公开(公告)号：US09830262B2

公开(公告)日：2017-11-28

申请号：US14133488

申请日：2013-12-18

Applicant: NVIDIA CORPORATION

Inventor： Jerome F. Duluk, Jr. ,  Cameron Buschardt ,  James Leroy Deming ,  Brian Fahs

IPC: G06F12/08 ,  G06F11/30 ,  G06F11/34

CPC classification number: G06F12/08 ,  G06F11/3037 ,  G06F11/3442 ,  G06F11/3471 ,  G06F2201/81 ,  G06F2201/815 ,  G06F2201/88 ,  G06F2212/205

Abstract: Embodiments of the approaches disclosed herein include a subsystem that includes an access tracking mechanism configured to monitor access operations directed to a first memory and a second memory. The access tracking mechanism detects an access operation generated by a processor for accessing a first memory page residing on the second memory. The access tracking mechanism further determines that the first memory page is included in a first subset of memory pages residing on the second memory. The access tracking mechanism further locates, within a reference vector, a reference bit that corresponds to the first memory page, and sets the reference bit. One advantage of the present invention is that memory pages in a hybrid system migrate as needed to increase overall memory performance.

公开(公告)号：US09785468B2

公开(公告)日：2017-10-10

申请号：US13563640

申请日：2012-07-31

Applicant: Nicholas Matthew Mitchell ,  Peter F. Sweeney

Inventor： Nicholas Matthew Mitchell ,  Peter F. Sweeney

IPC: G06F9/50 ,  G06F11/34

CPC classification number: G06F9/50 ,  G06F9/4806 ,  G06F11/3433 ,  G06F11/3442 ,  G06F11/3447 ,  G06F11/3452 ,  G06F11/3466 ,  G06F2201/865 ,  G06F2201/875 ,  G06F2209/508 ,  Y02D10/22 ,  Y02D10/34

Abstract: A computer program product for automatically gauging a benefit of a tuning action. The computer program product including a computer readable storage medium having computer readable program code embodied therewith. The computer readable program code including computer readable program code configured to collect a plurality of observations of a running state of a plurality of threads in a computer system. Computer readable program code configured to identify a plurality of resources of the computer system and a capacity of each resource of the plurality of resources. Computer readable program code configured to map an observation of the running state of each thread of the plurality of threads to a resource that the observation of each thread uses, respectively, and computer readable program code configured to apply the tuning action to a first resource of the plurality of resources to determine an impact on the performance of the computer system.

公开(公告)号：US09720709B1

公开(公告)日：2017-08-01

申请号：US14822753

申请日：2015-08-10

Applicant: Amazon Technologies, Inc.

Inventor： Thomas Charles Stickle

IPC: G06F9/445 ,  G06F9/50 ,  G06F11/34 ,  G06F11/30

CPC classification number: G06F9/44505 ,  G06F8/70 ,  G06F8/71 ,  G06F8/77 ,  G06F9/45558 ,  G06F9/5077 ,  G06F11/3006 ,  G06F11/301 ,  G06F11/3409 ,  G06F11/3442 ,  G06F2009/45587 ,  G06F2009/45591 ,  G06F2201/815

Abstract: A technology is described for a software container recommendation service. An example method may include collecting utilization metrics for an application hosted on a computing instance. The utilization metrics may be a measure of computing resources used by the application. The utilization metrics may be analyzed to determine a level of computing resources for the computing instance used by the application. A software container configuration for the application may be determined based at least in part on the utilization metrics when analysis of the utilization metrics indicates an underutilization of computing resources by the application. The specifications of the software container configuration may then be provided to a customer.

公开(公告)号：US09635101B2

公开(公告)日：2017-04-25

申请号：US14981730

申请日：2015-12-28

Applicant: NetApp, Inc.

