CN104158675A - Computing node arranging method, processing node, controller and system - Google Patents
Computing node arranging method, processing node, controller and system Download PDFInfo
- Publication number
- CN104158675A CN104158675A CN201310174927.2A CN201310174927A CN104158675A CN 104158675 A CN104158675 A CN 104158675A CN 201310174927 A CN201310174927 A CN 201310174927A CN 104158675 A CN104158675 A CN 104158675A
- Authority
- CN
- China
- Prior art keywords
- computing node
- information
- disposed
- deployment
- node
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- 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
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/508—Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement
- H04L41/5096—Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement wherein the managed service relates to distributed or central networked applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a computing node arranging method, a processing node, a controller and a system. The method comprises that arrangement suggest request information sent from the processing node is received, and an arrangement scheme is determined according to link and/or flow information; and arrangement suggest response information including the arrangement scheme is sent to the processing node so that the processing node arranges computing nodes to be arranged according to the arrangement scheme. According to the computing node arranging method, the controller can provide better arrangement scheme for the new computing nodes according to link information among data centers and flow information among the computing nodes, and a rearrangement scheme is provided for arranged computing nodes, so that the processing node can arrange the computing nodes to be arranged according to arrangement scheme; and thus, the communication quality among the computing nodes is improved, and the communication flow among the data centers is reduced.
Description
Technical field
The embodiment of the present invention relates to the communications field, relates in particular to a kind of computing node dispositions method, processing node, controller and system.
Background technology
The service deployment that appears as of virtual technology provides more mode, as a large amount of virtual machine (Virtual Machine that use in cloud computing, hereinafter to be referred as VM), as (the Content Provider of content supplier, hereinafter to be referred as CP) inner capacities that provides is larger, while needing more computational resource, can be to the more virtual machine of data center's (Data Center, hereinafter to be referred as DC) Request For Disposition; When the traffic carrying capacity of CP declines, can reduce the quantity of virtual machine.
In prior art, when disposing virtual machine, by the surplus resources of server in judgement DC, as internal memory, CPU (Central Processing Unit, hereinafter to be referred as CPU) whether meet computation requirement, need to be at this server deploy virtual machine thereby determine whether.For example, if receive deploying virtual machine request, be that CPU number is two, inside save as 1024M, disk read-write number of times is 50 times, from resource pool, selects a server, the surplus resources of the server that judgement is chosen: whether the number of CPU is at least two, whether internal memory is at least 1024M, and whether disk read-write number of times is at least 50 times, if wherein one undesirable, this server of mark does not meet the requirement of this selection, again in resource pool, selects new server.
Yet, above-mentioned virtual machine deployment method when needs are disposed a plurality of virtual machine, is selected a server at every turn from resource pool, whether the surplus resources that judges this server satisfies the demands and then disposes virtual machine, and each virtual machine may be deployed on the server of different data centers.If there is a large amount of network service between virtual machine, the virtual machine that participates in communication is positioned at different data centers, can cause network traffics increase, data congestion between data center, and communication quality is poor.
Summary of the invention
The embodiment of the present invention provides a kind of computing node dispositions method, processing node, controller and system, controller is treated deployment computing node according to link information, flow information etc. and is provided rational deployment scheme, thereby make processing node according to deployment scheme, to this computing node to be disposed, to dispose the communication flows reducing between data center, improve communication quality.
First aspect, the embodiment of the present invention provides a kind of computing node dispositions method, comprising:
The deployment recommendation request message that reception & disposal node sends, described deployment recommendation request message carries the descriptor of computing node to be disposed;
According to link information and/or flow information, determine deployment scheme, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages; Described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed;
To described processing node, send the deployment recommendation response message that comprises described deployment scheme.
In the possible implementation of the first aspect first, the deployment request information of computing node to be disposed described in also carrying in described deployment recommendation request message;
Describedly according to link information and/or flow information, determine deployment scheme, comprising:
According to described link information and/or flow information, determine the deployment scheme that meets described deployment request information.
In conjunction with the possible implementation of the first of first aspect, in the possible implementation of the second aspect first, described deployment request information comprises:
Relative position information between computing node described to be disposed, described in computing node to be disposed with dispose relative position information between computing node, described in communication quality between computing node to be disposed require information, described in computing node to be disposed with dispose communication quality between computing node require information, described in computing node to be disposed a kind of information or its combination of across data center, communicating by letter in total flow requirement information.
The first or the possible implementation of the second in conjunction with first aspect, first aspect, in the third the possible implementation aspect first, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
The first, the second or the third possible implementation in conjunction with first aspect, first aspect, in the 4th kind of possible implementation aspect first, the deployment recommendation request message that described reception & disposal node sends, described deployment recommendation request message carries the descriptor of computing node to be disposed, and comprising:
By agency, receive the deployment recommendation request message that described processing node sends;
The described deployment recommendation response message that comprises described deployment scheme to described processing node transmission, so that described processing node is according to computing node to be disposed described in described deployment scheme deployment, comprising:
By described agency, to described processing node, send the deployment recommendation response message that comprises described deployment scheme, so that described processing node is according to computing node to be disposed described in described deployment scheme deployment.
In conjunction with the arbitrary middle implementation in four kinds of possible implementations of the first to the of first aspect, first aspect, in the 5th kind of possible implementation aspect first, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
Second aspect, the embodiment of the present invention provides a kind of computing node dispositions method, comprising:
The deployment information request message that reception & disposal node sends, described deployment information request message carries the descriptor of computing node to be disposed;
Obtain link information and/or flow information, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages, described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node that described in, computing node to be disposed is relevant is to have the computing node of communication requirement with computing node to be disposed;
To described processing node, send the deployment information response message that comprises described link information and/or flow information.
In the possible implementation of the first aspect second, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
The possible implementation of the first in conjunction with second aspect or second aspect, in the possible implementation of the second aspect the secondth, the deployment information request message that described reception & disposal node sends, described deployment information request message carries the descriptor of computing node to be disposed, and comprising:
By agency, receive the deployment information request message that described processing node sends, described deployment information request message carries the descriptor of computing node to be disposed;
The described deployment information response message that comprises described link information and/or flow information that sends to described processing node, so that described processing node is determined deployment scheme according to described link information and/or flow information, comprising:
By described agency, to described processing node, send the deployment information response message that comprises described link information and/or flow information, so that described processing node is determined deployment scheme according to described link information and/or flow information.
In conjunction with the first or the possible implementation of the second of second aspect, second aspect, in the third the possible implementation aspect second, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
The 3rd aspect, the embodiment of the present invention provides a kind of computing node dispositions method, comprising:
To controller, send and dispose suggestion requests message, described deployment recommendation request message carries the descriptor of computing node to be disposed, so that described controller is according to link information and/or flow information, determine deployment scheme, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages; Described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed;
Receive the deployment recommendation response message that comprises described deployment scheme that described controller sends.
In the possible implementation of the first aspect the 3rd, the deployment request information of computing node to be disposed described in also carrying in the described deployment recommendation request message sending to described controller, so that described controller, according to described link information and/or flow information, is determined the deployment scheme that meets described deployment request information.
The possible implementation of the first in conjunction with the 3rd aspect, in the possible implementation of the second aspect the 3rd, described deployment request information comprises: described in relative position information between computing node to be disposed, computing node described to be disposed and disposed the relative position information between computing node, communication quality between computing node described to be disposed requires information, computing node described to be disposed and the communication quality of having disposed between computing node require information, computing node described to be disposed is across a kind of information or its combination in data center's communication total flow requirement information.
The first or the possible implementation of the second in conjunction with the 3rd aspect, the 3rd aspect, in the third possible implementation aspect the 3rd, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
The first, the second or the third possible implementation in conjunction with the 3rd aspect, the 3rd aspect, in the 4th kind of possible implementation aspect the 3rd, described to controller transmission deployment suggestion requests message, comprising: by agency, to controller, send and dispose suggestion requests message;
The deployment recommendation response message that comprises described deployment scheme that the described controller of described reception sends, comprising: by described agency, receive the deployment recommendation response message that comprises described deployment scheme that described controller sends.
In conjunction with the first the 3rd aspect, the 3rd aspect, the second or the third possible implementation, in the 4th kind of possible implementation aspect the 3rd, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
The 4th aspect, the embodiment of the present invention provides a kind of computing node dispositions method, comprising:
To controller, send and dispose information request message, described deployment information request message carries the descriptor of computing node to be disposed, so that described controller obtains link information and/or flow information, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages, described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed,
Receive the deployment information response message that comprises described link information and/or flow information that described controller sends;
According to described link information and/or flow information, determine deployment scheme.
In the possible implementation of the first aspect the 4th, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
The possible implementation of the first in conjunction with the 4th aspect or the 4th aspect, in the possible implementation of the second aspect the 4th, described to controller transmission deployment information request message, comprising: by agency, to controller, send and dispose information request message;
The response message that comprises described link information and/or flow information that the described controller of described reception sends, comprises; By described agency, receive the deployment information response message that comprises described link information and/or flow information that described controller sends.
In conjunction with the first or the possible implementation of the second of the 4th aspect, the 4th aspect, in the third the possible implementation aspect the 4th, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
The 5th aspect, the embodiment of the present invention provides a kind of controller, comprising:
Receiver module, the deployment recommendation request message sending for reception & disposal node, described deployment recommendation request message carries the descriptor of computing node to be disposed;
Determination module, be used for according to link information and/or flow information, determine deployment scheme, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages; Described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed;
Sending module, for sending the deployment recommendation response message that comprises described deployment scheme to described processing node.
In the possible implementation of the first aspect the 5th, the deployment request information of computing node to be disposed described in also carrying in the deployment recommendation request message that described receiver module receives;
Described determination module also, for according to described link information and/or flow information, is determined the deployment scheme that meets described deployment request information.
In conjunction with the possible implementation of the first of the 5th aspect, in the possible implementation of the second aspect the 5th, described deployment request information comprises:
Relative position information between computing node described to be disposed, described in computing node to be disposed with dispose relative position information between computing node, described in communication quality between computing node to be disposed require information, described in computing node to be disposed with dispose communication quality between computing node require information, described in computing node to be disposed a kind of information or its combination of across data center, communicating by letter in total flow requirement information.
The first or the possible implementation of the second in conjunction with the 5th aspect, the 5th aspect, in the third possible implementation aspect the 5th, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
The first, the second or the third possible implementation in conjunction with the 5th aspect, the 5th aspect, in the 4th kind of possible implementation aspect the 5th, the deployment recommendation request message that described receiver module also sends for receive described processing node by agency;
Described sending module is also for sending the deployment recommendation response message that comprises described deployment scheme to described processing node by described agency.
