Ultra-Large-Scale Sites

Total Page:16

File Type:pdf, Size:1020Kb

Ultra-Large-Scale Sites Ultra-large-scale Sites <working title> – Scalability, Availability and Performance in Social Media Sites (picture from social network visualization?) Walter Kriha With a forword by << >> Walter Kriha, Scalability and Availability Aspects…, V.1.9.1 page 1 03/12/2010 Copyright <<ISBN Number, Copyright, open access>> ©2010 Walter Kriha This selection and arrangement of content is licensed under the Creative Commons Attribution License: http://creativecommons.org/licenses/by/3.0/ online: www.kriha.de/krihaorg/ ... <a rel="license" href="http://creativecommons.org/licenses/by/3.0/de/"><img alt="Creative Commons License" style="border-width:0" src="http://i.creativecommons.org/l/by/3.0/de/88x31.png" /></a><br /><span xmlns:dc="http://purl.org/dc/elements/1.1/" href="http://purl.org/dc/dcmitype/Text" property="dc:title" rel="dc:type"> Building Scalable Social Media Sites</span> by <a xmlns:cc="http://creativecommons.org/ns#" href="wwww.kriha.de/krihaorg/books/ultra.pdf" property="cc:attributionName" rel="cc:attributionURL">Walter Kriha</a> is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by/3.0/de/">Creative Commons Attribution 3.0 Germany License</a>.<br />Permissions beyond the scope of this license may be available at <a xmlns:cc="http://creativecommons.org/ns#" href="www.kriha.org" rel="cc:morePermissions">www.kriha.org</a>. Walter Kriha, Scalability and Availability Aspects…, V.1.9.1 page 2 03/12/2010 Acknowledgements <<master course, Todd Hoff/highscalability.com..>> Walter Kriha, Scalability and Availability Aspects…, V.1.9.1 page 3 03/12/2010 ToDo’s - The role of ultra fast networks (Infiniband) on distributed algorithms and behaviour with respect to failure models - more on group behaviour from Clay Shirky etc. into the first part (also modelling of social groups and data) - OpenSocial as a modelling example. Does it scale? - finish chapter of popular sites and their architecture - alternative architectures better explained (spaces, queues) - cloud APIs (coming) - consensus algs for the lowest parts explained - failure models (empirical and theoretical, in connection with consensus algs) - practical part: ideas for monitoring, experiments, extending a site into a community site as an example, darkstar/wonderland scalability - feature management as a core technique (example: MMOGs) - ..and so on… - Time in virtual machines - The effect of virtual machines on distributed algorithms, e.g. consensus - Modelling performance with palladio - Space based architecture alternative - eventbasierte Frameworks (node.js / eventmachine) in I/O - client side optimization hints - queuing with data bases ( http://www.slideshare.net/postwait/postgresql- meet-your-queue ) - spanner: googles next infrastructure, http://www.royans.net/arch/spanner- googles-next-massive-storage-and-computation-infrastructure - CAP explanation: http://www.instapaper.com/text?u=http%3A%2F%2Fwww.julianbrowne.com%2 Farticle%2Fviewer%2Fbrewers-cap-theorem - Puppet config management: - http://bitfieldconsulting.com/puppet-vs-chef - Agile but extremely large systems configuration problems! Walter Kriha, Scalability and Availability Aspects…, V.1.9.1 page 4 03/12/2010 Foreword <<by ?>> Walter Kriha, Scalability and Availability Aspects…, V.1.9.1 page 5 03/12/2010 Copyright 2 Acknowledgements 3 ToDo’s 4 Foreword 5 Introduction 13 Part I: Media, People and Distributed Systems 17 Media 18 Meaning across Space and Time 18 Partitioning 18 Social Media 19 Being digital, distributed and social 19 Short Digression: The fragile concept of ownership in digital times 20 Superstructures 24 Social Media and their Price 24 People – communicating, participating, collaborating 25 Coordination 26 Where is the Money? 