CN109218053A - Implementation method, system and the storage medium of virtual data center - Google Patents
Implementation method, system and the storage medium of virtual data center Download PDFInfo
- Publication number
- CN109218053A CN109218053A CN201710534706.XA CN201710534706A CN109218053A CN 109218053 A CN109218053 A CN 109218053A CN 201710534706 A CN201710534706 A CN 201710534706A CN 109218053 A CN109218053 A CN 109218053A
- Authority
- CN
- China
- Prior art keywords
- network
- host computer
- physical
- virtual
- core switch
- 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
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
- H04L12/4641—Virtual LANs, VLANs, e.g. virtual private networks [VPN]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/04—Network management architectures or arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention relates to a kind of implementation method of virtual data center, system and storage mediums.Wherein, this method comprises: network element device is based on leaf ridge network architecture building physical network and constructs overlay network on the physical network, the network element device includes gateway, core switch, frame topcross, the gateway and each core switch are there are physical link, and there are physical links with each core switch for the frame topcross；Cloud platform configures network, issues network configuration information to controller；The controller is based on the network configuration information and generates the flow table guidance network element device by overlay network progress data forwarding, realizes the communication between fictitious host computer and the communication of fictitious host computer and outer net.By the implementation method, system and storage medium of above-mentioned virtual data center, the efficiency of transmission of data center is improved.
Description
Technical field
The present invention relates to fields of communication technology, more particularly to a kind of implementation method of virtual data center, device and deposit
Storage media.
Background technique
Traditional data center generallys use server virtualization, Storage Virtualization and network virtualization technology and reallocates resources
The dynamic adaptation of resource is realized in pond, but its data transmission efficiency is low, and with big data service, internet finance, traditional row
The birth of the emerging services such as industry internet form, data volume are in explosive growth, and traditional data center has been unable to meet demand.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide the implementation method of virtual data center a kind of, system and deposit
Storage media improves data transmission efficiency.
A kind of implementation method of virtual data center, which comprises
Network element device is based on leaf ridge network architecture building physical network and constructs overlay net on the physical network
Network, the network element device include gateway, core switch, frame topcross, and the gateway is exchanged with each core
Machine is there are physical link, and there are physical links with each core switch for the frame topcross；
Cloud platform configures network, issues network configuration information to controller；
The controller is based on network configuration information generation flow table and the network element device is instructed to pass through the overlay
Network carries out data forwarding, realizes the communication between fictitious host computer and the communication of fictitious host computer and outer net.
A kind of virtual data center system, the system comprises:
Network element device, for constructing based on leaf ridge network architecture building physical network and on the physical network
Overlay network, the network element device include gateway, core switch, frame topcross, the gateway with it is each
Core switch is there are physical link, and there are physical links with each core switch for the frame topcross；
Cloud platform issues network configuration information to controller for configuring to network；
Controller, it is described for instructing the network element device to pass through based on network configuration information generation flow table
Overlay network carries out data forwarding, realizes the communication between fictitious host computer and the communication of fictitious host computer and outer net.
A kind of computer readable storage medium, is stored thereon with computer program, realization when which is executed by processor
Following steps:
Network element device is based on leaf ridge network architecture building physical network and constructs overlay net on the physical network
Network, the network element device include gateway, core switch, frame topcross, and the gateway is exchanged with each core
Machine is there are physical link, and there are physical links with each core switch for the frame topcross；
Cloud platform configures network, issues network configuration information to controller；
The controller is based on network configuration information generation flow table and the network element device is instructed to pass through the overlay
Network carries out data forwarding, realizes the communication between fictitious host computer and the communication of fictitious host computer and outer net.
Implementation method, system and the storage medium of above-mentioned virtual data center build leaf ridge network by network element device
The physical network of framework simultaneously constructs overlay network on the physical network, wherein the network element device includes that gateway is set
There are physical link, the frame is crossed for standby, core switch, frame topcross and the gateway and each core switch
It changes planes and there are physical links for each core switch；Then network is configured by cloud platform, issues network configuration letter
It ceases to controller；Issuing flow table finally by the controller instructs the network element device to carry out by the overlay network
Data forwarding, to realize the communication between fictitious host computer and the communication of fictitious host computer and outer net.Gateway of the invention
And frame top formula interchanger and all core switch have physical link, so any two rack top formula interchanger either frame
Between top formula interchanger and gateway another rack top formula interchanger or net can be connected to via any one core switch
Equipment is closed, and the hop count of each of the links only has double bounce, route metric value is all identical, and core switch all in this way can mention
For the link of an end-to-end load sharing, to improve data transmission efficiency and link redundancy.
