Pub Date : 1988-03-27DOI: 10.1109/INFCOM.1988.13015
A. Weinrib, S. Shenker
The authors consider the problem of job placement in load-sharing algorithms for large heterogeneous distributed computing environments. They present simulation results using a simple model; the results indicate that, under heavy loads, the usual policy of placing jobs where they will incur the shortest expected delay leads to inefficient system performance. Thus, purely greedy policies are not sufficient; the authors identify a simple threshold algorithm that does significantly better. The authors introduce a novel adaptive algorithm having a performance much closer to optimal.<>
{"title":"Greed is not enough: adaptive load sharing in large heterogeneous systems","authors":"A. Weinrib, S. Shenker","doi":"10.1109/INFCOM.1988.13015","DOIUrl":"https://doi.org/10.1109/INFCOM.1988.13015","url":null,"abstract":"The authors consider the problem of job placement in load-sharing algorithms for large heterogeneous distributed computing environments. They present simulation results using a simple model; the results indicate that, under heavy loads, the usual policy of placing jobs where they will incur the shortest expected delay leads to inefficient system performance. Thus, purely greedy policies are not sufficient; the authors identify a simple threshold algorithm that does significantly better. The authors introduce a novel adaptive algorithm having a performance much closer to optimal.<<ETX>>","PeriodicalId":436217,"journal":{"name":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134333470","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}
Pub Date : 1988-03-27DOI: 10.1109/INFCOM.1988.12911
J. Pachl
The authors presents a problem that arises in the design of protocols for ring networks. It is shown that some existing and proposed protocols can reach a livelocked state as a result of a single transmission error. Livelock-free modifications of the protocols are described. The protocols covered fall into two classes: those in which error recovery utilizes a unique monitor station, and those in which all stations in the ring follow the same algorithm (decentralized protocols). It is shown that although the simplest protocol in each class is susceptible to livelocks, there are some nonobvious differences between the two classes. The problem is outlined and the assumptions made are also presented. Protocols with a monitor station are studied along with decentralized protocols. An example is given of a livelock. Informal arguments are used to show that the modifications proposed are livelock-free.<>
{"title":"Livelocks in slotted ring networks","authors":"J. Pachl","doi":"10.1109/INFCOM.1988.12911","DOIUrl":"https://doi.org/10.1109/INFCOM.1988.12911","url":null,"abstract":"The authors presents a problem that arises in the design of protocols for ring networks. It is shown that some existing and proposed protocols can reach a livelocked state as a result of a single transmission error. Livelock-free modifications of the protocols are described. The protocols covered fall into two classes: those in which error recovery utilizes a unique monitor station, and those in which all stations in the ring follow the same algorithm (decentralized protocols). It is shown that although the simplest protocol in each class is susceptible to livelocks, there are some nonobvious differences between the two classes. The problem is outlined and the assumptions made are also presented. Protocols with a monitor station are studied along with decentralized protocols. An example is given of a livelock. Informal arguments are used to show that the modifications proposed are livelock-free.<<ETX>>","PeriodicalId":436217,"journal":{"name":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129372103","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}
Pub Date : 1988-03-27DOI: 10.1109/INFCOM.1988.13002
J. Daigle, Robert B. Kuehl, Joseph D. Langford
The authors consider worker waiting times and throughput for an optical-disk-based document storage and retrieval system in an office environment. They model the system as a single-server queuing system having a finite number of each of two types of worker: document user and document entry. Worker think times are assumed to be exponentially distributed while job service times are drawn from general distributions; worker think times and job service times are dependent on worker type. Throughput and waiting time as a function of the number of users of each type are analyzed under a nonpreemptive rule in which document use has priority over document entry. The methodology developed to assess average delays in finite-source queuing systems with priority appears to be novel.<>
{"title":"Queueing analysis of an optical disk based office system","authors":"J. Daigle, Robert B. Kuehl, Joseph D. Langford","doi":"10.1109/INFCOM.1988.13002","DOIUrl":"https://doi.org/10.1109/INFCOM.1988.13002","url":null,"abstract":"The authors consider worker waiting times and throughput for an optical-disk-based document storage and retrieval system in an office environment. They model the system as a single-server queuing system having a finite number of each of two types of worker: document user and document entry. Worker think times are assumed to be exponentially distributed while job service times are drawn from general distributions; worker think times and job service times are dependent on worker type. Throughput and waiting time as a function of the number of users of each type are analyzed under a nonpreemptive rule in which document use has priority over document entry. The methodology developed to assess average delays in finite-source queuing systems with priority appears to be novel.<<ETX>>","PeriodicalId":436217,"journal":{"name":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","volume":"165 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132947356","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}
Pub Date : 1988-03-27DOI: 10.1109/INFCOM.1988.12931
J. Rodríguez
The design of a computer communications device is presented the purpose of which is to act as a translator between two virtual circuit protocols: Tymnet's X.PC, and the US Department of Defense's DOD's TCP. Protocol translation in general and details on how the X.PC/TCP translation is done are discussed. Problems found in the task of protocol translation are also discussed.<>
