Dynamic cluster database architecture
    2.
    发明授权
    Dynamic cluster database architecture 有权
    动态集群数据库架构

    公开(公告)号:US07447693B2

    公开(公告)日:2008-11-04

    申请号:US10390812

    申请日:2003-03-17

    IPC分类号: G06F7/00 G06F17/30

    摘要: A distributed database management system implemented on a cluster of computers. The cluster including disks organized as data nodes. The data nodes being locally connected to one or more computers in the cluster. The distributed database management system includes a distributed database manager layer having a lock manager, a resource manager, and an architecture manager. The lock manager serializes access to the data nodes in the cluster. The resource manager maintains a data representation of the resources of each computer in the cluster and makes the data available to other computers in the cluster to facilitate access to the resources by the other computers. The architecture manager defines logical ownership relationships between data nodes and computers in the cluster to permit the architecture of the database to be dynamically reconfigured to provide improved performance.

    摘要翻译: 在一组计算机上实现的分布式数据库管理系统。 集群包括组织为数据节点的磁盘。 数据节点本地连接到集群中的一台或多台计算机。 分布式数据库管理系统包括具有锁管理器,资源管理器和架构管理器的分布式数据库管理器层。 锁定管理器将访问集群中的数据节点序列化。 资源管理器维护集群中每台计算机的资源的数据表示,并使数据可用于集群中的其他计算机,以便其他计算机访问资源。 架构管理员定义集群中数据节点和计算机之间的逻辑所有权关系,以允许动态重新配置数据库的体系结构以提供改进的性能。

    Adaptive spin latches
    3.
    发明授权
    Adaptive spin latches 失效
    自适应旋转锁存器

    公开(公告)号:US06976107B2

    公开(公告)日:2005-12-13

    申请号:US10242524

    申请日:2002-09-12

    CPC分类号: G06F9/526

    摘要: An adaptive spin latch system is provided for use in a multiprocessor computer system. The spin latch system includes a run queue, a spin latch module and a wait queue. The run queue is adapted to store agent index data correlated to at least one agent in run mode. The spin latch module is adapted to put the at least one agent into sleep mode for a period of time correlated to a number of agents awaiting access to a resource. The wait queue is adapted to store agent index data correlated to the at least one agent in sleep mode. A method of regulating access by agents to a resource in a multiprocessor computing system is also provided.

    摘要翻译: 提供了一种在多处理器计算机系统中使用的自适应旋转锁存系统。 自旋锁存系统包括运行队列,自旋锁存模块和等待队列。 运行队列适于在运行模式下存储与至少一个代理相关的代理索引数据。 自旋锁存模块适于将至少一个代理进入休眠模式一段时间,其与等待访问资源的代理的数量相关。 等待队列适于在休眠模式下存储与至少一个代理相关的代理索引数据。 还提供了一种调节代理对多处理器计算系统中的资源的访问的方法。

    Dynamic cluster database architecture
    5.
    发明授权
    Dynamic cluster database architecture 失效
    动态集群数据库架构

    公开(公告)号:US07937377B2

    公开(公告)日:2011-05-03

    申请号:US11780446

    申请日:2007-07-19

    IPC分类号: G06F7/00

    摘要: distributed database management system implemented on a cluster of computers. The cluster including disks organized as data nodes. The data nodes being locally connected to one or more computers in the cluster. The distributed database management system includes a distributed database manager layer having a lock manager, a resource manager, and an architecture manager. The lock manager serializes access to the data nodes in the cluster. The resource manager maintains a data representation of the resources of each computer in the cluster and makes the data available to other computers in the cluster to facilitate access to the resources by the other computers. The architecture manager defines logical ownership relationships between data nodes and computers in the cluster to permit the architecture of the database to be dynamically reconfigured to provide improved performance.

    摘要翻译: 分布式数据库管理系统在一组计算机上实现。 集群包括组织为数据节点的磁盘。 数据节点本地连接到集群中的一台或多台计算机。 分布式数据库管理系统包括具有锁管理器,资源管理器和架构管理器的分布式数据库管理器层。 锁定管理器将访问集群中的数据节点序列化。 资源管理器维护集群中每台计算机的资源的数据表示,并使数据可用于集群中的其他计算机,以便其他计算机访问资源。 架构管理员定义集群中数据节点和计算机之间的逻辑所有权关系,以允许动态重新配置数据库的体系结构以提供改进的性能。

    DYNAMIC CLUSTER DATABASE ARCHITECTURE
    6.
    发明申请
    DYNAMIC CLUSTER DATABASE ARCHITECTURE 有权
    动态群集数据库架构

    公开(公告)号:US20080288554A1

    公开(公告)日:2008-11-20

    申请号:US12184796

    申请日:2008-08-01

    IPC分类号: G06F17/30

    摘要: A method for implementing distributed database management system operations on a computer cluster. The method includes defining ownership relationships between a plurality of computers in the computer cluster and a plurality of data nodes in the computer cluster, wherein a distributed database management system operation can be directly carried out by a first computer only on those data nodes owned by the first computer. The method further includes monitoring database usage characteristics. The method further includes carrying out a re-architecture step in response to the database usage characteristics by redefining ownership relationships to improve the efficiency of the distributed database management system operations.

