Quantum Corporation

Other

Advanced Digital Information Corporation

Don Doerner

Roderick B Wideman

Turguy Goker

Michael Zeis

Stephen W Moore

Jeff Leuschner

Doug Burling

Gregory Prestas

Rod Wideman

Marc A Smith

Barry Massey

John Rockenfeller

Gregory L Wade

Suayb Sefik Arslan

Thomas Demoor

Hoa Le

Greg Wade

Matthew C Dewey

Stephen Philip Spackman

Daniel J Byers

Sanam Mittal

Jeff Szmyd

Steve Lord

Robert I Walker

Stijn Blyweert

Frederik De Schrijver

Mary Hayes

Michael Jones

A method for utilizing an object storage system () for storing and retrieving a volume of data, the volume of data including a plurality of data objects, the method includes the steps of accumulating the volume of data to an ingest area () provided within a non-taped-based storage medium; copying a first subset of the plurality of data objects to a first tape medium (A); and copying a second subset of the plurality of data objects to a second tape medium (B) that is independent of the first tape medium (A). The method can further include managing the object storage system () with object storage software () to perform one or more of (i) generating a first extent parity that contains redundant information from the first subset of the plurality of data objects using erasure coding; and writing the first extent parity to the first tape medium (A); (ii) generating a second extent parity that contains redundant information from the second subset of the plurality of data objects using erasure coding; and writing the second extent parity to the second tape medium (B); and (iii) generating a volume parity that contains redundant information from the volume of data using erasure coding; and writing the volume parity to a third tape medium (C) that is independent of the first tape medium (A) and the second tape medium (B).

System and method for storing and retrieving objects across multiple media

Nonvolatile data storage systems, methods, and devices are disclosed. In one example, a nonvolatile storage device includes a volatile memory, a controller electrically coupled to the volatile memory, a nonvolatile memory electrically coupled to the controller, and a backup power source electrically coupled to the controller, the volatile memory, and the nonvolatile memory. The controller is configured to read and write primary data from a primary host and mirrored data from a secondary host in the volatile memory. The backup power source is configured to store sufficient energy to power the nonvolatile storage device during a backup operation. The controller is configured to, in response to a backup signal, copy the primary data and the mirrored data stored in the volatile memory to the nonvolatile memory.

Nonvolatile storage device with volatile memory

Example apparatus and methods identify files that are so small or so large that they compromise the efficient operation of a file system that uses re-assignable one-to-one inodes and inode numbers. Small files are aggregated into collections of files and large files are subdivided into collections of smaller files. Information for locating multiple related files with fewer lookups is generated and stored in a folder. An inode having a new type of inode number is then created. The new type of inode number encodes information for finding the folder. The encoded information may include a folder identifier that acts as a primary key into a database that is configured to locate a member of the aggregated or subdivided files with a single lookup. A filter file system may be updated with the new inode. The new inode number is unique within the filter file system and may not be re-assigned.

Filter file system with inode number as primary database key

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

Adaptive pre-fetching devices can predict data placement to improve the operating and/or electrical efficiency of a data storage system. A future input/output operation can be predicted from a current input/output operation, the state of the data storage apparatus, relationships between data currently being processed and data previously processed, or other factors. The apparatus and methods can improve data storage efficiency by selectively pre-fetching data, relocating data on the data storage apparatus, the backing storage, or within a plurality of data storage apparatus based on working set predictors to reduce cache misses or outperform fetch processes from the backing storage.

Adaptive pre-fetch

Embodiments include a data aware deduplicating object store. The data aware deduplicating data store includes a consistent hashing logic that manages a consistent hashing architecture for the object store. The consistent hashing architecture includes a metadata ring and a bulk ring. The consistent hashing architecture may be a multiple ring architecture comprising a metadata ring and two or more bulk rings. A bulk ring may include a key/value (k/v) data store, where a k/v data store stores a shard of an index and a reference count that facilitates the individual approach to garbage collection or data reclamation. The data aware deduplicating data store also includes a deduplication logic that provides data deduplication for data to be stored in the object store. The deduplication logic performs variable length deduplication and provides a shared nothing approach.

