CN105099939A - Method and device for implementing flow control among different data centers - Google Patents
Method and device for implementing flow control among different data centers Download PDFInfo
- Publication number
- CN105099939A CN105099939A CN201410165565.5A CN201410165565A CN105099939A CN 105099939 A CN105099939 A CN 105099939A CN 201410165565 A CN201410165565 A CN 201410165565A CN 105099939 A CN105099939 A CN 105099939A
- Authority
- CN
- China
- Prior art keywords
- data center
- correlation
- flow control
- application
- business
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a method and device for implementing flow control among different data centers. The method comprises that traffic dependence of applications operated by the different data centers is determined and stored in a correlation database; and when it is detected that resource of an application operated by one data center has faults during operation, the correlation database is inquired to determine another data center which runs another application related to the application, and a flow control request is sent to the other data center to make a request for flow control for service data generated between the applications.
Description
Technical field
The present invention relates to the system and method resource (network, server and storage system) of data center being carried out to real-time performance protection in distributive data center and system for cloud computing.Be specifically related to a kind of method and apparatus that traffic controls between different pieces of information center, in different pieces of information in the heart, relevant flow can be controlled in real time, thus realize the protection of Internet resources and performance.
Background technology
In distributive data center and system for cloud computing, for providing the business with comprehensive function to user, the application of increasing internet is co-operating across multiple data center.There is business correlation more and more closely in the internet application of different pieces of information center and system for cloud computing.Such as, as shown in Figure 2, A ground data center (201) and B ground data center (202) has the business of being mutually related.Application A (203) and application D (204) are one group of related application wherein.They produce real-time correlative flow in the pipeline (205) of two places data center.Due to the correlation of business, also there is correlation in performance and mutual flow in Liang Ge data center.When the problem of operation appears in a data center, data center resource and the flow with correlation all need to be controlled.
A kind of energy management coordination technique in the heart is in the data described in US granted patent No:US8402140B2.In the art, analyze the resource performance of typical data center and virtual data center, come the position of managing virtual machines at different pieces of information center by the business correlation between comprehensive utilization virtual machine and real-time performance parameter, thus realize the optimization of energy ezpenditure.But this patent only considers the positional control problem of correlation to virtual machine, do not consider that correlation is to the flow control between data center and Properties Control problem.
Therefore, need propose a kind of provide in the heart in the data based on business correlation for the performance of data center resource and the technique of real-time control of flow.
Summary of the invention
In order to the above-mentioned defect overcoming prior art proposes the present invention.Therefore, an object of the present invention proposes a kind of method and apparatus that traffic controls between different pieces of information center, in different pieces of information in the heart, can control in real time, thus realize the protection of Internet resources and performance to relevant flow.
To achieve these goals, according to the present invention, propose a kind of method that traffic controls between different pieces of information center, comprising: determine the business correlation between multiple application of running respectively in different pieces of information in the heart, and be stored into correlation data storehouse; And when the resource monitoring the application that data center runs be in operation break down time, determine to run another data center applying relevant Another Application to described by inquiry correlation data storehouse, and control request to another data center's transmitted traffic described, ask the business datum to producing between a described application and described Another Application to carry out flow control.
Preferably, described method also comprises: the data center receiving described flow control request determines corresponding flow control policy according to the service class of described business datum.
Preferably, described method also comprises: the data center receiving described flow control request determines corresponding flow control policy according to the business correlation level between a described application and described Another Application.
Preferably, described method also comprises: according to determined flow control policy, carries out flow control to described business datum
Preferably, described business correlation determines according to the grade of the business interface existed between the two methods run respectively in the heart in different pieces of information.
Preferably, described business correlation be for the two methods run respectively in the heart in different pieces of information between business datum, obtain according to the statistical calculations model of correlation.
In addition, according to the present invention, propose a kind of equipment that traffic controls between different pieces of information center, comprising: determine the business correlation between multiple application of running respectively in different pieces of information in the heart, and be stored into the unit in correlation data storehouse; And when the resource monitoring the application that data center runs be in operation break down time, determine to run another data center applying relevant Another Application to described by inquiry correlation data storehouse, and control request to another data center's transmitted traffic described, ask the unit business datum produced between a described application and described Another Application being carried out to flow control.
By the present invention, in distributive data center and mixed cloud network, between many data centers, by utilizing correlation thus controlling resource and flow, the resource utilization of multiple data centers entirety can be promoted and effectively control resources costs ratio.
Accompanying drawing explanation
By reference to following combination accompanying drawing to adopted detailed description of the preferred embodiment, above-mentioned purpose of the present invention, advantage and feature will become more apparent, wherein:
Fig. 1 shows the structured flowchart of the system for traffic control according to the embodiment of the present invention.
