PrintV:Drive - Adaptive Storage Virtualization
The Project
The efficient use of a storage system can be significantly enhanced by the integration of a virtualization solution. Storage virtualization transform between a logical address space, which is presented to the servers and the access to the physical disks. It is possible to combine the capacity of many storage systems into one or several big storage pools. Virtual disks are built from these storage pools without that the user has to worry about the limitations of the underlying hardware. The aim of this project is to develop efficient strategies for the redundant distribution of data and to integrate them into a storage management environment.
An important task is the distribution of data over the connected storage subsystems. Conventional approaches have serious drawbacks concerning the efficient use of the storage systems. Neither the capacity nor the bandwidth of the storage systems can be utilized in an adequate fashion, especially if a redundant data placement is needed.
Our Mission
The aim of this project is to develop scalable, adaptive data distribution algorithms, which are mostly based on randomized hashing schemes. We have integrates many of these algorithms into an out-of-band virtualization framework, which is based on a meta-data appliance and kernel drivers for the Linux 2.6 operating system.
