http://greg.nokes.name/2008/12/25/filesystem-scaling-in-high-traffic-web-applications/ A wayward journey into the depths of sanity Sun, 29 Aug 2010 22:08:17 +0000 hourly 1 http://wordpress.org/?v=3.0.1 http://greg.nokes.name/2008/12/25/filesystem-scaling-in-high-traffic-web-applications/comment-page-1/#comment-1164 DaRoost » Blog Archive » Scaling Wide Fri, 03 Jul 2009 22:20:50 +0000 http://30/2008/12/27/filesystem-scaling-in-high-traffic-web-applications#comment-1164 [...] If your application is filesystem IOPS heavy, filesystem sharding might be the route that you want to look at. Basically you add more hardware disk arrays, and split the reads and writes between them. You need to inject some logic into the save and open functions in your application so that it knows which filesystem each file is to be saved to and opened from. Usually you create a hash of the filename, and key off the first couple of characters in the hash. You can read more on this technique here. [...] [...] If your application is filesystem IOPS heavy, filesystem sharding might be the route that you want to look at. Basically you add more hardware disk arrays, and split the reads and writes between them. You need to inject some logic into the save and open functions in your application so that it knows which filesystem each file is to be saved to and opened from. Usually you create a hash of the filename, and key off the first couple of characters in the hash. You can read more on this technique here. [...]

]]>