In conjunction with the first of the 5th aspect, the 5th aspect, the second, the third or the 4th possible implementation, in the 5th kind of possible implementation aspect the 5th, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
The 6th aspect, the embodiment of the present invention provides a kind of controller, comprising:
Receiver module, the deployment information request message sending for reception & disposal node, described deployment information request message carries the descriptor of computing node to be disposed;
Acquisition module, be used for obtaining link information and/or flow information, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages, described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node that computing node described to be disposed is relevant is to have the computing node of communication requirement with computing node to be disposed,
Sending module, for sending the deployment information response message that comprises described link information and/or flow information to described processing node.
In the possible implementation of the first aspect the 6th, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
The possible implementation of the first in conjunction with the 6th aspect or the 6th aspect, in the possible implementation of the second aspect the 6th, the deployment information request message that described receiver module also sends for receive described processing node by agency, described deployment information request message carries the descriptor of computing node to be disposed;
Described sending module is also for send the deployment information response message that comprises described link information and/or flow information to described processing node by described agency, so that described processing node is determined deployment scheme according to described link information and/or flow information.
In conjunction with the first or the possible implementation of the second of the 6th aspect, the 6th aspect, in the third the possible implementation aspect the 6th, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
The 7th aspect, the embodiment of the present invention provides a kind of processing node, comprising:
Sending module, for sending and dispose suggestion requests message to controller, described deployment recommendation request message carries the descriptor of computing node to be disposed, so that described controller is according to link information and/or flow information, determine deployment scheme, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages; Described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed;
Receiver module, the deployment recommendation response message that comprises described deployment scheme sending for receiving described controller.
In the possible implementation of the first aspect the 7th, described sending module also for to described controller, send carry described in the described deployment recommendation request message of deployment request information of computing node to be disposed, so that described controller, according to link information and/or flow information, is determined the deployment scheme that meets described deployment request information.
In conjunction with the possible implementation of the first of the 7th aspect, in the possible implementation of the second aspect the 7th, described deployment request information comprises:
Relative position information between computing node described to be disposed, described in computing node to be disposed with dispose relative position information between computing node, described in communication quality between computing node to be disposed require information, described in computing node to be disposed with dispose communication quality between computing node require information, described in computing node to be disposed a kind of information or its combination of across data center, communicating by letter in total flow requirement information.
The first or the possible implementation of the second in conjunction with the 7th aspect, the 7th aspect, in the third possible implementation aspect the 7th, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
In conjunction with the first, the second or the third possible implementation of the 7th aspect, the 7th aspect, in the 4th kind of possible implementation aspect the 7th, described sending module is also for being sent and dispose suggestion requests message to controller by agency;
The deployment recommendation response message that comprises described deployment scheme that described receiver module also sends for receive described controller by described agency.
In conjunction with the first of the 7th aspect, the 7th aspect, the second, the third or the 4th kind of possible implementation, in the 5th kind of possible implementation aspect the 7th, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
The 8th aspect, a kind of processing node of the embodiment of the present invention, comprising:
Sending module, for sending and dispose information request message to controller, described deployment information request message carries the descriptor of computing node to be disposed, so that described controller obtains link information and/or flow information, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages, described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed,
Receiver module, the deployment information response message that comprises described link information and/or flow information sending for receiving described controller;
Determination module, for determining deployment scheme according to described link information and/or flow information.
In the possible implementation of the first aspect the 8th, described descriptor comprise computing node to be disposed node identification information, described in computing node to be disposed quantity information, described in tenant's identification information under computing node to be disposed, or, described in characteristic information under computing node to be disposed.
In conjunction with the possible implementation of the first of the 8th aspect or the 8th aspect, in the possible implementation of the second aspect the 8th, described sending module is also for being sent and dispose information request message to controller by agency;
The deployment information response message that comprises described link information and/or flow information that described receiver module also sends for receive described controller by described agency.
In conjunction with the first or the possible implementation of the second of the 8th aspect, the 8th aspect, in the third the possible implementation aspect the 8th, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
The 9th aspect, the embodiment of the present invention provides a kind of operation system, comprises controller described in as above the 5th aspect and the as above processing node described in the 7th aspect.
The tenth aspect, the embodiment of the present invention provides a kind of operation system, comprises controller described in as above the 6th aspect and the as above processing node described in the 8th aspect.
The computing node management method that the embodiment of the present invention provides, processing node, controller and system, link information between each data center that the data center that controller can be disposed according to the link information in operation system and between computing node to be disposed each data center that can dispose or computing node to be disposed and computing node to be disposed can not be disposed, flow information between each computing node relevant to computing node to be disposed etc., for new computing node, can determine the preferably deployment scheme of deployed position, processing node can be disposed new computing node according to deployment scheme, for the computing node of having disposed in operation system, can provide the deployment scheme that redeploys position, make processing node to this, to have disposed computing node according to deployment scheme and carry out position adjustment, change the communication flows between data center into flow in data center, thereby improve the communication quality between computing node, the communication flows between reduction data center.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skills, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is the first service system structure schematic diagram that computing node dispositions method of the present invention is suitable for;
Fig. 2 is the flow chart of computing node dispositions method embodiment mono-of the present invention;
Fig. 3 is the flow chart of computing node dispositions method embodiment bis-of the present invention;
Fig. 4 is the flow chart of computing node dispositions method embodiment tri-of the present invention;
Fig. 5 is the flow chart of computing node dispositions method embodiment tetra-of the present invention;
Fig. 6 is the second service system structure schematic diagram that computing node dispositions method of the present invention is suitable for;
Fig. 7 is the structural representation of controller embodiment mono-of the present invention;
Fig. 8 is the structural representation of controller embodiment bis-of the present invention;
Fig. 9 is the structural representation of processing node embodiment mono-of the present invention;
Figure 10 is the structural representation of processing node embodiment bis-of the present invention;
Figure 11 is the structural representation of controller embodiment tri-of the present invention;
Figure 12 is the structural representation of controller embodiment tetra-of the present invention;
Figure 13 is the structural representation of processing node embodiment tri-of the present invention;
Figure 14 is the structural representation of processing node embodiment tetra-of the present invention.
Embodiment
For making object, technical scheme and the advantage of the embodiment of the present invention clearer, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, rather than whole embodiment.Embodiment based in the present invention, those of ordinary skills, not making the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.
Fig. 1 is the first service system structure schematic diagram that computing node dispositions method of the present invention is suitable for.Please refer to Fig. 1, in the present embodiment, processing node management data center DC_A, DC_B, DC_C, as shown in solid black lines in figure, the DC_D of data center does not belong to processing node management, and between the DC_A of data center, DC_B, DC_C, there is communication, between the DC_B of data center and DC_D, exist and communicate by letter, in each data center, can dispose or dispose computing node (not shown).Wherein, computing node refers to various functional modules computing capability, that can carry out data processing that have, as virtual machine (Virtual Machine, hereinafter to be referred as VM), calculate container (Linux Container, hereinafter to be referred as LXC) and physical server etc. by software or hard-wired functional module, wherein, calculate container for example on operating system level for process provides virtual execution environment, the CPU with special ratios distributes time, input and output (Input Output, hereinafter to be referred as IO), limit the container of operable memory size etc.
Processing node can be realized by hardware or software, and for example, it can comprise hard-wired computing node administrative center or the third party application that can realize for software, tenant etc., and the present invention is not as restriction.When processing node is specially computing node administrative center, be also responsible for the management of each computing node in operation system, as shown in phantom in FIG., it can carry out unified management to the computing node of each data center, or administrative section computing node according to demand.In addition, also processing node can be divided into sub-administrative center targetedly, such as being divided into Virtual Machine Manager subcenter, Container Management subcenter etc., Virtual Machine Manager subcenter is responsible for the management of virtual machine, as the establishment of virtual machine, startup, delete, freeze and migration etc.; Container Management subcenter is responsible for calculating the management of container, as calculate container establishment, startup, delete, freeze and migration etc.Concrete, processing node completes the management of computing node alternately by the server of He Ge data center.
As shown in chain-dotted line in Fig. 1, controller and processing node can be based on HTML (Hypertext Markup Language) (Hyper Text Transport Protocol, hereinafter to be referred as HTTP) or transmission control protocol (Transmission Control Protocol, hereinafter to be referred as TCP) communicates; Or, also can communicate based on User Datagram Protoco (UDP) (User Datagram Protocol, hereinafter to be referred as UDP).Controller by with being connected of processing node, the deployment recommendation request message that reception & disposal node sends, the deployment scheme of determining computing node to be disposed according to link information and/or flow information, is carried at deployment scheme in deployment recommendation response message and sends to processing node; Or, controller by with being connected of processing node, the deployment information request message that reception & disposal node sends, obtain link information and/or flow information, and the link information getting and/or flow information are carried in deployment information response message and send to processing node, make processing node determine the deployment scheme of computing node to be disposed.Wherein, link information comprises: the link information between each data center that processing node is managed, and/or, each data center that processing node is managed and do not belong to the link information between each data center that this processing node manages; Flow information is the flow information between the computing node that computing node to be disposed is relevant to computing node to be disposed, and wherein, the computing node relevant to computing node to be disposed is to have the computing node of communication requirement with computing node to be disposed.Please refer to Fig. 1, the data center that processing node is managed is DC_A, DC_B, DC_C, and controller is determined deployment scheme according to the link information between DC_A, DC_B, DC_C; Or can also determine deployment scheme according to the link information between DC_A, DC_B, DC_C and DC_D.In addition, except considering the link information between data center, thereby it is also conceivable that the definite deployment scheme of flow information between computing node to be disposed.For example, for newly-increased computing node, can determine preferably deployed position according to link information, flow information or deployment request information etc.; For having disposed computing node in operation system, according to the flow information between computing node, link information between data center or deployment request information etc., provide the suggestion of the position redeploying, or, provide flow list or the traffic matrix of the flow information of disposing computing node.
Wherein, link information refers to the link-state information between operation system Zhong Ge data center, comprises total bandwidth, idle bandwidth, time delay, shake, packet loss of link etc.In general, the link between data center is two-way, and two-way state may be different.In addition, link information is not unalterable, but along with the time changes, can link information be carried out real-time, Event triggered or periodically be gathered by controller or other application, the link information collecting is stored in and in database, forms link information database.The link information table that carries out link information collection between the table 1 Wei Duitu1Zhong DC_A of data center, DC_B, DC_C and draw.With the first behavior example, the information such as total bandwidth when L_AB represents DC_A to DC_B transmission data, remaining bandwidth, time delay, shake, packet loss, as shown in Table 1, L_AB and L_BA are different.
