Pub Date : 1992-04-01DOI: 10.1109/PCCC.1992.200544
M. Rabinovich, Ed Lazowska
A modification of the tree protocol for distributed mutual exclusion is presented. The existing tree protocol is very efficient as long as all nodes in the system are accessible, but if suffers from performance degradation during the time when some nodes are down or partitioned. Although failures may be infrequent, once a node is down, it may remain down for a relatively long time. In the modified protocol, a node requesting mutual exclusion may experience performance degradation at most once after some failures occur but then it adapts to a new system topology and its performance returns to normal. In the case when all nodes in the system are accessible, the protocol exhibits the same performance as the existing tree protocol.<>
{"title":"The dynamic tree protocol: avoiding 'graceful degradation' in the tree protocol for distributed mutual exclusion","authors":"M. Rabinovich, Ed Lazowska","doi":"10.1109/PCCC.1992.200544","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200544","url":null,"abstract":"A modification of the tree protocol for distributed mutual exclusion is presented. The existing tree protocol is very efficient as long as all nodes in the system are accessible, but if suffers from performance degradation during the time when some nodes are down or partitioned. Although failures may be infrequent, once a node is down, it may remain down for a relatively long time. In the modified protocol, a node requesting mutual exclusion may experience performance degradation at most once after some failures occur but then it adapts to a new system topology and its performance returns to normal. In the case when all nodes in the system are accessible, the protocol exhibits the same performance as the existing tree protocol.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126157096","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 : 1992-04-01DOI: 10.1109/PCCC.1992.200507
R. Probert, H. Yu, K. Saleh
A model employing totally ordered events of a distributed system based on a logical clock has been presented by L. Lamport (1978). The authors propose a new interpretation and extension of Lamport's notion of concurrency by introducing the concept of relative concurrency to capture the nature of concurrency of distributed systems by means of a relative (or logical) clock. They then derive a totally ordered global events model based on the relative clock. Based on this model, they represent and interpret timing (ordering) information from observable scenarios, including collision scenarios of the system, expressed in an extended trace assertion language (ETAL) specification. Finally, a new approach is illustrated with a realistic example for test result analysis including timing information based on the global events model.<>
L. Lamport(1978)提出了一个基于逻辑时钟的分布式系统的完全有序事件模型。作者提出了Lamport并发概念的一种新的解释和扩展，通过引入相对并发的概念，通过相对(或逻辑)时钟来捕捉分布式系统并发的本质。然后，他们根据相对时钟推导出一个完全有序的全局事件模型。基于该模型，它们表示和解释来自可观察场景(包括系统的冲突场景)的计时(排序)信息，这些信息用扩展跟踪断言语言(ETAL)规范表示。最后，通过一个实例说明了一种基于全局事件模型的包含时间信息的测试结果分析新方法。
{"title":"Relative-clock-based specification and test result analysis of distributed systems","authors":"R. Probert, H. Yu, K. Saleh","doi":"10.1109/PCCC.1992.200507","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200507","url":null,"abstract":"A model employing totally ordered events of a distributed system based on a logical clock has been presented by L. Lamport (1978). The authors propose a new interpretation and extension of Lamport's notion of concurrency by introducing the concept of relative concurrency to capture the nature of concurrency of distributed systems by means of a relative (or logical) clock. They then derive a totally ordered global events model based on the relative clock. Based on this model, they represent and interpret timing (ordering) information from observable scenarios, including collision scenarios of the system, expressed in an extended trace assertion language (ETAL) specification. Finally, a new approach is illustrated with a realistic example for test result analysis including timing information based on the global events model.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123021991","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 : 1992-04-01DOI: 10.1109/PCCC.1992.200549
P. Kim, Hwan-Ik Choi, Yoon-Joon Lee, Sang Ho Lee, Myungjoon Kim
The authors have developed a multiuser storage system named MIDAS (multiuser index-based data access system). They describe the internal structure in conjunction with the design principles of MIDAS. To achieve a high degree of concurrency, the original B/sup +/-tree was modified and the various system tables were divided into several independent partitions. A database in MIDAS can have more than one disk volume and a file can be spread over several volumes. An extent-based disk manager was implemented by means of the raw device interface to circumvent shortcomings of the UNIX file system. The transaction notion was supported via the strict two-phase locking method with multiple granularity and a hybrid recovery scheme. The overall system architecture of MIDAS is presented. Some major modules in MIDAS are described.<>
