Abstract
Recently, the demand of low cost large scale storages increases. We developed VLSD (Virtual Large Scale Disks) toolkit for constructing virtual disk based distributed storages, which aggregate free spaces of individual disks. However, in order to construct large-scale storage, more than or equal to 3 fault tolerant RAID is important. The relationship between fault tolerance and capacity efficiency is trade-off. RAID1 is the most fault tolerant RAID in all of basic RAID classes. Indeed, RAID1 that consists of N disks can realize N-1 fault tolerance easily. We implemented RAID1 that supports N elementary disks. However, RAID has weakness to dynamic Byzantine failures or attacks. So, we developed RAIDv, voted RAID1 based on NMR (N Modular Redundancy). Although RAIDv has fault tolerance of dynamic failures, the fault tolerance of static failures is less than RAID1. In this paper, we have proposed Stateful RAIDv, RAIDv based on Stateful NMR. In Stateful NMR, voted result is always correct iff the state of at most one module is changed simultaneously and at least one module is normal. We also implement Stateful RAIDv and evaluate it. The fault tolerance of Stateful RAIDv is nearly equal to RAID1 if the repair rate is low.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
