A novel algorithm for packet classification that is based on a novel search structure for packet classification rules is provided. Addresses from all the containers are merged and maintained in a single Trie. Each entry in the Trie has additional information that can be traced back to the container from where the address originated. This information is used to keep the Trie in sync with the containers when the container definition dynamically changes.

A method of utilizing the same hardware network interface card (NIC) in a gateway of a datacenter to communicate datacenter tenant packet traffic and packet traffic for a set of applications that execute in the user space of the gateway and utilize a network stack in the kernel space of the gateway. The method sends and receives packets for the datacenter tenant packet traffic through a packet datapath in the user space. The method sends incoming packets from the NIC to the set of applications through the datapath in the user space, a user-kernel transport driver connecting the kernel network stack to the datapath in the user space, and the kernel network stack. The method receives outgoing packets at the NIC from the set of applications through the kernel network stack, the user-kernel transport driver, and the data path in the user space.

A communication system for transmitting data packets includes: at least one Access Node (AN) connectable to a user equipment (UE); a User Plane Function (UPF) component; and a data network (DN). The UPF component is a distributed component and comprises: at least one User Plane Function Edge (UPF-E) component and a User Plane Function Core (UPF-C) component, the UPF-E component being connected between the at least one AN and the UPF-C component, and the UPF-C component being connected between the UPF-E component and the data network (DN) or another UPF-C; and a UPF Management (UPF-M) component configured to terminate an N4 interface.

A Self-Describing Packet block (SDPB) is defined that allows concurrent processing of various fixed headers in a packet block defined to take advantage of multiple cores in a networking node forwarding path architecture. SPDB allows concurrent processing of various pieces of header data, metadata, and conditional commands carried in the same data packet by checking a serialization flag set upon creation of the data packet, without needing to serialize the processing or even parsing of the packet. When one or h more commands in one or more sub-blocks may be processed concurrently, the one or more commands are distributed to multiple processing resources for processing the commands in parallel. This architecture allows multiple unique functionalities each with their own separate outcome (execution of commands, doing service chaining, performing telemetry, allows virtualization and path steering) to be performed concurrently with simplified packet architecture without incurring additional encapsulation overhead.

Some embodiments relate to a link monitor for a switch having a PCIe-compliant interface. Some embodiments relate to an apparatus including a Peripheral Component Interconnect Express (PCIe)-compliant interface provided at a PCIe domain of a switch. The apparatus may also include a link monitor provided at a switching fabric of the switch that supports the PCIe domain of the switch. The link monitor to observe a factor-changing event of a state of a fabric link and obtain a value at least partially responsive to a weight computation, the weight computation for a factor associated with the factor-changing event. Related devices, systems and methods are also disclosed.

Methods and systems are disclosed. The method comprises: designating a first plurality of links from a first stack segment to a second stack segment as a first etherchannel link; designating a second plurality of links from the first stack segment to a third stack segment as a second etherchannel link, where the second stack segment and the third stack segment are in communication with a fourth stack segment; designating the first etherchannel link and the second etherchannel link as members of a hierarchical etherchannel link; and sending a packet from the first stack segment to the fourth stack segment using the hierarchical etherchannel link.

Examples described herein relate to a network interface that includes an initiator device to determine a storage node associated with an access command based on an association between an address in the command and a storage node. The network interface can include a redirector to update the association based on messages from one or more remote storage nodes. The association can be based on a look-up table associating a namespace identifier with prefix string and object size. In some examples, the access command is compatible with NVMe over Fabrics. The initiator device can determine a remote direct memory access (RDMA) queue-pair (QP) lookup for use to perform the access command.

Systems and methods of network packet switching use a table representation of a trie data structure to identify a timestamp (TS) range (or time range) for a received packet based on the packet timestamp (TS). The trie data structure is programmed with a plurality of predetermined time ranges. Each node in the trie data structure corresponds to a TS prefix and is associated with a corresponding predetermined time range. A search engine in the network switch can use the packet TS as a key to traverse the trie data structure and thereby matching the packet TS to a predetermined time range according to a Longest Prefix Match (LPM) process. Provided with the TS ranges of the incoming packets, various applications and logic engines in the network switch can accordingly process the packets, such as determining a new destination IP address and performing channel switch accordingly.

Methods and systems are provided for performing lossy dropping and ECN marking in a flow-based network. The system can maintain state information of individual packet flows, which can be set up or released dynamically based on injected data. Each flow can be provided with a flow-specific input queue upon arriving at a switch. Packets of a respective flow are acknowledged after reaching the egress point of the network, and the acknowledgement packets are sent back to the ingress point of the flow along the same data path. As a result, each switch can obtain state information of each flow and perform per-flow packet dropping and ECN marking.

Methods and systems are disclosed. The method comprises: designating a first plurality of links from a first stack segment to a second stack segment as a first etherchannel link; designating a second plurality of links from the first stack segment to a third stack segment as a second etherchannel link, where the second stack segment and the third stack segment are in communication with a fourth stack segment; designating the first etherchannel link and the second etherchannel link as members of a hierarchical etherchannel link; and sending a packet from the first stack segment to the fourth stack segment using the hierarchical etherchannel link.