{"title":"MIDAS: design philosophy and internals","authors":"P. Kim, Hwan-Ik Choi, Yoon-Joon Lee, Sang Ho Lee, Myungjoon Kim","doi":"10.1109/PCCC.1992.200549","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200549","url":null,"abstract":"The authors have developed a multiuser storage system named MIDAS (multiuser index-based data access system). They describe the internal structure in conjunction with the design principles of MIDAS. To achieve a high degree of concurrency, the original B/sup +/-tree was modified and the various system tables were divided into several independent partitions. A database in MIDAS can have more than one disk volume and a file can be spread over several volumes. An extent-based disk manager was implemented by means of the raw device interface to circumvent shortcomings of the UNIX file system. The transaction notion was supported via the strict two-phase locking method with multiple granularity and a hybrid recovery scheme. The overall system architecture of MIDAS is presented. Some major modules in MIDAS are described.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130353781","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 : 1992-04-01DOI: 10.1109/PCCC.1992.200543
V.R. Narender, R. Kannan
The authors propose an enhancement to the remote procedure call (RPC) called the dynamic RPC (DRPC), to facilitate dynamic client-server relationships, extensibility, and protocol transparency. A prototype DRPC has been implemented as a component of a distributed computing infrastructure, the communications manager for the DARPA initiative in concurrent engineering program. DRPC currently supports two popular commercial implementations of RPC-Sun ONC/RPC and Apollo NCS/RPC. A preliminary comparative performance analysis is presented.<>
{"title":"Dynamic RPC for extensibility","authors":"V.R. Narender, R. Kannan","doi":"10.1109/PCCC.1992.200543","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200543","url":null,"abstract":"The authors propose an enhancement to the remote procedure call (RPC) called the dynamic RPC (DRPC), to facilitate dynamic client-server relationships, extensibility, and protocol transparency. A prototype DRPC has been implemented as a component of a distributed computing infrastructure, the communications manager for the DARPA initiative in concurrent engineering program. DRPC currently supports two popular commercial implementations of RPC-Sun ONC/RPC and Apollo NCS/RPC. A preliminary comparative performance analysis is presented.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"175 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120956006","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 : 1992-04-01DOI: 10.1109/PCCC.1992.200583
A. Yu, K.-J. Lin
An algorithm for scheduling real-time periodic tasks on a multiprocessor system under a fault-tolerant requirement is presented. The approach incorporates both the redundancy and masking technique, and the imprecise computation model. Since the tasks in hard real-time systems have stringent timing constraints, the redundancy and masking technique is more appropriate than the rollback techniques, which usually require extra time for error recovery. The imprecise computation model provides flexible functionality by trading off the quality of the result produced by a task with the amount of processing time required to produce it. It therefore permits the performance of a real-time system to degrade gracefully. The algorithm was evaluated by stochastic analysis and Monte Carlo simulations. The results showed that the algorithm was resilient under hardware failure.<>
{"title":"A scheduling algorithm for replicated real-time tasks","authors":"A. Yu, K.-J. Lin","doi":"10.1109/PCCC.1992.200583","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200583","url":null,"abstract":"An algorithm for scheduling real-time periodic tasks on a multiprocessor system under a fault-tolerant requirement is presented. The approach incorporates both the redundancy and masking technique, and the imprecise computation model. Since the tasks in hard real-time systems have stringent timing constraints, the redundancy and masking technique is more appropriate than the rollback techniques, which usually require extra time for error recovery. The imprecise computation model provides flexible functionality by trading off the quality of the result produced by a task with the amount of processing time required to produce it. It therefore permits the performance of a real-time system to degrade gracefully. The algorithm was evaluated by stochastic analysis and Monte Carlo simulations. The results showed that the algorithm was resilient under hardware failure.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121636154","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 : 1992-04-01DOI: 10.1109/PCCC.1992.200528