{"title":"An X.PC/TCP protocol translator","authors":"J. Rodríguez","doi":"10.1109/INFCOM.1988.12931","DOIUrl":"https://doi.org/10.1109/INFCOM.1988.12931","url":null,"abstract":"The design of a computer communications device is presented the purpose of which is to act as a translator between two virtual circuit protocols: Tymnet's X.PC, and the US Department of Defense's DOD's TCP. Protocol translation in general and details on how the X.PC/TCP translation is done are discussed. Problems found in the task of protocol translation are also discussed.<<ETX>>","PeriodicalId":436217,"journal":{"name":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115406822","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}
Pub Date : 1988-03-27DOI: 10.1109/INFCOM.1988.13006
M. Paterakis, P. Papantoni-Kazakos
A simple full-feedback-sensing window random-access algorithm is proposed and analyzed in the presence of the Poisson user model. The throughput of the algorithm is 0.43. The proposed algorithm is better than J.I. Capetanaki's dynamic algorithm (1979) with respect to its delay and resistance to channel errors. The simple operations of the algorithm, along with its regenerative properties, facilitate the computation of the output traffic interdeparture distribution. The obtained distribution is useful in the evaluation of interacting systems which adopt the algorithm for their internal transmissions.<>
{"title":"A simple window random access algorithm with advantageous properties","authors":"M. Paterakis, P. Papantoni-Kazakos","doi":"10.1109/INFCOM.1988.13006","DOIUrl":"https://doi.org/10.1109/INFCOM.1988.13006","url":null,"abstract":"A simple full-feedback-sensing window random-access algorithm is proposed and analyzed in the presence of the Poisson user model. The throughput of the algorithm is 0.43. The proposed algorithm is better than J.I. Capetanaki's dynamic algorithm (1979) with respect to its delay and resistance to channel errors. The simple operations of the algorithm, along with its regenerative properties, facilitate the computation of the output traffic interdeparture distribution. The obtained distribution is useful in the evaluation of interacting systems which adopt the algorithm for their internal transmissions.<<ETX>>","PeriodicalId":436217,"journal":{"name":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","volume":"15 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115498120","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}
Pub Date : 1988-03-27DOI: 10.1109/INFCOM.1988.12972
A. Economides, Petros A. Ioannou, J. Silvester
The problem of routing virtual circuits according to dynamical probabilities in virtual-circuit packet-switched networks is considered. Queueing network models are introduced and performance measures are defined. A decentralized asynchronous adaptive routing methodology based on learning automata theory is presented. Every node in the network has a stochastic learning automaton as a router for every destination node. The routing probabilities that are assigned to the network paths are updated asynchronously on the basis of current network conditions. A learning algorithm suitable for routing is used. Some initial simulation experiments, for a simple network, show convergence to optimal routing.<>
{"title":"Decentralized adaptive routing for virtual circuit networks using stochastic learning automata","authors":"A. Economides, Petros A. Ioannou, J. Silvester","doi":"10.1109/INFCOM.1988.12972","DOIUrl":"https://doi.org/10.1109/INFCOM.1988.12972","url":null,"abstract":"The problem of routing virtual circuits according to dynamical probabilities in virtual-circuit packet-switched networks is considered. Queueing network models are introduced and performance measures are defined. A decentralized asynchronous adaptive routing methodology based on learning automata theory is presented. Every node in the network has a stochastic learning automaton as a router for every destination node. The routing probabilities that are assigned to the network paths are updated asynchronously on the basis of current network conditions. A learning algorithm suitable for routing is used. Some initial simulation experiments, for a simple network, show convergence to optimal routing.<<ETX>>","PeriodicalId":436217,"journal":{"name":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","volume":"117 20","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120827167","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}
Pub Date : 1988-03-27DOI: 10.1109/INFCOM.1988.12968
Ruben A. Quiros, Isaac D. Scherson
A novel implementation is presented, the Stubborn protocol, which provides the right compromise to obtain a balanced and near-optimal performance under both normal (control) operation and transient (emergency) conditions. It is based on the following simple principle: stations make access attempts as in the usual 1-persistent CSMA/CD (carrier-sense multiple-access with collision detection). In case of collision, a station with priority higher than zero will not interrupt transmission, but will exercise its right to extend the collision for a period proportional to its priority level. The station that persists longer will be able to start 'clean' transmission as soon as all others have desisted. The algorithm is complemented with tie-breaking procedures.<>
{"title":"Stubborn: a medium access protocol for expert assistants in distributed control systems","authors":"Ruben A. Quiros, Isaac D. Scherson","doi":"10.1109/INFCOM.1988.12968","DOIUrl":"https://doi.org/10.1109/INFCOM.1988.12968","url":null,"abstract":"A novel implementation is presented, the Stubborn protocol, which provides the right compromise to obtain a balanced and near-optimal performance under both normal (control) operation and transient (emergency) conditions. It is based on the following simple principle: stations make access attempts as in the usual 1-persistent CSMA/CD (carrier-sense multiple-access with collision detection). In case of collision, a station with priority higher than zero will not interrupt transmission, but will exercise its right to extend the collision for a period proportional to its priority level. The station that persists longer will be able to start 'clean' transmission as soon as all others have desisted. The algorithm is complemented with tie-breaking procedures.<<ETX>>","PeriodicalId":436217,"journal":{"name":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123980498","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}