29 Findability 30 Epidemics 31 Group Behavior 31 Social Graphs 32 Superstructures 32 The API Web – the Sensor Web – the Open Web? 33 Supersize Me – on network effects and endless growth 33 Security 34 Federated Access Control to Private Data 36 De-Anonymization of Private Data 37 Identity Spoofing in Social Networks 38 Scams 39 Bootstrapping a large community 40 Part II: Distributed Systems 41 Basics of Distributed Computing Systems 42 Remoteness, Concurrency and Interactions 42 Functions of distributed systems 43 Manifestation: Middleware and Programming Models 45 Theoretical Underpinnings 47 Topologies and Communication Styles 49 Classic Client/Server Computing 49 The Web Success Model 49 REST Architecture of the Web 50 Web2.0 and beyond 53 Web-Services and SOA 56 Walter Kriha, Scalability and Availability Aspects…, V.1.9.1 page 6 03/12/2010 Peer networks 59 Distributed Hashtable Approaches 60 Bittorrent Example 63 Special Hierarchies 64 Compute Grids 65 Event-Driven Application Architectures and Systems 66 Reliability, Availability, Scalability, Performance (RASP) 71 Resilience and Dependability 71 Scalability 72 Availability 75 Concepts and Replication Topologies 79 Failure Modes and Detection 85 J2EE Clustering for Scalability and Availability 89 Reliability 97 Deployment 97 Reliability and Scalability Tradeoff in Replication Groups 98 Performance 98 Monitoring and Logging 99 Distribution in Media Applications 99 Storage Subsystems for HDTV media 99 Audio Server for Interactive Rooms 103 Distributed Rendering in 3DSMAX 105 Understanding the Rendering Network Components of 3dsMax 105 Using partitioning to speed things up 107 Part III: Ultra Large Scale Distributed Media Architectures 109 Analysis Framework 110 Examples of Large Scale Social Sites 113 Wikipedia 113 Myspace 113 Flickr 115 Facebook 118 PlentyOfFish 118 Twitter – “A short messaging layer for the internet (A.Payne)” 118 Digg 119 Google 119 YouTube 119 Amazon 120 LiveJournal Architecture 120 LavaBit E-mail Provider 120 Stack Overflow 120 Massively Multiplayer Online Games (MMOGs) 122 On Shards, Shattering and Parallel Worlds 124 Shard Architecture and visible partitioning 125 Shardless Architecture and Dynamic Reconfiguration 127 Feature and Social Management 129 Walter Kriha, Scalability and Availability Aspects…, V.1.9.1 page 7 03/12/2010 Security in MMOGs 131 Methodologies in Building Large-Scale Sites 131 Limits in Hardware and Software – on prices, performance etc. 131 A History of Large Scale Site Technology 133 Growing Pains – How to start small and grow big 133 Feature Management 134 Patterns and Anti-Patterns of Scalability 134 Test and Deployment Methodology 135 Client-Side Optimizations 136 A Model for RASP in Large Scale Distribution 138 Canonical or Classic Site Architecture 138 Classic Document-Oriented Large Site Architecture (Wikipedia) 140 Message Queuing System (Twitter) 140 Social Data Distributor (Facebook) 140 Space-Based Programming 141 Queuing theory, OR 141 Basic Concepts 141 Applications of QT concepts in multi-tier Systems 151 Service Demand Reduction: Batching and Caching 151 Service Demand Reduction: Data-in-Index 153 Service Demand Measurements 153 The n-tier funnel architecture 154 Cost of slow machines in mid- or end-tier 154 Queue length and Residence Time 156 Output traffic shaping 156 The realism of Queuing Theory based Models for distributed systems 157 Request Processing: Asynchronous and/or fixed service time 157 Heterogeneous hardware and self-balancing algorithms 158 Dispatch in Multi-Queue Servers 158 Unfair Dispatch: Shortest Remaining Processing Time First 158 Request Design Alternatives 159 Heijunka 160 Tools for QT-Analysis 161 Applicability of QT in large-scale multi-tier architectures 162 Combinatorial Reliability and Availability Analysis 162 Stochastic Availability Analysis 168 Guerilla Capacity Planning 168 Concurreny and Coherence 169 Calculation of contention and coherence parameters 172 Client Distribution over Day/Week/Year 175 Simulation 175 Tools for statistical analysis, queuing models and simulation 176 Architectural Principles and Metrics 177 Architectural Principles 178 Metrics 178 Changes in Perspective 178 Part IV: System Components 179 System Components for Distributed Media 179 Component Interaction and Hierarchy 179 Walter Kriha, Scalability and Availability Aspects…, V.1.9.1 page 8 03/12/2010 Latency, Responsiveness and Distribution Architecture 179 Adaptations to media 184 Content Delivery Networks (CDN) 186 HA-Service Distributor 188 Distributed