401results about How to "Improve forwarding performance" patented technology

An adaptive antenna used in a receive only mode with a separate omnidirectional transmit antenna. The arrangement is especially effective for small, handheld wireless devices. The transmit antenna maybe integrated with the receive array by utilizing a horizontally polarized transmit and vertically polarized receiver ray. In other embodiments, the transmit antenna may be physically separate and not integrated with the receive array. In either case there is separate receive and transmit signal port as an interface to radio transceiver equipment. The use of an adaptive antenna in the receive only direction has the potential to increase forward links capacity to levels equal to or greater than reverse link capacity. This allows for a significant increase in the overall number of users that may be active at the same time in a wireless system.

The invention discloses a routing method of a content-centric network strategy layer. The method comprises the following steps of: respectively determining data transmission round-trip time, transmission rate and energy consumption of each network interface according to history states of forwarding data of n network interfaces; computing the energy consumption cost according to the determined the data transmission round-trip time, transmission rate and energy consumption of each network interface; and computing the minimum energy consumption cost under the limitation of the round-trip time, and forwarding interest packets by selecting k former interfaces with largest forwarding probability when the energy consumption cost is minimum, wherein the k is less than n. According to the states of a plurality of internet interfaces of equipment, the optimum network interface can be automatically selected for forwarding the interest packets, so as to forward the interest packets by the plurality of interfaces and realize multisource acquisition, thus avoiding interface failure brought by movement, improving the data forwarding mobility and reliability, and optimizing equipment forwarding property.

The invention discloses a data forwarding method, controller, forwarding device and system, and belongs to the field of computers. The data forwarding method comprises the steps that overload link port information sent by the forwarding device is received; a service flow, with biggest flow, in a port is queried according to identification, of the port, contained in the overload link port information; a new forwarding path is generated for the service flow; a new forwarding flow table of the service flow is generated for the forwarding device on the new forwarding path; the new forwarding flow table is sent to the corresponding forwarding device. Due to the facts that the service flow, with biggest flow, in a port is queried according to identification, of the port, contained in the received overload link port information, and the new forwarding path is generated for the service flow, the problem that a service flow cannot be further controlled after a controller confirms a forwarding path of the service flow is solved, and the purposes that flow distribution is optimized in real time, and then network forwarding performance is improved are achieved.

The invention discloses a data transmission method and device of a multilink transparent transmission interconnection network, wherein the method comprises the following steps: a TRILL (Trill) exchanger receives a well-known unicast data frame, wherein the well-known unicast data frame comprises a TRILL data frame or an Ethernet data frame; if the TRILL data frame is received, the TRILL exchanger judges whether the TRILL exchanger is the TRILL exchanger at the penultimate hop of the TRILL data frame according to the information carried in the TRILL data frame and a TRILL forwarding table; and if a judging result is positive, the TRILL exchanger unpacks the TRILL data frame to obtain the Ethernet data frame and transmits the Ethernet data frame to the last hop of TRILL exchanger. By using the method, the problem that the ERB (Edge Router Bridge) processing performance in the traditional TRILL network turns into the performance bottleneck of Trill Campus can be solved.

The invention relates to a method and a system of realizing sharing of gateway dynamic load. The arrangement of a plurality of new virtual MAC addresses in the same virtual backup group which is provided with a plurality of gate way devices assures that main equipment can forward the data message to an external network server by different gate way devices so as to realize the function of sharing gateway dynamic load. Aiming at the problems that the gate way backup and load sharing can increase network management load in the prior art, network bandwidth load and gate way device load, the invention provides the method and system of realizing sharing of gateway dynamic load. The invention simplifies the user configuration management, reduces occupation of network bandwidth caused by data transmission and improves the forwarding performance of the gate way device.

