Symmetric shared file storage system
    1.
    发明授权
    Symmetric shared file storage system 失效
    对称共享文件存储系统

    公开(公告)号:US06976060B2

    公开(公告)日:2005-12-13

    申请号:US09731418

    申请日:2000-12-05

    摘要: A system and method to allow scalability of file storage in terms of capacity and performance through a symmetric multicomputer architecture with shared storage, in which storage and protocol processing resources can be added to (or removed from) the system without any need of recognizing and/or explicitly migrating the data stored in the system. The invention permits accessing files stored (i.e., written) in any of multiple external protocol processing nodes to be retrieved from any other external protocol processing node.

    摘要翻译: 一种通过具有共享存储器的对称多计算机架构来允许文件存储在容量和性能方面的可扩展性的系统和方法,其中存储和协议处理资源可以被添加到系统(或从系统中移除),而不需要识别和/ 或显式迁移存储在系统中的数据。 本发明允许访问从任何其他外部协议处理节点检索的多个外部协议处理节点中存储(即,写入)的文件。

    Proximity-based memory allocation in a distributed memory system
    3.
    发明授权
    Proximity-based memory allocation in a distributed memory system 有权
    分布式存储系统中基于接近度的内存分配

    公开(公告)号:US08150946B2

    公开(公告)日:2012-04-03

    申请号:US11409205

    申请日:2006-04-21

    IPC分类号: G06F15/177

    CPC分类号: H04L67/10 H04L12/00

    摘要: A system and method for allocating the nearest available physical memory in a distributed, shared memory system. In various embodiments, a processor node may broadcast a memory request to a first subset of nodes connected to it via a communication network. In some embodiments, if none of these nodes is able to satisfy the request, the processor node may broadcast the request to additional subsets of nodes. In some embodiments, each node of the first subset of nodes may be removed from the processor node by one network hop and each node of the additional subsets of nodes may be removed from the processor node by no more than an iteratively increasing number of network hops. In some embodiments, the processor node may send an acknowledgment to one node that can fulfill the request and a negative acknowledgement to other nodes that can fulfill the request.

    摘要翻译: 一种用于在分布式共享存储器系统中分配最近的可用物理存储器的系统和方法。 在各种实施例中,处理器节点可以经由通信网络向连接到其的节点的第一子集广播存储器请求。 在一些实施例中,如果这些节点都不能满足该请求,则处理器节点可以将该请求广播到附加的节点子集。 在一些实施例中,节点的第一子集的每个节点可以通过一个网络跳从处理器节点移除,并且可以通过不超过迭代增加的网络跳数来从处理器节点移除附加子节点的每个节点 。 在一些实施例中,处理器节点可以向可以满足请求的一个节点发送确认,并向可以满足该请求的其他节点发送否定的确认。

    Memory protection in a computer system employing memory virtualization
    4.
    发明授权
    Memory protection in a computer system employing memory virtualization 有权
    采用内存虚拟化的计算机系统中的内存保护

    公开(公告)号:US07917710B2

    公开(公告)日:2011-03-29

    申请号:US11446645

    申请日:2006-06-05

    IPC分类号: G06F12/00 G06F13/00 G06F13/28

    CPC分类号: G06F12/1475 G06F21/6227

    摘要: The use of a token-based memory protection technique may provide memory protection in a computer system employing memory virtualization. A token-based memory protection technique may include assigning a unique identifier to an application, process, or thread, and associating the identifier with a block of memory allocated to that application, process, or thread. Subsequent to assigning the identifier, a packet requesting access to that block of memory may include a token to be compared to the identifier. A memory controller may be configured to associate the identifier with the block of memory and to compare the token in the memory request packet to the identifier before granting access. If a second block of memory is subsequently allocated to the application, process, or thread, the identifier may be disassociated with the first block of memory and associated with the second block of memory.

