The present invention is a method for providing error correction for an array of disks (828) using non-volatile random access memory (NV-RAM) (816). Non-volatile RAM (816) is used to increase the speed of RAID recovery from a disk error(s). This is done by listing of all blocks for which the parity is possibly inconsistent. This list of blocks is much smaller than the total number of parity blocks (820) in the RAID. The total number of parity blocks (820) in the RAID (828) is in the range of hundreds of thousands. Knowledge of the number of parity blocks that are possibly inconsistent makes it possible to fix only those few blocks, identified in the list, resulting in a significant time savings. The technique for safely writing to a RAID with a broken disk is complicated. In this technique, data that can become corrupted is copied into NV-RAM (816) before the potentially corrupting operation is performed.
展开▼
