Abstract: A system includes a memory device, and a processing device, operatively coupled with the memory device, to perform operations including detecting a failure of a key-value store, identifying a non-filled zone of the memory device resulting from the failure, wherein the non-filled zone stores, in the key-value store, at least one of: an uncommitted key block or an uncommitted value block, and recovering the non-filled zone to obtain a recovered zone.

Abstract: Methods, systems, and devices for techniques to group media blocks are described. In some cases, a computing system may generate a memory map for a preconfigured size or chunk of data. For example, the computing system may divide files of media blocks into a set of fixed sized chunks of consecutive media blocks. Upon an application requesting a memory map for a set of media blocks, a storage layer of the computing system may generate a sub-map of the memory map for each chunk of data containing a media block of the set of requested media blocks. In some cases, the computing system may assign the chunks of data a continuous range of addresses in the virtual address space of the application. Upon generating the memory map, the storage layer may return an indication of the virtual address ranges of the requested media blocks to the application.

Abstract: Methods, systems, and devices for techniques to balance log structured merge trees are described. A computing system may rebalance a tree structure having an ordered set of leaf nodes by splitting or joining leaf nodes of the tree structure. To split a leaf node, the computing system may select a key to evenly partition key and value data stored in the leaf. The computing system may place each key block of the leaf node having keys less than or equal to the selected key in a first new leaf node, and may place each key block of the leaf node having keys greater than the selected key in a second new leaf node. To join leaf nodes of the tree structure, the computing system may place each key block and each value block of the leaf node and the adjacent leaf node in a new leaf node.

Abstract: Methods, systems, and devices for access heatmap generation at a memory device are described. In some examples, a memory device may maintain a register for tracking access operation occurrence, for which access operations of an address of the memory device may be mapped to multiple fields of the register. In some cases, in response to a first access operation performed on a first address of the memory device, the memory device may increment a first field and a second field of the register and, in response to a second access operation performed on a second address of the memory device, the memory device may increment the first field and a third field of the register. In some examples, the memory device may maintain a second register having a set of fields that each indicate a respective address for which an access occurrence satisfies a threshold.

Abstract: Methods, systems, and devices for access heatmap implementations at a host device are described. A host device may leverage access operation monitoring that is performed at a memory device, including various examples of signaling and management of monitoring configurations. For example, a memory device may maintain a storage location for tracking access operation occurrence, for which access operations of a given address may be mapped to multiple fields, and for which each field may be associated with access operations of a respective subset of the addresses. In some examples, such registers may be configured or accessed based on indications (e.g., commands, requests) from a host device, which may support dynamic access operation monitoring that is responsive to various operating conditions. In some examples, the host device may perform evaluations based on such minimum values associated with respective addresses to determine a distribution of data across various portions of memory.

Abstract: A system and method for reordering data blocks received from a zone of a memory device. An example method includes sending, by a host system to a memory sub-system comprising a memory device, a plurality of write commands; receiving, by the host system from the memory sub-system, block allocation metadata, wherein the block allocation metadata references one or more locations in the memory device corresponding to a zone; generating, by the host system, a reorder map based on the block allocation metadata; reading a plurality of data blocks associated with the zone; and reordering, by the host system, the plurality of data blocks based on the reorder map.

Abstract: A memory system includes a memory device comprising a content addressable memory (CAM) block comprising a plurality of key tables each storing a respective plurality of stored search keys. The memory system further includes a processing device that receives, from a requestor, an input search key and an indication of one of the plurality of key tables and identifies a match between the input search key and one of the plurality of stored search keys in the one of the plurality of key tables. The one of the plurality of stored search keys has an associated offset value indicating a location in a sorted string table (SSTable) corresponding to the one of the plurality of key tables. The processing device further reads the offset value from the one of the plurality of key tables and returns, to the requestor, the offset value read from the one of the plurality of key tables. The requestor can retrieve, from the location in the SSTable, data representing a value associated with the input search key.

Abstract: A request to retrieve data from a memory device of a memory sub-system can be received from a machine learning (ML) framework executing on a host system, where the data comprises a plurality of logical partitions. A set of parallel I/O threads can be initiated to retrieve the data from the memory device, where each I/O thread of the set of parallel I/O threads retrieves a different portion of the data from a different corresponding logical partition and stores the different portion of the data in a I/O buffer of a set of I/O buffers corresponding to the set of I/O threads in parallel. The different portion of the data can be successively provided from each I/O buffer to the ML framework, where the set of parallel I/O threads is to continually retrieve the data from the memory device until all of the data from the logical partitions has been provided to the ML framework.