The invention discloses a method, a device and network equipment for realizing bidirectional forwarding detection. The method comprises the steps of: dividing a plurality of sessions to be subjected to bidirectional forwarding detection into session groups with a set number, and polling each session sub-group according to a set polling period; specific to each session in the currently polled session sub-group, performing the following steps of: sending a keep-alive message to opposite-end equipment of each session and judging whether the keep-alive message sent by the opposite-end equipment is received or not in a set detection period; if the judgment is negative, determining that the corresponding session is in connectivity fault; or else, determining that the corresponding session is free of connectivity fault. According to the method disclosed by the invention, all the sessions do not need to be polled at the same time, so that the occupancy amount of a CPU (Central Processing Unit) is reduced and the system forwarding performance is increased.

A forward link power control mechanism measures the reverse link power control bits which are transmitted on the forward traffic channel. At the remote station, the reverse link power control bits from multiples base stations or multiple signal paths are measured, combined, and filtered to yield an improved measurement of the forward link signal quality. The reverse link power control bits which are deemed unreliable are omitted from use in the power control loop. The remote station generates a set of forward link power control bit in accordance with the measurements and transmits these bits to all base stations in communication with the remote station. Each base station adjusts its gain of the forward traffic channel in accordance to its measurement of the forward link power control bit.

The invention discloses a method and a system for realizing data flow hardware forwarding. A network route device is also disclosed. In the method, a first forwarding table of a hardware forwarding chip is refreshed and a second forwarding table is sent down according to an out interface of an interface board. For business messages which are output by the configured out interface, following steps are executed: the hardware forwarding chip searches the first forwarding table to obtain the next hop of the refreshed route and searches the business messages to CPU of the interface board to be treated by an interface which is connected with the CPU of the interface board; the business messages treated by the CPU of the interface board trigger the hardware forwarding chip to search the second forwarding table to obtain a real next hop, and the three-layer hardware forwarding is implemented on the treated business messages by the out interface. By adopting the method and the system, the hardware forwarding chip forwards data flow to the CPU of the interface board for the business treatment. After the treatment, the three-layer forwarding can be implemented again by the hardware forwarding chip. Simultaneously, the configuration is simple and the forwarding performance is improved.

The invention is designed for use in solving the issue existed in currently-used technology that is the capacity expansion of router is limited by globally sending down the forwarding information table. The method comprises: according to the routing information, generating the forwarding information table; according to the route filter strategy corresponding to each interface board, making the route filter for the forwarding information, and sending the filtered route information to the relay engine.

The invention provides a method for achieving IPSecVPN main link and backup link dynamic switching, and relates to the field of network safety. The method in each period comprises the steps that 1), whether a main link is normal or not is detected through a DPD mechanism, the step 3 is carried out if yes, and the step 2 is carried out if not; 2) the traffic of a VPN is forwarded from an IPSec tunnel of a backup link, and the process is ended; 3) the traffic of the VPN is forwarded from an IPSec tunnel of the main link, and the process is ended. According to the method for achieving the IPSecVPN main link and backup link dynamic switching, the DPD detecting mechanism of the IPSec and a wan interface route are ingeniously connected, flexible processing is carried out according to the priority of the link state to the route, switching of the main link and the backup link can also be achieved even though GRE is not available, and data forwarding performance is improved.

The invention relates to an openstack based agent deployment system and method, and relates to the field of cloud computing. The openstack based agent deployment system comprises a server, a first management access switch, a second management access switch, a management core switch and at least one computing node, wherein the server is connected with the management core switch through the second management access switch, and the management core switch is connected with the first management access switch. The characteristics lie in that each computing node comprises an agent virtual machine and a management virtual switch, and an agent management network card of the agent virtual machine is bound to the management virtual switch; each computing node corresponds to one computing node management network card, the computing node management network card accesses to a port of the first management access switch, and the management virtual switch binds the computing node management network card. The openstack based agent deployment system reduces forwarding paths, improves the network forwarding performance and reduce the later workload of the operation and maintenance personnel under the condition of conforming to third-level requirements of classified protection.

