公开(公告)号：US20140373028A1

公开(公告)日：2014-12-18

申请号：US13920524

申请日：2013-06-18

Applicant: Advanced Micro Devices, Inc.

Inventor： Alexander Lyashevsky ,  Sudhanva Gurumurthi ,  Vilas Sridharan

IPC: G06F9/52

CPC classification number: G06F11/00 ,  G06F9/3851 ,  G06F9/52 ,  G06F11/1608 ,  G06F11/1633 ,  G06F11/1637 ,  G06F11/1654 ,  G06F11/1687 ,  G06F11/202 ,  G06F11/2038 ,  G06F11/2041 ,  G06F11/2048 ,  G06F2201/825 ,  G06F2201/83

Abstract: A system, method and computer program product to execute a first and a second work-group, and compare the signature variables of the first work-group to the signature variables of the second work-group via a synchronization mechanism. The first and the second work-group are mapped to an identifier via software. This mapping ensures that the first and second work-groups execute exactly the same data for exactly the same code without changes to the underlying hardware. By executing the first and second work-groups independently, the underlying computation of the first and second work-groups can be verified. Moreover, system performance is not substantially affected because the execution results of the first and second work-groups are compared only at specified comparison points.

Abstract translation: 一种用于执行第一和第二工作组的系统，方法和计算机程序产品，并且经由同步机制将第一工作组的签名变量与第二工作组的签名变量进行比较。 第一个和第二个工作组通过软件映射到一个标识符。 此映射确保第一个和第二个工作组对完全相同的代码执行完全相同的数据，而不会更改底层硬件。 通过独立地执行第一和第二工作组，可以验证第一和第二工作组的基础计算。 此外，由于第一和第二工作组的执行结果仅在指定的比较点进行比较，系统性能基本上不受影响。

公开(公告)号：US08869149B2

公开(公告)日：2014-10-21

申请号：US13627317

申请日：2012-09-26

Applicant: International Business Machines Corporation

Inventor： Parijat Dube ,  Xiaoqiao Meng ,  Jian Tan ,  Li Zhang

IPC: G06F9/46

CPC classification number: G06F9/50 ,  G06F11/3404 ,  G06F11/3442 ,  G06F11/3476 ,  G06F2201/815 ,  G06F2201/825 ,  G06F2201/835 ,  G06F2209/504 ,  G06F2209/508 ,  Y02D10/22

Abstract: A system and method may be utilized to identify concurrency levels of processing stages in a distributed system, identify common resources and bottlenecks in the distributed system using the identified concurrency levels, and allocate resources in the distributed system using the identified concurrency levels.

公开(公告)号：US08868530B1

公开(公告)日：2014-10-21

申请号：US13550470

申请日：2012-07-16

Applicant: Omprakaash Thoppal ,  William A. Zumach

Inventor： Omprakaash Thoppal ,  William A. Zumach

IPC: G06F17/00

CPC classification number: G06F11/2092 ,  G06F3/0622 ,  G06F3/0637 ,  G06F3/067 ,  G06F11/1662 ,  G06F11/2097 ,  G06F2201/825

Abstract: Machine implemented method and system for a networked storage system having a first storage system node providing storage space to a client computing system at a first storage device and a second storage system node managing a second storage device are provided. A lock is granted by the first storage system node to the client computing system for accessing a data container stored at the first storage device. The first storage system node updates a lock data structure for managing the lock granted to the client computing system. Information regarding the lock is then replicated at the second storage system node, such that the second storage system node can recover the lock, when the first storage system node becomes unavailable and the second storage system node takes over the first storage device to interface with the client computing system.

Abstract translation: 提供了一种具有第一存储系统节点的网络存储系统的机器实现方法和系统，所述第一存储系统节点向第一存储设备处的客户端计算系统和管理第二存储设备的第二存储系统节点提供存储空间。 第一存储系统节点将锁定授予客户端计算系统，以访问存储在第一存储设备中的数据容器。 第一存储系统节点更新用于管理授予客户端计算系统的锁的锁定数据结构。 然后在第二存储系统节点处复制关于锁的信息，使得当第一存储系统节点变得不可用并且第二存储系统节点接管第一存储设备以与第二存储系统节点接口时，第二存储系统节点可以恢复锁定 客户端计算系统。

