International Business Machines Corporation

Richard Greenberg

Kevin Jack Erickson

John Charles Purkett

Dana H Brown

Thomas W Glaser

Hal Hjalmar Ottesen

Earl Albert Cunningham

John R Reidenbach

Zine-Eddine Boutaghou

Jerry Lee Neubauer

Peter M Herman

Robert E Schopp

Daniel L Good

Timothy J Blank

Timothy Joseph Chainer

David Robison Hall

Jonathan Darrel Coker

John Stewart Best

Lowell James Berg

Christopher H Bajorek

David John Craft

Jerome Thomas Coffey

Donald John Wanek

William Woodrow Brooks, Jr

Steven Harry Voss

Robert A Scranton

Michael John Shea

David Alan Styczinski

Lynn Charles Berning

Russell A Billings

Hjalmar H Ottesen

Walter E Zahn

Nigel F Misso

Jerr L Neubauer

Douglas W Nelson

John Charles Jans, Sr

Kenneth William Meyer

Avijit Mukherjee

A method and apparatus are provided for scheduling commands for random access storage devices with a shortest access chain scheduling algorithm. A plurality of possible chains for a queue of commands are processed. The plurality of possible chains are compared to identify one of the plurality of possible chains having a predetermined property. A first command of the identified one chain having the predetermined property is selected as a next command to execute. The predetermined property includes, for example, a shortest access time or a lowest energy usage.

Method and apparatus for scheduling data accesses for random access storage devices with shortest access chain scheduling algorithm

An electrical signal is communicated between a first device and a second device during a plurality of active clock periods, where the electrical signal is in one of multiple possible states during each of the active clock periods. Timing circuitry within one of the first and second devices detects a predetermined sequence of states in the electrical signal, and in response to detecting the predetermined sequence, adjusts the timing of a subsequent state of the electrical signal with respect to an associated active clock period. Adjustment of signal timing in this manner is useful in reducing signal error due to the line charging effect.

Method and system for selectively varying signal delay in response to detection of a quiescent signal

A method and apparatus are provided for utilizing error correction code (ECC) in a direct access storage device (DASD). A plurality of predetermined file conditions are identified. Each of the plurality of predetermined file conditions are related to a read data raw error rate. An ECC burst control is provided with an ECC engine for varying an ECC correction power of the ECC engine. The ECC correction power is selectively varied responsive to the identified predetermined file conditions.

Method and apparatus for selectively varying error correcting code (ECC) power in a direct access storage device (DASD)

A system and method for encoding a servo address in a disk drive system having at least one disk for storing data is disclosed. A servo address associated with a sector in a track, or cylinder, on a surface of a disk and comprised of a sector number, a track number, and in multiple disk systems, a head number is encoded into the encoded servo address. Encoding the servo address saves disk storage space because the encoded servo address uses fewer bits than a conventional servo address while still enabling the disk drive system to verify the location of any sector.

System and method of encoding an index mark into a servo address

Apparatus and methods for storing predefined information with error correcting code (ECC) in a direct access storage device are provided. Predetermined information is identified and loaded to an ECC generator for customer data to be read and written. The identified predetermined information includes an address for customer data to be read and written. The customer data is written and loaded in parallel to the ECC generator. Then the generated ECC that reflects the pre-loaded predetermined information is written at the end of the written customer data. The customer data and ECC is read and loaded in parallel to the ECC generator. Errors in the predetermined information that is not written to the disk surface, can be detected from the read ECC.

Method and error correcting code (ECC) apparatus for storing predefined

Storing data on a data processing system is done upon generation of a data file by displaying a user interface allowing user selection of storage criteria for the data file. Responsive to user selection of storage criteria for a file determining a physical format type for the file from a plurality of available physical format types. Then the file is stored on a direct access storage device as at least a first record conforming with the determined physical format type.

Storage of user defined type file data in corresponding select physical

A capacitor discharge retract system is provided for small disk drives wherein the small spindle size is incapable of generating enough electrical energy to enable conventional actuator retraction and the form factor is too small to accommodate capacitors of sufficient size to enable a conventional capacitive discharge system. A capacitive discharge retract technique is enabled using an elevated voltage, significantly above the disk drive supply voltage, to allow smaller capacitive storage elements to perform the function. The effectiveness of the system is further enhanced in those environments where a source of the required elevated voltage can be found already resident in the device circuitry where it was generated to support another function.

Actuator retract/unload system for low power disk drives

A low profile, high capacity, high performance disk drive includes a plurality of disk surfaces mounted in parallel for simultaneous rotation about an axis. Each of a plurality of data transducer heads for reading and/or writing data to the data surfaces is attached to a slider. A stacked arm actuator for moving the data transducer heads in a radial direction across the disk surfaces includes a supporting arm and a suspension load beam attached to the supporting arm. The suspension load beam connects the supporting arm to the slider. The suspension load beam includes a load dimple bearing on the slider and has opposed stiffening flanges extending in a plane adjacent the slider. The actuator includes a stack of 9 head arm suspension assemblies and the stack has a height of 16.634 mm. An interdisk spacing of less than 1.4 mm provides a height dimension of 14.635 for a stack of 8 disks. Shock and electrical isolation is accomplished using four mounting blocks carrying energy absorbing, highly damped, resilient material.

