{"title":"RIO的队列管理,实现高吞吐量和低延迟","authors":"Y. Hori, T. Ikenaga, Y. Oie","doi":"10.1109/PACRIM.2001.953709","DOIUrl":null,"url":null,"abstract":"We focus on the RIO queueing mechanism in statistical bandwidth allocation service, which uses AF-PHB. We study the parameterization of RIO to achieve both high throughput and low delay. We are able to parameterize RIO for that purpose in terms of both min-th and maxp used in dropping \"Out\" packets. Furthermore, we also examine the parameterization regarding EWMA (exponential weighted moving average), ie, weight factor w/sub qout/, and show that dropping \"Out\" packets should depend upon the queue length without much delay, unlike RED. From our simulation results, we can see that our parameterization provides high throughput performance and also limits the queue length in a narrow range very well.","PeriodicalId":261724,"journal":{"name":"2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (IEEE Cat. No.01CH37233)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2001-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Queue management of RIO to achieve high throughput and low delay\",\"authors\":\"Y. Hori, T. Ikenaga, Y. Oie\",\"doi\":\"10.1109/PACRIM.2001.953709\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We focus on the RIO queueing mechanism in statistical bandwidth allocation service, which uses AF-PHB. We study the parameterization of RIO to achieve both high throughput and low delay. We are able to parameterize RIO for that purpose in terms of both min-th and maxp used in dropping \\\"Out\\\" packets. Furthermore, we also examine the parameterization regarding EWMA (exponential weighted moving average), ie, weight factor w/sub qout/, and show that dropping \\\"Out\\\" packets should depend upon the queue length without much delay, unlike RED. From our simulation results, we can see that our parameterization provides high throughput performance and also limits the queue length in a narrow range very well.\",\"PeriodicalId\":261724,\"journal\":{\"name\":\"2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (IEEE Cat. No.01CH37233)\",\"volume\":\"68 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2001-08-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (IEEE Cat. No.01CH37233)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/PACRIM.2001.953709\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (IEEE Cat. No.01CH37233)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PACRIM.2001.953709","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Queue management of RIO to achieve high throughput and low delay
We focus on the RIO queueing mechanism in statistical bandwidth allocation service, which uses AF-PHB. We study the parameterization of RIO to achieve both high throughput and low delay. We are able to parameterize RIO for that purpose in terms of both min-th and maxp used in dropping "Out" packets. Furthermore, we also examine the parameterization regarding EWMA (exponential weighted moving average), ie, weight factor w/sub qout/, and show that dropping "Out" packets should depend upon the queue length without much delay, unlike RED. From our simulation results, we can see that our parameterization provides high throughput performance and also limits the queue length in a narrow range very well.