公开(公告)号：US20160269317A1

公开(公告)日：2016-09-15

申请号：US14641793

申请日：2015-03-09

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Zah BARZIK ,  Lior CHEN ,  Michael KELLER ,  Rivka M. MATOSEVICH

IPC: H04L12/927 ,  H04L12/911

Abstract: Methods, computing systems and computer program products implement embodiments of the present invention that include assigning multiple storage resources to a reserve pool, and defining one or more storage policy parameters that include allocation policies and deallocation policy parameters. A software defined storage (SDS) controller is initialized by allocating, from the reserve pool, one or more of the storage resources to the SDS controller, and a current state of the SDS controller is monitored. In a first embodiment, upon detecting that the state of the SDS controller meets a given allocation policy parameter, an additional storage resource from the reserve pool is allocated from the reserve pool to the SDS controller. In a second embodiment, upon detecting that the state of the SDS controller meets a given deallocation policy parameter, a given the SDS controller is deallocated from the SDS controller and released back to the storage pool.

Abstract translation: 方法，计算系统和计算机程序产品实现本发明的实施例，其包括将多个存储资源分配给保留池，以及定义包括分配策略和解除分配策略参数的一个或多个存储策略参数。 通过从储备池将一个或多个存储资源分配给SDS控制器来初始化软件定义的存储（SDS）控制器，并且监视SDS控制器的当前状态。 在第一实施例中，当检测到SDS控制器的状态满足给定的分配策略参数时，从备用池向SDS控制器分配来自保留池的附加存储资源。 在第二实施例中，当检测到SDS控制器的状态满足给定的解除分配策略参数时，给定的SDS控制器从SDS控制器被释放并释放回存储池。

公开(公告)号：US20130185379A1

公开(公告)日：2013-07-18

申请号：US13782221

申请日：2013-03-01

Applicant: International Business Machines Corporation

Inventor： Michael KELLER

IPC: G06F15/167

CPC classification number: G06F11/1438 ,  G06F2201/84

Abstract: Exemplary method, system, and computer program product embodiments for efficient state tracking for clusters are provided. In one embodiment, by way of example only, in a distributed shared memory architecture, an asynchronous calculation of deltas and the views is performed while concurrently receiving client requests and concurrently tracking the client requests times. The results of the asynchronous calculation may be applied to each of the client requests that are competing for data of the same concurrency during a certain period with currently executing client requests. Additional system and computer program product embodiments are disclosed and provide related advantages.

Abstract translation: 提供了用于集群的有效状态跟踪的示例性方法，系统和计算机程序产品实施例。 在一个实施例中，仅作为示例，在分布式共享存储器架构中，在同时接收客户端请求并同时跟踪客户机请求时间的同时执行三角形和视图的异步计算。 异步计算的结果可以应用于在当前执行客户端请求的特定时段期间竞争相同并发性的数据的每个客户端请求。 公开了附加的系统和计算机程序产品实施例并提供相关的优点。

公开(公告)号：US20180159873A1

公开(公告)日：2018-06-07

申请号：US15888271

申请日：2018-02-05

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Amit BAREKET ,  Michael KELLER ,  Daniel LEREYA ,  Avraham SABZEROU ,  Moshe WEISS

IPC: H04L29/06

CPC classification number: H04L63/1416

Abstract: Methods, computing systems and computer program products implement embodiments of the present invention that include associating a token with a computing device, defining preferences for the computing device, and conveying, by the computing device, the token and the preferences to an event processing system. Upon the event processing system, an event message from a computing system via a one-way firewall and matching the computing device preferences to the event message, the event processing system can convey the token and the event message to a push notification system. In some embodiments, upon the push notification service receiving the token and the event message, the mobile device can be identified based on the token, and the event message can be conveyed to the computing device. The event messages may include a severity level, and the preferences may include a severity threshold and a message detail level.

公开(公告)号：US20180101447A1

公开(公告)日：2018-04-12

申请号：US15837088

申请日：2017-12-11

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Michael KELLER

IPC: G06F11/14

CPC classification number: G06F11/1438 ,  G06F2201/84

Abstract: Exemplary method, system, and computer program product embodiments for efficient state tracking for clusters are provided. In one embodiment, by way of example only, in a distributed shared memory architecture, an asynchronous calculation of deltas and the views is performed while concurrently receiving client requests and concurrently tracking the client requests times. The results of the asynchronous calculation may be applied to each of the client requests that are competing for data of the same concurrency during a certain period with currently executing client requests. A latency is bound for the client requests by a time necessitated for the asynchronous calculation of at least two of the deltas where a first state snapshot is atomically taken while simultaneously calculating the at least two of the deltas.

