| 摘要 |
The present disclosure includes systems and techniques relating to implementing fault tolerant data storage in solid state memory. In some implementations, a method includes receiving data to be stored, dividing data into logical data blocks, assigning the blocks to a logical block grouping comprising at least one physical data storage block from two or more of multiple solid state physical memory devices, storing the blocks in physical data storage blocks, determining a code that corresponds to the persisted data, and storing the code that corresponds to the data stored in the logical block grouping. Blocks of damaged stored data may be recovered by identifying the logical data block and logical block grouping corresponding to the damaged physical data storage block, reading the data and the code stored in the identified grouping, and comparing the code to the read data other than the data stored in the damaged block.
|
