| 摘要 |
A system and method for storing data in a storage system having storage elements arranged in parallel for concurrent access such that data can be continuously communicated to the storage element array while one of the storage elements is in error recovery. Some of the storage elements receive data of a stripe and the remaining storage elements receive parity information based on the data of the stripe. An unresponsive storage element in error recovery is dropped from the other storage elements for receiving data until error recovery is complete and the storage element is responsive for receiving data. While the storage element is unresponsive, one of the storage elements scheduled to receive parity information receives data to be written to the unresponsive storage element instead of the parity information. Communication to the storage elements continues while the failed storage element is in error recovery. Error recovery is accomplished by using the parity information of the other parity information storage elements. |
