Sun Microsystems, Inc.

International Business Machines Corporation

Becton Dickinson and Company Limited

Yahoo! Inc.

Oracle America, Inc.

Ilya Gluhovsky

Brian Walter O'Krafka

David Vengerov

Jan L Bonebakker

Emmanuel Yashchin

John Richard Busch

Herbert M Lee

Raja Palani Velu

Michael D Lock

Sunil S Dalal

Alan Jerome Hoffman

Anantharaman Nagarajan

Michael Lock

A method for maximizing revenue generated from a plurality of service level agreements (SLAs) that includes receiving a first subset of the plurality of SLAs for executing a first plurality of jobs, wherein each SLA in the first subset specifies a first maximum requested delay that is greater than an initial minimum offered delay, and wherein a price of each SLA in the first subset is defined by the maximum requested delay and a price/delay function, calculating a first expected revenue from executing the first subset, and optimizing a second subset of the plurality of SLAs by replacing the initial minimum offered delay on the initial price/delay function with a new minimum offered delay based on the expected revenue, wherein each SLA in the second subset specifies a second maximum requested delay that is greater than the new minimum offered delay.

Method and system for maximizing revenue generated from service level agreements

A method of generating an aggregated forecasting landscape for a particular advertiser's bidded term constructs standardized forecasting landscapes for each marketplace, rescales, by the advertiser's clickability in the respective marketplace, each of the standardized landscapes corresponding to the previous appearance of the advertiser's ad in that marketplace and whose appearance was attributed to the bidded term, and adds together the rescaled landscapes, thereby giving the advertiser a more accurate representation of how many total clicks he can expect for his advertisement as a function of how much he is willing/able to pay. In particular, estimation variance is reduced by introducing rank into the construction of the standardized landscapes, which increases the accuracy of the calculations.

Method for generating forecasting landscapes

One embodiment of the present invention provides a system that characterizes computer system workloads. During operation, the system collects metrics for a number of workloads of interest as the workloads of interest execute on a computer system. Next, the system uses the collected metrics to build a statistical regression model, wherein the statistical regression model uses a performance indicator as a response, and uses the metrics as predictors. The system then defines a distance metric between workloads, wherein the distance between two workloads is a function of the differences between metric values for the two workloads. Furthermore, these differences are weighted by corresponding coefficients for the metric values in the statistical regression model.

Method and apparatus for characterizing computer system workloads

One embodiment of the present invention provides a system that computes a distance metric between computer system workloads. During operation, the system receives a dataset containing metrics that have been collected for a number of workloads of interest. Next, the system uses splines to define bases for a regression model which uses a performance indicator y as a response and uses the metrics (represented by a vector x) as predictors. The system then fits the regression model to the dataset using a penalized least squares (PLS) criterion to obtain functions f, . . . , f, which are smooth univariate functions of individual metrics that add up to the regression function f, such that y=f(x)+&#x3b5;= wherein &#x3b5; represents noise. Finally, the system uses the fitted regression function to define the distance metric.

Method and apparatus for computing a distance metric between computer system workloads

One embodiment of the present invention provides a system that selects bases to form a regression model for cache performance. During operation, the system receives empirical data for a cache rate. The system also receives derivative constraints for the cache rate. Next, the system obtains candidate bases that satisfy the derivative constraints. For each of these candidate bases, the system: (1) computes an aggregate error E incurred using the candidate basis over the empirical data; (2) computes an instability measure I of an extrapolation fit for using the candidate basis over an extrapolation region; and then (3) computes a selection criterion F for the candidate basis, wherein F is a function of E and I. Finally, the system minimizes the selection criterion F across the candidate bases to select the basis used for the regression model.

Selecting basis functions to form a regression model for cache performance

A method for generating an uncertainty characterization for a system simulation model, including obtaining system simulation input, wherein the system simulation input comprises a cache simulation output, generating one of the group consisting of a deterministic uncertainty model and a stochastic uncertainty model, using the cache simulation output and the system simulation model for at least one system input configuration, and generating the uncertainty characterization for the system simulation model using one of the group consisting of the deterministic uncertainty model and the stochastic uncertainty model.

Method and apparatus for determining output uncertainty of computer system models

A method for a cache architecture simulation includes obtaining a first sample set for the cache architecture using a non-stationary Gaussian field model, performing a cache architecture simulation using the first sample set to produce a first set of simulation data, and fitting a first multivariate model to the first set of simulation data.

Experimental design and statistical modeling tool for workload characterization

A method for modeling a system configuration, including isotonizing an unconstrained additive model of a cache architecture to obtain an isotonic additive model for the cache architecture, wherein the isotonic additive model is of the same functional form as the unconstrained additive model, smoothing the isotonic additive model using a flat spot technique to obtain a characterization of the cache architecture, and modeling a system configuration using the characterization of the cache architecture.

Isotonic additive models in workload characterization

A diagnostic system in which, at every point in time, a forecast is made of the future response times of each EPP (nd-to-endrobelatform) probe in a battery of probes. Thresholds are established in terms of the distribution of future EPP values. The theory of Generalized Additive Models is used to build a predictive model based on a combination of a) data normally generated by network nodes, b) results of a battery of probes and c) profile curves reflecting expected response times (i.e. based on recent history) corresponding to this battery for various times of day, days of week, month of year, etc. The model is pre-computed, and does not have to be dynamically adjusted. The model produces, at regular intervals, forecasts for outcomes of various EPP probes for various horizons of interest; also, it produces thresholds for the respective forecasts based on a number of factors, including acceptable rate of false alarms, forecast variance and EPP values that are expected based on the recorded history. The system is capable of maintaining a pre-specified low rate of false alarms that could otherwise cause a substantial disturbance in network operation.

System and method of predicting future behavior of a battery of end-to-end probes to anticipate and prevent computer network performance degradation

One embodiment of the present invention provides a system that facilitates modeling the effects of overlapping of memory references in a queueing system model. The system receives a memory reference during execution of a queueing system model. Upon receiving the memory reference, the system determines if the memory reference generates a cache miss. If so, the system models the cache miss in a manner that accounts for possible overlapping of the cache miss with other memory references and other processor operations.

Modeling overlapping of memory references in a queueing system model

An apparatus and method for identifying clusters in two-dimensional data by generating a two-dimensional histogram characterized by a grid of bins, determining a density estimate based on the bins, and identifying at least one cluster in the data. A smoothed density estimate is generated using a Gaussian kernel estimator algorithm. Clusters are identified by locating peaks and valleys in the density estimate (e.g., by comparing slope of adjacent bins). Boundaries (e.g., polygons) around clusters are identified using bins after bins are identified as being associated with a cluster. Boundaries can be simplified (e.g., by reducing the number of vertices in a polygon) to facilitate data manipulation.

Growing community of inventors

Mountain View, CA, United States of America

Ilya Gluhovsky