    摘要翻译: 使用基于令牌的存储器保护技术可以在采用存储器虚拟化的计算机系统中提供存储器保护。 基于令牌的存储器保护技术可以包括向应用,处理或线程分配唯一标识符,以及将标识符与分配给该应用,处理或线程的存储器块相关联。 在分配标识符之后,请求访问该存储器块的分组可以包括要与标识符进行比较的令牌。 存储器控制器可以被配置为将标识符与存储器块相关联,并且在授予访问之前将存储器请求包中的令牌与标识符进行比较。 如果随后将第二块存储器分配给应用程序,进程或线程,则可以将该标识符与第一存储器块解除关联并与第二存储器块相关联。

    METHOD AND SYSTEM FOR COORDINATING HYPERVISOR SCHEDULING
    5.
    发明申请
    METHOD AND SYSTEM FOR COORDINATING HYPERVISOR SCHEDULING 有权
    用于协调高斯调度的方法和系统

    公开(公告)号:US20090089790A1

    公开(公告)日:2009-04-02

    申请号:US11932844

    申请日:2007-10-31

    IPC分类号: G06F9/46

    CPC分类号: G06F9/52 G06F9/522

    摘要: A method for executing an application on a plurality of nodes, that includes synchronizing a first clock of a first node of the plurality of nodes and a second clock of a second node of the plurality of nodes, configuring a first hypervisor on the first node to execute a first application domain and a first privileged domain, wherein configuring the hypervisor comprises allocating a first number of cycles of the first clock to the first privileged domain, configuring a second hypervisor on the second node to execute a second application domain and a second privileged domain, wherein configuring the second hypervisor that includes allocating the first number of cycles of the first clock to the second privileged domain, and executing the application in the first application domain and the second application domain, wherein the first application domain and the second application domain execute semi-synchronously and the first privileged domain and the second privileged domain execute semi-synchronously.

    摘要翻译: 一种用于在多个节点上执行应用的方法,包括同步所述多个节点中的第一节点的第一时钟和所述多个节点中的第二节点的第二时钟,将所述第一节点上的第一管理程序配置为 执行第一应用域和第一特权域,其中配置管理程序包括将第一时钟的第一数量的周期分配给第一特权域,在第二节点上配置第二管理程序以执行第二应用域和第二特权域 域,其中配置所述第二管理程序,所述第二管理程序包括将所述第一时钟的所述第一数量的周期分配给所述第二特权域,以及在所述第一应用域和所述第二应用域中执行所述应用,其中所述第一应用域和所述第二应用域 执行半同步,第一特权域和第二特权域执行半 - 异步地

    Metadata management for scalable process location and migration
    7.
    发明授权
    Metadata management for scalable process location and migration 有权
    用于可扩展的进程位置和迁移的元数据管理

    公开(公告)号:US08234260B1

    公开(公告)日:2012-07-31

    申请号:US11158750

    申请日:2005-06-22

    IPC分类号: G06F7/00 G06F17/30

    CPC分类号: G06F9/4856

    摘要: A method for metadata management for scalable processes, involving creating a process by a first home processor, wherein the process is associated with a process identification (ID), storing the processor ID and information identifying the first home processor in a global process look-up data structure (GPLD), requesting metadata associated with the process, searching the GPLD to obtain the first home processor of the process using the process ID, and retrieving the metadata associated with the process from the first home processor.

    摘要翻译: 一种用于可扩展处理的元数据管理的方法,涉及由第一家庭处理器创建过程,其中所述过程与进程标识(ID)相关联,将处理器ID和标识第一家庭处理器的信息存储在全局处理查找 数据结构(GPLD),请求与该过程相关联的元数据,搜索GPLD以使用进程ID获得该进程的第一家庭处理器,以及从第一家庭处理器检索与该进程相关联的元数据。

    Logging latency reduction
    8.
    发明授权
    Logging latency reduction 有权
    记录延迟降低

    公开(公告)号:US08069305B2

    公开(公告)日:2011-11-29

    申请号:US11828323

    申请日:2007-07-25

    IPC分类号: G06F13/10

    摘要: A disk is divided into K angular regions. A log write request is replicated K times and K number of identical log writes are issued to the disk to be written to each of the angular regions of the log. Upon completion of the first write, the application requesting the log write is informed of its completion resulting in a reduction of rotational latency by a factor of K.

