Pub Date : 2008-05-15DOI: 10.1109/HSPR.2008.4734413
W. Olesinski, H. Eberle, N. Gura, N. Chrysos
We have recently proposed a novel architecture called Output Buffered Switch with Input Groups (OBIG) together with a scheduler called Parallel Wrapped Wave Front Arbiter with Fast Scheduler (PWWFA-FS) for building large, fast switches. In this paper we continue this work and tackle the issue of flow control. We show how on/off and credit flow control schemes can be applied in OBIG; we further introduce implicit flow control that does not use any explicit control information. Simulation results show how the proposed flow control schemes perform in our architecture.
{"title":"Flow control in Output Buffered Switch with Input Groups","authors":"W. Olesinski, H. Eberle, N. Gura, N. Chrysos","doi":"10.1109/HSPR.2008.4734413","DOIUrl":"https://doi.org/10.1109/HSPR.2008.4734413","url":null,"abstract":"We have recently proposed a novel architecture called Output Buffered Switch with Input Groups (OBIG) together with a scheduler called Parallel Wrapped Wave Front Arbiter with Fast Scheduler (PWWFA-FS) for building large, fast switches. In this paper we continue this work and tackle the issue of flow control. We show how on/off and credit flow control schemes can be applied in OBIG; we further introduce implicit flow control that does not use any explicit control information. Simulation results show how the proposed flow control schemes perform in our architecture.","PeriodicalId":130484,"journal":{"name":"2008 International Conference on High Performance Switching and Routing","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116226123","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 : 2008-05-15DOI: 10.1109/HSPR.2008.4734433
S. Shimizu, T. Kihara, Y. Arakawa, N. Yamanaka, K. Shiba
A hardware off-loading engine to speed up the shortest path calculation in OSPF (open shortest path first) has been developed. The developed system is co-designed with both hardware and software to optimize an architecture of a router for highly functional traffic engineering (TE). To speed up the shortest path calculation, we employ a dynamically reconfigurable processor, IPFlex DAPDNA-2, as a hardware off-loader, and newly structured a novel high-speed parallel shortest path algorithm, called MPSA (Multi-route Parallel Search Algorithm). The proposed algorithm consists of simple processing, in which multiple paths are simultaneously searched by multiple processor element (PE) of DAPDNA-2. Therefore, it reduces the execution time of shortest path calculation to 2.8% compared with the popular shortest path algorithm, Dijkstrapsilas algorithm. Our prototype works together with a famous software-based router, GNU Zebra, on commodity Linux PC. The proposed architecture and prototype system can be applied to future network sophisticated TE.
{"title":"A prototype of a dynamically reconfigurable processor based off-loading engine for accelerating the shortest path calculation with GNU zebra","authors":"S. Shimizu, T. Kihara, Y. Arakawa, N. Yamanaka, K. Shiba","doi":"10.1109/HSPR.2008.4734433","DOIUrl":"https://doi.org/10.1109/HSPR.2008.4734433","url":null,"abstract":"A hardware off-loading engine to speed up the shortest path calculation in OSPF (open shortest path first) has been developed. The developed system is co-designed with both hardware and software to optimize an architecture of a router for highly functional traffic engineering (TE). To speed up the shortest path calculation, we employ a dynamically reconfigurable processor, IPFlex DAPDNA-2, as a hardware off-loader, and newly structured a novel high-speed parallel shortest path algorithm, called MPSA (Multi-route Parallel Search Algorithm). The proposed algorithm consists of simple processing, in which multiple paths are simultaneously searched by multiple processor element (PE) of DAPDNA-2. Therefore, it reduces the execution time of shortest path calculation to 2.8% compared with the popular shortest path algorithm, Dijkstrapsilas algorithm. Our prototype works together with a famous software-based router, GNU Zebra, on commodity Linux PC. The proposed architecture and prototype system can be applied to future network sophisticated TE.","PeriodicalId":130484,"journal":{"name":"2008 International Conference on High Performance Switching and Routing","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132822977","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 : 2008-05-15DOI: 10.1109/HSPR.2008.4734441
S. Al-Mamory, Hongli Zhang
The intrusion detection system (IDS) is a security technology that attempts to identify network intrusions. Defending against multistep intrusions which prepare for each other is a challenging task. In this paper, alerts classified into predefined classes. Then, the context-free grammar (CFG) was used to describe the multistep attacks using alerts classes. Based on the CFGs, the modified LR parser was recruited to generate the parse trees of the scenarios presented in the alerts. The experiments were performed on two different sets of network traffic traces, using different open-source and commercial IDSs. The detected scenarios are represented by correlation graphs (CGs). The experimental results show that the CFG can describe multistep attacks explicitly and the modified LR parser, based on the CFG, can construct scenarios successfully.
