Abstract: Some examples relate to determining routing decisions on a network device in a SD-WAN. In an example, a network device in a SD-WAN comprising a plurality of network nodes may receive respective routing information from a respective routing agent present on each node of the plurality of network nodes. The network device may determine an overlay network topology among the plurality of network nodes. Based on the overlay network topology and the respective routing information received from the respective routing agent, the network device may determine a respective routing decision for each node. The network device may distribute the respective routing decision to corresponding network node in the SD-WAN.

Abstract: One embodiment is directed to a system that comprises a network device, including at least a first port, which is configured to analyze information within one or more messages received during a session initiated by another network device. The system is configured to perform operations including determining a total number of sessions for the first port of the network device and determining whether the total number of sessions for the first port exceeds a threshold value. If the total number of sessions for the first port exceeds the threshold value, an application associated with the first port is classified as a peer-to-peer application. Thereafter, a policy may be enforced based on this classification.

Abstract: The present disclosure discloses a method and network device for achieving enhanced performance with multiple CPU cores in a network device having a symmetric multiprocessing architecture. The disclosed method allows for storing, by each central processing unit (CPU) core, a non-atomic data structure, which is specific to each networking CPU core, in a memory shared by the plurality of CPU cores. Also, the memory is not associated with any locking mechanism. In response to a data packet is received by a particular CPU core, the disclosed system will update a value of the non-atomic data structure corresponding to the particular CPU core. The data structure may be a counter or a fragment table. Further, a dedicated CPU core is allocated to process only data packets received from other CPU cores, and is responsible for dynamically responding to queries receives from a control plane process.

Abstract: The present disclosure discloses a method and network device for achieving enhanced performance with multiple CPU cores in a network device having a symmetric multiprocessing architecture. The disclosed method allows for storing, by each central processing unit (CPU) core, a non-atomic data structure, which is specific to each networking CPU core, in a memory shared by the plurality of CPU cores. Also, the memory is not associated with any locking mechanism. In response to a data packet is received by a particular CPU core, the disclosed system will update a value of the non-atomic data structure corresponding to the particular CPU core. The data structure may be a counter or a fragment table. Further, a dedicated CPU core is allocated to process only data packets received from other CPU cores, and is responsible for dynamically responding to queries receives from a control plane process.

Abstract: One embodiment is directed to a system that comprises a network device, including at least a first port, which is configured to analyze information within one or more messages received during a session initiated by another network device. The system is configured to perform operations including determining a total number of sessions for the first port of the network device and determining whether the total number of sessions for the first port exceeds a threshold value. If the total number of sessions for the first port exceeds the threshold value, an application associated with the first port is classified as a peer-to-peer application. Thereafter, a policy may be enforced based on this classification.