Load Balancers 189 Distributed Caching – not an Optimization 191 Caching and Application Architecture 191 Caching Strategies 192 When not to cache 192 Invalidation Events vs. Timeout 193 Operational Criticality 193 Pre-Loading of Caches 193 Local or distributed caches 193 Partitioning Schemes 194 Memory or Disk 194 Distribution of values 194 Granularity 194 Statistics 194 Size and Replacement Algorithms 195 Cache Hierarchies 195 Memcached 195 Fragment Architecture and Processor 197 Compression 201 Local or predictive processing 202 Search Engine Architecture and Integration 202 Special Web Servers (light-weight) 203 A pull based Web Server Design? 203 Scheduler and parallel Processor 204 High-availability failure detector 204 and lock service 204 Buffering and compensation for networked audio 204 Data Center Architecture 205 Geographically Dispersed Data Centers and Topology 205 Scale-out vs. Scale-up 206 Data Stores 208 Requirements and Criteria 209 virtualized storage: 209 External Storage Sub-Systems 210 Grid-Storage/Distributed File Systems 210 Distributed Clustered Storage 214 ZFS 215 Database Partitioning and Sharding 215 Cache concepts with shards and partitions 222 Why Sharding is Bad 223 Social data examples and modeling: 224 Partitioning concepts and consequences
Recommended publications
  • Here I Led Subcommittee Reports Related to Data-Intensive Science and Post-Moore Computing) and in CRA’S Board of Directors Since 2015
    Vivek Sarkar Curriculum Vitae Contents 1 Summary 2 2 Education 3 3 Professional Experience 3 3.1 2017-present: College of Computing, Georgia Institute of Technology . 3 3.2 2007-present: Department of Computer Science, Rice University . 5 3.3 1987-2007: International Business Machines Corporation . 7 4 Professional Awards 11 5 Research Awards 12 6 Industry Gifts 15 7 Graduate Student and Other Mentoring 17 8 Professional Service 19 8.1 Conference Committees . 20 8.2 Advisory/Award/Review/Steering Committees . 25 9 Keynote Talks, Invited Talks, Panels (Selected) 27 10 Teaching 33 11 Publications 37 11.1 Refereed Conference and Journal Publications . 37 11.2 Refereed Workshop Publications . 51 11.3 Books, Book Chapters, and Edited Volumes . 58 12 Patents 58 13 Software Artifacts (Selected) 59 14 Personal Information 60 Page 1 of 60 01/06/2020 1 Summary Over thirty years of sustained contributions to programming models, compilers and runtime systems for high performance computing, which include: 1) Leading the development of ASTI during 1991{1996, IBM's first product compiler component for optimizing locality, parallelism, and the (then) new FORTRAN 90 high-productivity array language (ASTI has continued to ship as part of IBM's XL Fortran product compilers since 1996, and was also used as the foundation for IBM's High Performance Fortran compiler product); 2) Leading the research and development of the open source Jikes Research Virtual Machine at IBM during 1998{2001, a first-of-a-kind Java Virtual Machine (JVM) and dynamic compiler implemented
    [Show full text]
  • Collaboration and Social Media-2008
    Research Report Collaboration and Social Media-2008 Taking Stock of Today’s Experiences and Tomorrow’s Opportunities Geoffrey Bock Steve Paxhia The Gilbane Group June 9, 2008 Gilbane Group Inc. 763 Massachusetts Avenue Cambridge, MA 02139 USA Tel: 617.497.9443 Fax: 617.497.5256 [email protected] http://gilbane.com With Thanks to Our Sponsors Platinum Gold Silver ©2008 Gilbane Group, Inc. i http://gilbane.com Collaboration and Social Media — 2008 Table of Contents With Thanks to Our Sponsors .................................................................................. i Our Perspective ................................................................................. vi How American Companies Use Social Media ....................................... i Tracking Social Media ............................................................................................. 2 Adopting Social Media .............................................................................................. 5 Social Media Profiles .............................................................................................. 10 A Social Media Roadmap ....................................................................................... 30 Customer Stories ............................................................................. 32 Awareness at Earth Knowledge ............................................................................. 33 EMC Documentum eRoom at Bechtel ................................................................... 36 EMC Documentum eRoom
