Emc Corporation

Emc IP Holding Company LLC

Infinio Systems, Inc.

David W Harvey

Bradford B Glade

Matthew D Waxman

John Kemeny

Lee W VanTine

Jeffrey Alan Brown

Daniel E Cummins

James A Wentworth

Peter John McCann

Fernando Oliveira

Walter M Caritj

Dennis Thomas Duprey

Peter Puhov

Robert Foley

Henry Austin Spang, Iv

Xiangping Chen

Walter A O'Brien, Iii

Alan Lee Taylor

Matthew H Long

Mark K Ku

Dean D Throop

Khang Can

Marc C Cassano

Manish Madhukar

Philippe Armangau

Jean-Pierre Bono

Vamsi K Vankamamidi

Roy E Clark

Miles Aram De Forest

Shuyu Lee

Paul Thomas McGrath

Dilesh Naik

H Austin Spang, Iv

Earle MacHardy

Gregory S Schaffer

Helen S Raizen

Michael J McCarthy

Thomas Earl Linnell

Anoop George Ninan

David Haase

Steven D Sardella

Michael E Bappe

Nagapraveen Veeravenkata Seela

Karl M Owen

Robert W Beauchamp

Michael D Haynes

Steven A Morley

Scott Howard Davis

Vishal Misra

Charles Christopher Bailey

Dayanand Suldhal

Hongliang Tang

Long Zhang

Michael Paul Wagner

Wayne E Garrett, Jr

Miles Aram DeForest

Antonio Fontes

Steve Morley

Mark J Cariddi

Hooman Vassef

Daniel B Lewis

Zhiqi Liu

Walter O'Brien

Jean Marie Schiff

Peter E Tolvanen

David John Agans

Dipak Prasad

Sriram Nagasubramanian

Martin Charles Martin

Ryan Gadsby

Richard G Chandler

Carson Jeffrey Barker

William B Whalen

Thomas M Rivera

David F Winchell

Walter A O'Brien Iii

Described are techniques for processing read and write requests in a system having a NUMA (non-uniform memory access) configuration. Such techniques may include receiving, at a front end adapter of the system, a write request, to write first data to a first storage device, storing a first copy of the first data in first memory local to a first domain, copying, using a first inter-storage processor communication connection, the first data from the first memory to a third memory of a third domain thereby creating a second copy of the first data in the third memory; and determining, in accordance with a first heuristic and first criteria, whether to use the first copy of the first data stored in the first memory or the second copy of the first data stored in the third memory as a source when writing the first data to the first storage device.

Optimizations to avoid intersocket links

A method, computer program product, and computing system for receiving an IO request for a RAID array. An actual queue depth of the RAID array is compared to a maximum queue depth for the RAID array. An IO queue weight is determined for the IO request. The IO queue weight is revised based upon a degrade mode condition for the RAID array, thus defining a revised IO queue weight. The actual queue depth is incremented based upon the revised IO queue weight.

IO request system and method

An improved technique involves processing a workflow in stages, and processing all requests in a queue for a given stage before moving onto the next stage. Along these lines, each request received by a storage processor is assigned to a core and placed in a first queue for that core. Within that core, a single system thread executes first instructions for a task, e.g., checking the storage cache for the requested data from a request, and then transfers the request to a second queue. Rather than perform additional tasks to completely satisfy the request, however, the thread executes the first instructions for a prespecified number of requests in the first queue. Only when the thread has executed instructions for the prespecified number of requests, the thread begins execution of second instructions for requests in the second queue, and work on the next task begins.

Techniques for increasing storage system performance in processor-bound workloads with large working sets and poor spatial locality

Systems and methods for a content addressable cache that is optimized for SSD use are disclosed. In some embodiments, the cache utilizes an identifier array where identification information is stored for each entry in the cache. However, the size of the bit field used for the identification information is not sufficient to uniquely identify the data stored at the associated entry in the cache. A smaller bit field increases the likelihood of a 'false positive', where the identification information indicates a cache hit when the actual data does not match the digest. A larger bit field decreases the probability of a 'false positive', at the expense of increased metadata memory space. Thus, the architecture allows for a compromise between metadata memory size and processing cycles.

Optimized read cache for persistent cache on solid state devices

A method, computer program product, and computing system for determining a queue depth and a flush rate for each of a plurality of pending data queues associated with a cache system, thus defining a queue depth/flush rate pair for each of the plurality of pending data queues. A predicted drain time is determined for each of the plurality of pending data queues based, at least in part, upon the queue depth/flush rate pair, thus defining a plurality of predicted drain times that are respectively associated with the plurality of pending data queues.

