Quantum Corporation

A method for product decoding within a data storage system includes receiving data to be decoded within a first decoder; performing a plurality of decoding iterations to decode the data utilizing a first decoder and a second decoder; and outputting fully decoded data based on the performance of the plurality of decoding iterations. Each of the plurality of decoding iterations includes (i) decoding the data with the first decoder operating at a first decoder operational mode to generate once decoded data; (ii) sending the once decoded data from the first decoder to the second decoder; (iii) receiving error information from the first decoder with an artificial intelligence system; (iv) selecting a second decoder operational mode based at least in part on the error information that is received by the artificial intelligence system; and (v) decoding the once decoded data with the second decoder operating at the second decoder operational mode to generate twice decoded data; and outputting fully decoded data based on the performance of the plurality of decoding iterations.

A method for product decoding within a data storage system includes receiving data to be decoded within a first decoder; performing a plurality of decoding iterations to decode the data utilizing a first decoder and a second decoder; and outputting fully decoded data based on the performance of the plurality of decoding iterations. Each of the plurality of decoding iterations includes (i) decoding the data with the first decoder operating at a first decoder operational mode to generate once decoded data; (ii) sending the once decoded data from the first decoder to the second decoder; (iii) receiving error information from the first decoder with an artificial intelligence system; (iv) selecting a second decoder operational mode based at least in part on the error information that is received by the artificial intelligence system; and (v) decoding the once decoded data with the second decoder operating at the second decoder operational mode to generate twice decoded data; and outputting fully decoded data based on the performance of the plurality of decoding iterations.

Example apparatus and methods control whether and when hybrid rateless Reed Solomon (RS) error correcting codes (ECC) for a message are produced, stored, and distributed. The control may be based on a property (e.g., reliability, error state, speed) of a message recipient. Example apparatus and methods may also control whether and when fountain codes for the message are produced, stored, and distributed. Once again, the control may be based on a property of a message or ECC recipient. Both the hybrid rateless RS ECC and the fountain codes may be produced from data stored in a modified RS matrix. The modified RS matrix may store row-centric error detection codes (EDC) instead of conventional cyclic redundancy check (CRC) characters. The modified RS matrix may store column-centric ECC that may be produced serially. Different types or numbers of ECC may be produced, stored, and provided for different messages stored at different recipients.

Systems, methods, and circuitries are provided for supporting distributed erasure coding in a shared file system. In one example, a method is provided to be performed by an initiator device configured to read and write data in files stored in a plurality of storage nodes that are controlled by a file management system. The method includes generating a stripe by identifying data to be stored in a storage system; dividing the data into K data segments; and performing an erasure encoding operation on the K data segments to generate a parity segment, wherein the stripe includes the K data segments and the parity segment. The method includes requesting, from the file management system, respective memory allocations in the storage devices for storing respective segments of the stripe; and transmitting, to each of the plurality of storage nodes, a respective instruction to store a respective data or parity segment in the memory allocation on the respective storage device.

Example apparatus and methods control whether and when hybrid rateless Reed Solomon (RS) error correcting codes (ECC) for a message are produced, stored, and distributed. The control may be based on a property (e.g., reliability, error state, speed) of a message recipient. Example apparatus and methods may also control whether and when fountain codes for the message are produced, stored, and distributed. Once again, the control may be based on a property of a message or ECC recipient. Both the hybrid rateless RS ECC and the fountain codes may be produced from data stored in a modified RS matrix. The modified RS matrix may store row-centric error detection codes (EDC) instead of conventional cyclic redundancy check (CRC) characters. The modified RS matrix may store column-centric ECC that may be produced serially. Different types or numbers of ECC may be produced, stored, and provided for different messages stored at different recipients.

Example apparatus and methods control whether and when hybrid rateless Reed Solomon (RS) error correcting codes (ECC) for a message are produced, stored, and distributed. The control may be based on a property (e.g., reliability, error state, speed) of a message recipient. Example apparatus and methods may also control whether and when fountain codes for the message are produced, stored, and distributed. Once again, the control may be based on a property of a message or ECC recipient. Both the hybrid rateless RS ECC and the fountain codes may be produced from data stored in a modified RS matrix. The modified RS matrix may store row-centric error detection codes (EDC) instead of conventional cyclic redundancy check (CRC) characters. The modified RS matrix may store column-centric ECC that may be produced serially. Different types or numbers of ECC may be produced, stored, and provided for different messages stored at different recipients.

Example apparatus and methods control an error correcting code (ECC) approach for data stored on a solid state device (SSD). The control may be based on a property (e.g., reliability, error state, speed) of an SSD, or on an attribute of the data to be stored. Approaches including a hybrid rateless Reed-Solomon ECC approach or a fountain code ECC approach may be selected. Example apparatus and methods may store padded portions of an ECC at different locations in an SSD. Example apparatus and methods may dynamically generate performance test data about the SSD, and dynamically control the ECC approach based on the performance test data. Different types or numbers of ECC may be produced, stored, and provided for different data sets stored at different SSDs or at different physical locations within an SSD. The SSD may be local, or may be part of a cloud-based storage system.

A magnetic tape device or system can store erasure encoded data that generates a multi-dimensional erasure code corresponding to an erasure encoded object comprising a code-word (CW). The multi-dimensional erasure code enables using a single magnetic tape in response to a random object/file request, and correct for an error within the single magnetic tape without using other tapes. Encoding logic can further utilize other magnetic tapes to generate additional parity tapes that recover data from an error of the single magnetic tape in response to the error satisfying a threshold severity for a reconstruction of the erasure coded object or chunk(s) of the CW. The encoding logic can be controlled, at least in part, by one or more iterative coding processes between multiple erasure code dimensions that are orthogonal to one another.

Systems, methods, and circuitries are provided for supporting distributed erasure coding in a shared file system. In one example, a method is provided to be performed by an initiator device configured to read and write data in files stored in a plurality of storage nodes that are controlled by a file management system. The method includes generating a stripe by identifying data to be stored in a storage system; dividing the data into K data segments; and performing an erasure encoding operation on the K data segments to generate a parity segment, wherein the stripe includes the K data segments and the parity segment. The method includes requesting, from the file management system, respective memory allocations in the storage devices for storing respective segments of the stripe; and transmitting, to each of the plurality of storage nodes, a respective instruction to store a respective data or parity segment in the memory allocation on the respective storage device.

Example apparatus and methods control whether and when hybrid rateless Reed Solomon (RS) error correcting codes (ECC) for a message are produced, stored, and distributed. The control may be based on a property (e.g., reliability, error state, speed) of a message recipient. Example apparatus and methods may also control whether and when fountain codes for the message are produced, stored, and distributed. Once again, the control may be based on a property of a message or ECC recipient. Both the hybrid rateless RS ECC and the fountain codes may be produced from data stored in a modified RS matrix. The modified RS matrix may store row-centric error detection codes (EDC) instead of conventional cyclic redundancy check (CRC) characters. The modified RS matrix may store column-centric ECC that may be produced serially. Different types or numbers of ECC may be produced, stored, and provided for different messages stored at different recipients.