{"title":"A simulation study of replication control protocols using volatile witnesses","authors":"P. K. Sloope, Jehan-Francois Pâris, D. Long","doi":"10.1109/SIMSYM.1992.227571","DOIUrl":"https://doi.org/10.1109/SIMSYM.1992.227571","url":null,"abstract":"Voting protocols guarantee the consistency of replicated data objects by disallowing all access requests that cannot gather a sufficient quorum of replicas. The performance of voting protocols can be greatly enhanced by adding to the replicas small independent entities that hold no data but can attest to the state of the replicated data object. It has been recently proposed to store these witnesses in volatile storage. Volatile witnesses respond faster to write requests than those stored in stable storage. They can also be more easily regenerated as many local area networks contain a majority of diskless sites. The authors present a simulation study of the availability afforded by two voting protocols using volatile witnesses and investigate the impact of access rates, network topology and witness placement on the availability of the replicated data.<<ETX>>","PeriodicalId":215380,"journal":{"name":"Proceedings. 25th Annual Simulation Symposium","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123322553","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":"Simulation analysis of a collisionless multiple access protocol for a wavelength division multiplexed star-coupled configuration","authors":"P. Dowd, K. Bogineni","doi":"10.1109/SIMSYM.1992.227569","DOIUrl":"https://doi.org/10.1109/SIMSYM.1992.227569","url":null,"abstract":"A collisionless wavelength division multiple access protocol is introduced for a passive star-coupled photonic network that possesses significant performance and flexibility advantages over alternative approaches. A detailed simulation analysis is developed to study the behavior of the protocol with varying system characteristics. The protocol is control channel based: one of the WDM channels is used to reserve access for data packet transmission on the remaining data channels. Control channel access arbitration is achieved through time-division multiplexing, enabling all active nodes to transmit once every control cycle. This approach significantly reduces the long synchronization delays typical of time-division multiplexing systems: the control cycle length is proportional to the control packet size rather than the data packet size. The proposed approach has the advantage that variable sized data packets in a collisionless environment are supported without utilization degradation. Furthermore, a mechanism is introduced that relaxes the constraints on the switching times of the optical components by decreasing the performance sensitivity. The performance is evaluated in terms of network throughput, packet delay, and control and data channel utilization. In particular, this paper examines the performance impact with variations in the number of nodes and data channels, packet generation rate, data packet length, and the optical device switching latencies.<<ETX>>","PeriodicalId":215380,"journal":{"name":"Proceedings. 25th Annual Simulation Symposium","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122688908","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":"En route to more efficient conservative parallel event simulation","authors":"Meng-Lin Yu","doi":"10.1109/SIMSYM.1992.227577","DOIUrl":"https://doi.org/10.1109/SIMSYM.1992.227577","url":null,"abstract":"This paper presents some techniques to improve the performance of a conservative algorithm, YADDES, for asynchronous discrete event simulation. A guideline is developed for minimizing the complexity of lookahead computation and a modular approach is proposed for reducing the overhead for simulating large numbers of components.<<ETX>>","PeriodicalId":215380,"journal":{"name":"Proceedings. 25th Annual Simulation Symposium","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128414864","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":"Simulation of self-stabilizing algorithms in distributed systems","authors":"M. Flatebo, A. Datta","doi":"10.1109/SIMSYM.1992.227579","DOIUrl":"https://doi.org/10.1109/SIMSYM.1992.227579","url":null,"abstract":"The property of self-stabilization in distributed systems was originally introduced by Dijkstra (1974). Depending on the connectivity and propagation delay in the system, each machine gets a partial view of the global state. The set of global states can be split up into two categories, legal and illegal. In a self-stabilizing system, regardless of the initial state of the system, legal or illegal, the system automatically converges to a legal state in a finite number of steps. Also, if an error occurs in the system causing the system to be put into an illegal state, the system again corrects itself and converges to a legal state in a finite amount of time. Many self-stabilizing algorithms have been developed, but the complexity of self-stabilizing algorithms is difficult to determine. This paper provides an experimental analysis of various self-stabilizing algorithms in order to help determine the efficiency of these algorithms and to compare algorithms which solve the same problem.<<ETX>>","PeriodicalId":215380,"journal":{"name":"Proceedings. 25th Annual Simulation Symposium","volume":"125 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126282618","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":"Knowledge-based distributed simulation generator","authors":"Y. Wong, Shu-Yuen Hwang","doi":"10.1109/SIMSYM.1992.227566","DOIUrl":"https://doi.org/10.1109/SIMSYM.1992.227566","url":null,"abstract":"The way to speed up the entire process of simulation can be considered from two points of view: the machine side and the human side. The former refers to the use of efficient programming techniques to speed up the simulation program. Specifically, parallel or distributed simulation is the trend, due to the advance of computer hardware technology. The latter refers to the use of intelligent method to automate the whole process of simulation model construction. This paper presents the STNMG system, which is a knowledge-based automatic simulation model generator for public switched telephone networks. Through dialog with its user, STNMG can acquire the necessary information about the simulated system and save it as an internal specification. A time warp optimistic simulator for the simulated system specified by user is then constructed based on this internal specification. The prototype of STNMG is proposed.