F.R. Steinberg, C. B. Silio
Data flow design and very-high-speed integrated circuit (VHSIC) hardware description language (VHDL) behavioral simulation are presented for a physical layer encoder/decoder (ENDEC) chip that supports use of a Playthrough protocol on ring topology local area networks. The authors describe the Playthrough protocol's operational concept. The ENDEC design uses as much of the fiber distributed data interface (FDDI) standard as possible to support a 100-Mb/s data transfer rate on fiber-optic media with a chip that is plug compatible with the Advanced Micro Devices (AMD) FDDI ENDEC chip. The design uses an adaptation of the AMD FDDI ENDEC data flow structure; however, because the Playthrough media access control (MAC) protocol differs from FDDI's, a new control flow structure and a different internal structure are required to accommodate Playthrough MAC (PMAC) chip functions.<>
{"title":"Adaptation of FDDI physical layer chip to Playthrough protocol","authors":"F.R. Steinberg, C. B. Silio","doi":"10.1109/PCCC.1992.200528","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200528","url":null,"abstract":"Data flow design and very-high-speed integrated circuit (VHSIC) hardware description language (VHDL) behavioral simulation are presented for a physical layer encoder/decoder (ENDEC) chip that supports use of a Playthrough protocol on ring topology local area networks. The authors describe the Playthrough protocol's operational concept. The ENDEC design uses as much of the fiber distributed data interface (FDDI) standard as possible to support a 100-Mb/s data transfer rate on fiber-optic media with a chip that is plug compatible with the Advanced Micro Devices (AMD) FDDI ENDEC chip. The design uses an adaptation of the AMD FDDI ENDEC data flow structure; however, because the Playthrough media access control (MAC) protocol differs from FDDI's, a new control flow structure and a different internal structure are required to accommodate Playthrough MAC (PMAC) chip functions.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127744356","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 : 1992-04-01DOI: 10.1109/PCCC.1992.200557
R. W. Holbrook, K. Hamidian
A receiver was developed to operate in the near-far interference situation commonly occurring in direct-sequence/spread-spectrum multiple-access communication systems. The receiver was designed to provide robustness to the interference of one unintended user blocking the intended signal at the receiver under consideration. The improvement over a standard correlation receiver was accomplished by using the three-valued property of the crosscorrelation of Gold spreading sequences to identify and subtract the interference from the intended signal. The performance of this receiver is analyzed using Monte Carlo analysis and the results are compared to the standard correlation receiver.<>
{"title":"A crosscorrelation reduction receiver robust to the near-end effect","authors":"R. W. Holbrook, K. Hamidian","doi":"10.1109/PCCC.1992.200557","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200557","url":null,"abstract":"A receiver was developed to operate in the near-far interference situation commonly occurring in direct-sequence/spread-spectrum multiple-access communication systems. The receiver was designed to provide robustness to the interference of one unintended user blocking the intended signal at the receiver under consideration. The improvement over a standard correlation receiver was accomplished by using the three-valued property of the crosscorrelation of Gold spreading sequences to identify and subtract the interference from the intended signal. The performance of this receiver is analyzed using Monte Carlo analysis and the results are compared to the standard correlation receiver.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122263759","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 : 1992-04-01DOI: 10.1109/PCCC.1992.200565
V. Kafedziski
The results of investigations concerning the characterization of the performance of quadrature amplitude modulation (QAM) digital radio in the presence of selective fading and additive noise are presented. The prediction of outage probability due to multipath fading is accomplished by using Rummler's simplified three-path model. The three-path model for characterization of the transmission medium is described. The procedure of outage calculation is outlined. A mathematical model is defined that is used to calculate the error performance of QAM systems in the presence of intersymbol interference and additive noise. The results obtained by using both the method of signatures and Monte Carlo simulation are presented.<>
