Paul Mark Barnett

US Patent:

7290048, Oct 30, 2007

Filed:

Jan 29, 2003

Appl. No.:

10/354230

Inventors:

Paul T. Barnett - Plano TX, US
Daniel M. Braddock - Austin TX, US
Allan Drew Clarke - Austin TX, US
Richard Gimarc - Austin TX, US
Theodore F. Lehr - Austin TX, US
Annette Palmer - Austin TX, US
Rajinikala Ramachandran - Austin TX, US
James Renyolds - Mt. Desert ME, US
Amy Carolyn Spellman - Dripping Springs TX, US
Carolyn West - Austin TX, US
Timothy E. Wise - Austin TX, US
Tom Zauli - Boston MA, US
Kenneth Zink - Austin TX, US

Assignee:

HyperFormix, Inc. - Austin TX

International Classification:

G06F 15/173
G05B 19/148
G06F 9/46

US Classification:

709223, 709224, 709226

Abstract:

A method of semi-automatic data collection, data analysis and model generation for performance analysis of computer networks and software is provided. The invention provides a graphical user interface which indicates the overall data flow in the performance analysis process and guides the user through the proper sequence of steps in that process. Underneath the graphical user interface, the invention provides software tools which include novel data pipeline for transformation of network traces, resource data and application data into organized hash tables, and further into spreadsheets for introduction into computer network simulation programs. The invention also provides novel algorithms for recognizing transaction and parentage between transactions from low level network trace data. The invention further provides novel methods of visualization of trace data and transaction and parentage associations.

US Patent:

7676569, Mar 9, 2010

Filed:

Feb 1, 2006

Appl. No.:

11/345415

Inventors:

Paul T. Barnett - Plano TX, US
Timothy E. Wise - Austin TX, US
Allan Drew Clarke - Austin TX, US
Richard Gimarc - Austin TX, US
James Reynolds - Mt. Desert ME, US
Amy Spellmann - Johnson City TX, US

Assignee:

HyperFormix, Inc. - Austin TX

International Classification:

G06F 15/173

US Classification:

709224

Abstract:

The invention provides a method for preparing a discrete event simulation model of a production network including a client and a plurality of servers on a plurality of network tiers connected by a network comprising the steps of executing a business function from the client on the production network, gathering resource data from the plurality of servers, normalizing the resource data, calculating a consumption of resources used by the plurality of servers, estimating a transaction cost associated with the consumption of resources and building a discrete event simulation model from the transaction cost.

US Patent:

7680916, Mar 16, 2010

Filed:

Apr 24, 2007

Appl. No.:

11/789499

Inventors:

Paul T. Barnett - Plano TX, US
James Reynolds - Mt. Desert ME, US

Assignee:

Hyperformix, Inc. - Austin TX

International Classification:

G06F 15/173
H04J 3/22

US Classification:

709223, 370468

Abstract:

Method and apparatus for separating background utilization from transaction resource consumption to simulate resource costs on system servers including a computer application server is taught. Transaction throughput combined with resource consumption data. Regression analysis on the resulting data set provides information useful for determining performance and for creating discrete event simulations. In a first embodiment, data from an application server is combined with the application transaction log to find a background utilization on the application servers and to simulate transaction resource cost with a background load. In a second embodiment, data from servers other than the application server are combined with the application transaction log to estimate the resource cost per transaction for a given resource in the system. In a third embodiment, data from servers other than the application server are combined with the application transaction log to simulate resource cost for a given resource based on transaction throughput.

US Patent:

7734775, Jun 8, 2010

Filed:

Oct 26, 2007

Appl. No.:

11/977824

Inventors:

Paul T. Barnett - Plano TX, US
Daniel M. Braddock - Austin TX, US
Allan Drew Clarke - Austin TX, US
Richard Gimarc - Austin TX, US
Theodore F. Lehr - Austin TX, US
Annette Palmer - Austin TX, US
Rajinikala Ramachandran - Austin TX, US
James Reynolds - Mt. Desert MA, US
Amy Carolyn Spellmann - Dripping Springs TX, US
Carolyn West - Austin TX, US
Timothy E. Wise - Austin TX, US
Tom Zauli - Boston MA, US
Kenneth Zink - Austin TX, US

Assignee:

Hyperformix, Inc - Austin TX

International Classification:

G06F 15/173
G06F 11/00

US Classification:

709224, 709223, 714 39, 703 14

Abstract:

A method of semi-automatic data collection, data analysis and model generation for performance analysis of computer networks and software is provided. The invention provides a graphical user interface which indicates the overall data flow in the performance analysis process and guides the user through the proper sequence of steps in that process. Underneath the graphical user interface, the invention provides software tools which include novel data pipeline for transformation of network traces, resource data and application data into organized hash tables, and further into spreadsheets for introduction into computer network simulation programs. The invention also provides novel algorithms for recognizing transaction and parentage between transactions from low level network trace data. The invention further provides novel methods of visualization of trace data and transaction and parentage associations.

US Patent:

7818150, Oct 19, 2010

Filed:

Mar 13, 2006

Appl. No.:

11/374826

Inventors:

Paul T. Barnett - Plano TX, US
Timothy E. Wise - Austin TX, US
Allan Drew Clarke - Austin TX, US
Richard Gimarc - Austin TX, US
James Reynolds - Mt. Desert ME, US

Assignee:

HyPerformix, Inc. - Austin TX

International Classification:

G06F 7/48

US Classification:

703 6

Abstract:

A method is disclosed that preparing a discrete event simulation model of a production network is provided including a client and a plurality of servers connected by a network comprising the steps of initiating a single business function trace test on the production network; gathering network flow trace data from the network; deriving a transaction summary from the network flow trace data; initiating a single business function load test on the production network; gathering resource data from the plurality of servers; normalizing the resource data; gathering web log data from at least one server from the plurality of servers; calculating a number of business functions running on the production network; calculating a consumption of resources used by the plurality of servers; calculating a business function cost associated with the consumption of resources; creating a business function profile from the transaction summary and the business function cost; and building a discrete event simulation model from the business function profile.

US Patent:

8055612, Nov 8, 2011

Filed:

Apr 30, 2008

Appl. No.:

12/150694

Inventors:

Paul Barnett - Plano TX, US

Assignee:

Hyperformix, Inc. - Austin TX

International Classification:

G06F 17/30
G06F 15/16

US Classification:

707609, 709224

Abstract:

A method and apparatus for merging data acquired by two or more capture devices from two or more points in a computer system, duplicate frames are analyzed to determine the time difference between the timestamp of a first capture device and the timestamp of a second capture device. The invention compares the frames for duplicates. If the duplicate frames are the first set of duplicate frames discovered, then all previous timestamps and all subsequent timestamps from the second capture device are adjusted by the calculated time difference. If duplicate frames are again discovered, the time difference is recalculated and all subsequent frames from the second capture device are adjusted by the calculated time difference. After all the frames have been analyzed and the timestamps adjusted, the frames are merged together and put into chronological order to simulate a single capture of data encompassing all of the points where the data was collected.

US Patent:

8521684, Aug 27, 2013

Filed:

Sep 2, 2011

Appl. No.:

13/199597

Inventors:

Paul Barnett - Plano TX, US

Assignee:

CA, Inc. - Islandia NY

International Classification:

G06F 17/30
G06F 15/16

US Classification:

707609, 709224

Abstract:

A method and apparatus for merging data acquired by two or more capture devices from two or more points in a computer system, frames are compared for duplicates, then duplicate frames are analyzed to determine the time difference between the timestamps of a first capture device and a second capture device. If the duplicate frames are the first set of duplicate frames discovered, then all previous timestamps and all subsequent timestamps from the second capture device are adjusted by the time difference. If duplicate frames are again discovered, the time difference is recalculated and all subsequent frames from the second capture device are adjusted by the recalculated time difference. After all the frames have been analyzed and the timestamps adjusted, the frames are merged together and put into chronological order to simulate a single capture of data encompassing all of the points where the data was collected.

US Patent:

20050050098, Mar 3, 2005

Filed:

Sep 3, 2003

Appl. No.:

10/654817

Inventors:

Paul Barnett - Plano TX, US

International Classification:

G06F017/00

US Classification:

707104100

Abstract:

A method and apparatus for merging data acquired by two or more capture devices from two or more points in a computer system, duplicate frames are analyzed to determine the time difference between the timestamp of a first capture device and the timestamp of a second capture device. The invention compares the frames for duplicates. If the duplicate frames are the first set of duplicate frames discovered, then all previous timestamps and all subsequent timestamps from the second capture device are adjusted by the calculated time difference. If duplicate frames are again discovered, the time difference is recalculated and all subsequent frames from the second capture device are adjusted by the calculated time difference. After all the frames have been analyzed and the timestamps adjusted, the frames are merged together and put into chronological order to simulate a single capture of data encompassing all of the points where the data was collected.