Abstract: A first network device may provide a link discovery message to a second network device, and may identify a link based on the link discovery message. The first network device may provide, to the second network device, a first control channel message that identifies the link at the first network device, a current state of the link as a power on state, and a desired state of the link as a power sleep state, and may receive, from the second network device, a second control channel message that identifies the link at the second network device, the current state of the link as the power on state, and the desired state of the link as the power sleep state. The first network device may place the link in the power sleep state based on the first control channel message and the second control channel message.

Abstract: A network device may determine a bandwidth utilization and a power consumption by the network device, and may receive a carbon emission value and an electricity cost associated with the network device. The network device may determine weights for the power consumption, the carbon emission value, and the electricity cost, and may calculate one or more of a unit power metric, a per link power metric, a per component power metric, or a per device power metric based on the bandwidth utilization, the power consumption, the carbon emission value, the electricity cost, and the weights. The network device may perform one or more actions based on the one or more of the unit power metric, the per link power metric, the per component power metric, or the per device power metric.

Abstract: A first network device may create a port group for a plurality of links directly connected to a second network device, and may select the first network device as a controller network device and the second network device as a worker network device. The first network device may rank the plurality of links of the port group to generate a list of ranked links, and may select, from the list of ranked links, a highest ranked link as a control channel. The first network device may power off one or more of the plurality of links, except the control channel, based on one of a configuration, a policy, or a traffic prediction, and may identify a termination of a time period associated with powering off the one or more of the plurality of links. The first network device may power on the one or more of the plurality of links based on the termination of the time period.

Abstract: In some implementations, a network device may transmit, based on a time window, a request to disable a link for a candidate length of time. The network device may receive, based on the candidate length of time, an indication to disable the link for a length of time. The network device may power off one or more components associated with the link based on the indication to disable the link for the length of time. In some implementations, a network device may receive a request to disable a link for a candidate length of time. The network device may transmit, based on the candidate length of time and a time window, an indication to disable the link for a length of time. The network device may power off one or more components associated with the link based on the indication to disable the link for the length of time.

Abstract: This disclosure describes techniques for improving and/or reducing the power consumption by a router or other computing system. For example, this disclosure describes determining, by a computing system, an expected scale of a network device relative to a maximum scale of the network device; and adjusting, by the computing system and based on a comparison of the expected scale to the maximum scale, power consumption of the network device.

Abstract: In some examples, a computing system includes a memory and programmable processors in communication with the memory. The computing system is configured to obtain network information from a network device within a datacenter, wherein the network device includes at least one visual indicator. The computing system is further configured to determine a network event based on the network information. The computing system is further configured to instruct, based on the network event, the network device to configure the at least one visual indicator as active or inactive.

Abstract: In some examples, a computing system includes memory and one or more programmable processors in communication with the memory. The computing system is configured to visual indicator status information of a network device, wherein the visual indicator status information includes information for one or more virtual visual indicators of the network device to indicate a state of the network device or a state of one or more links associated with the network device. The computing system is further configured to generate, based on the visual indicator status information of the network device, a user interface that includes a representation of the network device and one or more virtual visual indicators indicating the state of the network device or the state of one or more links associated with the network device. The computing system is further configured to output, for display on a display device, the user interface.

Abstract: A device may receive a lock request associated with using an embedded device of a containerized environment from a first instance of an application being executed in a first container of the containerized environment. The device may perform a lock operation associated with the embedded device to permit the first instance of the application to use the embedded device and to prevent a second instance of the application, executing in a second container of the containerized environment, from using the embedded device. The device may monitor use of the embedded device during an access operation of the first instance of the application to detect an unlock event associated with unlocking the embedded device. The device may perform an unlock operation based on detecting the unlock event to permit the second instance of the application to use the embedded device.

Abstract: In some implementations, a network device may determine a maximum bandwidth requirement (MBR) associated with a network device. The network device may reduce based at least in part on the MBR, a power level of a component of the network device.

Abstract: A network device sends, via a first port of the network device and to a server device, first traffic, wherein the server device provides a NFV service line card of the network device, and wherein the first traffic is at least one of first management plane traffic associated with the NFV service line card, first control plane traffic associated with the NFV service line card, or first data plane traffic associated with the NFV service line card. The network device receives, via a second port of the network device and from the server device, second traffic, wherein the second traffic is at least one of second management plane traffic associated with the NFV service line card, second control plane traffic associated with the NFV service line card, or second data plane traffic associated with the NFV service line card.

