公开(公告)号：US08261278B2

公开(公告)日：2012-09-04

申请号：US12024783

申请日：2008-02-01

Applicant: Zahur Peracha

Inventor： Zahur Peracha

IPC: G06F9/455 ,  G06F9/46

CPC classification number: G06F11/3409 ,  G06F11/3452 ,  G06F11/3466 ,  G06F2201/81 ,  G06F2201/815 ,  G06F2201/87 ,  G06F2201/875 ,  G06F2201/88

Abstract: An application monitoring system determines the health of one or more resources used to process a transaction, business application, or other computer process. Performance data is generated in response to monitoring application execution and processed to determine and an actual and baseline value for resource usage data. Resource usage baseline data may be determined from previous resource usage data associated with a resource and particular transaction (a resource-transaction pair). The baseline values are compared to actual values to determine a deviation for the actual value. Deviation information for the time series data can be reported through an interface or some other manner.

Abstract translation: 应用程序监视系统确定用于处理事务，业务应用程序或其他计算机进程的一个或多个资源的运行状况。 性能数据是响应于监视应用程序执行生成的，并被处理以确定资源使用数据的实际值和基准值。 可以从与资源和特定事务（资源 - 事务对）相关联的先前资源使用数据确定资源使用基准数据。 将基准值与实际值进行比较，以确定实际值的偏差。 可以通过界面或其他方式报告时间序列数据的偏差信息。

公开(公告)号：US08230245B2

公开(公告)日：2012-07-24

申请号：US12321675

申请日：2009-01-23

Applicant: Mukund Khatri ,  Humayun Khalid ,  Robert W. Hormuth

Inventor： Mukund Khatri ,  Humayun Khalid ,  Robert W. Hormuth

IPC: G06F1/26

CPC classification number: G06F1/3203 ,  G06F1/329 ,  G06F11/3409 ,  G06F11/3452 ,  G06F11/3495 ,  G06F2201/87 ,  G06F2201/88 ,  Y02D10/24

Abstract: Systems and methods are disclosed for power management in information handling systems using processor performance data to validate changes to processor performance states. Processor utilization data and processor performance data is obtained during system operation. The processor utilization data is analyzed to determine a desired performance state for the processor. Before setting the actual performance state of the processor to this desired performance state, however, processor performance data is analyzed to determine if prior changes to the performance state have been effective. The performance state of the processor is then changed are maintained based upon this additional performance verification analysis.

Abstract translation: 公开了用于使用处理器性能数据来验证对处理器性能状态的改变的信息处理系统中的电力管理的系统和方法。 处理器利用率数据和处理器性能数据在系统运行期间获得。 分析处理器利用率数据以确定处理器的期望的性能状态。 然而，在将处理器的实际性能状态设置为所需性能状态之前，分析处理器性能数据，以确定先前对性能状态的更改是否有效。 然后基于这种额外的性能验证分析来维持处理器的性能状态。

公开(公告)号：US08204719B2

公开(公告)日：2012-06-19

申请号：US10648179

申请日：2003-08-26

Applicant: Yixin Diao ,  Denise Y. Dyko ,  Frank N. Eskesen ,  Joseph L. Hellerstein ,  Alexander Keller ,  Lisa F. Spainhower

Inventor： Yixin Diao ,  Denise Y. Dyko ,  Frank N. Eskesen ,  Joseph L. Hellerstein ,  Alexander Keller ,  Lisa F. Spainhower

IPC: G06F7/60

CPC classification number: G06F11/3447 ,  G06F11/3419 ,  G06F2201/87 ,  G06F2201/88

Abstract: Techniques for constructing and using models in accordance with service level management are disclosed. In one aspect of the invention, a technique for constructing a model (e.g., a system model) representative of a resource for use in managing a service associated with the resource, comprises the following steps/operations. A set of resource metrics is obtained in accordance with a resource abstract model (RAM) associated with the resource. Then, a model representative of the resource is constructed based on at least a portion of the set of resource metrics obtained from the resource abstract model.

