WO2015192793A1 - Packet processing - Google Patents

Packet processing Download PDF

Info

Publication number
WO2015192793A1
WO2015192793A1 PCT/CN2015/081815 CN2015081815W WO2015192793A1 WO 2015192793 A1 WO2015192793 A1 WO 2015192793A1 CN 2015081815 W CN2015081815 W CN 2015081815W WO 2015192793 A1 WO2015192793 A1 WO 2015192793A1
Authority
WO
WIPO (PCT)
Prior art keywords
port
port information
uplink
destination
packet
Prior art date
Application number
PCT/CN2015/081815
Other languages
English (en)
French (fr)
Inventor
Mengtao ZHOU
Zhenglin QI
Original Assignee
Hangzhou H3C Technologies Co., Ltd.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou H3C Technologies Co., Ltd. filed Critical Hangzhou H3C Technologies Co., Ltd.
Publication of WO2015192793A1 publication Critical patent/WO2015192793A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H04L12/46—Interconnection of networks
    • H04L12/4604—LAN interconnection over a backbone network, e.g. Internet, Frame Relay
    • H04L12/462—LAN interconnection over a bridge based backbone
    • H04L12/4625—Single bridge functionality, e.g. connection of two networks over a single bridge

Definitions

  • one physical server may be virtualized into plural logical virtual machines (VM) .
  • VM logical virtual machines
  • Communications between VMs within the same physical server are forwarded by an external network device, i.e., all communication traffic is exchanged and forwarded by a network access device, and a network device performs management and control over all of traffic. Therefore, a network access device can identify the VMs, i.e., VMs are visible to the network access device.
  • the network access device that can identify VMs is referred to as a control device.
  • the network access device is a switch in a switch stacking system.
  • a switch stacking system may have a first layer including one or more control bridges (CB) and a second layer including one or more remote extending devices.
  • a remote extending device may also be referred to as a port extender (PE) .
  • the control bridges may be separate physical devices that are virtualized to act as a single switch.
  • the CB may for example be on an aggregation layer of the network.
  • the port extenders may be switches that are configure to act as remote line cards of the CB.
  • the port extenders may be on an access layer of the network.
  • the CBs and PEs may be virtualized to act as a single switch.
  • One example of a stacking system is the Intelligent Resilient Framework system.
  • FIG. 1 is a flowchart illustrating a packet processing method in accordance with an example of the present disclosure
  • FIG. 2 is a flowchart illustrating a packet processing method in an IRF system in accordance with an example of the present disclosure
  • FIG. 3 is a schematic diagram illustrating a network in which the technical mechanism of an example is applicable in accordance with an example of the present disclosure
  • FIG. 4 is a flowchart illustrating a packet processing method in which a PE performs proxy forwarding in accordance with an example of the present disclosure
  • FIG. 5 is a flowchart illustrating a packet processing method in which a PE performs local forwarding in accordance with an example of the present disclosure
  • FIG. 6 is a schematic diagram illustrating modules of a remote extending device in accordance with an example of the present disclosure.
  • FIG. 7 is a schematic diagram illustrating modules of a remote extending device in accordance with an example of the present disclosure.
  • Centralized remote extending devices may adopt a non-Hash forwarding (Pinning) mode to forward uplink packets to control devices, i.e., uplink packets having the same destination port are forwarded to a control device via the same port extending links, and then forwarded further by the control device through the same port.
  • Pinning non-Hash forwarding
  • Distributed remote extending devices may adopt a Hash forwarding mode to forward uplink packets, i.e., applying a Hash algorithm to contents of a packet, using the Hash result to determine an egress port for the uplink packet from a link-aggregation group formed by all of uplink egress ports on the remote extending device.
  • FIG. 1 is a flowchart illustrating a packet processing method in accordance with an example of the present disclosure.
  • the method is applicable to a network virtualization system, and may include the following procedures.
  • a remote extending device receives a downlink packet sent by a control device, stores a first relation which associates a source address with source port information of the downlink packet and a second relation which associates the source port information of the downlink packet with a port on the remote extending device that received the downlink packet.
  • the remote extending device receives an uplink packet, determines port information associated by the first relation with a destination address in the uplink packet as destination port information, and determines a port associated by the second relation with the destination port information as an uplink egress port.
  • the remote extending device adds the destination port information into the uplink packet, and forwards the uplink packet through the uplink egress port.
