Abstract:
A system, computer-implemented method, and/or non-transitory computer-readable media may provide a warm start technique for cloud-hosted functions. This warm start technique may reduce latency associated with a time to execution of a cloud-hosted function, such as by determining a cloud-hosted function associated with an activated function graph and instantiating the cloud-hosted function ahead of its execution in association with the activated function graph (e.g. in anticipation of a later requested execution of the cloud-hosted function), and/or maintaining an already instantiated cloud-hosted function for a hold time that is dynamically determined for the cloud-hosted function (in anticipation of a later requested execution of the cloud-hosted function being made during that hold time).
Abstract:
Dynamically by-passing a service function instance on a service chain after the service function instance has processed the first few packets of a traffic flow may improve the overall processing efficiency of the service chain. When using a control plane mechanism, a service function instance communicates a by-pass indication to a control plane entity to prompt the control plane entity to re-route remaining portions of the traffic flow around the service function instance. When using a data plane mechanism, a service function instance includes a by-pass indication in a service chain header (SCH) of a packet in a traffic flow, and forwards the packet to a data plane entity. The by-pass indication will prompt the data plane entity to re-route remaining portions of the traffic flow around the service function instance.
Abstract:
A method implemented by a path computation element (PCE), comprising receiving a path computation request to compute a network path for a source-destination pair in a service chain (SC) network, wherein the path computation request comprises at least one network routing constraint and a service function (SF) input associated with a plurality of SFs, computing a plurality of network paths through the network for the source-destination pair according to the network routing constraint, selecting at least a first of the network paths according to the SF input, and sending a path computation response indicating at least the first network path in response to the received path computation request.
Abstract:
A method for managing a chain of service appliances. A method for interoperating with a legacy service appliance which does not understand/interpret the service chain header format. The method specifies a proxy device which receives a data packet with chain header that contains a chain ID. The chain ID identifies a particular service chain of network services to be performed on the data packet by a plurality of service appliances. The method removes a chain header from the data packet. The method sends the data packet to the service appliance via a logical port that corresponds to the data packet's chain ID. The method includes receiving the data packet back from the service appliance via the logical port. Lastly, the method includes restoring the chain header in the data packet based upon the logical port through which the data packet is received.
Abstract:
A method implemented by a network element (NE), comprising receiving a classification message comprising a classification rule for identifying a service function chain (SFC) in a network, wherein the SFC comprises an ordered set of service functions (SFs) that provides services to an application, and a dynamic application-specific contextual data associated with an operation of the application, receiving a first of a plurality of application data packets, determining that the first of the application data packets matches the classification rule, generating a first SFC packet by adding the dynamic application-specific contextual data to the first of the application data packets according to the classification rule to enable communication of the dynamic application-specific contextual data to at least one of the SFs in the SFC, and sending the first SFC packet towards a next NE according to an SF path in the network associated with the SFC.
Abstract:
A method implemented by a network controller, comprising receiving an address filter from a service chain orchestrator, wherein the address filter comprises a plurality of service instance (SI) addresses associated with a plurality of SIs in a network, obtaining network topology information from a plurality of service function (SF) forwarders controlled by the network controller, wherein the network topology information indicates a plurality of network devices communicatively coupled to the plurality of controlled SF forwarders, and wherein at least some of the network devices are SI hosting devices, and generating a service chain topology map by building mappings between at least some of the plurality of controlled SF forwarders, the SI hosting devices, and the plurality of SIs according to the network topology information and the address filter.
Abstract:
In a network switch of a software-defined network (SDN) architecture, a method for improving cache replacement (CR) efficiency implemented therein, the method comprising maintaining a flow table comprising a plurality of flow entries, computing a replacement index (RI) value for each of the plurality of flow entries resulting in a plurality of RI values, wherein computing an RI value for a flow entry is at least partially based on latency sensitivity of a forwarding path specified by the flow entry, and generating, based on at least some of the computed RI values, an eviction list comprising a number of list entries, wherein each of the list entries points to one of at least a fraction of the flow entries.
Abstract:
Metadata may be embedded in a service chain header (SCH) appended to a packet that is forwarded over a service chain path. The metadata may include information that is used to process the packet at a downstream service function chain (SFC) entity on the service chain path. The metadata TLV field may identify a service action to be performed by a downstream SFC entity. For example, the metadata TLV field may instruct the downstream SFC entity to drop the packet, to redirect the packet (or a traffic flow associated with the packet), to mirror a traffic flow, to terminate a communication connection, to start or stop a packet accounting, and/or to apply a higher grade of service. Alternatively, the metadata TLV field specifies an OAM service action list that identifies service actions that have been performed on the packet.
Abstract:
A system, computer-implemented method, and/or non-transitory computer-readable media may provide a warm start technique for cloud-hosted functions. A call is received from a web application. In response to the received call, a function graph is activated and includes a collection of functions associated with the web-application. The function graph also includes a plurality of states and transitions between the states. In response to the activation of the function graph, a cloud-hosted function associated with a particular state in the plurality of states included in the function graph is determined Before the particular state is triggered within the function graph to execute the cloud-hosted function, the determined cloud-hosted function is instantiated.
Abstract:
A method implemented in a network engine comprising receiving, by a service function (SF) orchestrator in the network engine, a registration request message from a third-party SF manager requesting registration of a SF comprising one or more SF instances in a network, wherein the registration request message comprises vendor identification information identifying a vendor of the SF and SF identification information identifying the SF, receiving a capability information message from the third-party SF manager indicating vendor-specific capability information associated with the SF, receiving a service request message from a service client requesting a network service and one or more policies for the service, generating the network service by utilizing the one or more SF instances according to the one or more policies and the vendor-specific capability information, and sending the one or more policies to the one or more SF instances.