Abstract: In general, techniques are described for enabling a network of network devices (or “nodes”) to provide redundant multicast streams from redundant multicast sources to an egress network node. In some examples, the egress network node (or a controller for the network) computes maximally redundant trees (MRTs) from the egress network node to a virtual proxy node virtually added to the network topology by the egress network node for redundant multicast sources of redundant multicast streams.

Abstract: An optical coupling device can couple incident light from a fiber into waveguides, but can reduce the coupling of return light from the waveguides into the fiber. A Faraday rotator layer can rotate by forty-five degrees, with a first handedness, respective planes of polarization of incident beams, and can rotate by forty-five degrees, with a second handedness opposite the first handedness, respective planes of polarization of return beams. A redirection layer can include at least one grating coupler that can redirect an incident beam of one polarization so that the redirected path extends within the redirection layer toward a first waveguide, and can redirect an incident beam of an opposite polarization so that the redirected path extends within the redirection layer toward a second waveguide. An optional birefringent layer can spatially separate incident beam having different polarizations, so that two single-polarization grating couplers can be used.

Abstract: In some embodiments, an apparatus includes a quadrature amplitude modulation (QAM) optical modulator which includes a first phase modulator (PM), a second PM, a tunable optical coupler (TOC), and an optical combiner (OC). The TOC is configured to split a light wave at an adjustable power splitting ratio to produce a first split light wave and a second split light wave. The first PM is configured to modulate the first split light wave in response to a first multi-level electrical signal to produce a first modulated light wave. The second PM is configured to modulate the second split light wave in response to a second multi-level electrical signal to produce a second modulated light wave. The OC is then configured to combine the first modulated light wave and the second modulated light wave to generate a QAM optical signal.

Abstract: Techniques are described for automatic provisioning of inter-control center communications protocol (ICCP) and automatic provisioning of virtual local area networks (VLANs) on an inter-chassis link (ICL) between multi-chassis link aggregation group (MC-LAG) peer devices. The MC-LAG peer devices may comprise two network devices included in an MC-LAG that is multi-homed to each of a plurality of MC-LAG client devices. In one example, the disclosed techniques enable detection of one or more VLANs configured on a multi-homed interface of the MC-LAG, and automatic provisioning of the detected VLANs on the ICL within the MC-LAG. In another example, the disclosed techniques enable determination of one or more ICCP parameters from MC-LAG configuration information, and automatic provisioning of ICCP over the ICL according to the determined ICCP parameters. The MC-LAG may be included within an enterprise switch of an enterprise network or within a data center switch of a data center network.

Abstract: A first component of a network device may provide an offload request to a second component of the network device to offload a data flow from the first component. The offload request may direct the second component to provide the data flow towards a destination device and bypass the first component. The first component may receive a beacon from the second component. The beacon may identify information regarding one or more data flows offloaded from the first component. The first component may process the one or more data flows based on the information regarding the one or more data flows included in the beacon and without receiving the one or more data flows.

Abstract: Techniques are disclosed for reducing the time required to instantiate network services in a service provider network to service requests by subscriber devices. In one example, an orchestration engine pre-creates pools of different virtual network functions (VNFs). Upon receiving a request to service network traffic from a subscriber device, the orchestration engine dynamically creates a service chain using the appropriate VNFs from the pools of different VNFs. In another example, the orchestration engine pre-creates pools of common service chains. Upon receiving a request to service network traffic from a subscriber device, the orchestration engine selects the appropriate service chain from the pools of service chains. After configuring the service chain, the orchestration engine issues instructions to a Software-Defined Networking (SDN) controller causing the SDN controller to update forwarding information in the service provider network to enable the service chain to service the subscriber traffic.

Abstract: Techniques are disclosed for a queuing system for network devices. In one example, a network device determines a transmit rate of packets from the queue. In one example the network device determines the transmit rate by determining a number of tokens used over a unit of time by a token bucket shaper for the queue to dequeue the packets from the queue, wherein each of the tokens represents a given number of bytes to be dequeued from the queue. The network device determines a temporal queue length of the queue based on a target queue latency and the determined transmit rate. Further, the network device adjusts at least one parameter of the queue based on the determined temporal queue length such that an actual queue latency of the queue at the determined transmit rate is equal to the target queue latency.

