CN102355417A - Data center two-layer interconnection method and device - Google Patents
Data center two-layer interconnection method and device Download PDFInfo
- Publication number
- CN102355417A CN102355417A CN2011103002787A CN201110300278A CN102355417A CN 102355417 A CN102355417 A CN 102355417A CN 2011103002787 A CN2011103002787 A CN 2011103002787A CN 201110300278 A CN201110300278 A CN 201110300278A CN 102355417 A CN102355417 A CN 102355417A
- Authority
- CN
- China
- Prior art keywords
- arp
- mac address
- port
- sending
- arp request
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000004044 response Effects 0.000 claims abstract description 87
- 238000012545 processing Methods 0.000 claims description 169
- 230000008569 process Effects 0.000 claims description 20
- 230000032683 aging Effects 0.000 claims description 16
- 238000004148 unit process Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 abstract description 9
- 230000006854 communication Effects 0.000 description 9
- 230000005012 migration Effects 0.000 description 9
- 238000013508 migration Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 101100059544 Arabidopsis thaliana CDC5 gene Proteins 0.000 description 4
- 101150115300 MAC1 gene Proteins 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000010076 replication Effects 0.000 description 2
- 101100289995 Caenorhabditis elegans mac-1 gene Proteins 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/60—Software-defined switches
- H04L49/602—Multilayer or multiprotocol switching, e.g. IP switching
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L61/00—Network arrangements, protocols or services for addressing or naming
- H04L61/09—Mapping addresses
- H04L61/10—Mapping addresses of different types
- H04L61/103—Mapping addresses of different types across network layers, e.g. resolution of network layer into physical layer addresses or address resolution protocol [ARP]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Small-Scale Networks (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a data center two-layer interconnection method and a device. The method comprises the following steps of: previously enabling MAC-MFF (Media Access Control-Forced Forwarding) on edge equipment, forwarding an ARP (Address Resolution Protocol) request and ARP response according to an MFF mechanism proxy and learning ARP information according to received ARP response; and amending a source MAC address of a service message into an MAC address of the edge equipment when the service message is received, searching the corresponding ARP information according to a destination IP (Internet Protocol) address of the service message, amending the destination MAC address of the service message according to the searched ARP information, and forwarding the amended service message. By adopting the method and the device, the problem of overlarge MAC address scale during data center two-layer interconnection can be solved.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a two-layer interconnection method and a two-layer interconnection device for a data center.
Background
The traditional Internet Data Center (IDC) mainly uses services such as selling bandwidth and cabinet space, hosting host, providing network connectivity and the like, and provides infrastructure services by taking a machine room as a unit. With the rapid development of the IT industry, the user traffic volume is increasing explosively, and the IDC of the operators faces unprecedented dilemma, such as: the limitation of space resources, unbalanced development of high and low end machine rooms, low utilization rate of hardware resources, high construction and operation cost, single service structure, high service competition and technical development pressure and the like.
The only method capable of solving the dilemma of operators at present is to implement cloud computing service, improve the utilization rate of equipment, reduce operation cost and improve profit margin. At present, the main method for implementing the cloud computing technology by an operator is virtualization, and flexible scheduling of resources, especially flexible scheduling of computing resources, is realized through virtualization. The flexible scheduling of computing resources is easy to realize in the same data center, and the difficulty lies in the flexible scheduling of resources realized among a plurality of data centers, which requires the construction of a large-scale two-layer network.
However, building a wide range of two-tier networks faces a number of problems, the most troublesome of which are: too large a MAC address: the MAC addresses of a plurality of IDCs are doubled due to two-layer interconnection among IDC clouds, so that the switch is difficult to load; ultra-wide broadcast domain: two-layer interconnection among IDC clouds can cause a huge two-layer broadcast domain to be formed among a plurality of IDCs, so that ARP broadcast and unknown unicast are further diffused, and the threat of two-layer network broadcast storm is increased.
The traditional MAC address learning is a hardware chip-based source MAC address learning mode, is simple to implement, but cannot identify and distinguish messages, and can automatically learn all received messages, so that the MAC table is over-large in scale.
At present, a method called "address flooding learning" based on a data plane is applied to a deficiency of MAC address learning in a hardware chip-based source MAC address learning manner by an Overlay Transport Virtualization (OTV) technology, and a control plane protocol is used to: the IS-IS routing protocol implements MAC address learning. Therefore, the scale of MAC address learning can be controlled, and the problem of overlarge MAC address can be solved.
Referring to fig. 1, fig. 1 is a schematic diagram of a MAC address learning process of an OTV in the prior art, wherein a data center site A, B, C is respectively connected to a backbone network through edge devices 1, 2, and 3, and a topology in each data center is not shown. When the edge device of each data center site learns a new MAC address from the inside of the data center site, the associated VLAN ID and the next-hop IP address (interface IP of the edge device connected to the backbone network) are notified to the outside through the IS-IS routing protocol, and are copied and forwarded to all neighbors in the backbone network through the multicast tree. For example, in fig. 1, a dashed line 11 indicates that edge device 1 forwards a new MAC address learned from inside data center site a to data center site B through multicast tree replication in the backbone network, and a dashed line 12 indicates that edge device 1 forwards a new MAC address learned from inside data center site a to data center site C through multicast tree replication in the backbone network.
However, the implementation technology of OTV IS too complex, an IS-IS routing protocol needs to be applied in the two-layer network, and new modifications (involving modification of IETF standard, substantial modification of software plane, etc.) need to be made to the existing IS-IS routing protocol; in addition, the complex implementation technology also causes the MAC address learning quantity to be limited, and the method can only be applied to the interconnection of certain enterprise data centers and cannot be applied to the interconnection of large-scale data centers, especially the interconnection among clouds of IDCs of operators.
Disclosure of Invention
In view of this, the present invention provides a two-layer interconnection method for a data center, which can solve the problem of an excessively large MAC address scale.
In order to achieve the above object, the present invention provides a two-layer interconnection method for a data center, which configures and enables an MFF on an edge device in advance; the method comprises the following steps:
when the first port receives an ARP request of user equipment, the edge equipment modifies the source MAC address of the ARP request into the MAC address of the edge equipment, then the edge equipment sends the ARP request out from the second port, records ARP information after receiving corresponding ARP response from the second port, and modifies the source MAC address of the ARP response into the MAC address of the edge equipment, and then the ARP response is sent out from the first port;
when the edge device receives an ARP request of the edge device of a remote site at the second port, the source MAC address of the ARP request is modified to be the MAC address of the edge device, and then the ARP request is sent out from the first port, after a corresponding ARP response is received from the first port, ARP information is recorded, and the source MAC address of the ARP response is modified to be the MAC address of the edge device, and then the ARP response is sent out from the second port;
when the edge device receives a service message of the user equipment at the first port, modifying a source MAC address of the service message into an MAC address of the edge device, modifying a target MAC address of the service message according to ARP information corresponding to a target IP of the service message, and sending the modified service message out from the second port;
when the edge device receives a service message of the edge device of the remote site at the second port, modifying the source MAC address of the service message into the MAC address of the edge device, modifying the destination MAC address of the service message according to the ARP information corresponding to the destination IP of the service message, and sending the modified service message out from the first port;
the first port is a port of user equipment inside a connection site; the second port is a port for connecting edge equipment of a remote site.
