Abstract: A method for data access is disclosed. The method includes: receiving a file access request; acquiring one or more node lists corresponding to the file, wherein each node list comprises at least two nodes, and the mutually corresponding disks between the respective nodes store the same contents; accessing data chunks included in the file from the respective nodes selected from each of the node lists; and when an accessing from a certain node fails, selecting another node from the node list that comprises the certain node, and accessing a respective data chunk included in the file from the selected node according to the identifier of the file. A system and a device with tolerance of disk fault are also disclosed.

Abstract: It is described a bad disk block self-detection method, including: each mounted chunk is partitioned into n sub-chunks, all sub-chunks having a same size, where n is an integer not less than 2; checking information is set at a fixed location of each sub-chunk, data is stored onto locations of each sub-chunk other than the fixed location, where the checking information is parity checking information for the data; and when the data is read or written, data verification is performed based on the checking information set at the fixed location of the read sub-chunk. It is also described a bad disk block self-detection apparatus and a computer storage medium. With the described above, the bad block on the disk can be detected rapidly, and it is able to instruct data migration and disk replacement.

Abstract: A method for recovering hard disk data, a server and a distributed storage system relate to a computer technology. In the method, a data recovery request is received. The request includes at least one ID of sectors whose data is to be recovered. Based on the at least one ID of the sectors whose data is to be recovered, at least one sector whose data is to be recovered is located. Obtain at least one standby sector ID and a file backup corresponding to the at least one ID of the sectors whose data is to be recovered, and locate at least one standby sector based on the at least one standby sector ID. Write, into the at least one standby sector, data that is in the file backup and the same as the data stored in the at least one sector whose data is to be recovered.

Abstract: A method, apparatus and system for storing and reading the directory index and belongs to the field of computer technology is provided. The method includes: configuring all directories in the directory index with identifiers respectively; according to each directory identifier, splitting the directory index so as to obtain the directory split item corresponding to each directory identifier, wherein each directory split item and its corresponding directory identifier are stored as a record item, and each directory split item comprises at least corresponding sub-directory identifier and corresponding file storage address. By the configuration of the disclosure, the granularity of the directory index is refined, and access performance for the directory index is improved.

Abstract: The present invention relates to disk fault tolerance method, device and system which relates to a field of computer. The method comprises: receiving a file access request; acquiring one or more node lists corresponding to the file, wherein each node list comprises at least two nodes, and the mutually corresponding disks between the respective nodes store the same contents; accessing data chunks included in the file from the respective nodes selected from each of the node lists; and when an accessing from a certain node fails, selecting another node from the node list that comprises the certain node, and accessing a respective data chunk included in the file from the selected node according to the identifier of the file. The present invention proposes a multilevel pairing storage technology in combination with advantages of the dual machine duplexing mechanism, wherein a plurality of completely independent machines are mutually backed up from a node level to a disk level.