We will, in this thesis, closely investigate the performance of SSDs andmagnetic disks. Looking at physical attributes of these two disk technolo-gies, we will try to give an understanding of how they perform in dif-ferent scenarios based on real workloads. Based on what we learn frominvestigating the performance in these scenarios, we will try to get an un-derstanding of what performance issues the different storage technologiesfaces. We will look at how optimizations in Operating System (OS) and atapplication-level have an impact on SSDs and magnetic disks, as well aswhat we can do to achieve best possible performance.
In our benchmarks, we show that early generation SSD suffer from writeamplification, and will, because of that, have problems achieving goodperformance on random write operations. By introducing a log-basedfile system, we see that we can remove the effect of write amplificationreceived by random write operations, and give us a more stable perfor-mance. We discuss, and benchmark, possible alternatives for optimizingexisting applications for magnetic disks, by introducing SSDs, as an alter-native to magnetic disks as storage device. By going from high-end mag-netic disks to SSDs, we see that we, in some cases, can achieve orders ofmagnitude better performance, without changing application level code.