J Supercomput (2008) 46: 108–123 DOI 10.1007/s11227-007-0159-8 RAID0.5: design and implementation of a low cost disk array data protection method John A. Chandy Published online: 6 December 2007 © Springer Science+Business Media, LLC 2007 Abstract RAID has long been established as an effective way to provide highly re- liable as well as high-performance disk subsystems. However, reliability in RAID systems comes at the cost of extra disks. In this paper, we describe a mechanism that we have termed RAID0.5 that enables striped disks with very high data reliability but low disk cost. We take advantage of the fact that most disk systems use offline backup systems for disaster recovery. With the use of these offline backup systems, the disk system needs to only replicate data since the last backup, thus drastically reducing the storage space requirement. Though RAID0.5 has the same data loss characteristics of traditional mirroring, the lower storage space comes at the cost of lower availability. Thus, RAID0.5 is a tradeoff between lower disk cost and lower availability while still preserving very high data reliability. We present analytical reliability models and ex- perimental results that demonstrate the enhanced reliability and performance of the proposed RAID0.5 system. Keywords Storage · RAID · Availability · Reliability 1 Introduction Disk arrays have long been used to improve the performance of storage systems [8, 13]. The parallelism inherent in multi-disk systems can significantly boost both the throughput and response times as compared to a single disk system. However, the increased performance comes at the cost of lower reliability. As a result, disk arrays need some form of redundancy to improve reliability. The most common and cost effective solution to improve the reliability of disk systems is the use of Redundant Array of Inexpensive (or Independent) Disks (RAID) [11]. A RAID system stripes J.A. Chandy ( ) University of Connecticut, Storrs, CT, USA e-mail: john.chandy@uconn.edu