High capacity, high performance low profile disk drive

A system and related architecture for providing random access cache storage between a processor accessing data at high speed and in small block units and a mass storage medium holding data in large transfer units. Lossless data compression is applied to large transfer units of data before storage in a DRAM. Cache address space is assigned in allocation units which are assigned without a prespecified pattern within the DRAM but linked through chains. The chain lengths are adjusted to match the compressibility characteristics of transfer units and include resources for scavenging residuals. Logical blocks materially smaller than the transfer units are accessed and decompressed during readout from the DRAM. The system architecture provides resources for accessing the individual logical blocks through an index. The invention is particularly suited for a disk drive cache system having a small cache DRAM in conjunction with a magnetic or optical disk mass storage system reading highly compressible data.

Compressed data cache storage system

Apparatus and methods are provided to prevent writing and reading at an incorrect position and seeking to incorrect position. A servo address is written in a servo burst and loaded into an error correcting code (ECC) generator for generating write positioning ECC check bytes. The write positioning ECC check bytes are written at the end of the written servo address in the servo burst. When customer data is to be written, the written servo address and write positioning ECC check bytes are read and loaded into the ECC generator to determine whether the writing position is correct. Then the servo address or logical block address (LBA) is preloaded into a second error correcting code (ECC) generator and the customer data is written and loaded into the second error correcting code (ECC) generator for generating data and read positioning ECC check bytes. The data and read positioning ECC check bytes are written at the end of the written customer data. When customer data is to be read, the LEA is preloaded into the second error correcting code (ECC) generator and then the written customer data and the data and read positioning ECC check bytes are read and loaded into the second ECC generator to determine whether the reading position is correct. A secondary servo address that includes a portion of the servo address is written in the servo burst. The secondary servo address can be written adjacent to the servo address; in an automatic gain control (AGC) field; or in a fine servo field of the servo burst. The secondary servo address is read to determine a transducer head position. During a write operation, the secondary servo address can be used exclusively or as a redundancy to the main servo address. The secondary servo address can be used instead of the write positioning check bytes.

Servo address apparatus and positioning methods for read, write and seek

A servo address is encoded in a disk drive system having at least one disk for storing data. A servo address associated with a sector in a track, or cylinder, on a surface of a disk and comprised of a sector number, a track number, and in multiple disk systems, a head number is encoded into the encoded servo address. Encoding the servo address saves disk storage space because the encoded servo address uses fewer bits than a conventional servo address while still enabling the disk drive system to locate positions on the disk.

System and method for encoding a servo address

A disk drive stores multimedia data in long spiral data tracks. The tracks on opposite surfaces of the disk spiral in opposite directions, so that a track on one surface can be read as the actuator sweeps in, and a track on the opposite surface can be read as the actuator sweeps out. Because the actuator only follows spiral tracks without performing long seek operations, the actuator motor can be reduced in size and stresses on actuator bearings and other parts are reduced. Additionally, due to reduced disturbances associated with seeks, it is possible to follow tracks more closely and therefore reduce the width of individual tracks. Further cost reductions are accomplished by spinning the disks at a slower speed and reducing the size of the spin motor accordingly. Finally, data density can be increased simply because multimedia data does not require the same low error rate as conventional data. Preferably, a group of disk drives optimized for multimedia data is used to form a video-on-demand system. Compressed, interleaved portions of a video presentation, such as a motion picture, are stored in blocks on the spiral tracks. The drives read the blocks on one spiral track at a time from beginning to end, placing the data from these blocks in a set of buffers corresponding to different short time intervals. Video signals are output from the buffers. Any short time interval of the presentation can be accessed on demand by switching to the appropriate buffer.

Disk storage device with spiral data track and incremental error offsets

A digital storage system is disclosed in which a flying read/write head is loaded onto the surface of moving storage media with controlled velocity to avoid contact with the surface of the storage media. Head load velocity is detected by measuring the back EMF generated by the head arm actuator. Improved control and accuracy is obtained by breaking up the head arm actuator drive power into a series of pulses and measuring the back EMF induced into the low impedance voice coil of the head arm actuator in between pulses but only after the actuator current has been reduced to substantially zero in order to avoid interference by actuator current induced voltages.

Pulsed current velocity controlled head load method and apparatus which

A secondary data storage system for a host computer system includes a disk drive system having a device controller, at least a first magnetic disk and a read/write magnetic transducer positionable with respect to a recording surface of each magnetic disk. A write operation exposes data on adjacent tracks to potential damage if an off track condition occurs to the transducer during a write. A method for controlling write operations through the device controller provides backup of data in tracks adjacent to a target track for the write operation prior to the write operation occurring. The method detects occurrence of events resulting in an off track condition of the magnetic transducer relative to a target track. Occurrence of such an event triggers a determination of damage to the contents of tracks adjacent to the target track and restoration of those tracks. Write operations to the target track are blocked until shock events discontinue.

Growing community of inventors

Rochester, MN, United States of America

Richard Greenberg