公开(公告)号：US20160196193A1

公开(公告)日：2016-07-07

申请号：US15070012

申请日：2016-03-15

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Michael Karl Gschwind ,  Valentina Salapura

IPC: G06F11/14 ,  G06F3/06

CPC classification number: G06F11/1474 ,  G06F3/0619 ,  G06F3/0629 ,  G06F3/0673 ,  G06F9/466 ,  G06F11/1407 ,  G06F11/1438 ,  G06F11/1451 ,  G06F13/24 ,  G06F2201/805 ,  G06F2201/825 ,  G06F2201/84

Abstract: Autonomous recovery from a transient hardware failure by executing portions of a stream of program instructions as a transaction. A start of a transaction is created in a stream of program instructions executing on a first processor of a multi-processor computer. A snapshot of a system state information is saved when the transaction begins. When the transaction ends, store data of the transaction is committed. If a transient hardware failure occurs, the transaction is aborted without notifying the computer software application that initiated the stream of program instructions. The transaction is re-executed on a second processor of the multi-processors, based on the saved snapshot of the system state information.

Abstract translation: 通过执行程序指令流的部分作为事务，从暂时的硬件故障中自动恢复。 在多处理器计算机的第一处理器上执行的程序指令流中创建事务的开始。 当事务开始时，将保存系统状态信息的快照。 当事务结束时，事务的存储数据被提交。 如果发生瞬态硬件故障，则事务中止，而不通知启动程序指令流的计算机软件应用程序。 基于保存的系统状态信息的快照，在多处理器的第二处理器上重新执行事务。

公开(公告)号：US20160196192A1

公开(公告)日：2016-07-07

申请号：US15070009

申请日：2016-03-15

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Michael Karl Gschwind ,  Valentina Salapura

IPC: G06F11/14

CPC classification number: G06F11/1474 ,  G06F3/0619 ,  G06F3/0629 ,  G06F3/0673 ,  G06F9/466 ,  G06F11/1407 ,  G06F11/1438 ,  G06F11/1451 ,  G06F13/24 ,  G06F2201/805 ,  G06F2201/825 ,  G06F2201/84

Abstract: Autonomous recovery from a transient hardware failure by executing portions of a stream of program instructions as a transaction. A start of a transaction is created in a stream of executing program instructions. A snapshot of a system state information is saved when the transaction begins. When a predefined number of program instructions in the stream are executed, the transaction ends, and store data of the transaction is committed. A new transaction then begins. If a transient hardware failure occurs, the transaction is aborted without notifying the computer software application that initiated the stream of program instructions. The transaction is re-executed, based on the saved snapshot of the system state information.

Abstract translation: 通过执行程序指令流的部分作为事务，从暂时的硬件故障中自动恢复。 在执行程序指令的流中创建事务的开始。 当事务开始时，将保存系统状态信息的快照。 当流中预定义数量的程序指令被执行时，事务结束，事务的存储数据被提交。 然后开始一个新的交易。 如果发生瞬态硬件故障，则事务中止，而不通知启动程序指令流的计算机软件应用程序。 根据系统状态信息的保存快照重新执行事务。

公开(公告)号：US09367252B2

公开(公告)日：2016-06-14

申请号：US14834392

申请日：2015-08-24

Applicant: Amazon Technologies, Inc.

Inventor： Timothy Andrew Rath ,  Jakub Kulesza ,  David Alan Lutz

IPC: G06F11/00 ,  G06F3/06 ,  G06F11/20 ,  H04L29/08

CPC classification number: H04L41/0668 ,  G06F3/0617 ,  G06F3/0653 ,  G06F3/0659 ,  G06F3/0683 ,  G06F11/1425 ,  G06F11/1662 ,  G06F11/2028 ,  G06F11/2041 ,  G06F11/2048 ,  G06F11/2094 ,  G06F11/2097 ,  G06F2201/825 ,  H04L67/1097 ,  H04L67/16

Abstract: A system that implements a data storage service may store data on behalf of storage service clients. The system may maintain data in multiple replicas of various partitions that are stored on respective computing nodes in the system. The system may employ a single master failover protocol, usable when a replica attempts to become the master replica for a replica group of which it is a member. Attempting to become the master replica may include acquiring a lock associated with the replica group, and gathering state information from the other replicas in the group. The state information may indicate whether another replica supports the attempt (in which case it is included in a failover quorum) or stores more recent data or metadata than the replica attempting to become the master (in which case synchronization may be required). If the failover quorum includes enough replicas, the replica may become the master.

