{"title":"Performance and Application Scenario Evaluation of Network Hardware Queue","authors":"Xiang Gao, Rongkai Liu, Xiancheng Lin","doi":"10.1109/CCAI57533.2023.10201305","DOIUrl":null,"url":null,"abstract":"With the development of computer and network technology, it has brought great challenges to the efficient processing of the network. In particular, the number of CPU cores is increasing, which leads to the need for efficient cooperation of software and better concurrency. At the same time, the traditional software network packet processing method not only consumes a lot of host resources, but also causes uneven CPU load, which affects the overall performance. In the existing cutting-edge research, many network data processing of traditional software queues is realized through hardware queues, such as Intel’s DLB hardware queues. Taking the DLB hardware queue as an example, this research evaluates in detail its possible accelerated business scenarios and corresponding technical architecture, and also evaluates the basic performance of DLB technology, which lays a good foundation for future technology application and promotion.","PeriodicalId":285760,"journal":{"name":"2023 IEEE 3rd International Conference on Computer Communication and Artificial Intelligence (CCAI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE 3rd International Conference on Computer Communication and Artificial Intelligence (CCAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCAI57533.2023.10201305","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
With the development of computer and network technology, it has brought great challenges to the efficient processing of the network. In particular, the number of CPU cores is increasing, which leads to the need for efficient cooperation of software and better concurrency. At the same time, the traditional software network packet processing method not only consumes a lot of host resources, but also causes uneven CPU load, which affects the overall performance. In the existing cutting-edge research, many network data processing of traditional software queues is realized through hardware queues, such as Intel’s DLB hardware queues. Taking the DLB hardware queue as an example, this research evaluates in detail its possible accelerated business scenarios and corresponding technical architecture, and also evaluates the basic performance of DLB technology, which lays a good foundation for future technology application and promotion.