Abstract: In the present disclosure, systems and techniques for network device hardware containerization is described. In one example, a network device of a network having a topology of network devices includes processing circuitry of a routing component wherein the processing circuitry generates user space containers to operate forwarding engines in each of a plurality of forwarding components of the network device; stores information for directing communications involving the plurality of forwarding components and the network devices; and configures, by at least one user space container running on the processing circuitry of the routing component, one or more corresponding forwarding engines in a respective forwarding component using the information.

Abstract: A device may receive a lock request associated with using an embedded device of a containerized environment from a first instance of an application being executed in a first container of the containerized environment. The device may perform a lock operation associated with the embedded device to permit the first instance of the application to use the embedded device and to prevent a second instance of the application, executing in a second container of the containerized environment, from using the embedded device. The device may monitor use of the embedded device during an access operation of the first instance of the application to detect an unlock event associated with unlocking the embedded device. The device may perform an unlock operation based on detecting the unlock event to permit the second instance of the application to use the embedded device.

Abstract: In the present disclosure, systems and techniques for network device hardware containerization is described. In one example, a network device of a network having a topology of network devices includes processing circuitry of a routing component wherein the processing circuitry generates user space containers to operate forwarding engines in each of a plurality of forwarding components of the network device; stores information for directing communications involving the plurality of forwarding components and the network devices; and configures, by at least one user space container running on the processing circuitry of the routing component, one or more corresponding forwarding engines in a respective forwarding component using the information.

Abstract: A network device may determine, based on at least one network egress characteristic associated with a network device, a measure of priority associated with a network address. The network device may provide the measure of priority to a plurality of other routers, determine that a particular network egress characteristic of the at least one network egress characteristic has changed, and update the measure of priority based on the particular network egress characteristic. Based on the updated measure of priority, the network device may perform an action.

Abstract: In general, techniques provide a mapping of host devices to different virtual router identifiers used to identify the source MAC address used for forwarding packets to the participating host devices. For example, a method may include receiving an Address Resolution Protocol (ARP) request for a first Internet protocol (IP) address from a host device, the first IP address comprising a virtual IP address of the virtual router. The method may also include determining a virtual router redundancy protocol (VRRP) virtual router identifier (VRID) associated with the first IP address. The method may further include generating a mapping between the host device and the determined VRID. The method may also include determining a virtual source MAC address of the virtual router based on the mapping and forwarding a second packet to the host device that specifies a virtual source MAC address for the second packet.

Abstract: A device may determine first configuration information associated with configuring a chassis. The device may configure the chassis in a first mode using the first configuration information to cause the chassis to perform routing for a network. The device may determine, after a first period of routing for the network, second configuration information associated with configuring the chassis. The second configuration information may relate to utilizing one or more computing resources of a server device external to the chassis to perform routing for the chassis. The device may configure the chassis in a second mode using the second configuration information to cause the chassis to perform, in a second period, routing for the network.

Abstract: In some examples, a computing device includes one or more processors and a physical interface device (IFD) connected to one or more of the processors. One or more of the processors are configured to detect a change in physical link status for a physical link in a network interface card, receive a list of active virtual machines associated with the physical link, and transmit a virtual IFD status notification message to the active virtual machines of virtual IFDs impacted by the physical link status change, the virtual IFD status notification message identifying the physical link status change.

Abstract: A first network device may activate the first network device as being associated with a Virtual Router Redundancy Protocol (VRRP) group. The first network device may receive, from a second network device, a duplicate address detection message. The first network device may compare a data link layer address associated with the duplicate address detection message and a Virtual Media Access Control (VMAC) address of the VRRP group. The first network device may disregard the duplicate address detection message after comparing the data link layer address and the VMAC address of the VRRP group.

Abstract: A configurable advertisement count and skew timer in a virtual router can be used to improve the speed with which a backup virtual router assumes the role of master upon the master router's failure. Enhanced VRRP packets having a type other than one may be used to cause MAC address movement from a failed master router to a backup router assuming the role of master router without placing an undue load on other routers in the network, such as by dropping the enhanced VRRP packets having a type other than one without processing the packets in the control plane of a receiving virtual router.

Abstract: A configurable advertisement count and skew timer in a virtual router can be used to improve the speed with which a backup virtual router assumes the role of master upon the master router's failure. Enhanced VRRP packets having a type other than one may be used to cause MAC address movement from a failed master router to a backup router assuming the role of master router without placing an undue load on other routers in the network, such as by dropping the enhanced VRRP packets having a type other than one without processing the packets in the control plane of a receiving virtual router.