Table 1
| Link identification | Total bandwidth | Remaining bandwidth | Time delay | Shake | Packet loss |
| L_AB | 10G | 5G | 50ms | 20ms | 20ppm |
| L_AC | 10G | 3G | 50ms | 10ms | 10ppm |
| L_BA | 10G | 2G | 50ms | 40ms | 10ppm |
| L_BC | 1G | 200M | 50ms | 20ms | 200ppm |
| L_CA | 1G | 200M | 50ms | 10ms | 50ppm |
| L_CB | 1G | 200M | 50ms | 40ms | 10ppm |
The flow information of computing node refers to the flow status information of communicating by letter between computing node, comprises sometime the information such as total communication flows, average bandwidth, burst time span, burst bandwidth of section.In general, flow information between computing node is not unalterable, but change along with the variation of time, can flow information be carried out real-time, Event triggered or periodically be gathered by controller or other application, the flow information collecting is stored in and in database, forms flow information database.Take computing node as virtual machine instance, please refer to Fig. 1, two virtual machine VM_1 and VM_2 in the DC_A of tentation data center, have been disposed, two virtual machine VM_3 and VM_4 in DC_B, have been disposed, there is communication in VM_1, VM_2, VM_3, VM_4, section to VM_1, VM_2, VM_3, VM_4 between carry out flow information collection can obtain the flow status information of each computing node between communicating by letter sometime each other.Table 2 is the flow information table between VM_1, VM_2, VM_3, VM_4.Wherein, take T12 as example, T12 can represent the information such as total communication flows between VM_1 and VM_2, average bandwidth, burst time span, burst bandwidth.
Table 2
It should be noted that, in Fig. 1, be with processing node and controller be independently deployed as example the present invention will be described in detail.Yet the present invention is not as restriction, in actual application scenarios, that by software or hardware mode, realizes also can be deployed in processing node and controller on the same server in operation system, or, be deployed in respectively on different servers.
Fig. 2 is the flow chart of computing node dispositions method embodiment mono-of the present invention.The present embodiment does not meet applicable to having disposed computing node in operation system the scene that business demand needs are disposed new computing node, or in operation system, disposed the scene that computing node needs adjustment and deployment position, the present embodiment be take controller and the embodiment of the present invention is described in detail as executive agent.Concrete, the present embodiment comprises the following steps:
101, the deployment recommendation request message that reception & disposal node sends, deployment recommendation request message carries the descriptor of computing node to be disposed.
The service operation initial stage, (the Content Provider of content supplier, hereinafter to be referred as CP) quantity of the computing node that needs is few, but, the development of reckoning along with business, the quantity of the computing node that CP needs is also more and more accordingly, the new computing node of some data center's deploy that need to be in operation system; Or, owing to processing a plurality of computing nodes same business, that disposed, be deployed in different data centers, according to demand, the computing node that need to dispose those carries out position adjustment.Now, processing node sends and disposes suggestion requests message to controller, and controller receives this descriptor of carrying computing node to be disposed.
Wherein, descriptor comprises the identification information of computing node to be disposed, the sign of the tenant under the quantity of computing node to be disposed, computing node to be disposed etc., wherein, tenant's sign is for example tenant's title or the identification number (IDentity corresponding with title, hereinafter to be referred as ID), as Tengxun, Baidu, 3456123,7890123(3456123, the 7890123rd, the Digital ID of Tengxun and Baidu correspondence under controller) etc., use tenant to identify as when disposing the descriptor of computing node, represent all computing nodes under this tenant, the sign of one or more computing nodes, as { VM_a} represents a virtual machine a, and { VM_c} represents one group of virtual machine a, b, c for VM_a, VM_b, in addition, also a certain class can be able to be identified to the characteristic information of computing node to be disposed as the identification information of computing node to be disposed, as Internet protocol (Internet Protocol, hereinafter to be referred as IP) address information, network segment address information or medium access control (media access control, below detect MAC) address information, IP address range information etc., wherein, 192.168.3.X/24 represent under subnet sign 192.168.3.X, Internet protocol (Internet Protocol, hereinafter to be referred as IP) front 24 all computing nodes that are 192.168.1 in address.
102, according to link information and/or flow information, determine deployment scheme, wherein, link information comprises the link information between each data center that processing node manages, and/or, each data center that processing node is managed and do not belong to the link information between each data center that processing node manages; Flow information is the flow information between the computing node that computing node to be disposed is relevant to computing node to be disposed.Wherein, the computing node that computing node to be disposed is relevant is to have the computing node of communication requirement with computing node to be disposed.
After receiving the deployment recommendation request message of processing node transmission, link information between each data center that controller is managed according to processing node, each data center that processing node is managed and do not belong at least one information in the flow information between link information between each data center that processing node manages, the computing node relevant with computing node to be disposed, determine the deployment scheme of computing node to be disposed.For example, for new computing node, can determine preferably deployed position; For the computing node of having disposed in operation system, according to the flow information between computing node, link information etc., provide the suggestion that redeploys position.
Further, can also carry the deployment request information of computing node to be disposed in deployment recommendation request message, controller, according to link information and/or flow information, is determined the deployment scheme that meets deployment request information.Concrete, if do not dispose any computing node in each data center in operation system, now can only consider the link information between each data center that processing node administers, according to link information, determine the deployment scheme that meets deployment request information.Deployment request information can be treat dispose between computing node or computing node to be disposed with dispose that deployment relative position, communication quality between computing node requires or computing node to be disposed across the communicate by letter constraints of total flow requirement of data center.
103, to processing node, send the deployment recommendation response message that comprises deployment scheme.
When controller is to send to processing node the deployment recommendation response message that comprises deployment scheme after disposing computing node to determine deployment scheme, make processing node dispose computing node to be disposed according to deployment scheme.For example, processing node can, according to deployment recommendation response message, be deployed in by computing node to be disposed the data center that link remaining bandwidth is large, time delay is little, packet loss is low; Or, by two, exist the computing node of a large amount of network services to be deployed in same data center.Deployment scheme can be that controller is determined according at least one information in the information such as the flow information between link information or computing node to be disposed and relative computing node, deployment request information; Or processing node also can not adopted deployment recommendation request message.
The computing node dispositions method that the embodiment of the present invention provides, each data center that link information between each data center that controller is managed according to processing node in operation system or processing node are managed to do not belong to flow information between link information between each data center that processing node manages, each computing node relevant with computing node to be disposed etc., for new computing node, can determine the preferably suggestion of deployed position; For the computing node of having disposed in operation system, can provide the suggestion that redeploys position, by the computing node that has a large amount of network services is deployed in same data center, change the communication flows between data center into flow in data center, thereby improve the communication quality between computing node, the communication flows between reduction data center.
Fig. 3 is the flow chart of computing node dispositions method embodiment bis-of the present invention.The present embodiment be take controller and the embodiment of the present invention is described in detail as executive agent.Concrete, the present embodiment comprises the following steps:
201, the deployment information request message that reception & disposal node sends, deployment information request message carries the descriptor of computing node to be disposed.
202, obtain link information and/or flow information, wherein, link information comprises the link information between each data center that processing node manages, and/or, each data center that processing node is managed and do not belong to the link information between each data center that processing node manages, flow information is the flow information between the computing node that computing node to be disposed is relevant to computing node to be disposed, wherein, the computing node relevant to computing node to be disposed is to have the computing node of communication requirement with computing node to be disposed.
Controller receives the deployment information request message that processing node sends, obtain the link information between each data center that processing node manages, and/or, each data center that pending node is managed and do not belong to the link information between each data center that processing node manages, flow information is the flow information between the computing node that computing node to be disposed is relevant to computing node to be disposed, for example, can provide flow list or the traffic matrix of this computing node that need to carry out position adjustment of having disposed.Controller can, after receiving the deployment information request message of processing node transmission, obtain relevant link information or flow information immediately; Or, obtain flow information of computing node to be disposed etc. also can only carry flow request message in deployment recommendation request message after, for satisfying the demands, can design the concrete form of concrete deployment information request message, the present invention is not as restriction.
203, to processing node, send the deployment information response message that comprises link information and/or flow information.
The difference part of the present embodiment and above-described embodiment one is, in the present embodiment, controller does not send to processing node after determining deployment scheme in embodiment mono-step 102 again, but the response message of the link information getting and/or flow information is directly sent to processing node, by processing node voluntarily according to those information determining portion management side cases.Concrete, processing node can be determined deployment scheme according at least one information in link information, flow information or the deployment request of determining according to demand information.
The computing node dispositions method that the embodiment of the present invention provides, controller obtains link information, flow informations between each computing node relevant to computing node to be disposed etc. also send to processing node, make processing node for the computing node of having disposed in operation system, can provide the suggestion that redeploys position, by the computing node that has a large amount of network services is deployed in same data center, change the communication flows between data center into flow in data center, thereby the communication quality between raising computing node, reduce the communication flows between data center.
Fig. 4 is the flow chart of computing node dispositions method embodiment tri-of the present invention.The present embodiment does not meet applicable to the computing node of having disposed in operation system the scene that business demand needs are disposed new computing node, or the computing node of having disposed in operation system needs the scene of adjustment and deployment position, the present embodiment be take processing node and the embodiment of the present invention is described in detail as executive agent.Concrete, the present embodiment comprises the following steps:
301, to controller, send and dispose suggestion requests message, deployment recommendation request message carries the descriptor of computing node to be disposed, so that controller is according to link information, and/or flow information, determine deployment scheme, wherein, link information comprises the link information between each data center that processing node manages, and/or, each data center that processing node is managed and do not belong to the link information between each data center that processing node manages; Flow information is the flow information between the computing node that computing node to be disposed is relevant to computing node to be disposed, and wherein, the computing node relevant to computing node to be disposed is to have the computing node of communication requirement with computing node to be disposed.
Can embodiment shown in Figure 2 about the description of link information and flow information in the present embodiment, do not repeat them here.
302, receive the deployment recommendation response message that comprises deployment scheme that controller sends.
When controller receives the deployment recommendation request message of processing node transmission and determines after deployment scheme, to processing node, send the deployment recommendation response message that comprises deployment scheme, processing node receives this deployment recommendation response message.
After receiving the deployment recommendation response message of controller transmission, the deployment scheme that processing node can this deployment recommendation response message of selective basis comprises, by the server of the data center with administered, complete alternately the deployment of computing node to be disposed, the deletion of for example, the establishment of new computing node, startup, the computing node disposed, freeze and migration etc.; Or processing node also can not adopted the deployment scheme that deployment recommendation response message returns.
