The Impact of Operating System Structure on Personal Computer Performance

13522 Words Mar 19th, 2011 55 Pages
The Impact of Operating System Structure on Personal Computer Performance
Toby Jackson
Abstract
The Impact of Operating System Structure on Personal Computer Performance
Toby Jackson
This paper presents a comparative study of the performance of three operating systems that run on the personal computer architecture derived from the IBM-PC. The operating systems, Windows for Workgroups (tm), Windows NT (tm), and NetBSD (a freely available UNIX (tm) variant) cover a broad range of system functionality and user requirements, from a single address space model to full protection with preemptive multi-tasking. Our measurements were enabled by hardware counters in Intel’s Pentium (tm) processor that permit measurement of a broad range of processor
…show more content…
• Preemptive multi-tasking: People wait for printers and batch jobs and initiate context switches manu- ally. • High-level system abstractions: Abstractions like pipes and background jobs are not immediately useful for applications that use a graphical user interface. A key distinction between UNIX systems and the Microsoft OS products we studied is support in the Microsoft products for backwards compatibility with MS/DOS and Windows. The requirement of compatibility with Windows has influenced many aspects of the Windows NT structure. The structural impact of backwards compatibility is diffi- cult to evaluate in isolation; nonetheless the performance impact of the microkernel architecture chosen to implement this compatibility is substantial. This study explores how compatibility and the system structures it requires affects performance in the three systems.
For this paper we quantify the impact of differences between the three operating systems using hardware event counters in the Pentium microprocessor [Intel 94, Mathisen 94]. We will present results from two sets of experiments, one using microbenchmarks and another using application workloads. The general strategy for our analysis is:
• Measure microbenchmarks. • Explain microbenchmark results from available documentation. • Measure application performance. •

More about The Impact of Operating System Structure on Personal Computer Performance

Open Document