Latencies and weightings in a domain name service (DNS) system
A method for determining metrics of a content delivery and global traffic management network provides service metric probes that determine the service availability and metric measurements of types of services provided by a content delivery machine. Latency probes are also provided for determining the latency of various servers within a network. The latency probe calculates, for example, the latency from its location to a client's location using the round trip time for sending a packet to the client to obtain the latency value for that client. DNS servers use the latency test results, along with traffic weightings, to determine a server to return for a given DNS name.
1. A method, comprising:
determining latencies from locations associated with content servers to locations associated with DNS clients, wherein said determinations are made by servers operated by a service provider;
receiving one or more weightings for traffic from a user of the service provider, the service provider operating one or more DNS servers on behalf of the user;
wherein the one or more weightings from the user indicate more traffic should be sent to an address of a first content server compared to an address of a second content server, wherein the traffic comprises requests for content;
determining, by the one or more DNS servers operated by the service provider, for a given domain name, a content server address to return to a requesting DNS client using the one or more weightings and the determined latencies, so as to cause requests for content to be made to said determined content server address.
2. The method of claim 1 , wherein the one or more DNS servers are located in a plurality of points-of-presence (POPs) distributed across a plurality of locations in the world.
3. The method of claim 1 , wherein the determined content server address comprises an IP address.
4. The method of claim 1 , wherein the traffic comprises HTTP requests for web content.
5. A system of one or more servers connected to a global computer network and having circuitry forming one or more processors and memory holding instructions that are executed by the one or more processors, the system comprising:
servers operated by a service provider that determine latencies from locations associated with content servers to locations associated with DNS clients;
servers operated by the service provider that receive one or more weightings for traffic from a user of the service provider, the service provider operating one or more DNS servers on behalf of the user;
wherein the one or more weightings from the user indicate more traffic should be sent to an address of a first content server compared to an address of a second content server, wherein the traffic comprises requests for content;
wherein the one or more DNS servers operated by the service provider determine, for a given domain name, a content server address to return to a requesting DNS client using the one or more weightings and the determined latencies, so as to cause requests for content to be made to said determined content server address.
6. The system of claim 5 , wherein the one or more DNS servers are located in a plurality of points-of-presence (POPs) distributed across a plurality of locations in the world.
7. The system of claim 5 , wherein the determined content server address comprises an IP address.
8. The system of claim 5 , wherein the traffic comprises HTTP requests for web content.
9. A non-transitory program storage medium readable by one or more computers, tangibly embodying a program of instructions executable by the one or more computers to perform the steps of:
determining latencies from locations associated with content servers to locations associated with DNS clients, wherein said determinations are made by servers operated by a service provider;
receiving one or more weightings for traffic from a user of the service provider, the service provider operating one or more DNS servers on behalf of the user;
wherein the one or more weightings from the user indicate more traffic should be sent to an address of a first content server compared to an address of a second content server, wherein the traffic comprises requests for content;
determining, by the one or more DNS servers operated by the service provider, for a given domain name, a content server address to return to a requesting DNS client using the one or more weightings and the determined latencies, so as to cause requests for content to be made to said determined content server address.
10. The non-transitory program storage medium of claim 9 , wherein the one or more DNS servers are located in a plurality of points-of-presence (POPs) distributed across a plurality of locations in the world.
11. The non-transitory program storage medium of claim 9 , wherein the determined content server address comprises an IP address.
12. The non-transitory program storage medium of claim 9 , wherein the traffic comprises HTTP requests for web content.