The computing node dispositions method that the embodiment of the present invention provides, for new computing node, the suggestion of the better deployed position that processing node provides according to controller, carry out the establishment of computing node etc., for the computing node of having disposed in operation system, the suggestion that redeploys position providing according to controller, carry out position adjustment, for example, freeze certain or some computing nodes of having disposed, data center at other re-creates these computing nodes, thereby the computing node that has a large amount of network services is deployed in same data center, change the communication flows between data center into flow in data center, or the reasonable a plurality of data centers of link-quality, thereby the communication quality between raising computing node, reduce the communication flows between data center.
Fig. 5 is the flow chart of computing node dispositions method embodiment tetra-of the present invention.The present embodiment be take processing node and the embodiment of the present invention is described in detail as executive agent.Concrete, the present embodiment comprises the following steps:
401, to controller, send and dispose information request message, deployment information request message carries the descriptor of computing node to be disposed, so that controller obtains link information and/or flow information, wherein, link information comprises the link information between each data center that processing node manages, and/or, each data center that processing node is managed and do not belong to the link information between each data center that processing node manages, flow information is the flow information between the computing node that computing node to be disposed is relevant to computing node to be disposed, wherein, the computing node relevant to computing node to be disposed is to have the computing node of communication requirement with computing node to be disposed.
Can embodiment shown in Figure 2 about the description of link information and flow information in the present embodiment, do not repeat them here.
402, receive the deployment information response message that comprises link information and/or flow information that controller sends.
Controller can, after receiving the deployment information request message of processing node transmission, obtain relevant link information or flow information immediately; Or, obtain flow information of computing node to be disposed etc. also can only carry flow request message in deployment recommendation request message after, for satisfying the demands, can design the concrete form of concrete deployment information request message, the present invention is not as restriction.Processing node receives the deployment information response message that comprises link information and/or flow information that controller sends.
403, according to link information and/or flow information, determine deployment scheme.
Processing node is determined deployment scheme according to link information and/or flow information voluntarily.Concrete, processing node can be determined deployment scheme according at least one information in link information, flow information or the deployment request of determining according to demand information.
The computing node dispositions method that the embodiment of the present invention provides, processing node is according to the link information between each data center relevant to the data center at computing node to be disposed place in operation system, flow information between each computing node relevant to computing node to be disposed etc., for the computing node of having disposed in operation system, determine the suggestion that redeploys position, carry out position adjustment, for example, freeze certain or some computing nodes of having disposed, data center at other re-creates these computing nodes, thereby the computing node that has a large amount of network services is deployed in same data center, change the communication flows between data center into flow in data center, or the reasonable a plurality of data centers of link-quality, thereby the communication quality between raising computing node, reduce the communication flows between data center.
The angle that above-described embodiment one, embodiment bis-, embodiment tri-and embodiment tetra-are executive agent from controller and processing node is respectively set forth the present invention, wherein, in embodiment mono-and embodiment tri-, by controller, determined the deployment scheme of computing node to be disposed, in embodiment bis-and embodiment tetra-, processing node receive according to controller, obtain and send to after disposing the link information and flow information that computing node is relevant, by processing node, determined the deployment scheme of computing node to be disposed.Below, by different embodiment, the present invention will be described in detail.
Fig. 6 is the second service system structure schematic diagram that computing node dispositions method of the present invention is suitable for.Please refer to Fig. 6, in the present embodiment, with in operation system, processing node management 3 DC_A of data center, DC_B, DC_C be example the present invention will be described in detail, on the server of each data center, can dispose or dispose computing node (not shown).In addition, not shown processing node and controller.
In computing node dispositions method embodiment five of the present invention, the descriptor that the deployment recommendation request message that processing node sends to controller carries computing node to be disposed, for example, in this describing message, indication need to create two new computing nodes.The the first link information table that carries out link information collection between the table 3 Wei Tu6Zhong DC_A of data center, DC_B, DC_C and draw.
Table 3
| Link identification | Total bandwidth | Remaining bandwidth | Time delay | Shake | Packet loss |
| L_AB | 10G | 5G | 50ms | 20ms | 20ppm |
| L_AC | 10G | 5G | 50ms | 10ms | 10ppm |
| L_BC | 10G | 2G | 50ms | 40ms | 10ppm |
| L_BA | 10G | 5G | 50ms | 20ms | 20ppm |
| L_CA | 10G | 5G | 50ms | 10ms | 50ppm |
| L_CB | 10G | 200M | 50ms | 40ms | 10ppm |
The indication that controller receives processing node transmission need to create after the deployment recommendation request message of two new computing nodes, link information based on storing in link information database now, it is for example the link information table shown in table 3, travel through this table, determine the data center of the outbound remaining bandwidth of each data center and the summation maximum of inbound link remaining bandwidth, the data center that this is determined is as the data center that disposes new computing node.Concrete, please refer to table 3, the outbound remaining bandwidth of DC_A is that 10G(L_AB is 5G, L_AC is 5G), inbound link remaining bandwidth is that 10G(L_BA is 5G, L_CA is 5G), total surplus bandwidth is 20G; The outbound remaining bandwidth of DC_B is that 7G(L_BA is 5G, and L_BC is 2G), inbound link remaining bandwidth is that 5.2G(L_AB is 5G, L_CB is 200M), total surplus bandwidth is 12.2G; The outbound remaining bandwidth of DC_C is that 5.2G(L_CA is 5G, and L_CB is 200M), inbound link remaining bandwidth is that 7G(L_AC is 5G, L_BC is 2G, total surplus bandwidth is 7G).Can obtain thus, the total surplus bandwidth of DC_A is maximum, and total surplus band is roomy, in general, more can meet computing node across the communicating requirement of data center, improves communication quality.Therefore, this 2 computing nodes are disposed in controller suggestion in DC_A, determine the deployment scheme that can dispose these 2 computing nodes at DC_A.
In computing node dispositions method embodiment six of the present invention, the deployment recommendation request message that processing node sends to controller is except carrying the descriptor of computing node to be disposed, also carry the deployment request information of computing node to be disposed to limit the relative position information between computing node to be disposed, for example, in this describing message, indication need to create two new computing nodes, and deployment request information indicates these two new computing nodes in different data centers.The the second link information table that carries out link information collection between the table 4 Wei Tu4Zhong DC_A of data center, DC_B, DC_C and draw.
Table 4
| Link identification | Total bandwidth | Remaining bandwidth | Time delay | Shake | Packet loss |
| L_AB | 10G | 5G | 50ms | 20ms | 20ppm |
| L_AC | 10G | 5G | 50ms | 10ms | 10ppm |
| L_BC | 10G | 2G | 50ms | 40ms | 10ppm |
| L_BA | 10G | 5G | 50ms | 20ms | 20ppm |
| L_CA | 1G | 200M | 50ms | 10ms | 50ppm |
| L_CB | 1G | 200M | 50ms | 40ms | 10ppm |
Controller receive indication that processing node sends need to create two new computing nodes and this two computing nodes need to the deployment recommendation request message in different data centers after, link information based on storing in link information database now, it is for example the link information table shown in table 4, controller travels through this table, determine the Liang Ge data center of the link remaining bandwidth maximum between data center, Jiang Gailiangge data center is as the data center that disposes new computing node.Concrete, please refer to table 4, the link remaining bandwidth between DC_A and DC_B is that 10G(L_AB is 5G, L_BA is 5G); Link remaining bandwidth between DC_A and DC_C is that 5.2G(L_AC is 5G, and L_CA is 200M); Link remaining bandwidth between DC_B and DC_C is that 2.2G(L_BC is 2G, and L_CB is 200M).Can obtain thus, the link remaining bandwidth between DC_A and DC_B is maximum.Therefore, a computing node is respectively disposed in controller suggestion in DC_A and DC_B, determines the deployment scheme of respectively disposing a computing node in DC_A and DC_B.Now, because the deployed position of each computing node has two, therefore, can determine according to demand the preferential deployment data center of some computing nodes, suggestion is disposed this computing node in the higher deployment data center of the priority level of determining, and remaining computing node is deployed in other data centers; Or, if without priority requirement, advise two random being deployed in DC_A and DC_B of computing node.
Based on above-described embodiment six, optionally, deployment request information can also require to indicate to the communication quality between new computing node, for example, in deployment recommendation request message, carry descriptor and the deployment request information of computing node to be disposed, in describing message, indication need to create two new computing nodes, and deployment request information indicates these two new computing nodes in different data centers, and the shake of communicating by letter between these two new computing nodes is less than 30ms and is greater than 15ms.The 3rd link information table that carries out link information collection between the table 5 Wei Tu6Zhong DC_A of data center, DC_B, DC_C and draw.
Table 5
| Link identification | Total bandwidth | Remaining bandwidth | Time delay | Shake | Packet loss |
| L_AB | 10G | 5G | 50ms | 20ms | 20ppm |
| L_AC | 10G | 3G | 50ms | 10ms | 10ppm |
| L_BC | 10G | 2G | 50ms | 40ms | 10ppm |
| L_BA | 10G | 5G | 50ms | 20ms | 20ppm |
| L_CA | 1G | 200M | 50ms | 10ms | 50ppm |
| L_CB | 1G | 200M | 50ms | 40ms | 10ppm |
Controller receives indication that processing node sends and need to create two new computing nodes, these two computing nodes and need to the shake in communicating by letter between different data centers and this two new computing nodes be less than after the deployment recommendation request message that 30ms is greater than 15ms, link information based on storing in link information database now, it is for example the link information table shown in table 5, controller travels through this table, determine the Liang Ge data center that the shake of communicating by letter between data center satisfies the demands, Jiang Gailiangge data center is as the data center that disposes new computing node.Concrete, please refer to table 5, that between DC_A and DC_B, communicates by letter is dithered as 20ms; That between DC_A and DC_C, communicates by letter is dithered as 10ms; That between DC_B and DC_C, communicates by letter is dithered as 40ms.Can obtain thus, only have the shake of communicating by letter between DC_A and DC_B to meet the condition in deployment request information.Therefore, a computing node is respectively disposed in controller suggestion in DC_A and DC_B, determines the deployment scheme of respectively disposing a computing node in DC_A and DC_B.
Based on above-described embodiment six, optional, deployment request information can also between new computing node, new computing node and the communication quality of having disposed between computing node require to indicate.For example, in deployment recommendation request message, carry descriptor and the deployment request information of computing node to be disposed, in describing message, indication need to create two new computing node VM1 and VM2, deployment request information indication VM1 from VM2 in different data centers, VM1 from dispose computing node VMX and be deployed in different data centers and VM1 and dispose the shake of communicating by letter between computing node VMX and be less than 15ms.Please refer to Fig. 4, VMX is deployed in DC_A in advance.The 4th link information table that carries out link information collection between the table 6 Wei Tu6Zhong DC_A of data center, DC_B, DC_C and draw.
