New Techniques for Modeling File Data Distribution on Storage Nodes

This paper presents a new probabilistic model which describes the way data blocks belonging to a certain file are distributed along the disk in general purpose systems. The distribution type is classified depending on the kind of File System, the file size and the disk occupancy ratio. The resulting algorithm will be used to simulate the access timeto the data stored on a disk of an I/O node, where the position of data blocks determines the access time. In orderto perform the modeling, some parameters have been estimatedusing some stress tests with different degrees of diskoccupancy and file sizes on Ext2 and ReiserFS File Systems.