Estimating response time for auxiliary memory configurations with multiple movable-head disk modules

• Authors: Kenneth Omahen
• Venue: VLDB '75 Proceedings of the 1st International Conference on Very Large Data Bases
• Year: 1975

The hardware architecture for a large data base application often involves the use of movable-head disk modules for auxiliary memory. This paper considers design calculations for such systems and is divided into two main sections described below. A survey is given of literature dealing with queueing models for multiple-module movable-head disk configurations. References are also provided to papers related to single movable-head disks which describe techniques for estimating seek time distributions, queueing models for channel operation, etc., which are useful for the multiple-module case. A simple method is presented for estimating average response time for a multi-module configuration of movable-head disk units attached to a single block multiplexer channel. The technique is a synthesis of a method described by Seaman, Lind, and Wilson for analyzing a similar configuration having a selector channel and variations of a method for treating a block multiplexer channel described by Fuller and Baskett. Seaman et al. view the operation of each disk module as a M/G/1 queueing system using the FCFS discipline; channel operation in turn is analyzed using the "machine-interference" model. Fuller and Baskett treat the operation of a channel with rotational position sensing by means of a queueing model with Poisson arrivals (infinite-source) and service process consisting of (a) two exponential stages corresponding to rotational delay and data transfer time, respectively, where the first stage has variable service rate which is a function of the number of requests at the channel, or (b) one exponential stage with variable service rate dependen on number of requests at the channel system. The proposed technique involves the use of the method of Seaman et al. but replaces the machine-interference model for channel operation with either of two finite-source queueing models similar to those of Fuller and Baskett.