A packet loss processing method and a network device are provided. The method includes: A first node obtains a first forwarding label of a first packet, where the first packet is a discarded packet. The first node determines, based on the first forwarding label, that the first node does not have a LSP corresponding to the first forwarding label. The first node sends a first message to a second node, where the first message includes the first forwarding label, and the first message is used to indicate that the first node does not have the LSP corresponding to the first forwarding label. The second node may be, for example, a peer node of the first node. The first node sends the message to the peer node, to indicate that the first node does not have the LSP corresponding to the forwarding label.

Methods and system for directing traffic flows to a fast data path or a slow data path are disclosed. Parsers can produce packet header vectors (PHVs) for use in match-action units. The PHVs are also used to generate feature vectors for the traffic flows. A flow training engine produces a classification model. Feature vectors input to the classification model result in output predictions predicting if a traffic flow will be long lived or short lived. The classification models are used by network appliances to install traffic flows into fast data paths or the slow data paths based on the predictions.

A label switching router for a switching network configured for source routing can be configured to modify one or more reported properties of a link associated with that router based on one or more link quality metrics. For example, a router can include a link with available bandwidth of 10 Gbps, a value that can be used by a headend when evaluating nodes of the network against a set of constraints required by a particular requested connection or tunnel. A link of that router may exhibit an increased bit error rate which can be used by the label switching router to artificially deflate available bandwidth, thereby reducing the number of label switching paths including the router are selected by the headend.

A sub-system is described which is operative to be used as a virtual Provider Edge (v PE) cluster of an SDN communication system. The sub-system comprises a plurality of network elements, wherein the v PE cluster further comprises one or more virtual routing engines for routing traffic to/from the plurality of network elements, the one or more virtual routing engines are configured to communicate with a managing entity and with a plurality of virtual forwarding engines, and wherein the managing entity is configured to manage operation of the one or more virtual routing engines and the plurality of virtual forwarding engines. According to another aspect, the sub-system comprises a plurality of network elements and a managing entity, wherein the network elements having each one or more ports to convey traffic therethrough, and wherein at least one of the ports associated with the sub-system is configured to serve a plurality of customers.

Some embodiments provide a novel method for deploying different virtual networks over several public cloud datacenters for different entities. For each entity, the method (1) identifies a set of public cloud datacenters of one or more public cloud providers to connect a set of machines of the entity, (2) deploys managed forwarding nodes (MFNs) for the entity in the identified set of public cloud datacenters, and then (3) configures the MFNs to implement a virtual network that connects the entity's set of machines across its identified set of public cloud datacenters. In some embodiments, the method identifies the set of public cloud datacenters for an entity by receiving input from the entity's network administrator. In some embodiments, this input specifies the public cloud providers to use and/or the public cloud regions in which the virtual network should be defined. Conjunctively, or alternatively, this input in some embodiments specifies actual public cloud datacenters to use.

A routing system for distributing multicast routing information for a multicast service includes a plurality of routers including a multicast source router and a plurality of multicast receiver routers, the plurality of routers providing a multicast service, wherein the routers are configured to exchange multicast information associated with the multicast service including identification of multicast sources and the multicast receivers.

Systems and methods for routing traffic through a network along Label-Switched Paths (LSPs) that may extend across multiple autonomous systems include performing Internet Protocol (IP) routing lookups as a packet is transmitted along the LSP. In one implementation, a packet having a predetermined value (which may be inserted by an upstream network device) is received at a network device after travelling along a first segment of an LSP. In response to identifying the predetermined label value of the packet, the network device may perform an IP routing lookup using IP routing information included in the packet to identify a next hop for the packet. The network device may then update a label of the packet such that the packet is routed along a second segment of the LSP and transmit the communication packet to the next hop.

A ring node N belonging to a resilient MPLS ring (RMR) provisions and/or configures clockwise (CW) and anti-clockwise (AC) paths on the RMR by: (a) configuring two ring node segment identifiers (Ring-SIDs) on the ring node, wherein a first of the two Ring-SIDs (CW-Ring-SID) is to reach N in a clockwise direction on the ring and a second of the two Ring-SIDs (AC-Ring-SID) is to reach N in an anti-clockwise direction on the ring, and wherein the CW-Ring-SID and AC-Ring-SID are unique within a source packet routing in networking (SPRING) domain including the ring; (b) generating a message including the ring node's CW-Ring-SID and AC-Ring-SID; and (c) advertising the message, via an interior gateway protocol, for receipt by other ring nodes belonging to the ring such that (1) a clockwise multipoint-to-point path (CWP) is defined such that every other one of the ring nodes belonging to the ring can be an ingress for the CWP and such that only the node is an egress for the CWP, and (2) an anti-clockwise multipoint-to-point path (ACP) is defined such that every other one of the ring nodes belonging to the ring can be an ingress for the ACP and such that only the node is an egress for the ACP.

Systems, methods, and devices for improved routing operations in a network computing environment. A system includes a network topology comprising a plurality of spine nodes and a plurality of leaf nodes, wherein a link between a first spine node and a first leaf node is inactive. The first spine node includes one or more processors configurable to execute instructions stored in non-transitory computer readable storage media. The instructions include receiving a packet to be transmitted to the first leaf node. The instructions include identifying an alternative spine node at a same level in the network topology. The instructions include attaching a tunnel label to the packet, wherein the tunnel label indicates the packet should be transmitted to the alternative spine node.

A control plane (CP) entity is to adaptively reroute user plane traffic of a mobile node (MN) with use of a segment routing (SR) for IPv6. A message indicating an attachment of the MN to the mobile network is received selecting a first user plane (UP) anchor node. A first set of home network prefixes (HNPs) are allocated to the MN. An IP traffic flow using a first HNP prefix is established between the MN and a correspondent node (CN) along a first network path—defined at least in part by the first UP anchor node and an anchor node of the CN. In response to a handover of the MN, a message indicating a subsequent attachment of the MN is received selecting a second UP anchor node. The second UP anchor node is instructed to host the first HNP prefix previously allocated by the first UP anchor node.