Measurement of application response delay time

• US 10,250,475 B2
• Filed: 12/08/2016
• Issued: 04/02/2019
• Est. Priority Date: 12/08/2016
• Status: Active Grant

• Current Assignee: A10 Networks Incorporated
• Original Assignee: A10 Networks Incorporated
• Inventors: He, Yichao, Yang, Yang, Golshan, Ali
• Primary Examiner(s): Etienne, Ario
• Assistant Examiner(s): Mendaye, Kidest
• Application Number:
  US15/373,001
• Publication Number:
  US 20180167298A1
• Time in Patent Office: 845 Days
• CPC Class Codes: H04L 43/0864 Round trip delays
• CPC Class Codes: H04L 61/4511 using domain name system [DNS]
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/14 Session management for real-time applications in data packet communications networks H04L65/1066

Abstract

A method and system for measuring application response delay is described. The method may commence with receiving a Domain Name System (DNS) request from a client DNS server. The method may include measuring round trip time between the client DNS server and a first Global Server Load Balancing (GSLB) controller, between the first GSLB controller and a server load balancer (SLB) collocated with the first GSLB controller, and between the SLB and an application server. The method may further include receiving measurements of round trip time between the client DNS server and a second GSLB controller, between the second GSLB controller and an SLB collocated with the second GSLB controller, and between the second GSLB controller and a further application server. A cumulative response time associated with the application servers may be calculated based on the measurements to select an application server having a lowest cumulative response time.

Claims

1. A system for measuring application response delay, the system comprising at least a processor and associated memory:

a first Global Server Load Balancing (GSLB) controller associated with a plurality of distributed GSLB controllers, the first GSLB controller being utilized to;

receive, from a client, via a client Domain Name System (DNS) server, a DNS request, the DNS request including a request to establish a session between the client and one of a plurality of application servers;

responsive to the receiving the DNS request, measure a first round trip time (RTT) between the client DNS server and the first GSLB controller of the plurality of distributed GSLB controllers;

measure a second RTT between the first GSLB controller and a first server load balancer (SLB) collocated with the first GSLB controller;

measure a third RTT between the first SLB and at least one application server;

receive, from a second GSLB controller, a measurement of a first RTT between the client DNS server and the second GSLB controller, a measurement of a second RTT between the second GSLB controller and a second SLB collocated with the second GSLB controller, and a measurement of a third RTT between the second SLB and at least one further application server;

based on the measurements, calculate a cumulative response time associated with the at least one application server and a cumulative response time associated with the at least one further application server;

based on the calculation, select an application server from the at least one application server and the at least one further application server, the application server having a lowest cumulative response time from the cumulative response time associated with the at least one application server and the cumulative response time associated with the at least one further application server; and

based on the selection, send a DNS response to the client DNS server, the DNS response including network data of the SLB associated with the selected application server;

the second GSLB controller associated with the plurality of distributed GSLB controllers, the second GSLB controller being utilized to;

receive, from the first GSLB controller, an instruction to measure the first RTT between the client DNS server and the second GSLB controller, the second RTT between the second GSLB controller and the second SLB, and the third RTT between the second SLB and the at least one further application server;

in response to the instruction, measure the first RTT between the client DNS server and the second GSLB controller, the second RTT between the second GSLB controller and the second SLB, and the third RTT between the second SLB and the at least one further application server; and

provide the measurements to the first GSLB controller; and

a database for storing the measurements associated with the first GSLB controller and the measurements associated with the second GSLB controller.

2. The system of claim 1, wherein the first GSLB controller is further utilized to:

request the second GSLB controller to measure the first RTT between the client DNS server and the second GSLB controller, the second RTT between the second GSLB controller and the second SLB collocated with the second GSLB controller, and the third RTT between the second SLB and the at least one further application server.

3. The system of claim 1, wherein the calculating of the cumulative response time associated with the at least one application server includes summing the first RTT between the client DNS server and the first GSLB controller, the second RTT between the first GSLB controller and a first SLB, and third RTT between the first SLB and the at least one application server;

and

wherein the calculating of the cumulative response time associated with the at least one further application server includes summing the first RTT between the client DNS server and the second GSLB controller, the second RTT between the second GSLB controller and the second SLB, and third RTT between the second SLB and the at least one further application server.

4. The system of claim 1, wherein the first GSLB controller and the second GSLB controller are utilized to exchange requests.

5. The system of claim 1, wherein the first GSLB controller is further utilized to:

determine, based on a domain name included into the DNS request, a type of the session requested to be established by the client;

request, from each of the first SLB and the second SLB, a processing time associated with each of the at least one application server and the at least one further application server, the processing time including time needed for each of the at least one application server and the at least one further application server for processing the session based on the type of the session; and

receive the processing time associated with each of the at least one application server and the at least one further application server.

6. The system of claim 5, wherein the first GSLB controller is further utilized to:

sum, for at least one application server and the at least one further application server, the cumulative response time and the processing time.

7. The system of claim 5, wherein the domain name includes a string selected from a group comprising:

a Hypertext Transfer Protocol, a File Transfer Protocol, a Session Initiation Protocol, a voice over Internet protocol, a web, a file, a mail, a Post Office Protocol, an exchange, and an email.

8. The system of claim 1, wherein the first GSLB controller, the second GSLB controller, and each of the plurality of GSLB controllers are utilized to:

maintain a response time table in a database for storing the measurements and the cumulative response time.

9. The system of claim 8, wherein the first GSLB controller is further utilized to:

periodically measure a RTT between each of the plurality of GSLB controllers and each of SLBs collocated with each of the plurality of GSLB controllers; and

store the measured RTT to the database.

10. A method for measuring application response delay, the method comprising:

receiving, by a first Global Server Load Balancing (GSLB) controller associated with a plurality of distributed GSLB controllers, from a client, via a client Domain Name System (DNS) server, a DNS request, the DNS request including a request to establish a session between the client and one of a plurality of application servers;

responsive to the receiving the DNS request, measuring, by the first GSLB controller, a first round trip time (RTT) between the client DNS server and the first GSLB controller of the plurality of distributed GSLB controllers;

measuring, by the first GSLB controller, a second RTT between the first GSLB controller and a first server load balancer (SLB) collocated with the first GSLB controller;

measuring, by the first GSLB controller, a third RTT between the first SLB and at least one application server;

receiving, by the first GSLB controller, from a second GSLB controller of the plurality of distributed GSLB controllers, a measurement of a first RTT between the client DNS server and the second GSLB controller, a measurement of a second RTT between the second GSLB controller and a second SLB collocated with the second GSLB controller, and a measurement of a third RTT between the second SLB and at least one further application server;

based on the measurements, calculating, by the first GSLB controller, a cumulative response time associated with the at least one application server and a cumulative response time associated with the at least one further application server;

based on the calculation, selecting, by the first GSLB controller, an application server from the at least one application server and the at least one further application server, the application server having a lowest cumulative response time from the cumulative response time associated with the at least one application server and the cumulative response time associated with the at least one further application server; and

based on the selection, sending, by the first GSLB controller, a DNS response to the client DNS server, the DNS response including network data of the SLB associated with the selected application server.

11. The method of claim 10, further comprising:

requesting, by the first GSLB controller, the second GSLB controller to measure the first RTT between the client DNS server and the second GSLB controller, the second RTT between the second GSLB controller and the second SLB collocated with the second GSLB controller, and the third RTT between the second SLB and the at least one further application server.

12. The method of claim 10, wherein the calculating of the cumulative response time associated with the at least one application server includes summing the first RTT between the client DNS server and the first GSLB controller, the second RTT between the first GSLB controller and a first SLB, and third RTT between the first SLB and the at least one application server;

and

wherein the calculating of the cumulative response time associated with the at least one further application server includes summing the first RTT between the client DNS server and the second GSLB controller, the second RTT between the second GSLB controller and the second SLB, and third RTT between the second SLB and the at least one further application server.

13. The method of claim 10, wherein the first GSLB controller and the second GSLB controller are operable to exchange requests.