Table 6
| Link identification | Total bandwidth | Remaining bandwidth | Time delay | Shake | Packet loss |
| L_AB | 10G | 5G | 50ms | 20ms | 20ppm |
| L_AC | 10G | 3G | 50ms | 10ms | 20ppm |
| L_BC | 10G | 2G | 50ms | 40ms | 10ppm |
| L_BA | 10G | 5G | 50ms | 20ms | 20ppm |
| L_CA | 1G | 200M | 50ms | 10ms | 50ppm |
| L_CB | 1G | 200M | 50ms | 40ms | 10ppm |
The indication that controller receives processing node transmission need to create two new computing node VM1 and VM2, deployment request information indication VM1 from VM2 in different data centers, VM1 from dispose computing node VMX and be deployed in different data centers and VM1 and dispose the shake of communicating by letter between computing node VMX and be less than after the deployment recommendation request message of 15ms, link information based on storing in link information database now, it is for example the link information table shown in table 6, controller travels through this table, determine the Liang Ge data center that the shake of communicating by letter between data center satisfies the demands, Jiang Gailiangge data center is as the data center that disposes new computing node.Concrete, please refer to table 6, that between DC_A and DC_B, communicates by letter is dithered as 20ms; That between DC_A and DC_C, communicates by letter is dithered as 10ms; That between DC_B and DC_C, communicates by letter is dithered as 40ms.Can obtain thus, only have the shake of communicating by letter between DC_A and DC_B to meet the condition in deployment request information, VMX is deployed in DC_A in advance.Therefore, computing node VM1 is disposed in controller suggestion in DC_C, disposes computing node VM2 in DC_A or DC_B, determines and in DC_C, disposes computing node VM1, the deployment scheme of disposing computing node VM2 in DC_A or DC_B.
Based on above-described embodiment six, optionally, computing node to be disposed is to dispose computing node in operation system, as belong at least one computing node of a certain subnet, the descriptor that the deployment recommendation request message that processing node sends to controller carries computing node to be disposed, descriptor, except comprising the quantity of computing node to be disposed, can also comprise subnet sign; Deployment request information can also be for indicating the computing node of this subnet minimum across the communication flows of data center.For example, computing node is virtual machine, and subnet is designated 192.168.10.X/24, has 4 computing node: VM_1, VM_2, VM_3 and VM_4(not shown) belong to this subnet, current deployed position be the first two in DC_C, latter two is in DC_A.Table 7A communicates the first communication stream scale that flow collection draws between VM_1, VM_2, VM_3 and VM_4 in Fig. 6.For the purpose of simple declaration, here be only the communication flows of having listed between each computing node, with MB, calculate, in other feasible execution modes, this communication stream scale also can comprise the information such as average bandwidth between each computing node, burst time span, burst bandwidth.
Table 7A
It is minimum across the communication total flow of data center that controller receives each virtual machine that indication subnet that processing node sends is designated under 192.168.10.X/24, and each data center disposes after the deployment recommendation request message of 2 virtual machines, controller is divided the deployed position of each virtual machine under this subnet, the requirement of dividing is that these 4 virtual machines are divided into the DC_C of data center and the DC_A that belongs to subnet 192.168.10.X/24, each data center divides two virtual machines, possible division result is as shown in table 7B, table 7B is division result signal table in table 7A.
Table 7B
The behavior example that it is 1 that the table of take is divided sequence number in 7B, this line display controller is divided into VM_1 and VM_2 in DC_C, now VM_1 and VM_2 are positioned at same data center, the communication flows of VM_1 to the communication flows of VM_2 and VM_2 to VM_1 is equivalent to the inner stream flow in DC_C, therefore can be not counted between data center, be the communication flows between DC_C and DC_A, as shown in upper left corner dash area in table 7A; In like manner, VM_3 and VM_4 are divided in DC_A, now VM_3 and VM_4 are arranged in same data, VM_3 is equivalent to the inner stream flow of DC_A to communication flows and the VM_4 of VM_4 to the communication flows of VM_3, therefore can be not counted between data center, be the communication flows between DC_C and DC_A, as shown in lower right corner dash area in table 7A.Therefore, divide sequence number dispose VM_1, VM_2, VM_3 and VM_4 as the division methods shown in 1 if take, according to table 7A, do not consider the flow of the data center inside of the upper left corner and lower right corner part, the communication flows summation between DC_A and DC_C is 240MB.
In like manner, can show that dividing other modes that sequence number is 2～6 divides lower DC_A and the communication flows summation between DC_C, concrete, as shown as shown in 7B.
Controller traversal list 7B, finds that the communication flows summation between DC_A and DC_C is minimum, is 160MB when VM_2 and VM_3 are as shown in division sequence number 3 or division sequence number 6 in same data center time; Find that the communication flows summation between DC_A and DC_C is 240MB, larger when VM_2 and VM_3 are in different data center time.Therefore, controller suggestion re-starts deployment to VM_1, VM_2, VM_3 and VM_4, and VM_2 and VM_3 are deployed in DC_A, VM_1 and VM_4 are deployed in DC_C, or, VM_2 and VM_3 are deployed in DC_C, VM_1 and VM_4 are deployed in DC_A.
Based on above-described embodiment six, optionally, computing node to be disposed is in operation system, to have disposed computing node, as belong at least one computing node of a certain tenant, the descriptor that the deployment recommendation request message that processing node sends to controller carries computing node to be disposed, descriptor, except comprising the quantity of computing node to be disposed, can also comprise that tenant identifies; Deployment request information can also for the computing node of indicating this subnet, across the communication flows of data center, minimum and each data center disposes 2 computing nodes.For example, computing node is virtual machine, tenant is designated CP_1234, have 6 computing node: VM_1, VM_2, VM_3, VM_4, VM_5 and VM_6(not shown) belong to this tenant, current deployed position is that VM_1, VM_2 are in DC_C, VM_3, VM_4 are in DC_A, and VM_5 and VM_6 are in DC_B.Table 8A communicates the second communication flowmeter that flow collection draws between VM_1, VM_2, VM_3, VM_4, VM_5 and VM_6 in Fig. 6.For the purpose of simple declaration, here be only the communication flows of having listed between each computing node, with MB, calculate, in other feasible execution modes, this communication stream scale also can comprise the information such as average bandwidth between each computing node, burst time span, burst bandwidth.
Table 8A
Controller receives indication tenant that processing node sends and is designated each virtual machine under CP_1234 minimum and each data center disposes after the deployment recommendation request message of 2 virtual machines across the communication flows of data center, controller is divided the deployed position of each virtual machine under this tenant, the requirement of dividing is that these 6 virtual machines are divided in the DC_C of data center, the DC_A and DC_B that belongs to tenant CP_1234, each data center divides two virtual machines, possible division result is as shown in table 8B, and table 8B is division result signal table in table 8A.
Table 8B
The behavior example that it is 3 that the table of take is divided sequence number in 8B, this line display controller is divided into VM_1 and VM_4 in DC_C, now VM_1 and VM_4 are positioned at same data center, the communication flows of VM_1 to the communication flows of VM_4 and VM_4 to VM_1 is equivalent to the inner stream flow in DC_C, therefore can be not counted in the communication flows between the A of data center; In like manner, VM_2 and VM_3 are divided in data DC_A, and now the communication flows of VM_2 and VM_3 and VM_3 are equivalent to the inner stream flow in DC_A to the communication flows of VM_2, therefore, can be not counted in the communication flows between data center; In like manner, VM_5 and VM_6 are divided in data DC_B, now the communication flows of VM_5 and VM_6 and VM_6 are equivalent to the inner stream flow in DC_B to the communication flows of VM_5, therefore, can be not counted in the communication flows between data center, concrete, under this kind of dividing mode, be not counted in the part of communication flows between data center as shown in dash area in table 8A.Therefore, divide need to dispose VM_1, VM_2, VM_3, VM_4, VM_5 and VM_6 as the division methods shown in 3 if take,, according to table 8A, do not consider to show dash area shown in 8A, the communication flows summation between DC_A, DC_B and DC_C is 480MB.
In like manner, can draw the communication flows summation between each data center under the division methods shown in other division sequence numbers, concrete, as shown in table 8B.It should be noted that, under different computing node numbers and different divisions require, dividing mode is also different, does not enumerate herein.In actual scene, can select according to demand computing node number and dividing mode.
Controller traversal list 8B, find when VM_1 and VM_4 in same data center, VM_2 and VM_3 in same data center, VM_5 and VM_6 during in same data center, the communication flows summation between each data center is 480MB, smaller.Therefore, controller suggestion re-starts deployment to VM_1, VM_2, VM_3, VM_4, VM_5 and VM_6, VM_1 and VM_4 are deployed in same data center, VM_2 and VM_3 are deployed in to same data center, VM_5 and VM_6 are deployed in to same data center.Concrete, as dash area in table 8B, divide the division methods shown in sequence number 3 or 10.
In computing node dispositions method embodiment seven of the present invention, for having disposed computing node in operation system, the deployment recommendation request message that processing node sends to controller is except carrying the descriptor of computing node to be disposed, also carry the flow solicited message of computing node to be disposed, the flow status of disposing computing node is known in request.For example, with computing node, be specially virtual machine instance, please refer to Fig. 6, in operation system, have 9 virtual machines, VM_1, VM_2, VM_3 are deployed in DC_A, and VM_4, VM_5, VM_6 are deployed in DC_B, VM_7, VM_8, VM_9 are deployed in DC_C, not shown concrete virtual machine.Table 9A communicates the third communication flowmeter that flow collection draws between VM_1, VM_2, VM_3, VM_4, VM_5, VM_6, VM_7, VM_8, VM_9 in Fig. 4.For the purpose of simple declaration, here be only the communication flows of having listed between each computing node, with MB, calculate, in other feasible execution modes, this communication stream scale also can comprise the information such as average bandwidth between each computing node, burst time span, burst bandwidth.
Table 9A
If what controller received that deployment recommendation request message carries is the flow request message of VM1, traversal list 9A, extraction is for there being other virtual machines of communication between VM1, then corresponding flow is extracted, the communication flows information extracting is shown as shown 9B, shows 9B for VM being communicated in table 9A the result signal table of flow information extraction.