Detailed description of the invention
Fig. 1 is the implementation method flow chart of virtual data center in one embodiment；
Fig. 2 is that physical network builds flow chart in one embodiment；
Fig. 3 is virtual data center network topology structure figure in one embodiment；
Fig. 4 is the flow chart that cloud platform fictitious host computer accesses network in one embodiment；
Fig. 5 is overlay network topological diagram in one embodiment；
Fig. 6 is overlay network data flow direction figure in one embodiment；
Fig. 7 is underlay network data flow direction figure in one embodiment；
Fig. 8 is the flow chart of cloud platform fictitious host computer migration in one embodiment.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
In one embodiment, as shown in Figure 1, providing a kind of implementation method of virtual data center, the method packet
It includes:
Step S110, network element device are based on leaf ridge network architecture building physical network and construct on the physical network
Overlay network, wherein network element device includes gateway (GW), core switch, frame topcross (ToR), gateway
With each core switch there are physical link, there are physical links with each core switch for frame topcross.
Specifically, the leaf ridge network architecture (spine-leaf) by upper layer ridge interchanger and lower layer leaf group of switches at,
Wherein, ridge interchanger serves as the role of convergence switch, and leaf interchanger serves as the role of access switch.In the leaf ridge network architecture
In, it is only jumped every one between each leaf interchanger and another leaf interchanger.
In the present embodiment, network element device includes gateway, multiple cores interchanger and multiple frame topcross, institute
Multiple frame topcross are stated as the leaf interchanger of multiple cores interchanger, the multiple core switch functions simultaneously as gateway and sets
Standby leaf interchanger.
Further, after the physical network of virtual data center being built according to the leaf ridge network architecture, SDN is disposed
((Software Defined Network, SDN) controller node (hereinafter referred to as controller) simultaneously guarantees in the physical network
Telephone net node and controller three layers of IP (Internet Protocol, Internet Protocol) it is reachable, by controller by physics
Part of nodes on network is configured to virtual network node, constructs overlay network.
Step S120, cloud platform configure network, issue network configuration information to controller.
Specifically, cloud platform network configure mainly include to virtual flow-line, network, subnet, port, secure group into
Row such as create, deletes, modifying, checking at the relevant operations, realizes ponds of infrastructure resources such as calculating, storage, network and on-demand
Scheduling.
In one embodiment, cloud platform is configured to Openstack cloud platform.Wherein, Openstack is by NASA (beauty
National Aeronautics and Space Administration of state) and Rackspace cooperation research and development cloud computing management software, be the item of a complete open source code
Mesh and free software.OpenStack provides the solution about IaaS (infrastructure services), and being one can manage
The cloud operating system in vast resources pond in entire data center, including calculating, storage and Internet resources.Administrator can pass through pipe
It manages platform and manages whole system, and can be that user delimit resource by Web (WWW) interface.
Step S130, controller be based on network configuration information generate flow table instruct network element device by overlay network into
Row data forwarding realizes the communication between fictitious host computer and the communication of fictitious host computer and outer net.
Specifically, the northbound interface of controller receives the network configuration information of cloud platform, and is converted to flow table and passes through
Openflow agreement is issued to network element device, and network element device inquires flow table matching flow entry with regard to the forwarding of achievable data packet.Stream
List item is mainly made of matching field, priority, counter, instruction, time-out time, Cookie and mark.Matching field is used for
The matching of data packet, if it does, then needing to be implemented the instruction for including in flow entry；Precedence field is indicated in flow table conflict
When, execute sequence, matching field and the precedence field of flow entry jointly define a unique flow entry；Counter is used to
The master data of statistical data stream.
In one embodiment, overlay network is based on VXLAN (Virtual Extensible LAN) tunneling technique structure
It builds.
Specifically, the configuration of VXLAN attribute is carried out at the interface UI of controller, includes VXLAN device name, device type
(VXLAN L2 gateway or VXLAN L3 gateway), management IP, endpoint of a tunnel IP.It can pass through in the good information of UI interface configurations
NETCONF agreement is issued on corresponding interchanger, and can be ordered by " show " of interchanger and be checked that the tunnel VXLAN is established
Situation.
In one embodiment, as shown in Fig. 2, network element device wraps the step of being based on leaf ridge network architecture building physical network
It includes:
Step S210, frame topcross stack two-by-two, and double network interfaces of physical server do multilink bundling, are separately connected two
The frame topcross of stacking.
Multilink bundling is done in step S220, the port of core switch two-by-two, connects two frame topcross of stacking one by one.
Step S230, gateway stack two-by-two, and multilink bundling is done in the port of core switch two-by-two, are separately connected stacking
Two gateways.
Specifically, it stacks and refers to that the network element device by one or more combines co-operation, so as in a limited space
It is interior that port as much as possible is provided, improve gateway performance.
In the present embodiment, multilink bundling be based on LACP agreement (Link Aggregation Control Protocol,
Link aggregate control protocol).
In the present embodiment, physical server includes calculating virtualized server and two kinds of bare metal server.
