Emc IP Holding Company LLC

Emc Corporation

Los Alamos National Security, LLC

Seagate Technology Incorporated

Triad National Security, LLC

Ut-battelle, Inc.

John Michael Bent

Sorin Faibish

James M Pedone, Jr

Gary Alan Grider

Uday K Gupta

Percy Tzelnic

Aaron Torres

Sassan Teymouri

Zhenhua Zhang

Dennis P J Ting

Tao Peng

Jingwang Zhang

Xuezhao Liu

Ian Davies

Dennis P Ting

Kenneth K Claffey

Eriks Sasha Paegle

Patrick S Combes

Mohamad H El-Batal

Haiying Tang

Ujjwal Lanjewar

Dominique P Cote

Stephen W Poole

James Pedone

Dennis Pei Jean Ting

Jon David Trantham

Riyan Alex Mendonsa

James J Moore

Haiyun Bao

David Bonnie

Sasan Teymouri

Hsing-bung Chen

Jun He

Bikrant Kumar Singh

Raj Bahadur Das

Philippe Armangau

Edward Charles Gage

Jeffrey Mark Nick

Mehmet Fatih Erden

Praveen Viraraghavan

John West Dykes

John Forecast

Joshua Ward Christensen

Nikita Danilov

Peter M Maddocks

Gang Ma

Joshua E Simons

Stephen S Huh

Nicholas James Dance

Bradley W Settlemyer

Latchesar A Ionkov

George Tuma

Adam Manzanares

Sai Narasimhamurthy

Tim Shaffer

Dennis Ting, Jr

Serkay Olmez

A processor may determine, for each subdevice of a set of subdevices of a storage enclosure device, one or more reliability measures of the subdevice. A processor may determine, based at least on the one or more reliability measures for the subdevices and a spatial layout rule, a set of striping groups that maximizes a reliability of the set of subdevices of the storage enclosure device, each of the striping groups including a respective subset of the set of subdevices, wherein the spatial layout rule prescribes a geometric layout of the subdevices within striping groups across the storage enclosure device. A processor may store output data of a data striping operation to a particular subset of subdevices associated with a particular striping group of the set of striping groups.

Wear leveling and grouping of drives based on position in chassis

Described are hard disk drives (HDDs) operable for archival applications and utilizing the same mechanical and electrical design of conventional HDDs. The capacity of a conventional HDD may be extended by up to 25% to 40% or more by employing multiple write and/or read spins before declaring success in write and read processes. The multiple write and/or read spins are designed to address the lower reliability that would otherwise result from high density packing of the data, at the cost of reducing performance. The result is an HDD with lower performance at higher capacity without sacrificing reliability and without altering conventional HDD mechanical or electrical design.

High-density archival storage using conventional hard disk drive architecture

A method includes receiving a piece of data at an upper-layer server of a multi-tiered storage system comprising the upper-layer server and a block server, and determining a signature for the piece of data. A first bloom filter stored on the upper-layer server is a copy of a second bloom filter stored on the block server. The first bloom filter is checked for the signature. When a match is found in the first bloom filter, the piece of data is sent for storage at the block server, and it is verified at the block server whether a match is present for the piece of data. When a match is present, the piece of data is deduplicated. When a match is not present, the piece of data is stored. When a match is not found in the first bloom filter, the piece of data is stored in the block server.

Deduplication in multiple-tiered storage systems

A method includes receiving a piece of data for storage in a storage system, breaking the piece of data into a plurality of fixed size data portions, and determining a deduplication hash for each of the fixed size data portions. The method further includes checking for matching hashes already stored in the storage system, storing fixed size data portions unmatched to an already stored hash with metadata identifying the unmatched hash fixed size data portions in the storage system, and storing metadata for hash fixed size data portions already stored in the data storage system. The piece of data is reviewed for further deduplication using sliding window hashes during background activity of the data storage system.

Hybrid deduplication in storage systems

A composite layout to store one or more extents of a data object in a first storage system and one or more extents of the data object in a second, different storage system. The first storage system may be configured for the efficient storage of small chunks of data such as, e.g., chunks of data small than the addressable block size of the storage devices used by the storage systems.

Data storage layouts

Operations are monitored that involve a plurality of servers coupled to a plurality of data storage enclosures via a rack-level, storage networking fabric. The servers are operable to provide data storage services utilizing the data storage enclosures via a network. The data storage enclosures each have one or more data storage devices. The servers and the data storage enclosures are mounted within a data center rack. A failed unit determined that includes a failed one of the servers or a failed one of the data storage devices within a selected one of the data storage enclosures. A replacement is found for the failed unit within the data center rack, and the replacement is established for the failed unit within the data center rack. The establishment of the replacement involves establishing a new connection via the storage networking fabric.