The present invention also provides an edge device, comprising: the device comprises a configuration unit, a first transceiving unit, a second transceiving unit and a processing unit;
the configuration unit is used for configuring and enabling the MFF in advance;
the first transceiving unit is used for sending a first processing instruction to the processing unit when the first port receives an ARP request of the user equipment, and sending the ARP request out from the second port after the processing unit processes the ARP request according to the first processing instruction; the ARP response processing unit is used for sending an ARP response from the first port to the processing unit after the ARP request received by the first port is sent from the second port and if a corresponding ARP response is received by the second port; the second port is used for sending a first processing instruction to the processing unit when receiving an ARP request of the edge equipment of the remote site, and sending the ARP request out from the first port after the processing unit processes the ARP request according to the first processing instruction; the ARP response processing unit is used for sending an ARP response from the second port to the processing unit after the ARP request received by the second port is sent from the first port and if the first port receives a corresponding ARP response, the second processing instruction is sent to the processing unit, and the ARP response is sent from the second port after the processing unit processes the ARP response according to the second processing instruction;
the second transceiving unit is used for sending a third processing instruction to the processing unit when the first port receives the service message of the user equipment, and sending the service message out from the second port after the processing unit processes the service message according to the third processing instruction; the second port is used for sending a third processing instruction to the processing unit when receiving the service message of the edge device of the remote site, and sending the service message out from the first port after the processing unit processes the service message according to the third processing instruction;
the processing unit is used for setting the source MAC address of the ARP request received by the first transceiving unit as the MAC address of the processing unit when receiving the first processing instruction of the first transceiving unit; the first receiving and sending unit is used for receiving a first processing instruction of the first receiving and sending unit, recording ARP information and modifying a source MAC address of ARP response into an MAC address of the first receiving and sending unit; when receiving a third processing instruction of the second transceiver unit, modifying the source MAC address of the service message received by the second transceiver unit into the MAC address of the second transceiver unit, and modifying the destination MAC address of the service message according to the ARP information corresponding to the destination IP of the service message;
the first port is a port of user equipment inside a connection site; the second port is a port for connecting edge equipment of a remote site.
According to the technical scheme, the invention enables the MFF on the edge equipment of the data center site, depots and forwards the ARP request and the ARP response according to the MFF mechanism, and learns the ARP information according to the received ARP response; when receiving the service message, modifying the source MAC address of the service message into the MAC address of the service message, searching the corresponding ARP information according to the destination IP address of the service message, modifying the destination MAC address of the service message according to the searched ARP information, and forwarding the modified service message. By applying the invention, the MAC address in each data center station can not be transmitted to other data center stations, thereby effectively reducing the scale of the MAC address table and solving the problem of overlarge MAC address scale when two layers of data centers are interconnected.
Drawings
FIG. 1 is a schematic diagram of a MAC address learning process of a prior art OTV;
FIG. 2 is an exemplary diagram of a two-tier internetworking of a data center according to an embodiment of the present invention;
FIG. 3 is an exemplary diagram of partitioning a plurality of two-tier broadcast domains in a data center site based on that shown in FIG. 2;
FIG. 4 is a flow chart of a data center two-tier interconnect method according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an edge device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly apparent, the technical solutions of the present invention are described in detail below with reference to the accompanying drawings and examples.
The main idea of the invention is as follows: enabling MAC-forced forwarding (MFF) on an edge device of a data center site; forwarding ARP requests and ARP responses from the inside of a data center site or a remote data center site by proxy according to an MFF mechanism, and recording corresponding ARP information according to the received ARP responses; when a service message in the data center site or from a remote data center site is received, the service message is modified and forwarded by proxy according to the ARP information corresponding to the destination IP address of the service message, and two-layer interconnection of the data center is realized.
Here, the MFF's main function is to implement ARP proxy: an Ethernet Access Node (EAN) intercepts an ARP request of user equipment, and takes the MAC address of a specified Access Router (AR) as a responded MAC address through an ARP answering mechanism, so that a user is forced to send all traffic to the specified AR.
Referring to fig. 2, fig. 2 is an exemplary schematic diagram of a two-tier interconnection network of a data center according to an embodiment of the present invention, where EAN1, EAN2, and EAN3 are edge devices of a data center site A, B, C, respectively. The MAC address of EAN1 is MAC _ A, the user equipment inside the data center site A is connected through a port P11, and the access to a backbone network is realized through a port P12; the MAC address of EAN2 is MAC _ B, and the EAN2 is connected with user equipment inside a data center site B through a port P21 and is accessed to a backbone network through a port P22; the MAC address of EAN3 is MAC _ C, and is connected to the user equipment inside data center site C through port P31, and is accessed to the backbone network through port P32. The site A comprises user equipment H1 and H2, the IP address and the MAC address of the user equipment H1 are respectively IP1 and MAC1, and the IP address and the MAC address of the user equipment H2 are respectively IP2 and MAC 2; the site B comprises user equipment H3, and the IP address and the MAC address of the user equipment H3 are respectively IP3 and MAC 3; the site C includes a user equipment H4, and the IP address and MAC address of the user equipment H4 are IP4 and MAC4, respectively. MFF is enabled on EAN1, EAN2 and EAN3, and EAN1, EAN2 and EAN3 simultaneously bear the function of AR.
When the user equipment H1 in site a wants to communicate with the user equipment H3 in site C, the user equipment H1 first needs to know the MAC address of the user equipment H3, which can be known by ARP request.
The user equipment H1 sends an ARP request with the destination IP address IP3, and since MFF is enabled, EAN1 intercepts the ARP request at port P11, and then sends the source MAC of the ARP request: MAC1, modified to its own MAC address: MAC _ a and sends the modified ARP request to the backbone network through port P12;
EAN2, EAN3 may both receive the ARP request, but since user equipment H3 is not in site C, EAN3 does not return an ARP response.
After EAN2 receives the ARP request at port P22, the source MAC address of the ARP request is: MAC _ A, modified to its own MAC address: MAC _ B and broadcasts the modified ARP request within site B through port P21;
after receiving the ARP request, the user equipment 3 finds that the destination IP address is its own IP address, and thus learns the ARP information carried in the ARP request: IP1 and MAC _ B, and returning ARP response, wherein the source IP address and the source MAC address of the ARP response are respectively: IP3, MAC 3;
after receiving the ARP response of the user equipment H3 at the port P21, the EAN2 learns the ARP information of the ARP response: IP3, MAC3, and modifies the source MAC address of the ARP response to its own MAC address: MAC _ B, returning the modified ARP response to EAN1 through port P22;
after the EAN1 receives the ARP response at port P12, it learns the ARP information of the ARP response: IP3, MAC _ B, and modifies the source MAC to its own MAC address: MAC _ a, returning the modified ARP response to the user equipment H1 through port P11;
after receiving the ARP response, the user equipment H1 records the ARP information of the ARP response: IP3, MAC _ a; to this end, the user equipment H1 obtains the MAC address of the user equipment H3.
Here, since EAN1 enables MFF, the MAC address of host H3 obtained by user device H1 is not the MAC address of real user device H3, but the MAC address of EAN 1.
After obtaining the MAC address of the ue H3, the ue H1 may start communication with the ue H3, where the communication process is as follows:
the user equipment H1 sends a service message with a source IP address of IP1, a source MAC address of MAC3, a destination IP address of IP3 and a destination MAC address of MAC _ A;
after the EAN1 receives the service packet at the port P11, the EAN1 modifies the source MAC address of the service packet to MAC _ a, searches for corresponding ARP information in the ARP cache according to the destination IP address IP3 of the service packet, and according to the found ARP information: IP3, MAC _ B, modifying the destination MAC address of the service message into MAC _ B, then sending the modified service message to the backbone network through port P12;
after the EAN2 receives the service packet at the port P22, the EAN2 modifies the source MAC address of the service packet to MAC _ B, searches for corresponding ARP information in the ARP cache according to the destination IP address IP3 of the service packet, and according to the found ARP information: the IP3 and the MAC3 modify the destination MAC address of the service message into MAC3, and then send the modified service message to the user equipment H3 through a port P21;
after receiving the service packet, the user equipment H3 finds that the destination IP address and the destination MAC address of the service packet are the IP address and the MAC address of itself, respectively, and therefore, receives and normally processes the service packet.
