TCP中的并发处理

Yu Dong, N. Pissinou, Jian Wang
{"title":"TCP中的并发处理","authors":"Yu Dong, N. Pissinou, Jian Wang","doi":"10.1109/CNSR.2007.23","DOIUrl":null,"url":null,"abstract":"In this paper, we propose an extension to current TCP protocol named concurrent TCP (cTCP), which can improve throughput of connections through balancing traffic load on multiple end-to-end paths. We keep the single-sliding-window architecture of TCP untouched for compatibility reasons. The two core components of the design are a packet scheduling switch that balances load among paths, and a duplicated acknowledgement classifier that handles packet reordering. We implemented our protocol in FreeBSD kernel and compared the performance of cTCP with theoretical results. Experiment outcomes show that throughputs of our protocol are close to the ideal values.","PeriodicalId":266936,"journal":{"name":"Fifth Annual Conference on Communication Networks and Services Research (CNSR '07)","volume":"137 3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"16","resultStr":"{\"title\":\"Concurrency Handling in TCP\",\"authors\":\"Yu Dong, N. Pissinou, Jian Wang\",\"doi\":\"10.1109/CNSR.2007.23\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we propose an extension to current TCP protocol named concurrent TCP (cTCP), which can improve throughput of connections through balancing traffic load on multiple end-to-end paths. We keep the single-sliding-window architecture of TCP untouched for compatibility reasons. The two core components of the design are a packet scheduling switch that balances load among paths, and a duplicated acknowledgement classifier that handles packet reordering. We implemented our protocol in FreeBSD kernel and compared the performance of cTCP with theoretical results. Experiment outcomes show that throughputs of our protocol are close to the ideal values.\",\"PeriodicalId\":266936,\"journal\":{\"name\":\"Fifth Annual Conference on Communication Networks and Services Research (CNSR '07)\",\"volume\":\"137 3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-05-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"16\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Fifth Annual Conference on Communication Networks and Services Research (CNSR '07)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CNSR.2007.23\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fifth Annual Conference on Communication Networks and Services Research (CNSR '07)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CNSR.2007.23","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 16

摘要

本文提出了对当前TCP协议的一种扩展,即并发TCP (concurrent TCP, cTCP),它可以通过在多个端到端路径上均衡流量负载来提高连接的吞吐量。出于兼容性原因,我们保持TCP的单滑动窗口架构不变。该设计的两个核心组件是在路径之间平衡负载的数据包调度开关和处理数据包重新排序的重复确认分类器。我们在FreeBSD内核中实现了cTCP协议,并将其性能与理论结果进行了比较。实验结果表明,该协议的吞吐量接近理想值。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Concurrency Handling in TCP
In this paper, we propose an extension to current TCP protocol named concurrent TCP (cTCP), which can improve throughput of connections through balancing traffic load on multiple end-to-end paths. We keep the single-sliding-window architecture of TCP untouched for compatibility reasons. The two core components of the design are a packet scheduling switch that balances load among paths, and a duplicated acknowledgement classifier that handles packet reordering. We implemented our protocol in FreeBSD kernel and compared the performance of cTCP with theoretical results. Experiment outcomes show that throughputs of our protocol are close to the ideal values.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信