Abstract: An example method includes receiving a resource request for at least one compute and/or storage resource from a distributed computing system distributed among multiple data centers, determining a resource policy that is associated with the resource request, wherein the resource policy includes a rule specifying at least one metadata tag and at least one criterion associated with the at least one metadata tag, identifying at least one object included in a resource object model that complies with the rule of the resource policy, wherein the at least one object has an assigned value for the metadata tag that satisfies the at least one criterion, selecting a data center that is associated with the at least one object identified from the resource object model, and deploying, on the selected data center, the at least one compute or storage resource.

Abstract: A fabrication-tolerant non-linear waveguide taper for a waveguide transition can be designed by computing the scattering rate associated with the waveguide transition as a function of waveguide width of the waveguide taper for each of multiple sets of parameter values characterizing the waveguide transition (e.g., a set of nominal parameter values and sets of parameter values associated with process corners representing process variations from the nominal parameter values), determining an envelope of the computed width-dependent scattering rates, and computing a non-linear taper profile of the waveguide taper based on the envelope.

Abstract: A system and method for dynamically altering static parameters on a live network device is disclosed. The system includes a live network device having a plurality of parameters configured thereon that control the application of services to subscriber packet flows and a machine learning device operable to monitor the subscriber packet flows and apply a machine learned model to identify patterns in the monitored subscriber pack flows. The machine learning device is further operable to dynamically alter at least one of the plurality of parameters on the network device based upon the patterns in the monitored subscriber packet flows.

Abstract: The disclosed method may include (1) detecting, within at least one interface of a first endpoint device, a connectivity failure that disrupts a Layer 2 service based on an MPLS connection between the interface of the first endpoint device and at least one interface of a second endpoint device, (2) in response to detecting the connectivity failure, sending, to the second endpoint device, a first bidirectional BFD packet that prompts the second endpoint device to at least partially disable the interface of the second endpoint device, (3) determining that the connectivity failure has been corrected, and then (4) re-establishing the Layer 2 service based on the MPLS connection by sending, to the second endpoint device, a second BFD packet that prompts the second endpoint device to re-enable the interface of the second endpoint device. Various other apparatuses, systems, and methods are also disclosed.

Abstract: A policy controller executes algorithms to operate on a list of devices forming a computer network to generate outputs including one or more graphic user interfaces. The graphic user interfaces, when displayed on a display device, provide various versions of a visual representation of a network topology for the actual computer network or a computer network being modeled. The graphic user interfaces include graphic symbols representative of various devices included in the computer network that are arranged into one or more radial arrangements. The graphic user interfaces include graphic lines indicative of the physical interconnections between the devices, the graphic lines extending across the radial arrangement(s) and extending between the graphic symbols representative of devices to provide a visual representation of the interconnections that communicatively couple the devices.

Abstract: The disclosed embodiments provide for rules-based deployment of software installations. In some aspects, operational parameters for a computer system are monitored over time to generate a historical database of values for the operational parameters. The computer system may include multiple instances of a software installation. A portion of the multiple instances is updated with a new version of software. The operational parameters are then monitored to quantify whether the new version results in an improvement or degradation of performance of the computer system. The improvement or degradation is based on comparing values of the operational parameters after deployment to their historical values. Depending on the evaluation of the operational parameters after the installation, the installation may be rolled back if a degradation is indicated. Otherwise, the new software version may be propagated to additional installation instances.

Abstract: In one example, a network management system (NMS) and method discovers device roles for network devices. The NMS includes a learning module configured to include a learning model, the learning model trained to associate configuration segments for each of a plurality of network devices with device roles performed by the network devices. The NMS discovers a network service on a network, receives configuration information from the discovered network service and splits the configuration information received from the discovered network service into configuration segments based on a vendor neutral yang model associated with the discovered network service. The NMS then determines if the discovered network service performs one or more of the device roles performed by the network devices used to train the learning model, wherein determining includes applying the learning model to the configuration segments of the discovered network service.

Abstract: An example method includes determining, by a network controller, based on a high-level data model, vendor-agnostic device information for a first network device, translating the vendor-agnostic device information into vendor-specific device information, sending, to the first network device, first configuration information included in the vendor-specific device information to cause the first network device to switch into a maintenance mode and enable diversion of network traffic from the first network device to a second network device, responsive to verifying that the first network device has diverted the traffic, initiating maintenance procedures on the first network device while the first network device is in the maintenance mode, and sending, to the first network device, second configuration information included in the vendor-specific device information to cause the first network device to switch out of the maintenance mode and enable reversion of network traffic from the second device to the first network

Abstract: This disclosure is related to devices, systems, and techniques for controlling a flow of network traffic between two or more devices. For example, a network device includes a control unit, a forwarding unit including a forwarding manager including a server configured to store a tunnel hierarchy structure, and a packet processor. The packet processor is configured to receive, via an interface card of a set of interface cards, a packet including a packet header. The forwarding manager is configured to parse the packet header in order to identify a service corresponding to the packet, wherein the service is associated with a service color, identify, based on the tunnel hierarchy structure, a set of tunnels, wherein each tunnel of the set of tunnels is associated with a tunnel color, and determine whether at least one tunnel of a set of tunnels associated with the tunnel color is in an online state.

Abstract: Techniques are described by which a routing protocol, such as border gateway protocol (BGP), is extended to control propagation and importation of information using route targets (RTs) specified as bitmasks that encode link administrative group information. For example, a network control device (e.g., controller) is configured to allocate one or more subset of resources (e.g., nodes or links) of an underlay network to each of one or more virtual networks established over the underlay network. The controller generates a bitmask encoded with link administrative group information of the one or more links. The controller then outputs, to a plurality of provider edge (PE) routers that are participating in a respective virtual network, a routing protocol message to advertise the one or more subset of resources, wherein the routing protocol message includes a route target specified as the bitmask.