Abstract translation: 公开了根据服务水平管理构建和使用模型的技术。 在本发明的一个方面，一种用于构建代表用于管理与资源相关联的服务的资源的模型（例如，系统模型）的技术包括以下步骤/操作。 根据与资源相关联的资源抽象模型（RAM）获得一组资源度量。 然后，基于从资源抽象模型获得的资源度量集合的至少一部分来构建代表资源的模型。

公开(公告)号：US20120151488A1

公开(公告)日：2012-06-14

申请号：US13307338

申请日：2011-11-30

Applicant: Mauro Arcese ,  Antonio Perrone ,  Sandro Piccinini ,  Stefano Sidoti

Inventor： Mauro Arcese ,  Antonio Perrone ,  Sandro Piccinini ,  Stefano Sidoti

IPC: G06F9/46

CPC classification number: G06F9/45504 ,  G06F3/04812 ,  G06F9/4881 ,  G06F11/34 ,  G06F11/3419 ,  G06F11/3476 ,  G06F11/36 ,  G06F2201/835 ,  G06F2201/87

Abstract: A mechanism modifies a deployment descriptor of each application component including at least one producer application component or consumer application component, by adding, for each producer application component or consumer application component, an application component identifier, a producer or consumer type, and a recipient identifier of a recipient the application component uses. Responsive to determining a match exists and the given application component is of producer type, the application server virtual machine logs an identifier of a recipient containing a message sent by the given application component, a correlation identifier of the given application component, and an execution start time. Responsive to determining a match exists and the given application component is of consumer type, the application server virtual machine logs an identifier of the recipient resource containing a message processed by the given application component, a correlation identifier of the given application component, and an execution end time.

Abstract translation: 机制通过针对每个生产者应用程序组件或消费者应用程序组件添加应用程序组件标识符，生产者或消费者类型以及接收者标识符来修改包括至少一个生产者应用程序组件或消费者应用程序组件的每个应用程序组件的部署描述符 应用程序组件使用的收件人。 响应于确定匹配存在并且给定应用组件是生产者类型，应用服务器虚拟机记录包含由给定应用组件发送的消息的接收者的标识符，给定应用组件的相关标识符和执行开始 时间。 响应于确定匹配存在并且给定的应用组件是消费者类型，应用服务器虚拟机记录包含由给定应用组件处理的消息的接收者资源的标识符，给定应用组件的相关标识符和执行 时间结束。

公开(公告)号：US08170845B2

公开(公告)日：2012-05-01

申请号：US12236824

申请日：2008-09-24

Applicant: Dinesh Kumar ,  Li Zhang

Inventor： Dinesh Kumar ,  Li Zhang

IPC: G06F7/60 ,  G06G7/62

CPC classification number: H04L41/147 ,  G06F11/3419 ,  G06F11/3447 ,  G06F2201/87 ,  H04L41/145 ,  H04L43/0864

Abstract: A method for modeling performance of an information technology system having one or more servers for serving a number of types of transactions includes modeling a service time of each transaction type at each server and a processor overhead at each server as one of a polynomial, exponential, or logarithmic function of the average arrival rate of each transaction type at the corresponding server to generate service time and processor overhead functions and inferring optimal values of coefficients in the service time and processor overhead functions to generate a performance model of the information technology system.

Abstract translation: 用于对具有用于服务多种类型的事务的一个或多个服务器的信息技术系统的性能进行建模的方法包括对每个服务器处的每个事务类型的服务时间进行建模，以及在每个服务器处建模处理器开销，作为多项式，指数， 或每个交易类型的平均到达率的对数函数，以产生服务时间和处理器开销函数，并推断服务时间和处理器开销函数中的系数的最优值，以生成信息技术系统的性能模型。

公开(公告)号：US08156087B2

公开(公告)日：2012-04-10

申请号：US12431637

申请日：2009-04-28

Applicant: Toshihiro Shimizu ,  Hirokazu Iwakura

Inventor： Toshihiro Shimizu ,  Hirokazu Iwakura

IPC: G06F7/00 ,  G06F17/30

CPC classification number: G06F11/3495 ,  G06F11/3419 ,  G06F11/3476 ,  G06F2201/87 ,  G06F2201/875

Abstract: A system analysis apparatus includes a message reconstruction module which reconstructs observed data and data of which the observation has failed, into messages regarding a request and a response which are communicated on a system. The apparatus includes a message candidate extraction module which compares message rules with the reconstructed messages, and extracts messages in the message rules which are identical to the reconstructed messages, from the messages defined in the message rules, as message candidates. The apparatus includes a call relationship extraction module which extracts a call relationship between the message candidates. The apparatus includes a matching module which compares transaction models in which processes in units of transactions on the system have been modeled on the basis of call relationships among the processes on the system, with the extracted call relationship, and selects and determines a transaction model identical to the call relationship.