  • Forwarding uplink packets using information of forwarding paths obtained by remote extending devices from downlink packets guarantees uplink packets be forwarded through a particular uplink egress port based on information in the downlink packet. This may help guarantee a particular path for the uplink packet. For instance, control devices may forward downlink packets according to the shortest path forwarding principle, thus by guaranteeing a particular egress port for the uplink packet based on the downlink packet information, the above method may guarantee that the uplink packets are forwarded along the shortest paths. Therefore, fewer control devices are involved in forwarding of each uplink packet, stack link resources are saved. In some cases, packet loss due to control device failure may also be reduced.
  • the above network virtualization system may be a scale-up virtualization system adopting HIGIG protocols (e.g., HIGIG 2) , e.g., IRF3 systems or the like.
  • Information of a port may be a (Module, Port) tuple defined in HIGIG2 protocol.
  • the first relation may be stored as a MAC address table entry
  • the second relation may be stored as an egress port table entry in block S101.
  • the remote extending device may search MAC address table entries stored in the remote extending device for an entry including the destination MAC address in the uplink packet, and determine the destination port information of the uplink packet. According to the destination port information, the remote extending device may search egress port table entries stored in the remote extending device to determine the uplink egress port of the uplink packet.
  • the destination port information is generated by a target control device which is directly connected to the uplink egress port.
  • the target control device may apply a mapping method to port information of the destination port to obtain second port information as the destination port information.
  • the target control device may apply a de-mapping method to the destination port information in the uplink packet (i.e., the above second port information) to obtain the actual information of the destination port, and use the actual information to identify the destination port.
  • a control device may map information of a source port in the downlink packet, denoted as M1, to port information MP1 which is recognizable to the remote extending device.
  • the control device may de-map information of a destination port MP1 in the uplink packet to the source port information M1.
  • the remote extending device may send the uplink packet which includes the destination port information to the target control device which is directly connected to the determined uplink egress port in block S103 to enable the target control device to forward the uplink packet according to the destination port information in the uplink packet and a MAC address table entry stored in the target control device.
  • the MAC address table entry stored in the target control device is established by the target control device by studying a received downlink packet.
  • the remote extending device may be a port extender (PE) in an stacking system and the control device may be a control bridge (CB) in a stacking system.
  • IRF is one example of a stacking system.
  • the method is applicable to an IRF system which includes a CB and a PE.
  • the PE may execute the following procedures.
  • the PE receives an uplink packet which includes a destination MAC address.
  • the PE determines destination port information of the uplink packet by searching MAC address table entries stored in the PE using the destination MAC address in the uplink packet.
  • the PE determines an uplink egress port by searching egress port table entries stored in the PE using the destination port information determined in block S202.
  • the PE adds the destination port information into the uplink packet, and sends the uplink packet to a CB directly connected to the uplink egress port determined in block S203 (simply referred to as the target CB) through the uplink egress port.
  • the MAC address table entry in block S202 and the egress port table entry in block S203 stored in the PE are established by the PE when studying a source MAC address in a downlink packet sent by the target CB.
  • the destination port information determined in block S202 may be second port information which is obtained by processing actual port information.
  • the destination port information may be obtained by the target CB by applying a Mod mapping method to port information of a destination port in a downlink packet received from the destination port of the uplink packet.
  • the procedure in block S204 may include:
  • the MAC address table entries stored in the target CB were established when the target CB studied source MAC addresses in received downlink packets.
  • the destination port information determined in block S202 may be actual information of a port.
  • the procedure in block S204 may include:
  • the PE sends the uplink packet which includes the destination port information through the determined uplink egress port to the target CB to enable the target CB to forward the uplink packet according to the destination port information in the uplink packet.