Data center storage availability architecture using rack-level network fabric

Each disk drive in an array includes a housing that encloses a motor and at least one magnetic disk. The housing also encloses first and second actuators each with respective first and second heads that independently access the magnetic disk. The first actuator is mapped to a first logical unit and the second actuator is mapped to a second logical unit. A host interface of each disk drive facilitates access to the first and second logical units. A system includes a first storage controller attached to all of the first logical units as a first active server and attached to all of the second logical units as a first passive server. A second storage controller operates redundantly with the first storage controller. The second storage controller is attached to all of the second logical units as a second active server and attached to all of the first logical units as a second passive server.

Disk array using multiple actuator drives with logical units coupled to active and passive servers

A first data storage rack has a first computing unit coupled to a first plurality of storage drives via a first storage controller. A second data storage rack has a second computing unit coupled to a second plurality of storage drives via a second storage controller. A first rack-to-rack storage link cable couples the first computing unit to the second storage controller such that the first computing unit can provide access to the second plurality of drives in response to a failure that prevents the second computing unit from providing access to the second plurality of drives via a system network.

System and method to increase data center availability using rack-to-rack storage link cable

A data storage erasure system may have a host connected to a plurality of data storage devices via a network controller with each of the plurality of data storage devices and the network controller connected to a pods controller and each of the plurality of the data storage devices having a device controller. A rebuild strategy can be generated with a rebuild module connected to the plurality of data storage devices, the network controller, and the pods controller. The rebuild strategy may be directed to minimize data rebuild times in the event of a failure in the plurality of data storage devices by executing the rebuild strategy in response to a detected or predicted failure in at least one data storage device of the plurality of data storage devices.

Multi-level erasure system with cooperative optimization

Methods and apparatus are provided for filtering dynamically loadable namespaces (DLNs). An exemplary method comprises, in response to a job submitted by an application, obtaining a DLN portion of a global single namespace of a file system, wherein the DLN is associated with the job and is maintained in a capacity tier of a storage system; obtaining filtering directives from a user; reducing the DLN using a filtering mechanism on a directory tree associated with the DLN, based on the filtering directives, by removing files in the directory tree of the DLN that do not satisfy requirements of the filtering directives to generate a filtered DLN; and dynamically loading the filtered DLN, including reduced metadata for the filtered DLN relative to the DLN, from the capacity tier into a performance tier of the storage system for processing by the application.

Methods and apparatus for filtering dynamically loadable namespaces (DLNs)

A computer-executable method, system, and computer program product for managing metadata in a distributed data storage system, wherein the distributed data storage system includes a first burst buffer having a key-value store enabled to store metadata, the computer-executable method, system, and computer program product comprising receiving, from a compute node, metadata related to data stored within the distributed data storage system, indexing the metadata at the first burst buffer, and processing the metadata in the first burst buffer.

Advanced metadata management

Techniques are provided for pattern-aware prefetching using a parallel log-structured file system. At least a portion of one or more files is accessed by detecting at least one pattern in a non-sequential access of the one or more files; and obtaining at least a portion of the one or more files based on the detected at least one pattern. The obtaining step comprises, for example, a prefetching or pre-allocation of the at least the portion of the one or more files. A prefetch cache can store the portion of the one or more obtained files. The cached portion of the one or more files can be provided from the prefetch cache to an application requesting the at least a portion of the one or more files.

Pattern-aware prefetching using parallel log-structured file system

Methods and apparatus are provided for reorganizing dynamically loadable namespaces (DLNs). In one exemplary embodiment, a method comprises the steps of, in response to a job submitted by an application, obtaining a DLN portion of a global single namespace of a file system, wherein the DLN is associated with the job and is maintained in a capacity tier of object storage of a storage system; obtaining one or more reordering directives from a user; rearranging one or more files in the DLN into a new directory hierarchy based on the one or more reordering directives to generate a reordered DLN; and dynamically loading the reordered DLN, including the metadata only for the reordered DLN, from the capacity tier of object storage into a performance tier of storage of the storage system for processing by the application. The reordered DLN is merged into the DLN following one or more modifications to the reordered DLN.

Methods and apparatus for reorganizing dynamically loadable namespaces (DLNs)

A method includes, upon a read operation for a stripe of a storage device, determining a percentage amount of potential read amplification for the read operation. A current age of the stripe in the read operation is determined as a percentage of a longest safe elapsed time between read scrub operations on a stripe of the storage device. A read scrub operation is performed on the stripe when the current age is greater than the percentage amount of potential read amplification.

Cost-benefit aware read-amplification in RAID scrubbing

A multi-tier storage system is provided with direct client access to an archive storage tier for input/output operations. An exemplary method comprises communicating over a network with (i) a cluster file system on a first storage tier, and (ii) a second archive storage tier comprising an object store; providing a client of the cluster file system with access to one or more files in the cluster file system on the first storage tier; and executing a translation shim to provide the client of the cluster file system with one or more of read and write access to one or more files on the second archive storage tier. The translation shim converts between the protocols of the cluster file system and the protocols of the second archive storage tier, to allow unmodified applications to optionally access the second archive storage tier using existing cluster file system protocols.

Multi-tier storage system with direct client access to archive storage tier

Growing community of inventors

Los Alamos, NM, United States of America

John Michael Bent