International Business Machines Corporation

Micron Technology Incorporated

Samsung Electronics Co., Ltd.

Skhynix Inc.

Jonathan Mark Haswell

Shirish Dnyaneshware Bahirat

William Richard Akin

Rodney Carlton Burnett

Kevin G Kramer

Tewari Renu

David Maxwell Cannon

Howard Newton Martin

Matthew Joseph Anglin

Colin Scott Dawson

Erick Christian Kissel

Generating data checksum for a data object including multiple data units comprises, for each data unit, obtaining a corresponding address of the data unit, and rotating the data unit based on said corresponding address of the data unit to generate a rotated data unit. A checksum value for the data object is determined based on said rotated data units.

Enhanced checksum system

In an example, an apparatus may include a memory comprising a number of groups of memory cells and a controller coupled to the memory and configured to track respective invalidation velocities of the number of groups of memory cells and to assign categories to the number of groups of memory cells based on the invalidation velocities.

Data categorization based on invalidation velocities

An example apparatus for memory addressing can include an array of memory cells. The apparatus can include a memory cache configured to store at least a portion of an address mapping table. The address mapping table can include a number of regions corresponding to respective amounts of logical address space of the array. The address mapping table can map translation units (TUs) to physical locations in the array. Each one of the number of regions can include a first table. The first table can include entries corresponding to respective TU logical address of the respective amounts of logical address space, respective pointers, and respective offsets. Each one of the number of regions can include a second table. The second table can include entries corresponding to respective physical address ranges of the array. The entries of the second table can include respective physical address fields and corresponding respective count fields.

Memory addressing

An example apparatus for die addressing can include an array of memory cells and a memory cache. The memory cache can be configured to store at least a portion of an address mapping table. The address mapping table can include entries that map translation units (TUs) to physical locations in the array. The entries can include data that indicate a location within the array that stores a particular TU without including data that indicates which die of the array the TU is stored in.

Die addressing using a reduced size translation table entry

The present disclosure includes apparatuses and methods for logical to physical mapping. A number of embodiments include a logical to physical (L2P) update table, a L2P table cache, and a controller. The controller may be configured to cause a list of updates to be applied to an L2P table to be stored in the L2P update table.

Logical to physical mapping

Memory systems that include NAND flash memory and dynamic random access memory (DRAM) are configured to allow a considerably higher ratio of NAND to DRAM without a significant increase in write amplitude. The NAND includes a logical-to-physical (L2P) table. The DRAM includes a buffer divided into regions, an update table of recently written data and linked lists, one for each region of the buffer linking all items in the update table in that region, the DRAM maintaining a set of linked lists, each identifying all regions with the same number of updates in the update table.

Memory system with configurable NAND to DRAM ratio and method of configuring and using such memory system

Variable-size table for address translation

According to an embodiment of the invention, cache management comprises maintaining a cache comprising a hash table including rows of data items in the cache, wherein each row in the hash table is associated with a hash value representing a logical block address (LBA) of each data item in that row. Searching for a target data item in the cache includes calculating a hash value representing a LBA of the target data item, and using the hash value to index into a counting Bloom filter that indicates that the target data item is either not in the cache, indicating a cache miss, or that the target data item may be in the cache. If a cache miss is not indicated, using the hash value to select a row in the hash table, and indicating a cache miss if the target data item is not found in the selected row.

Cache system optimized for cache miss detection

Systems and methods for retrieving data from a storage system having a plurality of storage pools are provided. The method comprises processing configurable data retrieval instructions to determine a first storage pool from which target backup data is to be retrieved, in response to a data restore request; and retrieving the target backup data from the first storage pool to satisfy the restore request. The configurable data retrieval instructions are managed by a source external to the storage system with administrative authority to change the configurable data retrieval instructions to optimize data restoration from the storage system.

Data recovery in a hierarchical data storage system

A method for improving the performance of a computer system when it is detected that a process wishes to gain access to and update an object while it is locked for commitment to stable storage. The process wishing to gain access to the object is provided a copy of the existing object, with this copy now being considered as the new primary copy of the object. Updates can be made to this new copy without any impact to the commitment to the stable storage and without a delay to the process making the new updates. Any future searches for the object will return references to this new copy, while the original copy is only maintained for the period required to complete it's commitment to stable storage.

Copy on access to locked objects

A file system boundary emulation system emulates a virtual boundary of a filesystem within an existing file system for data management at a fileset granularity, within the framework of a wide area filesystem federation. The system dynamically assigns a fileset ID to the file that belongs to that fileset. The system comprises a fileset defined by the virtual boundary of the file. The virtual boundary is less than and contained within the file system. The fileset identifies the file via the file ID and the fileset ID. The system maps the file ID to the fileset ID. The filesets are dynamically created and removed based on administrative instructions. Filesets are used for fine grained data management and namespace control in a filesystem federation.

System for emulating a virtual boundary of a file system for data management at a fileset granularity

A filing system controls block-level storage and selects a required level of performance and reliability for a file stored on a storage system on a file-by-file basis. A policy manager contains at least one rule relating to a RAID level of protection for a file stored on the storage system and the RAID level of protection is selected from a plurality of RAID levels of protection. At least one rule is based on an access pattern of files stored on storage systems. An access manager provides the policy manager with information relating to access patterns of files stored on the storage system. At least two files can be stored on the storage system having different RAID levels of protection, and at least two files can be stored on a same storage unit of the storage system can have different RAID levels of protection.

Growing community of inventors

San Jose, CA, United States of America

Jonathan Mark Haswell