Inventor： Vipul Mathur ,  Neeraja Yadwadkar ,  Lakshmi Narayanan Bairavasundaram ,  Rukma Ameet Talwadker ,  Kaladhar Voruganti ,  Sai Rama Krishna Susaria

IPC: H04L29/08 ,  H04L29/06 ,  H04L12/54 ,  G06F9/46 ,  H04L12/24 ,  G06F11/34 ,  G06F11/30

CPC classification number: H04L67/1008 ,  G06F9/465 ,  G06F11/3006 ,  G06F11/3034 ,  G06F11/3409 ,  G06F11/3442 ,  G06F11/3447 ,  G06F11/3485 ,  G06F2201/81 ,  G06F2201/86 ,  H04L12/54 ,  H04L29/06 ,  H04L41/5009 ,  H04L47/70 ,  H04L67/1097 ,  Y02D10/34

Abstract: Described herein is a system and method for dynamically managing service-level objectives (SLOs) for workloads of a cluster storage system. Proposed states/solutions of the cluster may be produced and evaluated to select one that achieves the SLOs for each workload. A planner engine may produce a state tree comprising nodes, each node representing a proposed state/solution. New nodes may be added to the state tree based on new solution types that are permitted, or nodes may be removed based on a received time constraint for executing a proposed solution or a client certification of a solution. The planner engine may call an evaluation engine to evaluate proposed states, the evaluation engine using an evaluation function that considers SLO, cost, and optimization goal characteristics to produce a single evaluation value for each proposed state. The planner engine may call a modeler engine that is trained using machine learning techniques.

公开(公告)号：US20170097850A1

公开(公告)日：2017-04-06

申请号：US15379871

申请日：2016-12-15

Applicant: International Business Machines Corporation

Inventor： Nicholas Matthew MITCHELL ,  Peter F. SWEENEY

IPC: G06F9/50 ,  G06F9/48

CPC classification number: G06F9/50 ,  G06F9/4806 ,  G06F11/3433 ,  G06F11/3442 ,  G06F11/3447 ,  G06F11/3452 ,  G06F11/3466 ,  G06F2201/865 ,  G06F2201/875 ,  G06F2209/508 ,  Y02D10/22 ,  Y02D10/34

Abstract: A non-transitory, computer readable, storage medium storing a program of instructions executable by a machine to perform a method of gauging a benefit of a tuning action, the method includes acquiring a set of time series data sampled from an environment of an application, using a processor.

公开(公告)号：US09569236B2

公开(公告)日：2017-02-14

申请号：US14023861

申请日：2013-09-11

Applicant: International Business Machines Corporation

Inventor： Robert Birke ,  Yiyu L. Chen ,  Martin L. Schmatz

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

CPC classification number: G06F9/45533 ,  G06F9/5027 ,  G06F11/3006 ,  G06F11/34 ,  G06F11/3442 ,  G06F11/3452 ,  G06F2009/4557 ,  G06F2201/815 ,  G06F2209/501

Abstract: The sizing of virtual machines is optimized based on projected performance metrics. All virtual machine configuration resources are normalized by a processing device. The normalized resources for the virtual machine configurations are then stored in a catalogue. An application is then profiled to obtain resource demand estimates for each virtual machine configuration and a base performance is calculated for the application. The base performance is used to predict performance estimates on all virtual machine configurations in the catalogue. Accordingly, a virtual machine configuration having a lowest response time is selected.

Abstract translation: 基于预计的性能指标优化虚拟机的大小。 所有虚拟机配置资源都由处理设备进行归一化。 然后将虚拟机配置的归一化资源存储在目录中。 然后分析应用程序以获得每个虚拟机配置的资源需求估计，并为应用程序计算基本性能。 基本性能用于预测目录中所有虚拟机配置的性能估计。 因此，选择具有最低响应时间的虚拟机配置。

公开(公告)号：US20170031794A1

公开(公告)日：2017-02-02

申请号：US15295077

申请日：2016-10-17

Applicant: International Business Machines Corporation

Inventor： Carlos H. Cardonha ,  Marcos D. de Assuncao ,  Renato L. de Freitas Cunha ,  Marco A. Stelmar Netto

IPC: G06F11/30 ,  G06F9/50 ,  G06F11/32 ,  G06F11/34

CPC classification number: G06F11/3006 ,  G06F9/44505 ,  G06F9/5011 ,  G06F9/5061 ,  G06F11/3024 ,  G06F11/328 ,  G06F11/3409 ,  G06F11/3423 ,  G06F11/3433 ,  G06F11/3442 ,  G06F11/3452 ,  G06F11/3495 ,  G06F2201/81 ,  G06F2201/875

Abstract: Embodiments of the present invention provide systems, methods, and computer program products for configuring auto-scaling parameters of a computing environment, as well as alerting a user when auto-scaling operations are not attainable given current operating configurations.

