利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

45 条记录 (耗时 0.025 秒)

    Addressing node failure during a hyperswap operation
    2.
    发明授权
    Addressing node failure during a hyperswap operation 失效
    在超级交换操作期间寻址节点故障

    公开(公告)号：US08161142B2

    公开(公告)日：2012-04-17

    申请号：US12605758

    申请日：2009-10-26

    申请人： Ahmed Mohammad Bashir ,  Prasenjit Sarkar ,  Soumitra Sarkar ,  Mark James Seaman

    发明人： Ahmed Mohammad Bashir ,  Prasenjit Sarkar ,  Soumitra Sarkar ,  Mark James Seaman

    IPC分类号： G06F15/177

    CPC分类号： G06F11/1417 ,  G06F11/2046 ,  G06F11/2056

    摘要： A method, system, and article are provided to enable a Hyperswap operation in a clustered computer system. Each node in the system is configured with flash memory, with a hierarchical list of boot volumes therein. Following a Hyperswap operation, the current boot volume is communicated to each node in the cluster and each node joining the cluster. All previously inactive nodes that were booted from the improper boot volume are re-booted from the correct and the flash memory is amended to reflect the correct boot volume.

    摘要翻译： 提供了一种方法，系统和文章来实现群集计算机系统中的Hyperswap操作。 系统中的每个节点配置有闪存，其中包含引导卷的分层列表。 在Hyperswap操作之后，当前引导卷被传送到集群中的每个节点，并且每个节点加入集群。 从不正确的引导卷引导的所有以前不活动的节点从正确的重新引导，并且闪存被修改以反映正确的引导卷。

    INFORMATION THEORY BASED RESULT MERGING FOR SEARCHING HIERARCHICAL ENTITIES ACROSS HETEROGENEOUS DATA SOURCES
    3.
    发明申请
    INFORMATION THEORY BASED RESULT MERGING FOR SEARCHING HIERARCHICAL ENTITIES ACROSS HETEROGENEOUS DATA SOURCES 失效
    基于异构数据源搜索分层实体的信息理论结果合并

    公开(公告)号：US20110082859A1

    公开(公告)日：2011-04-07

    申请号：US12575210

    申请日：2009-10-07

    申请人： Yu Deng ,  Murthy V. Devarakonda ,  Rafah A. Hosn ,  Ruchi Mahindru ,  Nithya Rajamani ,  Soumitra Sarkar

    发明人： Yu Deng ,  Murthy V. Devarakonda ,  Rafah A. Hosn ,  Ruchi Mahindru ,  Nithya Rajamani ,  Soumitra Sarkar

    IPC分类号： G06F17/30

    CPC分类号： G06F17/3053 ,  G06F17/30451 ,  G06F17/30598 ,  G06F17/30867 ,  G06F17/30941

    摘要： A method, system, and computer program product are disclosed for merging search results. In one embodiment, the method comprises identifying a query, splitting the query into sub-queries, and calculating information content for each of the sub-queries. This method also comprises executing each of the sub-queries to obtain a plurality of search results, and combining the search results based on the information content calculated for the sub-queries. In an embodiment, the execution of each of the sub-queries includes identifying a multitude of search results for at least one of the sub-queries; and the combining includes grouping said multitude of search results into a plurality of clusters, and computing a relevance score for each of said clusters. In the embodiment the combining further includes merging the clusters based on the relevance scores computed for the clusters as well as the information content calculated for the sub-queries.

    摘要翻译： 公开了一种用于合并搜索结果的方法，系统和计算机程序产品。 在一个实施例中，该方法包括识别查询，将查询分割成子查询，以及计算每个子查询的信息内容。 该方法还包括执行每个子查询以获得多个搜索结果，并且基于为子查询计算的信息内容来组合搜索结果。 在一个实施例中，每个子查询的执行包括识别至少一个子查询的大量搜索结果; 并且所述组合包括将所述多个搜索结果分组为多个群集，以及计算每个所述群集的相关性得分。 在该实施例中，组合还包括基于针对集群计算的相关性分数以及为子查询计算的信息内容来合并集群。

    DETECTING MISSING ELEMENTS IN A STORAGE AREA NETWORK WITH MULTIPLE SOURCES OF INFORMATION
    4.
    发明申请
    DETECTING MISSING ELEMENTS IN A STORAGE AREA NETWORK WITH MULTIPLE SOURCES OF INFORMATION 失效
    在具有多种信息来源的存储区域网络中检测丢失的元素

