Lenovo (singapore) Pte. Ltd.

International Business Machines Corporation

Western Digital Technologies, Inc.

Jeffrey R Hobbet

Donald R Frame

Daryl Carvis Cromer

Michael Scott Mettler

Randall Scott Springfield

Philip Lee Childs

Takashi Sugawara

Howard J Locker

Michael Terrell Vanover

Bernd Lamberts

Remmelt Pit

Joaquin F Pacheco

Kenneth Dean Timmons

Matthew Brent Griffith

Scott David Ruppert

Evan Richardson

Steve J Livaccari

John Weldon Nicholson

David Carroll Challener

Philip John Jakes

Tin-Lup Wong

Hiroaki Yasuda

Steven Dale Goodman

Ravi I Singh

Masahiko Nagai

Maulik Thaker

David Timothy Zimmerman

An approach to exchanging information between data storage devices (DSDs) within a secure data center and an external fleet health manager (FHM) application includes querying one or more DSDs for data to be analyzed, including providing a unique query identifier, whereby a particular DSD responsively provides (i) a device identifier identifying itself, (ii) a random key code for authentication and integrity purposes, (iii) the data to be analyzed, and (iv) the query identifier for the FHM application to verify. The FHM application can then digitally sign a corrective action payload, using the key code from the particular DSD, including the query identifier and the device identifier and a recommended corrective action, and transmit the signed corrective action payload to the data center for application to the particular DSD, whereby the DSD can execute pre-defined fundamental repair action operation(s) corresponding to the corrective action for in-situ repair.

Fleet health management corrective action communication exchange

An approach to identifying a corrective action for a data storage device (DSD), such as one implemented in a fleet of DSDs in a data center, involves receiving error data about excursions from normal operational behavior of the DSD, inputting data representing a particular excursion into a probabilistic decision network which characterizes a set of DSD operational metrics and certain DSD controller rules that represent internal controls of the DSD and corresponding conditional relationships among the operational metrics, determining from the decision network the likelihood that one or more possible causes was a contributing factor to the particular excursion, and determining a corrective action for the particular excursion based on the determined likelihood of a particular cause of the one or more possible causes. The corrective action may then be shared with the DSD for in-situ execution of corresponding self-repair operations.

Fleet health management device classification framework

A modified hard disk drive (HDD) state is provided. The modified HDD state corresponds to a state wherein the heads of a hard disk drive assembly are parked as a baseline setting, but permitted to float over the platters for completing requests on a limited basis. This prioritizes HHD protection in certain contexts.

Systems and methods for protecting hard disk drives

A method, apparatus, and system are disclosed for updating firmware on a storage device. The apparatus includes a detection module and an update module. The detection module detects, during a boot sequence, an indicator of an available update of firmware controlling a storage device. The available update is stored on non-volatile storage media of the storage device. The update module updates the storage device with the available update in response to the detection module detecting the indicator of the available update.

Method and apparatus for updating firmware on a storage device

An exemplary method includes performing flash memory operations; receiving a signal from a voltage monitor as being associated with the performed flash memory operations; and, based at least in part on the received signal, setting a limit for performing subsequent flash memory operations. In such a method, the limit can act to avoid resetting flash memory responsive to current demand associated with subsequent flash memory operations. Various other apparatuses, systems, methods, etc., are also disclosed.

Solid-state memory management

A method and apparatus are disclosed for concatenating a first RAID and a second RAID. The apparatus includes a concatenation module and a direction module. The concatenation module concatenates a first Redundant Array of Independent Disks ('RAID') with a second RAID into a top-level RAID. The first RAID and the second RAID may have disparate operational characteristics. The direction module directs storage operations to one of the first RAID and the second RAID based on a direction policy.

Concatenating a first raid with a second raid

An apparatus and method are disclosed for distributing writes asymmetrically. An asymmetric distribution module calculates an asymmetric distribution of writes for a plurality of drives. A write module writes data to each drive in accordance with the asymmetric distribution of writes.

