{"title":"一种元数据服务器集群协同容错机制","authors":"Z. X. Li, Q. Wei, Y. Wang","doi":"10.1109/ICON.2007.4444136","DOIUrl":null,"url":null,"abstract":"In object-based storage system, metadata residing in metadata server (MDS) is crucial to the survival of overall system. Keeping metadata always available is becoming one of the key issues to be addressed for object-based storage system design and implementation. This paper presents a novel cooperative fault-tolerance mechanism for metadata server cluster, called Co-MDS. The Co-MDS consolidates disk space of individual MDS into a global metadata storage space and provides high fault-tolerance by distributing metadata and its parity data across collaborative metadata server cluster environment. With this mechanism, metadata is still available even when a part of metadata servers fail. Our design is transparent for applications and complies with OSD T10 standard. The experiments demonstrate that the proposed collaborative mechanism can offer high fault-tolerance and significant performance.","PeriodicalId":131548,"journal":{"name":"2007 15th IEEE International Conference on Networks","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Novel Collaborative Fault-Tolerance Mechanism for Metadata Server Cluster\",\"authors\":\"Z. X. Li, Q. Wei, Y. Wang\",\"doi\":\"10.1109/ICON.2007.4444136\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In object-based storage system, metadata residing in metadata server (MDS) is crucial to the survival of overall system. Keeping metadata always available is becoming one of the key issues to be addressed for object-based storage system design and implementation. This paper presents a novel cooperative fault-tolerance mechanism for metadata server cluster, called Co-MDS. The Co-MDS consolidates disk space of individual MDS into a global metadata storage space and provides high fault-tolerance by distributing metadata and its parity data across collaborative metadata server cluster environment. With this mechanism, metadata is still available even when a part of metadata servers fail. Our design is transparent for applications and complies with OSD T10 standard. The experiments demonstrate that the proposed collaborative mechanism can offer high fault-tolerance and significant performance.\",\"PeriodicalId\":131548,\"journal\":{\"name\":\"2007 15th IEEE International Conference on Networks\",\"volume\":\"12 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 15th IEEE International Conference on Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICON.2007.4444136\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 15th IEEE International Conference on Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICON.2007.4444136","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Novel Collaborative Fault-Tolerance Mechanism for Metadata Server Cluster
In object-based storage system, metadata residing in metadata server (MDS) is crucial to the survival of overall system. Keeping metadata always available is becoming one of the key issues to be addressed for object-based storage system design and implementation. This paper presents a novel cooperative fault-tolerance mechanism for metadata server cluster, called Co-MDS. The Co-MDS consolidates disk space of individual MDS into a global metadata storage space and provides high fault-tolerance by distributing metadata and its parity data across collaborative metadata server cluster environment. With this mechanism, metadata is still available even when a part of metadata servers fail. Our design is transparent for applications and complies with OSD T10 standard. The experiments demonstrate that the proposed collaborative mechanism can offer high fault-tolerance and significant performance.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