Table 9B
With the example of classifying as at VM_2 place, while representing that VM_1 and VM_2 communicate, VM_1 is to the communication flows of VM_2, and outflow is 100MB; VM_2 is to the communication flows of VM_1, and inbound traffics are 90MB.Controller is extracting the communication flows information of VM1, processing node this communication flows information sent to processing node, so that can be determined the deployment scheme of VM_1, VM_2, VM_3, VM_4, VM_5, VM_6, VM_7, VM_8, VM_9 voluntarily according to this flow information.Concrete, controller can be carried at the content shown in the sign of VM1 and table 9B in deployment recommendation response message and send to processing node, also after can calculating the communication flows summation of each communication object, send to again processing node, for example, take communication object as VM_2 be example, outflow is 100MB, if flow is 90MB, communication flows summation is 190MB, and the deployment recommendation response message that controller sends to computing node management is to carry the sign of VM_1 and the communication flows summation of VM_1 and VM_2 is 190MB.In actual scene, controller can select VM1 and all communication flows information of communication object or flow information of part communication object to send to processing node.
In above-mentioned each embodiment, be all processing node and controller point-to-point communication, processing node directly sends and disposes suggestion requests message to controller, and receives the deployment recommendation response message that controller sends; The deployment recommendation request message that the direct reception & disposal node of controller sends, directly sends deployment recommendation response message to processing node after determining deployment scheme.Yet in actual scene, processing node also can indirectly be communicated by letter with controller.For example, in computing node deployment way embodiment eight of the present invention, the deployment recommendation request message that controller can send by acting on behalf of reception & disposal node, determines after deployment scheme and to processing node, sends deployment recommendation response message by agency; In like manner, processing node also can be sent and dispose suggestion requests message to controller by agency; By agency, receive the deployment recommendation response message that controller sends.Because agency can realize the decoupling zero between the conversion of message format and the conversion of content and processing node and controller, limitation is little, and the scope of application is more extensive.Therefore, in actual application scenarios, can select according to demand processing node and controller direct communication, or, thereby select between processing node and controller by agency's indirect communication.
In addition, in above-mentioned each embodiment, link information is the link information between each data center that link information comprises that processing node manages, yet, each data center that link information also can be managed for processing node and do not belong to the link information between each data center that processing node manages.For example, please refer to Fig. 1, if desired new computing node is deployed in to DC_B or DC_C, and new computing node to be disposed exists and communicate by letter with computing node in DC_D, need to consider the link information between DC_B and DC_C, DC_B and DC_D, DC_C and DC_D.
Fig. 7 is the structural representation of controller embodiment mono-of the present invention.The controller 100 that the present embodiment provides, can realize each step of the method that is applied to controller in any embodiment of the present invention, and specific implementation process repeats no more herein.Concrete, the controller 100 that the present embodiment provides can comprise:
Receiver module 11, the deployment recommendation request message sending for reception & disposal node, deployment recommendation request message carries the descriptor of computing node to be disposed;
Determination module 12, be used for according to link information and/or flow information, determine deployment scheme, wherein, link information comprises the link information between each data center that processing node manages, and/or, each data center that processing node is managed and do not belong to the link information between each data center that processing node manages; Flow information is the flow information between the computing node that computing node to be disposed is relevant to computing node to be disposed, and wherein, the computing node relevant to computing node to be disposed is to have the computing node of communication requirement with computing node to be disposed;
Sending module 13, for sending the deployment recommendation response message that comprises deployment scheme to processing node.
The controller that the embodiment of the present invention provides, flow information between the link information between each data center that the data center that can dispose according to the link information between each data center that can dispose to computing node to be disposed in operation system or computing node to be disposed and computing node to be disposed can not be disposed, each computing node relevant with computing node to be disposed etc., for new computing node, can determine the preferably suggestion of deployed position; For the computing node of having disposed in operation system, can provide the suggestion that redeploys position, by the computing node that has a large amount of network services is deployed in same data center, change the communication flows between data center into flow in data center, thereby improve the communication quality between computing node, the communication flows between reduction data center.
The deployment request information of also carrying computing node to be disposed in the deployment recommendation request message that further, receiver module 11 receives;
Determination module 12 also, for according to link information and/or flow information, is determined the deployment scheme that meets deployment request information.
Further, deployment request information comprises: the relative position information between computing node to be disposed, computing node to be disposed and relative position information, the communication quality between computing node to be disposed disposed between computing node require information, computing node to be disposed and dispose a kind of information or its combination that the communication quality between computing node requires information, computing node to be disposed to communicate by letter in total flow requirement information across data center.
Further, descriptor comprises the identification information of computing node to be disposed, the tenant's identification information under the quantity information of computing node to be disposed or computing node to be disposed.
Further, the receiver module 11 deployment recommendation request message for sending by acting on behalf of reception & disposal node also;
Sending module 13 is also for sending the deployment recommendation response message that comprises deployment scheme to processing node by agency.
Further, computing node to be disposed comprises newly-increased computing node or has disposed computing node.
Fig. 8 is the structural representation of controller embodiment bis-of the present invention.The controller 200 that the present embodiment provides, can realize each step of the method that is applied to controller that any embodiment of the present invention provides, and specific implementation process repeats no more herein.Concrete, the controller 200 that the present embodiment provides can comprise:
Receiver module 21, the deployment information request message sending for reception & disposal node, deployment information request message carries the descriptor of computing node to be disposed;
Acquisition module 22, be used for obtaining link information and/or flow information, wherein, link information comprises the link information between each data center that processing node manages, and/or, each data center that processing node is managed and do not belong to the link information between each data center that processing node manages, flow information is the flow information between the computing node that computing node to be disposed is relevant to computing node to be disposed, wherein, the computing node that computing node to be disposed is relevant is to have the computing node of communication requirement with computing node to be disposed;
Sending module 23, for sending the deployment information response message that comprises link information and/or flow information to processing node.
The controller that the embodiment of the present invention provides, by obtaining flow information between link information, each computing node relevant to computing node to be disposed etc. and sending to processing node, make processing node for the computing node of having disposed in operation system, can provide the suggestion that redeploys position, by the computing node that has a large amount of network services is deployed in same data center, change the communication flows between data center into flow in data center, thereby improve the communication quality between computing node, the communication flows between reduction data center.
Further, descriptor comprises the identification information of computing node to be disposed, the tenant's identification information under the quantity information of computing node to be disposed or computing node to be disposed.。
Further, receiver module 21 is the deployment information request message for sending by acting on behalf of reception & disposal node also, and deployment information request message carries the descriptor of computing node to be disposed;
Sending module 23 is also for send the deployment information response message that comprises link information and/or flow information to processing node by agency, so that processing node is determined deployment scheme according to link information and/or flow information.
Further, computing node to be disposed comprises newly-increased computing node or has disposed computing node.
Fig. 9 is the structural representation of processing node embodiment mono-of the present invention.The processing node 300 that the present embodiment provides, can realize each step of the method that is applied to processing node that any embodiment of the present invention provides, and specific implementation process repeats no more herein.Concrete, the processing node 300 that the present embodiment provides can comprise:
Sending module 31, for sending and dispose suggestion requests message to controller, deployment recommendation request message carries the descriptor of computing node to be disposed, so that controller is according to link information and/or flow information, determine deployment scheme, wherein, link information comprises the link information between each data center that processing node manages, and/or, each data center that processing node is managed and do not belong to the link information between each data center that processing node manages; Flow information is the flow information between the computing node that computing node to be disposed is relevant to computing node to be disposed, and wherein, the computing node relevant to computing node to be disposed is to have the computing node of communication requirement with computing node to be disposed;
Receiver module 32, the deployment recommendation response message that comprises deployment scheme sending for receiving controller.
The processing node that the embodiment of the present invention provides, for new computing node, the suggestion of the better deployed position that processing node provides according to controller, carry out the establishment of computing node etc., for the computing node of having disposed in operation system, the suggestion that redeploys position providing according to controller, carry out position adjustment, for example, freeze certain or some computing nodes of having disposed, data center at other re-creates these computing nodes, thereby the computing node that has a large amount of network services is deployed in same data center, change the communication flows between data center into flow in data center, or the reasonable a plurality of data centers of link-quality, thereby the communication quality between raising computing node, reduce the communication flows between data center.
Further, sending module 31 is also for send the deployment recommendation request message of the deployment request information of carrying computing node to be disposed to controller, so that controller, according to link information and/or flow information, is determined the deployment scheme that meets deployment request information.
Further, deployment request information comprises: the relative position information between computing node to be disposed, computing node to be disposed and relative position information, the communication quality between computing node to be disposed disposed between computing node require information, computing node to be disposed and dispose a kind of information or its combination that the communication quality between computing node requires information, computing node to be disposed to communicate by letter in total flow requirement information across data center.
Further, descriptor comprises the identification information of computing node to be disposed, the tenant's identification information under the quantity information of computing node to be disposed or computing node to be disposed.。
Further, sending module 31 is also for being sent and dispose suggestion requests message to controller by agency;
The deployment recommendation response message that comprises deployment scheme that receiver module 32 also sends for receive controller by agency.
Further, computing node to be disposed comprises newly-increased computing node or has disposed computing node.
Figure 10 is the structural representation of processing node embodiment bis-of the present invention.The processing node 400 that the present embodiment provides, can realize each step of the method that is applied to processing node that any embodiment of the present invention provides, and specific implementation process repeats no more herein.Concrete, the processing node 400 that the present embodiment provides can comprise:
Sending module 41, for sending and dispose information request message to controller, deployment information request message carries the descriptor of computing node to be disposed, so that controller obtains link information and/or flow information, wherein, link information comprises the link information between each data center that processing node manages, and/or, each data center that processing node is managed and do not belong to the link information between each data center that processing node manages, flow information is the flow information between the computing node that computing node to be disposed is relevant to computing node to be disposed, wherein, the computing node relevant to computing node to be disposed is to have the computing node of communication requirement with computing node to be disposed,
Receiver module 42, the deployment information response message that comprises link information and/or flow information sending for receiving controller;
Determination module 43, for determining deployment scheme according to link information and/or flow information.
The processing node that the embodiment of the present invention provides, according to the link information between each data center relevant to the data center at computing node to be disposed place in operation system, flow information between each computing node relevant to computing node to be disposed etc., for the computing node of having disposed in operation system, determine the suggestion that redeploys position, carry out position adjustment, for example, freeze certain or some computing nodes of having disposed, data center at other re-creates these computing nodes, thereby the computing node that has a large amount of network services is deployed in same data center, change the communication flows between data center into flow in data center, or the reasonable a plurality of data centers of link-quality, thereby the communication quality between raising computing node, reduce the communication flows between data center.
Further, descriptor comprises the identification information of computing node to be disposed, the tenant's identification information under the quantity information of computing node to be disposed or computing node to be disposed
Further, sending module 41 is also for being sent and dispose information request message to controller by agency;
The deployment information response message that comprises link information and/or flow information that receiver module 42 also sends for receive controller by agency.
