1) For hardware you want cheap, expendable, bare metal. Look up posts about how Google built their own servers for reference. 2) For RAID, go with software only RAID. You will sidestep problems caused by hardware RAID controllers having custom data format each (i.e. non-swapable for different model/make). 3) For filesystem, look for OpenAFS. CERN is using OpenAFS to store petabytes of data from LHC. 4) For operating system, look at Debian. Coupled with FAI (fully automated installation), it will enable you to deploy multiple servers in an automated way, to host your files.