Search All Patents in Edge Computing
Patent US10440104
Issued 2019-10-08
Load Balancing With Layered Edge Servers
N nodes are assigned to a first layer of nodes having a first domain name server (DNS) anycast Internet Protocol (IP) address and a first fully qualified domain name (FQDN). M nodes are assigned to a second layer of nodes having a second DNS anycast IP address and a second FQDN. When a request to resolve the first FQDN for the first layer of nodes is received by a DNS of a node of the first layer and a load on the ES of the node is less than a threshold, the DNS handles the request by returning an edge server (ES) anycast IP address for the ES of the node. When the load on the ES is greater than the threshold, the DNS offloads the request by returning the second FQDN so that the second FQDN of the second layer is resolved to the second DNS anycast IP address.
Much More than Average Length Specification
View the Patent Matrix® Diagram to Explore the Claim Relationships
USPTO Full Text Publication >
- 1. A non-transitory computer-readable storage medium storing computer-executable instructions for controlling a network of nodes, each node of the network of nodes having a domain name server (DNS) and an edge server (ES) to load balance traffic for the ES, the computer-executable instructions comprising instructions that when executed:
access a first DNS anycast Internet Protocol (IP) address and a first fully qualified domain name (FQDN), the first DNS anycast IP address and the first FQDN being associated with each node from a first layer of nodes of the network of nodes, wherein the first layer of nodes includes N number of nodes and N is an integer greater than one; and announce the first DNS anycast IP address of the first layer of nodes; and when a request to resolve the first FQDN for the first layer of nodes is received by the DNS of one node of the first layer of nodes:
when a load on the ES of the one node indicates that the DNS of the one node should not be offloading load from the ES of the one node, handle the request by returning an ES anycast IP address for the ES of the one node; and
when the load on the ES of the one node indicates that the DNS of the one node should be offloading load from the ES of the one node, offload the request by returning a second FQDN of a second layer of nodes of the network so that the second FQDN of the second layer of nodes is resolved to a second DNS anycast IP address, the second FQDN and the second DNS anycast IP address being associated with each node from the second layer of nodes, wherein the second layer of nodes includes M number of nodes and M is an integer greater than zero and less than N.
- 13. A network of nodes, each node of the network including a domain name server (DNS) and an edge server (ES), the network comprising:
a first layer of nodes including N nodes, wherein N is an integer greater than one, and wherein the first layer of nodes has:
a first DNS anycast Internet Protocol (IP) address for the DNSes of the ESes of the first layer; and
a first fully qualified domain name (FQDN) for the first layer of nodes, wherein the first DNS anycast IP address and the first FQDN are associated with each node from the first layer of nodes; and
a second layer of nodes including M nodes, wherein M is an integer greater than zero and less than N, wherein the second layer of nodes has:
a second DNS anycast IP address for the DNSes of the ESes of the second layer of nodes; and
a second FQDN for the second layer of nodes, wherein the second DNS anycast IP address and the second FQDN are associated with each node from the second layer of nodes, and wherein the DNS of one node of the first layer of nodes includes:
a component that either:
handles a request to resolve the first FQDN for the first layer by returning an ES anycast IP address for the ES of the one node; or
offloads the request to resolve the first FQDN for the first layer by returning the second FQDN of the second layer of nodes so that the second FQDN of the second layer of nodes is resolved to the second DNS anycast IP address of the second layer of nodes; and
a load controller that monitors load on the ES of the one node and that, based on a load on the ES of the one node, directs the DNS of the one node to handle requests or offload requests.
- 18. A method of load balancing nodes of a network, each node of the network including a domain name server (DNS) and an edge server (ES), the method comprising:
assigning N nodes to a first layer of nodes having a first DNS anycast Internet Protocol (IP) address and a first fully qualified domain name (FQDN), wherein the first DNS anycast IP address and the first FQDN is associated with each node from the first layer of nodes, and wherein N is an integer greater than one; assigning M nodes to a second layer of nodes having a second DNS anycast IP address and a second FQDN, wherein the second DNS anycast IP address and the second FQDN is associated with each node from the second layer of nodes, and wherein M is an integer greater than zero and less than N, when a request to resolve the first FQDN for the first layer of nodes is received by the DNS of one node of the first layer of nodes:
when a load on the ES of the one node is less than a threshold, handle the request by returning an ES anycast IP address for the ES of the one node; and
when the load on the ES of the one node is greater than the threshold, offload the request by returning the second FQDN of the second layer of nodes of the network so that the second FQDN of the second layer of nodes is resolved to the second DNS anycast IP address of the second layer of nodes.