    [Show full text]
  • Live Distributed Objects
    LIVE DISTRIBUTED OBJECTS A Dissertation Presented to the Faculty of the Graduate School of Cornell University in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy by Krzysztof Jan Ostrowski August 2008 c 2008 Krzysztof Jan Ostrowski ALL RIGHTS RESERVED LIVE DISTRIBUTED OBJECTS Krzysztof Jan Ostrowski, Ph.D. Cornell University 2008 Distributed multiparty protocols such as multicast, atomic commit, or gossip are currently underutilized, but we envision that they could be used pervasively, and that developers could work with such protocols similarly to how they work with CORBA/COM/.NET/Java objects. We have created a new programming model and a platform in which protocol instances are represented as objects of a new type called live distributed objects: strongly-typed building blocks that can be composed in a type-safe manner through a drag and drop interface. Unlike most prior object-oriented distributed protocol embeddings, our model appears to be flexible enough to accommodate most popular protocols, and to be applied uniformly to any part of a distributed system, to build not only front-end, but also back-end components, such as multicast channels, naming, or membership services. While the platform is not limited to applications based on multicast, it is replication- centric, and reliable multicast protocols are important building blocks that can be used to create a variety of scalable components, from shared documents to fault-tolerant storage or scalable role delegation. We propose a new multicast architecture compatible with the model and designed in accordance with object-oriented principles such as modu- larity and encapsulation.
    [Show full text]
  • Metrics That Matter Social Software for Business Performance Metrics That Matter
    Metrics that Matter Social Software for Business Performance Metrics that Matter Contents Introduction: When will social software prove itself? | 1 Current approaches to social software will likely fail | 2 Creating and retaining leaders | 3 Social software is essential to meet the challenge of constant change | 6 Extreme performance improvement is achievable | 9 Companies must focus to move the needle on business performance | 12 Long-term benefits of social software are transformative | 20 Conclusion: Social software is worth your time | 23 Appendix | 24 Note: Social software tools considered in this paper include wikis, blogs, microblogs, discussion forums, social networks, social book- marks, tagging, crowdsourcing, and prediction markets. Only internal-facing solutions (Socialcast, Socialtext, Traction, etc.) were in scope, excluding their external-facing equivalents (Twitter, Facebook, etc.). Social Software for Business Performance Introduction: When will social software prove itself? ENIOR executives are skeptical of the that business performance improvements are Svalue of social software. Their reluctance is possible: OSIsoft1 realized a 22% improvement understandable but self-defeating. Social soft- in average time to issue resolution through ware has the potential to address operational the customer support team’s use of Socialtext2 “pain points” and significantly wikis. Alcoa Fastening enhance business perfor- Systems3 experienced a 61% mance in the short–term and reduction in time spent transform it in the long–term. Companies that on compliance activities Companies that embrace embrace this through the use of Traction this opportunity will have a opportunity will Software.4 Both companies distinct advantage over their have a distinct believe these improvements competitors; skeptics will would have been impossible likely finish last.
