2.1. Storage Devices
Cloud computing and other extensive storage demanding applications have been placing ever-greater demands on storage systems. Surveillance systems placed in private and public places are generating massive video content that need to be stored and processed real-time or later as situations warrant (Sahu et al., 2011). Data mining for patterns, face recognition algorithms, and other data extensive applications have been requiring higher processing power and fast access to data. For instance, face recognition applications have to process captured video-feed real-time in order to identify criminals walking in train stations or other public areas (Zhang et al., 2015; Zhang et al., 2014).
Redundant Array of Inexpensive Disks (RAID) has been a dominant technology for performance improvement and reliability of storage systems. A RAID system is an arrangement of two or more independent drives configured to work in parallel (Chen et al., 1994). Standard hard disks are the most used; however, the use of SSD technology has recently been flourishing. Different RAID configurations are optimized for different situations. RAID implementations include striping (RAID 0), mirroring (RAID 1), striping with parity (RAID 5), and striping with double parity (RAID 6). Moreover, more advanced configurations called Nested (Hybrid) RAID (Vijayan, et al. 1995) or top arrays have been developed to accommodate more size, performance, and reliability. For instance, storage systems might combine mirroring and striping, originally denoted as RAID 1+0, which yields RAID 10 when the + is omitted. Similarly, combining the distributed parity of RAID 5 and the striping of RAID 0 yields RAID 50 (Layton, 2011).