This paper shows how system call traces can be obtained with minimal interference to the system being characterized, and used as realistic, repeatable workloads for experiments to evaluate operating system and file system designs and configuration alternatives. Our system call trace mechanism, called ULTrU, captures a compleie trace of each UNIX process's calls t o the operating system. The performance impact is normally small, and it runs in user mode without special privileges. We show how the resulting traces can be used t o drivefull, repeatable reexecution of the captured behaviour, and present a case study which shows the usefulness and accuracy of the tool for predicting the impact of file system caching on a W W W server's performance.

This paper shows how system call traces can be obtained with minimal interference to the system being characterised, and used as realistic, repeatable workloads for experiments to evaluate operating system and le system designs and con guration alternatives.Our system call trace mechanism, called Ultra, captures a complete trace of each Unix process's calls to the operating system. The performance impact is normally small, and it runs in user mode without special privileges.Traces can be rerun in two ways: the operating system activity can be reproduced by simply replaying the system calls interspersed with appropriate delays. More interestingly, we also show how the resulting traces can be used to drive full, repeatable reexecution of the captured behaviour.The paper concludes with an evaluation and comparison of the usefulness and accuracy of these techniques for predicting the performance impact of system con guration altenatives. We present two case studies, examining the e ect of le system caching on a Www server's performance, and the performance bene t of using a local disk instead of an NFS leserver.

No abstract

A trace of a workload's system calls can be obtained with minimal interference, and can be used as to drive repeatable experiments to evaluate system configuration alternatives. Replaying system call traces alone sometimes leads to inaccurate predictions because paging, and access to memory-mapped files, are not modelled.This paper extends tracing to handle such workloads. At trace capture time, the application's page-level virtual memory access is monitored. The size of the page access trace, and capture overheads, are reduced by excluding recently-accessed pages. This leads to a slight loss of accuracy. Using a suite of memory-intensive applications, we evaluate the capture overhead and measure the predictive accuracy of the approach.

No abstract