| 摘要 |
In a RAID level 5 disk drive subsystem, one or more additional disk drives, called "reserve" disks are intercoupled to the array of disk drives and a control system is included for storing recovered digital data on the additional disk drive if a sector on one of the disk drives becomes defective. The system reduces the number of disk accesses required to obtain the information stored on the defective sector. Once the information has been recovered, it is then stored on the "reserve" disk. Thereafter, whenever this information is required, the system reads the required information from the "reserve" disk, instead of going through an entire recovery process for the defective sector. Since the recovery process can take a time that is greater than several disk access times, the present invention improves the speed and the availability of data. In another embodiment of the invention, a bitmap memory is used wherein bits in the bitmap memory representing sectors may be set to indicate whether or not sectors are defective. In a further embodiment of the invention, a disk drive tester, which can be embodied in either hardware or software, is incorporated into the apparatus for periodically testing the "reserve" disk.
|