  • the mechanism is applied to the IRF3 network as shown in FIG. 3.
  • ports U1 and U2 are both uplink ingress ports on a PE
  • port information of U1 may be (M1, U1)
  • port information of U2 may be (M2, U2)
  • Port U3 is a downlink ingress port on CB1
  • port information is (M3, U3)
  • Port U4 is a downlink ingress port on CB3, and port information is (M4, U4)
  • CB1 and CB2 both stores a MAC address table entry (0-0-2, M2, U2) , i.e., a user device having the MAC address of 0-0-2 is connected to port U2 of the PE.
  • CB1 and CB2 are directly connected to the PE respectively.
  • FIG. 3 merely shows 3 CBs and 1 PE as an example for illustrating the mechanism of various examples.
  • CB1 sends a downlink packet through U3 to U2 of the PE and the PE sends an uplink packet through U2 to U3 of CB1.
  • CB1 receives a downlink packet through U3, studies the source MAC address of the downlink packet, and establishes a MAC address table entry.
  • the downlink packet includes the source MAC address (0-0-3) and a source port information (M3, U3) , i.e., port information of U3.
  • CB1 After studying the source MAC address of the downlink packet, CB1 establishes a MAC address table entry, which may be (0-0-3, M3, U3) .
  • CB1 searches MAC address table entries stored in CB1 for the destination MAC address in the downlink packet to determine destination port information of the downlink packet, and adds the destination port information into the downlink packet.
  • the destination MAC address of the downlink packet is 0-0-2, and MAC address table entries stored in CB1 may be as shown in Table 1.
  • the destination port information found using the MAC address 0-0-2 is (M2, U2) , and is added into the downlink packet.
  • CB1 determines an egress port for the downlink packet according to the shortest forwarding path principle.
  • CB1 determines the egress port is S1 since the destination port information of the downlink packet is (M2, U2) .
  • the shortest forwarding path principle refers to a principle that if the CB is an IRF device and links connecting the CB to a PE involves multiple IRF members, the IRF device selects the shortest path to the PE. If an IRF member has multiple paths leading to a PE, the IRF member may perform link-aggregation HASH selection to select a path.
  • the starting point of the principle is to reduce consumption of bandwidth of stack links of the IRF network.
  • the downlink egress port S1 on CB1 maps the Mod in the source port information in the downlink packet to MP1, adds the mapped source port information MP1 into the downlink packet, and forwards the downlink packet to P1 on the PE.
  • Mod mapping functions in the egress direction are enabled on S1 of CB, which map the Mod in the source port information in the downlink packet to MP1.
  • the source port information in the downlink packet is mapped from (M3, U3) to (MP1, U3) .
  • the Mod mapping functions in the egress direction may be enabled on a downlink egress port of the CB, i.e., the CB may map actual port information (e.g., Mod, which is the actual Mod of a downlink egress port of the CB) in source port information in a downlink packet to a second Mod identifiable to the PEs so that the PEs may establish an identifiable MAC address table entry.
  • Mod which is the actual Mod of a downlink egress port of the CB
  • a PE may determine an uplink egress port by using the MAC address table entry. Subsequently, after receiving the uplink packet including the destination port, the CB may detect the destination port information is not the actual destination port information, search MAC address table entries stored in the CB to determine the actual Mod of the destination port of the uplink packet, and forward the uplink packet through the correct destination port.
  • the PE serves as a proxy in forwarding the uplink packet, and the main forwarding task is done by the target CB.
  • the target CB may determine the destination port information is not actual information of the destination port, search information stored in the target CB to obtain actual information of the destination port, and implement the forwarding process.
  • all downlink packets forwarded to the PE may have the Mod in the source port information in the downlink packets mapped to the same second Mod when forwarded through the downlink egress port S1 of CB1, thus uplink packets to be received by user devices connected to CB1 can be forwarded to port S1 by the PE through port P1 on the PE.
  • downlink egress ports of different CBs may map the Mod in source port information of downlink packets to different second Mods to enable the PE to identify different physical links connected to the CBs.
  • S1 of CB1 as shown in FIG. 3 may map Mods in source port information of all received downlink packets to MP1
  • S2 of CB2 may map Mods in source port information of all received downlink packets to MP2.
  • a centralized PE receives a downlink packet through P1, studies the source MAC address of the downlink packet, and establishes a MAC address table entry and an egress port table entry.