Further, after physical circuit connects, in frame topcross, core switch, gateway these three equipment
Upper starting three-layer routing agreement such as enables OSPF (Open Shortest Path First, ospf) association
View notices link-state information and route table items each other.
In one embodiment, virtual data center network topology structure figure is as shown in Figure 3, wherein virtual machine server
Core switch is linked by frame topcross with bare metal server, a pair of of gateway is disposed on core switch and is used
In north-south traffic communication and the overlay network that terminates, and by flow introduce firewall box carry out necessary security protection and
NAT (Network Address Translation, network address translation) forwarding, leads to public network or private network.
The data center network built according to the above method has high availability, the net caused by link failure and equipment fault
Network interruption, which has, resists effect well, service impact caused by reducing to greatest extent because of line fault.
After physical network is put up, tenant's virtual network can be created by cloud platform, and create the virtual master of tenant
Machine needs to configure virtual network, meets the needs to network interconnection intercommunication of tenant according to user.
In one embodiment, as shown in figure 4, by fictitious host computer access network the following steps are included:
Step S410, cloud platform create virtual network.
Specifically, after cloud platform creates network according to the request of administrator, creation subnet also may be selected, and specify subnet
IP address.Meanwhile cloud platform can also delete the information of creation, can directly delete whole network, it can also be independent
Delete host ip/DHCP Agent in subnet or subnet.
Step S420, cloud platform creates the host of fictitious host computer and specified fictitious host computer, in the virtual switch of host
Virtual port is created on machine and the fictitious host computer is articulated to the virtual port, while virtual port and virtual network being tied up
It is fixed.
Specifically, cloud platform dispatches a server in virtualized server cluster as the host of fictitious host computer
Machine creates a virtual port on the virtual switch (vSwitch) of host, and void machine host is articulated to this virtual terminal
On mouth, and with the UUID of northbound interface notification controller virtual port (Universally Unique Identifier, it is general
Unique identifier), the information such as network ID and IP address.
Further, after the network interface of fictitious host computer is online, vSwitch can send out Openflow port status asynchronous message
Notification controller, controller analytic message obtains the Switch ID of network interface, port ID station location marker information, according to this information tune
With the UUID of the OVSDB background service inquiry virtual port of vSwitch.
The UUID of virtual port is got and then the detailed of controller is sent to by northbound interface according to cloud platform
Network id latched port position in information, the hairnet network segment Id above and below the port vSwitch, bundling port and virtual
Network.
Step S430, cloud platform distribute internet protocol address (Internet Protocol to fictitious host computer by controller
Address, IP address).
Specifically, fictitious host computer sends DHCP (Dynamic Host Configuration Protocol, DynamicHost
Configuration protocol) request the Dynamic Host Configuration Protocol server IP address requesting into subnet, interchanger receives the flow entry that default is matched after message
With Openflow packet in message up sending controller, controller is according to the binding relationship and cloud platform of port and virtual network
IP address is pushed to fictitious host computer with Openflow packet out message to the IP address of controller.
The network of virtual machine access is referred to as tenant network, and tenant network is by the overlay network carrying, as shown in figure 8, virtually
Host and bare metal server are all the role of host in a network, pass through VTEP (VXLAN Tunneling connected two-by-two
End Point, VXLAN termination point of a tunnel) interchanger and gateway, two or three layers of communication and VM between fictitious host computer (VM) may be implemented
It is communicated to the north-south between outer net.
Fig. 6 is overlay network data flow direction figure, and as indicated with an arrow, what it is through gateway is north-south flow, remaining
It is East and West direction flow, by issuing flow table in VTEP interchanger, interchanger matches flow entry one by one and turns to message controller
Hair, two communication between VM1, VM2 being such as connected on the same virtual switch, so that it may be matched on affiliated VTEP point
To the Mac table of VM1 to VM2, thus two laminar flow amounts between getting through two fictitious host computers.
Fictitious host computer VM1 and bare metal server belong to two subnets, and the communication between them belongs to three layers of communication,
VRF ownership table, network segment routing table, Host routes table can be matched on the VTEP interchanger of source, are found and are gone to purpose VTEP interchanger
Exit port, the corresponding VNI of virtual network where the VNI in the VXLAN heading of message is arranged to destination host, and send
To purpose interchanger；Purpose exchange opportunity matches VRF and belongs to table, network segment routing table, Host routes table, and modifies the source of message
Mac is interchanger Mac, the address purpose Mac is the corresponding address Mac of bare metal server, and message is sent to destination host, on the contrary
?.
