{"title":"高性能分布式RMA锁","authors":"P. Schmid, Maciej Besta, T. Hoefler","doi":"10.1145/2907294.2907323","DOIUrl":null,"url":null,"abstract":"We propose a topology-aware distributed Reader-Writer lock that accelerates irregular workloads for supercomputers and data centers. The core idea behind the lock is a modular design that is an interplay of three distributed data structures: a counter of readers/writers in the critical section, a set of queues for ordering writers waiting for the lock, and a tree that binds all the queues and synchronizes writers with readers. Each structure is associated with a parameter for favoring either readers or writers, enabling adjustable performance that can be viewed as a point in a three dimensional parameter space. We also develop a distributed topology-aware MCS lock that is a building block of the above design and improves state-of-the-art MPI implementations. Both schemes use non-blocking Remote Memory Access (RMA) techniques for highest performance and scalability. We evaluate our schemes on a Cray XC30 and illustrate that they outperform state-of-the-art MPI-3 RMA locking protocols by 81% and 73%, respectively. Finally, we use them to accelerate a distributed hashtable that represents irregular workloads such as key-value stores or graph processing.","PeriodicalId":20515,"journal":{"name":"Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing","volume":"20 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2016-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"31","resultStr":"{\"title\":\"High-Performance Distributed RMA Locks\",\"authors\":\"P. Schmid, Maciej Besta, T. Hoefler\",\"doi\":\"10.1145/2907294.2907323\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a topology-aware distributed Reader-Writer lock that accelerates irregular workloads for supercomputers and data centers. The core idea behind the lock is a modular design that is an interplay of three distributed data structures: a counter of readers/writers in the critical section, a set of queues for ordering writers waiting for the lock, and a tree that binds all the queues and synchronizes writers with readers. Each structure is associated with a parameter for favoring either readers or writers, enabling adjustable performance that can be viewed as a point in a three dimensional parameter space. We also develop a distributed topology-aware MCS lock that is a building block of the above design and improves state-of-the-art MPI implementations. Both schemes use non-blocking Remote Memory Access (RMA) techniques for highest performance and scalability. We evaluate our schemes on a Cray XC30 and illustrate that they outperform state-of-the-art MPI-3 RMA locking protocols by 81% and 73%, respectively. Finally, we use them to accelerate a distributed hashtable that represents irregular workloads such as key-value stores or graph processing.\",\"PeriodicalId\":20515,\"journal\":{\"name\":\"Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing\",\"volume\":\"20 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-05-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"31\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2907294.2907323\",\"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 25th ACM International Symposium on High-Performance Parallel and Distributed Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2907294.2907323","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
We propose a topology-aware distributed Reader-Writer lock that accelerates irregular workloads for supercomputers and data centers. The core idea behind the lock is a modular design that is an interplay of three distributed data structures: a counter of readers/writers in the critical section, a set of queues for ordering writers waiting for the lock, and a tree that binds all the queues and synchronizes writers with readers. Each structure is associated with a parameter for favoring either readers or writers, enabling adjustable performance that can be viewed as a point in a three dimensional parameter space. We also develop a distributed topology-aware MCS lock that is a building block of the above design and improves state-of-the-art MPI implementations. Both schemes use non-blocking Remote Memory Access (RMA) techniques for highest performance and scalability. We evaluate our schemes on a Cray XC30 and illustrate that they outperform state-of-the-art MPI-3 RMA locking protocols by 81% and 73%, respectively. Finally, we use them to accelerate a distributed hashtable that represents irregular workloads such as key-value stores or graph processing.