Browse Prior Art Database

Cyclic Memory Record Format Without Intrarecord Gaps

IP.com Disclosure Number: IPCOM000087791D
Original Publication Date: 1977-Mar-01
Included in the Prior Art Database: 2005-Mar-03
Document File: 2 page(s) / 22K

Publishing Venue

IBM

Related People

Chang, HK: AUTHOR [+2]

Abstract

A data storage system, including a cyclic memory, such as a disk file, in which data is stored serially along tracks on a record medium, includes a control unit for controlling input or output data transfers between the memory and a host system channel. The data storage system operates in a command/response mode. Data is recorded in the cyclic memory in the illustrated format.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 53% of the total text.

Page 1 of 2

Cyclic Memory Record Format Without Intrarecord Gaps

A data storage system, including a cyclic memory, such as a disk file, in which data is stored serially along tracks on a record medium, includes a control unit for controlling input or output data transfers between the memory and a host system channel. The data storage system operates in a command/response mode. Data is recorded in the cyclic memory in the illustrated format.

For each block of data to be stored in the memory there is an associated identifier (ID). In response to write commands from the host system, the control unit causes the cyclic memory to write each ID field contiguously with a data field in a continuous record which is spaced from similar records by interrecord gaps. However, each ID field is not written contiguously with the data field it identifies, but with the data field preceding that which it identifies. As illustrated, ID(N) is written contiguously with DATA(N1).

Thus operations, subsequent to reading or writing ID, which would have taken place in intrarecord gaps in a conventional Count-Key-Data format can now take place during the contiguous data field and interrecord gap. The elimination of intrarecord gaps results in a net saving of space on the medium. Error correction code (ECC) bits are generated for the data only and are stored at the end of the data field. The ID must have its own error correction which may be realized by a simple error correction code or triplication.

Typical operations which take place during the time interval between ID and its associated data field are ID processing, correct ID data check, if any, status presentation,...