公开(公告)号：US20140052826A1

公开(公告)日：2014-02-20

申请号：US13969980

申请日：2013-08-19

Applicant: International Business Machines Corporation

Inventor： Masahiro Ohkawa

IPC: H04L29/08

CPC classification number: H04L67/02 ,  G06F11/1443 ,  G06F11/1471 ,  G06F11/20 ,  G06F11/2023 ,  G06F11/2035 ,  G06F11/2046 ,  G06F2201/80 ,  G06F2201/82 ,  G06F2201/825 ,  H04L69/40

Abstract: Embodiments relate to a method, system and program product for performing data processing. The system includes a plurality of computer servers configured to perform data processing, a client in processing communication with the computer servers and enabled to request data processing from any of the servers and a storing component included in the client for storing information relating to requested data to be processed. A processing component included in each computer server for applying a control lock to data being processed. A reprocessing request component is included in the client for enabling a new server to take over processing of requested data upon failure of previously processing computer server. The computer server obtains information relating to requested data from storing component and information relating to control lock information from the processing component such that the new computer server commences processing at a processing point exactly prior to the failure.

Abstract translation: 实施例涉及用于执行数据处理的方法，系统和程序产品。 该系统包括被配置为执行数据处理的多个计算机服务器，客户端处理与计算机服务器的通信并且能够从任何服务器请求数据处理，以及包括在客户机中的存储组件，用于存储与所请求的数据有关的信息 被处理。 包括在每个计算机服务器中的处理组件，用于将控制锁应用于正在处理的数据。 客户端中包含重新处理请求组件，以使新服务器在先前处理计算机服务器故障时能够接管所请求数据的处理。 计算机服务器从存储组件获取与所请求的数据有关的信息以及与来自处理组件的控制锁定信息相关的信息，使得新的计算机服务器在故障之前的处理点处开始处理。

公开(公告)号：US20130227332A1

公开(公告)日：2013-08-29

申请号：US13408045

申请日：2012-02-29

Applicant: SHANE ROBERT VERMETTE ,  Amrit Mishra ,  Vijay Manguluru ,  Ajit Kumar Das

Inventor： SHANE ROBERT VERMETTE ,  Amrit Mishra ,  Vijay Manguluru ,  Ajit Kumar Das

IPC: G06F11/00

CPC classification number: G06Q10/063114 ,  G06F9/466 ,  G06F11/1402 ,  G06F11/1438 ,  G06F17/30359 ,  G06F2201/825

Abstract: Embodiments of the invention provide systems and methods for recovering a failed data summarization. According to one embodiment, recovering a failed instance can comprise processing existing summarization instances identified as instances for which a new data summarization instance needs to wait. Upon a completion or a timeout of each of the instances identified as instances for which the new data summarization instance needs to wait, an exclusive lock can be acquired on a table storing scope information for the plurality of data summarization instances. One or more existing data summarization instances that match the new data summarization instance or that have an overlapping scope with the new data summarization instance can be processed, remaining tasks to be performed by the new data summarization instance can be defined, the exclusive lock can be released, and the remaining tasks to be performed by the new data summarization instance can be performed.

Abstract translation: 本发明的实施例提供了用于恢复故障数据摘要的系统和方法。 根据一个实施例，恢复失败的实例可以包括处理被识别为新数据摘要实例需要等待的实例的现有摘要实例。 在被识别为新数据汇总实例需要等待的实例的每个实例的完成或超时时，可以在存储用于多个数据汇总实例的范围信息的表上获取排他锁。 可以处理与新数据汇总实例匹配的一个或多个现有数据汇总实例，或与新数据汇总实例具有重叠作用域的一个或多个现有数据汇总实例，可以定义由新数据汇总实例执行的剩余任务，独占锁可以 释放，并且可以执行由新数据汇总实例执行的剩余任务。

公开(公告)号：US08499299B1

公开(公告)日：2013-07-30

申请号：US12825932

申请日：2010-06-29

Applicant: Arpad Jakab ,  Humberto Yeverino ,  Suman Cherukuri ,  Jeffrey Daudel ,  Jonathan Lindo