Abstract: In some examples, a switching system includes a plurality of fabric endpoints and a multi-stage switching fabric having a plurality of fabric planes each having a plurality of stages to switch data units between any of the plurality of fabric endpoints. A fabric endpoint of the fabric endpoints is configured to send, to a switch of a first one of the stages and within a first fabric plane of the plurality of fabric planes, a self-ping message destined for the fabric endpoint. The fabric endpoint is configured to send, in response to determining the fabric endpoint has not received the self-ping message after a predetermined time, an indication of a connectivity fault for the first fabric plane.

Abstract: A method includes modulating a digital signal via pulse amplitude modulation (PAM) and applying Nyquist shaping to the digital signal to generate a filtered digital signal. The method also includes converting the filtered digital signal into an analog signal and transmitting the analog signal in an optical communication channel via a dense wavelength division multiplexing (DWDM) scheme.

Abstract: Techniques are described in which a centralized controller, such as a software defined networking (SDN) controller, constructs a service chain that includes a physical network function (PNF) between a bare metal server (BMS) and a virtual execution element (e.g., virtual machine or container), or in some instances a remote BMS, or vice-versa. In accordance with the techniques disclosed herein, the controller may construct an inter-network service chain that includes PNFs, or a combination of PNFs and virtualized network functions (VNFs). The controller may construct an inter-network service chain to steer traffic between a BMS and a virtual execution element or remote BMS through an inter-network service chain using Virtual Extensible Local Area Network (VXLAN) as an underlying transport technology through the service chain.

Abstract: A computing device includes processing circuitry coupled to a memory device, and an orchestration agent configured for execution by the processing circuitry. The orchestration agent is an agent of an orchestrator for a computing infrastructure that includes the computing device, wherein the orchestration agent is configured to: detect configuration events from the computing device to determine local configuration state of the computing device; aggregate the local configuration state from the computing device with configuration state from a network controller to generate aggregated configuration state; and store the aggregated configuration state for application to operation of the computing device.

Abstract: The disclosure sets forth techniques, devices, systems, and methods for measuring a packet residency time in a network device. In some aspects, a network flow measurement protocol includes data fields in flow data records exported to a traffic collector, including a packet ingress time and a packet egress time. The data fields allow the calculation of the packet residency time within a network device, as well as the time required for the packet to traverse between two network devices in the network. A filter can be installed on one or more network devices in a network. For packets that match the filter criteria, the network device records the times of packet arrival and packet departure, and, in some aspects, a packet residency time of the packet with the network device. The network device exports the flow data record pertaining to this packet to a traffic flow data collector.

Abstract: In some examples, a method includes receiving, by an orchestrator for a virtualized computing infrastructure, namespace specification data the specifies a namespace, a first virtual network for the namespace, and a second virtual network for the namespace; sending, by the orchestrator to a network controller for the virtualized computing infrastructure, based on the namespace specification data, at least one request to create, for a virtual execution element to be deployed to the namespace and instantiated in a computing device of the virtualized computing infrastructure, respective virtual network interfaces for the first virtual network and the second virtual network; and send, by the network controller to the computing device, interface configuration data to configure a first virtual network interface for the first virtual network and a second virtual network interface for the second virtual network.

Abstract: An example network device executes a plurality of virtual machines (VMs). The network device is configured to determine to assign a number of Internet protocol (IP) addresses to the plurality of VMs, the number of IP addresses being greater than two, determine a first IP address, determine a range value that is equal to or greater than the number of IP addresses, generate a message according to Duplicate Address Protocol (DAD) including data indicating that the message includes a range of addresses, the data further indicating the first IP address and the range value; and send the message according to DAD via the network interface to one or more network devices to determine whether any IP address in a range starting with the first IP address and through the range value is in use by the one or more network devices.

Abstract: The disclosure describes examples where a first data center includes a first gateway router, a first set of computing devices, and a second set of computing devices. The first set of computing devices is configured to execute a software defined networking (SDN) controller cluster to facilitate operation of one or more virtual networks within the first data center. The second set of computing devices is configured to execute one or more control nodes to exchange route information, between the first gateway router and a second gateway router of a second data center different than the first data center, for a virtual network between computing devices within the second data center, and to communicate control information for the second data center to the second set of computing devices, wherein the one or more control nodes form a subcluster of the SDN controller cluster.

Abstract: A network device intercepts, from an application associated with a user space, a request message associated with obtaining information regarding a network state from a kernel. The network device directs the request message to a service daemon of the user space based on intercepting the request message, and determines, using the service daemon, network state information regarding the network state. The network device intercepts, from the service daemon, a response message associated with providing the network state information to the application, and directs an altered response message to the application based on intercepting the response message such that the altered response message identifies the kernel as a source of the response message and not the service daemon as the source of the response message.

Abstract: This disclosure describes techniques for improved multicasting of source VLAN multicast traffic. For example, a method includes receiving, by a switch device within a data center of a leaf and spine network, multicast traffic from a multicast source; sending, by the switch device and to a border device within the data center that is communicatively coupled to a multicast rendezvous point external to the data center, a source-active routing message to indicate that the switch device is receiving multicast traffic from the multicast source; receiving, by the switch device and from the border device, a response routing message including an extended community that indicates whether there are any interested multicast receivers; and configuring, by the switch device, a forwarding engine of the switch device based on the extended community.