Large archival storage systems experience long periods of idleness broken up by rare data accesses. These systems can loose data for a variety of reasons. Such failures can occur at the device level or at the block level. To deal with these failures, we need to detect them early enough to be able to use the redundancy built into the storage system. We propose a system where drives are periodically accessed to detect drive failure, and where we read all the archived data on all the disks to detect block failures and compensate for them. We research the impact of "disk scrubbing" and its scheduling.

No abstract

For three decades, Kryder's law correctly predicted an exponential increase in bit density on disk platters, leading to an exponential drop in cost per gigabyte, and thus to an entrenched expectation that if data could be stored for a few years the incremental cost of storing it forever would be minimal. However, disk now is over 7 times as expensive as Kryder's law would have predicted, and industry projections suggest that in 2020 the gap will reach 200 times, disrupting this expectation.Our model shows that archives based upon alternative media are surprisingly cost competitive with archives based upon traditional disk media over the long-term. We propose using Archival Flash for long-term data preservation, with the trade off between longer data retention period and lower write cycles.

P2P storage systems must protect data against temporary unavailability and the effects of churn in order to become platforms for safe storage. This paper evaluates and compares redundancy techniques for P2P storage according to availability, accessibility, and maintainability using traces and theoretical results.