Microsoft Technology Licensing, LLC

Matthew C Odhner

Giedrius Zizys

Kent S Schliiter

Boyd Cannon Multerer

Michael W Thomas

Eric W Nace

Michelle M Rowe

Tom A Cox

A methods and systems for capacity planning of server resources are described wherein a load simulation tool is used to use actual data gathered from a server cluster during operation to simulate server cluster operation in which the load (requests per second) can be increased, and the effects on the utilization of resources can be observed. Plans containing recommendations are then presented to a system user so the user can make decisions necessary regarding whether to change configuration hardware to meet expected load increases in the future.

Load simulation tool for server resource capacity planning

Load stimulation tool for server resource capacity planning

Methods and systems for capacity planning of server resources are described wherein fixed resources of a server cluster are used in comparison to similar server cluster benchmarks to determine the maximum load&#x2014;requests per second&#x2014;that can be handled by the server cluster. The maximum load is used to determine utilization of server resources and to provide estimates of server resource utilization for hypothetical loads. A recommendation as to changes to server resources to handle the hypothetical loads is displayed to the user.

Capacity planning for server resources

A network test system utilizes known good responses when testing responses from in-test servers. In one embodiment, the test system includes a verification server that is known to provide correct responses. In-test servers are subjected to very high rates of requests, and the responses are compared to responses from the verification server. Hash values are optionally used to represent the correct responses, and are compared to similar hash values produced from the actual responses of the in-test servers. Dynamic data is accommodated by basing the hash values on only the static portions of responses. Alternatively, dynamic data is accommodated by using search patterns&#x2014;when receiving an actual response from an in-test server, the response is searched for the specified search pattern. The response is deemed to be incorrect if the search pattern does not occur. Wildcards and other variable elements are used in the search patterns.

Server stress-testing response verification

Growing community of inventors

Woodinville, WA, United States of America

Matthew C Odhner