Abstract translation: 系统分析装置包括消息重建模块，其将观测数据和观测失败的数据重建成关于在系统上传送的请求和响应的消息。 该装置包括消息候选提取模块，其将消息规则与重构的消息进行比较，并从消息规则中定义的消息中提取与重构消息相同的消息规则中的消息作为消息候选。 该装置包括提取消息候选者之间的呼叫关系的呼叫关系提取模块。 该装置包括：匹配模块，其比较事件模型，其中系统中的事务单元中的进程已经被建模，基于系统中的进程之间的呼叫关系以及所提取的呼叫关系，并且选择并确定相同的事务模型 到呼叫关系。

公开(公告)号：US08151251B2

公开(公告)日：2012-04-03

申请号：US11755773

申请日：2007-05-31

Applicant: Akhilesh Laddha ,  Ritwik Batabyal

Inventor： Akhilesh Laddha ,  Ritwik Batabyal

IPC: G06F9/45

CPC classification number: G06F11/3495 ,  G06F11/3419 ,  G06F2201/865 ,  G06F2201/87

Abstract: A method of dynamically generating profiling data using runtime non-intrusive profiling of application transactions which are contained in containers such as web servers, application servers, portal servers and J2EE/ECM containers, includes the following steps: using common resources of memory and environment for both profiling activity and application transactions; remotely executing project specific profiling administration and configuration; using the executed project specific profiling administration and configuration and completing remote profiling, and generating profiling data by taking assistance selectively from Aspect Oriented Programming, and Application Response Measurement; and, selectively using the profiling data to analyze performance bottlenecks and do auditing as needed by a user. The profiling is done by capturing metrics based on accepted standards, partially using the same memory as for the application transactions, without code-contamination in the containers and can be done layer-wise, tier-wise or at method level. A computer readable medium encoded with the method is included.

Abstract translation: 使用包含在诸如Web服务器，应用服务器，门户服务器和J2EE / ECM容器之类的容器中的应用程序事务的运行时非侵入性分析来动态生成分析数据的方法包括以下步骤：使用内存和环境的常见资源 分析活动和应用交易; 远程执行项目特定的分析管理和配置; 使用执行的项目特定的分析管理和配置，并完成远程分析，并通过从面向对象编程和应用程序响应测量中选择性地提供帮助来生成分析数据; 并选择性地使用分析数据来分析性能瓶颈，并根据用户的需要进行审计。 分析是通过基于接受的标准捕获指标，部分使用与应用程序事务相同的内存，而不会在容器中进行代码污染，并且可以按层次，层次或方法级进行。 包括用该方法编码的计算机可读介质。

公开(公告)号：US08140903B2

公开(公告)日：2012-03-20

申请号：US12425075

申请日：2009-04-16

Applicant: Benjiman L. Goodman ,  Sertac Cakici ,  Samuel I. Ward ,  Linton B. Ward, Jr.

Inventor： Benjiman L. Goodman ,  Sertac Cakici ,  Samuel I. Ward ,  Linton B. Ward, Jr.

IPC: G06F11/00

CPC classification number: G06F11/349 ,  G06F2201/87

Abstract: A method for tracing thread bus transactions in a multiprocessor system comprises decoding, by a processor, a first thread instruction of a thread, the thread comprising an ordered series of thread instructions. In the event the first thread instruction is a set bus trace enable bit (BTEB) instruction, the processor sets a bus trace enable bit corresponding to the thread. In the event the BTEB is set, the processor determines whether the first thread instruction is a trace-eligible instruction and, in the event the first thread instruction is a trace-eligible instruction, and the BTEB is set, the processor sets a snoop tag trace enable bit (STTEB). A hardware trace monitor (HTM) monitors bus transactions, each bus transaction comprising a STTE. In the event a monitored bus transaction comprises a set STTEB, the HTM stores the bus transaction as trace data. In the event a monitored bus transaction comprises a reset STTEB, the HTM does not store the bus transaction as trace data.