{"title":"Multistep attacks extraction using compiler techniques","authors":"S. Al-Mamory, Hongli Zhang","doi":"10.1109/HSPR.2008.4734441","DOIUrl":"https://doi.org/10.1109/HSPR.2008.4734441","url":null,"abstract":"The intrusion detection system (IDS) is a security technology that attempts to identify network intrusions. Defending against multistep intrusions which prepare for each other is a challenging task. In this paper, alerts classified into predefined classes. Then, the context-free grammar (CFG) was used to describe the multistep attacks using alerts classes. Based on the CFGs, the modified LR parser was recruited to generate the parse trees of the scenarios presented in the alerts. The experiments were performed on two different sets of network traffic traces, using different open-source and commercial IDSs. The detected scenarios are represented by correlation graphs (CGs). The experimental results show that the CFG can describe multistep attacks explicitly and the modified LR parser, based on the CFG, can construct scenarios successfully.","PeriodicalId":130484,"journal":{"name":"2008 International Conference on High Performance Switching and Routing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133661434","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 : 2008-05-15DOI: 10.1109/HSPR.2008.4734432
Qiang Wu, T. Wolf
Computer networks require increasingly complex packet processing services on routers to adapt to new functionality, security, and performance requirements. Embedded multicore packet processing systems that can provide this capability are difficult to program and manage at runtime. We propose a novel way of representing processing tasks, obtaining runtime profiling information, and mapping tasks to processors. By duplicating processing tasks with heavy processing requirements, a more balanced workload can be obtained. The mapping algorithm considers that balance when assigning tasks to processors as well as the cost of inter-processor communication. Our evaluation results show that our approach can improve the system throughput by 2.39-2.89 times at a cost of 1.49-1.64 times higher inter-processor communication.
{"title":"Dynamic workload profiling and task allocation in packet processing systems","authors":"Qiang Wu, T. Wolf","doi":"10.1109/HSPR.2008.4734432","DOIUrl":"https://doi.org/10.1109/HSPR.2008.4734432","url":null,"abstract":"Computer networks require increasingly complex packet processing services on routers to adapt to new functionality, security, and performance requirements. Embedded multicore packet processing systems that can provide this capability are difficult to program and manage at runtime. We propose a novel way of representing processing tasks, obtaining runtime profiling information, and mapping tasks to processors. By duplicating processing tasks with heavy processing requirements, a more balanced workload can be obtained. The mapping algorithm considers that balance when assigning tasks to processors as well as the cost of inter-processor communication. Our evaluation results show that our approach can improve the system throughput by 2.39-2.89 times at a cost of 1.49-1.64 times higher inter-processor communication.","PeriodicalId":130484,"journal":{"name":"2008 International Conference on High Performance Switching and Routing","volume":"345 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114049599","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}
Wireless mesh networks (WMNs) is an emerging communication paradigm to enable resilient, cost-efficient and reliable services for the future-generation wireless networks. In this paper, we study the broadcasting (one-to-all communication) in WMNs with known topology, i.e., where for each primitive the schedule of transmissions is precomputed based on full knowledge about the size and the topology of the network. We show that broadcasting can complete in D + O(log n) time units in the WMN with size n and diameter D. Furthermore, we explore the fault-tolerant broadcasting in WMN.We show an O(n)-time deterministic radio broadcasting schedule with large number of link failures. This is an optimal schedule in the sense that there exists a network topology in which the broadcasting cannot complete in less than Omega(n) units of time.
{"title":"Optimal fault-tolerant broadcasting in Wireless Mesh Networks","authors":"Qin Xin, Yan Zhang, L. Yang","doi":"10.1002/wcm.718","DOIUrl":"https://doi.org/10.1002/wcm.718","url":null,"abstract":"Wireless mesh networks (WMNs) is an emerging communication paradigm to enable resilient, cost-efficient and reliable services for the future-generation wireless networks. In this paper, we study the broadcasting (one-to-all communication) in WMNs with known topology, i.e., where for each primitive the schedule of transmissions is precomputed based on full knowledge about the size and the topology of the network. We show that broadcasting can complete in D + O(log n) time units in the WMN with size n and diameter D. Furthermore, we explore the fault-tolerant broadcasting in WMN.We show an O(n)-time deterministic radio broadcasting schedule with large number of link failures. This is an optimal schedule in the sense that there exists a network topology in which the broadcasting cannot complete in less than Omega(n) units of time.","PeriodicalId":130484,"journal":{"name":"2008 International Conference on High Performance Switching and Routing","volume":"40 1-8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116510129","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 : 2008-05-15DOI: 10.1109/HSPR.2008.4734448
Stefano Secci, J. Rougier, A. Pattavina
A novel composite-star architecture, nicknamed the Petaweb, has been recently proposed for high capacity optical core networks. Its topologic structure is such that electronic edge nodes are always connected to each other through a single core switch, and that the core switches are disconnected. The aim is to simplify the traffic engineering and the upgradeability of core networks. In its regular form, this architecture suffers from high fiber cost and low utilization. A recent work tackles the problem of directly designing a quasi-regular composite-star structure, showing that the network cost can get more than halved and that the resources utilization can be significantly improved. In this paper, we compare the quasi-regular composite-star structure to classical irregular multi-hop structures. We show that increasing the weight of a propagation delay virtual cost in the design dimensioning objective function, multi-hop core networks tend to assume a quasi-regular composite-star like topologic structure, with a few core fibers. This suggests that such an architecture is the natural solution whether length-dependent additive costs are considered as part of the design dimensioning objective.
