Abstract: In general, techniques are described for a computing device including a virtual router, a pod comprising a container, and a network plugin. The virtual router includes a virtual router agent. The network plugin includes processing circuitry configured to receive, from the virtual router agent, an indication of an interface type for a virtual network for the pod and to configure, for the pod, a virtual network interface having the interface type, the virtual network interface for communicating on the virtual network.

Abstract: Techniques are described for performing latency-aware load balancing. In some examples, a computing device communicably coupled to a plurality of service endpoints that are in motion with respect to the computing device may receive data to be processed. The computing device may select, based at least in part on a communication latency of each of the plurality of service endpoints and a predicted compute latency of each of the plurality of service endpoints, a service endpoint out of the plurality of service endpoints to process the data. The computing device may send the data to the selected service endpoint for processing.

Abstract: In general, techniques are described for a computing device including a virtual router, a pod comprising a container, and a network plugin. The virtual router includes a virtual router agent. The network plugin includes processing circuitry configured to receive, from the virtual router agent, an indication of an interface type for a virtual network for the pod and to configure, for the pod, a virtual network interface having the interface type, the virtual network interface for communicating on the virtual network.

Abstract: Techniques are described for performing latency-aware load balancing. In some examples, a computing device communicably coupled to a plurality of service endpoints that are in motion with respect to the computing device may receive data to be processed. The computing device may select, based at least in part on a communication latency of each of the plurality of service endpoints and a predicted compute latency of each of the plurality of service endpoints, a service endpoint out of the plurality of service endpoints to process the data. The computing device may send the data to the selected service endpoint for processing.

Abstract: Techniques are described for performing latency-aware load balancing. In some examples, a computing device communicably coupled to a plurality of service endpoints that are in motion with respect to the computing device may receive data to be processed. The computing device may select, based at least in part on a communication latency of each of the plurality of service endpoints and a predicted compute latency of each of the plurality of service endpoints, a service endpoint out of the plurality of service endpoints to process the data. The computing device may send the data to the selected service endpoint for processing.

Abstract: In general, techniques are described for deploying a logically-related group of one or more containers (“pod”) that supports the Data Plane Development Kit (DPDK) to support fast path packet communication on a data channel between a virtual router and the pod. In an example, a computing device comprises a virtual router comprising processing circuitry and configured to implement, in a computing infrastructure that includes the computing device, a virtual network to enable communications among virtual network endpoints connected via the virtual network. The computing devices comprises a pod comprising a containerized application, wherein the virtual router and the pod are configured to create a Unix domain socket using a file system resource that is accessible by the pod and by the virtual router and is not accessible by any other pods deployed to the computing device.

Abstract: In general, techniques are described for a computing device including a virtual router, a pod comprising a container, and a network plugin. The virtual router includes a virtual router agent. The network plugin includes processing circuitry configured to receive, from the virtual router agent, an indication of an interface type for a virtual network for the pod and to configure, for the pod, a virtual network interface having the interface type, the virtual network interface for communicating on the virtual network.

Abstract: Techniques for enabling offline, intelligent load balancing of Stream Control Transmission Protocol (SCTP) traffic are provided. According to one embodiment, a load balancer can receive one or more SCTP packets that have been replicated from a network being monitored. The load balancer can further recover an SCTP message from the one or more SCTP packets and can map the SCTP message to an egress port based on one or more parameters decoded from the SCTP message and one or more rules. The load balancer can then transmit the SCTP message out of the egress port towards an analytic probe or tool for analysis.

Abstract: Techniques for enabling offline, intelligent load balancing of Stream Control Transmission Protocol (SCTP) traffic are provided. According to one embodiment, a load balancer can receive one or more SCTP packets that have been replicated from a network being monitored. The load balancer can further recover an SCTP message from the one or more SCTP packets and can map the SCTP message to an egress port based on one or more parameters decoded from the SCTP message and one or more rules. The load balancer can then transmit the SCTP message out of the egress port towards an analytic probe or tool for analysis.