  • supposing the downlink packet includes a source MAC address (0-0-3) , a destination MAC address (0-0-2) , source port information (MP1, U3) and destination port information (M2, U2) , the MAC address table entry established by the centralized PE according to the information may be (0-0-3, MP1, U3) as shown in Table 2.0-
  • the PE may also establish an egress port table entry (MP1, P1) corresponding to the MAC address table entry.
  • MP1, P1 egress port table entry
  • the centralized PE deletes destination port information in the downlink packet, and forwards the downlink packet through U2.
  • the centralized PE determines the destination port of the downlink packet to be U2 according to the destination port information (M2, U2) in the downlink packet, thus deletes the destination port information in the downlink packet and forwards the downlink packet through U2.
  • the centralized PE receives an uplink packet through U2.
  • the uplink packet includes a source MAC address (0-0-2) and source port information (M2, U2) , i.e., port information of U2.
  • the centralized PE searches MAC address table entries and egress port table entries stored in the PE for the destination MAC address of the uplink packet to determine an egress port of the uplink packet.
  • the destination MAC address of the uplink packet is 0-0-3
  • the PE searches the MAC address table entries in the PE (as shown in Table 2) and finds that the MAC address table entry matching the destination MAC address 0-0-3 is (0-0-3, MP1, U3) .
  • the PE determines the destination port information of the uplink packet is (MP1, U3) , searches egress port table entries stored in the PE (as shown in Table 3) for the destination port information, finds the egress port table entry matching the destination port information MP1 is (MP1, P1) , and determines the uplink egress port of the uplink packet is P1.
  • the centralized PE adds the determined destination port information into the uplink packet, and sends the uplink packet through P1 to the downlink egress port S1 on CB1.
  • CB1 receives the uplink packet through S1, determines the destination port information in the uplink packet is not actual information of a destination port, searches MAC address table entries stored in CB1 for the destination MAC address, and forwards the uplink packet after determining actual information of the destination port of the uplink packet.
  • CB1 detects the destination port information (MP1, U3) in the uplink packet is not actual information of a destination port.
  • CB1 searches MAC address table entries in CB1 (as shown in Table 1) for the destination MAC address (0-0-3) in the uplink packet, finds the MAC address table entry matching the destination MAC address 0-0-3 is (0-0-3, M3, U3) , determines actual information of the destination port is (M3, U3) , and forwards the uplink packet through U3.
  • the downlink packet is sent by CB3 through U4 to U2 on the centralized PE, i.e., the target CB of the uplink packet is not a CB directly connected to the centralized PE
  • procedures of studying the source MAC address of the downlink packet, establishing the MAC address table entry and applying Mod mapping to the source port information in the downlink packet are implemented by the CB directly connected to the PE (i.e., CB2) . That is, the downlink packet is sent to CB3 through U4, and forwarded by CB3 to CB2.
  • CB2 studies the source MAC address of the downlink packet, establishes a source MAC address table entry according to the downlink packet, and enables MOD mapping functions on S2.
  • the PE performs proxy forwarding.
  • the PE performs local forwarding.
  • CB3 sends a downlink packet through U4 to U2 of PE, and PE sends an uplink packet through U2 to U4 of CB3.
  • FIG. 5 is a flowchart illustrating a process in accordance with an example. The process may include the following procedures.
  • CB3 receives a downlink packet through U4, and sends the downlink packet to CB2 through an IRF link.
  • the downlink packet includes a source MAC address (0-0-4) , a destination MAC address (0-0-2) , and source port information (M4, U4) , i.e., port information of U4.
  • CB3 sends the downlink packet to CB2 through the IRF link according to the shortest forwarding path principle.
  • CB2 receives the downlink packet through the IRF link, studies the source MAC address of the downlink packet, and establishes a MAC address table entry.
  • the downlink packet includes the source MAC address (0-0-4) , the destination MAC address (0-0-2) and the source port information (M4, U4) , the MAC address table entry established by CB2 after CB2 studies the source MAC address in the downlink packet is (0-0-4, M4, U4) .
  • CB2 searches MAC address table entries stored in CB2 for the destination MAC address in the downlink packet to determine destination port information of the downlink packet, and adds the destination port information into the downlink packet.
  • the destination MAC address of the downlink packet is 0-0-2, and MAC address table entries stored in CB2 may be as shown in Table 5.
  • the destination port information found using the MAC address 0-0-2 is (M2, U2) , and is added into the downlink packet.
  • CB2 determines an egress port for the downlink packet according to the shortest forwarding path principle.
  • CB2 determines the egress port is S2 since the destination port information of the downlink packet is (M2, U2) .