North-south flow is similar with three laminar flow amount of East and West direction, but VXLAN gateway VTEP point opposite end next-hop is not to pass through Fig. 4
Shown step access network, but VLAN (Virtual Local Area Network, void are created by northbound interface layout
Quasi- local area network) sub-interface access.It is illustrated with the flow of outer net to fictitious host computer VM5, is one according to cloud platform arranging service
When the virtual router of tenant creates flowexit, a void can be created on the tie point of the FW/NAT equipment of VXLAN gateway
The exclusive vlan sub-interface of quasi- router, and record the relationship of VLAN and virtual router.VXLAN gateway VTEP point is receiving pair
It after the message for holding next-hop, can be mapped in a virtual flow-line domain according to message VLAN, table, net are belonged to by matching VRF
Section routing table, Host routes table set the VNI in the VXLAN heading of message to the exit port for going to purpose VTEP interchanger
The corresponding VNI of virtual network where being set to destination host, and it is sent to purpose interchanger；Purpose exchange opportunity matching VRF returns
Belong to table, network segment routing table, Host routes table, and the source Mac for modifying message is interchanger Mac, the address purpose Mac is fictitious host computer
The corresponding address Mac VM5, is sent to destination host for message.Flow processing and above-mentioned East and West direction three of the fictitious host computer VM5 to outer net
Laminar flow amount is similar, and only the different from exit port type, is vlan sub-interface herein, so VLAN mark will be stamped by going out to message
Label, to identify virtual router attaching information.
Fig. 7 is underlay network data flow direction figure, and underlay network is bottom bearer network, can be used to find out figure
VM1 is changed to the flow of bare metal server via vSwitch interchanger, frame topcross, core switch, frame top cross in 6
Four switching equipment of machine have been forwarded on destination host.Overlay, underlay layered network architecture, every layer of equipment have point
Work, under this three layer intercommunications scene, using the VXLAN tunneling technique based on Mac in UDP, by underlay network and tenant's net
Network decoupling, frame topcross and core switch do not need the host MAC of study tenant network, expand fictitious host computer scale for
The pure underlay network equipment be it is transparent, its MAC table and fib table capacity and performance will not be caused to impact, are not related to extending
Property problem.
In one embodiment, as shown in figure 8, the above method further include:
Step S810 shines fictitious host computer copy when host detects that every monitor control index reaches warning value fastly
Purpose host.
Specifically, snapshot refers to a mirror image with read only attribute of fictitious host computer.
In the present embodiment, when host detects that the monitoring indexes such as CPU, memory reach warning value, start Autonomic Migration Framework
Process, and in the case where fictitious host computer does not stop working, former host copy shines purpose host fastly.
Step S820, purpose host extract the fictitious host computer snapshot documents of former host and purpose host and add
It is downloaded to the fictitious host computer of purpose host.
Step S830, the virtual port and virtual network that controller is mounted the fictitious host computer of purpose host are bound simultaneously
Former virtual port and virtual network is unbinding.
Specifically, after the fictitious host computer start completion of purpose host, network interface is online, and vSwitch can send out Openflow
Port status asynchronous message notification controller, controller analytic message obtain the Switch ID of network interface, the position port ID mark
Know information, the UUID of the OVSDB background service inquiry virtual port of vSwitch is called according to this information.
The UUID of virtual port is got and then the detailed of controller is sent to by northbound interface according to cloud platform
Network ID latched port position in information, the hairnet network segment ID above and below the port vSwitch, bundling port and virtual
The fictitious host computer of network, purpose host can be with normal communication.
After the fictitious host computer start completion of purpose host, the fictitious host computer port of sourcesink host is offline, and vSwitch can be sent out
Send Openflow port status asynchronous message notification controller, controller analytic message obtain network interface Switch ID,
The port and former network unbundlings are discharged the port by port ID station location marker information.
In one embodiment, the above method further include:
When frame topcross total bandwidth meets dilatation condition, an at least physical server is added, by physical server
It is connect with frame top server.
Specifically, physical server includes calculating virtualized server and bare metal server: newly-increased bare metal is taken
Business device is connected to the idle port of frame topcross with cable, and user directly can regard industry using newly-increased bare metal server
Business server；Newly-increased calculating virtualized server is connected to the idle port of frame topcross with cable, user can lead to
It crosses cloud platform and creates virtual server on this host.
In one embodiment, the above method further include:
When frame topcross total bandwidth reaches threshold value, an at least frame topcross is added, newly-increased frame is crossed
It changes planes and is connect with each core switch with physical link and start three-layer routing agreement in newly-increased frame topcross.
Specifically, the threshold value refers to that frame topcross can access the maximum value of physical server；Three-layer routing association
Ospf protocol can be used in view.
Virtualized server or bare metal service are calculated it is possible to further continue to add in newly-increased frame topcross
Device, to achieve the effect that the East and West direction flow dilatation to data center's totality.
In one embodiment, a kind of virtual data center system is also provided, which includes:
Network element device, for constructing based on leaf ridge network architecture building physical network and on the physical network
Overlay network, wherein network element device includes gateway, core switch, frame topcross, gateway and each core
Heart interchanger is there are physical link, and there are physical links with each core switch for frame topcross；
Cloud platform issues network configuration information to controller for configuring to network；
Controller instructs network element device to be counted by overlay network for generating flow table based on network configuration information
According to forwarding, the communication between fictitious host computer and the communication of fictitious host computer and outer net are realized.
