32results about How to "Guaranteed forwarding performance" patented technology

This invention discloses a method for setting up label switch path of MIPLS VPN tunnel including: a label switch router LSR in a network determines the forward equivalence FEC corresponding to the destination IP address of the MPLS VPN tunnel to distribute label to it firstly and set up a binding relation between the FEC and the distributed label and notifies the binding relation with the prior label to its upper reach LSR, which receives the binding relation notified by the lower reach LSR to process the binding relation with the prior label priorly. This invention also discloses a LSP set-up system and a device of the MPLS VPN tunnel.

The invention discloses a message forwarding method, a device and a system. In a forwarding network including a controller, a user side LB, a vBNG and a network side LB, when the network side LB receives a first message forwarded from the network side to a target terminal of the user side, by matching a target identifier used for identifying the target terminal of the first message to a first sharing chart item, a pre-planned forwarding path from a first output port of the network side LB to a first forwarding unit for processing the launching of the target terminal can be determined, so the first message sent to the target terminal can be precisely forwarded to the first forwarding unit for processing the online of the target terminal; it is avoided that the message forwarded from the network side to the user side may be forwarded to an improper forwarding unit in the vBNG; occasions that messages received on the network side should be forwarded across VMs in the vBNG are avoided; and forwarding performance of the vBNG is ensured.

The invention discloses a method for forwarding traffic based on a virtual switch cluster. The method comprises the following steps of: setting an aggregation group member list which stores all member information of an aggregation group; setting an aggregation group traffic forwarding member list which stores information of aggregation group members which are used for forwarding the traffic, wherein the aggregation group traffic forwarding member list only comprises aggregation group local member information in an initial state; and determining that the traffic of physical equipment exceeds the total bandwidth of members in the aggregation group traffic forwarding member list, or exceeds a threshold value related to the total bandwidth, adding nonlocal members which are selected from the aggregation group member list to the aggregation group traffic forwarding member list, and forwarding the traffic according to the modified aggregation group traffic forwarding member list. The invention also discloses a system for forwarding the traffic based on the virtual switch cluster correspondingly. By the method and the system, the traffic can be forwarded in the scene of the virtual switch cluster on the premise of occupying limited bandwidth of a stack link as few as possible, so that the performance of traffic forwarding in the scene of the virtual switch cluster is ensured.

The invention provides a method that a DSLAM device implements virtual MAC addresses, including; when learning the basic functions and addresses of an exchanger, according to user configured VMAC mapping method, a DSLAM device generates a VMAC address corresponding to the user MAC address, and when configuring user data in a Radius or broadband connection sever, inputs user marked VMAC and binds it with user name. The invention completes a two-way MAC address conversion operation by hardware device in order to implement the only mark of the user, which ensures transmitting performance of the system.

The embodiment of the invention provides a method and a device for maintaining a count value of a multicast counter. The method mainly comprises the following steps: acquiring a multicast message to be dequeued, allocating an engine to the multicast message to be dequeued, and recording an operation value, wherein the operation value is used for recording the information of the quantity of the dequeued multicast messages; and updating the operation value based on the dequeuing situation of the other multicast messages, and updating the count value of the multicast counter based on the operation value. The invention can remit the impact of the large-quantity high-rate multicast messages on the bandwidth of the common high-speed memories of QDR, DDR and the like to a certain extent, and can ensure the message forwarding performance of the system.

The invention relates to a device and method for realizing abnormal flow control, in particular to a processing method for controlling abnormal flow in communication data forwarding equipment. The present invention consists of two functional modules. The forwarding engine is responsible for data forwarding and actual traffic detection and control processing. The traffic analysis unit performs statistical analysis according to the packets sent by the forwarding engine, and uses the analysis results to set the forwarding engine and control the forwarding engine. the behavior of. The real-time analysis in the method adopts a sampling method, that is, to analyze short packets within a certain period of time, rather than continuously and dynamically analyzing them. The invention greatly reduces the processing workload, and ensures the forwarding performance of the forwarding engine, can control the most common abnormal flow in the existing network environment, and has strong practical value in the field of data communication.

The invention provides a border gateway protocol (BGP) routing decision method and comprises the following steps: setting border gateway protocol decision message which is sent to the neighbor after the updating of the BGP routing is finished; setting a decision waiting timer T1 which is started after the BGP neighbor is established; executing the BGP routing decision by the equipment according to the BGP decision message and the timer T1 arranged; besides, the invention also provides a BGP routing decision device. The technical scheme of the invention can be used for reducing the resource occupation of the BGP routing decision.

