{"title":"因果一致部分复制的全局镇定","authors":"Zhuolun Xiang, N. Vaidya","doi":"10.1145/3369740.3369795","DOIUrl":null,"url":null,"abstract":"Causally consistent distributed storage systems have received significant attention due to the potential for providing high throughput. Global stabilization is a technique established for achieving causal consistency in distributed multi-version key-value store systems, adopted by previous works such as GentleRain [6] and Cure [1]. However, previous designs with global stabilization assume full replication, where the set of the data is split into partitions with each partition replicated at all data centers, and each client is restricted to access servers within only one data center. In this paper, we propose a theoretical framework of global stabilization to support general partial replication with causal consistency, where each server can store an arbitrary subset of the data, and each client is allowed to communicate with any subset of the servers and migrate among them without extra delays. We propose an algorithm that implements causal consistency for distributed multi-version key-value stores with general partial replication, and our algorithm is optimal in terms of the remote update visibility latency, i.e. how fast update from a remote server is visible to the client, under general partial replication. Simulation results on the performance of our algorithm compared to the previous work are also provided.","PeriodicalId":240048,"journal":{"name":"Proceedings of the 21st International Conference on Distributed Computing and Networking","volume":"78 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"Global Stabilization for Causally Consistent Partial Replication\",\"authors\":\"Zhuolun Xiang, N. Vaidya\",\"doi\":\"10.1145/3369740.3369795\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Causally consistent distributed storage systems have received significant attention due to the potential for providing high throughput. Global stabilization is a technique established for achieving causal consistency in distributed multi-version key-value store systems, adopted by previous works such as GentleRain [6] and Cure [1]. However, previous designs with global stabilization assume full replication, where the set of the data is split into partitions with each partition replicated at all data centers, and each client is restricted to access servers within only one data center. In this paper, we propose a theoretical framework of global stabilization to support general partial replication with causal consistency, where each server can store an arbitrary subset of the data, and each client is allowed to communicate with any subset of the servers and migrate among them without extra delays. We propose an algorithm that implements causal consistency for distributed multi-version key-value stores with general partial replication, and our algorithm is optimal in terms of the remote update visibility latency, i.e. how fast update from a remote server is visible to the client, under general partial replication. Simulation results on the performance of our algorithm compared to the previous work are also provided.\",\"PeriodicalId\":240048,\"journal\":{\"name\":\"Proceedings of the 21st International Conference on Distributed Computing and Networking\",\"volume\":\"78 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-03-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 21st International Conference on Distributed Computing and Networking\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3369740.3369795\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 21st International Conference on Distributed Computing and Networking","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3369740.3369795","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Global Stabilization for Causally Consistent Partial Replication
Causally consistent distributed storage systems have received significant attention due to the potential for providing high throughput. Global stabilization is a technique established for achieving causal consistency in distributed multi-version key-value store systems, adopted by previous works such as GentleRain [6] and Cure [1]. However, previous designs with global stabilization assume full replication, where the set of the data is split into partitions with each partition replicated at all data centers, and each client is restricted to access servers within only one data center. In this paper, we propose a theoretical framework of global stabilization to support general partial replication with causal consistency, where each server can store an arbitrary subset of the data, and each client is allowed to communicate with any subset of the servers and migrate among them without extra delays. We propose an algorithm that implements causal consistency for distributed multi-version key-value stores with general partial replication, and our algorithm is optimal in terms of the remote update visibility latency, i.e. how fast update from a remote server is visible to the client, under general partial replication. Simulation results on the performance of our algorithm compared to the previous work are also provided.