公开(公告)号：US09317297B2

公开(公告)日：2016-04-19

申请号：US13629131

申请日：2012-09-27

Applicant: Intel Corporation

Inventor： Justin E. Gottschlich ,  Klaus Danne ,  Cristiano L. Pereira ,  Gilles A. Pokam ,  Rolf Kassa ,  Shiliang Hu ,  Tim Kranich

IPC: G06F9/44 ,  G06F9/38 ,  G06F9/455 ,  G06F11/30 ,  G06F11/36 ,  G06F11/34 ,  G06F9/52

CPC classification number: G06F9/3005 ,  G06F9/30072 ,  G06F9/3802 ,  G06F9/3851 ,  G06F9/44 ,  G06F9/455 ,  G06F9/52 ,  G06F11/30 ,  G06F11/3414 ,  G06F11/3476 ,  G06F11/36 ,  G06F11/3664 ,  G06F11/3688 ,  G06F2201/815 ,  G06F2201/825 ,  G06F2201/865

Abstract: Embodiments may provide a method for performing a replay of a previous execution of a program. The method includes generating an order of recorded chunks of instructions across a plurality of recorded threads based, at least in part, on log files generated from the previous execution of the program. The method includes initiating execution of the program, the executing program having a plurality of threads, each thread having a number of chunks of instructions. The method includes intercepting, by a virtual machine unit executing on a processor, an instruction of a chunk before the instruction is executed. The method includes determining, by a replay module executing on the processor, that the chunk is an active chunk if the chunk is currently in line for execution according to the order of recorded chunks, and responsive to a determination that the chunk is the active chunk, executing the instruction.

Abstract translation: 实施例可以提供用于执行程序的先前执行的重放的方法。 该方法包括至少部分地基于从先前执行的程序生成的日志文件来生成跨多个记录的线程的所记录的指令块的顺序。 该方法包括启动程序的执行，执行程序具有多个线程，每个线程具有多个指令块。 该方法包括在执行指令之前由在处理器上执行的虚拟机单元截取块的指令。 该方法包括通过在处理器上执行的重放模块来确定，如果该组块当前正在与行记录在一起以便执行，则根据所记录的块的顺序来确定该块是活动块，并且响应于该块是活动块的确定 执行指令。

公开(公告)号：US20150379038A1

公开(公告)日：2015-12-31

申请号：US14315091

申请日：2014-06-25

Applicant: VMware, Inc.

Inventor： Dian Nikolov

IPC: G06F17/30 ,  G06F11/14

CPC classification number: G06F16/1815 ,  G06F11/1448 ,  G06F11/1484 ,  G06F11/203 ,  G06F11/2071 ,  G06F11/2097 ,  G06F16/2358 ,  G06F16/275 ,  G06F16/951 ,  G06F2201/80 ,  G06F2201/825

Abstract: Techniques disclosed herein relate to synchronizing a first database with a second database. Embodiments include detecting a write operation modifying properties of a data object in the first database. While the data object is locked, embodiments write object change data to a journal table. Embodiments query the journal table of the recovery database to retrieve a portion of the object change data corresponding to a first window of time and comprising a plurality of entries. The retrieved portion of object change data is processed to create processed object data by collapsing duplicate entries within the plurality of entries. Embodiments retrieve object data from the first database, corresponding to properties of data objects specified in the processed object change data. The retrieved object data is pushed to the second database, whereby the second database is synchronized with the first database.

Abstract translation: 本文公开的技术涉及使第一数据库与第二数据库同步。 实施例包括检测在第一数据库中修改数据对象的属性的写操作。 当数据对象被锁定时，实施例将对象改变数据写入日志表。 实施例查询恢复数据库的日志表以检索对应于第一时间窗口的对象改变数据的一部分并且包括多个条目。 处理对象改变数据的检索部分，以通过折叠多个条目中的重复条目来创建处理对象数据。 实施例从第一数据库检索对象数据，对应于在处理对象改变数据中指定的数据对象的属性。 检索到的对象数据被推送到第二数据库，由此第二数据库与第一数据库同步。

