{"title":"Optimization of relay placement for scalable virtual private LAN services","authors":"Mohammad Borhani, Ioannis Avgouleas, A. Gurtov","doi":"10.1145/3527974.3545719","DOIUrl":"https://doi.org/10.1145/3527974.3545719","url":null,"abstract":"Virtual Private LAN Services are becoming popular for securely connecting geographically dispersed devices to a common protected LAN network isolated from the rest of the Internet. Traditional IP routing protocols cannot provide such connectivity; thus an overlay network of encrypted HIP/IPsec tunnels can be used instead. However, the number of full-mesh tunnels between communicating devices grows exponentially to the number of devices thereby suggesting the investigation of alternatives. The introduction of relaying, which entails selecting a subset of hub routers to retain full-mesh connectivity, allows non-hub routers, the so-called spokes, to maintain connectivity via a hub. In this work, we study the effect of relay-based routing that minimizes the number of hubs, the connection cost between spokes and hubs, the cost of connecting hubs, and the hubs deployment cost. Additionally, we prove that this minimization problem is NP-hard and, thus, intractable for large scale networks. Therefore, we propose an algorithm with provable guarantees that provides an approximate but efficient solution. Initial simulation results indicate a reduction by more than 90% in the memory required for routing tables at the expense of a minor increase in the tunnel path length.","PeriodicalId":294749,"journal":{"name":"Proceedings of the ACM SIGCOMM Workshop on Future of Internet Routing & Addressing","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126831274","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}
{"title":"Attaining stable and loop-free inter-domain routing without path vectors","authors":"J. Garcia-Luna-Aceves","doi":"10.1145/3527974.3545718","DOIUrl":"https://doi.org/10.1145/3527974.3545718","url":null,"abstract":"A sufficient condition for loop-free routing is introduced based on path labels. A path label consists of the identifier of the first node and hop-count length of a path to a destination. This condition is applied to the policy mechanisms used in BGP, which results in BGP-ELF (BGP Enhanced for Loop Freedom). BGP-ELF uses updates, queries, and replies based on path labels to attain multi-path loop-free and stable routing across autonomous systems without the need for path vectors.","PeriodicalId":294749,"journal":{"name":"Proceedings of the ACM SIGCOMM Workshop on Future of Internet Routing & Addressing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117331896","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}
{"title":"Enabling granularity-customizable geocast in network layer using P4-based software defined network","authors":"Xindi Hou, Shuai Gao, Ningchun Liu, Gaofeng Hong","doi":"10.1145/3527974.3545720","DOIUrl":"https://doi.org/10.1145/3527974.3545720","url":null,"abstract":"Geocast is a one-to-many communication paradigm for sending the data packets to a designated area rather than an IP address. However, the traditional IP-based solutions cannot cope with the challenges in flexibility, mobility, and implementation overhead in situations where users are requiring a granularity-customizable geocast. Therefore, we propose to implement the granularity-customizable geocast at the edge of the network by embedding a novel network-layer addressing scheme using P4-based Software Defined Network (SDN). In this paper, a geographic subdivision and coding method named EMD is used to subdivide the global region. Then, we introduce the GeoIP as the network address and propose a GeoIP packet processing scheme by utilizing P4. The proposed GeoIP-based addressing scheme is deployed at the edge of the network. To make our design compatible with the current Internet, a Geolocation Name Service (GNS) system is designed to support the Internet-wide geocast. In addition, a prototype system is built to implement and evaluate our design. Experiment results show that the proposed design is feasible to provide granularity-customizable geocast at a relatively low cost.","PeriodicalId":294749,"journal":{"name":"Proceedings of the ACM SIGCOMM Workshop on Future of Internet Routing & Addressing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123661354","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}
D. Trossen, A. Farrel, Daniel King, M. Boucadair, L. M. C. Murillo