In one embodiment, network element device further includes physical server；Gateway stacks two-by-two, for respectively with institute
State the connection of core switch physics aggregated links；Frame topcross stacks two-by-two, for using respectively with the core switch
The connection of physics aggregated links；Gateway, core switch, frame topcross start three-layer routing agreement；Physical server
Double network interfaces do multilink bundling, for connecting respectively with the frame topcross.
In one embodiment, overlay network is constructed based on VXLAN tunneling technique.
In one embodiment, cloud platform is also used to create the host of virtual network and fictitious host computer and specified fictitious host computer
Machine creates virtual port on the virtual switch of host and the fictitious host computer is articulated to virtual port, while will be empty
Quasi- port and virtual network are bound；Cloud platform is also used to distribute IP address internet protocol address to fictitious host computer by controller.
In one embodiment, former host is also used to when detecting that every monitor control index reaches warning value, will thereon
Fictitious host computer copy shine purpose host fastly；Purpose host is also used to extract the virtual of former host and purpose host
Host snapshot documents and the fictitious host computer for being loaded into the purpose host；Controller is also used to the purpose host
The virtual port that is mounted of fictitious host computer and virtual network carry out binding and former virtual port and virtual network is unbinding.
In one embodiment, above system further include: added when frame topcross total bandwidth meets dilatation condition
An at least physical server, the newly-increased physical server are connect with frame top server switch.
In one embodiment, the system also includes: when frame topcross total bandwidth reaches threshold value, add to
A few frame topcross, the newly-increased frame topcross are connect with physical link with each core switch and in newly-increased framves
Top cross is changed planes upper starting three-layer routing agreement.
In one embodiment, a kind of computer readable storage medium is also provided, computer program is stored thereon with, it is described
When computer program is executed by one or more processors, so that one or more processors execute following steps: network element device
Physical network is constructed based on the leaf ridge network architecture and overlay network, the network element device packet are constructed on the physical network
Gateway, core switch, frame topcross are included, there are physical link, institutes with each core switch for the gateway
Stating frame topcross, there are physical links with each core switch；Cloud platform configures network, issues network configuration letter
It ceases to controller；The controller is based on the network configuration information and generates the flow table guidance network element device described in
Overlay network carries out data forwarding, realizes the communication between fictitious host computer and the communication of fictitious host computer and outer net.
In one embodiment, network element device further includes physical server, and network element device performed by processor is based on leaf
It includes: that frame topcross stacks two-by-two that the ridge network architecture, which constructs physical network, and double network interfaces of physical server do multilink bundling, point
It Lian Jie not two frame topcross stacked；Multilink bundling is done in the port of core switch two-by-two, connects two of stacking one by one
Frame topcross；Gateway stacks two-by-two, and multilink bundling is done in the port of core switch two-by-two, is separately connected two of stacking
Gateway.
In one embodiment, the step of cloud platform performed by processor configures network includes: that the cloud is flat
Platform creates virtual network；Cloud platform creates the host of fictitious host computer and specified fictitious host computer, in the virtual switch of host
Fictitious host computer is simultaneously articulated to virtual port by upper creation virtual port, while by virtual port and network bound；Cloud platform passes through
Controller distributes IP address internet protocol address to fictitious host computer.
In one embodiment, processor is also executed the following steps: when host detects that every monitor control index reaches alert
When ring value, keeps the working condition of fictitious host computer and fictitious host computer copy is shone into purpose host fastly；Purpose host extracts
The fictitious host computer snapshot documents of former host and purpose host and the fictitious host computer for being loaded into purpose host；Controller
The virtual port and virtual network that the fictitious host computer of purpose host is mounted carry out binding and by former virtual ports and virtually
Network de binding.
In one embodiment, processor is also executed the following steps: when frame topcross total bandwidth meets dilatation condition,
An at least physical server is added, newly-increased physical server is connect with frame top server switch.
In one embodiment, processor is also executed the following steps: when frame topcross total bandwidth reaches threshold value, is increased
If an at least frame topcross, newly-increased frame topcross is connect with each core switch with physical link and newly-increased
Frame topcross on start three-layer routing agreement.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, described program can be stored in a computer-readable storage medium
In, in the embodiment of the present invention, which be can be stored in the storage medium of computer system, and by the computer system
At least one processor executes, and includes the process such as the embodiment of above-mentioned each method with realization.Wherein, the storage medium can be
Magnetic disk, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of implementation method of virtual data center, which is characterized in that the described method includes:
Network element device is based on leaf ridge network architecture building physical network and constructs overlay network, institute on the physical network
Stating network element device includes gateway, core switch, frame topcross, and the gateway and each core switch exist
Physical link, there are physical links with each core switch for the frame topcross；
Cloud platform configures network, issues network configuration information to controller；
The controller is based on network configuration information generation flow table and the network element device is instructed to pass through the overlay network
Data forwarding is carried out, realizes the communication between fictitious host computer and the communication of fictitious host computer and outer net.