Therefore, in the above process, the edge device of each data center station intercepts and captures the ARP protocol message between the user devices according to the MFF mechanism, and records the corresponding ARP information, so as to modify the source MAC address and the destination MAC address of the received service message in the communication process between the user devices, and send the modified service message by proxy, thereby implementing the two-layer interconnection of the data centers.
In practical application, in order to reduce unnecessary ARP broadcasts, when an edge device of a data center site receives an ARP request, it may also be determined whether ARP information corresponding to a destination IP address of the ARP request already exists, and if so, the MAC address of the edge device may be directly returned. For example, in fig. 2, after the user equipment H1 sends an ARP request with a destination IP address of IP3 and receives a corresponding ARP response, the EAN1 already records ARP information corresponding to IP 3: IP3, MAC _ B.
At this time, if the user equipment H2 in site a needs to communicate with the user equipment H3 in site B, an ARP request with the destination IP address IP3 may be sent first to obtain the MAC address of the user equipment H3; after EAN1 intercepts the ARP request, the ARP cache is searched to determine that the ARP information corresponding to the IP3 already exists, so that the MAC address of the EAN1 is directly: the MAC _ a is returned to the user equipment H2, so that the ARP information corresponding to the user equipment H3 learned by the user equipment H2 is: IP3, MAC _ a.
Thus, the user equipment H2 can send the service message with the destination IP address IP3 and the destination MAC address MAC _ a according to the obtained ARP information corresponding to the user equipment H3; after EAN1 receives the service message, the source MAC of the service message is modified into MAC _ A, the corresponding ARP information is searched in the ARP cache according to IP3, and according to the searched ARP information: the IP3 and the MAC _ B modify the target MAC of the service message into the MAC _ B and then send the MAC to the EAN 2; the EAN2 modifies the source MAC address of the service message into MAC _ B, and searches the corresponding ARP information in the ARP cache according to the IP 3: and the IP3 and the MAC3 modify the destination MAC of the service message into MAC3 and then send the modified MAC to the user equipment H3. To this end, communication between user device H2 and user device H3 is achieved.
In addition, for the condition that the sent ARP request does not receive the corresponding ARP response, a punishment mechanism can be established to further reduce unnecessary ARP broadcast and reduce the number of ARP broadcast messages in the network. For example, in fig. 3, if the user equipment H1 requests a MAC address of a user equipment that is dropped or does not exist, EAN1 intercepts the ARP request and broadcasts the ARP request through the backbone network, and EAN2 and EAN3 receive the ARP request and broadcast the ARP request in the respective sites to which the request belongs. If the user equipment H1 continuously sends the ARP request multiple times, it will occupy a lot of network resources, resulting in unnecessary waste of resources. For this, the EAN1 may establish a penalty record for the ARP request or the user equipment H1 that sent the ARP request, and if the ARP request is received again within a preset time or the ARP request sent by the user equipment H1 is received, it is directly discarded, so that unnecessary ARP broadcasting may be reduced.
In addition, after enabling the MFF on the edge device of the data center site, the edge device may also support migration of the virtual machine between the data center sites, and the IP address and the MAC address of the virtual machine remain unchanged before and after the virtual machine migration. Still taking fig. 2 as an example, suppose that virtual machine X on user equipment H1 migrates to user equipment H3, the IP address of virtual machine X is assumed to be IP1, and the MAC address is MAC 1. Then the virtual machine X migration process is as follows:
after the virtual machine X is restarted on the user equipment H3, a free ARP message with a source IP address of IP1 and a source MAC address of MAC1 can be sent;
EAN2 intercepts the free ARP message, and searches ARP information corresponding to IP1 in an ARP cache, if the ARP information is found, the virtual machine X is originally in the site B and is not migrated, so that the found ARP information is only needed to be updated; if not, modifying the source MAC address of the free ARP message into MAC _ B and then sending the MAC _ B to a backbone network;
after EAN1 receives the free ARP message, ARP information corresponding to IP1 is searched in an ARP cache, and the virtual machine X is shown to be migrated from the site A to the site B, so that the ARP information is updated, the source MAC address of the free ARP message is modified, and then the free ARP message is broadcasted in the site A, so that all switches in the site A learn MAC addresses according to the received free ARP message, and the MAC addresses of the virtual machines and the corresponding output ports are learned again;
after the EAN3 receives the gratuitous ARP message, the ARP information corresponding to the IP1 is not found in the ARP cache, which indicates that the migration event of the virtual machine X from the site C to the site B does not occur, and therefore, no processing is required.
It can be seen from the migration process that after the virtual machine is migrated, the user equipment to which the virtual machine is migrated sends a free ARP message, and after the edge device of the data center site receives the free ARP message, the free ARP message after the virtual machine is migrated is identified by matching ARP information, so that each user equipment in the data center site where the virtual machine is located before the virtual machine is migrated can know that the virtual machine is migrated, and further, each user equipment in the data center site where the virtual machine is located before the virtual machine is migrated can update the corresponding ARP information according to the free ARP message, thereby completing the virtual machine migration process and realizing rapid migration of services.
In the embodiment of the present invention shown in fig. 2, MFF is enabled on edge devices of each data center site, an ARP request of a user equipment is answered in a proxy manner according to an MFF mechanism, ARP information is learned based on an interactive service in the process, and a service packet between the data center sites is forwarded in a proxy manner according to the learned ARP information, so that two-layer interconnection of the data centers is realized, and it is ensured that an MAC address inside each data center site is not propagated to other data center sites through a backbone network, and an exchange inside each data center site can learn an MAC address inside the site where it is located, and cannot learn MAC addresses in other data center sites, thereby greatly reducing the scale of an MAC address table. In addition, in the above embodiment, the edge device only performs ARP information learning based on the interactive service, that is, only when receiving the corresponding ARP response after sending the ARP request, performs ARP information learning, and sends the learned ARP information to the hardware, instead of learning the ARP information of all ARP requests, so that the ARP table entries are also few, and the forwarding performance of the hardware is not affected.
The data center is interconnected in two layers, namely actually, two layers of interconnection between two layers of broadcasting domains formed by data center sites. For some huge data center sites, the data center sites can be further divided into a plurality of two-layer broadcast domains, and edge devices with the same functions as the edge devices of the data center sites are configured for each two-layer broadcast domain, so that a multi-stage MFF framework is realized, the number of MAC addresses in each stage of MFF framework can be reduced, and the ARP broadcast range is further narrowed. In the embodiment shown in fig. 2, it also belongs to a multi-stage MFF architecture: in the two-stage MFF architecture, when user equipment between data center sites communicates, an ARP request needs to pass through the edge device of the site where the ARP request is located and the proxy of the edge device of a remote site, and a service message also needs to pass through the edge device of the site where the ARP request is located and proxy forwarding of the edge device of the remote site to realize communication.
A communication situation when the data center site is divided into a plurality of two-layer broadcast domains to form a multi-level MFF architecture is described below with reference to fig. 3 based on the data center site shown in fig. 2.
