摘要:
One or more data-storing disk devices support logical tracks extending between radial recording zones of tracks in the device(s). Each data-storing disk in the device(s) is formatted into a plurality of radial recording zones of physical tracks, each radial recording zone having a like number of physical tracks, each physical track may be one circumvolution of a single spiral track. The physical tracks in the respective recording zones store a different number of data bytes. Each logical track including a plurality of said physical tracks; at least one of the physical tracks in each of the logical tracks is in a different one of the radial recording zones in different ones of the devices or in a single device. Described are an extended logical track and extended logical cylinder accessing methods and apparatus. Not all of the physical tracks of any of the devices or recording zones need be a member of any logical track.
摘要:
Bitmap compression for fast searches and updates is provided. Compressing a bitmap includes receiving a bitmap to compress, and reading the bitmap to determine a value of a bit location for all bits in the bitmap. In one embodiment, a compressed bitmap is created by encoding a variable number of bytes to represent a distance between adjacent 1s in the uncompressed bitmap. In another embodiment, a compressed bitmap is created by representing a distance between adjacent 1s in the uncompressed bitmap using a plurality of bits, and encoding a marker word to indicate the number of bits used to represent the distance.
摘要:
A data stream received by a hard disk drive (HDD) is organized into at least one cluster having data blocks and spare data blocks and that is equal in size to an integer multiple of the number of sectors in a track of a disk of the HDD. A variable-index writing technique is used to write each data block of a cluster to a corresponding sector of a track that is encountered by a head when the sector is not defective. A sector of the track is skipped during writing when the sector is defective. The number of spare data blocks in a portion of a cluster corresponding to a single track is reduced by the number of sectors that are skipped in the track so that the number of data blocks plus the number of remaining spare data blocks equals the number of sectors in a track.
摘要:
A data recording disk file with a fixed block architecture sector format that eliminates the ID region. The servo region contains sector identification information in the form of a start-of-track indicating mark recorded in a selected sector of each track and a start-of-sector indicating mark recorded in each sector. A full track number identifier is encoded in the position field within the servo region of each sector. A look-up table is built at format time to map bad sectors out of the disk file. The table contains entries for each cluster of contiguous bad sectors, and is searched at runtime to provide conversion of logical sector location identifiers to physical sector location identifiers.
摘要:
A method for operating a synchronized array of fixed block (FBA) formatted Direct Access Storage Devices (DASDs) to store and update variable-length (CKD) formatted records. This method is suitable for use with DASDs that obtain high recording density by using read and write head technology requiring "micro-jogging" to adjust for differing read and write head alignment or banded disk architecture having a higher block count in the outer tracks than in the inner tracks. Magneto-resistive heads may require micro-jogging to realign the write head for recording after reading the physical track location. The invention employs a DASD staggered array architecture having logical tracks consisting of diagonal-major sequences of consecutive blocks arranged in a predetermined wrap-around manner such as a topological cylinder or torus. The minimum necessary number of DASDs (N) in the staggered array is limited by the fixed block size (B), the interblock gap size (G), the average DASD data transfer rate (D), and the micro-jog delay time (T). A (N+1).sup.th DASD may be added to record the parity of each diagonal-major sequence for improved fault-tolerance.
摘要:
A magnetic recording disk has servo sectors that are generally equally spaced on a given track and read during seek, settle, and track-following operations. An algorithm is used to determine the allowable time separation between servo sectors on a track and lengths of associated data sections that may be accommodated on the disk. In such a manner, the servo sectors are equally spaced on a given track and may be located within a data field of a data sector, within an identification region, or immediately after an address indicating mark (such as an address mark or an index mark). The rate at which the servo sectors are sampled is constant and independent of the number and lengths of the data sections. As a result of this independent relationship, this technique is suitable for a banded recording disk using sectored servo. The banded magnetic recording disk with multiple radially-spaced data bands has generally equally angularly-spaced servo sectors extending across the bands to provide a constant servo sample rate independent of the data rate.
摘要:
The Hamming distance of an array of storage devices is increased by generating a parity check matrix based on column equations that are formed using an orthogonal parity code and includes a higher-order multiplier that changes each column. The higher order multiplier is selected to generate a finite basic field of a predetermined number of elements. The array has M rows and N columns, such that M is greater than or equal to three and N is greater than or equal to three. Row 1 through row M−2 of the array each have n–p data storage devices and p parity storage devices. Row M−1 of the array has n−(p+1) data storage devices and (p+1) parity storage devices. Lastly, row M of the array has N parity storage devices.
摘要:
A magnetic recording disk drive has head positioning servo sectors with servo sector numbers (SSNs) that are not recorded on the disk. The SSNs are encoded through the use of multiple servo sector types that are arranged in a specific sequence around the data tracks. The different servo sector types are identified by unique types of servo timing marks (STMs), which are used to locate the servo sectors. The SSNs that are used to identify the servo sectors on the track form a set or code of m fixed n-bit patterns. A SSN is determined when the STM types read from n sequential servo sectors match one of the fixed SSN pattems. A set or code of m servo sectors, where each servo sector is identified by a unique SSN pattern having length n, is denoted as an (m,n,d) code, where d is referred to as the minimum Hamming distance of the code. The Hamming distance between two patterns refers to the number of locations that are different between the two pattems.
摘要:
A method and means is described wherein servo sectors written on a disk (or servo sections written on a tape) are equally spaced on a given track and read during seek, settle and track following operations. An algorithm is used to determine the allowable time separation between servo sectors (or sections) on a track and lengths of associated data sections, such as data sectors or variable length records, that may be accommodated on the disk or tape in such manner that each of the servo sectors (or sections) equally spaced on a given track is located within a data field of a data sector or within an identification region or immediately after an address indicating mark (such as address mark or index mark). The rate at which the servo sector (or section) is sampled is constant and independent of the number and lengths of the data sections. As a result of this independent relationship, this technique is suitable for CLD recording, to banded disks using sectored servo as in conventional FBA, and also even to non-sectored architectures, such as count-key-data (CKD), wherein the data is written in records of variable length, and to tape drives formatted in FBA or CKD.
摘要:
Bitmap compression for fast searches and updates is provided. Compressing a bitmap includes receiving a bitmap to compress, and reading the bitmap to determine a value of a bit location for all bits in the bitmap. In one embodiment, a compressed bitmap is created by encoding a variable number of bytes to represent a distance between adjacent 1s in the uncompressed bitmap. In another embodiment, a compressed bitmap is created by representing a distance between adjacent 1s in the uncompressed bitmap using a plurality of bits, and encoding a marker word to indicate the number of bits used to represent the distance.