{"title":"基于提前预约机制的计算机网络性能研究","authors":"Lars-Olof Burchard","doi":"10.1109/ICON.2003.1266232","DOIUrl":null,"url":null,"abstract":"In contrast tu immediate reservations, advance reservations allow to reserve network bandwidth long before it is actnally required. Hence, advance reservations are an opportunity tu provide enhanced functionality in a computer network allowing to define new services, such as guaranteeing that a certain deadline for a transmission over the network can be met. Such functionality is required e.g. in the field of grid computing where also mmputing resources have to be allocated in advance. The impact of such advance reservation mechanisms on the performance of the network with respect to the amount of admitted requests and the allocated bandwidth has so far nut been examined in detail. In this paper, we show that advance reservations can lead to a reduced performance of the network with respect tu both metrics. The analysis of the reasons shows a fragmentation of the network resources resulting in decreased performance. In advance reservation environments, additional new services can he defined such as malleable reservations which are mtmduced in this paper and can lead to an increased performance of the network. In order tu deal with this new reservation type, four scheduling strategies are presented and compared. The results of the comparisons show that some strategies increase the resonrce fragmentation and are therefore unsuitable in the considered environment while others lead to a significantly better performance of the network","PeriodicalId":122389,"journal":{"name":"The 11th IEEE International Conference on Networks, 2003. ICON2003.","volume":"30 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2003-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"27","resultStr":"{\"title\":\"On the performance of computer networks with advance reservation mechanisms\",\"authors\":\"Lars-Olof Burchard\",\"doi\":\"10.1109/ICON.2003.1266232\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In contrast tu immediate reservations, advance reservations allow to reserve network bandwidth long before it is actnally required. Hence, advance reservations are an opportunity tu provide enhanced functionality in a computer network allowing to define new services, such as guaranteeing that a certain deadline for a transmission over the network can be met. Such functionality is required e.g. in the field of grid computing where also mmputing resources have to be allocated in advance. The impact of such advance reservation mechanisms on the performance of the network with respect to the amount of admitted requests and the allocated bandwidth has so far nut been examined in detail. In this paper, we show that advance reservations can lead to a reduced performance of the network with respect tu both metrics. The analysis of the reasons shows a fragmentation of the network resources resulting in decreased performance. In advance reservation environments, additional new services can he defined such as malleable reservations which are mtmduced in this paper and can lead to an increased performance of the network. In order tu deal with this new reservation type, four scheduling strategies are presented and compared. The results of the comparisons show that some strategies increase the resonrce fragmentation and are therefore unsuitable in the considered environment while others lead to a significantly better performance of the network\",\"PeriodicalId\":122389,\"journal\":{\"name\":\"The 11th IEEE International Conference on Networks, 2003. ICON2003.\",\"volume\":\"30 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2003-09-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"27\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"The 11th IEEE International Conference on Networks, 2003. ICON2003.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICON.2003.1266232\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"The 11th IEEE International Conference on Networks, 2003. ICON2003.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICON.2003.1266232","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
On the performance of computer networks with advance reservation mechanisms
In contrast tu immediate reservations, advance reservations allow to reserve network bandwidth long before it is actnally required. Hence, advance reservations are an opportunity tu provide enhanced functionality in a computer network allowing to define new services, such as guaranteeing that a certain deadline for a transmission over the network can be met. Such functionality is required e.g. in the field of grid computing where also mmputing resources have to be allocated in advance. The impact of such advance reservation mechanisms on the performance of the network with respect to the amount of admitted requests and the allocated bandwidth has so far nut been examined in detail. In this paper, we show that advance reservations can lead to a reduced performance of the network with respect tu both metrics. The analysis of the reasons shows a fragmentation of the network resources resulting in decreased performance. In advance reservation environments, additional new services can he defined such as malleable reservations which are mtmduced in this paper and can lead to an increased performance of the network. In order tu deal with this new reservation type, four scheduling strategies are presented and compared. The results of the comparisons show that some strategies increase the resonrce fragmentation and are therefore unsuitable in the considered environment while others lead to a significantly better performance of the network