A memory controller includes an error correction code engine, a buffer memory and a microprocessor. In response to a first decoding result of predetermined data, the microprocessor performs a repeated read operation on a memory device to obtain multiple read results of a data chunk having the predetermined data. The data chunk includes multiple bits. The microprocessor further performs a data reconstruction and error correction procedure according to the read results of the data chunk. In an operation of data reconstruction, the microprocessor determines a bit value corresponding to each bit in the data chunk according to the read results of the data chunk to generate a reconstructed data chunk. In an operation of error correction, the microprocessor provides the reconstructed data chunk to the error correction code engine to obtain a second decoding result of the predetermined data.

Techniques described and suggested herein include systems and methods for optimizing performance characteristics by differentiating data storage device types for data archives stored on data storage systems using redundancy coding techniques. For example, redundancy coded shards, which may include identity shards that contain unencoded original data of archives, may be stored on different types of data storage devices to optimize for various retrieval use cases and implemented environments. Implementing systems may monitor various performance characteristics so as to adaptively account for changes to some or all of the monitored parameters.

A storage management technique involves: selecting a first disk from a plurality of disks in a storage system as an anchor disk; allocating a first backup slice from the plurality of disks to a redundant array of independent disks (RAID) associated with the first disk, the first RAID including at least a slice allocated from the first disk; and if it is detected that there is an inaccessible disk in the plurality of disks, determining a backup slice for a slice of the inaccessible disk based on the allocation of the first backup slice to the first RAID, for use in data reconstruction of the inaccessible disk. This can ensure that a backup slice can always be successfully determined for slices of an inaccessible disk without introducing additional time complexity.

Methods and systems for enhanced error recovery are described. A first one or more data blocks to write to a first drive are received by a first drive controller module. A first parity block is calculated by the first drive controller module based on a first data block parity group. The first one or more data blocks are written by the first drive controller module to the first drive. The first parity block is written by the first drive controller module to the first drive.

A method, non-transitory computer readable medium and computing device that determines in response to an event when currently owned spare data storage devices by one of a pair of storage node computing devices in a high availability pair are insufficient to satisfy a requirement for the event for one or more additional spare data storage devices having one or more data storage device parameters. One or more currently owned spare data storage devices by the other one of the storage node computing devices sufficient to satisfy the requirement are identified. The identified one or more currently owned spare data storage devices owned by the other one of the pair of storage node computing devices that satisfy the requirement are assigned to the one of the pair of storage node computing devices.

Embodiments herein provide a method for controlling operations of a Redundant Array of Independent Disks (RAID) data storage system comprising a host device and a plurality of solid-state drives (SSDs). The method includes performing, by the at least one SSD, recovery of lost data by performing the auto-rebuild operation. The method also includes performing by the at least one SSD, the auto-error correction operation based on the IO error. The method also includes creating a snapshot of an address mapping table by all SSDs of the plurality of SSDs in the RAID data storage system. The auto-rebuild operation, the auto-error correction operation and the creation the snapshot of the address mapping table are all performed without the intervention from the host device.

A method comprising: receiving, at a vector processor, a request to store data; performing, by the vector processor, one or more transforms on the data; and directly instructing, by the vector processor, one or more storage device to store the data; wherein performing one or more transforms on the data comprises: erasure encoding the data to generate n data fragments configured such that any k of the data fragments are usable to regenerate the data, where k is less than n; and wherein directly instructing one or more storage device to store the data comprises: directly instructing the one or more storage devices to store the plurality of data fragments.

A storage array includes a plurality of hard disks, where each of the hard disks is divided into a plurality of chunks, and a plurality of chunks of different hard disks form a chunk group by using a redundancy algorithm. The storage array obtains fault information of a faulty area in a first hard disk, and determines a faulty chunk storing the lost data according to the fault information. The storage array recovers the data in the faulty chunk by using another chunk in a chunk group to which the faulty chunk belongs and stores the recovered data in a recovered chunk. The recovered chunk is located in a second hard disk which is not a hard disk for forming the chunk group.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for maintaining fault tolerance for new writes in a storage system when one or more components of the storage system are unavailable. One of the methods includes determining that one or more first disks of a capacity object of a storage system are unavailable, wherein the storage system comprises a segment usage table identifying the plurality of segments of the capacity object; in response: identifying a plurality of available second disks, adding a plurality of new segments corresponding to the second disks to the capacity object, and adding data identifying the plurality of new segments to the segment usage table; and for each of one or more new write requests to the capacity object: identifying an available segment from the plurality of new segments, and writing data associated with the new write request to the identified available segment.

A technique for repairing a RAID (Redundant Array of Independent Disks) group in a data storage system following a failure of a disk drive in the RAID group includes identifying regions of the failed disk drive that supported unallocated storage extents and writing predetermined data to corresponding regions of the spare disk drive. Any reading of other disk drives in the RAID group may thus be limited only to those regions of the failed disk drive that supported allocated storage extents.