{"title":"Providing more than 'just' reachability through semantic networking","authors":"D. Trossen, A. Farrel, Daniel King, M. Boucadair, L. M. C. Murillo","doi":"10.1145/3527974.3546974","DOIUrl":"https://doi.org/10.1145/3527974.3546974","url":null,"abstract":"The Internet has been constantly evolving beyond its original purpose to ensure the reachability between endpoints wherever they may be located. The many technologies developed in Standard Developing Organizations (SDOs) and through proprietary solutions bear witness to this continuous evolution, often driven through specifying and implementing new communication protocols or design practises. Parts of those solutions may overload, amend, or extend packet header semantics at the risk of endangering inter-operability of the solutions that make up the Internet system. This discussion paper advocates the Semantic Networking vision, explicitly exposing communication semantics as the essential abstraction for its runtime realization. We present an architecture for Semantic Networking and discuss key design considerations that may inform future research and development work, eventually leading to a new Internet architecture.","PeriodicalId":294749,"journal":{"name":"Proceedings of the ACM SIGCOMM Workshop on Future of Internet Routing & Addressing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132674931","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}
S. Salsano, Giulio Sidoretti, Carmine Scarpitta, Hesham El Backoury, D. López, L. Bracciale, P. Loreti
{"title":"Supporting future internet services with extensible in-band processing (EIP)","authors":"S. Salsano, Giulio Sidoretti, Carmine Scarpitta, Hesham El Backoury, D. López, L. Bracciale, P. Loreti","doi":"10.1145/3527974.3545727","DOIUrl":"https://doi.org/10.1145/3527974.3545727","url":null,"abstract":"Networking architectures need to evolve to support the requirements of future Internet services and 6G networks. In this paper we propose an evolutionary solution that extends the IPv6 networking architecture fully supporting the needs of future services, called Extensible In-band Processing (EIP). The EIP solution considers a feature-rich networking layer, in which hosts and routers can cooperate by reading and writing the EIP information in the IPv6 packet headers, to support a number of use cases. Example use case are: advanced monitoring, semantic routing, deterministic networking, slicing and so on. This list of use cases is not exhaustive, as a key feature of EIP is to be extensible for the support of new use cases. In the paper we describe the initial design of the EIP header and protocol mechanisms. We have released an open source prototype implementation of EIP for Linux OS, based on the eBPF packet processing framework. The implementation includes tools for the generation of test EIP packets and for the protocol dissection of packets. A replicable testbed provides an early demonstration of the advanced monitoring and semantic routing use cases.","PeriodicalId":294749,"journal":{"name":"Proceedings of the ACM SIGCOMM Workshop on Future of Internet Routing & Addressing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125411356","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}
{"title":"Topological addressing enabling energy efficient IoT communication","authors":"Guangpeng Li, D. Lou, L. Iannone","doi":"10.1145/3527974.3545722","DOIUrl":"https://doi.org/10.1145/3527974.3545722","url":null,"abstract":"This paper specifies a topological addressing scheme, called Native Short Address (NSA) that enables a more energy efficient IP packet transmission over links in the IoT domain, where it is effective and desirable not to carry full length addresses in the packet (especially large IPv6 addresses). NSA relies on an address assignment function that algorithmically calculates and assigns the address of IoT nodes, based on their roles and location in hierarchy. The small size of the assigned addresses helps lowering the power consumption. Moreover, the main feature of NSA is stateless forwarding, which reduces the computation complexity by eliminating routing calculation, thus making the overall system even more energy efficient. This paper focuses on a low power and lossy network, where the topology of the network is relatively static. The nodes' location is fixed and the connection between nodes is rather stable. The paper illustrates the NSA architecture, address allocation function, forwarding mechanism, header format design, including length-variable fields, and IPv6 interconnection support.","PeriodicalId":294749,"journal":{"name":"Proceedings of the ACM SIGCOMM Workshop on Future of Internet Routing & Addressing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117169101","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}
{"title":"A first step towards checking BGP routes in the dataplane","authors":"Thomas Wirtgen, O. Bonaventure","doi":"10.1145/3527974.3545723","DOIUrl":"https://doi.org/10.1145/3527974.3545723","url":null,"abstract":"BGP is a fragile routing protocol since it is based on an implicit system of trust between the Autonomous Systems (AS) participating in the exchange of routes on the Internet. Any router can announce the routes it wants without being the owner. Due to the lack of a validation system for the announcements made by BGP routers, a series of RFCs published after the release of BGP have partially solved this problem by introducing the Resource Public Key Infrastructure (RPKI). In this paper, we aim to complement the security mechanisms of BGP by introducing a new active control system. We propose to validate BGP paths in the dataplane. We extend the BGP implementation of FRRouting (an open source Internet routing protocol suite) to demonstrate the feasibility of our approach. Finally, we discuss the potential of an active system in a routing protocol to both secure BGP announcements and improve the routing decision.","PeriodicalId":294749,"journal":{"name":"Proceedings of the ACM SIGCOMM Workshop on Future of Internet Routing & Addressing","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127333538","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}
