发布求助
文献互助 智能选刊 最新文献

SIGOPS Workshop on System Performance Evaluation最新文献

筛选
英文 中文
Designing a commercial performance measurement system 设计一个商业绩效评估系统
SIGOPS Workshop on System Performance Evaluation Pub Date : 1900-01-01 DOI: 10.1145/800024.808353
Gary M. Holtwick
{"title":"Designing a commercial performance measurement system","authors":"Gary M. Holtwick","doi":"10.1145/800024.808353","DOIUrl":"https://doi.org/10.1145/800024.808353","url":null,"abstract":"Several years ago, we undertook the task of designing and constructing a software computer measurement system. The initial requirements we made of the system, problems that arose during the development phase when we actually tried to adhere to those requirements, the solutions to these problems, and subsequent use and modification of the completed product form the basis of discussion here.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"283 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":"121013045","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}
引用次数: 7
Throughput analysis of computer systems - multiprogramming versus multiprocessing 计算机系统的吞吐量分析。多道程序与多道处理
SIGOPS Workshop on System Performance Evaluation Pub Date : 1900-01-01 DOI: 10.1145/800024.808354
W. Chang, Y. Paternot, J. A. Ray
{"title":"Throughput analysis of computer systems - multiprogramming versus multiprocessing","authors":"W. Chang, Y. Paternot, J. A. Ray","doi":"10.1145/800024.808354","DOIUrl":"https://doi.org/10.1145/800024.808354","url":null,"abstract":"To increase system throughput, multiprogramming and multiprocessing systems are introduced. The first improves the throughput by means of interleaving the individual service requests, and the latter by exploiting the parallelism in the system design. The basic philosophy of multiprogramming is compared with that of multiprocessing to put the concepts in their proper perspective. Simple mathematical models, based on the theory of queues, were used to analyze the throughput capacity of these systems. The throughput of a given multiprogramming system configuration is compared with a number of multiprocessing systems. Within each multiprocessing system, the throughput is maximized by determining the optimum number of processors, and the optimum number of control and supervision programs which are required to control the system. The mathematical analysis is completely substantiated by the GPSS simulation results.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"1 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":"130672749","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}
引用次数: 4
A Petri Net model of the CDC 6400 CDC 6400的Petri网模型
SIGOPS Workshop on System Performance Evaluation Pub Date : 1900-01-01 DOI: 10.1145/800024.808367
J. D. Noe
{"title":"A Petri Net model of the CDC 6400","authors":"J. D. Noe","doi":"10.1145/800024.808367","DOIUrl":"https://doi.org/10.1145/800024.808367","url":null,"abstract":"Measurement and evaluation of computer systems requires a model of the computer under control of the operating system that shows the interrelation between task flow and allocation of resources. For multiprogramming and multiprocessing systems, the model needs to show parallelism of operations. Furthermore, it should allow easy shift into greater or less detail as required by the measurement investigation, while providing perspective on the whole system. An adaptation of Petri Nets has been found well suited to this purpose. The representation shows parallelism, and allows compression of either sequential or parallel operations when less detail is required. The paper describes a multiprocessor, multiprogramming system, the CDC 6400, in terms of Petri Nets and shows how this type of representation lends itself to planning system measurements.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"141 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":"132984791","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}
引用次数: 38
A software design and evaluation system 一个软件设计与评价系统
SIGOPS Workshop on System Performance Evaluation Pub Date : 1900-01-01 DOI: 10.1145/800024.808359
R. M. Graham, G. J. Clancy, David B. DeVaney
{"title":"A software design and evaluation system","authors":"R. M. Graham, G. J. Clancy, David B. DeVaney","doi":"10.1145/800024.808359","DOIUrl":"https://doi.org/10.1145/800024.808359","url":null,"abstract":"One of the most difficult problems facing the software designer and implementer is that of evaluating the performance of a proposed design before it is actually implemented. Pre-implementation evaluation is invaluable in assisting the designer to meet the specified performance objectives of the system being designed. This problem of meeting objectives is particularly severe for large multi-programmed, multi-processing operating systems. These systems have become so complex that even the most experienced system designer is unable to evaluate a system's performance using intuition alone. Use of more formal methods is required. Existing techniques are handicapped by a severe time lag. To avoid costly re-implementation, feedback must get to the designers before the design is “cast in concrete.” In this paper we describe a system which provides performance information at all stages in the design and implementation of a software system (which we will call the object system). Using this feedback the designer can spot the problems which adversely affect performance early enough in the design-implementation sequence that they can be corrected without having to reimplement much of the object system.\u0000 The key idea in our design and evaluation system is to use a single language to describe the object system at all stages of its design and implementation. This evolving source language description of the object system is used as direct input to the evaluation procedures. The initial sketch of the system's structure and data bases, which is the gross design specification, evolves into a final, detailed implementation specification which can be compiled into executable object code. As soon as any part of the object system is specified some evaluation information is available. As the design becomes more detailed this information becomes more precise. Thus, a fairly detailed and precise picture of the object system's performance is developed before it is implemented.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"23 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":"123008420","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}
引用次数: 1
Optimum choice of page sizes in a virtual memory with a hardware executive and a rapid-access secondary storage medium 在具有硬件执行器和快速访问辅助存储介质的虚拟内存中进行页面大小的最佳选择
SIGOPS Workshop on System Performance Evaluation Pub Date : 1900-01-01 DOI: 10.1145/800024.808365
E. Gelenbe
