A network interface device has data path circuitry configured to cause data to be moved into and/or out of the network interface device. The data path circuitry comprises: first circuitry for providing one or more data processing operations; and interface circuitry supporting channels. The channels comprises command channels receiving command information from a plurality of data path circuitry user instances, event channels providing respective command completion information to the plurality of data path user instances; and data channels providing the associated data.

The invention relates to a method for transmitting a target data frame (fA) on a path comprising at least one router (R) that has input ports (P1, P2, P3), at least one output port (PS) and an arbitration unit (UA) configured so as to select a data frame from a plurality of data frames each coming from a different input port and competing for transmission by one and the same output port. The method comprises specifying, for each of the access ports of the router, data frames (fB, fC) competing with the target data frame for transmission by a target output port of the router. An end-to-end transmission time of the target data frame on the path is then measured while the arbitration unit selects the competing data frame (fB) before the target data frame (fA) for transmission by the target output port (PS).

The invention relates to a method for transmitting a target data frame (fA) on a path comprising at least one router (R) that has input ports (P1, P2, P3), at least one output port (PS) and an arbitration unit (UA) configured so as to select a data frame from a plurality of data frames each coming from a different input port and competing for transmission by one and the same output port. The method comprises specifying, for each of the access ports of the router, data frames (fB, fC) competing with the target data frame for transmission by a target output port of the router. An end-to-end transmission time of the target data frame on the path is then measured while the arbitration unit selects the competing data frame (fB) before the target data frame (fA) for transmission by the target output port (PS).

A network interface includes a processor, memory, and a cache between the processor and the memory. The processor secures a plurality of buffers for storing transfer data in the memory, and manages an allocation order of available buffers of the plurality of buffers. The processor returns a buffer released after data transfer to a position before a predetermined position of the allocation order.

The disclosed embodiments, collectively referred to as the “Message Ordering Buffer” or “MOB”, relate to an improved messaging platform, or processing system, which may also be referred to as a message processing architecture or platform, which routes messages from a publisher to a subscriber ensuring related messages, e.g., ordered messages, are conveyed to a single recipient, e.g., processing thread, without unnecessarily committing resources of the architecture to that recipient or otherwise preventing message transmission to other recipients. The disclosed embodiments further include additional features which improve efficient and facilitate deployment in different application environments. The disclosed embodiments may be deployed as a message oriented middleware component directly installed, or accessed as a service, and accessed by publishers and subscribers, as described herein, so as to electronically exchange messages therebetween.

A packet backpressure detection method and apparatus are provided. The method includes: a device which having a Peripheral Component Interconnect Express (PCIe) port storing a plurality of packets for transmission in a packet queue and storing a packet that is to be transmitted next in a first buffer, where the queue comprises a plurality of packets that are to be transmitted via the PCIe port; and the queue is stored in a second buffer; recording a storage duration of each packet stored in the first buffer, and accumulating the storage duration of each packet stored in the first buffer; removing the packet from the first buffer after the packet is transmitted via the PCIe port; and generating an indication of packet pressure at the PCIe port based on the accumulated storage duration.

A packet backpressure detection method and apparatus are provided. The method includes: a device which having a Peripheral Component Interconnect Express (PCIe) port storing a plurality of packets for transmission in a packet queue and storing a packet that is to be transmitted next in a first buffer, where the queue comprises a plurality of packets that are to be transmitted via the PCIe port; and the queue is stored in a second buffer; recording a storage duration of each packet stored in the first buffer, and accumulating the storage duration of each packet stored in the first buffer; removing the packet from the first buffer after the packet is transmitted via the PCIe port; and generating an indication of packet pressure at the PCIe port based on the accumulated storage duration.

The present invention relates to a data transmission system including a data exchange unit; wherein, to transmit a data frame, it passes successively at least through an interface module that is configured to receive said data frame from outside the transmission system; an analysis and filtering module responsible for processing said data frame which is received from the interface module before encapsulation; and an encapsulation module responsible for encapsulating said data frame processed by the analysis and filtering module, wherein two successive modules through which said data frame passes are connected to one another by an interconnection device each including a temporary memory for storing said frame and the read and write accesses to said memory being frequency-independent.

A large-scale network node simulation method based on Linux container is provided, which solves problems of low packet transmission efficiency and multi-thread creation in real-time simulation in a large-scale network scenario. The method includes: scheduling all container nodes in a scenario; managing, by a container node, a dynamic thread through an idle thread management queue, and setting a finite state machine and a function pointer for the dynamic thread; registering, by a source container node, an output queue with a next-hop container node, and informing the next-hop container node to allocate a dynamic thread for receiving and processing the output queue. Packet transmission is realized between the container nodes through data units created in a shared memory. The sending thread and the receiving thread dynamically adjust the number of dynamic threads by checking the state of the output queue.

A large-scale network node simulation method based on Linux container is provided, which solves problems of low packet transmission efficiency and multi-thread creation in real-time simulation in a large-scale network scenario. The method includes: scheduling all container nodes in a scenario; managing, by a container node, a dynamic thread through an idle thread management queue, and setting a finite state machine and a function pointer for the dynamic thread; registering, by a source container node, an output queue with a next-hop container node, and informing the next-hop container node to allocate a dynamic thread for receiving and processing the output queue. Packet transmission is realized between the container nodes through data units created in a shared memory. The sending thread and the receiving thread dynamically adjust the number of dynamic threads by checking the state of the output queue.