公开(公告)号：US08819059B2

公开(公告)日：2014-08-26

申请号：US13488150

申请日：2012-06-04

Applicant: Lior Aronovich ,  Asaf Levy ,  Liran Loya

Inventor： Lior Aronovich ,  Asaf Levy ,  Liran Loya

IPC: G06F7/00 ,  G06F17/30

CPC classification number: G06F11/2007 ,  G06F3/121 ,  G06F9/3863 ,  G06F9/526 ,  G06F11/1435 ,  G06F11/1471 ,  G06F11/1658 ,  G06F11/1666 ,  G06F11/2023 ,  G06F11/2043 ,  G06F11/2094 ,  G06F12/0813 ,  G06F17/30076 ,  G06F17/30312 ,  G06F2201/82 ,  G06F2201/825 ,  G06F2201/84 ,  G06F2209/523 ,  H04L67/1097

Abstract: In one exemplary embodiment, a DSM is used to store the data structures in a cluster shared memory, such that updates, deletions and insertions are applied to both the persistent data set and the DSM, and search, list and retrieval operations are processed directly from the DSM. A data structure in the persistent data set is stored in two separate DSM pages: a first page includes an identifying search key of the data structure, the search key also pointing to a location of the data structure in the storage. A second page includes the updatable properties of the data structure. A DSM storing the data structures' pages is organized as a two-row matrix.

Abstract translation: 在一个示例性实施例中，DSM用于将数据结构存储在群集共享存储器中，使得更新，删除和插入被应用于持久数据集和DSM两者，并且搜索，列表和检索操作直接从 帝斯曼 持久数据集中的数据结构存储在两个单独的DSM页面中：第一页包括数据结构的识别搜索关键字，搜索关键字还指向存储器中的数据结构的位置。 第二页包括数据结构的可更新属性。 存储数据结构页面的DSM被组织为两行矩阵。

公开(公告)号：US08813042B2

公开(公告)日：2014-08-19

申请号：US13441656

申请日：2012-04-06

Applicant: Dhruva Chakrabarti

Inventor： Dhruva Chakrabarti

IPC: G06F9/44

CPC classification number: G06F11/1438 ,  G06F2201/825

Abstract: In a method of identifying a globally consistent state in a multithreaded program, a plurality of locally consistent states is identified, in which a locally consistent state of a thread comprises a set of memory locations and their corresponding data values accessed between points in the multithreaded program where no locks are held. Globally consistent states are identified based at least in part on the locally consistent states.

Abstract translation: 在识别多线程程序中的全局一致状态的方法中，识别多个本地一致状态，其中线程的本地一致状态包括在多线程程序中的点之间访问的一组存储器位置及其对应的数据值 哪里没有锁。 至少部分地基于局部一致的状态来识别全局一致的状态。

公开(公告)号：US08762929B2

公开(公告)日：2014-06-24

申请号：US12970625

申请日：2010-12-16

Applicant: Volker Driesen

Inventor： Volker Driesen

IPC: G06F9/44

CPC classification number: G06F11/0718 ,  G06F8/60 ,  G06F8/70 ,  G06F11/004 ,  G06F11/0754 ,  G06F2201/825

Abstract: The present disclosure involves systems, products, and methods for excluding inconsistent objects from lifecycle management processing. One method includes operations for identifying a set of objects in a system, at least a subset of the set of objects associated with a lifecycle management process; prior to performing the lifecycle management process, determining a consistency status for each object in the subset of objects associated with the lifecycle management process; and performing the lifecycle management process, wherein performing the lifecycle management process includes executing at least one lifecycle management operation on each object in the set of objects determined to be consistent within the system prior to performing the lifecycle management process. In some instances, performing the lifecycle management process may include skipping the execution of the at least one lifecycle management operation for each inconsistent object during the lifecycle management process.

Abstract translation: 本公开涉及从生命周期管理处理中排除不一致对象的系统，产品和方法。 一种方法包括用于识别系统中的一组对象的操作，与生命周期管理过程相关联的对象集合中的至少一个子集; 在执行生命周期管理过程之前，确定与生命周期管理过程相关联的对象子集中的每个对象的一致性状态; 以及执行所述生命周期管理过程，其中执行所述生命周期管理过程包括对在执行所述生命周期管理过程之前被确定为在系统内一致的对象集合中的每个对象执行至少一个生命周期管理操作。 在某些情况下，执行生命周期管理过程可以包括在生命周期管理过程期间跳过针对每个不一致对象的至少一个生命周期管理操作的执行。

公开(公告)号：US08533171B2

公开(公告)日：2013-09-10

申请号：US13083465

申请日：2011-04-08

Applicant: Kedar Patwardhan

Inventor： Kedar Patwardhan

IPC: G06F7/00 ,  G06F17/00

CPC classification number: G06F17/30171 ,  G06F11/203 ,  G06F11/2038 ,  G06F11/2043 ,  G06F17/30203 ,  G06F2201/825

Abstract: A method for file lock recovery in a distributed computer system. The method includes executing a distributed computer system having a plurality of nodes comprising a cluster, and initiating a network file system server fail over from one node of the cluster to an adoptive node of the cluster. File lock services are then stopped at the adoptive node. File lock services are subsequently restarted at the adoptive node, wherein the restart causes the adoptive node to commence a grace period for other network file system clients to connect to the adoptive node and reclaim file locks. After restarting file lock services, a cluster file system is updated on the adoptive node with process identifiers, and file lock services are resumed at the adoptive node. The cluster file system can be simultaneously exposing the file lock services to other clients as well, like CIFS, etc.

