METRICS

The problem of determining page size in a page on demand system is discussed in detail in this paper. After having introduced the problem, the effect page size may have on various system performance measures is reviewed based on measurements of program ...

For rotating storage units, a paging drum organization is known to offer substantially better response time to I/O requests than is a more conventional (file) organization [Abate and Dubner, 1969; Fuller and Baskett, 1972 ]. When several, asynchronous ...

The HASP Execution Task Monitor periodically rearranges the OS/360 dispatching chain to give tasks pre-emptive execution priority in inverse order to their CPU utilization history. The effect is to keep the I/O bound tasks active and to prevent CPU ...

This paper presents the design and an evaluation method of an operating system in which the optimization of system utilization is controlled by resource-demanded dispatching of program segments and dynamic scheduling of segment execution. The basic ...

A multiple channel controller (MCC)is a controller which allocates a given number of channels among a larger number of peripheral devices, and permits simultaneous access to as many devices as there are channels available. Using simplifying assumptions, ...

A model of paging behavior of programs under multiprogramming and a model of dual processor multi-memory processing system with virtual memory are developed. Combining these two models, it is possible to evaluate the throughput of multiprogrammed ...

The practical value of queuing theory in engineering application such as in computer modeling has been limited, since the interest in mathematical tractability has almost always led to an oversimplified model. The diffusion process approximation is an ...

An approach often taken to the problem of understanding the behavior of a computer system has been to build a simulation model. Although models are excellent from the point of view that they allow unlimited inspection of behavior without introducing ...

This paper briefly reviews various classes of computer performance measurement activity, especially in the context of the development of an experimental discipline for testing hypotheses concerning software unit behavior. Several proposals for beginning ...

The only value of measurement and evaluation in business-related programs is to save money. The most traditional economic maxim, that of marginal analysis, can be applied to the selection of the best mix of measurement and evaluation techniques. Three ...

Performance measures of machine utilization is done on a continuing basis at Livermore. A brief description of the sampling and presentation techniques are given. The impact of timesharing and heavy I/O loading is shown graphically.

The paper establishes a definition for the quantity of computation based on information theory concepts. The definition is based on the recognition of a computing device, process or procedure as a set of associated information sources as defined by ...

An era of consumer awareness and power is upon us. Although the great “Silent Majority” of computer system users (or consumers) may not be aware of it yet, the dawn of their era of awareness and power is near! With the development of multiaccess ...

This paper describes the design of and experience with an automated benchmark-generation facility for system testing and performance evaluation. The basic approach involves two components. The first is a simple, highly parameterized “synthetic job”, ...

This paper describes how a regression model of the Research Center's APL system was constructed and used for evaluating system changes. The regression methodology that is generally used for performing such an analysis is believed to have been expanded ...

The Dialogue Monitor has been developed as a tool for the measurement of computer service. The objectives of such measurement are defined. A set of models and measures is developed. Operation of the Dialogue Monitor and analysis of the data obtained are ...

The objective of this brief paper is to point out an often overlooked central issue facing the computer manager today and to suggest a comprehensive technique to improve management and utilization of large-scale computer systems.

In the early days of ...

The first part of this paper describes AMS, a software monitor that is activated by both timing information and system events. The structure of the monitor is described and typical results are displayed. The last half of the paper examines the potential ...

Many computer systems are sufficiently complex that it is not possible to predict or understand all of the interactions among system components. Performance monitoring is a technique for measuring system performance and recording the internal states of ...