Referring to fig. 3, fig. 3 is an exemplary diagram of dividing a plurality of two-layer broadcast domains in a data center site based on that shown in fig. 2, and as shown in fig. 3, a data center site a is divided into a two-layer broadcast domain a1 and a two-layer broadcast domain a2, and is configured with an edge device EAN11 with a MAC address of MAC _ a1 and an edge device EAN12 with a MAC address of MAC _ a2, respectively, where the two-layer broadcast domain a1 includes a user device H1, and the two-layer broadcast domain a2 includes a user device H2; EAN11 and EAN12 have the same functionality as EAN1, and EAN11, EAN12, EAN1 access to the same network through respective ports.
When the user equipment H1 needs to communicate with the user equipment H3, the MAC address of the user equipment H3 is first obtained by sending an ARP request, as follows:
the user equipment H1 sends an ARP request with the destination IP address of IP 3;
EAN11 intercepts the ARP request, modifies the source MAC address of the ARP request into MAC _ A1 according to an MFF mechanism, and then sends the MAC address out;
EAN1 and EAN12 can both receive the ARP request, and as user equipment H3 does not belong to layer two broadcast domain a2, EAN12 will not return an ARP response; after EAN1 receives the ARP request, the source MAC address of the ARP request is modified into MAC _ A and then sent to the backbone network;
after EAN2 receives the ARP request, the source MAC address of the ARP request is modified into MAC _ B and then broadcast in site B;
after receiving the ARP request, the user equipment H3 learns the ARP information: IP1, MAC _ B, and returns ARP response with the source IP address of IP3 and the source MAC address of MAC 3;
after EAN2 receives the ARP response, learns the ARP information: IP3, MAC3, and returns to EAN1 after modifying the source MAC address of the ARP response to MAC _ B;
after EAN1 receives the ARP response, learns the ARP information: IP3, MAC _ B, and returns to EAN11 after modifying the source MAC address of the ARP response to MAC _ A;
after EAN11 receives the ARP response, learns the ARP information: IP3, MAC _ A, and returns to the user equipment H1 after modifying the source MAC address of the ARP response to MAC _ A1;
after the user equipment H1 receives the ARP response, it learns the ARP information: IP3, MAC _ a 1.
The user device H1 can then start communicating with the user device H3 by obtaining the MAC address to host H3 (actually the MAC address of EAN 11) as follows:
the user equipment H1 sends a service message with a source IP address of IP1, a source MAC address of MAC1, a destination IP address of IP3 and a destination MAC address of MAC _ A1;
after EAN11 receives the service message, the source MAC address of the service message is modified to MAC _ A1, the corresponding ARP information is searched according to the destination IP address of the service message, and according to the searched ARP information: the IP3 and the MAC _ A modify the destination MAC address of the service message into the MAC _ A and then send the MAC _ A to the EAN 1;
after EAN1 receives the service message, the source MAC address of the service message is modified to MAC _ A, the corresponding ARP information is searched according to the destination IP address of the service message, and according to the searched ARP information: the IP3 and the MAC _ B modify the destination MAC address of the service message into the MAC _ B and send the MAC _ B modified destination MAC address to the EAN 2;
after EAN2 receives the service message, the source MAC address of the service message is modified into MAC _ B, the corresponding ARP information is searched according to the destination IP address of the service message, and according to the searched ARP information: IP3, MAC3, modify the destination MAC address of the service message into MAC3, then send to user equipment H3;
therefore, the user equipment H1 and the user equipment H3 realize communication, and thus, after the data center site is divided into a plurality of two-layer broadcast domains to form a multi-level MFF architecture, normal communication of the user equipment between the data center sites can still be ensured, and the range of ARP broadcast can be further reduced.
Based on the foregoing principle description, the embodiment of the present invention provides a data center two-layer interconnection method and an edge device.
Referring to fig. 4, fig. 4 is a flowchart of a two-layer interconnection method of a data center according to an embodiment of the present invention, including the following steps:
Here, MFF has been enabled in advance on the edge device; the first port is a port for connecting user equipment inside the site; the second port is a port for connecting edge equipment of a remote site.
Here, the edge device discards a traffic packet whose destination MAC is not its own MAC address.
Here, the edge device discards a traffic packet whose destination MAC is not its own MAC address.
In the embodiment of the present invention shown in fig. 4, when the current EAN receives the ARP request, if the ARP information corresponding to the destination IP of the ARP request already exists, the ARP request may not be forwarded by proxy, but a corresponding ARP response may be directly returned, so that ARP broadcasts in the two-layer network may be greatly reduced.
Therefore, before the current EAN modifies the source MAC address of the ARP request as the MAC address of the current EAN after the first port receives the ARP request from the user equipment, and then sends the ARP request from the second port, the method further includes: searching corresponding ARP information in an ARP cache according to the target IP of the ARP request, if the corresponding ARP information is searched, returning the MAC address of the user equipment to the user equipment, and if the corresponding ARP information is not searched, modifying the source MAC address of the ARP request into the MAC address of the user equipment and then sending the source MAC address of the ARP request out from a second port;
after the current EAN receives the ARP request of the superior EAN at the second port, and before the current EAN is sent out from the first port after modifying the source MAC address of the ARP request to the MAC address of the current EAN, the method further includes: and searching corresponding ARP information in an ARP cache according to the target IP of the ARP request, if the corresponding ARP information is searched, returning the MAC address of the source MAC address to the upper EAN, and if the corresponding ARP information is not searched, modifying the source MAC address of the ARP request into the MAC address of the source MAC address of the ARP request and then sending the modified source MAC address from the first port.
In addition, for the condition that the sent ARP request does not receive the corresponding ARP response, a corresponding penalty mechanism can be established, so that ARP broadcast in the two-layer network is further reduced.
A penalty record may be established for the ARP request, which is no longer proxied to forward when it is received again within a preset time. The specific implementation can be as follows:
after the source MAC address of the ARP request is modified to be the MAC address of the source MAC address, the source MAC address is sent out from the second port, the method further includes: if the corresponding ARP response is not received within the preset time, setting a punishment mark and punishment aging time aiming at the ARP request, and deleting the punishment mark aiming at the ARP request if the aging time is exceeded;
thus, after the current EAN receives the ARP request of the user equipment at the first port, before the current EAN modifies the source MAC address of the ARP request to the MAC address of the current EAN and then sends the modified source MAC address to the second port, the method may further include: and judging whether a punishment mark aiming at the ARP request exists, if so, not sending the ARP request, otherwise, modifying the source MAC address of the ARP request to be the MAC address of the source MAC address and sending the source MAC address from the second port.
And a penalty record can be established for the user equipment sending the ARP request, and when the ARP request sent by the user equipment is received again in preset time, the ARP request is not forwarded by proxy. The specific implementation can be as follows:
after the source MAC address of the ARP request is modified to be the MAC address of the source MAC address, the source MAC address is sent out from the second port, the method further includes: if the corresponding ARP response is not received within the preset time, setting a punishment mark and punishment aging time aiming at the user equipment sending the ARP request, and deleting the punishment mark aiming at the user equipment sending the ARP request if the punishment mark exceeds the aging time;
thus, before the current EAN modifies the source MAC address of the ARP request to the MAC address of the current EAN after the first port receives the ARP request of the user equipment, and then sends the ARP request from the second port, the method further includes: and judging whether a punishment mark aiming at the user equipment sending the ARP request exists, if so, not sending the ARP request, otherwise, modifying the source MAC address of the ARP request to be the MAC address of the source MAC address and sending the modified source MAC address from the second port.
The embodiment of the present invention shown in fig. 4 may also support virtual machine migration, and if it is necessary to support virtual machine migration, the method may further include:
when the EAN receives a free ARP message of a user host at a first port, searching corresponding ARP information according to a target IP address of the free ARP message, if the ARP information is searched, updating the ARP information, and if not, modifying a source MAC address of the free ARP message into an MAC address of the EAN, and then sending the modified source MAC address of the free ARP message out from a second port;
when the EAN receives a free ARP message of the edge equipment of the remote site at the second port, the EAN searches corresponding ARP information according to the target IP address of the free ARP message, if the ARP information is found, the ARP information is updated, the source MAC address of the free ARP message is modified to be the MAC address of the EAN, and then the ARP message is sent out from the first port, and if the ARP message is not found, the EAN does not process the ARP message.