Figure 11 is the structural representation of controller embodiment tri-of the present invention.As shown in figure 11, the controller 500 that the present embodiment provides comprises processor 51 and memory 52.Controller 500 can also comprise reflector 53, receiver 54.Reflector 53 can be connected with processor 51 with receiver 54.Wherein, instruction is carried out in memory 52 storages, when controller 500 operation, between processor 51 and memory 52, communicate by letter, processor 51 calls the execution instruction in memory 52, for embodiment of the method shown in execution graph 2, it realizes principle and technique effect is similar, repeats no more herein.
Figure 12 is the structural representation of controller embodiment tetra-of the present invention.As shown in figure 12, the controller 600 that the present embodiment provides comprises processor 61 and memory 62.Controller 600 can also comprise reflector 63, receiver 64.Reflector 63 can be connected with processor 61 with receiver 64.Wherein, instruction is carried out in memory 62 storages, when controller 600 operation, between processor 61 and memory 62, communicate by letter, processor 61 calls the execution instruction in memory 62, for embodiment of the method shown in execution graph 3, it realizes principle and technique effect is similar, repeats no more herein.
Figure 13 is the structural representation of processing node embodiment tri-of the present invention.As shown in figure 13, the processing node 700 that the present embodiment provides comprises processor 71 and memory 72.Processing node 700 can also comprise reflector 73, receiver 74.Reflector 73 can be connected with processor 71 with receiver 74.Wherein, instruction is carried out in memory 72 storages, when processing node 700 operation, between processor 71 and memory 72, communicate by letter, processor 71 calls the execution instruction in memory 72, for embodiment of the method shown in execution graph 4, it realizes principle and technique effect is similar, repeats no more herein.
Figure 14 is the structural representation of processing node embodiment tetra-of the present invention.As shown in figure 14, the processing node 800 that the present embodiment provides comprises processor 81 and memory 82.Processing node 800 can also comprise reflector 83, receiver 84.Reflector 83 can be connected with processor 81 with receiver 84.Wherein, instruction is carried out in memory 82 storages, when processing node 800 operation, between processor 81 and memory 82, communicate by letter, processor 81 calls the execution instruction in memory 82, for embodiment of the method shown in execution graph 5, it realizes principle and technique effect is similar, repeats no more herein.
Embodiment based on said method and device, the present invention also provide a kind of operation system its can comprise controller and the processing node as shown in Fig. 9 or Figure 13 as shown in Fig. 7 or Figure 11; Or, can comprise controller and the processing node as shown in Figure 10 or Figure 14 as shown in Fig. 8 or Figure 12, specific works principle please refer to said method embodiment, repeats no more herein.
In the several embodiment that provide in the application, should be understood that, disclosed system, apparatus and method, can realize by another way.For example, device embodiment described above is only schematic, for example, the division of described unit, be only that a kind of logic function is divided, during actual realization, can have other dividing mode, for example a plurality of unit or assembly can in conjunction with or can be integrated into another system, or some features can ignore, or do not carry out.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, indirect coupling or the communication connection of device or unit can be electrically, machinery or other form.
The described unit as separating component explanation can or can not be also physically to separate, and the parts that show as unit can be or can not be also physical locations, can be positioned at a place, or also can be distributed in a plurality of network element.Can select according to the actual needs some or all of unit wherein to realize the object of the present embodiment scheme.
Finally it should be noted that: each embodiment, only in order to technical scheme of the present invention to be described, is not intended to limit above; Although the present invention is had been described in detail with reference to aforementioned each embodiment, those of ordinary skill in the art is to be understood that: its technical scheme that still can record aforementioned each embodiment is modified, or some or all of technical characterictic is wherein equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution depart from the scope of various embodiments of the present invention technical scheme.
Claims (42)
1. a computing node dispositions method, is characterized in that, comprising:
The deployment recommendation request message that reception & disposal node sends, described deployment recommendation request message carries the descriptor of computing node to be disposed;
According to link information and/or flow information, determine deployment scheme, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages; Described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed;
To described processing node, send the deployment recommendation response message that comprises described deployment scheme.
2. method according to claim 1, is characterized in that, the deployment request information of computing node to be disposed described in also carrying in described deployment recommendation request message;
Describedly according to link information and/or flow information, determine deployment scheme, comprising:
According to described link information and/or flow information, determine the deployment scheme that meets described deployment request information.
3. method according to claim 2, is characterized in that, described deployment request information comprises:
Relative position information between computing node described to be disposed, described in computing node to be disposed with dispose relative position information between computing node, described in communication quality between computing node to be disposed require information, described in computing node to be disposed with dispose communication quality between computing node require information, described in computing node to be disposed a kind of information or its combination of across data center, communicating by letter in total flow requirement information.
4. according to the method described in claim 1～3 any one, it is characterized in that, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
5. according to the method described in claim 1～4 any one, it is characterized in that, the deployment recommendation request message that described reception & disposal node sends, comprising:
By agency, receive the deployment recommendation request message that described processing node sends;
The described deployment recommendation response message that comprises described deployment scheme to described processing node transmission, so that described processing node is according to computing node to be disposed described in described deployment scheme deployment, comprising:
By described agency, to described processing node, send the deployment recommendation response message that comprises described deployment scheme, so that described processing node is according to computing node to be disposed described in described deployment scheme deployment.
6. according to the method described in claim 1～5 any one, it is characterized in that, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
7. a computing node dispositions method, is characterized in that, comprising:
The deployment information request message that reception & disposal node sends, described deployment information request message carries the descriptor of computing node to be disposed;
Obtain link information and/or flow information, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages, described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node that described in, computing node to be disposed is relevant is to have the computing node of communication requirement with computing node to be disposed;
To described processing node, send the deployment information response message that comprises described link information and/or flow information, so that described processing node is determined deployment scheme according to described link information and/or flow information.
8. method according to claim 7, is characterized in that, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
9. according to the method described in claim 7 or 8, it is characterized in that, the deployment information request message that described reception & disposal node sends, described deployment information request message carries the descriptor of computing node to be disposed, and comprising:
By agency, receive the deployment information request message that described processing node sends, described deployment information request message carries the descriptor of computing node to be disposed;
The described deployment information response message that comprises described link information and/or flow information that sends to described processing node, so that described processing node is determined deployment scheme according to described link information and/or flow information, comprising:
By described agency, to described processing node, send the deployment information response message that comprises described link information and/or flow information, so that described processing node is determined deployment scheme according to described link information and/or flow information.
10. according to the method described in claim 7～9 any one, it is characterized in that, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
11. 1 kinds of computing node dispositions methods, is characterized in that, comprising:
To controller, send and dispose suggestion requests message, described deployment recommendation request message carries the descriptor of computing node to be disposed, so that described controller is according to link information and/or flow information, determine deployment scheme, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages; Described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed;
Receive the deployment recommendation response message that comprises described deployment scheme that described controller sends.
12. methods according to claim 11, it is characterized in that, the deployment request information of computing node to be disposed described in also carrying in the described deployment recommendation request message sending to described controller, so that described controller, according to described link information and/or flow information, is determined the deployment scheme that meets described deployment request information.
13. methods according to claim 12, is characterized in that, described deployment request information comprises:
Relative position information between computing node described to be disposed, described in computing node to be disposed with dispose relative position information between computing node, described in communication quality between computing node to be disposed require information, described in computing node to be disposed with dispose communication quality between computing node require information, described in computing node to be disposed a kind of information or its combination of across data center, communicating by letter in total flow requirement information.
14. according to the method described in claim 11～13 any one, it is characterized in that, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
15. according to the method described in claim 11～14 any one, it is characterized in that, described to controller transmission deployment suggestion requests message, comprising:
By agency, to controller, send and dispose suggestion requests message;
The deployment recommendation response message that comprises described deployment scheme that the described controller of described reception sends, comprising:
By described agency, receive the deployment recommendation response message that comprises described deployment scheme that described controller sends.
16. according to the method described in claim 11～15 any one, it is characterized in that, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
17. 1 kinds of computing node dispositions methods, is characterized in that, comprising:
To controller, send and dispose information request message, described deployment information request message carries the descriptor of computing node to be disposed, so that described controller obtains link information and/or flow information, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages, described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed,
Receive the deployment information response message that comprises described link information and/or flow information that described controller sends;
According to described link information and/or flow information, determine deployment scheme.
18. methods according to claim 17, is characterized in that, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
19. according to the method described in claim 17 or 18, it is characterized in that, described to controller transmission deployment information request message, comprising:
By agency, to controller, send and dispose information request message;
The response message that comprises described link information and/or flow information that the described controller of described reception sends, comprises;
By described agency, receive the response message that comprises described link information and/or flow information that described controller sends.
20. according to the method described in claim 17～19 any one, it is characterized in that, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
21. 1 kinds of controllers, is characterized in that, comprising:
Receiver module, the deployment recommendation request message sending for reception & disposal node, described deployment recommendation request message carries the descriptor of computing node to be disposed;
Determination module, be used for according to link information and/or flow information, determine deployment scheme, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages; Described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed;
Sending module, for sending the deployment recommendation response message that comprises described deployment scheme to described processing node.
22. controllers according to claim 21, is characterized in that, the deployment request information of computing node to be disposed described in also carrying in the deployment recommendation request message that described receiver module receives;
Described determination module also, for according to described link information and/or flow information, is determined the deployment scheme that meets described deployment request information.
23. controllers according to claim 22, is characterized in that, described deployment request information comprises:
Relative position information between computing node described to be disposed, described in computing node to be disposed with dispose relative position information between computing node, described in communication quality between computing node to be disposed require information, described in computing node to be disposed with dispose communication quality between computing node require information, described in computing node to be disposed a kind of information or its combination of across data center, communicating by letter in total flow requirement information.
24. according to the controller described in claim 21～23 any one, it is characterized in that, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
25. according to the controller described in claim 21～24 any one, it is characterized in that the deployment recommendation request message that described receiver module also sends for receive described processing node by agency;
Described sending module is also for sending the deployment recommendation response message that comprises described deployment scheme to described processing node by described agency.
26. according to the controller described in claim 21～25 any one, it is characterized in that, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
27. 1 kinds of controllers, is characterized in that, comprising:
Receiver module, the deployment information request message sending for reception & disposal node, described deployment information request message carries the descriptor of computing node to be disposed;
Acquisition module, be used for obtaining link information and/or flow information, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages, described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node that computing node described to be disposed is relevant is to have the computing node of communication requirement with computing node to be disposed,
Sending module, for sending the deployment information response message that comprises described link information and/or flow information to described processing node.