Abstract translation: 本发明的实施例提供了用于配置计算环境的自动缩放参数的系统，方法和计算机程序产品，以及在给定当前操作配置的情况下不能实现自动缩放操作时提醒用户。

公开(公告)号：US09503334B2

公开(公告)日：2016-11-22

申请号：US14277853

申请日：2014-05-15

Applicant: International Business Machines Corporation

Inventor： Lance Bragstad ,  Michael J. Branson ,  Bin Cao ,  James E. Carey ,  Mathew R. Odden

IPC: H04L12/26 ,  H04L12/911 ,  H04L29/06 ,  G06F11/32 ,  G06F9/455 ,  G06F11/34 ,  H04L12/24

CPC classification number: H04L43/04 ,  G06F9/45558 ,  G06F11/32 ,  G06F11/3404 ,  G06F11/3409 ,  G06F11/3442 ,  G06F2009/45562 ,  G06F2201/81 ,  G06F2201/815 ,  G06F2201/865 ,  H04L41/0806 ,  H04L47/783 ,  H04L65/60

Abstract: Performance thresholds are defined for operators in a flow graph for a streaming application. A streams manager deploys the flow graph to one or more virtual machines (VMs). The performance of each portion of the flow graph on each VM is monitored. A VM is selected. When the performance of the portion of the flow graph in the selected VM does not satisfy the defined performance threshold(s), a determination is made regarding whether the portion of the flow graph is underperforming or overperforming. When the portion of the flow graph is underperforming, the portion of the flow graph is split into multiple portions that are implemented on multiple VMs. When the portion of the flow graph is overperforming, a determination is made of whether a neighbor VM is also overperforming. When a neighbor VM is also overperforming, the two VMs may be coalesced into a single VM.

Abstract translation: 针对流应用程序的流程图中的运算符定义了性能阈值。 流管理器将流程图部署到一个或多个虚拟机（VM）。 监视每个VM上流程图的每个部分的性能。 选择一个虚拟机。 当所选择的VM中的流程图的部分的性能不满足定义的性能阈值时，确定流程图的该部分是否表现不佳或超过性能。 当流程图的部分表现不佳时，流程图的部分被分割成在多个虚拟机上实现的多个部分。 当流程图的部分超过执行时，确定邻近VM是否也超过性能。 当邻居VM也超过性能时，两个VM可以合并成单个VM。

公开(公告)号：US20160306564A1

公开(公告)日：2016-10-20

申请号：US15194481

申请日：2016-06-27

Applicant: International Business Machines Corporation

Inventor： Sonia Cheng ,  Pamela H. Hurwitch ,  Roman Kisin ,  Anirudh Oswal ,  Deidre Paknad ,  Irina Simpson

IPC: G06F3/06 ,  H04L29/08

CPC classification number: G06F3/0608 ,  G06F3/0619 ,  G06F3/0634 ,  G06F3/0647 ,  G06F3/0653 ,  G06F3/067 ,  G06F9/466 ,  G06F11/3419 ,  G06F11/3442 ,  G06F12/02 ,  G06F2201/87 ,  H04L41/0893 ,  H04L41/22 ,  H04L67/1008 ,  H04L67/1097

Abstract: According to one aspect of the present disclosure, a method and technique for capacity forecasting is disclosed. The method includes: storing, in a memory, resource data associated with an environment, the resource data comprising inventory information of applications, processing resources and storage resources of the environment; and providing a ledger module executable by a processor unit to: create a capacity-associated transaction; identify and link at least one of an application, processing resource and storage resource to the transaction from the resource data; determine an initiation time and duration associated with the transaction; and forecast a change in capacity of at least one linked storage resource for the transaction and a time of the change in capacity.

公开(公告)号：US09471460B2

公开(公告)日：2016-10-18

申请号：US13434168

申请日：2012-03-29

Applicant: Malolan Chetlur ,  Parul Gupta ,  Mukundan Madhavan

Inventor： Malolan Chetlur ,  Parul Gupta ,  Mukundan Madhavan

IPC: G06F11/34 ,  H04W24/02

CPC classification number: G06F11/3457 ,  G06F11/3442 ,  H04W24/02

Abstract: Methods and arrangements for characterizing software base-station workloads. Input system parameters are mapped to work-determining parameters which act to determine computational requirements of a dynamic workload. A synthetic experiment is undertaken to measure the computational requirements determined by the work-determining parameters.

Abstract translation: 表征软件基站工作负载的方法和安排。 输入系统参数映射到工作确定参数，用于确定动态工作负载的计算需求。 进行合成实验来测量由工作确定参数确定的计算要求。