公开(公告)号：US20180095831A1

公开(公告)日：2018-04-05

申请号：US15805481

申请日：2017-11-07

Applicant: International Business Machines Corporation

Inventor： Michael KELLER

IPC: G06F11/14

CPC classification number: G06F11/1438 ,  G06F2201/84

Abstract: Exemplary method, system, and computer program product embodiments for efficient state tracking for clusters are provided. In one embodiment, by way of example only, in a distributed shared memory architecture, an asynchronous calculation of deltas and the views is performed while concurrently receiving client requests and concurrently tracking the client requests times. The results of the asynchronous calculation may be applied to each of the client requests that are competing for data of the same concurrency during a certain period with currently executing client requests. A latency is bound for the client requests by a time necessitated for the asynchronous calculation of at least two of the deltas where a first state snapshot is atomically taken while simultaneously calculating the at least two of the deltas.

公开(公告)号：US20170255530A1

公开(公告)日：2017-09-07

申请号：US15062601

申请日：2016-03-07

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Zah BARZIK ,  Lior CHEN ,  Michael KELLER ,  Rivka M. MATOSEVICH

IPC: G06F11/16 ,  G06F11/14 ,  H04L29/08

CPC classification number: G06F11/1666 ,  G06F3/0619 ,  G06F3/0629 ,  G06F3/0631 ,  G06F3/0655 ,  G06F3/067 ,  G06F3/0689 ,  G06F11/1464 ,  G06F17/30575 ,  G06F17/30584 ,  G06F2201/84 ,  H04L41/0663 ,  H04L41/0836 ,  H04L67/1097 ,  H04L69/40

Abstract: Methods, computing systems and computer program products implement embodiments of the present invention that include defining a plurality of failure domains for sets of storage devices in a storage facility, and defining, using the failure domains, one or more limitations for distributing data on the storage devices. Upon identifying a data distribution configuration for a software defined storage system that is compliant with the one or more limitations, the identified data distribution configuration can be presented to a user. The failure domains may include physical failure domains, logical failure domains, or a combination of physical and logical failure domains, and the limitations may include mandatory limitations or a combination of mandatory and non-mandatory limitations. In embodiments including non-mandatory limitations, the data distribution configuration may not comply with all the non-mandatory limitations, and any non-mandatory limitations that are not met can be flagged and presented to the user.

公开(公告)号：US20160378625A1

公开(公告)日：2016-12-29

申请号：US14754324

申请日：2015-06-29

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Daniel M. AIZER ,  Yuval BEN-HORIN ,  Michael KELLER ,  Osnat SHASHA

IPC: G06F11/20 ,  G06F3/06

CPC classification number: G06F11/2069 ,  G06F3/0619 ,  G06F3/065 ,  G06F3/067 ,  G06F11/00 ,  G06F11/2058 ,  G06F2201/805

Abstract: Methods, computing systems and computer program products implement embodiments of the present invention that include configuring a first storage system to mirror first storage regions to corresponding second storage regions in a second storage system via a first data connection, and to mirror the first storage regions to corresponding third storage regions in a third storage system via a second data connection. Upon the second storage system receiving, subsequent to detecting a failure of the first storage system, a host I/O request to retrieve data from a given second storage region and determining that the respective timestamp of the corresponding third storage region on the third storage system is more recent than the respective timestamp of the given second storage region on the second storage system, the second storage system retrieves, via a third data connection, the data from the corresponding third storage region on the third storage system.

Abstract translation: 方法，计算系统和计算机程序产品实现本发明的实施例，包括配置第一存储系统以经由第一数据连接将第一存储区域镜像到第二存储系统中的对应的第二存储区域，并将第一存储区域镜像到 通过第二数据连接在第三存储系统中的对应的第三存储区域。 在第二存储系统接收到在检测到第一存储系统的故障之后，从给定的第二存储区域检索数据并确定第三存储系统上相应的第三存储区域的相应时间戳的主机I / O请求 比第二存储系统上给定的第二存储区域的相应时间戳更新，第二存储系统经由第三数据连接从第三存储系统上的对应的第三存储区域检索数据。