14. The method of claim 10, further comprising:

determining, by the first GSLB controller, based on a domain name included into the DNS request, a type of the session requested to be established by the client;

requesting, by the first GSLB controller, from each of the first SLB and the second SLB, a processing time associated with each of the at least one application server and the at least one further application server, the processing time including time needed for each of the at least one application server and the at least one further application server for processing the session based on the type of the session; and

receiving, by the first GSLB controller, the processing time associated with each of the at least one application server and the at least one further application server.

15. The method of claim 14, further comprising:

summing, for at least one application server and the at least one further application server, the cumulative response time and the processing time.

16. The method of claim 14, wherein the domain name includes a string selected from a group comprising:

a Hypertext Transfer Protocol, a File Transfer Protocol, a Session Initiation Protocol, a voice over Internet protocol, a web, a file, a mail, a Post Office Protocol, an exchange, and an email.

17. The method of claim 10, further comprising:

maintaining, by the first GSLB controller, the second GSLB controller, and each of the plurality of GSLB controllers, a response time table in a database for storing the measurements and the cumulative response time.

18. The method of claim 17, further comprising:

based on the DNS request, searching for the cumulative response time associated with the client DNS server in the database.

19. The method of claim 17, further comprising:

periodically measuring a RTT between each of the plurality of GSLB controllers and each of SLBs collocated with each of the plurality of GSLB controllers; and

storing the measured RTT to the database.

20. A system for measuring application response delay, the system comprising at least a processor and associated memory:

a first Global Server Load Balancing (GSLB) controller associated with a plurality of distributed GSLB controllers, the first GSLB controller being utilized to;

receive, from a client, via a client DNS server, a DNS request, the DNS request including a request to establish a session between the client and one of a plurality of application servers;

responsive to the receiving the DNS request, measure a first round trip time (RTT) between the client DNS server and the first GSLB controller of the plurality of distributed GSLB controllers;

measure a second RTT between the first GSLB controller and a first server load balancer (SLB) collocated with the first GSLB controller;

measure a third RTT between the first SLB and at least one application server;

request a second GSLB controller to measure a first RTT between the client DNS server and the second GSLB controller, a second RTT between the second GSLB controller and a second SLB collocated with the second GSLB controller, and a third RTT between the second SLB and at least one further application server

receive, from the second GSLB controller, a measurement of the first RTT between the client DNS server and the second GSLB controller, a measurement of the second RTT between the second GSLB controller and the second SLB collocated with the second GSLB controller, and a measurement of the third RTT between the second SLB and the at least one further application server;

based on the measurements, calculate a cumulative response time associated with the at least one application server and a cumulative response time associated with the at least one further application server;

wherein the calculating of the cumulative response time associated with the at least one application server includes summing the first RTT between the client DNS server and the first GSLB controller, the second RTT between the first GSLB controller and a first SLB, and third RTT between the first SLB and the at least one application server; and

wherein the calculating of the cumulative response time associated with the at least one further application server includes summing the first RTT between the client DNS server and the second GSLB controller, the second RTT between the second GSLB controller and the second SLB, and third RTT between the second SLB and the at least one further application server;

based on the calculation, select an application server from the at least one application server and the at least one further application server, the application server having a lowest cumulative response time from the cumulative response time associated with the at least one application server and the cumulative response time the at least one further application server; and

based on the selection, send a DNS response to the client DNS server, the DNS response including network data of the SLB associated with the selected application server;

the second GSLB controller associated with the plurality of distributed GSLB controllers, wherein the first GSLB controller and the second GSLB controller are utilized to exchange requests, the second GSLB controller being utilized to;

receive, from the first GSLB controller, an instruction to measure the first RTT between the client DNS server and the second GSLB controller, the second RTT between the second GSLB controller and the second SLB, and the third RTT between the second SLB and the at least one further application server;

in response to the instruction, measure the first RTT between the client DNS server and the second GSLB controller, the second RTT between the second GSLB controller and the second SLB, and the third RTT between the second SLB and the at least one further application server; and

provide the measurements to the first GSLB controller; and

a database for storing the measurements associated with the first GSLB controller and the measurements associated with the second GSLB controller.