公开(公告)号：US10042678B2

公开(公告)日：2018-08-07

申请号：US14995789

申请日：2016-01-14

Applicant: Huawei Technologies Co., Ltd.

Inventor： Wenlong Huang ,  Haoyang Che ,  Chuanting Wang

IPC: G06F13/00 ,  G06F12/14 ,  G06F9/52 ,  G06F9/46 ,  G06F9/50 ,  G06F17/30

Abstract: A lock management method and system, and a method and an apparatus for configuring a lock management system is provided. A corresponding level of a lock management system is set for each service execution node according to the number of service execution nodes included in a distributed system, the number of system instances on all service execution nodes, the number of handling processes on all the service execution nodes, and a delay of access of each service execution node to a central control node of the distributed system. At least one lock manager is allocated to each service execution node separately according to the level, which is corresponding to each service execution node, of the lock management system. A lock level context is configured for each lock manager, where the lock level context is used to determine an adjacent lock manager of each lock manager.

公开(公告)号：US20160132364A1

公开(公告)日：2016-05-12

申请号：US14995789

申请日：2016-01-14

Applicant: Huawei Technologies Co., Ltd.

Inventor： Wenlong Huang ,  Haoyang Che ,  Chuanting Wang

IPC: G06F9/52 ,  G06F9/46

CPC classification number: G06F9/526 ,  G06F9/46 ,  G06F9/466 ,  G06F9/50 ,  G06F17/30362

Abstract: A lock management method and system, and a method and an apparatus for configuring a lock management system is provided. A corresponding level of a lock management system is set for each service execution node according to the number of service execution nodes included in a distributed system, the number of system instances on all service execution nodes, the number of handling processes on all the service execution nodes, and a delay of access of each service execution node to a central control node of the distributed system. At least one lock manager is allocated to each service execution node separately according to the level, which is corresponding to each service execution node, of the lock management system. A lock level context is configured for each lock manager, where the lock level context is used to determine an adjacent lock manager of each lock manager.

Abstract translation: 提供了一种锁管理方法和系统，以及用于配置锁管理系统的方法和装置。 根据分布式系统中包括的服务执行节点的数量，所有服务执行节点上的系统实例的数量，所有服务执行上的处理过程的数量，为每个服务执行节点设置相应级别的锁管理系统 节点，以及每个服务执行节点到分布式系统的中央控制节点的访问延迟。 至少一个锁管理器根据与锁管理系统的每个服务执行节点相对应的级别分别分配给每个服务执行节点。 为每个锁管理器配置锁级别上下文，其中锁级别上下文用于确定每个锁管理器的相邻锁管理器。

公开(公告)号：US09323796B2

公开(公告)日：2016-04-26

申请号：US14297968

申请日：2014-06-06

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yu Wen ,  Haoyang Che ,  Yong Zhang

IPC: G06F17/30 ,  G06F7/00

CPC classification number: G06F17/30312 ,  G06F17/30286 ,  G06F17/30539 ,  G06F17/30592 ,  G06F17/30595

Abstract: A data partitioning method and apparatus. The method includes: determining tuple relationship information according to received mixed loads and structure information of a database; determining tuple split cost information according to the tuple relationship information and a feature about whether the mixed loads are executable in parallel; obtaining multiple partitioning schemes according to the tuple split cost information, and determining, from the partitioning schemes, a partitioning scheme with a minimum total cost value as an optimum partitioning scheme to perform partitioning processing on data stored in the database. In the data partitioning method and apparatus, optimum partitioning is performed on data associated with the mixed loads in a database, after partitioning, data has features of a transaction load and an analytical load in the mixed loads, thereby improving working performance of the database system oriented to the mixed loads.

Abstract translation: 数据分割方法和装置。 该方法包括：根据接收到的混合负载和数据库的结构信息确定元组关系信息; 根据元组关系信息确定元组分割成本信息，以及关于混合负载是否可并行执行的特征; 根据元组分割成本信息获得多个分割方案，以及从划分方案中确定具有最小总成本值的划分方案作为对存储在数据库中的数据执行分区处理的最佳分区方案。 在数据分割方法和装置中，对与数据库中的混合负载相关联的数据执行最佳分区，分区后，数据具有事务负载的特征和混合负载中的分析负载，从而提高数据库系统的工作性能 面向混合负载。

公开(公告)号：US20140365492A1

公开(公告)日：2014-12-11

申请号：US14297968

申请日：2014-06-06

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yu Wen ,  Haoyang Che ,  Yong Zhang

IPC: G06F17/30

CPC classification number: G06F17/30312 ,  G06F17/30286 ,  G06F17/30539 ,  G06F17/30592 ,  G06F17/30595

Abstract: A data partitioning method and apparatus. The method includes: determining tuple relationship information according to received mixed loads and structure information of a database; determining tuple split cost information according to the tuple relationship information and a feature about whether the mixed loads are executable in parallel; obtaining multiple partitioning schemes according to the tuple split cost information, and determining, from the partitioning schemes, a partitioning scheme with a minimum total cost value as an optimum partitioning scheme to perform partitioning processing on data stored in the database. In the data partitioning method and apparatus, optimum partitioning is performed on data associated with the mixed loads in a database, after partitioning, data has features of a transaction load and an analytical load in the mixed loads, thereby improving working performance of the database system oriented to the mixed loads.

Abstract translation: 数据分割方法和装置。 该方法包括：根据接收到的混合负载和数据库的结构信息确定元组关系信息; 根据元组关系信息确定元组分割成本信息，以及关于混合负载是否可并行执行的特征; 根据元组分割成本信息获得多个分割方案，以及从划分方案中确定具有最小总成本值的划分方案作为对存储在数据库中的数据执行分区处理的最佳分区方案。 在数据分割方法和装置中，对与数据库中的混合负载相关联的数据执行最佳分区，分区后，数据具有事务负载的特征和混合负载中的分析负载，从而提高数据库系统的工作性能 面向混合负载。