Inventor： Arpad Jakab ,  Humberto Yeverino ,  Suman Cherukuri ,  Jeffrey Daudel ,  Jonathan Lindo

IPC: G06F9/455 ,  G06F9/46 ,  G06F11/00 ,  G06F9/44 ,  G06F13/22 ,  G06F12/00

CPC classification number: G06F11/3404 ,  G06F9/45504 ,  G06F11/3476 ,  G06F2201/815 ,  G06F2201/825

Abstract: Techniques for ensuring deterministic thread context switching in a virtual machine application program include, in one embodiment, providing a single application-level mutex that threads of the executing application program are forced to acquire to execute application code of the virtual machine application program. During a first recorded execution of the virtual machine application program, a record is created and stored in a computer that indicates the order in which threads acquire the application-level mutex. In a subsequent replay execution of the virtual machine application program from the recording, threads of the virtual machine application program are managed to ensure that the application-level mutex is acquired by threads in the same order indicated in the record such that any race conditions that occurred during the recorded execution as a result of executing application code are reproduced during the subsequent replay execution thereby aiding application development personnel in identifying and isolating program errors and bugs related to race conditions.

Abstract translation: 在一个实施例中，用于确保虚拟机应用程序中的确定性线程上下文切换的技术包括提供单个应用级互斥体，所述执行应用程序的线程被强制获取以执行虚拟机应用程序的应用代码。 在虚拟机应用程序的第一次记录执行期间，创建记录并存储在指示线程获取应用级互斥体的顺序的计算机中。 在从记录的虚拟机应用程序的后续重放执行中，管理虚拟机应用程序的线程以确保应用级互斥体以与记录中指示的相同顺序的线程获取，使得任何竞争条件 在执行应用程序代码的结果期间发生的记录执行期间在随后的重放执行期间被再现，从而帮助应用程序开发人员识别和隔离与竞争条件相关的程序错误和错误。

公开(公告)号：US20130174165A1

公开(公告)日：2013-07-04

申请号：US13340431

申请日：2011-12-29

Applicant: Rajat Chopra

Inventor： Rajat Chopra

IPC: G06F9/46

CPC classification number: G06F9/526 ,  G06F11/0757 ,  G06F11/1438 ,  G06F11/1482 ,  G06F17/30362 ,  G06F2201/825 ,  G06F2209/522

Abstract: A lock manager running on a machine may write a first entry for a first process to a queue associated with a resource. If the first entry is not at a front of the queue, the lock manager identifies a second entry that is at the front of the queue, and determines whether a second process associated with the second entry is operational. If the second process is not operational, the lock manager removes the second entry from the queue. Additionally, if the queue becomes unavailable, the lock manager may initiate failover to a backup copy of the queue.

Abstract translation: 在机器上运行的锁管理器可以将第一进程的第一条目写入与资源相关联的队列。 如果第一个条目不在队列的前面，则锁管理器识别位于队列前面的第二个条目，并确定与第二个条目关联的第二个进程是否可操作。 如果第二个进程不可操作，则锁管理器将从队列中删除第二个条目。 另外，如果队列变得不可用，则锁管理器可能会启动故障转移到队列的备份副本。

公开(公告)号：US20130073532A1

公开(公告)日：2013-03-21

申请号：US13239326

申请日：2011-09-21

Applicant: Yariv BACHAR ,  Ron EDELSTEIN ,  Ehud MEIRI

Inventor： Yariv BACHAR ,  Ron EDELSTEIN ,  Ehud MEIRI

IPC: G06F17/30

CPC classification number: G06F11/1461 ,  G06F7/32 ,  G06F9/52 ,  G06F11/3476 ,  G06F17/30008 ,  G06F17/30067 ,  G06F17/30286 ,  G06F2201/825

Abstract: A plurality of log processes are synchronized. Each is independently performed in parallel with one another, into a single set of log files. A line buffering mechanism of an operating system (OS) of the computing environment forecloses interleaving of the log processes. Log management operations are concurrently performed by a single process protected by a file-system lock of the OS. The log management operations include at least one of a log compression, log retention, and log rotation operation.

