In one embodiment, a device predicts, for each of a set of paths via which traffic for an online application can be routed, a distribution of an application experience metric for the online application. The device computes, for different subsets of the set of paths, aggregated distributions of their distributions of the application experience metric predicted by the device. The device makes comparisons between the aggregated distributions for the different subsets of the set of paths. The device causes, based on the comparisons, the traffic for the online application to be routed via a particular subset of the set of paths.

A packet processing system having each of a plurality of hierarchical clients and a packet memory arbiter serially communicatively coupled together via a plurality of primary interfaces thereby forming a unidirectional client chain. This chain is then able to be utilized by all of the hierarchical clients to write the packet data to or read the packet data from the packet memory.

A packet processing system having each of a plurality of hierarchical clients and a packet memory arbiter serially communicatively coupled together via a plurality of primary interfaces thereby forming a unidirectional client chain. This chain is then able to be utilized by all of the hierarchical clients to write the packet data to or read the packet data from the packet memory.

A packet processing system having each of a plurality of hierarchical clients and a packet memory arbiter serially communicatively coupled together via a plurality of primary interfaces thereby forming a unidirectional client chain. This chain is then able to be utilized by all of the hierarchical clients to write the packet data to or read the packet data from the packet memory.

Network requests can be automatically routed between two or more computer subsystems in some examples. In one such example, a system can determine that a user is eligible for a service based on usage data relating to an account of the user. Based on determining that the account is eligible for the service, the system can activate the service for the user by communicating with a service subsystem. Subsequent to activating the service for the user, the system can receive a network request associated with the user and determine that the network request has a characteristic. Based on determining that the network request has the characteristic, the system can forward the request to the service subsystem. The service subsystem can complete the network request using the service.

An overlay network system includes point-of-presence (POP) devices each comprising a telemetry component, a billboard agent, and a packet routing daemon. The telemetry components generate latency measurements for the POP on which each is disposed. A centralized billboard service provides border gateway protocol (BGP) announcements and point-of-presence (POP) peering decisions to each of the billboard agent components. On on each of the POPs, the path finding component and corresponding telemetry component, agent component, and routing daemon cooperate to transform the BGP announcements, peering decisions, and latency measurements into routing tables and link selections for packet streams routed through the POPs.

Systems including a telemetry service, a graph service coupled to transform outputs of the telemetry service into path routes through an overlay network, a billboard service configured to transform the path routes into border gateway protocol (BGP) announcements and point-of-presence (POP) peering decisions, multiple agent components, and multiple routing daemons, each disposed on a different POP of the overlay network along with a corresponding one of the agent components. The daemons receive BGP announcements and peering decisions from the billboard service via the corresponding agent component and transform the BGP announcements and peering decisions into routing tables for the POPs.

Systems and methods implemented in a node in a cloud-based system include loading a data structure into memory, wherein the data structure includes cities mapped to cells where the cells cover all of the Earth; receiving a call with a given latitude and longitude of a user device; finding a closest city to the given latitude and longitude utilizing the data structure; and providing the closest city in response to the call. The systems and methods can also include utilizing the closest city for policy in the cloud-based system for the user device.

A method to automatically alter the ECRF route determination for call delivery to a PSAP, and better identify the appropriate responders for incidents where significant elevation or height of the caller's location is involved. A pre-provisioned database for elevation and height consideration is provided either as part of or integrated with the ECRF based on the use of this additional sub-addressing data (building, height, etc.), and cross referenced to a pre-provisioned elevation or height associated with each specific building or floor. The routing of requests for emergency services through the use of either service provider delivered geodetic or civic location is provided. Emergency services routing and responder determination is based on both sub-addressing information in combination with a cross reference database of vertical height identifiers by accessing a pre-populated database of this cross-reference information.

A control server receives probe data from a plurality of data centers indicating measured latencies with a first IP address associated with an origin server. The control server sums the measured latencies of a first data center having a lowest measured latency and a second data center. When the sum is below a threshold value, the control server determines the IP address to be an anycast IP address and selects a proper subset of the plurality of data centers as proxying data centers for other data centers in the plurality of data centers. When the sum is not below the threshold value, the control server determines the IP address to not be an anycast IP address and selects the first data center having the lowest measure latencies as the proxying data center for other data centers in the plurality of data centers.