Apparatus and method for distributing writes asymmetrically among drives

An approach is provided that loads software files, such as an operating system, on a hybrid storage device. The hybrid storage device is a device that includes a nonvolatile storage device and a nonvolatile memory cache. The nonvolatile memory cache has less storage capacity than the nonvolatile storage device. The nonvolatile memory cache is preset ('pinned') to data corresponding to an initial set of address ranges of the nonvolatile storage device, such as all or part of the operating system that was loaded onto the nonvolatile storage device. A system usage metric is initialized along with a threshold value. The nonvolatile memory cache remains pinned to the initial set of address ranges until the system usage metric reaches the threshold value. When the system usage metric reaches the threshold value, then a caching algorithm is used to determine what data should be cached to the nonvolatile memory cache.

Cache mapping for solid state drives

Embodiments of the invention broadly contemplate systems, methods and arrangements for managing Adjacent Track Interference (ATI) risk through intelligent management of a table that logs individual tracks creating a risk of ATI in tracks adjacent thereto. Embodiments of the invention provide that tracks considered being at low risk for creating ATI be ejected from the table in order to maintain a track-level log of manageable size.

Systems and methods for adjacent track interference (ATI) risk management

A method and apparatus are disclosed for automatic solid state drive performance recovery. A detection module detects a first SSD exceeding a fragmentation threshold. A plurality of drives comprises the first SSD and stores a data copy of data stored on the first SSD. An erase module erases a mapping table for the first SSD. The mapping table maps Logical Block Addresses LBA to physical addresses for the first SSD. A rebuild module rebuilds the data and the mapping table on the first SSD from the data copy.

Method and apparatus for automatic solid state drive performance recovery

The invention broadly contemplates a security solution for storage devices that is inexpensive and robust. The invention allows a store of system specific data to be used to release the hard disk key of full-disk encryption (FDE) drives. This system specific data is passed to the FDE drives and used to calculate the actual encryption key. This allows for safe disposal of an FDE drive containing confidential data, as the lack of available system specific decryption data makes decryption virtually impossible.

Security for storage devices

The instant invention broadly contemplates balancing of asymmetric RAID arrays based on application usage patterns. The instantly claimed invention broadly contemplates balancing the type of workload and delivery of the work load in asymmetric RAID arrays by intelligently implementing different types of applications on disks strategically positioned to deliver workload to the RAID channel that is most capable of handling the work load. The invention makes use of the fact that some applications are more large block, sequential transfer dependant while other applications are more small block, high random, high IOP dependent, and places these applications accordingly within the asymmetric RAID array.

Asymmetric load balancing for RAID storage systems

An apparatus, system, and method are disclosed for rapidly grading the operating condition of computer storage. A storage log modulelogs error information regarding any error in a storage subsystemthat occurs during normal operation. A storage test moduleperforms a cursory checkof the storage subsystemas requested by a user. A storage diagnostic modulegrades the storage subsystemon an operating condition scale based at least in part upon the error information logged and upon results of the cursory check. In one embodiment, the storage subsystemis graded as pristine if no error has been logged and no error was detected by the cursory check, as potentially failing if any error has been logged but no error was detected by the cursory check, and as failing if any error was detected by the cursory check

Apparatus, system, and method for rapid grading of computer storage operating condition

Systems and methods for easily and at high speed re-encrypting data recorded on a magnetic recording medium when the data is encrypted using an encryption key and the encryption key is changed. A track where effective user data is not recorded is set as a first reserved track, then data is read out from the first updating source track and decrypted using a first encryption key KEY, which is reencrypted using a second encryption key KEYand recorded in the first reserved track, next, the first updating source track is set as a second reserved track, and a second updating source track is set, and the encryption key is updated by repeating these steps until all tracks to be subjected to the key updating processing have been subjected to the key updating processing.

Magnetic recording medium encryption

A system, method, and program product is provided that recovers from a sector error affecting a critical file. A damaged sector prevents a critical file from being read prevents the computer system from booting. A controller records a sector number corresponding to the damaged sector. The system is rebooted using an alternative boot media. The system accesses the primary nonvolatile storage media after the rebooting. The damaged sector number is read from the error log and a file map is used to determine the critical file that is stored in the damaged sector. A backup copy of the critical file is retrieved from a backup media. The backup copy is written to the primary media using undamaged sectors and the critical file is mapped to the undamaged sectors. The system is subsequently booted successfully from the primary nonvolatile storage media.

Growing community of inventors

Holly Springs, NC, United States of America

Jeffrey R Hobbet