  • the method of determining the egress port according to the shortest forwarding path principle may be the same with the conventional method, and is not described further herein.
  • CB2 sends the downlink packet to an uplink egress port P2 on the distributed PE through downlink egress port S2 on CB2.
  • the distributed PE receives the downlink packet through P2, studies the source MAC address of the downlink packet, and establishes a MAC address table entry and an egress port table entry.
  • the downlink packet includes a source MAC address (0-0-4) , a destination MAC address (0-0-2) , source port information (M4, U4) , and destination port information (M2, U2) .
  • the MAC address table entry established by the distributed PE by studying the source MAC address may be (0-0-4, M4, U4) as shown in Table 6.
  • the PE may also establish an egress port table entry (M4, P2) corresponding to the MAC address.
  • M4, P2 egress port table entry
  • the distributed PE deletes destination port information in the downlink packet, and forwards the downlink packet through U2.
  • the distributed PE receives an uplink packet through U2.
  • the uplink packet includes a source MAC address (0-0-2) , a destination MAC address (0-0-4) , and source port information (M2, U2) .
  • the distributed PE searches MAC address table entries and egress port table entries stored in the PE for the destination MAC address of the uplink packet to determine an egress port of the uplink packet.
  • the destination MAC address of the uplink packet is 0-0-4
  • the PE searches the MAC address table entries in the PE (as shown in Table 5) and finds that the MAC address table entry matching the destination MAC address 0-0-4 is (-0-0-4, M4, U4) .
  • the PE determines the destination port information of the uplink packet is (M4, U4) , searches egress port table entries stored in the PE (as shown in Table 6) for the destination port information, finds the egress port table entry matching the destination port information M4 is (M4, P2) , and determines the uplink egress port of the uplink packet is P2.
  • the distributed PE adds the determined destination port information into the uplink packet, and sends the uplink packet through P2 to the downlink egress port S2 on CB2.
  • the distributed PE adds the destination port information (M4, U4) into the uplink packet, and sends the uplink packet through P2 to S2 of CB2.
  • CB2 receives the uplink packet through the downlink egress port S2, and searches egress port table entries for the destination port information in the uplink packet.
  • the destination port information in the uplink packet is (M4, U4) . Since the port is not a port on CB2, CB2 may search egress port table entries in CB2 for the destination port information, determines the egress port table entry matching M4 is (M4, IRF1) , and determines the egress port of the uplink packet is IRF1.
  • CB2 sends the uplink packet to CB3 through IRF1 so that CB3 deletes the destination port information in the uplink packet and sends the uplink packet through U4 according to the destination port information (M4, U4) .
  • the CB directly connected to the distributed PE i.e., CB2
  • the target CB of the uplink packet i.e., CB3
  • an uplink packet received from U2 by either a centralized PE or a distributed PE is always forwarded from P1 to CB1, and then forwarded by CB1 through a corresponding port. That is, only one CB is required in the forwarding path to process the uplink packet.
  • a centralized PE forwards uplink packets received from U2 always through the same port to the same CB, e.g., through P2 to CB2, then forwarded by CB2 to CB1, and forwarded by CB1.
  • CB1 and CB2 are needed in the forwarding path to process the uplink packet.
  • an uplink packet received through U2 is forwarded under a Hash forwarding mode. Supposing the egress port on the PE determined by a Hash algorithm is P2, the PE may forward the uplink packet through P2 to CB2 which forwards the uplink packet to CB1, and CB1 finally forwards the uplink packet through a corresponding port.
  • CB1 and CB2 are also needed in the forwarding path to process the uplink packet.
  • the method of forwarding uplink packets provided by various examples can guarantee the shortest forwarding paths to involve as few CBs as possible in packet forwarding, which not only saves bandwidth resources between CBs but also reduces packet loss resulted from CB failures.
  • FIG. 6 is a schematic diagram illustrating modules of a remote extending device in accordance with an example of the present disclosure.
  • the remote extending device is applicable to a network virtualization system.
  • the device may include a processor and a memory.
  • the memory may include:
  • a receiving module 601 to receive a downlink packet sent by a control device, store a first relation which associates a source address with information of a source port of the downlink packet and a second relation which associates the information of the source port of the downlink packet with a port on the remote extending device that received the downlink packet;
