{"title":"Elastic Gigabit NDN Forwarder for Big Data Applications","authors":"Junior Dongo, C. Mahmoudi, F. Mourlin","doi":"10.1109/GIIS48668.2019.9044959","DOIUrl":null,"url":null,"abstract":"Information Centric Networking is more and more used today. Named Data Networking (NDN) is one implementation of such paradigm focusing the communication on the information instead of the hosts. The performance of the NDN forwarder - called Name Forwarder Daemon (NFD) - is one major challenge faced by the NDN community especially due to the complex structures of both the naming prefixes and the forwarding tables. High-performance NFD is a major requirement to enable Big Data processing over NDN due to the scale of the exchanges used in real life applications. This paper proposes an approach to overcome the actual limitation of the packets processing capability of the NFD. The proposed approach uses state-of-the-art virtualization techniques to distribute the processing among several NFD instances to build an elastic NFD. The proposed forwarder architecture challenges the status quo in term of applicability of NFD for high-speed Big Data transfers that we demonstrate with experiments using our proof-of-concept implementation.","PeriodicalId":165839,"journal":{"name":"2019 Global Information Infrastructure and Networking Symposium (GIIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 Global Information Infrastructure and Networking Symposium (GIIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/GIIS48668.2019.9044959","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Information Centric Networking is more and more used today. Named Data Networking (NDN) is one implementation of such paradigm focusing the communication on the information instead of the hosts. The performance of the NDN forwarder - called Name Forwarder Daemon (NFD) - is one major challenge faced by the NDN community especially due to the complex structures of both the naming prefixes and the forwarding tables. High-performance NFD is a major requirement to enable Big Data processing over NDN due to the scale of the exchanges used in real life applications. This paper proposes an approach to overcome the actual limitation of the packets processing capability of the NFD. The proposed approach uses state-of-the-art virtualization techniques to distribute the processing among several NFD instances to build an elastic NFD. The proposed forwarder architecture challenges the status quo in term of applicability of NFD for high-speed Big Data transfers that we demonstrate with experiments using our proof-of-concept implementation.