International Business Machines Corporation

Western Digital Technologies, Inc.

Hitachi Global Storage Technologies Netherlands B.v.

Hgst Netherlands, B.v.

Hitachi Global Storage Technologies B.v.

Bernd Lamberts

Remmelt Pit

Mantle Man-Hon Yu

Kris Victor Schouterden

Louis Joseph Serrano

Jordan Asher Katine

Pankaj Mehra

Sridhar Chatradhi

Donald Ray Gillis

Jeffrey R Hobbet

David H Jen

Zarko Popov

Shad Henry Thorstenson

Mantle M Yu

Thomas E Stanley

Evan Richardson

Erhard Theodor Schreck

Vladimir Nikitin

Vijay Karamcheti

Wen-Chien David Hsiao

David Robison Hall

Martin Aureliano Hassner

Bernhard E Knigge

Hitoshi Yoshida

Qing Dai

Terence T Lam

Karl Arthur Flechsig

James Terrence Olson

Yinshi Liu

Ravi I Singh

Paul Hodges

Timothy G Lieber

Robert Lester

Samuel Weisan Yuan

Donald Lee Clare

Cory J Peterson

Craig K Yanagisawa

Douglas Michael Zuercher

Adam Polcyn

William Harlow McConnell

Karl Gong

Hoan Andrew Au

Mao Nishiyama

Andrew E Larson

Theofilos George Fkiaras

Karthik Venkatesh

Markus Staudenmann

George Robert Houston

Ammar A Zayed

Ryoheita Hattori

Michael Yang

Abhishek Srivastava

Maulik Thaker

Mark Bergquist

Terry Olson

Classica Jain

Andy Larson

Victor Ramirez

Frank J Wang

Various illustrative aspects are directed to a data storage device, comprising one or more disks; an actuator mechanism configured to position one or more heads proximate to a corresponding disk surface of the one or more disks; and one or more processing devices. The one or more processing devices are configured to receive signals indicative of conditions of a write operation by the selected head. The one or more processing devices are further configured to determine, based on the signals, a verification status indicating whether the write operation was successful. The one or more processing devices are further configured to output the verification status within a selected time limit.

Data storage device with write protection and guaranteed rapid write verification in energy-assisted recording (EAR)

The present disclosure is directed to a data storage device that includes a refresh monitor based on a learning based feedback control. The refresh monitor is used to control refresh operations to account for effects of writes to media, e.g., adjacent track interference (ATI). Read operations are analyzed to derive damage information usable to update one or more probability distributions, upon which the learning is updated or reinforced and carried forward. In one embodiments, the data storage device includes control circuitry configured to maintain a refresh monitor based on a learning system, analyze a read operation with the refresh monitor; adjust the refresh monitor by updating the one or more probability distributions based on the analyzed read operation; and execute a refresh operation to refresh data based on the adjusted refresh monitor.

Data storage device adjusting refresh monitor based on a learning based feedback control

A Data Storage Device (DSD) includes a memory for storing data, and a controller configured to execute firmware or code to perform a task. While performing the task, the controller is further configured to assign unique identifiers to respective firmware or code portions that are executed to perform the task, and create a list or data structure including the unique identifier assigned to the firmware or code portion that created the task. A unique identifier is added to the list or data structure for each firmware or code portion executed for the task. The list or data structure indicates the order in which the firmware or code portions are executed.

Exception analysis for data storage devices

A Data Storage Device (DSD) includes at least one Non-Volatile Memory (NVM) configured to store data and a Non-Volatile Cache (NVC). Write data is stored in a volatile memory in preparation for writing the write data in the at least one NVM. In response to a power loss of the DSD, at least a portion of the data stored in the volatile memory is transferred from the volatile memory to the NVC and one or more parameters are determined for deriving a margin representing an additional amount of data for transfer from the volatile memory to the NVC using a remaining power following a power loss. A size of the NVC is adjusted based at least in part on the derived margin.

