Pub Date : 2001-04-16DOI: 10.1109/CDCS.2001.918686
E. P. Duarte, A. Santos
A network management system must be fault-tolerant in order to provide the required fault management functionality. It is often useful to examine MIB objects of a faulty agent in order to determine why it is faulty. This paper presents a new framework for replicating of SNMP management objects in local area networks. The framework is based on groups of agents that communicate with each other using reliable multicast. A group of agents provides fault-tolerant object functionality. A SNMP service is proposed that allows replicated MIB objects of a faulty agent of a given group to be accessed through fault-free agents of that group. The presented framework allows the dynamic definition of agent groups, and management objects to be replicated in each group. A practical fault-tolerant tool for local area network fault management was implemented and is presented. The system employs SNMP agents that interact with a group communication tool. As an example, we show how the examination of TCP-related objects of faulty agents have been used in the fault diagnosis process. The impact of replication on network performance is evaluated as well as a probabilistic analysis of replicated object consistency.
{"title":"Network fault management based on SNMP agent groups","authors":"E. P. Duarte, A. Santos","doi":"10.1109/CDCS.2001.918686","DOIUrl":"https://doi.org/10.1109/CDCS.2001.918686","url":null,"abstract":"A network management system must be fault-tolerant in order to provide the required fault management functionality. It is often useful to examine MIB objects of a faulty agent in order to determine why it is faulty. This paper presents a new framework for replicating of SNMP management objects in local area networks. The framework is based on groups of agents that communicate with each other using reliable multicast. A group of agents provides fault-tolerant object functionality. A SNMP service is proposed that allows replicated MIB objects of a faulty agent of a given group to be accessed through fault-free agents of that group. The presented framework allows the dynamic definition of agent groups, and management objects to be replicated in each group. A practical fault-tolerant tool for local area network fault management was implemented and is presented. The system employs SNMP agents that interact with a group communication tool. As an example, we show how the examination of TCP-related objects of faulty agents have been used in the fault diagnosis process. The impact of replication on network performance is evaluated as well as a probabilistic analysis of replicated object consistency.","PeriodicalId":273489,"journal":{"name":"Proceedings 21st International Conference on Distributed Computing Systems Workshops","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115589476","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 : 2001-04-16DOI: 10.1109/CDCS.2001.918704
H. Okamura
We propose an adaptive resource management system that manages computational resources, such as disk space, memory and CPU power, in home-area networks comprised of various devices, such as personal computers and information appliances. This system enables "poor" devices with limited computational resources to borrow excess computational resources from "rich" devices. Existing distributed systems and software frameworks for home-area networks do not account for important characteristics of home-area network environments, such as user needs based on family members' interests and physical state changes of devices; e.g., disconnection from and reconnection to networks. The proposed system overcomes this problem by employing dynamic adaptation mechanisms. A prototype of this adaptive resource management system, called PPS/J, was designed and implemented on a Java virtual machine. The overhead of the dynamic adaptation mechanisms was measured on the PPS/J, and we found it sufficiently low during application program execution.
{"title":"Adaptive resource management system for home-area networks","authors":"H. Okamura","doi":"10.1109/CDCS.2001.918704","DOIUrl":"https://doi.org/10.1109/CDCS.2001.918704","url":null,"abstract":"We propose an adaptive resource management system that manages computational resources, such as disk space, memory and CPU power, in home-area networks comprised of various devices, such as personal computers and information appliances. This system enables \"poor\" devices with limited computational resources to borrow excess computational resources from \"rich\" devices. Existing distributed systems and software frameworks for home-area networks do not account for important characteristics of home-area network environments, such as user needs based on family members' interests and physical state changes of devices; e.g., disconnection from and reconnection to networks. The proposed system overcomes this problem by employing dynamic adaptation mechanisms. A prototype of this adaptive resource management system, called PPS/J, was designed and implemented on a Java virtual machine. The overhead of the dynamic adaptation mechanisms was measured on the PPS/J, and we found it sufficiently low during application program execution.","PeriodicalId":273489,"journal":{"name":"Proceedings 21st International Conference on Distributed Computing Systems Workshops","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115625651","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 : 2001-04-16DOI: 10.1109/CDCS.2001.918688
V. Hilt, M. Mauve, W. Effelsberg
With the increasing popularity of MBone conferences, the need arose to archive the multimedia streams of these conferences. Like all network applications, a conference recorder is subject to packet loss, which introduces gaps into recorded media streams. Such gaps degrade the playback quality of an archived media stream or even disable the correct playback. We present a novel scheme for the loss-free recording of media streams. In contrast to existing systems that require the placement of recording caches within the network, our approach enables an end-to-end system design. We present a detailed protocol analysis that confirms the validity of our approach.
{"title":"A light-weight repair protocol for the loss-free recording of MBone sessions","authors":"V. Hilt, M. Mauve, W. Effelsberg","doi":"10.1109/CDCS.2001.918688","DOIUrl":"https://doi.org/10.1109/CDCS.2001.918688","url":null,"abstract":"With the increasing popularity of MBone conferences, the need arose to archive the multimedia streams of these conferences. Like all network applications, a conference recorder is subject to packet loss, which introduces gaps into recorded media streams. Such gaps degrade the playback quality of an archived media stream or even disable the correct playback. We present a novel scheme for the loss-free recording of media streams. In contrast to existing systems that require the placement of recording caches within the network, our approach enables an end-to-end system design. We present a detailed protocol analysis that confirms the validity of our approach.","PeriodicalId":273489,"journal":{"name":"Proceedings 21st International Conference on Distributed Computing Systems Workshops","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122487516","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 : 2001-04-16DOI: 10.1109/CDCS.2001.918744
Si Wu, Ding Quanlong, C. Ko
We propose a prediction-based longest queue first (PLQF) scheduling algorithm. The main idea behind PLQF is that of providing the information of incoming traffic to the scheduler. During scheduling, the scheduler considers not only the queue length, but also the incoming traffic. The purpose is to minimize cell loss ratio (CLR) and improve the buffer utilization. A CSD (channel state dependent) version of the PLQF algorithm is also designed for wireless error-prone channels, targeting to utilize channel status to improve overall performance. Theoretical analysis shows that the PLQF algorithm we proposed can lead to a lower CLR than the conventional algorithms, especially for bursty traffic. Simulation results prove this to be true. Therefore, the PLQF algorithm is promising as an efficient scheduling algorithm.
{"title":"Improving the performance of wireless LAN using a new scheduling algorithm","authors":"Si Wu, Ding Quanlong, C. Ko","doi":"10.1109/CDCS.2001.918744","DOIUrl":"https://doi.org/10.1109/CDCS.2001.918744","url":null,"abstract":"We propose a prediction-based longest queue first (PLQF) scheduling algorithm. The main idea behind PLQF is that of providing the information of incoming traffic to the scheduler. During scheduling, the scheduler considers not only the queue length, but also the incoming traffic. The purpose is to minimize cell loss ratio (CLR) and improve the buffer utilization. A CSD (channel state dependent) version of the PLQF algorithm is also designed for wireless error-prone channels, targeting to utilize channel status to improve overall performance. Theoretical analysis shows that the PLQF algorithm we proposed can lead to a lower CLR than the conventional algorithms, especially for bursty traffic. Simulation results prove this to be true. Therefore, the PLQF algorithm is promising as an efficient scheduling algorithm.","PeriodicalId":273489,"journal":{"name":"Proceedings 21st International Conference on Distributed Computing Systems Workshops","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126466376","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 : 2001-04-16DOI: 10.1109/CDCS.2001.918721
Peng Ge, P. McKinley
Multicasting of compressed video streams over wireless networks demands significantly different approaches to error control than those used in wired networks, due to high packet loss rate. This paper describes an experimental study of a proxy service to enhance interactive MPEG-1 video streams when multicast across wireless local area networks. The architecture and operation of the proxy service are presented, followed by results of a performance study conducted on a mobile computing testbed The main contribution of the paper is to show that a combination of forward and backward error control is effective when applied to video streams for mobile collaborating users.
{"title":"Experimental evaluation of error control for video multicast over wireless LANs","authors":"Peng Ge, P. McKinley","doi":"10.1109/CDCS.2001.918721","DOIUrl":"https://doi.org/10.1109/CDCS.2001.918721","url":null,"abstract":"Multicasting of compressed video streams over wireless networks demands significantly different approaches to error control than those used in wired networks, due to high packet loss rate. This paper describes an experimental study of a proxy service to enhance interactive MPEG-1 video streams when multicast across wireless local area networks. The architecture and operation of the proxy service are presented, followed by results of a performance study conducted on a mobile computing testbed The main contribution of the paper is to show that a combination of forward and backward error control is effective when applied to video streams for mobile collaborating users.","PeriodicalId":273489,"journal":{"name":"Proceedings 21st International Conference on Distributed Computing Systems Workshops","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116540507","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 : 2001-04-16DOI: 10.1109/CDCS.2001.918712
U. Saif, D. Greaves
RPC is widely used to access and modify remote state. Its procedural call semantics are argued as an efficient unifying paradigm for both local and remote access. Our experience with ubiquitous device control systems has shown otherwise. RPC semantics of a synchronous, blocking invocation on a statically typed interface are overly restrictive, inflexible, and fail to provide an efficient unifying abstraction for accessing and modifying state in ubiquitous systems. This paper considers other alternatives and proposes the use of comvets (conditional, mobility aware events) as the unifying generic communication paradigm for such systems.
{"title":"Communication primitives for ubiquitous systems or RPC considered harmful","authors":"U. Saif, D. Greaves","doi":"10.1109/CDCS.2001.918712","DOIUrl":"https://doi.org/10.1109/CDCS.2001.918712","url":null,"abstract":"RPC is widely used to access and modify remote state. Its procedural call semantics are argued as an efficient unifying paradigm for both local and remote access. Our experience with ubiquitous device control systems has shown otherwise. RPC semantics of a synchronous, blocking invocation on a statically typed interface are overly restrictive, inflexible, and fail to provide an efficient unifying abstraction for accessing and modifying state in ubiquitous systems. This paper considers other alternatives and proposes the use of comvets (conditional, mobility aware events) as the unifying generic communication paradigm for such systems.","PeriodicalId":273489,"journal":{"name":"Proceedings 21st International Conference on Distributed Computing Systems Workshops","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133680302","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 : 2001-04-16DOI: 10.1109/CDCS.2001.918732
Chia-Chen Lee, Teh-Sheng Huang, Wen-Cheng Sheu, Jain-Feng Tsai, H. Wu
Due to the rapid growth of the Internet, the Internet has had a drastic influence and impact on not only our daily life but also on enterprise information applications. Object oriented technology is widely used in the software industry currently. Web based and distributed object based computing systems comprise the integration of object oriented technology and distributed computing, which is a new computing paradigm. This paradigm gives a new system architecture to be taken into consideration for solving the problems of interoperability and integration of heterogeneous systems. The Common Object Request Broker Architecture (CORBA) provides a standard infrastructure for performing object interoperability transparently. However, a Web based, CORBA based and distributed object architecture will compete very well with the performances of CORBA object binding and interoperability between CORBA objects, and object management issues when the number of CORBA objects are soaring. We propose CORBA based multithreading and factory models to improve the performance of the distributed object architecture. Also, we give a Web based and CORBA based telecommunication service order provisioning system to act as an experimental evaluation.
{"title":"Using threading and factory model to improve the performance of distributed object computing system","authors":"Chia-Chen Lee, Teh-Sheng Huang, Wen-Cheng Sheu, Jain-Feng Tsai, H. Wu","doi":"10.1109/CDCS.2001.918732","DOIUrl":"https://doi.org/10.1109/CDCS.2001.918732","url":null,"abstract":"Due to the rapid growth of the Internet, the Internet has had a drastic influence and impact on not only our daily life but also on enterprise information applications. Object oriented technology is widely used in the software industry currently. Web based and distributed object based computing systems comprise the integration of object oriented technology and distributed computing, which is a new computing paradigm. This paradigm gives a new system architecture to be taken into consideration for solving the problems of interoperability and integration of heterogeneous systems. The Common Object Request Broker Architecture (CORBA) provides a standard infrastructure for performing object interoperability transparently. However, a Web based, CORBA based and distributed object architecture will compete very well with the performances of CORBA object binding and interoperability between CORBA objects, and object management issues when the number of CORBA objects are soaring. We propose CORBA based multithreading and factory models to improve the performance of the distributed object architecture. Also, we give a Web based and CORBA based telecommunication service order provisioning system to act as an experimental evaluation.","PeriodicalId":273489,"journal":{"name":"Proceedings 21st International Conference on Distributed Computing Systems Workshops","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129314936","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 : 2001-04-16DOI: 10.1109/CDCS.2001.918679
C. Delporte-Gallet, H. Fauconnier
We describe a group communication system for real-time systems and show how to use it. This system, we call the synchronized phase system (SPS) ensures a property weaker than the classical virtual synchrony, but SPS, with some liveness properties is powerful enough to build an atomic broadcast service. Moreover, for real-time systems we can give explicit bounds on the size of good periods (periods without timing failure) to ensure the timeliness properties on message delivery. This system has been implemented to build a real time atomic broadcast service in the French project ATR.
{"title":"An example of real-time group communication system","authors":"C. Delporte-Gallet, H. Fauconnier","doi":"10.1109/CDCS.2001.918679","DOIUrl":"https://doi.org/10.1109/CDCS.2001.918679","url":null,"abstract":"We describe a group communication system for real-time systems and show how to use it. This system, we call the synchronized phase system (SPS) ensures a property weaker than the classical virtual synchrony, but SPS, with some liveness properties is powerful enough to build an atomic broadcast service. Moreover, for real-time systems we can give explicit bounds on the size of good periods (periods without timing failure) to ensure the timeliness properties on message delivery. This system has been implemented to build a real time atomic broadcast service in the French project ATR.","PeriodicalId":273489,"journal":{"name":"Proceedings 21st International Conference on Distributed Computing Systems Workshops","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122052610","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 : 2001-04-16DOI: 10.1109/CDCS.2001.918751
A. Amer, D. Long
The ability to automatically hoard data on a computer's local store would go a long way towards freeing the mobile user from dependence on the network and potentially unbounded latencies. An important step in developing a fully automated file hoarding algorithm is the ability to automatically identify strong relationships between files. We present a mechanism for visualizing the degree of long-term relationships inherent in a file access stream. We do this by comparing the performance of static and dynamic relationship predictors. We demonstrate that even the simplest associations (from a static/first-successor predictor) maintain relatively high accuracy over extended periods of time, closely tracking the performance of an equivalent dynamic (last-successor) predictor. We then introduce rank-difference plots, a visualization technique which allows us to demonstrate how this behavior is caused by stable static pairings of files that are lost by the adaptation of the dynamic predictor for a substantial subset of frequently accessed files. We conclude by demonstrating how a third pairing mechanism can make use of these observations to outperform both the dynamic and static predictors.
{"title":"Dynamic relationships and the persistence of pairings","authors":"A. Amer, D. Long","doi":"10.1109/CDCS.2001.918751","DOIUrl":"https://doi.org/10.1109/CDCS.2001.918751","url":null,"abstract":"The ability to automatically hoard data on a computer's local store would go a long way towards freeing the mobile user from dependence on the network and potentially unbounded latencies. An important step in developing a fully automated file hoarding algorithm is the ability to automatically identify strong relationships between files. We present a mechanism for visualizing the degree of long-term relationships inherent in a file access stream. We do this by comparing the performance of static and dynamic relationship predictors. We demonstrate that even the simplest associations (from a static/first-successor predictor) maintain relatively high accuracy over extended periods of time, closely tracking the performance of an equivalent dynamic (last-successor) predictor. We then introduce rank-difference plots, a visualization technique which allows us to demonstrate how this behavior is caused by stable static pairings of files that are lost by the adaptation of the dynamic predictor for a substantial subset of frequently accessed files. We conclude by demonstrating how a third pairing mechanism can make use of these observations to outperform both the dynamic and static predictors.","PeriodicalId":273489,"journal":{"name":"Proceedings 21st International Conference on Distributed Computing Systems Workshops","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123808178","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 : 2001-04-16DOI: 10.1109/CDCS.2001.918691
G. Piccinelli, L. Mokrushin
Until recently, the Internet was dominated by Web sites and store-fronts. We have now entered the next Internet evolution: e-services. E-services are modular, nimble electronic services that perform work, achieve tasks or complete transactions. The first step to turn an existing asset or service into an e-service revolves around accessibility. The virtualisation of the service provides communication channels that support automated conversational capabilities. The format of the service description allows automated discovery and enables automated negotiation on contractual terms and parameters. The second step towards the realisation of the full potential for the e-service vision focuses instead on composition and interaction orchestration. Beyond business conversations for point interactions, e-services can expose complete interaction processes. A service delivery is no longer a one-to-one (buyer-to-seller) relationship, but it now triggers the dynamic creation of business networks. In this paper, we first give a feeling about the e-service vision. We then propose a service model based on the ideas of functional incompleteness, multi-party orchestration and dynamic service composition. A prototype based on the proposed model, called DySCo (Dynamic Service Composition) is presented.
{"title":"Dynamic e-service composition in DySCo","authors":"G. Piccinelli, L. Mokrushin","doi":"10.1109/CDCS.2001.918691","DOIUrl":"https://doi.org/10.1109/CDCS.2001.918691","url":null,"abstract":"Until recently, the Internet was dominated by Web sites and store-fronts. We have now entered the next Internet evolution: e-services. E-services are modular, nimble electronic services that perform work, achieve tasks or complete transactions. The first step to turn an existing asset or service into an e-service revolves around accessibility. The virtualisation of the service provides communication channels that support automated conversational capabilities. The format of the service description allows automated discovery and enables automated negotiation on contractual terms and parameters. The second step towards the realisation of the full potential for the e-service vision focuses instead on composition and interaction orchestration. Beyond business conversations for point interactions, e-services can expose complete interaction processes. A service delivery is no longer a one-to-one (buyer-to-seller) relationship, but it now triggers the dynamic creation of business networks. In this paper, we first give a feeling about the e-service vision. We then propose a service model based on the ideas of functional incompleteness, multi-party orchestration and dynamic service composition. A prototype based on the proposed model, called DySCo (Dynamic Service Composition) is presented.","PeriodicalId":273489,"journal":{"name":"Proceedings 21st International Conference on Distributed Computing Systems Workshops","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122237659","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：