The invention relates to a method and a system for processing data packet loss, a readable storage medium and electronic equipment. The method includes acquiring current running locations of data forwarding processes when data packet forwarding fails in the data forwarding processes under the condition that data packet loss statistics modes are started; updating storage contents in statistical information storage regions according to the current running locations; releasing data packets which fail to be forwarded. The statistical information storage regions are used for storing running locations of the data forwarding processes whenever data packet forwarding fails and the frequencies of data packet forwarding failure at the running locations. According to the technical scheme, the method,the system, the readable storage medium and the electronic equipment have the advantages that workload on technicians can be effectively relieved, and data packet loss statistics can be carried out on the data packets which fail to be forwarded without modification on other codes after business logics are modified; the forwarding performance of data forwarding processes can be guaranteed, and thestability of the data forwarding processes can be improved.

The invention discloses a method and a device for a VPWS message to traverse a three-layer IP network. A control plane and a forwarding plane are included. A main control board multi-core CPU is takenas the core of the control plane, the multiple control plane protocols of a routing protocol, a LDP protocol, a GRE protocol and an ARP protocol are operated, and various table items including a routing table, an MPLS label table, a GRE session table, and an ARP table, which are required when the forwarding plane processes data, are generated. The forwarding plane is implemented by a main controlboard switching chip and an interface board FPGA. The main control board switch chip and the interface board FPGA are cooperated with each other to process a VPWS data packet. When an UNI interface receives the packet, the main control board switching chip is responsible for receiving the data packet, after corresponding processing, the data packet is sent to the interface board FPGA, and the FPGA packages and processes the data packet and then sends the data packet. When the NNI interface receives the packet, the interface board FPGA is responsible for receiving the data packet to carry outunpacking processing, and then the data packet is sent to the main control board switching chip, and the main control board switching chip processes the data packet and then sends the data packet out.The Wire-speed forwarding of VPWS over GRE can be realized and the forwarding performance of a device port is ensured.

The invention relates to virtual network equipment, a virtual overlay network and a configuration and message transmission method, and the virtual network equipment comprises a Vth end which is used for plugging a virtual machine/container and providing a virtual network card for the virtual machine/container; and the tun end is arranged in the linux system kernel, serves as a virtual tunnel configuration interface of the linux system kernel, configures the type of the virtual tunnel according to the received virtual tunnel type configuration information, and configures the identifier of the virtual tunnel according to the virtual tunnel identifier configuration information. The virtual overlay network constructed by the virtual network equipment provided by the invention does not depend on a third-party virtual switch OpenvSwitch, so that the forwarding performance of data traffic is effectively ensured. Therefore, when a plurality of tenants exist and the VPC network addresses of the plurality of tenants are overlapped, forwarding can also be performed based on the tun identifier, and the difficulty and workload of network configuration and network maintenance are reduced.

The embodiment of the invention discloses a data request processing method and device and a computer readable storage medium. The method is applied to flow forwarding equipment, and comprises the following steps: receiving a data request of which a target domain name is a domain name of the flow forwarding equipment, wherein a target domain name is further stored in the specified area in the datarequest, and the target domain name is different from the domain name of the flow forwarding equipment; verifying the target domain name according to a preset domain name list; updating the target domain name of the data request into the target domain name under the condition that the verification of the target domain name is passed; and forwarding the updated data request of the target domain name. According to the embodiment of the invention, there is no need to apply for a special path for each server in the back-end service system, the implementation is very convenient, path conflicts canbe avoided, and the flow forwarding performance can be ensured.

The invention provides a routing method based on a GPU. A routing table Table_24 is preserved in the GPU of a host display card, a routing table Table_long is preserved in a CPU of a host, when the prefix length of an inquired IP address is smaller than or equal to 24, a next-hop routing address is acquired from the routing table Table_24, or else access to the routing table Table_long is further conducted, and the next-hop routing address is acquired from the routing table Table_long. By the adoption of the method, design and implementation of a high-performance routing lookup forwarding engine are accelerated through the GPU, the CPU bottleneck of a software router is avoided, the defects in the performance of the software router are overcome, and high throughput is achieved.

The invention discloses an application layer adaptive data forwarding system for distinguishing real-time and non-real-time data streams, belongs to the technical field of data forwarding, and aims to solve the technical problem of how to optimize application layer data forwarding based on an application layer and improve data forwarding performance. According to the technical scheme, the system comprises a data sending scheduling module, a hard disk storage, a temporary non-real-time data buffer area, a non-real-time data buffer area and a plurality of real-time data buffer areas; wherein the real-time data buffer area is used for storing real-time data received by a data port corresponding to the forwarding node; the temporary non-real-time data buffer area is used for storing data transferred from the non-real-time data buffer area; the non-real-time data buffer area is used for caching normally received non-real-time data; and the data sending scheduling module is used for taking out the data in the real-time data sending buffer area according to a specified strategy, checking a source address field and a target address field in the data packet application data unit, and forwarding the data to a next hop according to a routing table.