Abstract:
In an example method, an instruction to begin monitoring incoming traffic of a multicast data flow is received by a router. The instruction is received from a downstream router. The example method further includes monitoring incoming traffic of the multicast data flow. At least partly in response to determining that an expected amount of the incoming traffic of the multicast data flow is being received at the router, reporting to a network administrator device, a location of the router in the multicast data flow. Further, at least partly in response to determining that an expected amount of the incoming traffic of the multicast a data flow is not being received, sending, by the router and to an upstream router, an instruction to begin monitoring incoming traffic of the multicast data flow.
Abstract:
In an example method, an instruction to begin monitoring incoming traffic of a multicast data flow is received by a router. The instruction is received from a downstream router. The example method further includes monitoring incoming traffic of the multicast data flow. At least partly in response to determining that an expected amount of the incoming traffic of the multicast data flow is being received at the router, reporting to a network administrator device, a location of the router in the multicast data flow. Further, at least partly in response to determining that an expected amount of the incoming traffic of the multicast a data flow is not being received, sending, by the router and to an upstream router, an instruction to begin monitoring incoming traffic of the multicast data flow.
Abstract:
Techniques and mechanisms for a control plane approach for dense topologies that focusses on discovering shared ECMP groups in the control plane independent of per-prefix learning and then learning prefixes via these shared ECMP groups instead of learning prefixes via one next-hop at a time. In dense topologies, this approach helps minimize BGP path scale, corresponding signaling and enables control plane scaling that is an order of magnitude higher than a traditional eBGP control plane. During link and node topology changes, the described control plane approach enables control plane signaling that is prefix independent and an order of magnitude lower. A control plane approach to path-list sharing and prefix independent signaling on link and node topology changes enables prefix independent convergence (PIC) in scenarios that would not be possible otherwise with traditional FIB driven path-list sharing and PIC.
Abstract:
In one embodiment, a device deploys a first machine learning model to an inference location in a network. The first machine learning model is used at the inference location to make inferences about the network. The device receives, from the inference location, an indication that the first machine learning model is exhibiting poor performance. The device identifies a corrective measure for the poor performance that minimizes resource consumption by a model training pipeline of the device. The device deploys, based on the corrective measure, a second machine learning model to the inference location. The second machine learning model is used in lieu of the first machine learning model to make the inferences about the network.
Abstract:
This disclosure describes a method usable in a network that has a combination of mLDP-capable and BIER-capable devices. The disclosed method includes advertising, by an mLDP-capable multicast source, an indication of a BIER edge router that it has determined is usable as a path between the BIER devices and the mLDP-capable multicast source. A provider edge router can include in a multicast join message both an indication of the mLDP-capable multicast source as well as the indication of the BIER router advertised as being usable as the path to the mLDP-capable multicast source. The BIER devices can communicate with each other to pass a multicast join message to the BIER edge router that is indicated as being usable as the path to the mLDP-capable multicast source.
Abstract:
A method including receiving, at a first router of a plurality of routers, a first message from the plurality of routers. The first message includes a designated router priority and a weight for each respective router. Based on the designated router priorities, a designated router is elected and a one or more eligible group designated routers are determined. The method determines whether the first router is the designated router or the at least one eligible group designated router. If the first router is the designated router, the first router provides a second message to the remaining routers indicating the eligible group designated routers and their weights.
Abstract:
In an embodiment, a method comprises receiving a path advertisement comprising information about an available path and a well-known community value associated with the available path. A modified best path calculation is performed in response to receiving the available path either from a higher-ranked device or from a device that is not participating in diverse path calculation, resulting in creating a particular best path. The particular best path is advertised to other routers with or without a restriction indicator based on whether it is a client learned path or non-client iBGP peer learned path and based on whether the advertisement is directed to a client or a non-client iBGP peer.