{"title":"A Multicomputer Message Switching Data Processing System","authors":"E. Cohler, H. Rubinstein","doi":"10.1109/TCOM.1967.1089594","DOIUrl":null,"url":null,"abstract":"This paper describes a number of new techniques for data processing in a message switching center that will improve system reliability and increase system availability. This data processing system contains several processor equipment pools introduced to avoid costly duplexing, yet it will keep equipment failures from interrupting operation. The system uses list processing techniques for memory allocation which result in efficient memory usage and allow each processor access to the entire message store. Direct access to memory interface is used to permit automatic switchover of service from one processor to another if the processor fails and to minimize the use of per-line-equipment. Techniques will also be described for message accounting, routing, and processor scheduling, which are independent of machine configuration.","PeriodicalId":134522,"journal":{"name":"IEEE Transactions on Communication Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1967-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Communication Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TCOM.1967.1089594","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
This paper describes a number of new techniques for data processing in a message switching center that will improve system reliability and increase system availability. This data processing system contains several processor equipment pools introduced to avoid costly duplexing, yet it will keep equipment failures from interrupting operation. The system uses list processing techniques for memory allocation which result in efficient memory usage and allow each processor access to the entire message store. Direct access to memory interface is used to permit automatic switchover of service from one processor to another if the processor fails and to minimize the use of per-line-equipment. Techniques will also be described for message accounting, routing, and processor scheduling, which are independent of machine configuration.