https://www.bibsonomy.org/user/draganigajic/scalabilityBibSonomy RSS Feed for /user/draganigajic/scalabilityWe started High Scalability to help you build successful scalable websites. This site tries to bring together all the lore, art, science, practice, and experience of building scalable websites into one place so you can learn how to build your system with confidence.http://www.highscalability.com/draganigajic2011-07-13T18:13:52+02:00100+ 1k+ scalability <span itemprop="description">We started High Scalability to help you build successful scalable websites. This site tries to bring together all the lore, art, science, practice, and experience of building scalable websites into one place so you can learn how to build your system with confidence.</span>February 17th, 2008 A 'problem' with the Mongrel/Rails platform A request comes in to the web server, and if it's dynamic, falls down to a waiting mongrel process. Mongrel calls Rails which wraps a big lock around most of the request/response cycle so the mongrel thats serving the request has to wait for a response from Rails to unlock and start serving other requests. This is the Blocked Thread stability anti-pattern that Michael Nygard talks about in Release It!. The problem is that Nginx or Apache doesn't know that a mongrel is blocked and keeps blindly sending requests. Thats means that even a single blocked mongrel will result in some slow responses for requests that come in to that same mongrel. Cut the Request Fat And one way to do that is to use the "Skinny Request, Fat Backend" principle. What that means in practical terms is pretty simple: Do as little as possible inside of the Request/Response cycle.http://www.last100meters.com/2008/2/18/skinny-requst-fat-backend-scaling-rails-let-mongrels-breathdraganigajic2011-07-13T18:13:51+02:00! 100+ rails scalability <span itemprop="description">February 17th, 2008 A &#039;problem&#039; with the Mongrel/Rails platform A request comes in to the web server, and if it&#039;s dynamic, falls down to a waiting mongrel process. Mongrel calls Rails which wraps a big lock around most of the request/response cycle so the mongrel thats serving the request has to wait for a response from Rails to unlock and start serving other requests. This is the Blocked Thread stability anti-pattern that Michael Nygard talks about in Release It!. The problem is that Nginx or Apache doesn&#039;t know that a mongrel is blocked and keeps blindly sending requests. Thats means that even a single blocked mongrel will result in some slow responses for requests that come in to that same mongrel. Cut the Request Fat And one way to do that is to use the &#034;Skinny Request, Fat Backend&#034; principle. What that means in practical terms is pretty simple: Do as little as possible inside of the Request/Response cycle.</span>points to frontpage onlyhttp://www.highscalability.com/friends-sale-architecture-300-million-page-view-month-facebook-ror-appdraganigajic2011-07-13T18:13:51+02:00! 100+ rails ruby scalability <span itemprop="description">points to frontpage only</span>points to frontpage onlyhttp://www.highscalability.com/scaling-twitter-making-twitter-10000-percent-fasterdraganigajic2011-07-13T18:13:51+02:00! 100+ scalability twitter <span itemprop="description">points to frontpage only</span>or what we learned building slidesharehttp://www.slideshare.net/jboutelle/scalable-web-architectures-w-ruby-and-amazon-s3-14894/draganigajic2011-07-13T18:13:51+02:00amazon presentation ruby s3 scalability slideshare <span itemprop="description">or what we learned building slideshare</span>http://code.google.com/p/scalr/draganigajic2011-07-13T18:13:46+02:00100+ EC2 aws deployment googlecode hosting scalability software <a itemprop="url" data-versiondate="2011-07-13T18:13:46+02:00" href="http://code.google.com/p/scalr/" rel="nofollow" class="description-link">http://code.google.com/p/scalr/</a>* Cost: $242 / mo. * CPU: AMD Single CPU Dual Core Athlon 3800 * Memory: 2GB * Bandwidth: 2000GBhttp://shanti.railsblog.com/how-7-mongrels-handled-a-550k-pageview-digging/draganigajic2011-07-13T18:13:45+02:00100+ blogpost rails scalability webserver <span itemprop="description">* Cost: $242 / mo. * CPU: AMD Single CPU Dual Core Athlon 3800 * Memory: 2GB * Bandwidth: 2000GB</span>http://highscalability.com/scaling-out-mysqldraganigajic2011-07-13T18:13:43+02:00db mysql scalability <a itemprop="url" data-versiondate="2011-07-13T18:13:43+02:00" href="http://highscalability.com/scaling-out-mysql" rel="nofollow" class="description-link">http://highscalability.com/scaling-out-mysql</a>http://highscalability.com/product-supervisor-monitor-and-control-your-processesdraganigajic2011-07-13T18:13:43+02:00distributed linux monit monitoring python scalability supervisor <a itemprop="url" data-versiondate="2011-07-13T18:13:43+02:00" href="http://highscalability.com/product-supervisor-monitor-and-control-your-processes" rel="nofollow" class="description-link">http://highscalability.com/product-supervisor-monitor-and-control-your-processes</a>http://people.planetpostgresql.org/xzilla/index.php?