    [Show full text]
  • Online Research Tools
    Online Research Tools A White Paper Alphabetical URL DataSet Link Compilation By Marcus P. Zillman, M.S., A.M.H.A. Executive Director – Virtual Private Library [email protected] Online Research Tools is a white paper link compilation of various online tools that will aid your research and searching of the Internet. These tools come in all types and descriptions and many are web applications without the need to download software to your computer. This white paper link compilation is constantly updated and is available online in the Research Tools section of the Virtual Private Library’s Subject Tracer™ Information Blog: http://www.ResearchResources.info/ If you know of other online research tools both free and fee based feel free to contact me so I may place them in this ongoing work as the goal is to make research and searching more efficient and productive both for the professional as well as the lay person. Figure 1: Research Resources – Online Research Tools 1 Online Research Tools – A White Paper Alpabetical URL DataSet Link Compilation [Updated: August 26, 2013] http://www.OnlineResearchTools.info/ [email protected] eVoice: 800-858-1462 © 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013 Marcus P. Zillman, M.S., A.M.H.A. Online Research Tools: 12VPN - Unblock Websites and Improve Privacy http://12vpn.com/ 123Do – Simple Task Queues To Help Your Work Flow http://iqdo.com/ 15Five - Know the Pulse of Your Company http://www.15five.com/ 1000 Genomes - A Deep Catalog of Human Genetic Variation http://www.1000genomes.org/
    [Show full text]
  • Enterprise Collaboration & Social Software
    Enterprise Collaboration & Social Software June 2013 INDUSTRY REPORT INSIDE THIS ISSUE Enterprise Collaboration & Social Software 1. Introduction INTRODUCTION 2. Market Trends This report focuses on technologies for collaboration and socialization within the enterprise. A number of forces are currently playing out in the enterprise IT 3. Competitive Landscape environment that are creating an inflection in the adoption and deployment of social and collaboration technologies. This significant uptrend has provided strong 4. M&A Activity growth for the sector and is driving a substantial amount of M&A and investment activity. This report includes a review of the recent M&A and private investing 5. Private Financings activities in enterprise social and collaboration software, particularly within the areas of group collaboration & workspaces, private social platforms, project and 6. Valution Trends social task management, event scheduling, web collaboration, white boarding & diagramming, and other related technologies. We have also profiled about 50 emerging private players in these subcategories to provide an overview of the 7. Emerging Private Companies breadth and diversity of the players targeting this sector. OVERVIEW Socialization and collaboration technologies are currently reshaping the established enterprise collaboration market as well as creating whole new categories of offerings, especially around private social platforms. In addition, many other enterprise applications such as CRM and unified communications are heavily transformed through the incorporation of new technologies including group messaging & activity feeds, document collaboration, and analytics. Much of this change is being driven by the consumerization of IT and the incorporation of social technologies. As businesses look to leverage the benefits of improved “connecting” and “network building” that employees have experienced with Facebook and other social solutions, a convergence is occurring between the enterprise social software and collaboration markets.
    [Show full text]
  • Optimizing Applications for Multicore by Intel Software Engineer Levent Akyil Welcome to the Parallel Universe
    Letter to the Editor by parallelism author and expert James Reinders Are You Ready to Enter a Parallel Universe: Optimizing Applications for Multicore by Intel software engineer Levent Akyil Welcome to the Parallel Universe Contents Think Parallel or Perish, BY JAMES REINDERS .........................................................................................2 James Reinders, Lead Evangelist and a Director with Intel® Software Development Products, sees a future where every software developer needs to be thinking about parallelism first when programming. He first published“ Think Parallel or Perish“ three years ago. Now he revisits his comments to offer an update on where we have gone and what still lies ahead. Parallelization Methodology...................................................................................................................... 4 The four stages of parallel application development addressed by Intel® Parallel Studio. Writing Parallel Code Safely, BY PETER VARHOL ........................................................................... 5 Writing multithreaded code to take full advantage of multiple processors and multicore processors is difficult. The new Intel® Parallel Studio should help us bridge that gap. Are You Ready to Enter a Parallel Universe: Optimizing Applications for Multicore, BY LEVENT AKYIL .............................................. 8 A look at parallelization methods made possible by the new Intel® Parallel Studio—designed for Microsoft Visual Studio* C/C++ developers of Windows* applications.