  • a searching module 602 to receive an uplink packet, determine information of a port associated by the first relation with a destination address in the uplink packet as information of a destination port, and determine a port associated by the second relation with the information of the destination port as an uplink egress port;
  • a sending module 603 to add the information of the destination port into the uplink packet, and forward the uplink packet through the uplink egress port.
  • the above modules may be a series of machine-readable instructions capable of making the processor the perform the above actions.
  • FIG. 7 is a schematic diagram illustrating modules of a remote extending device in accordance with an example of the present disclosure.
  • the remote extending device may be a PE in an stacking system.
  • the PE may include:
  • a receiving module 701 to receive an uplink packet which includes a destination MAC address
  • a searching module 702 to search MAC address table entries stored in the PE for a destination MAC address in the uplink packet to determine destination port information of the uplink packet after the receiving module 701 receiving the uplink packet, and search egress port table entries stored in the PE for the destination port information to determine an uplink egress port of the uplink packet;
  • a sending module 703 to add the destination port information determined by the searching module 702 into the uplink packet, and send the uplink packet to a target CB through the uplink egress port determined by the searching module 702.
  • the MAC address table entries used by the searching module 702 in determining the destination port information of the uplink packet and the egress port table entries used by the searching module 702 in determining the uplink egress port of the uplink packet are established by the PE when the PE studies source MAC addresses in downlink packets sent by a CB directly connected to the PE.
  • the destination port information determined by the searching module 702 may be generated by the target CB by applying a Mod mapping method to port information of a destination port in a downlink packet received from the destination port of the uplink packet.
  • the sending module 703 is further to send the uplink packet which includes the destination port information through the uplink egress port to the target CB to enable the target CB to search MAC address table entries stored in the target CB using the destination MAC address in the uplink packet to determine the actual destination port of the uplink packet in response to a determination that the destination port information in the uplink packet is not actual information of a destination port.
  • the sending module 703 is further to send the uplink packet which includes the destination port information through the determined uplink egress port to the target CB to enable the target CB to forward the uplink packet according to the destination port information in the uplink packet.
  • the sending module 703 is to enable the CB directly connected to the uplink egress port determined by the searching module 702 to search for the actual destination port in MAC address table entries established by the CB when the CB studies source MAC addresses of received downlink packets.
  • the hardware modules may be implemented by hardware or a hardware platform with necessary software.
  • the software may include machine-readable instructions which are stored in a non-transitory storage medium.
  • the examples may be embodied as software products.
  • the hardware may be dedicated hardware or general-purpose hardware executing machine-readable instruction.
  • a hardware module may comprise dedicated circuitry or logic that is permanently configured (e.g., as a special-purpose processor, such as a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC) ) to perform certain operations.
  • a module may also comprise programmable logic or circuitry (e.g., as encompassed within a general-purpose processor or other programmable processor) that is temporarily configured by software to perform certain operations.
  • the machine-readable instructions corresponding to modules may cause an operating system running in a computer to implement part or all of the operations described herein.
  • a non-transitory computer-readable storage medium may be a storage device in an extension board inserted in the computer or a storage in an extension unit connected to the computer.
  • a CPU in the extension board or the extension unit executes at least part of the operations according to the instructions based on the program codes to realize the technical scheme of any of the above examples.
  • the non-transitory computer-readable storage medium for providing the program codes may include floppy disk, hard drive, magneto-optical disk, compact disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW) , magnetic tape drive, Flash card, ROM and so on.
  • the program code may be downloaded from a server computer via a communication network.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Small-Scale Networks (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
PCT/CN2015/081815 2014-06-20 2015-06-18 Packet processing WO2015192793A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410279952.1A CN105471742B (zh) 2014-06-20 2014-06-20 一种报文处理方法及设备
CN201410279952.1 2014-06-20