Pub Date : 1988-03-27DOI: 10.1109/INFCOM.1988.12914
J. Bannister, U. Warrier
The authors present the framework for a downline load service to which users subscribe to be properly loaded with their required code images. They review the user's requirements and present the outline of a service definition and protocol that satisfies the requirements. The analysis of downline-load protocol performance is given from the point of view of the time required to downline load a large number of devices. The authors also examine the impact of the total traffic generated by downline loading. Two downline-loading algorithms are studied and their performance characteristics compared.<>
{"title":"Design and analysis of network down line road protocols","authors":"J. Bannister, U. Warrier","doi":"10.1109/INFCOM.1988.12914","DOIUrl":"https://doi.org/10.1109/INFCOM.1988.12914","url":null,"abstract":"The authors present the framework for a downline load service to which users subscribe to be properly loaded with their required code images. They review the user's requirements and present the outline of a service definition and protocol that satisfies the requirements. The analysis of downline-load protocol performance is given from the point of view of the time required to downline load a large number of devices. The authors also examine the impact of the total traffic generated by downline loading. Two downline-loading algorithms are studied and their performance characteristics compared.<<ETX>>","PeriodicalId":436217,"journal":{"name":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125749882","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}
Pub Date : 1988-03-27DOI: 10.1109/INFCOM.1988.12957
I. Rubin, M. Ouaily
The authors carry out message delay and system throughput analysis for communication and telecommunications system applications which require the use of finite-capacity service systems using preemptive buffering (PB) disciplines. Such systems are of particular importance in situation where it is essential to provide short (and at times, bounded) message waiting-time delays, for messages which are selected for service. The authors analyze and compare the performance of such service systems, modeling them as finite capacity M/G/1/N queueing systems and using the service/buffering policies first-come-first-served/nonpreemptive buffering (FCFS/NPB), FCFS/PB, and last-come-first-served/preemptive buffering (LCFS/PB). They evaluate the performance tradeoffs offered by these policies, as they relate to the mean and variance of the waiting times of messages which are eventually served or eventually rejected/preempted.<>
{"title":"Performance of finite capacity communication and queuing systems under various service and buffer preemption policies","authors":"I. Rubin, M. Ouaily","doi":"10.1109/INFCOM.1988.12957","DOIUrl":"https://doi.org/10.1109/INFCOM.1988.12957","url":null,"abstract":"The authors carry out message delay and system throughput analysis for communication and telecommunications system applications which require the use of finite-capacity service systems using preemptive buffering (PB) disciplines. Such systems are of particular importance in situation where it is essential to provide short (and at times, bounded) message waiting-time delays, for messages which are selected for service. The authors analyze and compare the performance of such service systems, modeling them as finite capacity M/G/1/N queueing systems and using the service/buffering policies first-come-first-served/nonpreemptive buffering (FCFS/NPB), FCFS/PB, and last-come-first-served/preemptive buffering (LCFS/PB). They evaluate the performance tradeoffs offered by these policies, as they relate to the mean and variance of the waiting times of messages which are eventually served or eventually rejected/preempted.<<ETX>>","PeriodicalId":436217,"journal":{"name":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","volume":"88 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128302700","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}
Pub Date : 1988-03-27DOI: 10.1109/INFCOM.1988.12935
M. Hluchyj, M. Karol
The authors study the performance of four different approaches for providing the queuing necessary to smooth fluctuations in packet arrivals to a space-division packet switch. They are (1) input queueing, where a separate first-in, first-out (FIFO) buffer is provided at each input to switch; (2) input smoothing, where a frame of b packets is stored at each of the N input lines to the switch and simultaneously launched into a switch fabric of size Nb*Nb; (3) output queuing, where packets are queued in a separate FIFO buffer located at each output of the switch; and (4) completely shared buffering, where all queuing is done at the outputs and all buffers are completely shared among all the output lines.<>
{"title":"Queueing in space-division packet switching","authors":"M. Hluchyj, M. Karol","doi":"10.1109/INFCOM.1988.12935","DOIUrl":"https://doi.org/10.1109/INFCOM.1988.12935","url":null,"abstract":"The authors study the performance of four different approaches for providing the queuing necessary to smooth fluctuations in packet arrivals to a space-division packet switch. They are (1) input queueing, where a separate first-in, first-out (FIFO) buffer is provided at each input to switch; (2) input smoothing, where a frame of b packets is stored at each of the N input lines to the switch and simultaneously launched into a switch fabric of size Nb*Nb; (3) output queuing, where packets are queued in a separate FIFO buffer located at each output of the switch; and (4) completely shared buffering, where all queuing is done at the outputs and all buffers are completely shared among all the output lines.<<ETX>>","PeriodicalId":436217,"journal":{"name":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129001125","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：