Closing the Gap of Write- vs. Read-intensive Data Stores Using SSDs

In this project, new storage approaches for big data will be explored. Key point is the efficient use of modern hardware, especially modern storage technology such as SSDs. These new technologies have highly improved performance in comparison to traditional hardware. However, classical data structures and algorithms can not directly be applied due to the different characteristics of these devices. Also, the high cost of the new technology makes their exclusive use uneconomical in many cases. Therefore, hybrid storage approaches will be investigated that efficiently use modern and traditional technologies in a combined fashion thus leveraging both. This research has the potential to impact all existing key-value stores and database management systems alike. Methodology: Our focus is to fundamentally rethink write-intensive data structures (e.g. the log-structured merge tree) in the light of modern hardware including but not limited to solid state drives (SSDs). There are major differences between SSDs and traditional disk drives, for which the current write-intensive structures are designed...

Tilmann Rabl
Faculty Supervisor: 
Dr. Hans Arno-Jacobsen
Project Year: