F. Brasileiro, F. Greve, F. Tronel, M. Hurfin, J. Narzul
Presents a framework for the development of higher level communication protocols that provides extra functionalities not supplied by standard off-the-shelf lower level communication protocols. The framework is based on the event channel abstraction which allows circumventing the main drawbacks of the layered-based approach traditionally used to develop such protocols, whilst at the same time providing a flexible, simple and well structured way to implement them. The event channel service provided by EVA establishes how entities that share the same address space interact. Then, the application designer has the opportunity to define the most appropriate lower level communication protocols that control the way entities that execute within different processes will interact. The framework specifies a way to accommodate these protocols and provides several standard protocol implementations. Further a development methodology is described for constructing applications on top of the framework. In designing the framework, we have followed the approach of using, whenever possible, well established concepts, thus the paper also discusses the utilisation of such concepts in improving both the efficiency and the structuring of the framework and of the applications to be built on top of it.
{"title":"EVA: an event-based framework for developing specialised communication protocols","authors":"F. Brasileiro, F. Greve, F. Tronel, M. Hurfin, J. Narzul","doi":"10.1109/NCA.2001.962523","DOIUrl":"https://doi.org/10.1109/NCA.2001.962523","url":null,"abstract":"Presents a framework for the development of higher level communication protocols that provides extra functionalities not supplied by standard off-the-shelf lower level communication protocols. The framework is based on the event channel abstraction which allows circumventing the main drawbacks of the layered-based approach traditionally used to develop such protocols, whilst at the same time providing a flexible, simple and well structured way to implement them. The event channel service provided by EVA establishes how entities that share the same address space interact. Then, the application designer has the opportunity to define the most appropriate lower level communication protocols that control the way entities that execute within different processes will interact. The framework specifies a way to accommodate these protocols and provides several standard protocol implementations. Further a development methodology is described for constructing applications on top of the framework. In designing the framework, we have followed the approach of using, whenever possible, well established concepts, thus the paper also discusses the utilisation of such concepts in improving both the efficiency and the structuring of the framework and of the applications to be built on top of it.","PeriodicalId":385607,"journal":{"name":"Proceedings IEEE International Symposium on Network Computing and Applications. NCA 2001","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115466376","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}
Failover between file server boxes requires data mirroring between them if they don't share access to the disk drives, which is typical for low-end and mid-range network attached storage servers. Most of designs for such data mirroring is done using existing network connections and on top of IP or TCP. The paper presents a design using an additional dedicated Ethernet interface and working directly on top of the data link layer. The proposed scheme will have the advantage of better performance including low overhead during normal operations and fast re-synchronization during recovery.
{"title":"Box-to-box disk mirroring using Ethernet","authors":"Qiang Li","doi":"10.1109/NCA.2001.962552","DOIUrl":"https://doi.org/10.1109/NCA.2001.962552","url":null,"abstract":"Failover between file server boxes requires data mirroring between them if they don't share access to the disk drives, which is typical for low-end and mid-range network attached storage servers. Most of designs for such data mirroring is done using existing network connections and on top of IP or TCP. The paper presents a design using an additional dedicated Ethernet interface and working directly on top of the data link layer. The proposed scheme will have the advantage of better performance including low overhead during normal operations and fast re-synchronization during recovery.","PeriodicalId":385607,"journal":{"name":"Proceedings IEEE International Symposium on Network Computing and Applications. NCA 2001","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122712711","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}
The efficient implementation of collective communication patterns in a parallel machine is a challenging design effort, that requires the solution of many problems. In this paper we present an in-depth description of how the Quadrics network supports both hardware- and software-based collectives. We describe the main features of the two building blocks of this network, a network interface that can perform zero-copy user-level communication and a wormhole routing switch. We also focus our attention on the routing and flow control algorithms, deadlock avoidance and on how the processing nodes are integrated in a global, virtual shared memory. Experimental results conducted on 64-node AlphaServer cluster indicate that the time to complete the hardware-based barrier synchronization on the whole network is as low as 6 /spl mu/s, with very good scalability. Good latency and scalability are also achieved with the software-based synchronization, which takes about 15 /spl mu/s. With the broadcast, similar performance is achieved by the hardware- and software-based implementations, which can deliver messages of up to 256 bytes in 13 /spl mu/s and can get a sustained asymptotic bandwidth of 288 Mbytes/sec on all the nodes. The hardware-based barrier is almost insensitive to the network congestion, with 93% of the synchronizations taking less than 20 /spl mu/s when the network is flooded with a background traffic of unicast messages. On the other hand, the software-based implementation suffers from a significant performance degradation. With high load the hardware broadcast maintains a reasonably good latency, delivering messages up to 2KB in 200 /spl mu/s, while the software broadcast suffers from slightly higher latencies inherited from the synchronization mechanism. Both broadcast algorithms experience a significative performance degradation of the sustained bandwidth with large messages.
{"title":"Hardware- and software-based collective communication on the Quadrics network","authors":"F. Petrini, S. Coll, E. Frachtenberg, A. Hoisie","doi":"10.1109/NCA.2001.962513","DOIUrl":"https://doi.org/10.1109/NCA.2001.962513","url":null,"abstract":"The efficient implementation of collective communication patterns in a parallel machine is a challenging design effort, that requires the solution of many problems. In this paper we present an in-depth description of how the Quadrics network supports both hardware- and software-based collectives. We describe the main features of the two building blocks of this network, a network interface that can perform zero-copy user-level communication and a wormhole routing switch. We also focus our attention on the routing and flow control algorithms, deadlock avoidance and on how the processing nodes are integrated in a global, virtual shared memory. Experimental results conducted on 64-node AlphaServer cluster indicate that the time to complete the hardware-based barrier synchronization on the whole network is as low as 6 /spl mu/s, with very good scalability. Good latency and scalability are also achieved with the software-based synchronization, which takes about 15 /spl mu/s. With the broadcast, similar performance is achieved by the hardware- and software-based implementations, which can deliver messages of up to 256 bytes in 13 /spl mu/s and can get a sustained asymptotic bandwidth of 288 Mbytes/sec on all the nodes. The hardware-based barrier is almost insensitive to the network congestion, with 93% of the synchronizations taking less than 20 /spl mu/s when the network is flooded with a background traffic of unicast messages. On the other hand, the software-based implementation suffers from a significant performance degradation. With high load the hardware broadcast maintains a reasonably good latency, delivering messages up to 2KB in 200 /spl mu/s, while the software broadcast suffers from slightly higher latencies inherited from the synchronization mechanism. Both broadcast algorithms experience a significative performance degradation of the sustained bandwidth with large messages.","PeriodicalId":385607,"journal":{"name":"Proceedings IEEE International Symposium on Network Computing and Applications. NCA 2001","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124565024","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}
The authors present a potential new approach of application integrated congestion management. It is applicable for time-sensitive traffic and is based on the principle of direct protocol interactivity. In contrast to classical transport protocols, we envision a transport mechanism which is interactive and can provide event notification to the subscriber of its communication service. We then show a network aware adaptive MPEG-2 video transcoding mechanics, which directly interacts with the protocol and adjusts its production in sync with the impairment events in the transport layer. The authors present the novel symbiotic mechanics, and share the performance result observed on the MPEG-2 video stream carried by this symbiosis implementation. We report dramatic improvement in time-conformant video delivery by such protocol interactivity.
{"title":"Network aware video transcoding for symbiotic rate adaptation on interactive transport","authors":"J. Khan, Qiong Gu","doi":"10.1109/NCA.2001.962533","DOIUrl":"https://doi.org/10.1109/NCA.2001.962533","url":null,"abstract":"The authors present a potential new approach of application integrated congestion management. It is applicable for time-sensitive traffic and is based on the principle of direct protocol interactivity. In contrast to classical transport protocols, we envision a transport mechanism which is interactive and can provide event notification to the subscriber of its communication service. We then show a network aware adaptive MPEG-2 video transcoding mechanics, which directly interacts with the protocol and adjusts its production in sync with the impairment events in the transport layer. The authors present the novel symbiotic mechanics, and share the performance result observed on the MPEG-2 video stream carried by this symbiosis implementation. We report dramatic improvement in time-conformant video delivery by such protocol interactivity.","PeriodicalId":385607,"journal":{"name":"Proceedings IEEE International Symposium on Network Computing and Applications. NCA 2001","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131818108","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}
Ad hoc networking is often thought of as simply a mechanism by which participants in a network can find each other in some automated fashion. Our experience in building such networks, however, has convinced us that there is far more to ad hoc networks than simple discovery. In this paper, we will discuss the other requirements of the infrastructure that must be provided for real ad hoc networking to take place, illustrating our points with examples drawn from the existing Jini/sup TM/ networking system.
{"title":"Constructing ad hoc networks","authors":"J. Waldo","doi":"10.1109/NCA.2001.962511","DOIUrl":"https://doi.org/10.1109/NCA.2001.962511","url":null,"abstract":"Ad hoc networking is often thought of as simply a mechanism by which participants in a network can find each other in some automated fashion. Our experience in building such networks, however, has convinced us that there is far more to ad hoc networks than simple discovery. In this paper, we will discuss the other requirements of the infrastructure that must be provided for real ad hoc networking to take place, illustrating our points with examples drawn from the existing Jini/sup TM/ networking system.","PeriodicalId":385607,"journal":{"name":"Proceedings IEEE International Symposium on Network Computing and Applications. NCA 2001","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132096610","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}
A number of approaches have been proposed by different vendors for the next generation Internet router architectures, capable of processing millions of packets per second. Most of this processing speed stems from employing latest high-performance network processor or multiprocessors as the forwarding engine of the router However, all these improvements have been proposed without any detailed study in performance evaluation. The impact of instruction level parallelism, branch prediction, multiprocessing, and cache architectures on the performance of routers is not known. In the paper a methodology is proposed, which extends an execution-driven simulator to evaluate router architectures. We incorporate the exact model of an IP router into RSIM to analyze its performance and also develop a framework for feeding real Internet traces to the simulator Our work enables us to vary system parameters to simulate and analyze designs of realistic system with a range of traces. It is shown that the performance of Internet routers can be dramatically enhanced by using multiprocessor architectures. The router design also considers various cache replacement policies and router arbitration policies.
{"title":"Execution-driven simulation of IP router architectures","authors":"L. Bhuyan, Hu-Jun Wang","doi":"10.1109/NCA.2001.962526","DOIUrl":"https://doi.org/10.1109/NCA.2001.962526","url":null,"abstract":"A number of approaches have been proposed by different vendors for the next generation Internet router architectures, capable of processing millions of packets per second. Most of this processing speed stems from employing latest high-performance network processor or multiprocessors as the forwarding engine of the router However, all these improvements have been proposed without any detailed study in performance evaluation. The impact of instruction level parallelism, branch prediction, multiprocessing, and cache architectures on the performance of routers is not known. In the paper a methodology is proposed, which extends an execution-driven simulator to evaluate router architectures. We incorporate the exact model of an IP router into RSIM to analyze its performance and also develop a framework for feeding real Internet traces to the simulator Our work enables us to vary system parameters to simulate and analyze designs of realistic system with a range of traces. It is shown that the performance of Internet routers can be dramatically enhanced by using multiprocessor architectures. The router design also considers various cache replacement policies and router arbitration policies.","PeriodicalId":385607,"journal":{"name":"Proceedings IEEE International Symposium on Network Computing and Applications. NCA 2001","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128621103","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}
We propose a logic-based approach for reasoning about (public-key infrastructure) PKI trust models. Our formalism uses the predicate calculus language to describe a PKI trust model with greater precision than the widely used graph. It allows us to formalize the certificates and the statements about entities beliefs with regard to public key authenticity and certification authority's (CA's) trustworthiness. In this formalism, we take into account the number of CAs that have participated in an entity belief, the trust level in a statement and the policies constraints. By using this approach, we can verify the suitability of a model to applications with particular requirements.
{"title":"A predicate calculus logic for the PKI trust model analysis","authors":"H. Bakkali, Bahia Idrissi Kaitouni","doi":"10.1109/NCA.2001.962557","DOIUrl":"https://doi.org/10.1109/NCA.2001.962557","url":null,"abstract":"We propose a logic-based approach for reasoning about (public-key infrastructure) PKI trust models. Our formalism uses the predicate calculus language to describe a PKI trust model with greater precision than the widely used graph. It allows us to formalize the certificates and the statements about entities beliefs with regard to public key authenticity and certification authority's (CA's) trustworthiness. In this formalism, we take into account the number of CAs that have participated in an entity belief, the trust level in a statement and the policies constraints. By using this approach, we can verify the suitability of a model to applications with particular requirements.","PeriodicalId":385607,"journal":{"name":"Proceedings IEEE International Symposium on Network Computing and Applications. NCA 2001","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131001983","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}
J. Pereira, R. Oliveira, L. Rodrigues, Anne-Marie Kermarrec
Traditional reliable broadcast protocols fail to scale to large settings. The paper proposes a reliable multicast protocol that integrates two approaches to deal with the large-scale dimension in group communication protocols: gossip-based probabilistic broadcast and semantic reliability. The aim of the resulting protocol is to improve the resiliency of the probabilistic protocol to network congestion by allocating scarce resources to semantically relevant messages. Although intuitively it seems that a straightforward combination of probabilistic and semantic reliable protocols is possible, we show that it offers disappointing results. Instead, we propose an architecture based on a specialized probabilistic semantically reliable layer and show that it produces the desired results. The combined primitive is thus scalable to large number of participants, highly resilient to network and process failures, and delivers a high quality data flow even when the load exceeds the available bandwidth. We present a summary of simulation results that compare different protocol configurations.
