Mateus Saquetti, Guilherme Bueno, Weverton Cordeiro, J. Azambuja
{"title":"VirtP4: An Architecture for P4 Virtualization","authors":"Mateus Saquetti, Guilherme Bueno, Weverton Cordeiro, J. Azambuja","doi":"10.1109/IPDPSW.2019.00021","DOIUrl":null,"url":null,"abstract":"This paper presents VirtP4, an architecture for the virtualization of P4-based programmable forwarding planes. VirtP4 provides parallel execution of true independent virtual switch instances with assistance of traffic control and packet routing. The architecture is implemented in a NetFPGA-SUME board running two virtual switches, a L2 Switch and a Router. The area occupation data show the possibility of implementing up to 13 P4 instances in parallel. When compared to related works, performance results exhibit improvements up to 3 orders of magnitude for bandwidth and 2 orders of magnitude for latency.","PeriodicalId":292054,"journal":{"name":"2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IPDPSW.2019.00021","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
Abstract
This paper presents VirtP4, an architecture for the virtualization of P4-based programmable forwarding planes. VirtP4 provides parallel execution of true independent virtual switch instances with assistance of traffic control and packet routing. The architecture is implemented in a NetFPGA-SUME board running two virtual switches, a L2 Switch and a Router. The area occupation data show the possibility of implementing up to 13 P4 instances in parallel. When compared to related works, performance results exhibit improvements up to 3 orders of magnitude for bandwidth and 2 orders of magnitude for latency.