公开(公告)号：US20210286653A1

公开(公告)日：2021-09-16

申请号：US16817795

申请日：2020-03-13

Applicant: International Business Machines Corporation

Inventor： Alexei Karve ,  Matthew Staffelbach ,  Ameya Tayade ,  Ramesh S. Palakodeti

IPC: G06F9/50

Abstract: A system, computer program product, and method are provided for dynamically orchestrating a prerequisite driven codified infrastructure. A prerequisite defines deployment of one or more resources in the codified infrastructure through the use of a codified logic expression. One or more probes are created and leveraged to monitor a dynamic resource state for one or more prerequisites. A new codified infrastructure is generated based on the change(s) to the monitored dynamic resource state for the one or more prerequisites. The identified one or more changes are applied to the new codified infrastructure and the new codified infrastructure is executed based on the applied change(s).

公开(公告)号：US11025511B2

公开(公告)日：2021-06-01

申请号：US15841403

申请日：2017-12-14

Applicant: International Business Machines Corporation

Inventor： Neeraj Asthana ,  Thomas E. Chefalas ,  Alexei Karve ,  Clifford A. Pickover

IPC: G06F15/16 ,  H04L12/24 ,  G06F9/50 ,  H04L29/08

Abstract: Techniques that facilitate orchestration engine blueprint aspects for hybrid cloud composition are provided. In one example, a system includes a blueprint component and a hybrid cloud composition component. The blueprint component determines one or more blueprint-level aspects for a blueprint associated with a cloud-based computing platform. The one or more blueprint-level aspects are indicative of encoded information for one or more features associated with one or more computing resources for the cloud-based computing platform. The hybrid cloud composition component determines a set of resource definitions for the cloud-based computing platform based on the one or more blueprint-level aspects.

公开(公告)号：US10754637B1

公开(公告)日：2020-08-25

申请号：US16259205

申请日：2019-01-28

Applicant: International Business Machines Corporation

Inventor： Sai Zeng ,  Alexei Karve ,  Ubaid Ullah Hafeez

IPC: G06F8/65 ,  G06F9/50 ,  G06F9/455 ,  H04L29/08 ,  H04L29/06 ,  G06F8/61

Abstract: Managing performing patches on a workload associated with a computing platform comprising: identify the workload associated with the computing platform, wherein the workload can comprise a first workload portion upon which a first subset of patches can be performed offline and a second workload portion upon which a second subset of patches can be performed online; determine, for the first workload portion, a portion of the first subset of patches that can be performed within a maintenance time window while offline based on vulnerability scores of patches of the first subset of patches, and determine, for the second workload portion, the second subset of patches that can be performed while online; and determine the vulnerability scores of the patches of the first subset of patches based on importance levels of the patches.

公开(公告)号：US10725814B2

公开(公告)日：2020-07-28

申请号：US16109078

申请日：2018-08-22

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Alexei Karve ,  Andrzej Kochut ,  Ruchi Mahindru ,  Charles O. Schulz ,  Mahesh Viswanathan

IPC: G06F9/455

Abstract: A computer-implemented method includes receiving a template for creating a virtual machine (VM) instance; separating the template into a repeated portion and a unique portion; determining whether the repeated portion is stored in a cache; creating based on determining that the repeated portion is stored in the cache, the VM instance using the repeated portion stored in the cache; completing the unique portion of the VM instance to create a completed VM instance; and deploying the completed VM instance.

公开(公告)号：US20200110638A1

公开(公告)日：2020-04-09

申请号：US16150446

申请日：2018-10-03

Applicant: International Business Machines Corporation

Inventor： Neeraj Asthana ,  Thomas Chefalas ,  Alexei Karve ,  Matthew Staffelbach ,  Alla Segal ,  Sai Zeng

IPC: G06F9/50 ,  G06F9/455 ,  G06F11/34

Abstract: An aspect includes the automatic generation of blueprints for orchestration engines from discovered workload representations. A computer-implemented method includes receiving, using a processor, a description of a workload executing in a source computing environment. The description of the workload is mapped, using the processor, to one or more resource descriptors located in a repository of resource descriptors describing resources available in a target computing environment. A declarative representation of the workload in the target computing environment is generated, using the processor, based at least in part on the mapping and the description of the workload. The declarative representation includes a specification of resources required by the workload in the target environment.

