{"title":"ConMidbox:在支持SDN/ nfv的网络中整合的中间盒选择和路由","authors":"Guiyan Liu, Songtao Guo, Pan Li, Liang Liu","doi":"10.1109/IPDPS47924.2020.00101","DOIUrl":null,"url":null,"abstract":"Software defined networking (SDN) and network function virtualization (NFV) can flexibly manage software middlebox based services, and the consolidated middlebox model is able to simplify traffic routing and reduce the number of routing rules in the SDN-enabled switches. However, different network functions in middleboxes may change the volume of processed traffics, thus high congestion may occur in specific bottleneck links if middlebox selection and traffic routing are not well jointly planned. Besides, in a statically switch-controller configured SDN, traffic dynamics will not only affect the link load in data plane, but also pose a challenge to controller load balancing. Therefore, it’s necessary to achieve better quality-of-service (QoS) performance in both control and data plane. This paper first formulates it as a joint traffic-aware consolidated middleboxes selection and routing (JTMSR) problem and proves its NP-hardness. Then, a two-phase RL_RFRD algorithm is designed to achieve the controller and link load balancing where the first phase is to redirect selected flows by applying wildcard rules and the second phase is to find fine-grained routing path by a rounding-based algorithm with bounded approximation factor. Finally, the extensive simulation results demonstrate that the proposed algorithm has near-optimal controller load balancing and link load balancing performance and reduces response time by about 2x-5x compared with other algorithms.","PeriodicalId":6805,"journal":{"name":"2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","volume":"9 1","pages":"946-955"},"PeriodicalIF":0.0000,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"ConMidbox: Consolidated Middleboxes Selection and Routing in SDN/NFV-Enabled Networks\",\"authors\":\"Guiyan Liu, Songtao Guo, Pan Li, Liang Liu\",\"doi\":\"10.1109/IPDPS47924.2020.00101\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Software defined networking (SDN) and network function virtualization (NFV) can flexibly manage software middlebox based services, and the consolidated middlebox model is able to simplify traffic routing and reduce the number of routing rules in the SDN-enabled switches. However, different network functions in middleboxes may change the volume of processed traffics, thus high congestion may occur in specific bottleneck links if middlebox selection and traffic routing are not well jointly planned. Besides, in a statically switch-controller configured SDN, traffic dynamics will not only affect the link load in data plane, but also pose a challenge to controller load balancing. Therefore, it’s necessary to achieve better quality-of-service (QoS) performance in both control and data plane. This paper first formulates it as a joint traffic-aware consolidated middleboxes selection and routing (JTMSR) problem and proves its NP-hardness. Then, a two-phase RL_RFRD algorithm is designed to achieve the controller and link load balancing where the first phase is to redirect selected flows by applying wildcard rules and the second phase is to find fine-grained routing path by a rounding-based algorithm with bounded approximation factor. Finally, the extensive simulation results demonstrate that the proposed algorithm has near-optimal controller load balancing and link load balancing performance and reduces response time by about 2x-5x compared with other algorithms.\",\"PeriodicalId\":6805,\"journal\":{\"name\":\"2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS)\",\"volume\":\"9 1\",\"pages\":\"946-955\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IPDPS47924.2020.00101\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IPDPS47924.2020.00101","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
摘要
SDN (Software defined networking)和NFV (network function virtualization)可以灵活地管理基于软件中间件的业务,合并的中间件模型可以简化流量路由,减少SDN交换机的路由规则数量。但是,由于中间盒的网络功能不同,处理的流量可能会发生变化,如果中间盒选择和流量路由规划不好,可能会在特定的瓶颈链路上出现高拥塞。此外,在交换机-控制器静态配置的SDN网络中,流量动态不仅会影响数据平面的链路负载,还会对控制器负载均衡提出挑战。因此,有必要在控制平面和数据平面实现更好的服务质量(QoS)性能。本文首先将其描述为一个联合流量感知的合并中箱选择和路由问题,并证明了其np -硬度。然后,设计两阶段RL_RFRD算法实现控制器和链路的负载均衡,第一阶段是应用通配符规则对所选流进行重定向,第二阶段是使用有界近似因子的基于舍入的算法寻找细粒度路由路径。最后,大量的仿真结果表明,该算法具有接近最优的控制器负载均衡和链路负载均衡性能,与其他算法相比,响应时间缩短了约2 -5倍。
ConMidbox: Consolidated Middleboxes Selection and Routing in SDN/NFV-Enabled Networks
Software defined networking (SDN) and network function virtualization (NFV) can flexibly manage software middlebox based services, and the consolidated middlebox model is able to simplify traffic routing and reduce the number of routing rules in the SDN-enabled switches. However, different network functions in middleboxes may change the volume of processed traffics, thus high congestion may occur in specific bottleneck links if middlebox selection and traffic routing are not well jointly planned. Besides, in a statically switch-controller configured SDN, traffic dynamics will not only affect the link load in data plane, but also pose a challenge to controller load balancing. Therefore, it’s necessary to achieve better quality-of-service (QoS) performance in both control and data plane. This paper first formulates it as a joint traffic-aware consolidated middleboxes selection and routing (JTMSR) problem and proves its NP-hardness. Then, a two-phase RL_RFRD algorithm is designed to achieve the controller and link load balancing where the first phase is to redirect selected flows by applying wildcard rules and the second phase is to find fine-grained routing path by a rounding-based algorithm with bounded approximation factor. Finally, the extensive simulation results demonstrate that the proposed algorithm has near-optimal controller load balancing and link load balancing performance and reduces response time by about 2x-5x compared with other algorithms.