2007/01/26 by Jim Gray, Gray, Jim, Catharine van Ingen +1
Computer Science · #Advanced Data Storage Technologies #Databases (cs.DB) #Distributed systems and fault tolerance #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Parallel Computing and Optimization Techniques #cs.AR #cs.DB
paper · pdf · doi:10.48550/arxiv.cs/0701166
arxiv created 2007/01/26 · openalex publication_date 2007/01/26 · arxiv updated 2009/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The SATA advertised bit error rate of one error in 10 terabytes is frightening. We moved 2 PB through low-cost hardware and saw five disk read error events, several controller failures, and many system reboots caused by security patches. We conclude that SATA uncorrectable read errors are not yet a dominant system-fault source - they happen, but are rare compared to other problems. We also conclude that UER (uncorrectable error rate) is not the relevant metric for our needs. When an uncorrectable read error happens, there are typically several damaged storage blocks (and many uncorrectable read errors.) Also, some uncorrectable read errors may be masked by the operating system. The more meaningful metric for data architects is Mean Time To Data Loss (MTTDL.)