In the embodiment of the present invention shown in fig. 4, if a plurality of two-layer broadcast domains are not divided in a data center site, the user equipment is a user host of the data center;
if the data center site is divided into a plurality of two-layer broadcast domains, and the edge device in each two-layer broadcast domain is configured with the function of the edge device; the user equipment is an edge device of the two-layer broadcast domain having the same function as the edge device.
The two-layer interconnection method of the data center in the embodiment of the invention is explained above, and the invention also provides edge equipment.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an edge device according to an embodiment of the present invention, the edge device including: a configuration unit 501, a first transceiver unit 502, a second transceiver unit 503, and a processing unit 504; wherein,
a configuration unit 501 for configuring and enabling the MFF in advance;
a first transceiving unit 502, configured to send a first processing instruction to the processing unit 504 when the first port receives an ARP request of a user equipment, and send the ARP request out of the second port after the processing unit 504 processes the ARP request according to the first processing instruction; the processing unit 504 is configured to send a second processing instruction to the processing unit 504 if the second port receives a corresponding ARP response after sending the ARP request received by the first port from the second port, and send the ARP response from the first port after the processing unit 504 processes the ARP response according to the second processing instruction; the second port is configured to send a first processing instruction to the processing unit 504 when receiving an ARP request of an edge device of a remote site, and send the ARP request out of the first port after the processing unit 504 processes the ARP request according to the first processing instruction; the processing unit 504 is configured to send a second processing instruction to the processing unit 504 if the first port receives a corresponding ARP response after sending the ARP request received by the second port from the first port, and send the ARP response from the second port after the processing unit 504 processes the ARP response according to the second processing instruction;
a second transceiving unit 503, configured to send a third processing instruction to the processing unit 504 when the first port receives a service packet whose destination MAC of the user equipment is an MAC address of the first port, and send the service packet out of the second port after the processing unit 504 processes the service packet according to the third processing instruction; the second port is configured to send a third processing instruction to the processing unit 504 when receiving a service packet whose destination MAC of the edge device of the remote site is the MAC address of the second port, and send the service packet out of the first port after the processing unit 504 processes the service packet according to the third processing instruction;
a processing unit 504, configured to, when receiving the first processing instruction of the first transceiving unit 502, set a source MAC address of the ARP request received by the first transceiving unit 502 as a MAC address of the source MAC address; the second processing unit is configured to record ARP information when receiving the second processing instruction of the first transceiving unit 502, and modify the source MAC address of the ARP response to its own MAC address; the second transceiver unit 503 is configured to modify a source MAC address of the service packet received by the second transceiver unit 503 into its own MAC address when receiving a third processing instruction of the second transceiver unit 503, and modify a destination MAC address of the service packet according to ARP information corresponding to a destination IP of the service packet;
the first port is a port of user equipment inside a connection site; the second port is a port for connecting edge equipment of a remote site.
After receiving the first processing instruction of the first transceiving unit 502, the processing unit 504 is further configured to, before the source MAC address of the ARP request received by the first transceiving unit 502 is the MAC address of the source MAC address,: searching corresponding ARP information in an ARP cache according to the target IP of the ARP request, if the corresponding ARP information is found, sending a response instruction to the first transceiving unit 502, and if the corresponding ARP information is not found, modifying the source MAC address of the ARP request into the MAC address of the source MAC address;
after the processing unit 504 processes the ARP request according to the first processing instruction, before the first transceiving unit 502 sends the ARP request of the user equipment received by the first port out from the second port, the first transceiving unit is further configured to: judging whether a response instruction of the processing unit 504 is received, if so, returning the MAC address of the user equipment to the user equipment, otherwise, sending the ARP request of the user equipment received at the first port out from the second port; after the processing unit 504 processes the ARP request according to the first processing instruction, before sending out the ARP request of the edge device of the remote station received at the second port from the first port, the processing unit is further configured to: and judging whether a response instruction of the processing unit 504 is received, if so, returning the MAC address of the MAC address to the edge device of the remote station, and otherwise, sending the ARP request of the edge device of the remote station received at the second port from the first port.
The first transceiving unit 502 is further configured to, after sending the ARP request of the user equipment received at the first port from the second port: if the corresponding ARP response is not received within the preset time, setting a punishment mark and punishment aging time aiming at the ARP request, and deleting the punishment mark aiming at the ARP request if the aging time is exceeded;
the first transceiving unit 502, after the first port receives the ARP request of the user equipment, and before sending the first processing instruction to the processing unit 504, is further configured to: and judging whether a penalty mark for the ARP request exists or not, if so, not sending a first processing instruction to the processing unit 504, and otherwise, sending the first processing instruction to the processing unit 504.
After the first transceiving unit 502 sends out the ARP request of the user equipment received at the first port from the second port, it is further configured to: if the corresponding ARP response is not received within the preset time, setting a punishment mark and punishment aging time aiming at the user equipment sending the ARP request, and deleting the punishment mark aiming at the user equipment sending the ARP request if the punishment mark exceeds the aging time;
the first transceiving unit 502, after the first port receives the ARP request of the user equipment, and before sending the first processing instruction to the processing unit 504, is further configured to: and judging whether a penalty mark for the user equipment sending the ARP request exists, if so, not sending a first processing instruction to the processing unit 504, and otherwise, sending the first processing instruction to the processing unit 504.
The first transceiving unit 502 is configured to send a fourth processing instruction to the processing unit 504 when the first port receives a gratuitous ARP packet of the user equipment, and send the gratuitous ARP packet out of the second port if the processing unit 504 receives a forwarding instruction of the processing unit 504 after the processing unit 504 processes the gratuitous ARP packet according to the fourth processing instruction; the second port is configured to send a fifth processing instruction to the processing unit 504 when receiving a gratuitous ARP packet of an edge device of a remote site, and send the gratuitous ARP packet out of the first port if receiving a forwarding instruction of the processing unit 504 after the processing unit 504 processes the gratuitous ARP packet according to the fifth processing instruction;
the processing unit 504 is configured to, after receiving the fourth processing instruction sent by the first transceiving unit 502, search for corresponding ARP information according to a destination IP address of a gratuitous ARP packet received by the first transceiving unit 502 at the first port, if the ARP information is found, update the ARP information, otherwise, modify a source MAC address of the gratuitous ARP packet to be an MAC address of the source MAC address, and send a forwarding instruction to the first transceiving unit 502; after receiving the fifth processing instruction sent by the first transceiving unit 502, the first transceiving unit 502 searches for corresponding ARP information according to the destination IP address of the gratuitous ARP packet received by the first transceiving unit 502 at the second port, if the ARP information is found, the ARP information is updated, the source MAC address of the gratuitous ARP packet is modified to be the MAC address of the source MAC address, and a forwarding instruction is sent to the first transceiving unit 502, and if the ARP information is not found, the processing is not performed.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (11)
1. A data center two-layer interconnection method is characterized in that MFFs are configured and enabled on edge equipment in advance; the method comprises the following steps:
when the first port receives an ARP request of user equipment, the edge equipment modifies the source MAC address of the ARP request into the MAC address of the edge equipment, then the edge equipment sends the ARP request out from the second port, records ARP information after receiving corresponding ARP response from the second port, and modifies the source MAC address of the ARP response into the MAC address of the edge equipment, and then the ARP response is sent out from the first port;
when the edge device receives an ARP request of the edge device of a remote site at the second port, the source MAC address of the ARP request is modified to be the MAC address of the edge device, and then the ARP request is sent out from the first port, after a corresponding ARP response is received from the first port, ARP information is recorded, and the source MAC address of the ARP response is modified to be the MAC address of the edge device, and then the ARP response is sent out from the second port;
when the edge device receives a service message of which the target MAC of the user device is the MAC address of the edge device, the edge device modifies the source MAC address of the service message into the MAC address of the edge device, modifies the target MAC address of the service message according to ARP information corresponding to the target IP of the service message, and sends out the modified service message from the second port;
when the edge device receives a service message of which the destination MAC of the edge device of the remote site is the MAC address of the edge device at the second port, modifying the source MAC address of the service message as the MAC address of the edge device, modifying the destination MAC address of the service message according to ARP information corresponding to the destination IP of the service message, and sending the modified service message out from the first port;
the first port is a port of user equipment inside a connection site; the second port is a port for connecting edge equipment of a remote site.
