Verizon Digital Media Services Inc.

Edgecast Inc.

Edgio, Inc.

Marcel Eric Schechner Flores

Derrick Sawyer

Robert J Peters

Derek Shiell

Amir Reza Khakpour

Carl Tewksbury

Sree Priyanka Uppu

Stephen McQuistin

Harkeerat Singh Bedi

David Andrews

Sergio Leonardo Ruiz

Colin Rasor

Provided is a Routing Early Warning System ('REWS') that preemptively detects and corrects network issues based on control plane messaging. REWS receives control plane messages for network paths to a source node, groups the control plane messages to different bins based on time, detects an anomaly based on a number of a first set of control plane messages grouped to a particular bin differing, by a threshold amount, from a steady state number of control plane messages grouped to at least one other bin, and isolates a cause of the anomaly based on a number of updated paths and addressing of one or more nodes specified in the first set of control plane messages. REWS modifies routing of the source node data plane traffic before the anomaly significant impacts the data plane in response to detecting the anomaly and isolating the anomaly cause using the control plane messages.

Systems and methods for preemptive detection and correction of network issues based on control plane messaging

Dynamic caching policies and/or dynamic purging policies are provided for modifying the entry and eviction of content to the cache (e.g., storage and/or memory) of a caching server based on the current and past cache performance and/or demand. The caching server may modify or replace a configured policy when cache performance is below one or more thresholds. Modifying the caching policy may change caching behavior of the caching server by changing the conditions that control the content that is entered into cache or the content that is deferred and not entered into cache after a request. This may include assigning different probabilities for entering the same content into cache based on different caching policies. Modifying the purging policy may change eviction behavior of the caching server by changing the conditions that control the cached content that is selected and removed from cache.

Dynamic caching and eviction policy in different points-of-presence of a content delivery network

Gateway devices at different sites of a primary Anycast network provide access to the sites by advertising a first set of Anycast addresses. A secondary shadow Anycast network advertises different second sets of Anycast addresses from the different sites in order to predetermine traffic shifts that occur as a result of changing one or more of the second set of Anycast addresses that are advertised from one or more of the sites. A traffic shifting device may implement a predetermined traffic shift in the primary Anycast network by selecting a particular second set of network addresses that produces a traffic shift at least equal to the predetermined traffic shift, mapping the particular second set of network addresses to a modified first set of addresses, and modifying routing in the primary Anycast network by advertising the modified first set of addresses instead of the first set of addresses.

Predictive Anycast traffic shaping

Dynamic caching and eviction

Multiple hit load balancing provides a quasi-persistent request distribution for encrypted requests passing over secure connections as well as for multiple requests passing over the same connection. The multiple hit load balancing involves tracking object demand at each server of a set of servers. The multiple hit load balancing further involves dynamically scaling the servers that cache and directly serve frequently requested objects based on the demand that is tracked by each of the servers. For infrequently requested objects, the servers perform a peer retrieval of the objects so to limit the number of the same object being redundantly cached by multiple servers of the set of servers.

Multiple hit load balancing

Automated steady state traffic management is provided for a distributed platform through immediate or real-time simulation of the capacity and performance impacts associated with shifting different load increments to different Points-of-presence (PoPs) of the distributed platform and by automatic and dynamic traffic management reconfiguration in response to an optimal set of changes identified from the simulation. A system produces data models to track the current distributed platform state and detect deviates from the steady state. Using the data models and scoring functions, the system scores the impact that different shifts of load to different destinations have on the overall distributed platform. The scoring reveals the optimal set of traffic management configuration changes that restore the steady state with the least capacity and performance impact.

Automated steady state traffic management

A load balancing appliance distributes data packets across different virtual connections for ongoing communications with clients over a connectionless communication protocol including User Datagram Protocol (UDP) or Quick Internet UDP Connections (QUIC). The load balancing appliance a distributor that binds and listens on a port through which the connectionless traffic is received. The distributor distributes the traffic to a different set of managers at each interval based on each set of managers binding to and listening on a different set of ports. Each set of managers establishes and manages virtual connections establishing during a particular interval, wherein managing a virtual connection involves creating a secondary connection to a back-end server selected for engaging in ongoing communications with a client of the virtual connection, and performing any packet conversions between the virtual connection with the client and the secondary connection to the back-end server in order to bridge the connections.

Systems and methods for load balancing virtual connection traffic

Some embodiments increase throughput across a connection between a host and a client by initializing the congestion window for that connection dynamically using a previously settled value from a prior instance of the connection established between the same or similar endpoints. An initialization agent tracks congestion window values for previously established connections between a host and various clients. For the tracked congestion window values of each monitored connection, the initialization agent stores an address identifying the client endpoint. When establishing a new connection, the initialization agent determines if the new connection is a recurring connection. A new connection is recurring when the new connection client address is similar or related to an address identified for a previous monitored connection. For a recurring connection, the initialization agent initializes the new connection congestion window using a value derived from the tracked congestion window values of the recurring connection.

Growing community of inventors

Los Angeles, CA, United States of America

Marcel Eric Schechner Flores