| 摘要 |
FAULT-TOLERANT, ERROR-CORRECTING STORAGE SYSTEM A storage device system (40) for computers capable of dynamically and transparently reconstructing lost data is described comprising a plurality of first individual storage devices (16) for storing digital nformation and a second individual storage device (16) for storage devices (16') for storing error/recovery code bits. There is logic for generating and storing error/recovery code bits in the second individual storage device (16') according to a pre-defined parity checking algorithm for the digital information and logic for using the error/recovery code bits to reconstruct a changed bit in error in the digitalo information according to the parity checking algorithm. An interface (60, 56, 46, 18, 14) is disposed to receive read and write requests from a user CPU (10, 54) and a plurality of storage device controllers (60') are connected between the interface and respective ones of the plurality of storage devices (16) for interfacing with the plurality of storage devices (16) and operating them concurrently. The CPU (44) includes logic (48) for immediately acknowledging a write to an associated storage device (16) upon the data being placed in a buffer memory (64), for checking data in the buffer memory (64) and indicating it as having been read from an associated storage device (16) without an actual read thereof when a read request therefor is received from a user (10, 54) whereby the buffer memory (64) acts as a cache memory in such cases. |