Abstract translation: 用于在多处理器系统中跟踪线程总线事务的方法包括由处理器解码线程的第一线程指令，所述线程包括有序序列的线程指令。 在第一个线程指令是一个设置的总线跟踪使能位（BTEB）指令的情况下，处理器设置与线程相对应的总线跟踪使能位。 在设置BTEB的情况下，处理器确定第一个线程指令是否是符合条件的指令，并且在第一个线程指令是符合跟踪条件的指令的情况下，并且BTEB被设置，处理器设置一个窥探标记 跟踪使能位（STTEB）。 硬件跟踪监视器（HTM）监视总线事务，每个总线事务包括STTE。 在监控总线事务包括一组STTEB的情况下，HTM将总线事务存储为跟踪数据。 在监控总线事务包括复位STTEB的情况下，HTM不将总线事务存储为跟踪数据。

公开(公告)号：US20120047250A1

公开(公告)日：2012-02-23

申请号：US12861709

申请日：2010-08-23

Applicant: Ray Y. Lai ,  Anjaneya Vara Vankayala Venkata ,  Hari Ravi

Inventor： Ray Y. Lai ,  Anjaneya Vara Vankayala Venkata ,  Hari Ravi

IPC: G06F15/173

CPC classification number: G06F11/3452 ,  G06F11/3414 ,  G06F11/3419 ,  G06F2201/87

Abstract: During a technique for estimating a scalability breakpoint of a software product, performance load tests of the software product are performed with different numbers of simulated concurrent users. For a given number of simulated concurrent users, a performance load test may include an associated set of transactions that are executed by the software product. Furthermore, during the performance load tests performance metrics for the transactions in the associated sets of transactions are measured. Then estimated total performance metrics for the transactions in the associated sets of transactions for the different numbers of simulated concurrent users are determined based on the measured performance metrics and the associated sets of transactions. Next, using the determined estimated total performance metrics, the estimated scalability breakpoint is calculated.

Abstract translation: 在用于估计软件产品的可伸缩性断点的技术中，使用不同数量的模拟并发用户执行软件产品的性能负载测试。 对于给定数量的模拟并发用户，性能负载测试可以包括由软件产品执行的相关联的一组事务。 此外，在性能负载测试期间，测量相关联交易集中的交易的性能指标。 然后，根据测量的绩效指标和相关的交易集合，确定不同数量的模拟并发用户的关联交易集中事务的估计总体性能指标。 接下来，使用所确定的估计总性能度量，计算估计的可扩展性断点。

公开(公告)号：US20110320540A1

公开(公告)日：2011-12-29

申请号：US12823516

申请日：2010-06-25

Applicant: Bart Oostlander ,  William Noble ,  Bryce Dunn ,  Murali Mogalayapalli ,  Stephen Kowal

Inventor： Bart Oostlander ,  William Noble ,  Bryce Dunn ,  Murali Mogalayapalli ,  Stephen Kowal

IPC: G06F15/16

CPC classification number: G06F11/3051 ,  G06F11/3006 ,  G06F11/3409 ,  G06F11/3419 ,  G06F11/3495 ,  G06F2201/87 ,  G06Q40/02

Abstract: An automated method is provided for constructing or updating a service model that defines the entities in an enterprise's computing environment. The method includes: defining a group of templates for updating the service model, where the group of templates identify different types of entities which comprise the service model and relationships between the types of entities including an entity that links software applications to respective computing infrastructure that supports the software applications; monitoring messages received from monitoring tools residing in the computing environment; and updating a service model in accordance with the group of templates using data encapsulated in the messages.

Abstract translation: 提供了一种自动化方法来构建或更新在企业的计算环境中定义实体的服务模型。 该方法包括：定义用于更新服务模型的一组模板，其中该组模板识别构成服务模型的不同类型的实体，以及包括将软件应用链接到支持的各个计算基础设施的实体之间的关系之间的关系 软件应用; 监测从驻留在计算环境中的监控工具接收到的消息; 以及使用封装在所述消息中的数据，根据所述模板组来更新服务模型。