Abstract translation: 多个日志进程同步。 每个都是独立执行的，彼此并行，成一组日志文件。 计算环境的操作系统（OS）的行缓冲机制抵消了日志进程的交错。 日志管理操作由被操作系统的文件系统锁定保护的单个进程同时执行。 日志管理操作包括日志压缩，日志保持和日志旋转操作中的至少一个。

公开(公告)号：US08127175B2

公开(公告)日：2012-02-28

申请号：US11723274

申请日：2007-03-19

Applicant: Paul Parkinson

Inventor： Paul Parkinson

IPC: G06F11/00

CPC classification number: G06F11/1482 ,  G06F11/1474 ,  G06F11/203 ,  G06F11/2035 ,  G06F2201/825

Abstract: Recovery of inflowed transactions are provided by any instance in a cluster, along with peer recovery of transactions in a cluster, and administrative functionality related to these aspects. A method of managing transaction processing comprises performing transaction processing using a first process, wherein the first process logs the transaction processing that it performs, detecting failure of the first process, wherein the transaction logs of the first process are locked, taking ownership of the locked transaction logs of the first process at a second process, unlocking the locked transaction logs of the first process for use by the second process, and recovering at least one transaction using the transaction logs.

Abstract translation: 流入交易的恢复由群集中的任何实例提供，以及群集中事务的对等恢复以及与这些方面相关的管理功能。 管理事务处理的方法包括使用第一进程执行事务处理，其中第一进程记录其执行的事务处理，检测第一进程的故障，其中第一进程的事务日志被锁定，获取锁定的所有权 在第二进程处的第一进程的事务日志，解锁第一进程的锁定的事务日志以供第二进程使用，以及使用事务日志恢复至少一个事务。

公开(公告)号：US08112452B2

公开(公告)日：2012-02-07

申请号：US12361678

申请日：2009-01-29

Applicant: Atul Adya ,  Gerald Cermak ,  John R. Douceur ,  Marvin M. Theimer ,  Roger P. Wattenhofer ,  William J. Bolosky

Inventor： Atul Adya ,  Gerald Cermak ,  John R. Douceur ,  Marvin M. Theimer ,  Roger P. Wattenhofer ,  William J. Bolosky

IPC: G06F7/00 ,  G06F17/30 ,  G06F12/00

CPC classification number: G06F17/30094 ,  G06F17/30171 ,  G06F17/30899 ,  G06F2201/825 ,  H04L63/0823 ,  H04L63/123 ,  Y10S707/956 ,  Y10S707/99931 ,  Y10S707/99938

Abstract: A serverless distributed file system manages the storage of files and directories using one or more directory groups. The directories may be managed using Byzantine-fault-tolerant groups, whereas files are managed without using Byzantine-fault-tolerant groups. Additionally, the file system may employ a hierarchical namespace to store files. Furthermore, the directory group may employ a plurality of locks to control access to objects (e.g., files and directories) in each directory.

Abstract translation: 无服务器分布式文件系统使用一个或多个目录组来管理文件和目录的存储。 可以使用拜占庭容错组来管理目录，而不使用拜占庭容错组来管理文件。 此外，文件系统可以使用分层命名空间来存储文件。 此外，目录组可以使用多个锁来控制对每个目录中的对象（例如，文件和目录）的访问。

公开(公告)号：US20110264876A1

公开(公告)日：2011-10-27

申请号：US12526662

申请日：2009-03-19

Applicant: Keiichi Kaiya ,  Toru Suzuki

Inventor： Keiichi Kaiya ,  Toru Suzuki

IPC: G06F12/16

CPC classification number: G06F3/0665 ,  G06F3/0617 ,  G06F3/0619 ,  G06F3/065 ,  G06F3/067 ,  G06F11/1658 ,  G06F12/0804 ,  G06F12/0866 ,  G06F2201/825 ,  G06F2212/284

Abstract: A storage system 1 includes a first storage apparatus 100 and a second storage apparatus 100 communicatively coupled to an external apparatus 300. The first and second storage apparatuses respectively have first and second storage areas VDEVs selectively accessible from the external apparatus, first and second temporary storage areas 113, and remote copy controllers 1122 configured to control data copy process. The storage system includes a data I/O process authority information storage unit LDK storing data I/O process authority information. Either of the remote copy controllers reads the data I/O process authority information and copies according to the data I/O process authority information, to the other storage apparatus, data stored either in the first storage area and the first temporary storage area, or in the second storage area and the second temporary storage area that are included in the storage apparatus to which the remote copy controller belongs.