2. the method according to claim 1, wherein the overlay network is based on VXLAN tunneling technique structure
It builds.
3. the method according to claim 1, wherein the network element device further includes physical server, the net
Element device be based on the leaf ridge network architecture building physical network the step of include:
The frame topcross stacks two-by-two, and double network interfaces of the physical server do multilink bundling, is separately connected two stackings
Frame topcross；
Multilink bundling is done in the port of the core switch two-by-two, connects two frame topcross of stacking one by one；
The gateway stacks two-by-two, and multilink bundling is done in the port of the core switch two-by-two, is separately connected the two of stacking
Platform gateway.
4. the method according to claim 1, wherein the cloud platform includes: the step of configuration to network
The cloud platform creates virtual network；
The cloud platform creates the host of fictitious host computer and specified fictitious host computer, creates on the virtual switch of the host
It builds virtual port and the fictitious host computer is articulated to the virtual port, while by the virtual port and the virtual network
Binding；
The cloud platform distributes internet protocol address to the fictitious host computer by the controller.
5. according to the method described in claim 4, it is characterized in that, the method also includes,
When the host detects that every monitor control index reaches warning value, fictitious host computer copy is shone into purpose host fastly
Machine；
The purpose host extracts the fictitious host computer snapshot documents of former host and purpose host and is loaded into described
The fictitious host computer of purpose host；
The virtual port and the virtual network that the controller is mounted the fictitious host computer of the purpose host are bound simultaneously
Former virtual port and the virtual network is unbinding.
6. according to the method described in claim 3, it is characterized in that, the method also includes:
When the frame topcross total bandwidth meets dilatation condition, an at least physical server is added, by newly-increased physics
Server is connect with the frame topcross.
7. according to the method described in claim 6, it is characterized in that, the method also includes:
When the frame topcross total bandwidth reaches threshold value, an at least frame topcross is added, newly-increased frame is crossed
It changes planes and is connect with each core switch with physical link and start three-layer routing agreement in the newly-increased frame topcross.
8. a kind of virtual data center system, which is characterized in that the system comprises:
Network element device, for constructing overlay net based on leaf ridge network architecture building physical network and on the physical network
Network, the network element device include gateway, core switch, frame topcross, and the gateway is exchanged with each core
Machine is there are physical link, and there are physical links with each core switch for the frame topcross；
Cloud platform issues network configuration information to controller for configuring to network；
Controller instructs the network element device to pass through the overlay net for generating flow table based on the network configuration information
Network carries out data forwarding, realizes the communication between fictitious host computer and the communication of fictitious host computer and outer net.
9. system according to claim 8, which is characterized in that the network element device further includes physical server；
The gateway stacks two-by-two, for being connect respectively with the core switch with physics aggregated links；
The frame topcross stacks two-by-two, for being connect respectively with the core switch with physics aggregated links；
The gateway, core switch, frame topcross start three-layer routing agreement；
Double network interfaces of the physical server do multilink bundling, for connecting respectively with the frame topcross.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that described program is processed
The implementation method of the virtual data center as described in any one of power 1 to 7 is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710534706.XA CN109218053A (en) | 2017-07-03 | 2017-07-03 | Implementation method, system and the storage medium of virtual data center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710534706.XA CN109218053A (en) | 2017-07-03 | 2017-07-03 | Implementation method, system and the storage medium of virtual data center |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109218053A true CN109218053A (en) | 2019-01-15 |
Family
