RAID-6 system reliability dependence on recovery, disk scrubbing, and group size
Jon G. Elerath · 2016
Analyses of 108 combinations of hard disk drive failure, restoration, latent defect and scrubbing distributions were analyzed. A subset of 8 combinations for 2 different RAID group sizes are presented to illustrate the impact that RAID group size, recovery times, and disk scrubbing of latent defect has on the occurrence of system (RAID group) failures for 10 years. Increasing the group size or extending the recovery or scrub times increases the expected number of failures, but the increase is not predictable based on the input distributions. RAID group data loss events show the same time-dependence, increasing or decreasing, as the HDD operational failures.