Server monitoring virtual points of presence

• US 6,973,489 B1
• Filed: 03/21/2000
• Issued: 12/06/2005
• Est. Priority Date: 03/21/2000
• Status: Expired due to Term

• Current Assignee: Micro Focus LLC (Open Text Corporation)
• Original Assignee: Mercury Interactive Corp. (HP Inc.)
• Inventors: Levy, Eli
• Primary Examiner(s): Dharia, Rupal
• Assistant Examiner(s): Nguyen, Quang N.
• Application Number:
  US09/531,821
• Time in Patent Office: 2,086 Days
• Field of Search: 709/203, 709/218, 709/223, 709/224, 709/238
• US Class Current: 709/224
• CPC Class Codes: G06F 11/3414 Workload generation, e.g. scripts, playback
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3495 for systems
• CPC Class Codes: G06F 2201/87 Monitoring of transactions
• CPC Class Codes: G06F 2201/875 Monitoring of systems including the internet
• CPC Class Codes: H04L 41/046 comprising network management agents or mobile agents therefor
• CPC Class Codes: H04L 41/342 between virtual entities, e.g. orchestrators, SDN or NFV entities
• CPC Class Codes: H04L 43/00 Arrangements for monitoring or testing data switching networks
• CPC Class Codes: H04L 43/06 Generation of reports
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 43/0864 Round trip delays
• CPC Class Codes: H04L 43/20 the monitoring system or the monitored elements being virtualised, abstracted or software-defined entities, e.g. SDN or NFV

Abstract

A server monitoring system monitors the performance of a web site or other Internet server system, as seen by users in multiple geographic access locations, without the need for special monitoring software or hardware within such locations. Automated agents that run at a central data center generate message traffic that is used to access and monitor the server system from the multiple remote locations. The message traffic associated with a particular remote access location is transmitted from the data center to the remote location across a dedicated link, such as an ATM link, and is routed onto the Internet at a corresponding Internet access point. The server response to each request message flows back to the data center across the same link as the corresponding request message. The remote access points thus serve as virtual points of presence for monitoring purposes. Server response times as seen from the remote access locations are determined by measuring the total response times as observed from the data center, and deducting from the total response times the round-trip latencies associated with the corresponding dedicated links. The response times and other performance data generated by the agents are aggregated within a database that is local to the agents. Multiple data centers may be interconnected such that each data center services a particular continent or other region using a respective set of virtual points of presence.

Claims

1. A method of monitoring access to a server system as experienced from multiple user locations on a computer network, comprising:

at a monitoring location, generating first and second request messages that represent requests from users of the server system;

transmitting the first request message over a first communications link from the monitoring location to a first network access location that is remote from the monitoring location for transmission on the network at the first network access location, to thereby simulate access to the server system by a user who is local to the first network access location;

transmitting the second request message over a second communications link from the monitoring location to a second network access location that is remote from both the monitoring location and the first network access location for transmission on the network at the second network access location, to thereby simulate access to the server system by a user who is local to the second network access location; and

at the monitoring location, monitoring responses received from the server system to the first and second request messages;

whereby user access to the server system as experienced by users local to the first and second network access locations is monitored without the need for monitoring components local to the first and second network access locations.

2. The method as in claim 1, wherein monitoring responses received from the server system comprises:

determining a total response time to the first request message as observed at the monitoring location; and

subtracting from the total response time a delay associated with the first communications link, to thereby determine a response time as experienced at the first network access point.

3. The method as in claim 2, further comprising estimating the delay based at least on a load applied to the first communications link.

4. The method as in claim 2, wherein the network is the Internet, and the first and second communications links are connection-oriented links that directly connect the monitoring location to the first and second network access locations, respectively.

5. The method as in claim 4, wherein the first and second communications links are Asynchronous Transfer Mode links.

6. The method as in claim 4, wherein the server system comprises a web server of a publicly accessible web site.

7. The method as in claim 1, wherein the first and second communications links are connection-oriented links that directly interconnect the data center with the first and second network access locations, respectively.

8. The method as in claim 7, wherein the first and second communications links are Asynchronous Transfer Mode links.

9. The method as in claim 8, wherein the network is the Internet.

10. The method as in claim 1, wherein transmitting the first request message over a first communications link comprises transferring the first request message over the first communications link to a router that is directly connected to the network.

11. The method as in claim 1, wherein transmitting the first request message over a first communications link comprises transferring the first request message over the first communications link to a modem that is locally connected to the network.

12. A system for monitoring performance of a server system as seen from multiple user locations, including user locations that are geographically remote from one another, the system comprising:

a plurality of agent computers that are locally interconnected at a central location, the agent computers configured to generate request messages to the server system as simulated users and to monitor responses from the server system to the request messages; and

a plurality of communications links, each communications link connecting one or more of the plurality of agent computers to a respective network access point within a respective user location that is geographically remote from the central location;

wherein the plurality of agent computers are configured to communicate with the server system via the plurality of communications links to monitor performance of the server system as seen from the multiple user locations;

whereby the system monitors the performance of the server system as seen from multiple user locations without the need for performance monitoring components local to said user locations.

13. The system as in claim 12, wherein each communications link is a dedicated, connection-oriented communications link.

14. The system as in claim 12, wherein at least some of the plurality of communications links are Asynchronous Transfer Mode links.

15. The system as in claim 12, wherein at least some of the plurality of communications links produce a round-trip latency that is predicable based on a current load on the communications link.

16. The system as in claim 12, wherein the server system is an Internet server system, and at least some of the communications links are directly peered to the Internet within respective user locations.

17. The system as in claim 12, wherein the plurality of agent computers are arranged into groups, wherein each group is assigned to a respective communications link and corresponding user location.

18. The system as in claim 17, wherein the agent computers within a group are configured to use unique IP (Internet Protocol) addresses associated with a corresponding remote Internet point of presence.

19. The system as in claim 17, wherein at least one of the groups comprises multiple agent computers that are grouped through a hub and a single port of a local switch.

20. The system as in claim 19, wherein the switch in connected to a router that is directly connected to the plurality of communications links.

21. The system as in claim 12, wherein the agent computers are configured to measure response times as seen from the user locations by measuring total response times to request messages, and by deducting round-trip latencies associated with the communications links.

22. The system as in claim 12, further comprising a database that locally stores server performance data generated by the plurality of agent computers.

23. A method for monitoring access to a server system as experienced from a network access location, comprising:

at a first location which is remote from the network access location, generating a user request message that is addressed to the server system;

sending the request message over a communications link to the network access location for transmission over a computer network from the network access location to the server system, to thereby simulate access to the server system by a user who is local to the network access location;

at the first location, receiving a response to the request message from the server system over the communications link; and

determining a response time to the user request message as experienced at the network access location;

whereby the performance of the server system as experienced from the network access location is measured without a need for any performance monitoring components at the network access location.

24. The method as in claim 23, wherein determining the response time as experienced at the network access location comprises determining a total response time observed at the first location, and subtracting from the total response time a round-trip delay attributable to the communications link.

25. The method as in claim 24, further comprising estimating the round-trip delay based at least upon a load applied to the communications link.

26. The method as in claim 23, wherein the computer network is the Internet, and the communications link is a connection-oriented link that directly connects the first location to the network access location.

27. The method as in claim 26, wherein the communications link is an Asynchronous Transfer Mode link.

28. The method as in claim 23, wherein the server system comprises a web server of a publicly accessible web site.

29. The method as in claim 23, further comprising recording the response time, and response times measured for other user locations, within a database that is local to the first location.

30. A system for monitoring a web site from multiple geographic locations, the system comprising:

a data center comprising at least one computer system programmed to access and monitor the web site; and

a plurality of Internet connection points, each of which is located at a different respective one of said multiple geographic locations, at least some of the Internet connection points being geographically remote from others and from the data center;

wherein the data center sends request messages to the web site, and receives response messages from the web site, through the plurality of Internet connection points to monitor the web site as seen by users in each of the multiple geographic locations.

31. The system as in claim 30, wherein the data center is connected to the plurality of Internet connection points by dedicated communications links.

32. The system as in claim 30, wherein the data center monitors the web site as seen by users in the multiple geographic locations without the use of any monitoring components in any of the multiple geographic locations.

33. The system as in claim 30, wherein the data center calculates response times of the web site as seen from each of the Internet connection points.