Other

Quantum Corporation

Computer Associates Think, Inc.

Emc Corporation

Matthew C Dewey

David J Van Maren

Bruce A Thompson

James M Wilson

Jerry A Blades

Roderick B Wideman

Don Doerner

Marc A Smith

Stephen Peter Jakas

Todd Pisek

Ellen F Jones

Systems, methods, and circuitries are provided for supporting multiple concurrent thread access to a storage array. In one example, a storage array includes a plurality of storage devices each divided into at least N subdivisions. A volume includes a set of subdivisions including a subdivision in each of M different storage devices. Memory management circuitry receives first data and second data for storing in the storage array and selects a first volume for storing the first data and a second volume for storing the second data. The second volume includes a different set of subdivisions than the first volume. The processor uses a first set of processor threads to process and store the first data in the first volume and uses a second set of processor threads to, concurrent with the processing and storing of the first data, process and store the second data in the second volume.

Storage array supporting multi-thread access

Embodiments redirect data from a source to a plurality of deduplication blockpools. In one embodiment, operations include accessing a binary large object (BLOB) that includes a plurality of blocklets, a blocklet having a hash value; upon determining that the plurality of blocklets includes less than a threshold number of blocklets: selecting, according to a first rule set, a target blockpool from among the plurality of deduplication blockpools; upon determining that the plurality of blocklets includes at least the threshold number of blocklets: selecting, according to a second, different rule set, a target blockpool. The second rule set includes a BalanceQuery rule that computes a fitness value for a member of the plurality of deduplication blockpools, and selects a target blockpool based, at least in part, on the fitness value. Embodiments provide the BLOB to the target blockpool.

Data redirector for scale out

Apparatus, methods, and other embodiments associated with reducing read starvation that is supported by a multi-purpose buffer managed by a least recently used (LRU) data structure are described. One example method includes changing how certain retired pages are added back into the LRU. The dual-purpose buffer may be used in data de-duplication to support satisfying ingest requests and to support satisfying read requests. The method may also include controlling the LRU to allocate active ingest pages and active read pages from the head of the LRU. The method may also include controlling the LRU to cause the active ingest page and the active read page to re-enter the LRU at the tail of the LRU. Unlike conventional approaches, the method may also include controlling the LRU to cause a retired ingest page to re-enter the LRU at a location other than the tail (e.g., head) of the LRU.

Reducing read starvation

Example apparatus and methods concern de-duplication reference tag reconciliation associated with garbage collection and/or reference health checking. One example method may include accessing data associated with members of a set of references to blocks of data stored by a data de-duplication system. The method may process the first data to manipulate a Bloom filter into a state from which membership in the set of references can be assessed. The method may also include accessing a block identifier identified with a member of the set of blocks of data stored by the data de-duplication system and assessing membership in the set of references for the block identifier by querying the Bloom filter with the block identifier. If the block is not referenced, as determined by querying the Bloom filter, then the method may include performing a block reclamation action on the unreferenced block.

De-duplication reference tag reconciliation

Mass storage system controller apparatus receives requests for access to files in a data storage system and manages access to the files in the data storage system, the data storage system having a plurality of storage devices and the requests being addressed to the data storage system as a single virtual storage device having addressable Command Regions allocated to controller commands and addressable Mapped Data Regions allocated for data storage. The apparatus includes a file system to manage access to files in the data storage system, the file system having a processor acting as a Command Region processor and acting as a Mapped Data Region processor. A disk emulator responds as a disk drive device to write/read commands and passes the write/read commands addressed to Command Regions of the virtual storage device to the Command Region processor, the write/read commands addressed to Command Regions containing controller commands for the file system. The Command Region processor responds to controller commands in the write/read commands and processes the controller commands to control files in the data storage system. The disk emulator responds as a disk drive device to write/read commands and passes write/read commands addressed to a Mapped Data Region of the virtual storage device to the Mapped Data Region processor. The Mapped Data Region processor responds to a write/read command with a Mapped Data Region address and transfers data to or from the data storage system for files mapped to the Mapped Data Region address.

Intelligent controller accessed through addressable virtual space

A method for recovering data from a cache memory of a second storage controller by access to a cache memory of a first storage controller is presented. The storage controllers are coupled by a private common data path. The method includes copying metadata corresponding to the data stored in the cache memory of the second storage controller to the cache memory of the first storage controller through the private common data path. The metadata may include pointers to and the size of the data. After copying the metadata pointers, the data in the cache memory of the second storage controller is established in the cache memory of the first storage controller. As a result, the entire set of data does not need to be totally recovered to the hard disk before resuming host communications in a recovery operation, which may take a relatively long time. Instead, if a controller fails, only a portion of the data in the cache of the failed controller, the data describing the recovery information, needs to be incorporated into the 'dirty' cache of the remaining controller before communications with the host are resumed.

Growing community of inventors

Broomfield, CO, United States of America

Matthew C Dewey