Abstract: Techniques for performing near-uniform load balancing in a visibility network based on usage prediction are provided. According to one embodiment, a packet broker of the visibility network can receive a control packet replicated from a core network, where the control packet includes a user or device identifier and a request to create a user session for a user identified by the user/device identifier. The packet broker can further determine, based on the user/device identifier and one or more other parameters, a rank value for the user session, where the rank value indicates an amount of network traffic that the user is likely to generate in the core network during the user session. The packet broker can then select an egress port for the user session based on the rank value and forward subsequent control and data traffic for the user session through the selected egress port.

Abstract: Techniques for implementing a smart filter generator in a visibility network are provided. In one set of embodiments, the smart filter generator can maintain at least one mapping between (1) a first-order parameter found in network traffic replicated from a core network monitored by the visibility network, and (2) a second-order parameter related to the first-order parameter, where the second-order parameter is not found in the network traffic replicated from the core network. The smart filter generator can further receive, from a user, a user-defined packet filter definition comprising a filtering criterion that makes use of the second-order parameter. The smart filter generator can then translate, based on the at least one mapping, the filtering criterion into a version that makes use of the first-order parameter, and can generate a new packet filter comprising the translated version of the filtering criterion.

Abstract: Techniques for performing near-uniform load balancing in a visibility network based on usage prediction are provided. According to one embodiment, a packet broker of the visibility network can receive a control packet replicated from a core network, where the control packet includes a user or device identifier and a request to create a user session for a user identified by the user/device identifier. The packet broker can further determine, based on the user/device identifier and one or more other parameters, a rank value for the user session, where the rank value indicates an amount of network traffic that the user is likely to generate in the core network during the user session. The packet broker can then select an egress port for the user session based on the rank value and forward subsequent control and data traffic for the user session through the selected egress port.

Abstract: A network visibility system provided according to an aspect of the present disclosure forms rules for routing of packets to appropriate analytic server, based on IP addresses discovered while processing packets. Due to such discovery and forming of rules based on discovery, manual configuration of the network visibility system can be avoided. In an embodiment, the network visibility system comprises a packet router and a router controller. The router controller receives the examined packets from the packet router and configures the packet router with the formed rules.

Abstract: Techniques for implementing a smart filter generator in a visibility network are provided. In one set of embodiments, the smart filter generator can maintain at least one mapping between (1) a first-order parameter found in network traffic replicated from a core network monitored by the visibility network, and (2) a second-order parameter related to the first-order parameter, where the second-order parameter is not found in the network traffic replicated from the core network. The smart filter generator can further receive, from a user, a user-defined packet filter definition comprising a filtering criterion that makes use of the second-order parameter. The smart filter generator can then translate, based on the at least one mapping, the filtering criterion into a version that makes use of the first-order parameter, and can generate a new packet filter comprising the translated version of the filtering criterion.

Abstract: Techniques for performing anomaly detection and prediction in a packet broker of a visibility network are provided. According to one embodiment, the packet broker can apply one or more machine learning models to network traffic that is replicated from a core network. The packet broker can further detect or predict, based on the application of the one or more machine learning models, the occurrence of a network traffic anomaly in the core network. The packet broker can then take one or more predefined actions in response to the detection/prediction of the anomaly.

Abstract: Techniques for enabling offline, intelligent load balancing of Stream Control Transmission Protocol (SCTP) traffic are provided. According to one embodiment, a load balancer can receive one or more SCTP packets that have been replicated from a network being monitored. The load balancer can further recover an SCTP message from the one or more SCTP packets and can map the SCTP message to an egress port based on one or more parameters decoded from the SCTP message and one or more rules. The load balancer can then transmit the SCTP message out of the egress port towards an analytic probe or tool for analysis.

Abstract: A network visibility system provided according to an aspect of the present disclosure forms rules for routing of packets to appropriate analytic server, based on IP addresses discovered while processing packets. Due to such discovery and forming of rules based on discovery, manual configuration of the network visibility system can be avoided. In an embodiment, the network visibility system comprises a packet router and a router controller. The router controller receives the examined packets from the packet router and configures the packet router with the formed rules.