    公开(公告)号：US20080059599A1

    公开(公告)日：2008-03-06

    申请号：US11470580

    申请日：2006-09-06

    申请人： Ashmi A. Chokshi ,  Glen Hattrup ,  David L. Merbach ,  Prasenjit Sarkar ,  Soumitra Sarkar

    发明人： Ashmi A. Chokshi ,  Glen Hattrup ,  David L. Merbach ,  Prasenjit Sarkar ,  Soumitra Sarkar

    IPC分类号： G06F15/167 ,  G06F15/16

    CPC分类号： H04L67/1097 ,  H04L41/046 ,  H04L41/12 ,  H04L41/22

    摘要： A detectibility service for a storage infrastructure manager (SIM) operating on a storage area network (SAN) is disclosed directed to addressing a situation where there may be multiple sources of duplicate or contradictory information to the SIM about the presence and condition of an element in the SAN. The service can account for both authoritative as well as nonauthoritative sources of information in a SAN, which participate in the discovery process scanning for SAN elements. Both authoritative and nonauthoritative sources of information can be used to report a given SAN element during a probe, taking advantage of the more efficient processing of information from authoritative sources to override information from nonauthoritative sources regardless of the order in which the various scans may occur.

    摘要翻译： 公开了一种在存储区域网络（SAN）上运行的存储基础架构管理器（SIM）的可检测性服务，用于解决可能存在SIM的多个重复或矛盾信息源的情况，该信息有关于元素的存在和状况 SAN。 该服务可以解决参与发现过程扫描SAN元素的SAN中的权威性和非授权信息来源。 权威和非授权的信息来源可以用于在探测期间报告给定的SAN元素，利用从权威来源更有效地处理信息来覆盖来自非权威来源的信息，而不管可能发生各种扫描的顺序。

    Append/read lock compatibility in a distributed file system
    5.
    发明申请
    Append/read lock compatibility in a distributed file system 审中-公开
    在分布式文件系统中附加/读取锁兼容性

    公开(公告)号：US20060288008A1

    公开(公告)日：2006-12-21

    申请号：US11158225

    申请日：2005-06-21

    申请人： Sukadev Bhattiprolu ,  Craig Everhart ,  Venkateswarara Jujjuri ,  Soumitra Sarkar

    发明人： Sukadev Bhattiprolu ,  Craig Everhart ,  Venkateswarara Jujjuri ,  Soumitra Sarkar

    IPC分类号： G06F17/30

    CPC分类号： G06F16/1774

    摘要： Extensions are provided to a lock for supporting concurrency of read and write operations of a shared resource in a computer system. Both reader and writer modes are maintained. In addition, an append mode and a prefix mode are provided. The append mode supports non-exclusive access to the shared resource while enabling modification of the shared resource after a marker. The prefix mode supports non-exclusive access to read the shared resource prior to the marker. Lock mode requests to the shared resources are mediated to ensure compatibility of granted lock modes with lock mode requests.

    摘要翻译： 扩展被提供给用于支持计算机系统中的共享资源的读写操作的并发的锁。 读写器模式都保持不变。 此外，还提供了附加模式和前缀模式。 附加模式支持对共享资源的非独占访问，同时在标记之后修改共享资源。 前缀模式支持非独占访问，以在标记之前读取共享资源。 对共享资源的锁定模式请求是中介的，以确保授权的锁定模式与锁定模式请求的兼容性。

    Method for running existing java beans in an enterprise java bean environment
    6.
    发明授权
    Method for running existing java beans in an enterprise java bean environment 有权
    在企业java bean环境中运行现有的java bean的方法

    公开(公告)号：US06754659B2

    公开(公告)日：2004-06-22

    申请号：US09828755

    申请日：2001-04-09

    申请人： Soumitra Sarkar ,  Daniel J. Labrecque ,  Steven W. Pogue

    发明人： Soumitra Sarkar ,  Daniel J. Labrecque ,  Steven W. Pogue

    IPC分类号： G06F1730

    CPC分类号： G06F9/541 ,  Y10S707/99945

    摘要： A method and system for running application code originally developed as simple Java Beans, in an Enterprise Java Bean (EJB) environment, without modifying the original application code is described. This is accomplished by running one or more original Java beans in an EJB environment based on control from an external program, using at least the steps of defining a single generic EJB and installing the single generic EJB in an EJB container; generating EJB support code for each of the one or more original Java beans, and executing the EJB support code to drive the generic EJB to perform the functions of the one or more original Java beans in an EJB environment.

