Method and system for selecting a host in a communications network

• US 7,617,274 B2
• Filed: 07/20/2004
• Issued: 11/10/2009
• Est. Priority Date: 09/13/1999
• Status: Expired due to Fees

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Packman, Eric W., Coughlin, Chesley B.
• Primary Examiner(s): Nguyen; Thu Ha T
• Application Number:
  US10/894,124
• Publication Number:
  US 20050044234A1
• Time in Patent Office: 1,939 Days
• Field of Search: 709/203, 709223-224, 709/227, 709/201, 709/225, 709/229, 718/105, 370/252, 707/2
• US Class Current: 709/203
• CPC Class Codes: H04L 41/5003 Managing SLA; Interaction between SLA and QoS
• CPC Class Codes: H04L 41/509 wherein the managed service relates to media content delivery, e.g. audio, video or TV
• CPC Class Codes: H04L 41/5093 wherein the managed service relates to messaging or chat services
• CPC Class Codes: H04L 43/0864 Round trip delays
• CPC Class Codes: H04L 61/4511 using domain name system [DNS]

Abstract

A system and method of selecting a host for a client in a client-server network, such as the Internet. The method includes initiating a plurality of responses, such as domain name system (DNS) responses, in a race to the local server and/or client. The method determines the most suitable host or server based on its shortest latency with the client.

Claims

1. A method of selecting a host for a client in a client-server network,

the method comprising:

receiving a request to identify the host for the client at an authoritative server;

instructing each of a plurality of servers to respond to the received request at a time that is related to the latency between each of the plurality of servers and the authoritative server, said latency being determined after said request;

sending a plurality of responses from the plurality of servers and the authoritative server to a local server after receiving the instruction, each response having an address representative of a respective host, said plurality of responses are sent to the local server at substantially the same time after a one direction latency is calculated between the authoritative server and each of the plurality of servers;

determining at least one latency involving data transmission between each of the plurality of servers and the local server and the authoritative server and the local server, the at least one latency being determined after the request; and

selecting a first arriving respective host address from a first arriving response of the plurality of responses.

2. The method as defined in claim 1, further comprising synchronizing the first server and the second server to a reference time.

3. The method as defined in claim 1, further comprising requesting resolution of a domain name of the host into an Internet protocol (IP) address.

4. The method as defined in claim 1, further comprising determining the latency between the authoritative server and each of the plurality of servers.

5. The method as defined in claim 1, wherein instructing each of the plurality of servers includes sending at least one packet to each of the plurality of servers, the packet indicating the instruction to send one of the plurality of responses from each of the plurality of servers.

6. The method as defined in claim 1, wherein instructing each of the plurality of servers includes synchronizing arrival of the at least one packet at each of the plurality of servers.

7. The method as defined in claim 1, wherein sending a plurality of responses includes sending a plurality of domain name system (DNS) responses from the plurality of servers.

8. The method as defined in claim 1, further comprising forwarding the first arriving respective host address to the client.

9. The method as defined in claim 1, further comprising establishing a data path between the client and a host represented by the first arriving respective host address.

10. The method as defined in claim 1, wherein receiving a request includes receiving at least one packet over a TCP/IP network.

11. A system for selecting a host for a client in a client-server network, the system comprising:

a local server in communication with the client-server network, said local server configured to send a request to identify a host;

a first server acting as an authoritative server in communication within the client-server network, the first server being configured to receive the request and to determine a future time at which to send a first response to the local server; and

a second server in communication with the first server, wherein the first server is further configured to instruct the second server to respond to the local server at the future time, and the second server is configured to send a second response to the local server at substantially the same time as the first response by the first server, and wherein each of the responses to the local server includes an address representative of a respective host the first and second responses being sent after a one direction latency is calculated between the first server and the second server;

wherein said local server is configured to determine a first latency involving data transmission between said first server and said local server and a second latency involving data transmission between said second server and said local server, the first latency and the second latency being determined after the request, the local server further configured to select a first arriving respective host address from a first arriving response, the first arriving response being one of the first response and second response.

12. The system as defined in claim 11, further comprising a third server in communication with the first server, wherein the first server is further configured to instruct the third server to respond to the local server, and the third server is configured to send a response to the local server at substantially the same time as the response by the second server.

13. A server system comprising:

a first server acting as an authoritative server coupled to a client-server network, said first server configured to receive a request, to determine a future start of race (SOR), and to instruct each of a plurality of servers to send a response to the request at said future SOR time resulting in a plurality of responses, each of said responses being sent after a one direction latency is calculated between the first server and each of the plurality of servers, said responses being sent to a local server, said local server configured to determine at least one latency involving data transmission between each of the plurality of servers and the local server and between the authoritative server and the local server, said at least one latency being determined after said request has been received, said local server configured to select a first arriving respective host address from a first arriving response of the plurality of responses.

14. The server system of claim 13 wherein said first server is to send the response to the request at said future SOR time.

15. The server system of claim 13 wherein the response includes an address representative of a respective host to each of said plurality of servers.

16. The server system of claim 15, wherein the local server is a domain name system server.

17. The server system of claim 15 wherein said response is a domain name service response.

18. The server system of claim 17, wherein the plurality of servers are domain name system servers.