Adaptive power loss management for data storage devices

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 data storage device is disclosed comprising a non-volatile storage medium (NVSM) having a plurality of data sectors and a plurality of reserve sectors. A map-out value is generated for each of a first plurality of the data sectors based on a read latency of each of the first plurality of data sectors, and when the map-out value of a first data sector in the first plurality of data sectors exceeds a threshold, a first logical block address (LBA) is mapped from the first data sector to a first reserve sector. When the map-out value of a second data sector in the first plurality of data sectors exceeds the map-out value of the first data sector, the first LBA is mapped from the first reserve sector back to the first data sector, and a second LBA is mapped from the second data sector to the first reserve sector.

Data storage device dynamically relocating data sectors based on map-out value

A dynamic scalable error correction coding (ECC) scheme for a data storage system involves a system controller predicting a type and/or amount of ECC needed to reconstruct data to be stored on a particular data storage device(s) based on operational data integrity information accessed from the array of data storage devices. Thus, redundancy does not need to be allocated unless required. The devices may be logically grouped into subsets according to common characteristics, whereby the prediction made for a device in a subset may be based on the data integrity information from that subset, as well as from other relevant subsets.

System-level error correction coding allocation based on device population data integrity sharing

Disclosed herein are magnetic storage media with embedded disconnected circuits, and magnetic storage systems comprising such media. A magnetic storage media comprises a recording layer comprising a storage location, and an embedded disconnected circuit (EDC) configured to assist in at least one of writing to or reading from the storage location in response to a wireless activation signal. A magnetic storage system comprises a signal generator configured to generate a wireless activation signal, a magnetic storage media with a plurality of storage locations, and a write transducer and/or a read receiver. The magnetic storage media has at least one EDC configured to assist in writing to and/or reading from at least one of the plurality of storage locations in response to the wireless activation signal.

Embedded disconnected circuits in magnetic storage media of data storage devices

Disclosed herein are methods of using embedded disconnected circuits (EDC) in magnetic storage media to assist in reading data from and writing data to the magnetic storage media. A wireless activation signal is used to activate an EDC in a magnetic storage media. Once activated, the EDC may assist to record data in and/or read data from one or more memory locations of the magnetic storage media.

Methods of using embedded disconnected circuits in magnetic storage media of data storage devices

The disclosed multi-device platform includes, by way of example, a system that receives a host command including a logical address and determines a hybrid storage device unit based on the logical address. The hybrid storage device unit has a set of hybrid physical storage devices and the set of hybrid physical storage devices includes one or more magnetic storage devices and one or more flash storage devices. The system selects a first plurality of physical storage devices from the set of hybrid physical storage devices, generates a plurality of device commands for the first plurality of physical storage devices based on the host command, and executes the plurality of device commands on the first plurality of physical storage devices.

Unified indirection in a multi-device hybrid storage unit

A Data Storage Device (DSD) includes a magnetic storage medium and a head configured to read and write data using a current default write policy that affects an amount of power output by at least one write-assistive component of the head. One or more experimental writes are performed by writing data on the magnetic storage medium using an experimental write policy for the at least one write-assistive component, and the data is read from the magnetic storage medium. An experimental performance of the one or more experimental writes is evaluated based on the reading of the data. An experimental prediction value is determined indicating a predicted usable life of the head based on the evaluation of the experimental performance. Based on the experimental prediction value, it is determined whether to change the current default write policy for the at least one write-assistive component for future non-experimental writes.

Energy-assisted magnetic recording device capable of predicting the usable life of magnetic head

Managing the flying height of a read-write head slider, such as in the context of a short or head switch seek, involves pre-heating the switched-to head while the active head is still performing a data read or write operation. Thus, both the active head and the switched-to head may be heated simultaneously, and once the switched-to head is switched to an active state upon the active head completing its corresponding operation, the switched-to head can immediately begin its operation with minimal or no further delay.

Preheating a hard disk drive head slider for head switch seek

A data formatting system and method to improve data efficiency and integrity in a hard disk are disclosed. One embodiment provides a disk drive system having a plurality of lookup tables which store a plurality of randomizer seeds which may be dynamically encoded into the preamble field of a customer data block if the customer data is deemed marginal. Encoding the randomizer seed into the preamble field prevents adjacent data track mis-writes and mis-reads.

Method and system for dynamically allocating read and write sequence randomizer

Growing community of inventors

Cupertino, CA, United States of America

Bernd Lamberts