Abstract: Techniques for presenting information about a network, virtualization infrastructure, cluster, or other computing environment, which may involve presentation of user interfaces that may enable nuanced, unique, and/or comprehensive insights into how infrastructure elements, instances, and/or computing resources are being used and information about patterns of usage and/or utilization. Techniques for communicating, within a computing system, information used to create, update, and/or modify the user interfaces that present information about a network, virtualization infrastructure, cluster, or other computing environment. Techniques in accordance with one or more aspects of the present disclosure may involve use of separate interfaces for collecting or accessing data used to draw a user interface that presents information about a network, and for collecting or receiving data used to update the user interface as changes occur to the utilization of infrastructure elements represented within the user interface.

Abstract: In some examples, a controller for a network includes a path computation module that determines, for a plurality of LSPs or other flows having a common source, shortest paths of the network from the common source to respective destinations of the plurality of LSPs based at least on a minimum bandwidth. The path computation module further determines, after determining the shortest paths, a shortest path for the LSP of the plurality of LSPs as the shortest path of the shortest paths of the network from the common source to a destination for the LSP. A path provisioning module of the controller, after the path computation module determines the shortest path for the LSP and in response to the path computation modules routing the LSP to the shortest path for the LSP on a network model of the network, installs the LSP to the network as routed to the shortest path.

Abstract: A device may receive policy information associated with a first application group and a second application group. The device may receive network topology information associated with a network. The device may generate a first policy based on the policy information and the network topology information, and generate a second policy based on the policy information and the network topology information. The device may provide, to the virtual network device, information associated with the first policy to permit the virtual network device to implement the first policy in association with network traffic transferred between the first application group and the second application group. The device may provide, to the physical network device, information associated with the second policy to permit the physical network device to implement the second policy in association with network traffic transferred between the first application group and the second application group.

Abstract: In some embodiments, an apparatus includes an optical transceiver which includes a rate-adaptive forward error correction (FEC) encoder and a rate-adaptive FEC decoder. The rate-adaptive FEC encoder is configured to adjust a number of a set of known symbols associated with a codeword to achieve rate adaption. A length of the codeword is fixed. The rate-adaptive FEC encoder is configured to generate the codeword based on (1) a set of information symbols including the set of known symbols and a set of data symbols, and (2) a fixed number of a set of parity symbols generated using information symbols. The rate-adaptive FEC decoder is configured to receive a set of reliability values associated with a channel word, and expand the set of reliability values to produce an expanded set of reliability values. The rate-adaptive FEC decoder is further configured to decode the expanded set of reliability values.

Abstract: A network device may include a controller and a hardware forwarding component. The hardware forwarding component may receive a network packets and assign the network packets to multiple network queues. The network device may also obtain, using a microcode engine of the hardware forwarding component, and for each of the network queues, a measurement of queue depth, each measurement of queue depth being obtained from memory of the hardware forwarding component. Based on the measurements of queue depth, the network device may generate and transmit a telemetry packet.

Abstract: In general, techniques are described for providing software redundancy for Virtual Network Functions (VNF). In one example, a method includes, by a host process executed by an insertable service card of a network device, pinning, to a plurality of hardware-based processors, active threads of an active network function. The host process pins, to a single hardware-based processor, backup threads of a backup network function for the active network function, wherein the plurality of hardware-based processors does not include the single hardware-based processor. The host process pins, to the single hardware-based processor, management threads of the active and backup network functions. The single hardware-based processor executes the management threads of the active and backup network functions to cause the management thread of the backup network function to receive, from the management thread of the active network function, state data generated by the active threads.

Abstract: In some embodiments, an apparatus includes a memory and a processor operatively coupled to the memory. The processor is configured to be operatively coupled to a first optical transponder and a second optical transponder. The processor is configured to receive, from the second optical transponder, a signal representing a skew value of an optical signal and a signal representing a bit-error-rate (BER) value of the optical signal. The skew value is associated with a skew between an in-phase component of the optical signal and a quadrature component of the optical signal. The processor is configured to determine, based on at least one of the skew value or the BER value, if a performance degradation of the first optical transponder satisfies a threshold. The processor is configured to send a control signal to the first optical transponder to adjust a pulse shaping or a data baud rate of the first optical transponder.