    [Show full text]
  • April 2006 Volume 31 Number 2
    APRIL 2006 VOLUME 31 NUMBER 2 THE USENIX MAGAZINE OPINION Musings RIK FARROW OpenSolaris:The Model TOM HAYNES PROGRAMMING Code Testing and Its Role in Teaching BRIAN KERNIGHAN Modular System Programming in MINIX 3 JORRIT N. HERDER, HERBERT BOS, BEN GRAS, PHILIP HOMBURG, AND ANDREW S. TANENBAUM Some Types of Memory Are More Equal Than Others DIOMEDIS SPINELLIS Simple Software Flow Analysis Using GNU Cflow CHAOS GOLUBITSKY Why You Should Use Ruby LU KE KANIES SYSADMIN Unwanted HTTP:Who Has the Time? DAVI D MALONE Auditing Superuser Usage RANDOLPH LANGLEY C OLUMNS Practical Perl Tools:Programming, Ho Hum DAVID BLANK-EDELMAN VoIP Watch HEISON CHAK /dev/random ROBERT G. FERRELL STANDARDS USENIX Standards Activities NICHOLAS M. STOUGHTON B O OK REVIEWS Book Reviews ELIZABETH ZWICKY, WITH SAM STOVER AND RI K FARROW USENIX NOTES Letter to the Editor TED DOLOTTA Fund to Establish the John Lions Chair C ONFERENCES LISA ’05:The 19th Large Installation System Administration Conference WORLDS ’05: Second Workshop on Real, Large Distributed Systems FAST ’05: 4th USENIX Conference on File and Storage Technologies The Advanced Computing Systems Association Upcoming Events 3RD SYMPOSIUM ON NETWORKED SYSTEMS 2ND STEPS TO REDUCING UNWANTED TRAFFIC ON DESIGN AND IMPLEMENTATION (NSDI ’06) THE INTERNET WORKSHOP (SRUTI ’06) Sponsored by USENIX, in cooperation with ACM SIGCOMM JULY 6–7, 2006, SAN JOSE, CA, USA and ACM SIGOPS http://www.usenix.org/sruti06 MAY 8–10, 2006, SAN JOSE, CA, USA Paper submissions due: April 20, 2006 http://www.usenix.org/nsdi06 2006
    [Show full text]
  • Understanding Wikis: from Ward’S Brain to Your Browser
    06_043998 ch01.qxp 6/19/07 8:20 PM Page 9 Chapter 1 Understanding Wikis: From Ward’s Brain to Your Browser In This Chapter ᮣ Finding your way to wikis ᮣ Understanding what makes a wiki a wiki ᮣ Comparing wikis with blogs and other Web sites ᮣ Examining the history and future of wikis ᮣ How to start using wikis hen Ward Cunningham started programming the first wiki engine Win 1994 and then released it on the Internet in 1995, he set forth a simple set of rules for creating Web sites that pushed all the technical gob- bledygook into the background and made creating and sharing content as easy as possible. Ward’s vision was simple: Create the simplest possible online database that could work. And his attitude was generous; he put the idea out there to let the world run with it. The results were incredible. Ward’s inventiveness and leadership had been long established by the role he played in senior engi- neering jobs, promoting design patterns, and helping develop the concept of Extreme Programming. That a novel idea like the wiki flowed from his mind onto the COPYRIGHTEDInternet was no surprise to those MATERIAL who knew him. The wiki concept turned out to have amazing properties. When content is in a shared space and is easy to create and connect, it can be collectively owned. The community of owners can range from just a few people up into the thousands, as in the case of the online wiki encyclopedia, Wikipedia. 06_043998 ch01.qxp 6/19/07 8:20 PM Page 10 10 Part I: Introducing Wikis This chapter introduces you to the wonderful world of wikis by showing you what a wiki is (or can be), how to find and use wikis for fun and profit, and how to get started with a wiki of your own.
    [Show full text]
  • The Effects of Wikis on Collaboration Practices in Organizations
    Collaborative Business - The effects of Wikis on collaboration practices in organizations Master Thesis, 15 Credits, Department of Informatics Presented: June, 2008 Authors: Osama Mansour Sahar Monavari Supervisor: Mia Sassén Examiners: Linda Öberg Hans Lundin Lund University Informatics Collaborative Business - The effects of Wikis on collaboration practices in organizations © Osama Mansour © Sahar Monavari Master thesis, presented June 2008 Size: 80 pages Supervisor: Mia Sassén Abstract Wikis and other web 2.0 technologies are increasingly used in business. In this sense, the overall purpose of this research was to investigate the effects of wikis on collaboration and the impact of collaboration on organizational innovation. Four interviews have been conducted with IS managers as well as regular Wiki users in different organizations to show how can wikis affect collaboration and exploit innovation. The results showed that the Wiki is used as a shared platform for collaboration and the ability to participate in the process of knowledge creation in an iterative manner helped in generating more ideas which leads to more innovation. We concluded that the Wiki affects the nature and context of collaboration. The research showed that the use of the wiki for internal collaboration purposes helped organizations to benefit from collective intelligence through allowing everyone within a team or a project to contribute and share ideas and experiences. Also, it showed the use of wikis for external use might be associated with problems such as the reluctance of collaborators to participate in the group work and other problems related to data quality and organizations won’t use it for more open use where information is opened for people outside the organization.
