缓冲区和节点大小对分组交换机性能的影响

M. Pustišek, A. Kos, J. Bester
{"title":"缓冲区和节点大小对分组交换机性能的影响","authors":"M. Pustišek, A. Kos, J. Bester","doi":"10.1109/MELCON.2004.1346992","DOIUrl":null,"url":null,"abstract":"Performance in packet switch with arbitrary buffer space and the switch size in three different buffer allocation schemes, OQ, VOQ and FPCF, are analyzed. The performance measures are mean and maximum packet delay and packet loss probability. For the analysis ns2, simulation environment is applied, where the VOQ and FPCF nodes are newly implemented. The results show that the node architecture itself determines the relations between size and buffer space on one hand and the node performance on the other. In all the architectures, packet loss probability decreases and mean queuing delay increases with increased buffer size. The switch size has no effect on the performance in OQ and causes slight increase of packet loss probability in FPCF due to its specific classification algorithm. In VOQ, N and B are strongly related because of the separation of total buffer space in N virtual queues and both substantially influence the performance. Changes in packet loss probability related to the switch size in FPCF can be compensated with additional buffer space without influencing the queuing delay. In VOQ, the additional buffer space required is much larger and well-planned buffer allocation is required.","PeriodicalId":164818,"journal":{"name":"Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.04CH37521)","volume":"284-286 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Effects of buffer and node size on packet switch performance\",\"authors\":\"M. Pustišek, A. Kos, J. Bester\",\"doi\":\"10.1109/MELCON.2004.1346992\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Performance in packet switch with arbitrary buffer space and the switch size in three different buffer allocation schemes, OQ, VOQ and FPCF, are analyzed. The performance measures are mean and maximum packet delay and packet loss probability. For the analysis ns2, simulation environment is applied, where the VOQ and FPCF nodes are newly implemented. The results show that the node architecture itself determines the relations between size and buffer space on one hand and the node performance on the other. In all the architectures, packet loss probability decreases and mean queuing delay increases with increased buffer size. The switch size has no effect on the performance in OQ and causes slight increase of packet loss probability in FPCF due to its specific classification algorithm. In VOQ, N and B are strongly related because of the separation of total buffer space in N virtual queues and both substantially influence the performance. Changes in packet loss probability related to the switch size in FPCF can be compensated with additional buffer space without influencing the queuing delay. In VOQ, the additional buffer space required is much larger and well-planned buffer allocation is required.\",\"PeriodicalId\":164818,\"journal\":{\"name\":\"Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.04CH37521)\",\"volume\":\"284-286 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2004-05-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.04CH37521)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/MELCON.2004.1346992\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.04CH37521)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MELCON.2004.1346992","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

分析了任意缓冲空间下分组交换机的性能以及交换机大小在OQ、VOQ和FPCF三种不同的缓冲分配方案下的性能。性能指标包括平均时延、最大时延和丢包概率。分析ns2采用仿真环境,其中VOQ和FPCF节点是新实现的。结果表明,节点体系结构本身决定了节点大小和缓冲空间之间的关系以及节点性能之间的关系。在所有的体系结构中,随着缓冲区大小的增加,丢包概率降低,平均排队延迟增加。交换机大小对OQ中的性能没有影响,并且由于其特定的分类算法,导致FPCF中的丢包概率略有增加。在VOQ中,N和B密切相关,因为N个虚拟队列中的总缓冲空间是分离的,两者都对性能有很大影响。在FPCF中,与交换机大小相关的丢包概率的变化可以用额外的缓冲空间来补偿,而不会影响排队延迟。在VOQ中,所需的额外缓冲区空间要大得多,并且需要精心规划缓冲区分配。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Effects of buffer and node size on packet switch performance
Performance in packet switch with arbitrary buffer space and the switch size in three different buffer allocation schemes, OQ, VOQ and FPCF, are analyzed. The performance measures are mean and maximum packet delay and packet loss probability. For the analysis ns2, simulation environment is applied, where the VOQ and FPCF nodes are newly implemented. The results show that the node architecture itself determines the relations between size and buffer space on one hand and the node performance on the other. In all the architectures, packet loss probability decreases and mean queuing delay increases with increased buffer size. The switch size has no effect on the performance in OQ and causes slight increase of packet loss probability in FPCF due to its specific classification algorithm. In VOQ, N and B are strongly related because of the separation of total buffer space in N virtual queues and both substantially influence the performance. Changes in packet loss probability related to the switch size in FPCF can be compensated with additional buffer space without influencing the queuing delay. In VOQ, the additional buffer space required is much larger and well-planned buffer allocation is required.
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
期刊最新文献
Virtual restoration of fragmented glass plate photographs Multirate decorrelating detector for UMTS Experimental comparison of substrate structures for inductors and transformers Illegal connection location on main power cable Formal verification of ad-hoc routing protocols using SPIN model checker
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1