Abstract: A method may include causing a signal to be transmitted that includes a plurality of wavelengths. The signal may be transmitted via an optical fiber that is associated with a particular wavelength. The particular wavelength may be included in the plurality of wavelengths. The method may include filtering the signal, based on the particular wavelength, to generate a filtered signal. The filtered signal may include the particular wavelength. The method may include detecting the filtered signal in association with the optical fiber. The method may include determining the particular wavelength based on the filtered signal. The method may include storing or providing information identifying at least one of the particular wavelength, the optical fiber, or a transmitter that transmitted the signal.

Abstract: In general, techniques are described for supporting bulk delivery of change of authorization data in authentication, authorization, and accounting (AAA) protocols, where delivery is performed as a change of authorization after a subscriber has successfully authenticated and initially authorized. In one example, the techniques are directed to a method including determining, by a RADIUS server for a service provider network, change of authorization data for services to which the subscriber of the service provider network has subscribed. The method further includes generating, by the RADIUS server, RADIUS messages that form a transaction between the RADIUS server and a network access server acting as a RADIUS client. The RADIUS messages provide all of the change of authorization data to the network access server prior to the network access server provisioning the services. The method further includes outputting, by the RADIUS server, the RADIUS messages to the network access server.

Abstract: Techniques are described for detecting egress network devices of a point-to-multipoint (P2MP) label switched path (LSP). For example, a network device may include one or more processors configured to identify a P2MP LSP for receiving multicast traffic from a multicast source for a specific multicast group for which the network device has an interested receiver, wherein the network device is to be an egress network device of the P2MP LSP; and send, to an ingress network device of the P2MP LSP, a P2MP egress identification message to add the network device as an egress network device of the P2MP LSP, wherein the one or more processors are further configured to output the P2MP egress identification message into a multipoint-to-point (MP2P) ring LSP for which the ingress network device of the P2MP LSP is a sole egress network device of the MP2P ring LSP.

Abstract: A computing device stores data defining a hierarchical navigation tree. For each respective user interface (UI) plugin of a plurality of UI plugins the device receives metadata for the respective UI plugin. The metadata for the respective UI plugin comprises a respective path descriptor for the respective UI plugin. For each respective node identified in the respective path descriptor for the respective UI plugin, the device marks the respective node identified by the respective path element as being active. The device outputs a UI for display. The UI comprises a pruned representation of the hierarchical navigation tree. For each respective node of a plurality of nodes in the hierarchical navigation tree, the pruned representation of the hierarchical navigation tree includes a label of the respective node in response to determining the respective node is marked as active. The UI may be a single-pane-of-glass interface that comprises nodes associated with separately developed UI plugins.

Abstract: An example network device includes a flow cache configured to store a flow cache entry that indicates a memory address referenced by one or more actions of the flow cache entry and a first learn index for the memory address, a memory address map configured to store a second learn index for the memory address, and one or more processors implemented in circuity. The network device is configured to receive a packet for the flow and obtain, from the flow cache entry for the flow, the memory address referenced by the one or more actions and the first learn index. The network device is further configured to determine the first learn index matches the second learn index and forward, in response to the determining, the packet using the one or more actions of the flow cache entry.

Abstract: When III-V semiconductor material is bonded to an oxide material, water molecules can degrade the bonding if they become trapped at the interface between the III-V material and the oxide material. Because water molecules can diffuse readily through oxide material, and may not diffuse as readily through III-V material or through silicon, forcing the III-V material against the oxide material can force water molecules at the interface into the oxide material and away from the interface. Water molecules present at the interface can be forced during manufacturing through vertical channels in a silicon layer into a buried oxide layer thereby to enhance bonding between the III-V material and the oxide material. Water molecules can be also forced through lateral channels in the oxide material, past a periphery of the III-V material, and, through diffusion, out of the oxide material into the atmosphere.