    摘要翻译: 磁盘分为K个角度区域。 日志写入请求被复制K次,K个相同的日志写入被发送到要写入日志的每个角度区域的磁盘。 在完成第一次写入之后,向应用程序请求日志写入通知其完成,导致旋转等待时间减少K倍。

    Function-based virtual-to-physical address translation
    9.
    发明授权
    Function-based virtual-to-physical address translation 有权
    基于功能的虚拟到物理地址转换

    公开(公告)号:US07822941B2

    公开(公告)日:2010-10-26

    申请号:US11446620

    申请日:2006-06-05

    IPC分类号: G06F12/00 G06F9/26 G06F9/34

    摘要: A computer system employing memory virtualization may employ a function-based technique for virtual-to-physical address translation. A function-based translation technique may involve replacing a generic trap handler and one or more translation table look-ups with a function to compute a corresponding physical address from a given virtual address. The computer system may be configured to determine a translation function dependent on mappings in one or more translation tables. The computer system may be configured to reorganize a memory, to reorganize one or more translation tables, or to allocate different blocks of memory to an application prior to determining a translation function. Different applications or threads executing on the computer system may employ different translation functions. Different regions of memory may be accessed using different translation functions. Some virtual addresses may be translated using a function while others may be translated using one or more translation table look-ups.

    摘要翻译: 采用存储器虚拟化的计算机系统可以采用基于功能的虚拟到物理地址转换技术。 基于函数的翻译技术可以包括用一个函数来替换一个通用陷阱处理程序和一个或多个翻译表查找,以从给定的虚拟地址计算对应的物理地址。 计算机系统可以被配置为根据一个或多个翻译表中的映射来确定翻译函数。 计算机系统可以被配置为在确定翻译功能之前重新组织存储器,重新组织一个或多个转换表,或者将不同的存储器块分配给应用。 在计算机系统上执行的不同应用或线程可以采用不同的翻译功能。 可以使用不同的翻译功能访问不同的存储器区域。 可以使用功能翻译一些虚拟地址,而可以使用一个或多个翻译表查找来翻译其他虚拟地址。

    Dynamic composition of an execution environment from multiple immutable file system images
    10.
    发明授权
    Dynamic composition of an execution environment from multiple immutable file system images 有权
    从多个不可变文件系统映像动态组合执行环境

    公开(公告)号:US07805409B2

    公开(公告)日:2010-09-28

    申请号:US12035132

    申请日:2008-02-21

    IPC分类号: G06F17/30

    CPC分类号: G06F17/30233

    摘要: A virtual file system is formed configured to enable the dynamic composition of immutable file system images. A file system containing a software distribution is divided into a plurality of mutually exclusive sub-trees. Each sub-tree includes a portion of the software distribution. An immutable file system image is formed for each sub-tree. During the booting of an operating system, a virtualization engine intercedes in the boot process to mount the immutable file system images to independent directories of the root file system. Upon request the virtualization engine, during run-time, combines virtual entries corresponding to immutable file system images so as to resemble the original software distribution.

    摘要翻译: 形成虚拟文件系统,其被配置为使能不可变文件系统图像的动态组合。 包含软件分发的文件系统被分成多个相互排斥的子树。 每个子树包括软件分发的一部分。 为每个子树形成一个不可变的文件系统映像。 在启动操作系统期间,虚拟化引擎在启动过程中进行了介入,以将不可变文件系统映像安装到根文件系统的独立目录中。 根据请求,虚拟化引擎在运行期间组合对应于不变文件系统映像的虚拟条目,以类似于原始软件分发。