{"title":"Comparison of quasi-regular composite-star and multi-hop structures for core networks","authors":"Stefano Secci, J. Rougier, A. Pattavina","doi":"10.1109/HSPR.2008.4734448","DOIUrl":"https://doi.org/10.1109/HSPR.2008.4734448","url":null,"abstract":"A novel composite-star architecture, nicknamed the Petaweb, has been recently proposed for high capacity optical core networks. Its topologic structure is such that electronic edge nodes are always connected to each other through a single core switch, and that the core switches are disconnected. The aim is to simplify the traffic engineering and the upgradeability of core networks. In its regular form, this architecture suffers from high fiber cost and low utilization. A recent work tackles the problem of directly designing a quasi-regular composite-star structure, showing that the network cost can get more than halved and that the resources utilization can be significantly improved. In this paper, we compare the quasi-regular composite-star structure to classical irregular multi-hop structures. We show that increasing the weight of a propagation delay virtual cost in the design dimensioning objective function, multi-hop core networks tend to assume a quasi-regular composite-star like topologic structure, with a few core fibers. This suggests that such an architecture is the natural solution whether length-dependent additive costs are considered as part of the design dimensioning objective.","PeriodicalId":130484,"journal":{"name":"2008 International Conference on High Performance Switching and Routing","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132284561","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 : 2008-05-15DOI: 10.1109/HSPR.2008.4734438
Yunxia Feng, Minglu Li, Minyou Wu
Dynamic channel assignment is attracting more and more attentions since it can greatly alleviate the problem of interference in wireless networks. Efficient broadcasting, however, is one of the main problems facing dynamic channel assignment. It is easy to send broadcast packets in a network that is always connected due to the broadcast property of wireless channel. The broadcast property, however, may be unavailable when the radios on nodes can dynamically switch to different channels. In this paper, we present a scheme to support efficient broadcasting in interface switching wireless networks, where the nodes demand channel reassignment whenever they start new communications. In these scenarios, traditional broadcasting protocols do not work owing to the absence of permanent connections. One advantage of our proposed scheme is that it does not need additional radio or special channel to transmit broadcast packets. Second, it reduces the broadcast redundancy by establishing a broadcast tree that minimizes the number of relay nodes. NS2 results show that the proposed broadcast ensures that the network achieves better performance and adapts quickly to flows change.
{"title":"Efficient broadcasting in interface switching wireless networks","authors":"Yunxia Feng, Minglu Li, Minyou Wu","doi":"10.1109/HSPR.2008.4734438","DOIUrl":"https://doi.org/10.1109/HSPR.2008.4734438","url":null,"abstract":"Dynamic channel assignment is attracting more and more attentions since it can greatly alleviate the problem of interference in wireless networks. Efficient broadcasting, however, is one of the main problems facing dynamic channel assignment. It is easy to send broadcast packets in a network that is always connected due to the broadcast property of wireless channel. The broadcast property, however, may be unavailable when the radios on nodes can dynamically switch to different channels. In this paper, we present a scheme to support efficient broadcasting in interface switching wireless networks, where the nodes demand channel reassignment whenever they start new communications. In these scenarios, traditional broadcasting protocols do not work owing to the absence of permanent connections. One advantage of our proposed scheme is that it does not need additional radio or special channel to transmit broadcast packets. Second, it reduces the broadcast redundancy by establishing a broadcast tree that minimizes the number of relay nodes. NS2 results show that the proposed broadcast ensures that the network achieves better performance and adapts quickly to flows change.","PeriodicalId":130484,"journal":{"name":"2008 International Conference on High Performance Switching and Routing","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114708436","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 : 2008-05-15DOI: 10.1109/HSPR.2008.4734420
Xin Wang, Min Lin, Zheng Huang, X. Xue
Although coding over P2P is effective in some ways, coding at routers can bring us more significant benefits. Unfortunately, routers in todaypsilas network are mostly not capable of network coding. We propose a novel scheme to equip routers with coding functionalities. To do this, we design a routing protocol based on network coding and regulate the coding functionalities at routers. Simulation results show that for content distributions in single-source and multiple-sink networks, our scheme exhibits better performance in terms of download time and balanced load.