    摘要翻译： 描述了一种在企业Java Bean（EJB）环境中最初开发为简单Java Beans的应用程序代码的方法和系统，而不修改原始应用程序代码。 这通过在外部程序的控制下运行EJB环境中的一个或多个原始Java Bean来实现，至少使用定义单个通用EJB并在EJB容器中安装单个通用EJB的步骤; 为一个或多个原始Java Bean中的每一个生成EJB支持代码，以及执行EJB支持代码以驱动通用EJB来执行EJB环境中的一个或多个原始Java Bean的功能。

    Transport gateway between a native network and a mixed network
    7.
    发明授权
    Transport gateway between a native network and a mixed network 失效
    本地网络和混合网络之间的传输网关

    公开(公告)号：US5802053A

    公开(公告)日：1998-09-01

    申请号：US543252

    申请日：1995-10-13

    申请人： Gregory Bollella ,  Kathleen Marie Hogan ,  Vachaspathi Peter Kompella ,  Alisa Lynn Morse ,  Diane Phylis Pozefsky ,  Soumitra Sarkar

    发明人： Gregory Bollella ,  Kathleen Marie Hogan ,  Vachaspathi Peter Kompella ,  Alisa Lynn Morse ,  Diane Phylis Pozefsky ,  Soumitra Sarkar

    IPC分类号： H04L29/06 ,  H04L29/12 ,  H04L12/66

    CPC分类号： H04L61/106 ,  H04L29/06 ,  H04L69/08

    摘要： In order to more fully support the need to interconnect dissimilar networks, methods and apparatus are set forth which allow a transport gateway between a native (SNA/APPN) network and a mixed or non-native network to preserve the dynamic functions of the native network. The functions of fully dynamic directory and route selection are supported, in addition to the ability to use parallel gateways when connecting a native network to a mixed network. The ability to route information through a gateway from a dependent LU requester in a non-native network to a dependent LU server in a SNA/APPN network is also demonstrated. This allows concatenation of native and non-native networks while maintaining the addressability and accessibility of the native network.

    摘要翻译： 为了更全面地支持需要互连不同的网络，阐述了允许本地（SNA / APPN）网络和混合或非本地网络之间的传输网关来保护本地网络的动态功能的方法和装置 。 支持完全动态目录和路由选择的功能，除了在将本机网络连接到混合网络时使用并行网关的能力。 通过网关将信息从非本地网络中的从属LU请求器路由到SNA / APPN网络中的依赖LU服务器的能力也被证明。 这允许本地网络和非本地网络的并置，同时保持本地网络的可寻址性和可访问性。

    Remediating resource overload
    10.
    发明授权
    Remediating resource overload 有权
    修复资源超载

    公开(公告)号：US08839243B2

    公开(公告)日：2014-09-16

    申请号：US13453019

    申请日：2012-04-23

    申请人： Salman A. Baset ,  Rafah A. Hosn ,  Ruchi Mahindru ,  Harigovind V. Ramasamy ,  Soumitra Sarkar ,  Chunqiang Tang ,  Norbert G. Vogl ,  Long Wang

    发明人： Salman A. Baset ,  Rafah A. Hosn ,  Ruchi Mahindru ,  Harigovind V. Ramasamy ,  Soumitra Sarkar ,  Chunqiang Tang ,  Norbert G. Vogl ,  Long Wang

    IPC分类号： G06F9/455

    CPC分类号： G06F9/5083 ,  G06F9/485 ,  G06F9/4856

    摘要： A method, an apparatus and an article of manufacture for remediating overload in an over-committed computing environment. The method includes measuring resource usage of each of multiple virtual machines on each of at least one hypervisor in a computing environment, upon detection of a resource overload on one of the at least one hypervisor, determining at least one operation that is to be taken for at least one of the multiple virtual machines on the hypervisor to remediate resource overload while increasing values of running virtual machines, and sending a command to the hypervisor to issue the at least one operation.

    摘要翻译： 一种用于在过度承诺的计算环境中修复过载的方法，装置和制品。 该方法包括：在检测到所述至少一个虚拟机管理程序中的一个虚拟机管理程序上的资源超负荷时，在计算环境中测量至少一个虚拟机管理程序的每一个上的多个虚拟机中的每个虚拟机的资源使用情况，确定将要采用的至少一个操作 虚拟机管理程序中的多个虚拟机中的至少一个，用于在增加正在运行的虚拟机的值的同时修复资源过载，以及向管理程序发送命令以发出至少一个操作。