ID=64991992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710534706.XA Pending CN109218053A (en) | 2017-07-03 | 2017-07-03 | Implementation method, system and the storage medium of virtual data center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109218053A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109995890A (en) * | 2019-03-08 | 2019-07-09 | 平安科技（深圳）有限公司 | A kind of method and server managing network address translation NAT gateway |
| CN110505095A (en) * | 2019-08-27 | 2019-11-26 | 浪潮云信息技术有限公司 | A method of large-scale virtual data center is built using a small amount of server |
| CN110519075A (en) * | 2019-07-24 | 2019-11-29 | 浪潮思科网络科技有限公司 | The communication system and method for physical host and virtual cloud host based on SDN |
| CN111277506A (en) * | 2020-01-20 | 2020-06-12 | 山东汇贸电子口岸有限公司 | Method for improving reliability of SLAAC (slow ranging Access control) distribution IPv6 address |
| CN111314196A (en) * | 2020-01-21 | 2020-06-19 | 山东汇贸电子口岸有限公司 | Data center network hybrid overlay communication method |
| CN111371591A (en) * | 2020-02-16 | 2020-07-03 | 苏州浪潮智能科技有限公司 | Configuration method and system for rapidly deploying SDN networking in double-machine virtualization |
| CN112383453A (en) * | 2021-01-15 | 2021-02-19 | 北京搜狐新媒体信息技术有限公司 | Data processing method and system |
| CN112737860A (en) * | 2021-01-06 | 2021-04-30 | 浪潮云信息技术股份公司 | Method for bare metal server VXLAN access and computer readable medium |
| CN112822085A (en) * | 2019-11-18 | 2021-05-18 | 华为技术有限公司 | Network deployment method and system |
| CN112929206A (en) * | 2021-01-22 | 2021-06-08 | 浪潮思科网络科技有限公司 | Method and device for configuring cloud physical machine in cloud network environment |
| CN112995173A (en) * | 2021-02-24 | 2021-06-18 | 紫光云技术有限公司 | Bare metal safety control method |
| CN113193981A (en) * | 2021-03-29 | 2021-07-30 | 新华三大数据技术有限公司 | Configuration issuing method and device and network system |
| CN114006707A (en) * | 2020-07-13 | 2022-02-01 | 中国电信股份有限公司 | East-west firewall configuration method, device and system |
| CN114500169A (en) * | 2021-12-27 | 2022-05-13 | 天翼云科技有限公司 | Method for establishing VXLAN tunnel, method and device for forwarding message |
| CN114978980A (en) * | 2022-04-08 | 2022-08-30 | 新奥特（北京）视频技术有限公司 | IP signal cross point scheduling device and method |
| CN115460303A (en) * | 2021-06-09 | 2022-12-09 | 中移(苏州)软件技术有限公司 | Data processing method, device, terminal and storage medium |
| WO2023016250A1 (en) * | 2021-08-09 | 2023-02-16 | 北京字节跳动网络技术有限公司 | Cloud service control system, method, and apparatus, electronic device, and storage medium |
| CN115801782A (en) * | 2023-01-29 | 2023-03-14 | 中国人民解放军61660部队 | Cross-regional data center cloud resource scheduling system and method |
| EP4207680A4 (en) * | 2020-09-27 | 2024-03-20 | Huawei Cloud Computing Technologies Co., Ltd. | Method, apparatus and system for docking bare machine to storage |
-
2017
- 2017-07-03 CN CN201710534706.XA patent/CN109218053A/en active Pending
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109995890A (en) * | 2019-03-08 | 2019-07-09 | 平安科技（深圳）有限公司 | A kind of method and server managing network address translation NAT gateway |
| WO2020181734A1 (en) * | 2019-03-08 | 2020-09-17 | 平安科技（深圳）有限公司 | Method for managing network address translation nat gateway and server |
| CN109995890B (en) * | 2019-03-08 | 2022-04-22 | 平安科技（深圳）有限公司 | Method and server for managing Network Address Translation (NAT) gateway |
| CN110519075A (en) * | 2019-07-24 | 2019-11-29 | 浪潮思科网络科技有限公司 | The communication system and method for physical host and virtual cloud host based on SDN |
| CN110519075B (en) * | 2019-07-24 | 2022-05-27 | 浪潮思科网络科技有限公司 | SDN-based communication system and method for physical host and virtual cloud host |
| CN110505095B (en) * | 2019-08-27 | 2022-04-08 | 浪潮云信息技术股份公司 | Method for building large-scale virtual data center by using small number of servers |
| CN110505095A (en) * | 2019-08-27 | 2019-11-26 | 浪潮云信息技术有限公司 | A method of large-scale virtual data center is built using a small amount of server |
| CN112822085B (en) * | 2019-11-18 | 2022-12-13 | 华为云计算技术有限公司 | Network deployment method and system |
| CN112822085A (en) * | 2019-11-18 | 2021-05-18 | 华为技术有限公司 | Network deployment method and system |
| CN111277506A (en) * | 2020-01-20 | 2020-06-12 | 山东汇贸电子口岸有限公司 | Method for improving reliability of SLAAC (slow ranging Access control) distribution IPv6 address |
| CN111314196A (en) * | 2020-01-21 | 2020-06-19 | 山东汇贸电子口岸有限公司 | Data center network hybrid overlay communication method |
| CN111371591B (en) * | 2020-02-16 | 2022-12-20 | 苏州浪潮智能科技有限公司 | Configuration method and system for rapidly deploying SDN networking in dual-machine virtualization |
| CN111371591A (en) * | 2020-02-16 | 2020-07-03 | 苏州浪潮智能科技有限公司 | Configuration method and system for rapidly deploying SDN networking in double-machine virtualization |