{"title":"Optimum choice of page sizes in a virtual memory with a hardware executive and a rapid-access secondary storage medium","authors":"E. Gelenbe","doi":"10.1145/800024.808365","DOIUrl":"https://doi.org/10.1145/800024.808365","url":null,"abstract":"A paged virtual memory system with a finite number n≥1 of page sizes, containing a hardware executive and a rapid-access secondary storage medium is considered. It is postulated that in such a system the smallest page size will be chosen small enough to render internal fragmentation negligible, and that this page size C1 will be fixed independently of the other page sizes. The problem of choosing the remaining page sizes is then cast as a problem of minimizing the bookkeeping space for page tables in the hardware executive, on the average, with the assumption that the probability distribution of segment sizes is known. The mathematical problem is solved for the uniform and exponential distributions and numerical results are given for the Poisson and an empirically determined distribution. These results indicate a rule of thumb which may be used to choose the remaining page sizes. Finally, the results are compared with paging with a single page size.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"31 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":"122187998","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}
引用次数: 2
CP-67 measurement and analysis overhead and throughput CP-67测量和分析开销和吞吐量
SIGOPS Workshop on System Performance Evaluation Pub Date : 1900-01-01 DOI: 10.1145/800024.808362
Y. Bard
{"title":"CP-67 measurement and analysis overhead and throughput","authors":"Y. Bard","doi":"10.1145/800024.808362","DOIUrl":"https://doi.org/10.1145/800024.808362","url":null,"abstract":"The performance of a complex time sharing system was monitored under actual operating conditions during a period in which changes in system configuration (both hardware and software) took place. Various techniques for assessing the impact of those changes on performance are discussed.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"62 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":"121795395","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}
引用次数: 4
The optimal organization of multiprogrammed multi-level memory 多程序多级存储器的最佳组织
SIGOPS Workshop on System Performance Evaluation Pub Date : 1900-01-01 DOI: 10.1145/800024.808356
S. R. Arora, A. Gallo
{"title":"The optimal organization of multiprogrammed multi-level memory","authors":"S. R. Arora, A. Gallo","doi":"10.1145/800024.808356","DOIUrl":"https://doi.org/10.1145/800024.808356","url":null,"abstract":"This study suggests a method for performance evaluation in a multiprogramming environment. The joint effect of two major cost elements - the processing time and the memory space - have been investigated. This involves two issues; 1) optimal memory loading and sizing, and 2) central site timing analysis. The latter has been approached mathematically with a cyclic queuing model; the memory space utilization was studied with a linear optimization model. Varying the values of the major cost carrying factors, through iteration, the authors investigate marginal utilities and search for the concept of an optimally balanced system.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"72 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":"128362056","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}
引用次数: 17
Analysis of system bottlenecks using a queueing network model 使用排队网络模型分析系统瓶颈
SIGOPS Workshop on System Performance Evaluation Pub Date : 1900-01-01 DOI: 10.1145/800024.808355
J. Buzen
{"title":"Analysis of system bottlenecks using a queueing network model","authors":"J. Buzen","doi":"10.1145/800024.808355","DOIUrl":"https://doi.org/10.1145/800024.808355","url":null,"abstract":"While it is well known that queues can build up at various points in large scale multiprogramming computer systems, comparatively little is known about the factors which govern the lengths of these queues and their relationship to overall system performance. The first part of this paper is concerned with developing a queueing network model which can be used to study a number of such questions. The model is then applied to a specific problem concerning the proportion of processing requests which should be directed to each of a set of functionally equivalent peripheral processors (e.g., disks and drums) in order to optimize overall system performance. A surprising result is that optimal performance is not attained when queue lengths and processor utilization percentages are equal, but rather when the fastest processor has the longest expected queue and is in effect creating a system bottleneck.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"3 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":"114080690","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}
引用次数: 75
Statistical methods in performance evaluation 绩效评估中的统计方法
SIGOPS Workshop on System Performance Evaluation Pub Date : 1900-01-01 DOI: 10.1145/800024.808363
P. Denning, B. Eisenstein
{"title":"Statistical methods in performance evaluation","authors":"P. Denning, B. Eisenstein","doi":"10.1145/800024.808363","DOIUrl":"https://doi.org/10.1145/800024.808363","url":null,"abstract":"This paper reviews the principles and definitions which underlie estimation theory and develops the theory for application to problems of performance evaluation and resource allocation. The statistical characterization of the estimates of a parameter is discussed with reference to the meaning and importance of biasedness, convergence criteria, and responsiveness.\u0000 Several sequential estimation algorithms in the form of stochastic approximation are analyzed and a comparison is made of the ability of these algorithms to determine the value of an “almost constant” parameter given noisy (uncertain) measurements.\u0000 A discussion of the shortcomings of the present theory as well as some open problems concludes the paper.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"11 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":"127256731","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}
引用次数: 2
A probabilistic framework for system performance evaluation 系统性能评估的概率框架
SIGOPS Workshop on System Performance Evaluation Pub Date : 1900-01-01 DOI: 10.1145/800024.808366
S. R. Kimbleton, C. Moore
{"title":"A probabilistic framework for system performance evaluation","authors":"S. R. Kimbleton, C. Moore","doi":"10.1145/800024.808366","DOIUrl":"https://doi.org/10.1145/800024.808366","url":null,"abstract":"A method for comparing throughput, turnaround time and availability is given for a processor-bound computer system. The method appears to be extendable to any computer system in which there is a clearly defined limiting resource.","PeriodicalId":296019,"journal":{"name":"SIGOPS Workshop on System Performance Evaluation","volume":"25 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":"131893999","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}
引用次数: 14
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书