Abstract
Measurement of the lengths of disk arm movements in a 2314 disk storage facility of an IBM 360/67 operating under the Michigan Terminal System yielded the unexpected data that the arms need not move in 63% of the accesses and need move for an average of only 30ms. in the remaining 37% of the cases. A description and analysis of a possible mechanism of action is presented. The predictions of this model do not disagree with the measured data.

This publication has 3 references indexed in Scilit: