Active application response delay time

• US 10,257,101 B2
• Filed: 02/27/2018
• Issued: 04/09/2019
• Est. Priority Date: 03/31/2014
• Status: Active Grant

• Current Assignee: A10 Networks Incorporated
• Original Assignee: A10 Networks Incorporated
• Inventors: Golshan, Ali, Grimm, Martin, Yang, Yang
• Primary Examiner(s): Avellino, Joseph E
• Assistant Examiner(s): McLeod, Marshall M
• Application Number:
  US15/906,974
• Publication Number:
  US 20180191625A1
• Time in Patent Office: 406 Days
• Field of Search: 709239, 709238, 709204, 709217, 709223
• CPC Class Codes: H04L 47/125 by balancing the load, e.g. traffic engineering
• CPC Class Codes: H04L 47/283 in response to processing delays, e.g. caused by jitter or round trip time [RTT]

Abstract

Provided are methods and systems for load balancing client requests between sites associated with a domain name. A method comprises determining a first active response delay time between a Domain Name System server and a first site. The method further comprises determining a first application response delay time between the first site and one or more first servers associated with the first site. According to the method, the first active response delay time and the first application response delay time are compounded to produce a first compounded response delay time. The method further comprises determining a second active response delay time and a second application response delay for a second site to produce a second compounded response delay time. The first compounded response delay time and the second compounded response delay time are compared to perform load balancing between the first site and the second site.

Claims

1. A system for load balancing of Domain Name System (DNS) requests, the system comprising:

a global site load balancer configured to;

select a first site load balancer associated with a first site and a second site load balancer associated with a second site, the first site and the second site being associated with a domain name of a client request received from a client;

instruct the first site load balancer to determine a first compounded response delay and instructing the second site load balancer to determine a second compounded response delay;

wherein the first site load balancer configured to;

based on the instructing, determine a first active response delay time between a DNS server and the first site;

determine a first application response delay time between the first site and one or more first servers associated with the first site;

determine the first compounded response delay time based on the first active response delay time and the first application response delay time;

wherein the second site load balancer is configured to;

based on the instructing, determine a second active response delay time between the DNS server and the second site;

determine a second application response delay time between the second site and one or more second servers associated with the second site;

determine the second compounded response delay time based on the second active response delay time and the second application response delay time; and

wherein the global site load balance is further configured to;

compare the first compounded response delay time and second compounded response delay time; and

based on the comparison, select a server from the one or more first servers associated with the first site and the one or more second servers associated with the second site; and

a database configured to store at least data associated with the first application response delay time, the first active response delay time, the second application response delay time, the second active response delay time, the first compounded response delay time, and the second compounded response delay time.

2. The system of claim 1, wherein the DNS server is a local DNS server.

3. The system of claim 1, wherein the server is selected to answer a DSN request.

4. The system of claim 1, wherein the selecting the server from the one or more first servers associated with the first site and the one or more second servers associated with the second site includes selecting a server associated with a lowest compounded response delay time.

5. The system of claim 1, wherein the determining the first active response delay time includes:

sending a request from a site load balancer associated with the first site to the DNS server, the request being associated with a first time;

receiving a response from the DNS server, the response being associated a second time; and

determining a time difference between the first time and the second time; and

wherein the determining the second active response delay time includes;

sending a request from a site load balancer associated with the second site to the DNS server, the request being associated with a first time;

receiving a response from the DNS server, the response being associated with a second time; and

determining a time difference between the first time and the second time.

6. The system of claim 1, wherein the determining the first application response delay time includes:

sending a request from a site load balancer associated with the first site to the one or more servers associated with the first site, the request being associated with a first time;

receiving a response from the one or more servers associated with the first site, the response being associated with a second time; and

determining a time difference between the first time and the second time; and

wherein the determining the second application response delay time includes;

sending a request from a site load balancer associated with the second site to the one or more servers associated with the second site, the request being associated with a first time;

receiving a response from the one or more servers associated with the second site, the response being associated with a second time; and

determining a time difference between the first time and the second time.

7. The system of claim 1, wherein the global site load balancer is further configured to coordinate the load balancing between the first site and the second site.

8. The system of claim 1, wherein the global site load balancer is further configured to:

determine a geographical location for the DNS server;

determine one or more sites from a plurality of sites based on a client request;

determine a geographical location for the one or more determined sites;

determine that the geographic location for the DNS server matches the geographic location for the one or more determined sites;

select the first site from the one or more determined sites, wherein a geographic location of the first site matches the geographic location for the DNS server; and

select the second site from the one or more determined sites, wherein a geographic location of the second site matches the geographic location for the DNS server.

9. The system of claim 8, wherein the global site load balancer is further configured to compose a table of responses, the table of responses including an IP address associated with the DNS server, an IP address associated with the first site, the first active response delay time, an IP address associated with the second site, and the second active response delay time.

