Browse Prior Art Database

Using Disk Cache Facilities to Traverse an Index Tree Entirely Within the Disk Subsystem Containing an Indexed Data Set

IP.com Disclosure Number: IPCOM000043708D
Original Publication Date: 1984-Sep-01
Included in the Prior Art Database: 2005-Feb-05
Document File: 2 page(s) / 53K

Publishing Venue

IBM

Related People

Dixon, JD: AUTHOR [+4]

Abstract

This article discusses the use of an indexing technique for computer systems using disk cache memory. Described is a method of traversing an index tree to reduce channel activity and central processing time when fetching indexed data. The basic elements of the disk subsystem, as shown in Fig. 1, include the disk cache buffer 11 and the various levels of the index data base 12, the microprocessor 13 which is used to control all logical processing associated with interpretation of information from one level of index, then issuing the read operation to fetch information from the next index level. Also included is the disk Volume Table of Contents (VTOC) 14 which is maintained in microprocessor storage 15. A typical three-level tree format index structure, as shown in Fig.

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

Using Disk Cache Facilities to Traverse an Index Tree Entirely Within the Disk Subsystem Containing an Indexed Data Set

This article discusses the use of an indexing technique for computer systems using disk cache memory. Described is a method of traversing an index tree to reduce channel activity and central processing time when fetching indexed data. The basic elements of the disk subsystem, as shown in Fig. 1, include the disk cache buffer 11 and the various levels of the index data base 12, the microprocessor 13 which is used to control all logical processing associated with interpretation of information from one level of index, then issuing the read operation to fetch information from the next index level. Also included is the disk Volume Table of Contents (VTOC) 14 which is maintained in microprocessor storage 15. A typical three-level tree format index structure, as shown in Fig. 2, is used to reduce the number of disk accesses necessary to locate and utilize a specific target data item. Without an index tree structure, it would be necessary to sequentially read every data base record until the target item is found. By traversing the index, one level is read so as to determine the next physical record location of either the next lower level of index or the final data item itself. To illustrate the saving in CPU time, Fig. 3 shows a time state diagram of the cycle time required in processing data on the conventional sequential basis. It is necessary to engage in CPU and I/O channel activity for each and every one of the four disk accesses. Considerable CPU time is required to execute th...