Splunk Inc.

Intel Corporation

Xiaolu Ye

Ning He

Jian Zhang

Minghao Lu

Xiao Liang Hu

Yang Cao

Zhou Zhou

Young Guo

Jie Cai

Bing Pei

Aiping Zhang

Chong Yu

Computing devices, computer-readable storage media, and computer-implemented methods are disclosed for prediction of capacity. In a central tier, central-tier benchmark values are generated from benchmark testing performed on different test configurations in a reference execution environment. In a deployment tier, deployment-tier benchmark values are generated from benchmark testing performed on a baseline deployed configuration in many execution environments. A sizing model is learned from the central-tier benchmark values to predict execution platform requirements given a set of workload input parameters. A performance model is learned from the deployment-tier and the central-tier benchmark values to predict a performance delta value reflecting relative performance between a particular execution environment and the reference execution environment. The performance delta value is used to adjust predicted execution platform requirements to tailor the prediction to a particular execution environment. The predicted execution platform requirements can be deployed and tested to validate or tune the performance model.

Two-tier capacity planning

Systems and methods for testing a subject system with a software testing process are described. The system receives Boolean states responsive to repeatedly applying a first test case to a subject system. Each Boolean state signifies an outcome of an application of the first test case to a version of a first software feature over a span of time. The system identifies test case outcomes for the first test case that are adjacent in time and different and generates an intermittency value for the first test case. The system determines that the intermittency value for the first test case exceeds an intermittency threshold and alerts an engineering resource. Finally, the system repeats the above operations until the intermittency value for the first test case does not exceed the intermittency threshold.

Intermittent failure metrics in technological processes

A method comprises sniffing an input from a client device to a host device and an output from the host device to the client device; recording a first time parameter in response to a characteristic data unit being inserted into the input that is outputted from a host stack of a host device; recording a second time parameter in response to the output that comprises the characteristic data unit being received by the host stack; and measuring a latency based on the first time parameter, the second time parameter and arrival time of the input and the output at a sniffing point.

Black-box host stack latency measurement

Growing community of inventors

Shanghai, China

Xiaolu Ye