Cache management system and method

A method includes (a) receiving a setup command directing a computing device to create a protocol endpoint to allow a remote host device to access storage volumes of the computing device presented to the remote host through the protocol endpoint as virtual storage volumes, (b) in response to receiving the setup command, creating a logical storage device object representing the protocol endpoint, the logical storage device object having zero underlying storage capacity, (c) subsequent to creating the logical storage device object, receiving a command directed at the protocol endpoint, and (d) in response to receiving the command, processing the command by a driver stack on the computing device containing the logical storage device object representing the protocol endpoint, the driver stack being shorter than another driver stack on the computing device used to process storage commands directed at another logical storage device object having non-zero underlying storage.

Lun with zero storage as a protocol endpoint

Described are techniques for migrating data. A source data storage system includes a source device and a target data storage system includes a target device. A passive path and an active path are provided for a host to access data of a logical device. The host recognizes the passive path and the active path as paths to the logical device. The passive path is between the host and the source data storage system. The active path is between the host and the target data storage system and used in connection with proxying at least some requests directed to the logical device received from the host through the target data storage system while migrating data for the logical device from the source device to the target device. Migrating is performed to migrate data for the logical device from the source device to the target device. Migrating is controlled by a migration module executing on the target data storage system that copies data from the source device to the target device.

Data migration techniques

There are disclosed techniques for use in managing data storage in a data storage system which comprise a data storage device and a cache memory. In one example, a method comprises the following steps. An I/O request is received and a durability requirement of the I/O request data associated with the I/O request is determined. Based on the durability requirement of the I/O request data, the I/O request data is classified. The classified I/O request data is stored in the cache memory.

Managing data storage

An electronic assembly perform data storage operations on behalf of a set of storage processors (SPs). The electronic assembly includes an enclosure, and a set of peripheral component interconnect express (PCIe) switches which installs within the enclosure. The set of PCIe switches is constructed and arranged to connect to the set of SPs while the set of SPs is external to the enclosure. The electronic assembly further includes a set of data storage devices which installs within the enclosure. The set of data storage devices is constructed and arranged to persistently store data on behalf of the set of SPs via PCIe-based communications through the set of PCIe switches.

Provisioning an enclosure with PCIe connectivity and storage devices

A technique for managing spare disk drives in a data storage system includes transferring segments of data from disk drives of an operating RAID group to spare regions on a set of spare disk drives to create unused space in the disk drives of the RAID group, thus using the spare regions to overprovision storage in the RAID group. Upon a failure of one of the disk drives in the RAID group, data of the failing disk drive are rebuilt based on the segments of data as well as on data from still-functioning disk drives in the RAID group. Thus, the spare disk drives act not only to overprovision storage for the RAID group prior to disk drive failure, but also to fulfill their role as spares in the event of a disk drive failure.

Using spare disk drives to overprovision raid groups

Methods and systems for enhanced error recovery are described. A first one or more data blocks to write to a first drive are received by a first drive controller module. A first parity block is calculated by the first drive controller module based on a first data block parity group. The first one or more data blocks are written by the first drive controller module to the first drive. The first parity block is written by the first drive controller module to the first drive.

Enhanced error recovery for data storage drives

A technique for managing file systems that support block sharing places a source/copy attribute in each block pointer. The source/copy attribute identifies the respective block pointer as either a source-block pointer or a copy-block pointer. A reference count on each data block maintains a count of the number of source-block pointers pointing to the data block but excludes the number of copy-block pointers pointing to the data block. Block pointers are arranged in block pointer sets (BPSs), and sharing relationships are formed among BPSs and copies of BPSs. The sharing relationships generally keep most block sharing information at the BPS level, with reference counts on data blocks tracking only the number of source-block pointers, which is typically small, often being equal to one.

Source/copy reference tracking with block pointer sets

A method is used in managing accesses to storage. An amount of data storage space in use by a mapped logical volume and RAID group characteristics of a storage pool used by the mapped logical volume are determined. Based on the amount and the RAID group characteristics, a report of storage resources corresponding to the mapped logical volume is produced. Based on the report, accesses to the mapped logical volume are controlled.

Managing accesses to storage

A method is used in recovering from metadata inconsistencies in storage systems. A metadata inconsistency is detected in a portion of a file system. The file system is managed by upper-layer component. The portion of the file system is recovered. Lower-layer component recovers the portion of the file system. The portion of the file system is validated. The upper-layer component validates the portion of the file system.

Recovering from metadata inconsistencies in storage systems

Growing community of inventors

Newton, MA, United States of America

David W Harvey