Storage Architecture With Integrity, Redundancy and Encryption
The authors propose a storage system that treats confidentiality, integrity and availability of data in a unified manner. Extending RAID6, it allows for failures of multiple disks, encrypts data on disk, and stores checksums to detect faulty data without disks failing, which occurs e.g. in solid state disks due to wear out of cells. By handling encryption and integrity check together, the probability of undetected faulty data is reduced further. They provide an implementation, i.e. a driver, which encapsulates all these features and uses parallel algorithms exploiting multicore processor performance to match the bandwidth available from multiple disks. They present performance figures of their experiments.