公开(公告)号：US09141481B1

公开(公告)日：2015-09-22

申请号：US12887598

申请日：2010-09-22

Applicant: Allan Havemose

Inventor： Allan Havemose

IPC: G06F11/14 ,  G06F9/54 ,  G06F17/30

CPC classification number: G06F11/1451 ,  G06F9/546 ,  G06F11/1482 ,  G06F11/1683 ,  G06F11/2041 ,  G06F11/2046 ,  G06F11/2097 ,  G06F17/30212 ,  G06F2201/82 ,  G06F2201/825

Abstract: A system, method, and computer readable medium for reliable messaging between two or more servers. The computer readable medium includes computer-executable instructions for execution by a processing system. Primary applications runs on primary hosts and one or more replicated instances of each primary application run on one or more backup hosts. The reliable messaging ensures consistent ordered delivery of messages in the event that messages are lost; arrive out of order, or in duplicate. The messaging layer operates over TCP or UDP with our without multi-cast and broad-cast and requires no modification to applications, operating system or libraries.

公开(公告)号：US20150242276A1

公开(公告)日：2015-08-27

申请号：US14191527

申请日：2014-02-27

Applicant: International Business Machines Corporation

Inventor： Harold W. Cain, III ,  Michael Karl Gschwind ,  Maged M. Michael ,  Valentina Salapura ,  Chung-Lung K. Shum

IPC: G06F11/14 ,  G06F9/46

CPC classification number: G06F11/0793 ,  G06F9/30145 ,  G06F9/467 ,  G06F11/0721 ,  G06F11/0745 ,  G06F11/0751 ,  G06F11/0772 ,  G06F11/079 ,  G06F11/141 ,  G06F11/1474 ,  G06F12/0815 ,  G06F12/084 ,  G06F12/0875 ,  G06F2201/825 ,  G06F2212/1032 ,  G06F2212/452 ,  G06F2212/62 ,  G06F2212/621

Abstract: A transactional memory system salvages a hardware lock elision (HLE) transaction. A processor of the transactional memory system executes a lock-acquire instruction in an HLE environment and records information about a lock elided to begin HLE transactional execution of a code region. The processor detects a pending point of failure in the code region during the HLE transactional execution. The processor stops HLE transactional execution at the point of failure in the code region. The processor acquires the lock using the information, and based on acquiring the lock, commits the speculative state of the stopped HLE transactional execution. The processor starts non-transactional execution at the point of failure in the code region.

Abstract translation: 事务存储系统抢救硬件锁定（HLE）事务。 事务存储器系统的处理器在HLE环境中执行锁定获取指令，并记录有关锁定的信息，以开始执行代码区域的HLE事务执行。 处理器在HLE事务执行期间检测代码区域中的未决故障点。 处理器在代码区域的故障点停止HLE事务执行。 处理器使用该信息获取锁，并且基于获取锁，提交停止的HLE事务执行的推测状态。 处理器在代码区域的故障点处开始非事务性执行。

公开(公告)号：US09116862B1

公开(公告)日：2015-08-25

申请号：US13352326

申请日：2012-01-17

Applicant: Timothy Andrew Rath ,  Jakub Kulesza ,  David A. Lutz

Inventor： Timothy Andrew Rath ,  Jakub Kulesza ,  David A. Lutz

IPC: G06F11/00 ,  G06F11/20

CPC classification number: H04L41/0668 ,  G06F3/0617 ,  G06F3/0653 ,  G06F3/0659 ,  G06F3/0683 ,  G06F11/1425 ,  G06F11/1662 ,  G06F11/2028 ,  G06F11/2041 ,  G06F11/2048 ,  G06F11/2094 ,  G06F11/2097 ,  G06F2201/825 ,  H04L67/1097 ,  H04L67/16

Abstract: A system that implements a data storage service may store data on behalf of storage service clients. The system may maintain data in multiple replicas of various partitions that are stored on respective computing nodes in the system. The system may employ a single master failover protocol, usable when a replica attempts to become the master replica for a replica group of which it is a member. Attempting to become the master replica may include acquiring a lock associated with the replica group, and gathering state information from the other replicas in the group. The state information may indicate whether another replica supports the attempt (in which case it is included in a failover quorum) or stores more recent data or metadata than the replica attempting to become the master (in which case synchronization may be required). If the failover quorum includes enough replicas, the replica may become the master.

