A system is provided including a first server storing a first data file for a first user, a second server storing a second data file for a second user, a first data card of the first user registered with the first server and locally storing a portion of the first data file, and a second data card of the second user registered with the second server and associated with the second data file. The first data card detects a pairing gesture between the first and second data cards, and in response, establishes a peer-to-peer connection between the data cards.

Techniques involve: determining, according to a determination that a performance level of a target storage unit is lower than a threshold level, whether idle disk slices that can be used for reconstructing malfunctioning disk slices in the target storage unit exist in a slice pool; determining a priority of the target storage unit according to a determination that the idle disk slices do not exist; and selecting replacing disk slices for reconstructing the malfunctioning disk slices from available storage units based at least in part on the priority, wherein the available storage units have performance levels not lower than the threshold level. In this way, data loss due to the off-line of storage units is prevented; and meanwhile, the performance of the entire storage system can be globally stabilized.

In accordance with embodiments disclosed herein, there are provided methods, systems, mechanisms, techniques, and apparatuses for presentation of direct accessed storage under a logical drive model; for implementing a distributed architecture for cooperative NVM Data protection; data mirroring for consistent SSD latency; for boosting a controller's performance and RAS with DIF support via concurrent RAID processing; for implementing arbitration and resource schemes of a doorbell mechanism, including doorbell arbitration for fairness and prevention of attack congestion; and for implementing multiple interrupt generation using a messaging unit and NTB in a controller through use of an interrupt coalescing scheme.

Provided are an apparatus, system and method for offloading data transfer operations between source and destination storage devices to a hardware accelerator. The hardware accelerator includes a memory space and control logic to receive, from a host processor, a command descriptor indicating at least one source storage device having transfer data to transfer to at least one destination storage device and a computational task to perform on the transfer data. The control logic sends read commands to the at least one source storage device to read the transfer data to at least one read buffer in the memory space and performs the computational task on the transfer data to produce modified transfer data. The control logic writes the modified transfer data to at least one write buffer in the memory space to cause the modified transfer data to be written to the at least one destination storage device.

Generating a transformed dataset for use by a machine learning model in an artificial intelligence infrastructure that includes one or more storage systems and one or more graphical processing unit (‘GPU’) servers, including: storing, within one or more storage systems, a transformed dataset generated by applying one or more transformations to a dataset that are identified based on one or more expected input formats of data received as input data by one or more machine learning models to be executed on one or more servers; and transmitting, from the one or more storage systems to the one or more servers without reapplying the one or more transformations on the dataset, the transformed dataset including data in the one or more expected formats of data to be received as input data by the one or more machine learning models.

Embodiments of the present disclosure relate to a data read method, a data storage method, an electronic device, and a computer program product. The data read method includes: receiving a data read request, the data read request comprising a data identifier associated with target data; determining a storage device of the target data based on the data identifier; and acquiring the target data from the storage device based on the data identifier. The data storage method includes: receiving a data storage request, the data storage request comprising a data identifier associated with data to be stored; determining, based on the data identifier, a target storage device for the data to be stored; and storing, based on the data identifier, the data to be stored to the target storage device. With the technical solutions of the present disclosure, a named data network with good performance and efficient operation can be achieved.

Fragmented data on a storage device may be additionally stored in a cache. A cache weight for determining storage of a data unit can be determined. For example, a computing device can receive storage device characteristics from a storage device. A data unit comprising multiple fragments may be stored on the storage device. The computing device can receive data unit characteristics from the storage device. The computing device can determine a cache weight for the data unit. The computing device may output the cache weight for determining storage of the data unit in a cache.

Apparatuses and methods related to commands to transfer data and/or perform logic operations are described. For example, a command that identifies a location of data and a target for transferring the data may be issued to a memory device. Or a command that identifies a location of data and one or more logic operations to be performed on that data may be issued to a memory device. A memory module may include different memory arrays (e.g., different technology types), and a command may identify data to be transferred between arrays or between controllers for the arrays. Commands may include targets for data expressed in or indicative of channels associated with the arrays, and data may be transferred between channels or between memory devices that share a channel, or both. Some commands may identify data, a target for the data, and a logic operation for the data.

Embodiments of the present disclosure provide a data storage method, an electronic device, and a computer program product. The method includes: determining the number of at least one first storage apparatus of a storage system, each first storage apparatus being persistent and storing a log that includes record entries of to-be-stored data; and writing, if it is determined that the number is greater than a threshold number, the to-be-stored data into a corresponding memory table from the log where the to-be-stored data is located, wherein data in the memory table will be written to a second storage apparatus of the storage system. In this way, the storage efficiency of the storage system can be improved.

A remote data replication method and a storage system, where a production array sends a data replication request to a disaster recovery array. The data replication request includes an identifier of a source object and a data block corresponding to the source object. The data block is stored in physical space of a hard disk of the production array. The disaster recovery array receives the data replication request. The disaster recovery array creates a target object when the disaster recovery array does not include an object having a same identifier as the source object. An identifier of the target object is the same as the identifier of the source object, the disaster recovery array writes the data block into the physical space.