The benchmark is written in C and can simulate several processes writing fixed size blocks concurrently into multiple files. The location for the write operations is given by NURand function from TPC-C benchmark that generates hotspots for I/O operations. A default distribution identical to the one found in our group’s personal files, presenting a subset of the type of data one could find at a cloud provider, is used to generate the blocks’ content. However, in the future, it will be possible to use other distributions and load them from a custom file. DEDISbench provides two workload modes, one reproduces a fully or peak loaded system, as Bonnie++, that performs as maximum write I/O operations per second as possible. The second reproduces a system under a reasonable nominal load, and can be useful for understanding the behavior of aliasing operations in a stable system with a limited I/O throughput.

I/O read Benchmark:

The benchmark can also evaluate read I/O operations, with the NURand distribution for I/O accesses and a peak or nominal load.