10. A method for load balancing of Domain Name System (DNS) requests, the method comprising:

selecting, by a global site load balancer, a first site load balancer associated with a first site and a second site load balancer associated with a second site, the first site and the second site being associated with a domain name of a client request received from a client;

instructing, by the global site load balancer, the first site load balancer to determine a first compounded response delay and instructing the second site load balancer to determine a second compounded response delay;

based on the instructing, determining, by the first site load balancer, a first active response delay time between a DNS server and the first site;

determining, by the first site load balancer, a first application response delay time between the first site and one or more first servers associated with the first site;

determining, by the first site load balancer, the first compounded response delay time based on the first active response delay time and the first application response delay time;

based on the instructing, determining, by the second site load balancer, a second active response delay time between the DNS server and the second site;

determining, by the second site load balancer, a second application response delay time between the second site and one or more second servers associated with the second site;

determining, by the second site load balancer, the second compounded response delay time based on the second active response delay time and the second application response delay time;

comparing, by the global site load balancer, the first compounded response delay time and second compounded response delay time; and

based on the comparison, selecting, by the global site load balancer, a server from the one or more first servers associated with the first site and the one or more second servers associated with the second site.

11. The method of claim 10, wherein the DNS server is a local DNS server.

12. The method of claim 10, wherein the server is selected to answer a DSN request.

13. The method of claim 10, wherein the selecting the server from the one or more first servers associated with the first site and the one or more second servers associated with the second site includes selecting a server associated with a lowest compounded response delay time.

14. The method of claim 13, further comprising routing a client request to one of the first site and the second site, the ne of the first site and the second site being associated with the server associated with the lowest compounded response delay time.

15. The method of claim 10, wherein the determining the first active response delay time includes:

sending a request from a site load balancer associated with the first site to the DNS server, the request being associated with a first time;

receiving a response from the DNS server, the response being associated a second time; and

determining a time difference between the first time and the second time; and

wherein the determining the second active response delay time includes;

sending a request from a site load balancer associated with the second site to the DNS server, the request being associated with a first time;

receiving a response from the DNS server, the response being associated with a second time; and

determining a time difference between the first time and the second time.

16. The method of claim 10, wherein the determining the first application response delay time includes:

sending a request from a site load balancer associated with the first site to the one or more servers associated with the first site, the request being associated with a first time;

receiving a response from the one or more servers associated with the first site, the response being associated with a second time; and

determining a time difference between the first time and the second time; and

wherein the determining the second application response delay time includes;

sending a request from a site load balancer associated with the second site to the one or more servers associated with the second site, the request being associated with a first time;

receiving a response from the one or more servers associated with the second site, the response being associated with a second time; and

determining a time difference between the first time and the second time.

17. The method of claim 10, further comprising reporting results of the comparison between the first compounded response delay time and the second compounded response delay time to a global site load balancer, wherein the global site load balancer coordinates the load balancing between the first site and the second site.

18. The method of claim 10, further comprising:

determining a geographical location for the DNS server;

determining one or more sites from a plurality of sites based on a client request;

determining a geographical location for the one or more determined sites;

determining that the geographic location for the DNS server matches the geographic location for the one or more determined sites;

selecting the first site from the one or more determined sites, wherein a geographic location of the first site matches the geographic location for the DNS server; and

selecting the second site from the one or more determined sites, wherein a geographic location of the second site matches the geographic location for the DNS server.

19. The method of claim 18, further comprising composing a table of responses, the table of responses including an IP address associated with the DNS server, an IP address associated with the first site, the first active response delay time, an IP address associated with the second site, and the second active response delay time.

20. A system for load balancing of Domain Name System (DNS) requests, the system comprising:

a global site load balancer configured to;

select a first site load balancer associated with a first site and a second site load balancer associated with a second site, the first site and the second site being associated with a domain name of a client request received from a client;

instruct the first site load balancer to determine a first compounded response delay and instructing the second site load balancer to determine a second compounded response delay;

wherein the first site load balancer is configured to;

based on the instructing, determine a first active response delay time between a DNS server and the first site, wherein the determining the first active response delay time includes;

sending a request from a site load balancer associated with the first site to the DNS server, the request being associated with a first time;

receiving a response from the DNS server, the response being associated a second time; and

determining a time difference between the first time and the second time;

determine a first application response delay time between the first site and one or more first servers associated with the first site, wherein the determining the first application response delay time includes;

sending a request from a site load balancer associated with the first site to the one or more servers associated with the first site, the request being associated with a first time;

receiving a response from the one or more servers associated with the first site, the response being associated with a second time; and

determining a time difference between the first time and the second time;

determine the first compounded response delay time based on the first active response delay time and the first application response delay time;

wherein the second site load balancer is configured to;

based on the instructing, determine a second active response delay time between the DNS server and the second site, wherein the determining the second active response delay time includes;

sending a request from a site load balancer associated with the second site to the DNS server, the request being associated with a first time;

receiving a response from the DNS server, the response being associated with a second time; and

determining a time difference between the first time and the second time;

determine a second application response delay time between the second site and one or more second servers associated with the second site, wherein the determining the second application response delay time includes;

sending a request from a site load balancer associated with the second site to the one or more servers associated with the second site, the request being associated with a first time;

receiving a response from the one or more servers associated with the second site, the response being associated with a second time; and

determining a time difference between the first time and the second time;

determine the second compounded response delay time based on the second active response delay time and the second application response delay time; and

wherein the global site load balance is further configured to;

compare the first compounded response delay time and second compounded response delay time; and

based on the comparison, select a server from the one or more first servers associated with the first site and the one or more second servers associated with the second site; and

a database configured to store at least data associated with the first application response delay time, the first active response delay time, the second application response delay time, the second active response delay time, the first compounded response delay time, and the second compounded response delay time.