2. The method for two-tier interconnection of data centers according to claim 1,
after the first port receives the ARP request of the user equipment, before the edge device modifies the source MAC address of the ARP request to the MAC address of the edge device and sends the modified source MAC address to the second port, the method further includes: searching corresponding ARP information in an ARP cache according to the target IP of the ARP request, if the corresponding ARP information is searched, returning the MAC address of the user equipment to the user equipment, and if the corresponding ARP information is not searched, modifying the source MAC address of the ARP request into the MAC address of the user equipment and then sending the source MAC address of the ARP request out from a second port;
after the edge device receives the ARP request of the edge device of the remote site at the second port, before the edge device modifies the source MAC address of the ARP request to the MAC address of the edge device and sends the modified source MAC address to the first port, the method further includes: and searching corresponding ARP information in an ARP cache according to the target IP of the ARP request, if the corresponding ARP information is searched, returning the MAC address of the source MAC address to the edge equipment of the remote station, and if the corresponding ARP information is not searched, modifying the source MAC address of the ARP request into the MAC address of the source MAC address of the ARP request and then sending the modified source MAC address from the first port.
3. The method for two-tier interconnection of data centers according to claim 2,
after the source MAC address of the ARP request is modified to be the MAC address of the source MAC address, the source MAC address is sent out from the second port, the method further includes: if the corresponding ARP response is not received within the preset time, setting a punishment mark and punishment aging time aiming at the ARP request, and deleting the punishment mark aiming at the ARP request if the aging time is exceeded;
before the current EAN modifies the source MAC address of the ARP request to the MAC address of the current EAN after the first port receives the ARP request from the user equipment and before the current EAN is sent out from the second port, the method further includes: and judging whether a punishment mark aiming at the ARP request exists, if so, not sending the ARP request, otherwise, modifying the source MAC address of the ARP request to be the MAC address of the source MAC address and sending the source MAC address from the second port.
4. A method of two-layer interworking between two-layer broadcast domains according to claim 2,
after the source MAC address of the ARP request is modified to be the MAC address of the source MAC address, the source MAC address is sent out from the second port, the method further includes: if the corresponding ARP response is not received within the preset time, setting a punishment mark and punishment aging time aiming at the user equipment sending the ARP request, and deleting the punishment mark aiming at the user equipment sending the ARP request if the punishment mark exceeds the aging time;
before the first port modifies a source MAC address of the ARP request as its own MAC address and sends the modified source MAC address to the second port after receiving the ARP request from the user equipment, the method further includes: and judging whether a punishment mark aiming at the user equipment sending the ARP request exists, if so, not sending the ARP request, otherwise, modifying the source MAC address of the ARP request to be the MAC address of the source MAC address and sending the modified source MAC address from the second port.
5. The method for two-tier interconnection of data centers according to any one of claims 1 to 4, further comprising:
when the edge device receives a free ARP message of the user device at the first port, searching corresponding ARP information according to a target IP address of the free ARP message, if the corresponding ARP information is searched, updating the ARP information, otherwise, modifying a source MAC address of the free ARP message into an MAC address of the edge device, and then sending the modified source MAC address of the free ARP message out from the second port;
when the edge device receives a free ARP message of the edge device of the remote site at the second port, the edge device searches corresponding ARP information according to the destination IP address of the free ARP message, if the free ARP message is found, the ARP information is updated, the source MAC address of the free ARP message is modified to be the MAC address of the edge device, and then the free ARP message is sent out from the first port, and if the free ARP message is not found, the edge device does not process the free ARP message.
6. The method for two-tier interconnection of data centers according to any one of claims 1 to 4,
the user equipment is a user host of the data center;
or,
the data center is divided into a plurality of two-layer broadcast domains, and the functions of the edge devices are configured at the edge devices of each two-layer broadcast domain;
the user equipment is an edge device of the two-layer broadcast domain having the same function as the edge device.
7. An edge device for data center two-tier interconnect, the edge device comprising: the device comprises a configuration unit, a first transceiving unit, a second transceiving unit and a processing unit;
the configuration unit is used for configuring and enabling the MFF in advance;
the first transceiving unit is used for sending a first processing instruction to the processing unit when the first port receives an ARP request of the user equipment, and sending the ARP request out from the second port after the processing unit processes the ARP request according to the first processing instruction; the ARP response processing unit is used for sending an ARP response from the first port to the processing unit after the ARP request received by the first port is sent from the second port and if a corresponding ARP response is received by the second port; the second port is used for sending a first processing instruction to the processing unit when receiving an ARP request of the edge equipment of the remote site, and sending the ARP request out from the first port after the processing unit processes the ARP request according to the first processing instruction; the ARP response processing unit is used for sending an ARP response from the second port to the processing unit after the ARP request received by the second port is sent from the first port and if the first port receives a corresponding ARP response, the second processing instruction is sent to the processing unit, and the ARP response is sent from the second port after the processing unit processes the ARP response according to the second processing instruction;
the second transceiving unit is used for sending a third processing instruction to the processing unit when the first port receives a service message of which the destination MAC of the user equipment is the MAC address of the first transceiving unit, and sending the service message out from the second port after the processing unit processes the service message according to the third processing instruction; the second port is used for sending a third processing instruction to the processing unit when receiving a service message of which the destination MAC of the edge device of the remote site is the MAC address of the second port, and sending the service message out from the first port after the processing unit processes the service message according to the third processing instruction;
the processing unit is used for setting the source MAC address of the ARP request received by the first transceiving unit as the MAC address of the processing unit when receiving the first processing instruction of the first transceiving unit; the first receiving and sending unit is used for receiving a first processing instruction of the first receiving and sending unit, recording ARP information and modifying a source MAC address of ARP response into an MAC address of the first receiving and sending unit; when receiving a third processing instruction of the second transceiver unit, modifying the source MAC address of the service message received by the second transceiver unit into the MAC address of the second transceiver unit, and modifying the destination MAC address of the service message according to the ARP information corresponding to the destination IP of the service message;
the first port is a port of user equipment inside a connection site; the second port is a port for connecting edge equipment of a remote site.