Data aware deduplication object storage (DADOS)

Embodiments provide adaptive storage management for optimizing multi-tier data storage. A storage manager may interact with storage decision advisors. The manager may adaptively make storage management decisions (e.g., flush, evict, recall, delete) after considering recommendations from and the credibility of the storage decision advisors. The manager may update the credibility of storage decision advisors based on how their recommendations affected optimization. The manager may adaptively choose when to rebalance or reconfigure the credibility of the storage decision advisors. Storage decision advisors may themselves be adaptive. Storage decision advisors may examine credibility feedback from the storage manager to determine which recommendations were useful and which were not. Storage decision advisors may then change when they will make a recommendation, when they will abstain from making a recommendation, the type of recommendation provided, or other behavior. Optimization may concern performance, cost, power usage, or other factors.

Adaptive storage management for optimizing multi-tier data storage system

Example methods and apparatus asynchronously verify data stored in a cloud data storage system. One embodiment comprises a monitoring circuit that determines if a data auditing condition associated with a cloud storage system or archived data stored in the cloud storage system has been met, a metadata mirror circuit that controls a metadata mirror to provide metadata, including a first checksum, associated with the archived data to the apparatus, a checksum circuit that computes a second checksum based on the archived data, a verification circuit that generates an audit of the first checksum and the second checksum by comparing the second checksum with the first checksum, and a reporting circuit that generates a log of the audit, that provides the log to the data storage system, and that provides a notification of a data integrity failure to a user associated with the archived data.

In-situ data verification for the cloud

Example apparatus and methods provide a file system that stores files in multiple different logical units. The logical units are associated with different classes of devices. The file system interacts with the logical units through block-based interfaces. The file system is a single file system that spans the multiple logical units. The multiple different logical units include data storage devices for which the file system manages block storage allocation and an object storage system that manages its own block storage allocation rather than having the file system manage its block storage allocation. The file system may maintain a single namespace, hierarchy, or directory structure for the multiple logical units. The object storage system may protect files using redundant copies, erasure codes, or other approaches. An archive process may selectively move files from other devices to the object storage system and leave a symbolic link behind.

File system with multi-class in situ tiered archiving

Example apparatus and methods provide a log structured block device for a hard disk drive (HDD). Data that is to be stored on an HDD is serialized and written as a series of data blocks using a sequential write. Information about where individual data blocks were supposed to be written (e.g., actual address, neighboring data blocks), where data blocks were actually written, and how often data blocks are accessed is maintained. During garbage collection, data blocks that are being accessed with similar frequencies may be relocated together, with the most frequently accessed (e.g., hottest) data blocks migrating to the outer cylinders of the disk and the least frequently accessed (e.g., coldest) data blocks migrating to the inner cylinders. Blocks stored in the same temperature regions that were intended to be located together when written may be repositioned to facilitate sequential reads.

Log structured block device for hard disk drive

Storage conditioning for a data storage system having D data storage devices (DSDs) is provided. E erasure codes (ECs) for an object are stored in the system, D&#x3e;E. A map of d E-sized vectors of the D DSDs is produced. A DSD appears in e vectors. The ratio d/e is the reduced form of D/E. A hash value is produced for the object. A destination vector for storing the ECs is selected using the hash value according to a pre-determined, substantially uniform distribution. A compromised vector affected by a first DSD becoming unable to store ECs is identified. An intact vector that is not affected by the first DSD is identified. A complete set of ECs is produced from an incomplete set of ECs in the compromised vector and is distributed to the intact vector then copied back when the compromised vector is once again intact.

Storage conditioning with intelligent rebuild

Example apparatus and methods provide improved reclamation, garbage collection (GC) and defragmentation (defrag) for data storage devices including solid state drives (SSD) or shingled magnetic recording (SMR) drives. An erasure code (EC) layer that facilitates logically or physically erasing data from the SSD or SMR as a comprehensive GC or defrag is added to the SSD or SMR. Erased data may be selectively recreated from the EC layer as needed. Pre-planned EC write zones may be established to further optimize GC and defrag. Recreated data may be written to selected locations to further optimize SSD and SMR performance. Erasure code data may be distributed to co-operating devices to further improve GC or defrag. Example apparatus and methods may also facilitate writing data to an SMR drive using tape or VTL applications or processes and providing a pseudo virtual tape library on the SMR drive.

Growing community of inventors

San Jose, CA, United States of America

Don Doerner