{"title":"Probabilistic semantically reliable multicast","authors":"J. Pereira, R. Oliveira, L. Rodrigues, Anne-Marie Kermarrec","doi":"10.1109/NCA.2001.962521","DOIUrl":"https://doi.org/10.1109/NCA.2001.962521","url":null,"abstract":"Traditional reliable broadcast protocols fail to scale to large settings. The paper proposes a reliable multicast protocol that integrates two approaches to deal with the large-scale dimension in group communication protocols: gossip-based probabilistic broadcast and semantic reliability. The aim of the resulting protocol is to improve the resiliency of the probabilistic protocol to network congestion by allocating scarce resources to semantically relevant messages. Although intuitively it seems that a straightforward combination of probabilistic and semantic reliable protocols is possible, we show that it offers disappointing results. Instead, we propose an architecture based on a specialized probabilistic semantically reliable layer and show that it produces the desired results. The combined primitive is thus scalable to large number of participants, highly resilient to network and process failures, and delivers a high quality data flow even when the load exceeds the available bandwidth. We present a summary of simulation results that compare different protocol configurations.","PeriodicalId":385607,"journal":{"name":"Proceedings IEEE International Symposium on Network Computing and Applications. NCA 2001","volume":"231 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123063296","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}
Mobile agents represent a modern approach for distributed programming in heterogenous clusters. To deal with massive dynamic behaviour, suitable tools for coding, testing, and observation of agents are needed. In this work, a universal concept and an implementation for a portable agent-oriented monitoring system is explained. The focal point of the monitor environment is the analysis and visualization of dynamic agent behaviour and node utilization for performance optimization as well as for basic debugging purposes.
{"title":"Monitoring of mobile agents in large cluster systems","authors":"Marco Gönne, C. Grewe, H. Pals","doi":"10.1109/NCA.2001.962551","DOIUrl":"https://doi.org/10.1109/NCA.2001.962551","url":null,"abstract":"Mobile agents represent a modern approach for distributed programming in heterogenous clusters. To deal with massive dynamic behaviour, suitable tools for coding, testing, and observation of agents are needed. In this work, a universal concept and an implementation for a portable agent-oriented monitoring system is explained. The focal point of the monitor environment is the analysis and visualization of dynamic agent behaviour and node utilization for performance optimization as well as for basic debugging purposes.","PeriodicalId":385607,"journal":{"name":"Proceedings IEEE International Symposium on Network Computing and Applications. NCA 2001","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114157298","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}
Addresses a key issue that arises when attaching storage devices directly to IP networks: the perceived need for hardware acceleration of the TCP/IP networking stack. While many implicitly assume that acceleration is required, the evidence shows that this conclusion is not well-founded. In the past, network accelerators have had mixed success, and the current economic justification for hardware acceleration is poor, given the low cost of host CPU cycles. The I/O load for many applications is dominated by disk latency, not transfer rate, and hardware protocol accelerators have little effect on the I/O performance in these environments. Application benchmarks were run on an IP storage subsystem to measure performance and CPU utilization on e-mail, database, file serving and backup applications. The results show that good performance can be obtained without protocol acceleration.
{"title":"IP storage and the CPU consumption myth","authors":"R. Horst","doi":"10.1109/NCA.2001.962532","DOIUrl":"https://doi.org/10.1109/NCA.2001.962532","url":null,"abstract":"Addresses a key issue that arises when attaching storage devices directly to IP networks: the perceived need for hardware acceleration of the TCP/IP networking stack. While many implicitly assume that acceleration is required, the evidence shows that this conclusion is not well-founded. In the past, network accelerators have had mixed success, and the current economic justification for hardware acceleration is poor, given the low cost of host CPU cycles. The I/O load for many applications is dominated by disk latency, not transfer rate, and hardware protocol accelerators have little effect on the I/O performance in these environments. Application benchmarks were run on an IP storage subsystem to measure performance and CPU utilization on e-mail, database, file serving and backup applications. The results show that good performance can be obtained without protocol acceleration.","PeriodicalId":385607,"journal":{"name":"Proceedings IEEE International Symposium on Network Computing and Applications. NCA 2001","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121801442","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：