8. The edge device of claim 7,
after receiving the first processing instruction of the first transceiving unit, the processing unit is further configured to, before the source MAC address of the ARP request received by the first transceiving unit is the MAC address of the processing unit: searching corresponding ARP information in an ARP cache according to the target IP of the ARP request, if the corresponding ARP information is searched, sending a response instruction to the first transceiving unit, and if the corresponding ARP information is not searched, modifying the source MAC address of the ARP request into the MAC address of the source MAC address;
the first transceiving unit, after the processing unit processes the ARP request according to the first processing instruction, is further configured to, before sending the ARP request of the user equipment received at the first port from the second port: judging whether a response instruction of the processing unit is received or not, if so, returning the MAC address of the processing unit to the user equipment, otherwise, sending the ARP request of the user equipment received at the first port out from the second port; after the processing unit processes the ARP request according to the first processing instruction, before sending out the ARP request of the edge device of the remote site received at the second port from the first port, the processing unit is further configured to: and judging whether a response instruction of the processing unit is received or not, if so, returning the MAC address of the processing unit to the edge equipment of the remote station, and otherwise, sending the ARP request of the edge equipment of the remote station received at the second port from the first port.
9. The edge device of claim 8,
the first transceiving unit is further configured to, after sending the ARP request of the user equipment received at the first port from the second port: if the corresponding ARP response is not received within the preset time, setting a punishment mark and punishment aging time aiming at the ARP request, and deleting the punishment mark aiming at the ARP request if the aging time is exceeded;
after the first port receives the ARP request of the user equipment, and before the first transceiving unit sends the first processing instruction to the processing unit, the first transceiving unit is further configured to: and judging whether a punishment mark aiming at the ARP request exists, if so, not sending a first processing instruction to the processing unit, and if not, sending the first processing instruction to the processing unit.
10. The edge device of claim 8,
after the first transceiving unit sends the ARP request of the user equipment received at the first port out from the second port, the first transceiving unit is further configured to: if the corresponding ARP response is not received within the preset time, setting a punishment mark and punishment aging time aiming at the user equipment sending the ARP request, and deleting the punishment mark aiming at the user equipment sending the ARP request if the punishment mark exceeds the aging time;
after the first port receives the ARP request of the user equipment, and before the first transceiving unit sends the first processing instruction to the processing unit, the first transceiving unit is further configured to: and judging whether a punishment mark aiming at the user equipment sending the ARP request exists, if so, not sending a first processing instruction to the processing unit, and otherwise, sending the first processing instruction to the processing unit.
11. The edge device according to any of claims 7-10,
the first transceiving unit is used for sending a fourth processing instruction to the processing unit when the first port receives a free ARP message of the user equipment, and sending the free ARP message out from the second port if the processing unit receives a forwarding instruction of the processing unit after processing the free ARP message according to the fourth processing instruction; the second port is used for sending a fifth processing instruction to the processing unit when receiving a free ARP message of the edge equipment of the remote site, and sending the free ARP message out from the first port if receiving a forwarding instruction of the processing unit after the processing unit processes the free ARP message according to the fifth processing instruction;
the processing unit is used for searching corresponding ARP information according to a target IP address of a free ARP message received by the first transceiving unit at the first port after receiving a fourth processing instruction sent by the first transceiving unit, if the corresponding ARP information is searched, updating the ARP information, and otherwise, modifying a source MAC address of the free ARP message into a self MAC address and sending a forwarding instruction to the first transceiving unit; and the ARP processing unit is used for searching corresponding ARP information according to the destination IP address of the free ARP message received by the first transceiving unit at the second port after receiving a fifth processing instruction sent by the first transceiving unit, updating the ARP information if the corresponding ARP information is searched, modifying the source MAC address of the free ARP message into the MAC address of the ARP message, sending a forwarding instruction to the first transceiving unit, and not processing if the corresponding ARP message is not searched.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103002787A CN102355417A (en) | 2011-10-08 | 2011-10-08 | Data center two-layer interconnection method and device |
| PCT/CN2012/081575 WO2013049989A1 (en) | 2011-10-08 | 2012-09-19 | Layer two interconnection between data centers |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103002787A CN102355417A (en) | 2011-10-08 | 2011-10-08 | Data center two-layer interconnection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102355417A true CN102355417A (en) | 2012-02-15 |
Family
ID=45578914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011103002787A Pending CN102355417A (en) | 2011-10-08 | 2011-10-08 | Data center two-layer interconnection method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN102355417A (en) |
| WO (1) | WO2013049989A1 (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102710509A (en) * | 2012-05-18 | 2012-10-03 | 杭州华三通信技术有限公司 | Automatic data center configuration method and method |
| WO2013049989A1 (en) * | 2011-10-08 | 2013-04-11 | Hangzhou H3C Technologies Co., Ltd. | Layer two interconnection between data centers |
| CN103841029A (en) * | 2012-11-21 | 2014-06-04 | 华为技术有限公司 | Data transmission method, data transmission device and data transmission system |
| CN103905325A (en) * | 2012-12-26 | 2014-07-02 | 中兴通讯股份有限公司 | Two-layer network data transmission method and network node |
| CN104168213A (en) * | 2014-08-18 | 2014-11-26 | 福建星网锐捷网络有限公司 | Data message processing method and device and network equipment in two-layer Internet |
| CN104283783A (en) * | 2014-10-11 | 2015-01-14 | 杭州华三通信技术有限公司 | Gateway equipment message transmitting method and device in plug and play network |
| WO2015015505A1 (en) * | 2013-08-01 | 2015-02-05 | Hewlett-Packard Development Company, L.P. | Address resolution rewriting |
| CN104935614A (en) * | 2014-03-18 | 2015-09-23 | 腾讯科技（深圳）有限公司 | Data transmission method and device thereof |
| CN105872117A (en) * | 2015-10-26 | 2016-08-17 | 乐视云计算有限公司 | Method and system for obtaining MAC address and virtual machine manager |
| EP2982098A4 (en) * | 2013-04-02 | 2016-12-07 | Hangzhou H3C Tech Co Ltd | Internet protocol address resolution |
| CN107070934A (en) * | 2017-04-26 | 2017-08-18 | 腾讯科技（深圳）有限公司 | A kind of transparent proxy implementation, device and client |
| CN107800697A (en) * | 2017-10-26 | 2018-03-13 | 新华三技术有限公司 | Access authentication method and device |
| CN108243262A (en) * | 2016-12-26 | 2018-07-03 | 大唐移动通信设备有限公司 | Learning method, device and the network three-layer equipment of ARP table |
| CN109995638A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | A kind of method and apparatus carrying out double layer intercommunication |
| CN112671629A (en) * | 2020-09-24 | 2021-04-16 | 紫光云技术有限公司 | Method for realizing private line access under cloud network |
