for Content Sharing Authors: Choon Hoong Ding, Sarana Nutanong, and Rajkumar Buyya Grid Computing and Distributed Systems Laboratory, Department of Computer Science and Software Engineering, The University of Melbourne, Australia (chd, sarana, raj)@cs.mu.oz.au ABSTRACT Peer-to-peer (P2P) technologies have been widely used for content sharing, popularly called “file-swapping” networks. This chapter gives a broad overview of content sharing P2P technologies. It starts with the fundamental concept of P2P computing followed by the analysis of network topologies used in peer-to-peer systems. Next, three milestone peer-to-peer technologies: Napster, Gnutella, and Fasttrack are explored in details, and they are finally concluded with the comparison table in the last section. 1. INTRODUCTION Peer-to-peer (P2P) content sharing has been an astonishingly successful P2P application on the Internet. P2P has gained tremendous public attention from Napster, the system supporting music sharing on the Web. It is a new emerging, interesting research technology and a promising product base. Intel P2P working group gave the definition of P2P as "The sharing of computer resources and services by direct exchange between systems". This thus gives P2P systems two main key characteristics: • Scalability: there is no algorithmic, or technical limitation of the size of the system, e.g. the complexity of the system should be somewhat constant regardless of number of nodes in the system. • Reliability: The malfunction on any given node will not effect the whole system (or maybe even any other nodes). File sharing network like Gnutella is a good example of scalability and reliability.
    [Show full text]
  • Toolkit on Environmental Sustainability for the ICT Sector Toolkit September 2012
    !"#"$%&&'()$*+%(,-."/0%1,-*(2- -------!"#"&*+$,-3*4%1*/%15- .*+%(*#-7(/"1A6()B"1,)/5-C%(,%1+'&- D%1-!"#"$%&&'()$*+%(,-- 6.789:;7!<-=9>37-;!6=7-=7- >9.?8@- Toolkit on environmental sustainability for the ICT !"#"$%&&'()$*+%(,-."/0%1,-*(2- -------!"#"&*+$,-3*4%1*/%15- !"#"$%&&'()$*+%(,-."/0%1,-*(2- sector -------!"#"&*+$,-3*4%1*/%15- .*+%(*#-7(/"1A6()B"1,)/5.*+%(*#-7(/"1A-C%(,%1+'&- 6()B"1,)/5-C%(,%1+'&- D%1-!"#"$%&&'()$*+%(,D%1---!"#"$%&&'()$*+%(,-- 6.789:;7!<-=9>37-;!6=7-=7-6.789:;7!<-=9>37-;!6=7-=7- >9.?8@- >9.?8@- Toolkit on environmental sustainability for the ICT sector Toolkit September 2012 About ITU-T and Climate Change: itu.int/ITU-T/climatechange/ Printed in Switzerland Geneva, 2012 E-mail: [email protected] Photo credits: Shutterstock® itu.int/ITU-T/climatechange/ess Acknowledgements This toolkit was developed by ITU-T with over 50 organizations and ICT companies to establish environmental sustainability requirements for the ICT sector. This toolkit provides ICT organizations with a checklist of sustainability requirements; guiding them in efforts to improve their eco-efficiency, and ensuring fair and transparent sustainability reporting. The toolkit deals with the following aspects of environmental sustainability in ICT organizations: sustainable buildings, sustainable ICT, sustainable products and services, end of life management for ICT equipment, general specifications and an assessment framework for environmental impacts of the ICT sector. The authors would like to thank Jyoti Banerjee (Fronesys) and Cristina Bueti (ITU) who gave up their time to coordinate all comments received and edit the toolkit. Special thanks are due to the contributory organizations of the Toolkit on Environmental Sustainability for the ICT Sector for their helpful review of a prior draft.
    [Show full text]