公开(公告)号：US20160173602A1

公开(公告)日：2016-06-16

申请号：US14571278

申请日：2014-12-15

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Jonathan AMIT ,  Lior CHEN ,  Michael KELLER ,  Rivka M. MATOSEVICH

IPC: H04L29/08

Abstract: Methods, computing systems and computer program products implement embodiments of the present invention that include configuring multiple servers coupled to a network as a software defined storage (SDS) grid. A first given server receives, via the network, an input/output (I/O) request from a host computer, and determines a location of data associated with the I/O request. In some embodiments, each of the servers maintains a local grid data map that store locations for all data managed by the SDS grid. Upon identifying, in its respective local grid data map, that a second given server is configured to process the I/O request, the first given server forwards the I/O request to the second given server for processing, and upon receiving a result of the I/O request from the second given server, the first given server conveys the result of the I/O request to the host computer.

Abstract translation: 方法，计算系统和计算机程序产品实现本发明的实施例，其包括将耦合到网络的多个服务器配置为软件定义的存储（SDS）网格。 第一个给定的服务器通过网络接收来自主机的输入/输出（I / O）请求，并且确定与I / O请求相关联的数据的位置。 在一些实施例中，每个服务器维护本地网格数据图，其存储由SDS网格管理的所有数据的位置。 在其各自的本地网格数据图中，识别出第二给定服务器被配置为处理I / O请求，第一给定服务器将I / O请求转发给第二给定服务器进行处理，并且在接收到 来自第二给定服务器的I / O请求，第一给定服务器将I / O请求的结果传送到主计算机。

公开(公告)号：US20140229692A1

公开(公告)日：2014-08-14

申请号：US13764031

申请日：2013-02-11

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Itzhack GOLDBERG ,  Michael KELLER ,  Moriel LECHTMAN ,  Orit NISSAN-MESSING ,  Eliyahu WEISSBREM

IPC: G06F3/06

CPC classification number: G06F17/30578 ,  G06F3/0614 ,  G06F3/065 ,  G06F3/067 ,  G06F11/14 ,  G06F11/1451 ,  G06F11/1469 ,  G06F11/2064 ,  G06F11/2069 ,  G06F11/2074 ,  G06F11/2082 ,  G06F2201/84

Abstract: Methods, apparatus and computer program products implement embodiments of the present invention that include conveying first data from local regions of a local volume of a local storage system to a remote storage system having a remote volume with remote regions in a one-to-one correspondence with the local regions. While conveying the first data, a request is received to update a given local region, and the given local region is marked. Subsequent to conveying the first data, a local snapshot referencing the local regions is created, and second data is conveyed from the marked local region to the remote storage system.

Abstract translation: 方法，装置和计算机程序产品实现本发明的实施例，其包括将本地存储系统的本地卷的本地区域的第一数据传送到具有一对一对应的具有远程区域的远程卷的远程存储系统 与当地区域。 在传送第一数据的同时，接收到请求以更新给定的局部区域，并且给定的局部区域被标记。 在传送第一数据之后，创建引用局部区域的本地快照，并且将第二数据从标记的本地区域传送到远程存储系统。

公开(公告)号：US20180276087A1

公开(公告)日：2018-09-27

申请号：US15995397

申请日：2018-06-01

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Ram ELRON ,  Michael KELLER ,  Rivka M. MATOSEVICH ,  Osnat SHASHA

IPC: G06F11/14 ,  G06F3/06 ,  G06F11/16

CPC classification number: G06F11/1471 ,  G06F3/0619 ,  G06F3/065 ,  G06F3/0653 ,  G06F3/067 ,  G06F11/1076 ,  G06F11/1662 ,  G06F11/2058 ,  G06F11/2082 ,  G06F2201/805 ,  G06F2201/81 ,  G06F2201/875

Abstract: Methods, computing systems and computer program products implement embodiments of the present invention that include detecting a loss of communication with a given storage node among multiple storage nodes in a distributed computing system. Upon detecting the loss of communication, a log including updates to the data stored in the given storage node is recorded and, the recorded updates can be applied to the given storage node upon communication with the given storage node being reestablished. In some embodiments, the distributed storage system may be configured as a software defined storage system where the storage nodes can be implemented as either virtual machines or software containers. In additional embodiments, upon detecting the loss of communication, a redistribution of the mirrored data among remaining storage nodes is initiated upon detecting the loss of communication, and the redistribution is rolled back upon reestablishing the communication.