Abstract translation: 一种在分布式计算机系统中进行文件锁恢复的方法。 该方法包括执行具有包括集群的多个节点的分布式计算机系统，以及启动从集群的一个节点到集群的收养节点的网络文件系统服务器故障切换。 文件锁服务然后在收养节点停止。 文件锁服务随后在收养节点重新启动，其中重新启动使得收养节点开始其他网络文件系统客户端连接到收养节点并回收文件锁的宽限期。 在重新启动文件锁定服务后，在采用进程标识符的收养节点上更新集群文件系统，并在收养节点恢复文件锁定服务。 群集文件系统可以同时将文件锁定服务暴露给其他客户端，如CIFS等。

公开(公告)号：US20120143836A1

公开(公告)日：2012-06-07

申请号：US12957937

申请日：2010-12-01

Applicant: ERIC P. FRIED ,  Rajeev Mishra ,  Lance W. Russell ,  Murali Vaddagiri

Inventor： ERIC P. FRIED ,  Rajeev Mishra ,  Lance W. Russell ,  Murali Vaddagiri

IPC: G06F17/30

CPC classification number: G06F11/1004 ,  G06F11/1425 ,  G06F11/1482 ,  G06F11/202 ,  G06F11/2046 ,  G06F2201/825

Abstract: According to a method of access to a shared data record subject to contemporaneous read and write access by multiple requesters, a requester reads a shared data record including a payload and a first checksum. The requester calculates a second checksum of the payload of the data record. If the first and second checksums are not equal, the requester again reads the shared data record, including a third checksum, and calculates a fourth checksum of the payload of the shared data record. If the third and fourth checksums are equal, the requester processes the shared data record as valid, and if the second and fourth checksums are equal, the requester handles the shared data record as corrupt.

公开(公告)号：US20110271069A1

公开(公告)日：2011-11-03

申请号：US12770577

申请日：2010-04-29

Applicant: Sarin Sumit Manmohan ,  Manav Laxmikant Deshmukh

Inventor： Sarin Sumit Manmohan ,  Manav Laxmikant Deshmukh

IPC: G06F12/14

CPC classification number: G06F11/2028 ,  G06F11/2038 ,  G06F11/2046 ,  G06F2201/825

Abstract: In response to an instruction to dismount a storage volume, for example, an object in the storage volume is identified and a handle that references the object is closed. Once an exclusive lock on the storage volume is acquired, the storage volume can be dismounted. The storage volume can then remounted.

Abstract translation: 响应于卸载存储卷的指令，例如，存储卷中的对象被识别，并且引用对象的句柄被关闭。 一旦获取了存储卷上的排他锁，就可以卸下存储卷。 然后可以重新安装存储卷。

公开(公告)号：US08037013B2

公开(公告)日：2011-10-11

申请号：US12802072

申请日：2010-05-27

Applicant: Mandavilli Navneeth Rao

Inventor： Mandavilli Navneeth Rao

IPC: G06F17/30

CPC classification number: G06F11/1471 ,  G06F2201/82 ,  G06F2201/825

Abstract: Locking allocated data space is disclosed. An indication is received that certain previous version data is required to be retained. A map of metadata records, each associated with a journaling process write of previous version data which write includes previous version data required to be retained, is built. In some embodiments, the map associates a write time with each record in the map. A reclamation process checks to determine whether any storage proposed to be reclaimed is included in the map of record identifiers. In some embodiments, the determination is made based at least in part on the write time associated in the map with at least a first record identifier in time-sorted order.

Abstract translation: 公开了锁定分配的数据空间。 接收到需要保留某些先前版本数据的指示。 元数据记录的映射，每个与日志记录过程相关联的记录的先前版本数据的写入包括需要保留的先前版本的数据。 在一些实施例中，地图将写入时间与地图中的每个记录相关联。 回收过程检查以确定建议要回收的任何存储是否包括在记录标识符的映射中。 在一些实施例中，至少部分地基于在地图中与至少第一记录标识符以时间排序的顺序相关联的写入时间进行确定。