Abstract: Techniques are provided to decouple service chain structure from the underlying network forwarding state and allow for data plane learning of service chain forwarding requirements and any association between services function state requirements and the forward and reverse forwarding paths for a service chain. In a network comprising a plurality of network nodes each configured to apply a service function to traffic that passes through the respective network node, a packet is received at a network node. When the network node determines that the service function it applies is stateful, it updates context information in a network service header of the packet to indicate that the service function applied at the network node is stateful and that traffic for a reverse path matching the classification criteria is to be returned to the network node.

Abstract: A plurality of network nodes are deployed in a network, each network node configured to apply a service function to traffic that passes through the respective network nodes. A controller generates information for a service chain that involves application to traffic of one or more service functions at corresponding ones of the plurality of network nodes along a forward path through the one or more network nodes. The controller identifies one or more of the service functions within the service chain that is stateful. When one or more of the service functions of the service chain is stateful, the controller generates information for a reverse path through the one or more service nodes for the one or more stateful service functions. The controller binds a forward chain identifier for the forward path with a reverse chain identifier for the reverse path for the service chain.

Abstract: Techniques are provided to decouple service chain structure from the underlying network forwarding state and allow for data plane learning of service chain forwarding requirements and any association between services function state requirements and the forward and reverse forwarding paths for a service chain. In a network comprising a plurality of network nodes each configured to apply a service function to traffic that passes through the respective network node, a packet is received at a network node. When the network node determines that the service function it applies is stateful, it updates context information in a network service header of the packet to indicate that the service function applied at the network node is stateful and that traffic for a reverse path matching the classification criteria is to be returned to the network node.

Abstract: Techniques are presented to enable the instantiation of a service chain that is comprised of service functions belonging to one or more administrative domains. A service chain consisting of one or more service functions in one administrative domain is made available to another administrative domain through an advertisement. This enables the building of inter-domain service chains without the need to share between the administrative domains details about the service chains and service functions in the respective administrative domains.

Abstract: Presented herein are techniques useful in a network comprising a plurality of network nodes each configured to apply one or more service functions to traffic that passes through the respective network nodes. A network node receives packets encapsulated in a service header that includes information defining a first set of context headers stacked into an association of metadata that is relevant to one or more service functions within a service path comprised of one or more network nodes. The network node performs at least one of the service functions in the service path and rewrites the service header with a second set of context headers. The second set of context headers include metadata derived from performing the service function(s) at the network node.

Abstract: In general, techniques are described for automatically discovering services in computer networks. A service node comprising a control unit and an interface may implement the techniques. The control unit determines services provided by the service node and generates a routing protocol message that includes service discovery information related to the services. The interface transmits the routing protocol message to enable network devices of the network to discover the services provided by the service node based on the service discovery information. The interface then receives traffic via a path established based on the service discovery information included in the routing protocol message and configured so that the service node applies at least one of the services to the traffic received via the path. The control unit then applies the one or more services to the traffic received via the path.

Abstract: Presented herein are techniques useful in a network comprising a plurality of network nodes each configured to apply one or more service functions to traffic that passes through the respective network nodes. A network node receives packets encapsulated in a service header that includes information defining a variable set of context headers stacked into an association of metadata that is relevant to one or more service functions within a service path comprised of one or more network nodes. The network node interprets a forwarding state and a next-hop network node for the service path from the service header, and determines a service action or associated metadata from the set of context headers.

Abstract: In general, techniques are described for providing feedback loops for service engineered paths. A service node comprising an interface and a control unit may implement the techniques. The interface receives traffic via a path configured within a network to direct the traffic from an ingress network device of the path to the service node. The control unit applies one or more services to the traffic received via the path and generates service-specific information related to the application of the one or more services to the traffic. The interface then sends the service-specific information to at least one network device configured to forward the traffic via the path so that the at least one network device configured to forward the traffic via the path is able to adapt the path based on the service-specific information.

Abstract: Presented herein are service-function chaining techniques. In one example, a service controller in a network comprising a plurality of service nodes receives one is configured to identify one or more service-functions hosted by each of the service nodes. The service controller defines a service-function chain in terms of service-functions to be applied to traffic in the network and provides information descriptive of the service-function chain to a classifier node.

Abstract: In one example, a network device receives a packet to be forwarded according to a label switching protocol, determines a service to be performed on the packet by a service network device, sends a label request message to the service network device, wherein the label request message indicates support for labels having a particular length, wherein the particular length is larger than twenty bits (e.g., forty bits), and wherein the label request message specifies the service to be performed on the packet, receives, in response to the label request message, a label mapping message defining a label of the particular length, appends the label to the packet to form a Multi-Protocol Label Switching (MPLS)-encapsulated packet, and forwards the MPLS-encapsulated packet according to the label switching protocol.