28. controllers according to claim 27, is characterized in that, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
29. according to the controller described in claim 27 or 28, it is characterized in that, the deployment information request message that described receiver module also sends for receive described processing node by agency, described deployment information request message carries the descriptor of computing node to be disposed;
Described sending module is also for send the deployment information response message that comprises described link information and/or flow information to described processing node by described agency, so that described processing node is determined deployment scheme according to described link information and/or flow information.
30. according to the controller described in claim 27～29 any one, it is characterized in that, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
31. 1 kinds of processing nodes, is characterized in that, comprising:
Sending module, for sending and dispose suggestion requests message to controller, described deployment recommendation request message carries the descriptor of computing node to be disposed, so that described controller is according to link information and/or flow information, determine deployment scheme, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages; Described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed;
Receiver module, the deployment recommendation response message that comprises described deployment scheme sending for receiving described controller.
32. processing nodes according to claim 31, it is characterized in that, described sending module also for to described controller, send carry described in the described deployment recommendation request message of deployment request information of computing node to be disposed, so that described controller, according to link information and/or flow information, is determined the deployment scheme that meets described deployment request information.
33. processing nodes according to claim 32, is characterized in that, described deployment request information comprises:
Relative position information between computing node described to be disposed, described in computing node to be disposed with dispose relative position information between computing node, described in communication quality between computing node to be disposed require information, described in computing node to be disposed with dispose communication quality between computing node require information, described in computing node to be disposed a kind of information or its combination of across data center, communicating by letter in total flow requirement information.
34. according to the processing node described in claim 31～33 any one, it is characterized in that, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
35. according to the processing node described in claim 31～34 any one, it is characterized in that, described sending module is also for being sent and dispose suggestion requests message to controller by agency;
The deployment recommendation response message that comprises described deployment scheme that described receiver module also sends for receive described controller by described agency.
36. according to the processing node described in claim 31～35 any one, it is characterized in that, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
37. 1 kinds of processing nodes, is characterized in that, comprising:
Sending module, for sending and dispose information request message to controller, described deployment information request message carries the descriptor of computing node to be disposed, so that described controller obtains link information and/or flow information, wherein, described link information comprises the link information between each data center that described processing node manages, and/or, each data center that described processing node is managed and do not belong to the link information between each data center that described processing node manages, described flow information be described in computing node to be disposed to described in flow information between the relevant computing node of computing node to be disposed, wherein, the computing node relevant to computing node described to be disposed is to have the computing node of communication requirement with computing node described to be disposed,
Receiver module, the deployment information response message that comprises described link information and/or flow information sending for receiving described controller;
Determination module, for determining deployment scheme according to described link information and/or flow information.
38. according to the processing node described in claim 37, it is characterized in that, described descriptor comprise computing node to be disposed identification information, described in computing node to be disposed quantity information or described in tenant's identification information under computing node to be disposed.
39. according to the processing node described in claim 37 or 38, it is characterized in that, described sending module is also for being sent and dispose information request message to controller by agency;
The deployment information response message that comprises described link information and/or flow information that described receiver module also sends for receive described controller by described agency.
40. according to the processing node described in claim 37～39 any one, it is characterized in that, described in computing node to be disposed comprise newly-increased computing node or disposed computing node.
41. 1 kinds of operation systems, is characterized in that, comprise controller and the processing node as described in claim 31～36 any one as described in claim 21～26 any one.
42. 1 kinds of operation systems, is characterized in that, comprise controller and the processing node as described in claim 37～40 any one described in claim 27～30 any one.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310174927.2A CN104158675B (en) | 2013-05-13 | 2013-05-13 | Calculate node dispositions method, processing node, controller and system |
| PCT/CN2014/076828 WO2014183574A1 (en) | 2013-05-13 | 2014-05-06 | Computer node deployment method, processing node, controller, and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310174927.2A CN104158675B (en) | 2013-05-13 | 2013-05-13 | Calculate node dispositions method, processing node, controller and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104158675A true CN104158675A (en) | 2014-11-19 |
| CN104158675B CN104158675B (en) | 2018-09-11 |
Family
ID=51884088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310174927.2A Active CN104158675B (en) | 2013-05-13 | 2013-05-13 | Calculate node dispositions method, processing node, controller and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN104158675B (en) |
| WO (1) | WO2014183574A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105656662A (en) * | 2014-12-08 | 2016-06-08 | 华为技术有限公司 | Fault locating method and apparatus |
| CN105677454A (en) * | 2014-11-20 | 2016-06-15 | 华为技术有限公司 | Integration method, device and system for computational resources |
| WO2016101780A1 (en) * | 2014-12-23 | 2016-06-30 | 华为技术有限公司 | Method and device for deploying service in virtualized network |
| WO2018072653A1 (en) * | 2016-10-18 | 2018-04-26 | Huawei Technologies Co., Ltd. | Systems and methods for customizing layer-2 protocol |
| CN109889370A (en) * | 2019-01-10 | 2019-06-14 | 中国移动通信集团海南有限公司 | A kind of network equipment location determining method, device and computer readable storage medium |
| WO2019174449A1 (en) * | 2018-03-13 | 2019-09-19 | 华为技术有限公司 | Method and apparatus for deploying virtualized network elements |
| CN113344152A (en) * | 2021-04-30 | 2021-09-03 | 华中农业大学 | System and method for intelligently detecting and uploading full-chain production information of dairy products |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080155537A1 (en) * | 2006-07-24 | 2008-06-26 | Peter Dinda | Methods and systems for automatic inference and adaptation of virtualized computing environments |
| CN102082692A (en) * | 2011-01-24 | 2011-06-01 | 华为技术有限公司 | Method and equipment for migrating virtual machines based on network data flow direction, and cluster system |
| CN102112981A (en) * | 2008-07-31 | 2011-06-29 | 思科技术公司 | Distribution of virtual machines in a communication network |
| CN103023799A (en) * | 2011-09-27 | 2013-04-03 | 日电（中国）有限公司 | Central control unit and virtual machine migration method used for virtual machine migration |
-
2013
- 2013-05-13 CN CN201310174927.2A patent/CN104158675B/en active Active
-
2014
- 2014-05-06 WO PCT/CN2014/076828 patent/WO2014183574A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080155537A1 (en) * | 2006-07-24 | 2008-06-26 | Peter Dinda | Methods and systems for automatic inference and adaptation of virtualized computing environments |
| CN102112981A (en) * | 2008-07-31 | 2011-06-29 | 思科技术公司 | Distribution of virtual machines in a communication network |
| CN102082692A (en) * | 2011-01-24 | 2011-06-01 | 华为技术有限公司 | Method and equipment for migrating virtual machines based on network data flow direction, and cluster system |
| CN103023799A (en) * | 2011-09-27 | 2013-04-03 | 日电（中国）有限公司 | Central control unit and virtual machine migration method used for virtual machine migration |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105677454A (en) * | 2014-11-20 | 2016-06-15 | 华为技术有限公司 | Integration method, device and system for computational resources |
| CN105677454B (en) * | 2014-11-20 | 2019-08-27 | 华为技术有限公司 | The integration method of computing resource, device and system |
| CN105656662A (en) * | 2014-12-08 | 2016-06-08 | 华为技术有限公司 | Fault locating method and apparatus |
| CN105656662B (en) * | 2014-12-08 | 2019-02-12 | 华为技术有限公司 | A kind of Fault Locating Method and device |
| WO2016101780A1 (en) * | 2014-12-23 | 2016-06-30 | 华为技术有限公司 | Method and device for deploying service in virtualized network |
| US11038777B2 (en) | 2014-12-23 | 2021-06-15 | Huawei Technologies Co., Ltd. | Method and apparatus for deploying service in virtualized network |
| US10333851B2 (en) | 2016-10-18 | 2019-06-25 | Huawei Technologies Co., Ltd. | Systems and methods for customizing layer-2 protocol |
| WO2018072653A1 (en) * | 2016-10-18 | 2018-04-26 | Huawei Technologies Co., Ltd. | Systems and methods for customizing layer-2 protocol |
| WO2019174449A1 (en) * | 2018-03-13 | 2019-09-19 | 华为技术有限公司 | Method and apparatus for deploying virtualized network elements |
| CN110275756A (en) * | 2018-03-13 | 2019-09-24 | 华为技术有限公司 | Virtualize the dispositions method and device of network element |
| CN110275756B (en) * | 2018-03-13 | 2023-04-18 | 华为技术有限公司 | Method and device for deploying virtualized network element |
| CN109889370A (en) * | 2019-01-10 | 2019-06-14 | 中国移动通信集团海南有限公司 | A kind of network equipment location determining method, device and computer readable storage medium |
| CN113344152A (en) * | 2021-04-30 | 2021-09-03 | 华中农业大学 | System and method for intelligently detecting and uploading full-chain production information of dairy products |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104158675B (en) | 2018-09-11 |
| WO2014183574A1 (en) | 2014-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104158675A (en) | Computing node arranging method, processing node, controller and system | |
| CN109618002B (en) | Micro-service gateway optimization method, device and storage medium | |
| CN108027805B (en) | Load distribution in a data network | |
| CN103118076B (en) | Upgraded server cluster system and load balancing method thereof | |
| CN108600300B (en) | Log data processing method and device | |
| CN107707943B (en) | A kind of method and system for realizing cloud service fusion | |
| CN109873736A (en) | A kind of micro services monitoring method and system | |
| CN105979009A (en) | Method for automatically balancing increased load of cloud application container | |
| CN105893205A (en) | Method and system for monitoring containers created based on docker | |
| CN104618693A (en) | Cloud computing based online processing task management method and system for monitoring video | |
| CN107809383A (en) | A kind of map paths method and device based on MVC | |
| CN105515977B (en) | Method, device and system for acquiring transmission path in network | |
| CN111432247B (en) | Traffic scheduling method, traffic scheduling device, server and storage medium | |
| CN104618164A (en) | Management method for rapid cloud computing platform application deployment | |
| CN107105013B (en) | File processing method, server, terminal and system | |
| CN103067486B (en) | Based on the large data processing method of PaaS platform | |
| CN106657180A (en) | Information transmission method and device for cloud services, terminal equipment, and system | |
| CN106330610A (en) | Load balance processing system and method | |
| CN114039875A (en) | Data acquisition method, device and system based on eBPF technology | |
| US10225358B2 (en) | Page push method, device, server and system | |
| CN107454165A (en) | Access method and device of a kind of hadoop cluster to ceph clusters | |
| CN114153609A (en) | Resource control method and device, electronic equipment and computer readable storage medium | |
| CN106789287A (en) | Front end load balanced device, back-end server and register method | |
| CN111352726A (en) | Streaming data processing method and device based on containerized micro-service | |
| CN109831473A (en) | Logistics service providing method and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |