Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Handling Defective Tracks in a Cached Storage System

IP.com Disclosure Number: IPCOM000050915D
Original Publication Date: 1982-Dec-01
Included in the Prior Art Database: 2005-Feb-10
Document File: 2 page(s) / 43K

Publishing Venue

IBM

Related People

Benhase, MT: AUTHOR [+4]

Abstract

A direct access storage device (DASD) is coupled to a host via a cache random-access memory. DASD at times will have a defective track which requires accessing an alternate track for fetching or storing data. Three possible controls are utilized for handling defective tracks; the procedure selected can be host dependent, that is, it can be modified to accommodate diverse job streams. A first control is to promote and replace the data from the alternate track using normal data promotion and replacement algorithms with respect to the caching random-access store. A second algorithm is to promote the entire alternate track and have a separate list in the cache directory pointing to the alternate track from the defective track such that the defective track need not be referenced.

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

Handling Defective Tracks in a Cached Storage System

A direct access storage device (DASD) is coupled to a host via a cache random-access memory. DASD at times will have a defective track which requires accessing an alternate track for fetching or storing data. Three possible controls are utilized for handling defective tracks; the procedure selected can be host dependent, that is, it can be modified to accommodate diverse job streams. A first control is to promote and replace the data from the alternate track using normal data promotion and replacement algorithms with respect to the caching random-access store. A second algorithm is to promote the entire alternate track and have a separate list in the cache directory pointing to the alternate track from the defective track such that the defective track need not be referenced. The third control is to completely bypass caching when an alternate track is involved.

A host connected to the cache DASD storage system can send a select signal to select which defective track mode is to be utilized in a given series of data transfer operations between the host and the DASD. A first algorithm is to treat the alternate track A the same as a defective track T, as indicated by the select line 1. That is, data from DASD is promoted to cache and recorded in the directory as if the alternate track A was a regular track, i.e., separately addressable. This requires moving head H from track T to alternate track A each time there is a data transfer between DASD and the cache. A subsequent host access request to such data transfer resul...