/archives/338-Disaster-recovery-at-1000-GBs.htmldraganigajic2011-07-13T18:13:38+02:00backup db postgresql scalability <a itemprop="url" data-versiondate="2011-07-13T18:13:38+02:00" href="http://people.planetpostgresql.org/xzilla/index.php?/archives/338-Disaster-recovery-at-1000-GBs.html" rel="nofollow" class="description-link">http://people.planetpostgresql.org/xzilla/index.php?/archives/338-Disaster-recovery-at-1000-GBs.html</a>http://highscalability.com/skype-plans-postgresql-scale-1-billion-usersdraganigajic2011-07-13T18:13:38+02:00100+ blogpost db postgresql scalability <a itemprop="url" data-versiondate="2011-07-13T18:13:38+02:00" href="http://highscalability.com/skype-plans-postgresql-scale-1-billion-users" rel="nofollow" class="description-link">http://highscalability.com/skype-plans-postgresql-scale-1-billion-users</a>http://highscalability.com/hscale-handling-200-million-transactions-month-using-transparent-partitioning-mysql-proxydraganigajic2011-07-13T18:13:38+02:00blogpost db mysql scalability <a itemprop="url" data-versiondate="2011-07-13T18:13:38+02:00" href="http://highscalability.com/hscale-handling-200-million-transactions-month-using-transparent-partitioning-mysql-proxy" rel="nofollow" class="description-link">http://highscalability.com/hscale-handling-200-million-transactions-month-using-transparent-partitioning-mysql-proxy</a>http://highscalability.com/draganigajic2011-07-13T18:13:25+02:00100+ 1k+ scalability <a itemprop="url" data-versiondate="2011-07-13T18:13:25+02:00" href="http://highscalability.com/" rel="nofollow" class="description-link">http://highscalability.com/</a>http://research.yahoo.com/node/2104draganigajic2011-07-13T18:13:20+02:00100+ cloudComputing hadoop java mapReduce presentation scalability slides video yahoo <a itemprop="url" data-versiondate="2011-07-13T18:13:20+02:00" href="http://research.yahoo.com/node/2104" rel="nofollow" class="description-link">http://research.yahoo.com/node/2104</a>http://code.google.com/p/cloudtools/draganigajic2011-07-13T18:13:19+02:00100+ amazon aws cloudComputing cluster ec2 googlecode java maven s3 scalability <a itemprop="url" data-versiondate="2011-07-13T18:13:19+02:00" href="http://code.google.com/p/cloudtools/" rel="nofollow" class="description-link">http://code.google.com/p/cloudtools/</a>http://zookeeper.sourceforge.net/draganigajic2011-07-13T18:13:18+02:00100+ computing database distributed hadoop scalability yahoo <a itemprop="url" data-versiondate="2011-07-13T18:13:18+02:00" href="http://zookeeper.sourceforge.net/" rel="nofollow" class="description-link">http://zookeeper.sourceforge.net/</a>http://highscalability.com/heroku-simultaneously-develop-and-deploy-automatically-scalable-rails-applications-clouddraganigajic2011-07-13T18:13:18+02:00! Heroku aws ec2 hosting rails ruby rubyonrails scalability sysadmin virtualization <a itemprop="url" data-versiondate="2011-07-13T18:13:18+02:00" href="http://highscalability.com/heroku-simultaneously-develop-and-deploy-automatically-scalable-rails-applications-cloud" rel="nofollow" class="description-link">http://highscalability.com/heroku-simultaneously-develop-and-deploy-automatically-scalable-rails-applications-cloud</a>http://strokedb.com/draganigajic2011-07-13T18:13:17+02:00! *read 100+ DB couchdb database distributed erlang git orm persistence ruby scalability storage webdev <a itemprop="url" data-versiondate="2011-07-13T18:13:17+02:00" href="http://strokedb.com/" rel="nofollow" class="description-link">http://strokedb.com/</a>http://blog.evanweaver.com/articles/2008/05/27/is-twitter-still-the-biggest-rails-site/#comment-029draganigajic2011-07-13T18:13:11+02:00blogpost discussion performance rails ruby scalability twitter <a itemprop="url" data-versiondate="2011-07-13T18:13:11+02:00" href="http://blog.evanweaver.com/articles/2008/05/27/is-twitter-still-the-biggest-rails-site/#comment-029" rel="nofollow" class="description-link">http://blog.evanweaver.com/articles/2008/05/27/is-twitter-still-the-biggest-rails-site/#comment-029</a>http://www.datacenterknowledge.com/archives/2008/Jun/23/video_jeff_deans_google_io_presentation.htmldraganigajic2011-07-13T18:13:09+02:00*watch datacenter google scalability video <a itemprop="url" data-versiondate="2011-07-13T18:13:09+02:00" href="http://www.datacenterknowledge.com/archives/2008/Jun/23/video_jeff_deans_google_io_presentation.html" rel="nofollow" class="description-link">http://www.datacenterknowledge.com/archives/2008/Jun/23/video_jeff_deans_google_io_presentation.html</a>