The invention provides a data forwarding method on the basis of a transport - multiple protocol label switch (T-MPLS) network and a system thereof. According to the label value, labels of user data are classified into an A type, a B type and a C type; and labels of A type is set as internal layer labels and the labels of B type and C type are set as external layer labels; user data enter the T-MPLS network and are packaged with an internal layer label and an external layer label; when the external layer label of the user data is determined to be a C type label according to the label classification, a service label table of the current network appliance is read through the internal layer label, and the next-hop forwarding address of the user data after leaving the current T-MPLS network is searched; the internal layer label and the external layer label of user data are stripped, the user data with the internal layer label and the external layer label stripped if forwarded according to the searched next-hop forwarding address; therefore, hardware processing resources can be saved on the basis of the method and system of the invention.

The invention provides a packet forwarding method and device. The method comprises the steps that an access point (AP) receives a first packet sent by a wireless terminal; a forwarding table is looked up to acquire a two-layer tunnel port for forwarding the first packet; the first packet after tunnel encapsulation is sent to a switch distributed by AC to AP through a two-layer tunnel corresponding to the two-layer tunnel port, and the switch sends the first packet to a destination device; preferably, the AP receives a second packet sent by the switch through the two-layer tunnel; the second packet is a packet sent by the destination device to the wireless terminal; and the second packet after tunnel decapsulation is sent to the wireless terminal according to the forwarding table. According to the invention, the amount of network configuration is reduced, and the performance of packet forwarding is improved.

A method and structure are disclosed for dispatching appropriate data to a network processing system comprising an improved technique for extracting protocol header fields for use by the network processor. This technique includes basic classification of a packet according to the types of protocol headers present in the packet. Based on the results of the classification, specific parameter fields are extracted from corresponding headers. All such parameter fields from one or more protocol headers in the packet are concatenated into a compressed dispatch message. Multiples of such dispatch messages are bundled into a single composite dispatch message. Thus, selected header fields from N packets are passed to the network processor in a single composite dispatch message, increasing the network processor's packet forwarding capacity by a factor of N. Likewise, multiple enqueue messages are bundled into a single composite enqueue message to direct enqueue and frame alterations to be taken on the bundle of N packets.

The invention provides a method and an apparatus for updating an MAC (Media Access Control) address table. The method comprises the following steps of: searching corresponding table items from the MAC address table according to a source MAC address of the Ethernet frame after an Ethernet frame is received; computing a difference value between a system time stamp of the received Ethernet frame and an table item time stamp recorded in the searched entry if the searching is successful; and updating the table item time stamp with the system time stamp when the difference value is greater than a preset value. In the invention, only when the difference value is greater than the preset value, the table item time stamp of the link list can be updated with the system time stamp, and each received Ethernet frame is unnecessarily subjected to write operation, thereby reducing times of carrying out the write operation on the MAC address table, improving the concurrent processing capacity of a multi-core processor to the Ethernet frame and improving the forwarding performance of the Ethernet frame.

The invention discloses a data processing method and system, and the method comprises the steps that an OVS network bridge unloads a received message to a network card in a pre-started hardware unloading mode based on a pre-established connection relation with a virtual machine, enables the network card to process the message, and loads a hardware rule for message processing to the network card. Through the above method, the OVS network bridge forwarding is unloaded; the message of the virtual machine connected to the OVS network bridge is directly forwarded over the network card. According tothe invention, the hardware rule for message processing can be generated according to the software rule for message processing, and forwarding is realized on the network card, so that the network card processes the message, thereby reducing the occupation of OVS network bridge forwarding on the resources of the CPU, reducing the load of the CPU, and improving the network forwarding performance.

