Browse Prior Art Database

Validity Verification of Compressed Data Using Disk Cache Facilities

IP.com Disclosure Number: IPCOM000043742D
Original Publication Date: 1984-Sep-01
Included in the Prior Art Database: 2005-Feb-05
Document File: 2 page(s) / 44K

Publishing Venue

IBM

Related People

Dixon, JD: AUTHOR [+5]

Abstract

A technique is described whereby random bit errors of compressed data may be detected at a time sufficiently close to time of compression, so as to be able to recover the original data. When backing up critical data sets in order to preserve the data in the event of a disaster, it is common to copy the critical data sets from magnetic disk to magnetic tape units. This can be a slow and costly process. Therefore, the use of data compression techniques was introduced to reduce the volume of backup data to be placed on the magnetic tape. However, a major limitation may occur in the event the compressed data cannot be recovered. The problem generally centers around the encoded data encountering random bit errors.

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 52% of the total text.

Page 1 of 2

Validity Verification of Compressed Data Using Disk Cache Facilities

A technique is described whereby random bit errors of compressed data may be detected at a time sufficiently close to time of compression, so as to be able to recover the original data. When backing up critical data sets in order to preserve the data in the event of a disaster, it is common to copy the critical data sets from magnetic disk to magnetic tape units. This can be a slow and costly process. Therefore, the use of data compression techniques was introduced to reduce the volume of backup data to be placed on the magnetic tape. However, a major limitation may occur in the event the compressed data cannot be recovered. The problem generally centers around the encoded data encountering random bit errors. In the worst-case situation, all of the original data is lost from the point of occurrence of the first bit error in the compressed version. The technique used in this article is to be able to recover the original data from its compressed version at the time the compression takes place. The elements involved in making backup copies of data from disk to magnetic tape are illustrated in Fig. 1. The backup process starts with the disk controller 1. Data read from the disk is compressed using special-purpose hardware. It is then sent over the I/O channel 2 for storage in either one of two buffers 3 and 4 maintained in main memory 5 and controlled by the central processor 6 to supervise the various phases of the backup copy operation. A double buffering technique is generally employed such that one main memory buffer is being filled with compressed data while the other buffer is emptying its data to the magnetic tape control unit 7 and subsequently to the tape unit 8. The data transfer bandwidth of the I/O channel is sufficiently wide so that both the transfer of data from disk to the buffer and from buffer to tape can occur concurrently. The improved technique, as illustrated in Fig. 2, essentially utilizes an internal data...