{"title":"Accurate Rate-Aware Flow-level Traffic Splitting","authors":"N. Wu, Shih-Hao Tseng, A. Tang","doi":"10.1109/ALLERTON.2018.8635940","DOIUrl":null,"url":null,"abstract":"This paper aims to accurately realize given traffic split ratios in switches with small performance degradation. For given traffic split ratios calculated mathematically by TE algorithms in the control plane, the load distribution mechanisms in the data plane implement such splits without breaking flows. Treating all flows equally, the state-of-the-art approaches deployed in switches do not provide enough accuracy especially when facing non-uniform flow size distribution. We instead propose a dynamic load distribution scheme based on the collected load sharing statistics. It finds the most accurate traffic splits with minimum route changes. We implement our solution in Open vSwitch (OVS). Trace-driven and end-to-end experiments demonstrate that 1) our approach effectively adjusts load distribution in real time to mitigate the inaccuracy of splits caused by the variation of flow size distribution, 2) it outperforms the existing approaches with respect to both higher accuracy and lower level of route changes, and 3) it requires path changes for less flows when routing strategies are reconfigured, hence leads to better flow experience such as higher goodput.","PeriodicalId":299280,"journal":{"name":"2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ALLERTON.2018.8635940","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
This paper aims to accurately realize given traffic split ratios in switches with small performance degradation. For given traffic split ratios calculated mathematically by TE algorithms in the control plane, the load distribution mechanisms in the data plane implement such splits without breaking flows. Treating all flows equally, the state-of-the-art approaches deployed in switches do not provide enough accuracy especially when facing non-uniform flow size distribution. We instead propose a dynamic load distribution scheme based on the collected load sharing statistics. It finds the most accurate traffic splits with minimum route changes. We implement our solution in Open vSwitch (OVS). Trace-driven and end-to-end experiments demonstrate that 1) our approach effectively adjusts load distribution in real time to mitigate the inaccuracy of splits caused by the variation of flow size distribution, 2) it outperforms the existing approaches with respect to both higher accuracy and lower level of route changes, and 3) it requires path changes for less flows when routing strategies are reconfigured, hence leads to better flow experience such as higher goodput.