<<ETX>>","PeriodicalId":215380,"journal":{"name":"Proceedings. 25th Annual Simulation Symposium","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132759574","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":"A simulation based analysis of naming schemes for distributed systems","authors":"T. Znati, J. Molka","doi":"10.1109/SIMSYM.1992.227578","DOIUrl":"https://doi.org/10.1109/SIMSYM.1992.227578","url":null,"abstract":"As the Internet grows in size and number of users, the way in which resources are identified and accessed becomes increasingly important. This implies the need for an efficient naming service. A naming service is a facility that enables clients to name objects, and subsequently use these names to locate these objects. Developing a naming facility and choosing the naming conventions involves a tradeoff between performance, user friendliness, object mobility, availability of naming information, individual autonomy, storage space requirement, and the cost of maintaining data consistency. The purpose of this paper is to analyze three different naming schemes in a wide area network, and study the impact of design parameters such as transmission capabilities, cache hit ratio, and servers' rate of failure on the performance of a naming facility.<<ETX>>","PeriodicalId":215380,"journal":{"name":"Proceedings. 25th Annual Simulation Symposium","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114141876","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":"The effect of inter-PE communication network configuration on the performance of array computers","authors":"H. Diab, H. Tabbara","doi":"10.1109/SIMSYM.1992.227565","DOIUrl":"https://doi.org/10.1109/SIMSYM.1992.227565","url":null,"abstract":"Discusses the effect of the inter-processor element communication network (IN) on the performance of SIMD machines using discrete event simulation. The performance evaluation process is based on modelling SIMD computer systems composed of a control unit supervising n processing elements (PEs) each having local memory. The PEs communicate with each other through the IN which is assumed to be static throughout the evaluation process. The influence of the IN delay between PEs on the overall system performance such as the speedup, utilization, and throughput is computed.<<ETX>>","PeriodicalId":215380,"journal":{"name":"Proceedings. 25th Annual Simulation Symposium","volume":"2 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131725841","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":"Scripting highly autonomous simulation behavior using case-based reasoning","authors":"Niels Catsimpoolas, J. Marti","doi":"10.1109/SIMSYM.1992.227581","DOIUrl":"https://doi.org/10.1109/SIMSYM.1992.227581","url":null,"abstract":"Describes additions to the object-oriented RISE system to allow high level simulation of autonomous units. The authors are attempting to use case-based reasoning as a basis for simulating the intelligent behavior of military units. They present details of the mechanism and argue that the key to its success is the proper balance of high level planning code, and efficient primitive behaviors.<<ETX>>","PeriodicalId":215380,"journal":{"name":"Proceedings. 25th Annual Simulation Symposium","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123851487","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":"Potential performance of parallel conservative simulation of VLSI circuits and systems","authors":"M. Rawling, R. Francis, D. Abramson","doi":"10.1109/SIMSYM.1992.227575","DOIUrl":"https://doi.org/10.1109/SIMSYM.1992.227575","url":null,"abstract":"The deterministic nature of conservative simulation makes it possible to conduct an accurate trace-driven analysis of an existing sequential simulator in order to predict concurrency profiles and speedup bounds for several parallel implementations. This paper describes such an analysis carried out on a commercial VLSI digital circuit simulator with results based on real instance evaluation times at microsecond resolutions. The authors consider a central event queue based model with and without lookahead, as well as the distributed message passing model. The results help to answer the important questions, 'Just how much concurrency is there in real commercial VLSI simulations?' and 'What type of machine would be best suited for a parallel implementation?'.<<ETX>>","PeriodicalId":215380,"journal":{"name":"Proceedings. 25th Annual Simulation Symposium","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127732663","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":"A framework for the efficient Petri net simulation of real-time systems","authors":"W. Evanco, Jeffrey Yang","doi":"10.1109/SIMSYM.1992.227561","DOIUrl":"https://doi.org/10.1109/SIMSYM.1992.227561","url":null,"abstract":"An efficient approach for the development and simulation of Petri net models of real-time systems is discussed. The approach is based on perturbation analytical techniques. Specifically, a variation of the standard clock approach, called the iterative standard clock, is used to efficiently simulate multiple experiments in a single computer run.<<ETX>>","PeriodicalId":215380,"journal":{"name":"Proceedings. 25th Annual Simulation Symposium","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115582294","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}