The invention relates to a load sharing method, a load sharing device and a load sharing system for message traffic. The method comprises the following steps of: resolving a received message, and acquiring the stream identification information of a message stream corresponding to the message; querying a message stream state table, and judging whether the message stream is processed by a processor of a multi-core processor, which corresponds to the message stream, or not according to the stream identification information; if the message stream is processed by the processor, arranging the message into the message stream, and processing the message by using the processor; if the message stream is not processed by the processor, arranging the message into the message stream, and distributing the message stream to an idle process of the multi-core processor for processing; and judging whether the processing of the message stream is finished or not, and if the processing of the message stream is finished, updating the message stream state table for the distribution of the next message stream. The problem of conflict between traffic load sharing and message sequence preservation in a multi-core system is solved, the dynamic balanced sharing of the traffic in the multi-core system is realized, the overhead of the message sequence preservation is eliminated, and message forwarding performance improved.

The invention provides a context routing processing method, network element equipment and a network server. The process context routing method includes: receiving context access information reported by context routing devices in a local area by the network server; computing frequency of historic context access according to context addressing in the context access information, and adjusting a context routing list according to the frequency; and issuing the context routing table adjusted to all context routing devices in the local area. By the context routing processing method, conflict between context flow transmission efficiency and cache hit ratio can be eliminated, so that higher integral transmission performance can be realize by least cost and cache hit ratio is increased.

The present invention discloses a multicast system based on a PCIE switching network, which comprises a main control board, a line card board and a PCIE switch, wherein the line card board comprises a control unit, a multicast identification unit, a multicast replication unit and a sending interface unit. The control unit is used to append the specific identification information to a message waiting to be sent; the multicast identification unit connected with the control unit is used to judge whether the message waiting to be sent is a multicast message, if yes, then the message waiting to be sent is sent to the multicast replication unit, and if not, then the message waiting to be sent is directly sent to the sending interface unit; the multicast replication unit connected with the multicast identification unit is used to replicate the multicast message and send the replicated multicast message to the sending interface unit; and the sending interface unit is used to encapsulate the multicast message or the non-multicast message into a PCIE message that is then sent to the switching network. For the PCIE switching network, the present invention simplifies the processing complexity of the CPU software of the line card board, reduces working repetition of the CPU of the line card board and increases the retransmission performance of the whole network device.

The method includes procedures: when processing first IP banding, network device of starting use of Internet secure protocol picks up information for unique identifying the IP message from the IP banding; then, building mapping from the information to relevant security policy; when processing other bandings of the IP message, Internet secure protocol maps to relevant security policy through the said unique information so as to implement process in high speed for the IP banding by the Internet secure protocol. Comparing with prior art, the invention overcomes disadvantages of using lots of memory, weighting process burden of gateway, lowering network throughput. The invention raises service range supported by network device, and guarantees high forwarding performance of network device.

This invention provides a method and equipment for transmitting data flows, in which, the method includes: using a part of key words of the data flow as the index to look for corresponding items in a tree list to look for corresponding dynamic chain list according to the content in the corresponding list, taking the rest part of the key words as the index to look for corresponding nodes in the dynamic list and getting outlet-interface information in the nodes to transmit said data flow. This invention also discloses equipment including: a management module, a tree list looking up module and a dynamic link looking up module and a transmission module.

The invention discloses an address resolution protocol (ARP) table entry synchronization method and a business processing method and equipment. The ARP table entry synchronization method is applied to distributed equipment comprising a master control board and at least two interface boards. The ARP table entry synchronization method comprises the following steps of: receiving an ARP request message asking for inquiring respective media access control (MAC) addresses of the interface boards by the interface boards; then performing ARP table entry learning according to the ARP request message if a receiving interface of the ARP request message is a non-aggregation interface; and performing ARP table entry synchronization according to the type of the receiving interface of the ARP request message. Chip resources of the interface boards are saved, so that the interface boards are capable of learning more ARP table entries, and the message transmitting and processing capacity of the interface boards is improved.