Abstract: Presented herein are techniques in which a service proxy in a service node is configured to receive a packet encapsulated in a service header that includes a variable set of context headers. The service proxy is configured to use the context headers in the service header to map data in the packet to a local identifier that is associated with one of a plurality of service-functions hosted by the service node. The service proxy is further configured to forward the data in the packet to the service-function associated with the local identifier.

Abstract: Techniques are described for detecting failure or degradation of a service enabling technology function independent from an operational state of a service node hosting the service enabling technology function. For example, a service node may provide one or more service enabling technology functions, and service engineered paths may be traffic-engineered through a network to service node network devices that host a service enabling technology function. A monitor component at the service layer of the service node can detect failure or degradation of one or more service enabling technology functions provided by the service node. The monitor component reports detection of failure or degradation to a fault detection network protocol in a forwarding plane of the service node. The fault detection network protocol communicates with an ingress router of a service engineered path to trigger fast reroute by the ingress of traffic flows to bypass the affected service enabling technology function.

Abstract: Presented herein are techniques for dynamic creation of a unique service path for a service chain. In one example, a service controller and a plurality of service nodes are provided, each service node configured to apply a service function to traffic that passes through the respective service node. The service controller defines a service chain identifying a set of service functions and an order in which they are applied. The service controller receives an indication that the service chain has been instantiated at a classifier, and creates a unique service path for the service chain, wherein the unique service path includes the service chain and the classifier at which the service chain is instantiated.

Abstract: Presented herein are techniques performed in a network comprising a plurality of network nodes each configured to apply one or more service functions to traffic that passes the respective network nodes in a service path. At a network node, an indication is received of a failure or degradation of one or more service functions or applications applied to traffic at the network node. Data descriptive of the failure or degradation is generated. A previous service hop network node at which a service function or application was applied to traffic in the service path is determined. The data descriptive of the failure or degradation is communicated to the previous service hop network node.

Abstract: Presented herein are techniques useful in a network comprising a plurality of network nodes each configured to apply one or more service functions to traffic that passes through the respective network nodes. A network node receives packets encapsulated in a service header that includes information defining a variable set of context headers stacked into an association of metadata that is relevant to one or more service functions within a service path comprised of one or more network nodes. The network node interprets a forwarding state and a next-hop network node for the service path from the service header, and determines a service action or associated metadata from the set of context headers.

Abstract: Presented herein are techniques for use in a network environment that includes one or more service zones, each service zone including at least one instance of an in-line application service to be applied to network traffic and one or more routers to direct network traffic to the at least one service, and a route target being assigned to a unique service zone to serve as a community value for route import and export between routers of other service zones, destination networks or source networks via a control protocol. An edge router in each service zone or destination network advertises routes by its destination network prefix tagged with its route target. A service chain is created by importing and exporting of destination network prefixes by way of route targets at edge routers of the service zones or source networks.

Abstract: A plurality of network nodes are deployed in a network, each network node configured to apply a service function to traffic that passes through the respective network nodes. A controller generates information for a service chain that involves application to traffic of one or more service functions at corresponding ones of the plurality of network nodes along a forward path through the one or more network nodes. The controller identifies one or more of the service functions within the service chain that is stateful. When one or more of the service functions of the service chain is stateful, the controller generates information for a reverse path through the one or more service nodes for the one or more stateful service functions. The controller binds a forward chain identifier for the forward path with a reverse chain identifier for the reverse path for the service chain.

Abstract: Techniques are provided to decouple service chain structure from the underlying network forwarding state and allow for data plane learning of service chain forwarding requirements and any association between services function state requirements and the forward and reverse forwarding paths for a service chain. In a network comprising a plurality of network nodes each configured to apply a service function to traffic that passes through the respective network node, a packet is received at a network node. When the network node determines that the service function it applies is stateful, it updates context information in a network service header of the packet to indicate that the service function applied at the network node is stateful and that traffic for a reverse path matching the classification criteria is to be returned to the network node.

Abstract: In general, techniques are described for enhancing the Application-Layer Traffic Optimization (ALTO) service to supplement network topological grouping with location-based groupings to account for endpoint mobility. For example, as described herein, an ALTO server maintains physical location information for a network of one or more endpoints that provides a service. A PID generator of the ALTO server aggregates the endpoints into a set of one or more PIDs based at least on the physical location information for the endpoints, wherein each PID is associated with a subset of the endpoints. The ALTO server generates network and cost maps for the ALTO service that include PID entries to identify a respective subset of the endpoints associated with each of the set of PIDs and cost entries that incorporate cost that reflect physical distances among endpoints.

Abstract: In general, techniques are described for transmitting MPLS labels over a network. More specifically, a network device such a router receives a packet to be forwarded according to a label switching protocol, such as Multi-Protocol Label Switching (MPLS). The router may determine a service instance for the packet based on a client device from which the packet originated. The network device may determine one or more services to apply to the packet based on the service instance for the packet and generate a label which having a service instance portion and a service information portion. The network device may append the label to the packet to form an MPLS-encapsulated packet, and may forward the MPLS-encapsulated packet via an output interface according to the label switching protocol.