Publications (1)

Publication Number Publication Date
WO2015192793A1 true WO2015192793A1 (en) 2015-12-23

Family

ID=54934886

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/081815 WO2015192793A1 (en) 2014-06-20 2015-06-18 Packet processing

Country Status (2)

Country Link
CN (1) CN105471742B (zh)
WO (1) WO2015192793A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018099354A1 (zh) * 2016-11-29 2018-06-07 新华三技术有限公司 报文传输

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108259345B (zh) * 2016-12-30 2021-01-26 新华三技术有限公司 端口生成方法和装置
CN108199975B (zh) * 2018-03-28 2022-03-25 新华三技术有限公司 一种流量控制方法及装置
CN109039798B (zh) * 2018-06-20 2021-01-26 新华三技术有限公司 分裂检测系统及方法
CN109039909B (zh) * 2018-07-17 2021-12-24 新华三技术有限公司 一种报文转发的方法及装置

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030185207A1 (en) * 2002-03-28 2003-10-02 Fujitsu Limited Address access system and method thereof
CN1725730A (zh) * 2005-04-08 2006-01-25 杭州华为三康技术有限公司 多层虚拟局域网交换的方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8798064B2 (en) * 2011-06-06 2014-08-05 Broadcom Corporation Method and system of frame forwarding with link aggregation in distributed ethernet bridges
CN103795518B (zh) * 2012-10-31 2017-04-05 杭州华三通信技术有限公司 一种设备间端口模式同步方法、设备及系统
CN103516609B (zh) * 2013-09-17 2017-05-17 杭州华三通信技术有限公司 一种业务报文的传输方法和设备
CN103731303B (zh) * 2013-12-20 2017-08-11 新华三技术有限公司 一种纵向融合架构接口实现多活性实体检测的方法及设备

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030185207A1 (en) * 2002-03-28 2003-10-02 Fujitsu Limited Address access system and method thereof
CN1725730A (zh) * 2005-04-08 2006-01-25 杭州华为三康技术有限公司 多层虚拟局域网交换的方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018099354A1 (zh) * 2016-11-29 2018-06-07 新华三技术有限公司 报文传输
US10833990B2 (en) 2016-11-29 2020-11-10 New H3C Technologies Co., Ltd. Transmitting packet

Also Published As

Publication number Publication date
CN105471742A (zh) 2016-04-06
CN105471742B (zh) 2018-11-09

Similar Documents

Publication Publication Date Title
US10791066B2 (en) Virtual network
US10541913B2 (en) Table entry in software defined network
EP4220395B1 (en) Method and apparatus for determining virtual machine migration
US9942148B1 (en) Tunneled packet aggregation for virtual networks
US9866409B2 (en) Method and system for VXLAN encapsulation offload
US11750515B2 (en) Data transmission method and apparatus
EP2874359B1 (en) Extended ethernet fabric switches
US20150358232A1 (en) Packet Forwarding Method and VXLAN Gateway
WO2015192793A1 (en) Packet processing
US20160197824A1 (en) Packet forwarding
US10313154B2 (en) Packet forwarding
US10158565B2 (en) Network services across non-contiguous subnets of a label switched network separated by a non-label switched network
EP3292664B1 (en) Multicast data packet forwarding
WO2016107594A1 (en) Accessing external network from virtual network
US10313275B2 (en) Packet forwarding
US9413635B2 (en) Method for controlling generation of routing information, method for generating routing information and apparatuses thereof
US9825814B2 (en) Dynamic attribute based application policy
US10313274B2 (en) Packet forwarding
US20170070473A1 (en) A switching fabric including a virtual switch
WO2016000648A1 (en) Controlling virtual edge port aggregator

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15810057

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15810057

Country of ref document: EP

Kind code of ref document: A1