Yahoo! Inc.

Excalibur Ip, LLC

David Apgar

Michael Christian

Erik James Reed

Igor Gashinsky

Jayanth Vijayaraghavan

Leif Hedstrom

Nitzan Katz

Ryan Troll

Michael F Christian

Randy Troll

Erik Reed

DNS wildcard beaconing. In one embodiment, for example, a computer-implemented method comprises: receiving a network request from a resolver to resolve a hostname, the network request from the resolver comprising a network address of the resolver, the hostname comprising a unique wildcard portion; storing first data representing an association between at least the unique wildcard portion and the network address of the resolver; receiving a network request from a client for a resource, the network request from the client comprising a network address of the client and at least the unique wildcard portion; storing second data representing an association between at least the unique wildcard portion and the network address of the client; based on the first data and the second data, associating the client with the resolver; and storing third data representing the association between the client and the resolver.

DNS wildcard beaconing

Techniques are described to determine clients residing behind LDNS resolvers. Web beacons instruct clients to retrieve zero-content images at unique hostnames. A request to the hostname is made by a client to an LDNS resolver. The LDNS sends the request to an authoritative server/beacon resolver for the hostname. The beacon resolver records the hostname with the LDNS resolver's IP address and responds with an IP address of a beacon collection server that is forwarded to the client by the LDNS. The client sends a request containing the unique hostname to the beacon collection server. The beacon collection server records the IP address of the client and the hostname. An aggregation server collects data from the beacon resolver and the beacon collection server. Using the hostnames as keys, IP addresses of clients are mapped to IP addresses of LDNS resolvers. Mapped data is exported to load balancing servers to determine routing.

DNS wildcard beaconing to determine client location and resolver load for global traffic load balancing

Techniques are described for directing connections between clients and the closest web server. Authoritative DNS resolvers of a network are placed at edges of the network. Using anycast, the authoritative DNS resolvers advertise routes of their destination netblock to the Internet. A request from a client to connect to the network is routed, based upon BGP tables, to the closest particular authoritative DNS resolver. Once the request is received, a response is sent to the client with the IP address of the closest web server. The closest web server is determined through in-network health check measurements, with the authoritative DNS resolvers dynamically selecting IP addresses closest to themselves. Routing protocols that directed the packet to the closest authoritative DNS resolver also dictate the route of subsequent traffic to the network. Thus, the closest web server selected by the authoritative DNS resolver is also the closest web server to the client.

Mapless global server load balancing of network traffic using anycast routing

Techniques are described for measuring TCP connection quality between a client and a plurality of data centers. A small amount of code, called a web beacon, is placed onto production web pages. When a client requests the production web page, the web page is served to the client. When the web page code is processed, the web beacon instructs the client to retrieve zero-content images from a plurality of data centers through TCP connections in the background. As each connection is made, a passive monitoring system measures and logs statistics about each TCP connection from the client to the data center. The statistics are aggregated into a database and may be sorted based upon ranges of IP addresses of clients and the connection quality measurements. The data is exported from the database to global load balancers to determine routing from subsequent clients to the plurality of data centers.

Method for determining network proximity for global traffic load balancing using passive TCP performance instrumentation

Growing community of inventors

San Francisco, CA, United States of America

David Apgar