公开(公告)号：US10341467B2

公开(公告)日：2019-07-02

申请号：US14994423

申请日：2016-01-13

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Danny Harnik ,  Alexei Karve ,  Andrzej Kochut ,  Dmitry Sotnikov

IPC: G06F16/30 ,  H04L29/06 ,  H04L29/08

Abstract: Methods and systems for data transfer include adding a data chunks to a priority queue in an order based on utilization priority. A reducibility score for the data chunks is determined. A data reduction operation is performed on a data chunk having a highest reducibility in the priority queue using a processor if sufficient resources are available. The data chunk having the lowest reducibility score is moved from the priority queue to a transfer queue for transmission if the transfer queue is not full.

公开(公告)号：US20190190798A1

公开(公告)日：2019-06-20

申请号：US15841420

申请日：2017-12-14

Applicant: International Business Machines Corporation

Inventor： Neeraj Asthana ,  Thomas E. Chefalas ,  Alexei Karve ,  Clifford A. Pickover

IPC: H04L12/24

Abstract: Techniques that facilitate orchestration engine blueprint aspects for hybrid cloud composition are provided. In one example, a system includes a learning component and a hybrid cloud composition component. The learning component learns one or more blueprint-level aspects associated with information for one or more computing resources of a cloud-based computing platform based on historical data associated with the cloud-based computing platform. The hybrid cloud composition component generates a set of resource definitions for the cloud-based computing platform based on the one or more blueprint-level aspects. The hybrid cloud composition component also modifies a blueprint associated with the cloud-based computing platform based on the set of resource definitions.

公开(公告)号：US20170201602A1

公开(公告)日：2017-07-13

申请号：US14994423

申请日：2016-01-13

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Danny Harnik ,  Alexei Karve ,  Andrzej Kochut ,  Dmitry Sotnikov

IPC: H04L29/06 ,  H04L29/08 ,  G06F17/30

CPC classification number: H04L69/04 ,  H03M7/30 ,  H03M7/6035 ,  H04L67/06

Abstract: Methods and systems for data transfer include adding a data chunks to a priority queue in an order based on utilization priority. A reducibility score for the data chunks is determined. A data reduction operation is performed on a data chunk having a highest reducibility in the priority queue using a processor if sufficient resources are available. The data chunk having the lowest reducibility score is moved from the priority queue to a transfer queue for transmission if the transfer queue is not full.

公开(公告)号：US09300552B2

公开(公告)日：2016-03-29

申请号：US14554331

申请日：2014-11-26

Applicant: International Business Machines Corporation

Inventor： Parijat Dube ,  Anshul Gandhi ,  Alexei Karve ,  Andrzej Kochut ,  Li Zhang

IPC: G06F9/44 ,  H04L12/24 ,  H04L29/08

CPC classification number: G06F8/20 ,  G06F8/61 ,  G06F8/70 ,  G06F8/77 ,  G06F9/45558 ,  G06F2009/4557 ,  G06F2009/45595 ,  H04L41/12 ,  H04L41/14 ,  H04L41/5006 ,  H04L41/5054 ,  H04L67/10

Abstract: A method for scaling a cloud infrastructure, comprises receiving at least one of resource-level metrics and application-level metrics, estimating parameters of at least one application based on the received metrics, automatically and dynamically determining directives for scaling application deployment based on the estimated parameters, and providing the directives to a cloud service provider to execute the scaling.

Abstract translation: 一种用于扩展云基础架构的方法，包括：接收资源级度量和应用级度量中的至少一个，基于所接收的度量来估计至少一个应用的参数，基于所估计的自动和动态地确定用于扩展应用程序部署的指令 参数，并向云服务提供商提供指令以执行缩放。

公开(公告)号：US20240241770A1

公开(公告)日：2024-07-18

申请号：US18155095

申请日：2023-01-17

Applicant: International Business Machines Corporation

Inventor： Alexei Karve ,  Maroun Touma ,  Kugamoorthy Gajananan ,  Sekou Lionel Remy

IPC: G06F9/50

CPC classification number: G06F9/5083

Abstract: Methods, systems and computer program products for workload summarization and congestion avoidance are provided. Aspects include generating a workload summary associated with the workload request responsive to receiving a workload request. Aspects also include detecting potential congestion associated with the workload request by predicting resource usage based on the workload summary and a knowledge base model. Aspects further include performing an action to avoid the potential congestion, the action comprising holding off the workload request for at least a predetermined duration.