| CN112839072A (en) * | 2020-10-19 | 2021-05-25 | 南京中兴新软件有限责任公司 | Data processing method, device, system, computer equipment and readable medium |
| CN112866113A (en) * | 2020-12-29 | 2021-05-28 | 京信网络系统股份有限公司 | Method, system, computer device and storage medium for ARP proxy in routing packet forwarding |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103731351B (en) * | 2013-12-16 | 2017-09-15 | 新华三技术有限公司 | A kind of broadcasting packet retransmission method and equipment |
| US10009268B2 (en) | 2014-01-06 | 2018-06-26 | Samsung Electronics Co., Ltd. | Method and apparatus for relaying packet transmission and updating network address information in communication system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1968184A (en) * | 2005-11-18 | 2007-05-23 | 杭州华为三康技术有限公司 | Link layer communication method in LAN and network device thereof |
| CN101026591A (en) * | 2007-04-13 | 2007-08-29 | 杭州华为三康技术有限公司 | Network address confilict user inter-access method and route repeating device |
| CN101521631A (en) * | 2009-04-14 | 2009-09-02 | 华为技术有限公司 | Treatment method, equipment and system for VPLS network messages |
| CN101577722A (en) * | 2009-06-03 | 2009-11-11 | 中兴通讯股份有限公司 | Method for realizing MAC forced forwarding function and device |
| CN102201963A (en) * | 2010-03-22 | 2011-09-28 | 杭州华三通信技术有限公司 | Media access control-forced forwarding method and functional unit |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102355417A (en) * | 2011-10-08 | 2012-02-15 | 杭州华三通信技术有限公司 | Data center two-layer interconnection method and device |
-
2011
- 2011-10-08 CN CN2011103002787A patent/CN102355417A/en active Pending
-
2012
- 2012-09-19 WO PCT/CN2012/081575 patent/WO2013049989A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1968184A (en) * | 2005-11-18 | 2007-05-23 | 杭州华为三康技术有限公司 | Link layer communication method in LAN and network device thereof |
| CN101026591A (en) * | 2007-04-13 | 2007-08-29 | 杭州华为三康技术有限公司 | Network address confilict user inter-access method and route repeating device |
| CN101521631A (en) * | 2009-04-14 | 2009-09-02 | 华为技术有限公司 | Treatment method, equipment and system for VPLS network messages |
| CN101577722A (en) * | 2009-06-03 | 2009-11-11 | 中兴通讯股份有限公司 | Method for realizing MAC forced forwarding function and device |
| CN102201963A (en) * | 2010-03-22 | 2011-09-28 | 杭州华三通信技术有限公司 | Media access control-forced forwarding method and functional unit |
Non-Patent Citations (1)
| Title |
|---|
| T.MELSEN 等: "MAC-Forced Forwarding:A Method for Subscriber Separation on an Ethernet Access Network", 《3GPP RFC4562》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013049989A1 (en) * | 2011-10-08 | 2013-04-11 | Hangzhou H3C Technologies Co., Ltd. | Layer two interconnection between data centers |
| CN102710509A (en) * | 2012-05-18 | 2012-10-03 | 杭州华三通信技术有限公司 | Automatic data center configuration method and method |
| CN102710509B (en) * | 2012-05-18 | 2015-04-15 | 杭州华三通信技术有限公司 | Automatic data center configuration method and method |
| CN103841029A (en) * | 2012-11-21 | 2014-06-04 | 华为技术有限公司 | Data transmission method, data transmission device and data transmission system |
| CN103841029B (en) * | 2012-11-21 | 2018-02-23 | 华为技术有限公司 | Data transmission method, device and system |
| CN103905325A (en) * | 2012-12-26 | 2014-07-02 | 中兴通讯股份有限公司 | Two-layer network data transmission method and network node |
| CN103905325B (en) * | 2012-12-26 | 2018-12-11 | 南京中兴软件有限责任公司 | Double layer network data transferring method and network node |
| EP2982098A4 (en) * | 2013-04-02 | 2016-12-07 | Hangzhou H3C Tech Co Ltd | Internet protocol address resolution |
| US10027623B2 (en) | 2013-04-02 | 2018-07-17 | Hewlett Packard Enterprise Development Lp | Internet protocol address resolution |
| WO2015015505A1 (en) * | 2013-08-01 | 2015-02-05 | Hewlett-Packard Development Company, L.P. | Address resolution rewriting |
| US10356037B2 (en) | 2013-08-01 | 2019-07-16 | Hewlett Packard Enterprise Development Lp | Address resolution rewriting |
| CN104935614A (en) * | 2014-03-18 | 2015-09-23 | 腾讯科技（深圳）有限公司 | Data transmission method and device thereof |
| WO2015139633A1 (en) * | 2014-03-18 | 2015-09-24 | Tencent Technology (Shenzhen) Company Limited | Data transmission method and apparatus |
| CN104935614B (en) * | 2014-03-18 | 2019-12-10 | 腾讯科技（深圳）有限公司 | Data transmission method and device |
| CN104168213A (en) * | 2014-08-18 | 2014-11-26 | 福建星网锐捷网络有限公司 | Data message processing method and device and network equipment in two-layer Internet |
| CN104283783A (en) * | 2014-10-11 | 2015-01-14 | 杭州华三通信技术有限公司 | Gateway equipment message transmitting method and device in plug and play network |
| CN104283783B (en) * | 2014-10-11 | 2017-09-15 | 新华三技术有限公司 | The method and apparatus that gateway device E-Packets in a kind of plug and play network |
| CN105872117A (en) * | 2015-10-26 | 2016-08-17 | 乐视云计算有限公司 | Method and system for obtaining MAC address and virtual machine manager |
| CN108243262A (en) * | 2016-12-26 | 2018-07-03 | 大唐移动通信设备有限公司 | Learning method, device and the network three-layer equipment of ARP table |
| CN107070934A (en) * | 2017-04-26 | 2017-08-18 | 腾讯科技（深圳）有限公司 | A kind of transparent proxy implementation, device and client |
| CN107800697A (en) * | 2017-10-26 | 2018-03-13 | 新华三技术有限公司 | Access authentication method and device |
| CN107800697B (en) * | 2017-10-26 | 2020-03-06 | 新华三技术有限公司 | Access authentication method and device |
| CN109995638A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | A kind of method and apparatus carrying out double layer intercommunication |
| CN112671629A (en) * | 2020-09-24 | 2021-04-16 | 紫光云技术有限公司 | Method for realizing private line access under cloud network |
| CN112839072A (en) * | 2020-10-19 | 2021-05-25 | 南京中兴新软件有限责任公司 | Data processing method, device, system, computer equipment and readable medium |
| CN112866113A (en) * | 2020-12-29 | 2021-05-28 | 京信网络系统股份有限公司 | Method, system, computer device and storage medium for ARP proxy in routing packet forwarding |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2013049989A1 (en) | 2013-04-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102355417A (en) | Data center two-layer interconnection method and device | |
| US11411776B2 (en) | Multi-cloud VPC routing and registration | |
| US9515930B2 (en) | Intelligent handling of virtual machine mobility in large data center environments | |
| CN102457583B (en) | Realization method of mobility of virtual machine and system thereof | |
| CN102263704B (en) | Topology construction method and device supporting layer 2 interconnection of data centers | |
| EP2600573B1 (en) | Method for transmitting addresses correspondence relationship in second-layer protocol using link status routing | |
| JP2020162146A (en) | System and method for distributed flow state p2p setup in virtual networks | |
| US9253140B2 (en) | System and method for optimizing within subnet communication in a network environment | |
| US6747979B1 (en) | Method and apparatus for bridging between networks | |
| US9461943B2 (en) | Network assisted virtual machine mobility | |
| CN107181688B (en) | System and method for realizing server-side cross-domain data transmission optimization in SDN network | |
| US11252126B1 (en) | Domain name resolution in environment with interconnected virtual private clouds | |
| CN103118148B (en) | A kind of ARP buffering updating method and equipment | |
| CN105264493A (en) | Dynamic virtual machines migration over information centric networks | |
| WO2012142750A1 (en) | Method, apparatus and system for address resolution | |
| CN107094110B (en) | DHCP message forwarding method and device | |
| CN111614541B (en) | Method for adding public cloud network physical host into VPC | |
| US20140325637A1 (en) | Supporting IP Address Overlapping Among Different Virtual Networks | |
| EP2584742B1 (en) | Method and switch for sending packet | |
| CN107547349A (en) | A kind of method and device of virtual machine (vm) migration | |
| WO2016134624A1 (en) | Routing method, device and system, and gateway dispatching method and device | |
| CN105591907B (en) | A kind of route obtaining method and device | |
| CN103685007B (en) | A kind of mac learning method when edge device message forwards and edge device | |
| WO2013159667A1 (en) | Virtual router redundancy protocol load balancing mode (vrrpe) | |
| CN110752989A (en) | Method and device for forwarding east-west traffic |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120215 |