| 摘要 |
Implementations of this invention provide improved technology for storage-device activation control in high-availability storage systems and tracking of in-service data statistics of storage-devices. Typical high-availability storage systems include a fault-tolerant redundant array of storage devices, such as disk drives. The invention may be implemented with one or more inactive (un-powered) drives physically installed in the storage system, but not part of the present fault-tolerant redundant array of disk drives. When a drive fails, one of the inactive drives is activated (powered-on) and it replaces the failed disk and becomes part of the present array. With the newly activated disk included, the data is reconstructed and the original fault-tolerance level is restored. Furthermore, the invention may be implemented so that it tracks the actual in-service time of the storage devices (such as disk drives). Field-derived, empirical data about actual in-service time of storage devices is collected and transmitted to a central data collection system. Using this actual data as a basis, a much more accurate MTBF may be calculated than the MTBF conventionally calculated.
|