    [Show full text]
  • August 2009 Volume 34 Number 4
    AUGUST 2009 VOLUME 34 NUMBER 4 OPINION Musings 2 Rik Farrow FILE SYSTEMS Cumulus: Filesystem Backup to the Cloud 7 Michael VR able, SteFan SaVage, and geoffrey M. VoelkeR THE USENIX MAGAZINE PROGRAMMinG Rethinking Browser Performance 14 leo MeyeRoVich Programming Video Cards for ­Database Applications 21 tiM kaldewey SECURITY Malware to Crimeware: How Far Have They Gone, and How Do We Catch Up? 35 daVid dittRich HARDWARE A Home-Built NTP Appliance 45 Rudi Van dRunen CoLUMns Practical Perl Tools: Scratch the ­Webapp Itch with CGI::Application, Part 1 56 daVid n. blank-edelMan Pete’s All Things Sun: T Servers—Why, and Why Not 61 PeteR baeR galVin iVoyeur: Who Invited the Salesmen? 67 daVe JoSePhSen /dev/random 71 RobeRt g. Ferrell BooK REVIEWS Book Reviews 74 elizabeth zwicky et al. USEniX NOTES USENIX Lifetime Achievement Award 78 STUG Award 79 USENIX Association Financial Report for 2008 79 ellie young Writing for ;login: 83 ConfERENCES NSDI ’09 Reports 84 Report on the 8th International Workshop on Peer-to-Peer Systems (IPTPS ’09) 97 Report on the First USENIX Workshop on Hot Topics in Parallelism (HotPar ’09) 99 Report on the 12th Workshop on Hot Topics in Operating Systems (HotOS XII) 109 The Advanced Computing Systems Association aug09covers.indd 1 7.13.09 9:21:47 AM Upcoming Events 22n d ACM Sy M p o S i u M o n op e r A t i n g Sy S t e ms 7t H uSENIX Sy M p o S i u M o n ne t w o r k e d Sy S t e ms prinCipleS (SoSp ’09) de S i g n A n d iM p l e M e n t A t i o n (nSDI ’10) Sponsored by ACM SIGOPS in cooperation with USENIX Sponsored
    [Show full text]
  • Database Replication in Large Scale Systemsa4paper
    Universidade do Minho Escola de Engenharia Departamento de Informática Dissertação de Mestrado Mestrado em Engenharia Informática Database Replication in Large Scale Systems Miguel Gonçalves de Araújo Trabalho efectuado sob a orientação do Professor Doutor José Orlando Pereira Junho 2011 Partially funded by project ReD – Resilient Database Clusters (PDTC / EIA-EIA / 109044 / 2008). ii Declaração Nome: Miguel Gonçalves de Araújo Endereço Electrónico: [email protected] Telefone: 963049012 Bilhete de Identidade: 12749319 Título da Tese: Database Replication in Large Scale Systems Orientador: Professor Doutor José Orlando Pereira Ano de conclusão: 2011 Designação do Mestrado: Mestrado em Engenharia Informática É AUTORIZADA A REPRODUÇÃO INTEGRAL DESTA TESE APENAS PARA EFEITOS DE INVESTIGAÇÃO, MEDIANTE DECLARAÇÃO ESCRITA DO INTERESSADO, QUE A TAL SE COMPROMETE. Universidade do Minho, 30 de Junho de 2011 Miguel Gonçalves de Araújo iii iv Experience is what you get when you didn’t get what you wanted. Randy Pausch (The Last Lecture) vi Acknowledgments First of all, I want to thank Prof. Dr. José Orlando Pereira for accepting being my adviser and for encouraging me to work on the Distributed Systems Group at University of Minho. His availability, patient and support were crucial on this work. I would also like to thank Prof. Dr. Rui Oliveira for equal encouragement on joining the group. A special thanks to my parents for all support throughout my journey and particularly all the incentives to keep on with my studies. I thank to my friends at the group that joined me on this important stage of my stud- ies. A special thank to Ricardo Coelho, Pedro Gomes and Ricardo Gonçalves for all the discussions and exchange of ideas, always encouraging my work.
    [Show full text]