    摘要翻译: 一种在计算机集群上实现分布式数据库管理系统操作的方法。 该方法包括定义计算机集群中的多个计算机与计算机集群中的多个数据节点之间的所有权关系,其中分布式数据库管理系统操作可以由第一计算机直接执行,仅在由 第一台电脑 该方法还包括监视数据库使用特性。 该方法还包括通过重新定义所有权关系来实现响应于数据库使用特性的重新架构步骤,以提高分布式数据库管理系统操作的效率。

    Dynamic cluster database architecture
    7.
    发明授权
    Dynamic cluster database architecture 有权
    动态集群数据库架构

    公开(公告)号:US07970797B2

    公开(公告)日:2011-06-28

    申请号:US12184796

    申请日:2008-08-01

    IPC分类号: G06F17/30

    摘要: A method for implementing distributed database management system operations on a computer cluster. The method includes defining ownership relationships between a plurality of computers in the computer cluster and a plurality of data nodes in the computer cluster, wherein a distributed database management system operation can be directly carried out by a first computer only on those data nodes owned by the first computer. The method further includes monitoring database usage characteristics. The method further includes carrying out a re-architecture step in response to the database usage characteristics by redefining ownership relationships to improve the efficiency of the distributed database management system operations.

    摘要翻译: 一种在计算机集群上实现分布式数据库管理系统操作的方法。 该方法包括定义计算机集群中的多个计算机与计算机集群中的多个数据节点之间的所有权关系,其中分布式数据库管理系统操作可由第一计算机直接执行,仅在由 第一台电脑 该方法还包括监视数据库使用特性。 该方法还包括通过重新定义所有权关系来实现响应于数据库使用特性的重新架构步骤,以提高分布式数据库管理系统操作的效率。

    Dynamic cluster database architecture
    8.
    发明授权
    Dynamic cluster database architecture 失效
    动态集群数据库架构

    公开(公告)号:US07933882B2

    公开(公告)日:2011-04-26

    申请号:US12259994

    申请日:2008-10-28

    IPC分类号: G06F7/00

    摘要: A method for implementing a set of database management components in a distributed database management system, the distributed database management system being implemented on a computer cluster. The method includes managing resources associated with an associated computer, the associated computer being one of a plurality of computers in the computer cluster. The method also includes managing locks on data stored on a plurality of associated data nodes coupled to the associated computer, wherein the associated data nodes are data nodes of a plurality of data nodes in the computer cluster. The method also includes specifying logical connections for the plurality of associated data nodes.

    摘要翻译: 一种在分布式数据库管理系统中实现一组数据库管理组件的方法,该分布式数据库管理系统正在计算机集群上实现。 该方法包括管理与相关联的计算机相关联的资源,相关联的计算机是计算机集群中的多个计算机之一。 该方法还包括对存储在耦合到相关联的计算机的多个相关联的数据节点上的数据进行管理锁定,其中相关联的数据节点是计算机集群中的多个数据节点的数据节点。 该方法还包括指定多个关联的数据节点的逻辑连接。

    Defensive heap memory management
    9.
    发明授权
    Defensive heap memory management 有权
    防御堆内存管理

    公开(公告)号:US07827375B2

    公开(公告)日:2010-11-02

    申请号:US11626691

    申请日:2007-01-24

    IPC分类号: G06F12/00 G06F13/00

    CPC分类号: G06F11/366 G06F12/023

    摘要: A data structure, method and system are provided incorporating a general purpose memory allocator and defensive heap memory manager. This provides an ability to reliably detect various types of memory errors, dynamically enable or disable memory debugging, enhance success of read and write operations using various memory verification techniques. Further, through separation of control information associated with allocated and free chunks of memory from the chunks themselves (separation of metadata from actual data), enhanced protection of vital information about the heap memory layout in general is provided. The heap memory manager uses read, write, and execute protected heap header walls and pool header walls and may, for each pool and memory block, separately use hidden front and back Memory Debug Information Areas (MDIAs) with checksums and well-known signature fields thereby enhancing overall memory management.

    摘要翻译: 提供了包含通用存储器分配器和防御堆存储器管理器的数据结构,方法和系统。 这提供了可靠地检测各种类型的存储器错误,动态地启用或禁用存储器调试的能力,使用各种存储器验证技术增强了读取和写入操作的成功。 此外,通过分离与分组本身的分配的和自由的存储块相关联的控制信息(元数据与实际数据的分离),提供了关于堆存储器布局的重要信息的增强保护。 堆内存管理器使用读,写和执行保护的堆标头墙和池标题墙,并且对于每个池和内存块,可以分别使用具有校验和和公知签名字段的隐藏的前端和后端内存调试信息区域(MDI) 从而增强整体内存管理。

    METHOD AND SYSTEM FOR CONTENT-BASED ENCRYPTED ACCESS TO A DATABASE
    10.
    发明申请
    METHOD AND SYSTEM FOR CONTENT-BASED ENCRYPTED ACCESS TO A DATABASE 有权
    用于基于内容的加密访问数据库的方法和系统

    公开(公告)号:US20080162946A1

    公开(公告)日:2008-07-03

    申请号:US11617597

    申请日:2006-12-28

    IPC分类号: H04L9/32

    CPC分类号: G06F21/6227

    摘要: Some aspects of the invention provide methods, systems, and computer program products for inserting an encrypted problem signature into a symptom database. A problem signature is first provided, which is then used to derive a hash value. The problem signature is then encrypted using the hash value. The hash value is further used to indicate the location in the database to insert the problem signature. The problem signature is then inserted at the location in the database indicated by the location.

    摘要翻译: 本发明的一些方面提供了用于将加密的问题签名插入症状数据库的方法,系统和计算机程序产品。 首先提供问题签名,然后将其用于导出哈希值。 然后使用哈希值对问题签名进行加密。 散列值进一步用于指示数据库中插入问题签名的位置。 然后将问题签名插入位置指示的数据库中的位置。