{"title":"Trace driven modeling and analysis of CPU scheduling in a multi-programming system","authors":"S. Sherman, F. Baskett, J. Browne","doi":"10.1145/800024.808358","DOIUrl":"https://doi.org/10.1145/800024.808358","url":null,"abstract":"Microscopic level job stream data obtained in a production environment by an event driven software probe is used to drive a model of a multiprogramming computer system. The CPU scheduling algorithm of the model is systematically varied. This technique, called trace driven modeling, provides an accurate replica of a production environment for the testing of variations in the system. At the same time alterations in scheduling methods can be easily carried out in a controlled way with cause and effects relationships being isolated. The scheduling methods tested included the best possible and worst possible methods, the traditional methods of multiprogramming theory, round-robin, first-come-first-serve, etc., and dynamic predictors. The relative and absolute performance of these scheduling methods is given. It is concluded that a successful CPU scheduling method must be pre-emptive and must prevent a given job from holding the CPU for too long a period.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121470680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Performance measurements on a virtual memory computer system in a batch-processing environment","authors":"A. Batson, R. Brundage","doi":"10.1145/800024.808360","DOIUrl":"https://doi.org/10.1145/800024.808360","url":null,"abstract":"A standard benchmark mix has been developed for a B5500 computer, and was run under different operating conditions to investigate the effects of overlaying on system performance. The results provide some data on the changes in throughput associated with the support of a virtual memory scheme.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122574072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Performance of the GE-645 associative memory while Multics is in operation","authors":"M. D. Schroeder","doi":"10.1145/800024.808361","DOIUrl":"https://doi.org/10.1145/800024.808361","url":null,"abstract":"The Multiplexed Information and Computing Service (Multics) of Project MAC at M.I.T. runs on a General Electric 645 computer system. The processors of this hardware system contain logic for both paging and segmentation of addressable memory. They directly accept two-part addresses of the form (segment number, word number) which they translate into absolute memory addresses through a series of indexed table lookups. To speed this address translation each processor contains a small, fast associative memory which remembers the most recently used address translation table entries. This paper reports the results of performance measurements on this associative memory. The measurements were made by attaching an electronic counter directly to a processor while Multics was in operation, and were taken for several associative memory sizes. The measurements show that for the observed load 16 associative registers are enough.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123599837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"UNIVAC 1108 Hardware Instrumentation System","authors":"D. T. Bordsen","doi":"10.1145/800024.808352","DOIUrl":"https://doi.org/10.1145/800024.808352","url":null,"abstract":"The UNIVAC 1108 Hardware Instrumentation System evolved out of the necessity to obtain information on the operations taking place within the 1108 multi-processor system. The instrumentation system supplies three different types of information; a trace of the software executed, a trace of the instructions executed, and a trace of the memory addresses referenced to obtain instructions and operands. This information is used to improve the performance of the UNIVAC 1108 software and to aid in the design of new processor and memory hierarchy designs.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124042415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automatic load adjustment in time-sharing systems","authors":"M. Wilkes","doi":"10.1145/800024.808364","DOIUrl":"https://doi.org/10.1145/800024.808364","url":null,"abstract":"The paper is concerned with the automatic adjustment of the number of console users on a time-sharing system according to the total load on the system. The control procedure comprises two algorithms. The first makes a periodic assessment ahead of time of the number of tasks that it would be necessary to insert into the system in order to keep the number of tasks actually within it (including those waiting on queues) under control. The second algorithm adjusts the number of users so that, when the system is under control, the number of tasks actually entering is, on the average, equal to the target number calculated in advance. The design of the first algorithm is critical from the point of view of stability and the greater part of the paper is devoted to a discussion of it based on the theory of linear recurrence relations. In designing the second algorithm, the main consideration is the avoidance of oscillation in the number of permitted users without, however, making the system so heavily damped that it is unresponsive.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123173008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Sim/61: A simulation measurement tool for a time-shared, demand paging operating system","authors":"S. Morganstein, J. Winograd, R. Herman","doi":"10.1145/800024.808357","DOIUrl":"https://doi.org/10.1145/800024.808357","url":null,"abstract":"A simulation program to be used as a performance measurement tool for RCA's Virtual Memory Operating System, VMOS, is presented. The model is a fairly detailed one structured much like the operating system itself. The program has been used to evaluate design decisions and is able, with some qualifications, to give quantitative predictions on measures which might be of interest to marketing and system design personnel.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131226354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}