Abstract translation: 实现数据存储服务的系统可以代表存储服务客户端存储数据。 系统可以将数据保存在存储在系统中各个计算节点上的各种分区的多个副本中。 系统可以使用单个主故障切换协议，当副本尝试成为其所属的副本组的主副本时可用。 尝试成为主副本可能包括获取与副本组相关联的锁，以及从组中的其他副本收集状态信息。 状态信息可以指示另一个副本是否支持尝试（在这种情况下它被包括在故障切换仲裁中），或存储比尝试成为主机的副本更多的最新数据或元数据（在这种情况下可能需要同步）。 如果故障转移仲裁包含足够的副本，副本可能会成为主服务器。

公开(公告)号：US20150212823A1

公开(公告)日：2015-07-30

申请号：US14572261

申请日：2014-12-16

Applicant: NEC Laboratories America, Inc.

Inventor： Cheng-Hong Li ,  Giuseppe Coviello ,  Srimat Chakradhar ,  Arash Rezaei

IPC: G06F9/38 ,  G06F9/48 ,  G06F9/30

CPC classification number: G06F9/3863 ,  G06F9/3009 ,  G06F9/3877 ,  G06F9/4856 ,  G06F11/1438 ,  G06F11/1446 ,  G06F11/203 ,  G06F11/2043 ,  G06F2201/825 ,  G06F2201/84 ,  G06F2209/509

Abstract: Methods are provided. A method for swapping-out an offload process from a coprocessor includes issuing a snapify_pause request from a host processor to the coprocessor to initiate a pausing of the offload process executing by the coprocessor and another process executing by the host processor using a plurality of locks. The offload process is previously offloaded from the host processor to the coprocessor. The method further includes issuing a snapify_capture request from the host processor to the coprocessor to initiate a local snapshot capture and saving of the local snapshot capture by the coprocessor. The method also includes issuing a snapify_wait request from the host processor to the coprocessor to wait for the local snapshot capture and the saving of the local snapshot capture to complete by the coprocessor.

Abstract translation: 提供方法。 用于从协处理器交换卸载过程的方法包括从主处理器向协处理器发出snapify_pause请求，以启动由协处理器执行的卸载过程的暂停以及由主处理器使用多个锁执行的另一进程。 卸载过程先前从主机处理器卸载到协处理器。 该方法还包括从主处理器向协处理器发出snapify_capture请求以发起本地快照捕获并且由协处理器保存本地快照捕获。 该方法还包括从主机处理器向协处理器发出一个snapify_wait请求，以等待本地快照捕获并保存本地快照捕获以由协处理器完成。

公开(公告)号：US09075762B2

公开(公告)日：2015-07-07

申请号：US13734755

申请日：2013-01-04

Applicant: International Business Machines Corporation

Inventor： Bruno R. Lahousse ,  Alan G. McClure ,  Terry O'Connor

IPC: G06F12/00 ,  G06F12/16 ,  G06F3/06 ,  G06F11/14 ,  G06F13/00 ,  G06F11/20

CPC classification number: G06F11/1469 ,  G06F3/0619 ,  G06F3/065 ,  G06F3/067 ,  G06F11/1435 ,  G06F11/1451 ,  G06F11/1461 ,  G06F11/1464 ,  G06F11/2071 ,  G06F12/16 ,  G06F2201/82 ,  G06F2201/825 ,  G06F2201/84

Abstract: Providing a computer program product, system, and method for setting copy permissions for target data in a copy relationship. Source data is copied from a first storage to a first data copy in a second storage. A request is received to copy requested data from the first data copy to a second data copy. The second copy operation is performed to copy the requested first data copy form the second storage to a second data copy in response to determining that the requested first data copy is not in the state that does not permit the copying. The request is denied in response to determining that the requested first data copy is in the state that does not permit copying.

Abstract translation: 提供用于在复制关系中设置目标数据的复制权限的计算机程序产品，系统和方法。 源数据从第一存储器复制到第二存储器中的第一数据副本。 接收到将请求的数据从第一数据拷贝复制到第二数据副本的请求。 响应于确定所请求的第一数据副本不处于不允许复制的状态，执行第二复制操作以将从第二存储器请求的请求的第一数据副本复制到第二数据副本。 响应于确定所请求的第一数据副本处于不允许复制的状态而拒绝该请求。