{"title":"Routers with coding and performance simulation","authors":"Xin Wang, Min Lin, Zheng Huang, X. Xue","doi":"10.1109/HSPR.2008.4734420","DOIUrl":"https://doi.org/10.1109/HSPR.2008.4734420","url":null,"abstract":"Although coding over P2P is effective in some ways, coding at routers can bring us more significant benefits. Unfortunately, routers in todaypsilas network are mostly not capable of network coding. We propose a novel scheme to equip routers with coding functionalities. To do this, we design a routing protocol based on network coding and regulate the coding functionalities at routers. Simulation results show that for content distributions in single-source and multiple-sink networks, our scheme exhibits better performance in terms of download time and balanced load.","PeriodicalId":130484,"journal":{"name":"2008 International Conference on High Performance Switching and Routing","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121847829","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 : 2008-05-15DOI: 10.1109/HSPR.2008.4734412
Hui Yu, J. Chen, Jianping Wang, S. Zheng, M. Nourani
IP lookup is a key task in packet processing to guarantee the high performance of the IP routers. It has been proposed to use TCAMs to implement IP-lookup accelerators for IP forwarding. In the paper, a new TCAM-based IP-lookup scheme MSMB-LPT is proposed and studied. It is shown that MSMB-LPT scheme significantly improve the performance of the state-of-art MSMB-PT scheme in terms of speedup and power consumption by simulations. These performance improvements are achieved with reduced cost.
{"title":"An improved TCAM-based IP lookup engine","authors":"Hui Yu, J. Chen, Jianping Wang, S. Zheng, M. Nourani","doi":"10.1109/HSPR.2008.4734412","DOIUrl":"https://doi.org/10.1109/HSPR.2008.4734412","url":null,"abstract":"IP lookup is a key task in packet processing to guarantee the high performance of the IP routers. It has been proposed to use TCAMs to implement IP-lookup accelerators for IP forwarding. In the paper, a new TCAM-based IP-lookup scheme MSMB-LPT is proposed and studied. It is shown that MSMB-LPT scheme significantly improve the performance of the state-of-art MSMB-PT scheme in terms of speedup and power consumption by simulations. These performance improvements are achieved with reduced cost.","PeriodicalId":130484,"journal":{"name":"2008 International Conference on High Performance Switching and Routing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125169435","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 subdivision of a sensor network into uniform clusters of physically close nodes is an important building block in the design of efficient upper layer network functions such as routing, broadcast, data aggregation, and query processing. This paper analyzes a low energy adaptive clustering hierarchy (LEACH) in terms of the optimum number of clusters and demonstrates through simulation that the optimum number calculated are not suitable for sensor networks including large number of nodes or covering large area. Based on the analysis results, we give a new formula of calculating the optimum number of clusters on an improved data gathering model. To decrease the energy dissipation further, we develop a new efficient uniform clustering algorithm in ad-hoc sensor networks. Simulation results show that it achieves fairly uniform cluster-head distribution across the network.
{"title":"Energy-efficient uniform clustering algorithm for wireless sensor networks","authors":"Zhongwen Guo, Jinfeng Dou, Peng Wang, Guangxue Zhang","doi":"10.1109/HSPR.2008.4734453","DOIUrl":"https://doi.org/10.1109/HSPR.2008.4734453","url":null,"abstract":"The efficient subdivision of a sensor network into uniform clusters of physically close nodes is an important building block in the design of efficient upper layer network functions such as routing, broadcast, data aggregation, and query processing. This paper analyzes a low energy adaptive clustering hierarchy (LEACH) in terms of the optimum number of clusters and demonstrates through simulation that the optimum number calculated are not suitable for sensor networks including large number of nodes or covering large area. Based on the analysis results, we give a new formula of calculating the optimum number of clusters on an improved data gathering model. To decrease the energy dissipation further, we develop a new efficient uniform clustering algorithm in ad-hoc sensor networks. Simulation results show that it achieves fairly uniform cluster-head distribution across the network.","PeriodicalId":130484,"journal":{"name":"2008 International Conference on High Performance Switching and Routing","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132544037","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：