{"title":"QAM digital radio outage probability in the presence of multipath fading and additive noise","authors":"V. Kafedziski","doi":"10.1109/PCCC.1992.200565","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200565","url":null,"abstract":"The results of investigations concerning the characterization of the performance of quadrature amplitude modulation (QAM) digital radio in the presence of selective fading and additive noise are presented. The prediction of outage probability due to multipath fading is accomplished by using Rummler's simplified three-path model. The three-path model for characterization of the transmission medium is described. The procedure of outage calculation is outlined. A mathematical model is defined that is used to calculate the error performance of QAM systems in the presence of intersymbol interference and additive noise. The results obtained by using both the method of signatures and Monte Carlo simulation are presented.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132211217","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 : 1992-04-01DOI: 10.1109/PCCC.1992.200519
J. Xu, D. Parnas
Nested or overlapping critical sections in processes frequently occur in many hard-real-time system applications. For a pre-run time schedule, the ability to schedule such processes can often significantly increase the chances of finding a feasible schedule. The authors study the properties of exclusion relations defined on nested or overlapping critical sections. An algorithm is presented that is able to systematically search for a feasible schedule that satisfies a given set of release times, deadline constraints, and precedence and exclusion relations, where the exclusion relations are defined on critical sections that may nest within or overlap with each other.<>
{"title":"Pre-run-time scheduling of processes with exclusion relations on nested or overlapping critical sections","authors":"J. Xu, D. Parnas","doi":"10.1109/PCCC.1992.200519","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200519","url":null,"abstract":"Nested or overlapping critical sections in processes frequently occur in many hard-real-time system applications. For a pre-run time schedule, the ability to schedule such processes can often significantly increase the chances of finding a feasible schedule. The authors study the properties of exclusion relations defined on nested or overlapping critical sections. An algorithm is presented that is able to systematically search for a feasible schedule that satisfies a given set of release times, deadline constraints, and precedence and exclusion relations, where the exclusion relations are defined on critical sections that may nest within or overlap with each other.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131758077","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 : 1992-04-01DOI: 10.1109/PCCC.1992.200602
B. Apduhan, T. Sueyoshi, Y. Namiuchi, T. Tezuka, I. Arita
The experiments and analysis of a reconfigurable multiprocessor simulation on a cluster of workstations connected by Ethernet are presented. The system model and simulation environment is described. The monitoring/debugging tool and the concept of SPP, a proposed parallel programming paradigm which can effectively reduce the synchronization operations, are described. The structure of the modules comprised by the system software model are also described. The sequential and parallel versions of a computationally intensive sequential program were executed on different network topologies and its speedup ratios are analyzed and discussed. The crucial issues in realizing reconfigurable multiprocessor simulation on a distributed environment are considered.<>
{"title":"Experiments of a reconfigurable multiprocessor simulation on a distributed environment","authors":"B. Apduhan, T. Sueyoshi, Y. Namiuchi, T. Tezuka, I. Arita","doi":"10.1109/PCCC.1992.200602","DOIUrl":"https://doi.org/10.1109/PCCC.1992.200602","url":null,"abstract":"The experiments and analysis of a reconfigurable multiprocessor simulation on a cluster of workstations connected by Ethernet are presented. The system model and simulation environment is described. The monitoring/debugging tool and the concept of SPP, a proposed parallel programming paradigm which can effectively reduce the synchronization operations, are described. The structure of the modules comprised by the system software model are also described. The sequential and parallel versions of a computationally intensive sequential program were executed on different network topologies and its speedup ratios are analyzed and discussed. The crucial issues in realizing reconfigurable multiprocessor simulation on a distributed environment are considered.<<ETX>>","PeriodicalId":250212,"journal":{"name":"Eleventh Annual International Phoenix Conference on Computers and Communication [1992 Conference Proceedings]","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132779215","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：