Abstract translation: 存储系统1包括通信地耦合到外部设备300的第一存储设备100和第二存储设备100.第一和第二存储设备分别具有可从外部设备选择性地访问的第一和第二存储区域VDEV，第一和第二临时存储 区域113和被配置为控制数据复制处理的远程复制控制器1122。 存储系统包括存储数据I / O处理权限信息的数据I / O处理权限信息存储单元LDK。 远程复制控制器中的任一个读取数据I / O处理权限信息并根据数据I / O处理权限信息复制到另一存储装置，存储在第一存储区域和第一临时存储区域中的数据，或 在包括在远程复制控制器所属的存储装置中的第二存储区域和第二临时存储区域中。

公开(公告)号：US20110214024A1

公开(公告)日：2011-09-01

申请号：US12713970

申请日：2010-02-26

Applicant: Loc D. Tran ,  Gary B. Genest ,  Dale J. Stroyick

Inventor： Loc D. Tran ,  Gary B. Genest ,  Dale J. Stroyick

IPC: G06F11/32

CPC classification number: G06F11/32 ,  G06F9/524 ,  G06F11/3476 ,  G06F2201/825

Abstract: A technique for collecting and correlating locking data collects and correlates information on a plurality of programs waiting on or holding a plurality of resources in a multi-computer database system. The technique identifies a program executing on one computer of the multi-computer database system that is waiting on a resource. The technique also identifies a second program, executing on another computer, as the ultimate holder of the resource. An operator display screen displays information corresponding to the first program and the second program. The operator display screen may be switched between a multiline display format and a single line display format. The collection, identification, and display of the locking data is performed periodically, to allow the operator to discover locking problems and take a desired corrective action.

Abstract translation: 用于收集和关联锁定数据的技术收集并关联在多计算机数据库系统中等待或保持多个资源的多个节目上的信息。 该技术标识在等待资源的多计算机数据库系统的一台计算机上执行的程序。 该技术还标识了第二个程序，在另一台计算机上执行，作为资源的最终持有者。 操作者显示画面显示与第一程序和第二程序对应的信息。 操作者显示画面可以在多行显示格式和单行显示格式之间切换。 周期性地执行锁定数据的收集，识别和显示，以允许操作者发现锁定问题并采取所需的纠正措施。

公开(公告)号：US07814065B2

公开(公告)日：2010-10-12

申请号：US11205529

申请日：2005-08-16

Applicant: Wilson Wai Shun Chan ,  Angelo Pruscino ,  Stefan Roesch ,  Michael Zoll ,  Tolga Yurek

Inventor： Wilson Wai Shun Chan ,  Angelo Pruscino ,  Stefan Roesch ,  Michael Zoll ,  Tolga Yurek

IPC: G06F17/30

CPC classification number: G06F11/2046 ,  G06F11/203 ,  G06F11/2033 ,  G06F11/2035 ,  G06F11/30 ,  G06F2201/825 ,  Y10S707/99939 ,  Y10S707/99942 ,  Y10S707/99953

Abstract: Techniques are provided for responding to the termination of a node by selecting another node, and assigning to the selected node the affinity relationships that existed between the terminated node and one or more objects. The resources that belong to the objects involved in the affinity relationships are remastered to the selected node. The selected node then performs recovery of the resources that had been opened by the terminated node and/or serves as a failover node to execute the transactions that had been executing on the terminated node.

Abstract translation: 提供了通过选择另一个节点来响应终止节点的技术，并且向所选节点分配存在于终止的节点与一个或多个对象之间的亲和度关系。 属于与亲和力关系相关的对象的资源将重新分配给所选节点。 所选择的节点然后执行已被终止的节点打开的资源的恢复和/或用作故障切换节点来执行在终止的节点上执行的事务。