The invention discloses a virtual private LAN service (VPLS) message processing method and a VPLS message processing device, and relates to the field of network technologies, for solving the problems that in existing VPLS networking adopting a virtual network function (VNF) technology, VPLS forwarding traffic detours and traffic forwarding performance is poor due to the fact that multiple virtual machines (VM) share one virtual switching instance (VSI). According to the method, one VSI is arranged on each forwarding plane VM; and the method comprises the steps of receiving a message comprising a MAC address of a first user and a MAC address of a second user sent by the first user by using the first forwarding plane VM, querying a MAC forwarding table, acquiring a first interface corresponding to the MAC address of the second user in the MAC forwarding table, encapsulating a first private network label and a first public network tunnel label in the message, encapsulating a MAC address of the first interface and a MAC address of an interface of a first opposite terminal in the encapsulated message to form a VPLS message, and sending the encapsulated VPLS message out via the first interface.

The present invention provides a message processing method and device. The method comprises: analyzing the received message, and obtaining the message characteristic of the message; searching the conversion according to the message, the conversion includes the corresponding relation between the message characteristic and the business identification, and if the message characteristic is searched, obtaining the first business identification corresponding to the message characteristic; determining whether the message supports rapid forward or not according to the first business identification, if the message supports rapid forward, correcting the message according to the stored rapid forward information; and forwarding the corrected message. According to the embodiment, the message forwarding performance of a firewall is effectively improved.

The invention discloses a method for updating router, comprising: a master control module detects and obtains IS-IS data, generates a router table according to the obtained IS-IS data, and creates a forwarding table in an interface module according to the generated router table; the master control module sends the router prefix information recorded by each router in the obtained IS-IS data and generated router table to a spare control module to be backed up; and if the master control module goes wrong, the spare control module modifies the backed-up IS-IS data according to network condition, generates a router table according to the modified IS-IS data and updates the forwarding table recorded by the interface module according to the backed-up router prefix information and generated router table. In the method, the interrupt of forwarding flow rate in the prior art which can only delete black hole router in ageing time is avoided, and the network flow rate forwarding performance of dual-control module devices is improved.

The invention provides a method and a device for fragmenting a message. By adopting a received data message processed by FPGA, a fragmenting information table entry is stored in an on-chip resource or an external memory of GPGA. The method comprises the following steps: comparing a characteristic value of the received fragmenting message with a characteristic value stored in the fragmenting information table entry; further judging whether the fragmenting message is a primary message or not if a consistent comparison result is acquired; storing primary message information into the fragmenting information table entry if the message is the primary message and sending the primary message; processing a subsequent fragmenting message which exists in the primary message according to a processing way of the received primary message and sending the processed subsequent fragmenting message; judging whether the primary message information of the subsequent fragmenting message exists or not if the message is the subsequent fragmenting message; processing in a processing way of the primary message if the primary message information of the subsequent fragmenting message exists, and sending the processed subsequent fragmenting message; storing the subsequent fragmenting message if the primary message information of the subsequent fragmenting message does not exist.

The embodiment of the invention provides a method, a device, and an apparatus for message forwarding of firewall equipment, and a storage medium. The method comprises the following steps: obtaining ato-be-forwarded message which comprises quintuple data; calculating a hash value of the quintuple data; querying whether a simplified session table item matched with the to-be-forwarded message existsin a simplified session array hash table previously built in the current CPU or not according to the hash value; obtaining a corresponding session table item template according to a template sessionaddress in the matched simplified session table item if the simplified session table item matched with the to-be-forwarded message exists in the simplified session array hash table; and forwarding theto-be-forwarded message according to the session table item template. According to the method, the device, and the apparatus for message forwarding of firewall equipment, and the storage medium, a large amount of memory space can be saved during the whole forwarding process; the problem that cache access failure probability is increased when a session table item is large due to large memory spaceoccupation can be avoided; and the stability of the overall forwarding performance of the firewall device can be improved.