摘要:
A system and method for advertising out-of-resources (OOR) conditions for entities, such as nodes, line cards and data links, in a manner that does not involve using a maximum cost to indicate the entity is “out-of-resources.” According to the technique, an OOR condition for an entity is advertised in one or more type-length-value (TLV) objects contained in an advertisement message. The advertisement message is flooded to nodes on a data network to inform them of the entity's OOR condition. Head-end nodes that process the advertisement message may use information contained in the TLV object to determine a path for a new label switched path (LSP) that does not include the entity associated with the OOR condition.
摘要:
A system and method for advertising out-of-resources (OOR) conditions for entities, such as nodes, line cards and data links, in a manner that does not involve using a maximum cost to indicate the entity is “out-of-resources.” According to the technique, an OOR condition for an entity is advertised in one or more type-length-value (TLV) objects contained in an advertisement message. The advertisement message is flooded to nodes on a data network to inform them of the entity's OOR condition. Head-end nodes that process the advertisement message may use information contained in the TLV object to determine a path for a new label switched path (LSP) that does not include the entity associated with the OOR condition.
摘要:
A virtual router (VR) communication arrangement enables services on different VRs executing on the same physical router to communicate without utilizing or substantially consuming communication resources, such as a network protocol stack and physical interfaces, of the physical router. The services are illustratively implemented as separately-scheduled VR processes executing on the physical router. A virtual router forwarding information base (vrFIB) is provided within a client socket library of each VR process and is used to determine whether the services are on the same physical router. If so, a lightweight interconnection is created between the services and a message (“packet”) is forwarded over that interconnection to effectuate communication. If the services are not on the same physical router, the packet is sent over the network protocol stack and communication is established using the communication resources of the router.
摘要:
The invention provides unique architectures and techniques for routing redundancy in a data switch configured to use label switching. Multiple label switch controllers (LSCs) each operate concurrently but independently of each other to provide routes through a data switching mechanism. Preferred embodiments provide a plurality of LSCs offering MPLS capabilities coupled to a single switch, such as an ATM switch. The similarly configured LSCs each can concurrently support a route for data (e.g., labeled ATM cells) within the data switching mechanism in parallel, thereby providing the ability to support redundant and multiple parallel data networks. The configuration is called a label switch router (LSR). A fully-meshed embodiment allows selected routes to share bandwidth on ports, while a fully parallel embodiment provides separate ports for selected routes. Since each LSC provides parallel routes with the other LSCs in an LSR, a communications between an LSR and a label edge router (LER) can use multipath routing to concurrently distribute data equally across the parallel routes for each destination. Alternatively, unipath routing techniques can select one route for use for each destination from the available routes concurrently offered by each LSC. In the event of a failure of one of the LSCs, multipath routing implementations can exclude transmission of data onto the failed network, while continuing to use the other parallel networks supported by non-failed LSCs in a concurrent manner. Alternatively, if a failure occurs with unipath routing, a new route offered by another LSC can be selected for data transfers. In either case, the LSC that fails does not need to provide state or connection information to the LSCs that operate subsequently to the failure, since they are already configured in parallel to support the same route. Upon an LSC failure, switch resources such as bandwidth that were used by the failed LSC are made available to the remaining non-failed LSCs. The design allows failures are handled gracefully without diminished network capacity or data loss resulting in a highly reliable routing capability provided within connection-based or circuit-switched networks.
摘要:
A virtual router (VR) communication arrangement enables services on different VRs executing on the same physical router to communicate without utilizing or substantially consuming communication resources, such as a network protocol stack and physical interfaces, of the physical router. The services are illustratively implemented as separately-scheduled VR processes executing on the physical router. A virtual router forwarding information base (vrFIB) is provided within a client socket library of each VR process and is used to determine whether the services are on the same physical router. If so, a lightweight interconnection is created between the services and a message (“packet”) is forwarded over that interconnection to effectuate communication. If the services are not on the same physical router, the packet is sent over the network protocol stack and communication is established using the communication resources of the router.