K. Khandaker, D. Trossen, Jinze Yang, Z. Despotovic, G. Carle
{"title":"On-path vs off-path traffic steering, that is the question","authors":"K. Khandaker, D. Trossen, Jinze Yang, Z. Despotovic, G. Carle","doi":"10.1145/3527974.3545721","DOIUrl":"https://doi.org/10.1145/3527974.3545721","url":null,"abstract":"Service-level traffic steering in the Internet has been using an indirection-based model for decades now, using the DNS to resolve a name to a locator, often complemented with load balancing techniques. Contrasting this off-path realization, service information as part of the data packet itself may determine the one of possibly many communication endpoints on-path while traversing the network. This paper compares both design choices regardless of the specific decision mechanism used. For this, we assume a compute-aware traffic steering mechanism for both approaches and determine latency penalties through off-path resolution steps as well as distributing scheduling decisions to on-path network ingress points. Lastly, we investigate latency variances and resilience in an AR/VR scenario.","PeriodicalId":294749,"journal":{"name":"Proceedings of the ACM SIGCOMM Workshop on Future of Internet Routing & Addressing","volume":"662 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115122022","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}
{"title":"Fast and efficient lookups via data-driven FIB designs","authors":"S. Ashok, Aditi Partap, Ammar Tahir","doi":"10.1145/3527974.3545728","DOIUrl":"https://doi.org/10.1145/3527974.3545728","url":null,"abstract":"With the rapidly growing number of hosts connected to the internet, there is an ever-increasing demand for fast and inexpensive switch memory. At the same time, the number of network functions handled at the switch, especially in the case of a programmable switch, is increasing steadily (e.g., for the purposes of routing, telemetry, load balancing), which require dedicated memory. Various compact and efficient data structures (e.g., Bloom filters [15], ludo hashes [10], cuckoo filters [3]) have been proposed in the past to address these needs. However, these data structures can provide varying performance depending on the distribution of the actual key-value pairs they store. In addition, several of these data structures are probabilistic in nature and hence also trade-off on accuracy to achieve a lower memory usage. In our work, we propose using data-driven approaches to analyze these key-value pairs (i.e., FIB lookup data) for patterns which can aid in building more informed FIB designs. Primarily, we argue that using an ensemble model comprising of hash tables and Bloom filters (the composition as dictated by the data) can better meet the specific requirements (processing speed, available memory, accuracy level) of the given switch. In this paper, we present a spectrum of designs that are possible within this space and implement one specific prototype. Finally, we present preliminary evaluation of this prototype using enterprise network data to support our proposal.","PeriodicalId":294749,"journal":{"name":"Proceedings of the ACM SIGCOMM Workshop on Future of Internet Routing & Addressing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124048107","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}
{"title":"Meshed tree routing in folded-clos topologies","authors":"P. Willis, N. Shenoy","doi":"10.1145/3527974.3545717","DOIUrl":"https://doi.org/10.1145/3527974.3545717","url":null,"abstract":"Data Center Networks (DCNs) are the backbone of data centers. Folded-Clos topologies are used in data centers networks due to the high redundancy and scalability they offer. Capacity challenges and advanced applications are placing increased demands on DCNs. While there have been a number of major studies focused on improving hardware and topology design for DCNs, fewer efforts have been directed towards investigating new algorithms and protocols to work efficiently on the highly connected and symmetrical topologies adopted in DCNs. Instead, we notice the integration of off-the-shelf protocols that are then retrofitted to the DCN communication needs. This increases the operational complexity in DCNs. In this article, we investigate a new Meshed Tree protocol (MTP) based off a novel Meshed Tree algorithm (MTA) to perform control and data plane operations in folded-Clos DCNs. We present implementation details of MTP, tested using the Global Environment for Network Innovation (GENI) testbed, and highlight features such as redundant route establishment and load balancing.","PeriodicalId":294749,"journal":{"name":"Proceedings of the ACM SIGCOMM Workshop on Future of Internet Routing & Addressing","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133106260","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}