| CN114006707A (en) * | 2020-07-13 | 2022-02-01 | 中国电信股份有限公司 | East-west firewall configuration method, device and system |
| CN114006707B (en) * | 2020-07-13 | 2023-11-21 | 中国电信股份有限公司 | East-west firewall configuration method, device and system |
| EP4207680A4 (en) * | 2020-09-27 | 2024-03-20 | Huawei Cloud Computing Technologies Co., Ltd. | Method, apparatus and system for docking bare machine to storage |
| CN112737860B (en) * | 2021-01-06 | 2023-06-20 | 浪潮云信息技术股份公司 | Method for accessing VXLAN of bare metal server and computer readable medium |
| CN112737860A (en) * | 2021-01-06 | 2021-04-30 | 浪潮云信息技术股份公司 | Method for bare metal server VXLAN access and computer readable medium |
| CN112383453A (en) * | 2021-01-15 | 2021-02-19 | 北京搜狐新媒体信息技术有限公司 | Data processing method and system |
| CN112929206A (en) * | 2021-01-22 | 2021-06-08 | 浪潮思科网络科技有限公司 | Method and device for configuring cloud physical machine in cloud network environment |
| CN112995173A (en) * | 2021-02-24 | 2021-06-18 | 紫光云技术有限公司 | Bare metal safety control method |
| CN113193981A (en) * | 2021-03-29 | 2021-07-30 | 新华三大数据技术有限公司 | Configuration issuing method and device and network system |
| CN115460303A (en) * | 2021-06-09 | 2022-12-09 | 中移(苏州)软件技术有限公司 | Data processing method, device, terminal and storage medium |
| CN115460303B (en) * | 2021-06-09 | 2024-09-03 | 中移(苏州)软件技术有限公司 | Data processing method, device, terminal and storage medium |
| WO2023016250A1 (en) * | 2021-08-09 | 2023-02-16 | 北京字节跳动网络技术有限公司 | Cloud service control system, method, and apparatus, electronic device, and storage medium |
| CN114500169A (en) * | 2021-12-27 | 2022-05-13 | 天翼云科技有限公司 | Method for establishing VXLAN tunnel, method and device for forwarding message |
| CN114500169B (en) * | 2021-12-27 | 2024-01-02 | 天翼云科技有限公司 | Method for establishing VXLAN tunnel, method and device for forwarding message |
| CN114978980B (en) * | 2022-04-08 | 2024-01-19 | 新奥特（北京）视频技术有限公司 | IP signal cross point scheduling device and method |
| CN114978980A (en) * | 2022-04-08 | 2022-08-30 | 新奥特（北京）视频技术有限公司 | IP signal cross point scheduling device and method |
| CN115801782B (en) * | 2023-01-29 | 2023-05-16 | 中国人民解放军61660部队 | Cross-regional data center cloud resource scheduling system and method |
| CN115801782A (en) * | 2023-01-29 | 2023-03-14 | 中国人民解放军61660部队 | Cross-regional data center cloud resource scheduling system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109218053A (en) | Implementation method, system and the storage medium of virtual data center | |
| US12047244B2 (en) | Method and system of connecting to a multipath hub in a cluster | |
| CN108989212B (en) | Multiple next hop routing protocol signaling and relationships thereof | |
| CN108989213B (en) | Transmitting LSP settings using selected fabric paths between virtual nodes | |
| CN108989202B (en) | Fabric path context based forwarding for virtual nodes | |
| CN108989203B (en) | Advertising selected fabric paths for service routing in virtual nodes | |
| CN104584491B (en) | Distributed virtual route and the system and method for exchanging (DVRS) are provided | |
| Wang et al. | A survey on data center networking for cloud computing | |
| US10320664B2 (en) | Cloud overlay for operations administration and management | |
| CN102857494B (en) | Universal network interface controller | |
| CN105051688B (en) | Expanded mark networking | |
| JP6434821B2 (en) | Communication apparatus and communication method | |
| WO2017173952A1 (en) | Method, device, and system for centralizing management of virtual machines and implementing communications between virtual machines | |
| US20150043348A1 (en) | Traffic Flow Redirection between Border Routers using Routing Encapsulation | |
| WO2014136864A1 (en) | Packet rewriting apparatus, control apparatus, communication system, packet transmitting method and program | |
| CN110050445B (en) | Method, device and system for sending and receiving message | |
| US20160006642A1 (en) | Network-wide service controller | |
| CN108353024A (en) | It is reduced via the multicast state of tunnelling in routing system | |
| CN102611618B (en) | Route protection converting method and device | |
| CN107733795B (en) | Ethernet virtual private network EVPN and public network intercommunication method and device | |
| CN106331206B (en) | Domain name management method and device | |
| WO2021082575A1 (en) | Packet forwarding method, apparatus, storage medium, and system | |
| CN113542111B (en) | Message forwarding method and network equipment | |
| JPWO2014054768A1 (en) | Communication system, virtual network management apparatus, virtual network management method and program | |
| CN105391635A (en) | Network virtualization method based on software defined network (SDN) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190115 |