Provided is a data access method including generating an index corresponding to a key in a first key-value pair in response to receiving the first key-value pair, writing the key- index pair corresponding to the key and the index into a block storage device, the key-index pair being stored in the block storage device in a log-structured merge-tree (LSM-Tree) structure, writing an index-value pair corresponding to the index and the value in the first key-value pair into a key-value solid state drive (KV SSD).

Data writing methods and computing devices are provided. An example data writing method is applied to a computer system, and the computer system includes a file system and a flash memory-based storage system. The example data writing method includes obtaining a target logical address, where the target logical address is an address allocated from a first logical block to target data to be written into the flash memory-based storage system, the first logical block is one of multiple logical blocks in the file system, and the flash memory-based storage system includes multiple physical blocks. It is determined that the target logical address belongs to the first logical block. The target data is written into a first physical block based on a correspondence between the first logical block and the first physical block, where the first physical block is one of the multiple physical blocks.

This disclosure provides for improvements in managing multi-drive, multi-die or multi-plane NAND flash memory. In one embodiment, the host directly assigns physical addresses and performs logical-to-physical address translation in a manner that reduces or eliminates the need for a memory controller to handle these functions, and initiates functions such as wear leveling in a manner that avoids competition with host data accesses. A memory controller optionally educates the host on array composition, capabilities and addressing restrictions. Host software can therefore interleave write and read requests across dies in a manner unencumbered by memory controller address translation. For multi-plane designs, the host writes related data in a manner consistent with multi-plane device addressing limitations. The host is therefore able to “plan ahead” in a manner supporting host issuance of true multi-plane read commands.

Several embodiments include a host computer coupled to a solid state drive (SSD). The filesystem of the host computer can receive a write pointer from the firmware of the SSD. The write pointer can reference a next available page to an erase block in the SSD. In response to a file write request to store a target file, the filesystem can determine a logical address range to store at least a portion of the target file based on the file write request and the write pointer. The filesystem can then generate a sector write command to send to the SSD. The sector write command can specify the determined logical address range.

The present disclosure involves systems, software, and computer implemented methods for compressed columnar data search using fingerprints. One example method includes compressing columnar data that includes dividing the columnar data into multiple data blocks and generating a fingerprint for each data block, storing the compressed columnar data and the generated fingerprints in an in-memory database, receiving a query for the columnar data, for each in-memory data block stored in the in-memory database, determining whether the in-memory data block satisfies the query and in response to a determination that the in-memory data block does not satisfy the query, pruning the in-memory data block from the multiple data blocks to generate an unpruned set of data blocks, decompressing the unpruned set of data blocks, and performing a query search on the decompressed unpruned set of data blocks for the received query.

A method is described. The method includes queuing an entry in a queue that identifies an inode that has been changed in an active storage system. The entry further describes a time in the future. The method includes processing the entry upon the time in the future being reached. The processing of the entry includes comparing respective content values maintained for different regions of the inode within the active storage system and a replicate storage system. The method further includes comparing content of those of the regions having different content values as between the active storage system and the replicate storage system. The method further includes updating those regions in the replicate storage system to reflect those regions within the active storage system based on the comparing, and, updating the respective content values of those regions in the replicate storage system.

A hardware-based processing node of an object memory fabric can comprise a memory module storing and managing one or more memory objects within an object-based memory space. Each memory object can be created natively within the memory module, accessed using a single memory reference instruction without Input/Output (I/O) instructions, and managed by the memory module at a single memory layer. The memory module can provide an interface layer below an application layer of a software stack. The interface layer can comprise one or more storage managers managing hardware of a processor and controlling portions of the object-based memory space visible to a virtual address space and physical address space of the processor. The storage managers can further provide an interface between the object-based memory space and an operating system executed by the processor and an alternate object memory based storage transparent to software using the interface layer.

This disclosure provides for improvements in managing multi-drive, multi-die or multi-plane NAND flash memory. In one embodiment, the host directly assigns physical addresses and performs logical-to-physical address translation in a manner that reduces or eliminates the need for a memory controller to handle these functions, and initiates functions such as wear leveling in a manner that avoids competition with host data accesses. A memory controller optionally educates the host on array composition, capabilities and addressing restrictions. Host software can therefore interleave write and read requests across dies in a manner unencumbered by memory controller address translation. For multi-plane designs, the host writes related data in a manner consistent with multi-plane device addressing limitations. The host is therefore able to “plan ahead” in a manner supporting host issuance of true multi-plane read commands.

The present disclosure provides methods, systems, and non-transitory computer readable media for optimizing data storing. An exemplary method comprises: receiving a data request for storing data on a storage device, wherein the data request is received on a host that is communicatively coupled to the storage device; determining, by the host, a data bucket to store the data, wherein the data bucket comprises a plurality of data blocks in the storage device, and the plurality of data blocks belong to more than one channel in the storage device; and storing the data across the plurality of data blocks.

A request for a particular file stored in memory of a mainframe computing system is received and the particular file is determined not to be registered in a catalog of the mainframe computing system. An index database separate from the catalog is searched for a record associated with the particular file and location of the particular file is determined from the index database. The particular file is then accessed from the identified location.