Endpoint web monitoring system and method for measuring popularity of a service or application on a web server

Patent metadata

Field	Value
Publication number	US-10230602-B2
Application number	US-201113295383-A
Country	US
Kind code	B2
Filing date	Nov 14, 2011
Priority date	Dec 9, 2010
Publication date	Mar 12, 2019
Grant date	Mar 12, 2019

Abstract

A system is provided that includes an artificial connection generator and a probe machine. The artificial connection generator is configured to establish one or more artificial connections with a server that at least partially hosts one or more services or applications for access by clients. The probe machine is configured to control a number of artificial connections with the server by the artificial connection generator. The probe machine also is configured to establish a probing connection with a server to determine a service time of the server that is indicative of a time period involved with execution by the server of one or more requests to the server. The probe machine is configured to derive a number of actual connections between the clients and the server based on changes in the service time of the server when the number of artificial connections with the server is varied.

First claim

What is claimed is:

1. A system comprising:
an artificial connection generator configured to establish one or more artificial connections with a server that at least partially hosts one or more services or applications for access by clients, where the artificial connections differ from actual connections sent by the clients to the server; and
a probe machine connected with the artificial connection generator, the probe machine configured to generate an artificial connection to the server and control a number of artificial connections with the server by sending control signals to the artificial connection generator, the probe machine also configured to determine a service time of the server that is indicative of a time period involved with execution by the server of one or more requests to the server, and the probe machine varying the number of artificial connections to examine changes in service times based on the number of artificial connections;
wherein the probe machine is configured to determine a difference between the number of artificial connections and a connection limitation parameter, and to derive a number of the actual connections between the clients and the server based on the difference and changes in the service time of the server when the number of artificial connections with the server is varied, where the derived number of the actual connections provides a popularity or traffic metric for the server, services or applications without having administrative access or privileges to the server or logs of the server.

2. The system of claim 1 , wherein the actual connections represent connections between the server and the clients other than the artificial connection generator and the probe machine.

3. The system of claim 1 , wherein the server is associated with the connection limitation parameter indicative of a number of requests that are received and executed by the server before placing additional requests into an accept queue before executing the additional requests.

4. The system of claim 3 , wherein the probe machine is configured to change the number of artificial connections with the server and monitor changes in the service time of the server in order to determine the connection limitation parameter of the server.

5. The system of claim 1 , wherein the probe machine is configured to increase the number of artificial connections between the artificial connection generator and the server until a round trip time (RTT) of a request sent to the server increases, and the probe machine is configured to derive the number of actual connections based on the number of artificial connections associated with the increase in the RTT of the request.

6. The system of claim 1 , wherein the artificial connection generator is configured to establish the one or more artificial connections by communicating at least one of an open-ended request or an incomplete request for information to the server.

7. The system of claim 1 , wherein the probe machine is configured to establish the probing connection by communicating one or more ping probes and at least one request for information to the server.

8. The system of claim 1 , wherein the probe machine is configured to derive the number of actual connections based on a number of the artificial connections with the server that increases the service time of the server, a number of the artificial connections with the server that does not increase the service time of the server, and the connection limitation parameter that is indicative of a number of requests that are received and executed by the server before placing additional requests into an accept queue before executing the additional requests.

9. The system of claim 1 , wherein the number of actual connections is restricted information of the server and the probe machine is configured to derive the number of actual connections without having access to the restricted information.

10. A method comprising:
measuring services times for executing requests sent to a server;
generating an artificial connection by a probe machine to the server;
controlling a number of artificial connections with the server based on control signals transmitted by the probe machine, where the artificial connections differ from actual connections sent by the clients to the server;
varying the number of artificial connections to examine changes in service times based on the number of artificial connections;
monitoring changes in the service times of the server based on changes in the number of artificial connections with the server;
determining a difference between the number of artificial connections and a connection limitation parameter; and
deriving a number of actual connections with the server based on the determined difference and changes in the service times of the server when the number of artificial connections with the server is varied, where the derived number of the actual connections provides a popularity or traffic metric for the service, a service or an application without having administrative access or privileges to the server or logs of the server.

11. The method of claim 10 , wherein the server is associated with the connection limitation parameter indicative of a number of requests that are received and executed by the server before placing additional requests into an accept queue before executing the additional requests.

12. The method of claim 11 , further comprising determining the connection limitation parameter of the server based on the changes in the service times.

13. The method of claim 10 , wherein controlling the number of artificial connections includes increasing the number of artificial connections with the server until round trip times (RTT) of the requests sent to the server increase, and the number of actual connections is derived based on the number of artificial connections associated with the increase in the RTT.

14. The method of claim 10 , wherein controlling the number of artificial connections includes directing one or more artificial connection generators to communicate at least one of an open-ended request or an incomplete request for information to the server.

15. The method of claim 10 , wherein measuring the service times includes communicating one or more ping probes and at least one request for information to the server.

16. The method of claim 10 , wherein the number of actual connections is derived based on a number of the artificial connections with the server that increases the service times of the server, a number of the artificial connections with the server that does not increase the service times of the server, and the connection limitation parameter that is indicative of a number of requests that are received and executed by the server before placing additional requests into an accept queue before executing the additional requests.

17. The method of claim 10 , wherein the number of actual connections is restricted information of the server and deriving the number of actual connections is performed without having access to the restricted information.

18. A computer readable storage medium for a system having a controller, the computer readable storage medium including one or more sets of instructions that are configured to direct the controller to:
measure services times for executing requests sent to a server;
generate an artificial connection by a probe machine to the server;
control a number of artificial connections with the server based on control signals transmitted by a probe machine, where the artificial connections differ f

Assignees

• Su Ao Jan
• Kuzmanovic Aleksandar
• Univ Northwestern

Inventors

• Su Ao-Jan
• Kuzmanovic Aleksandar

Classifications

• H04L43/0852 Primary

  Delays · CPC title

• H04L43/10

  Active monitoring, e.g. heartbeat, ping or trace-route · CPC title