Abstract: A system includes a memory device, and a processing device, operatively coupled with the memory device, to perform operations including detecting a failure of a key-value store, identifying a non-filled zone of the memory device resulting from the failure, wherein the non-filled zone stores, in the key-value store, at least one of: an uncommitted key block or an uncommitted value block, and recovering the non-filled zone to obtain a recovered zone.

Abstract: A system includes a zoned memory device allocating a zone storing a block belonging to a key-value set, and a processing device, operatively coupled with the zoned memory device, to perform operations including obtaining zone status information associated with the zone, identifying that the zone is a non-filled zone in view of the zone status information, and recovering the non-filled zone to obtain a recovered zone.

Abstract: A system and method for reordering data blocks received from a zone of a memory device. An example method includes sending, by a host system to a memory sub-system comprising a memory device, a plurality of write commands; receiving, by the host system from the memory sub-system, block allocation metadata, wherein the block allocation metadata references one or more locations in the memory device corresponding to a zone; generating, by the host system, a reorder map based on the block allocation metadata; reading a plurality of data blocks associated with the zone; and reordering, by the host system, the plurality of data blocks based on the reorder map.

Abstract: A system includes a zoned memory device allocating a zone storing a block belonging to a key-value set, and a processing device, operatively coupled with the zoned memory device, to perform operations including obtaining zone status information associated with the zone, identifying that the zone is a non-filled zone in view of the zone status information, and recovering the non-filled zone to obtain a recovered zone.

Abstract: A memory system includes a memory device comprising a content addressable memory (CAM) block comprising a plurality of key tables each storing a respective plurality of stored search keys. The memory system further includes a processing device that receives, from a requestor, an input search key and an indication of one of the plurality of key tables and identifies a match between the input search key and one of the plurality of stored search keys in the one of the plurality of key tables. The one of the plurality of stored search keys has an associated offset value indicating a location in a sorted string table (SSTable) corresponding to the one of the plurality of key tables. The processing device further reads the offset value from the one of the plurality of key tables and returns, to the requestor, the offset value read from the one of the plurality of key tables. The requestor can retrieve, from the location in the SSTable, data representing a value associated with the input search key.

Abstract: Aspects of the present disclosure provide for operations of a key-value store (KVS) that uses journaling with storage of data (e.g., key data or value data of a key-value pair) in different types of data storage objects (e.g., data storage formats) selected based on one or more criteria.

Abstract: A request to retrieve data from a memory device of a memory sub-system can be received from a machine learning (ML) framework executing on a host system, where the data comprises a plurality of logical partitions. A set of parallel I/O threads can be initiated to retrieve the data from the memory device, where each I/O thread of the set of parallel I/O threads retrieves a different portion of the data from a different corresponding logical partition and stores the different portion of the data in a I/O buffer of a set of I/O buffers corresponding to the set of I/O threads in parallel. The different portion of the data can be successively provided from each I/O buffer to the ML framework, where the set of parallel I/O threads is to continually retrieve the data from the memory device until all of the data from the logical partitions has been provided to the ML framework.

Abstract: A request to retrieve data from a memory device of a memory sub-system can be received from a machine learning (ML) framework executing on a host system, where the data comprises a plurality of logical partitions. A set of parallel I/O threads can be initiated to retrieve the data from the memory device, where each I/O thread of the set of parallel I/O threads retrieves a different portion of the data from a different corresponding logical partition and stores the different portion of the data in a I/O buffer of a set of I/O buffers corresponding to the set of I/O threads in parallel. The different portion of the data can be successively provided from each I/O buffer to the ML framework, where the set of parallel I/O threads is to continually retrieve the data from the memory device until all of the data from the logical partitions has been provided to the ML framework.

Abstract: A request to retrieve data from a memory device of a memory sub-system can be received from a machine learning (ML) framework executing on a host system, where the data comprises a plurality of logical partitions. A set of parallel I/O threads can be initiated to retrieve the data from the memory device, where each I/O thread of the set of parallel I/O threads retrieves a different portion of the data from a different corresponding logical partition and stores the different portion of the data in a I/O buffer of a set of I/O buffers corresponding to the set of I/O threads in parallel. The different portion of the data can be successively provided from each I/O buffer to the ML framework, where the set of parallel I/O threads is to continually retrieve the data from the memory device until all of the data from the logical partitions has been provided to the ML framework.

Abstract: Aspects of the present disclosure provide for operations of a key-value store (KVS) that uses journaling with storage of data (e.g., key data or value data of a key-value pair) in different types of data storage objects (e.g., data storage formats) selected based on one or more criteria.

Abstract: Aspects of the present disclosure provide for operations of a key-value store (KVS) that uses journaling with storage of data (e.g., key data or value data of a key-value pair) in different types of data storage objects (e.g., data storage formats) selected based on one or more criteria.