Fig. 2 is the schematic diagram for illustration of application scenarios of the present invention.
Fig. 3 shows the flow chart of the method controlled according to the traffic in the data center gone wrong of the embodiment of the present invention.
Fig. 4 shows the flow chart of the method for traffic control in the heart in the correlation data which according to the embodiment of the present invention.
Fig. 5 shows the exemplary plot according to correlation data of the present invention, mapping relations between SLA (business-level) and flow control policy.
Embodiment
Below with reference to the accompanying drawings the preferred embodiments of the present invention are described.In the accompanying drawings, identical element is by by identical reference symbol or numeral.In addition, in following description of the present invention, the specific descriptions to known function and configuration will be omitted, to avoid making theme of the present invention unclear.
As shown in Figure 2, there is business correlation in data center A ground and data center B ground.If the application A on data center A ground and the application D on data center B ground is relevant.There are the service traffics across data center between application A and application D.For example, there is business correlation between the usual and multiple payment platform of current e-commerce platform and logistics platform.
Below the definition of business correlation is described.Between the application at different pieces of information center, there is one-level business interface, correlation can be defined as " height ".Such as, there is one-level interface between the usual and multiple payment platform of e-commerce platform or logistics platform.Secondary traffic interface is there is between the application at different pieces of information center, correlation can be defined as " in ".Such as, e-commerce platform is secondary traffic interface by the interface between multiple payment platform and banking system.The business interface of existence three grades or more between the application at different pieces of information center, correlation can be defined as " low ".Between the application at different pieces of information center, there is not business interface, then correlation can be defined as nothing.
In addition, also business correlation can be tried to achieve according to the statistics definition of correlation.Such as, the correlation of time-based service success rate can be comprised to determine business relevance values.Particularly, fixed time interval is divided into equally spaced sub-interval, obtains the success rate of business at every sub-interval, thus obtain the time series of service success rate.The business relevance values between two methods is calculated according to this sequence.Different statistical calculations models can be adopted.Such as, the statistical calculations model based on cosine similarity process, dot product, mutual information, Jansen Shannon divergence or Dice coefficients process can be adopted.
Another example of relevant treatment is based on the similitude of shared resource utilization rate or distribution.Such as, long-time running, in a shared resource pond (as data center traffic shares bandwidth resources), has dependence on resource uses.Resource utilization or resource-profiled can be used to obtain correlated characteristic series.On the basis of correlated characteristic series obtaining resource utilization or resource distribution, carry out the relevance values of computing service by statistic correlation model as previously mentioned.
According to the present invention, if be mutually related in two or more data center, such as in the such multiple data centers of e-commerce platform, A payment platform, B payment platform and C payment platform, there is performance (resource) operation problem in one or more data center, the traffic management that the control module shown in Fig. 2 will provide between the data center that is associated.
The data center be associated refers to: same or different application operates in different data centers.Such as, can be the application that different service is provided intracardiac in the different server of distributive data center or different pieces of information.Such as in current shopping at network business, the product information platform of electric business and third-party payment platform are mutually cooperation thus provide complete business, are the data center be associated.
As shown in Figure 1, system according to the present invention comprises: correlation data library module 101, database management module 102, flow-control module 103, correlation control module 104, event manager module 105, monitoring resource module 106 and business-level control strategy storehouse 107:
In correlation data library module 101, store correlation table as shown in table 1.Multiple application is had between different data centers.Business correlation between two methods can be different stage, and as shown in the table is high, medium and low.Also business correlation may not be there is between two methods.About the concrete define method of business correlation, see above description.In addition, the data in table 1 can real-time update, also can define in system initialisation phase.
Table 1
Database management module 102 is for managing correlation data storehouse in the heart synchronous in the data.
Flow-control module 103 is for carrying out flow control to the related application between data center.Such as flow bandwidth control or two priority classes etc.In addition, this flow-control module 103 carries out information feed back by notebook data hub-interface 30 pairs of data center resource.Such as, flow control event is sent to the event handling daily record of data center, or relevant parameter that is direct and the mutual flow control of service server.
When the triggering receiving event manager module 105 and send, correlation control module 104 checks correlation data storehouse, sends message by data center's interface 20 to the data center be associated.After both sides (the Liang Ge data center be associated) confirm, the operation of turn-on flow rate control module 103.
Event manager module 105 analyzes the parameter value of monitoring resource module, presetting according to system, finds that operation problem (fault) also generates data-triggered.Such as, operation problem comprises: too high or system crash of system load etc.
Monitoring resource module 106 monitors the performance parameter of notebook data center resources.
Business-level control strategy storehouse 107 stores predefined service feature assurance level.
The flow chart of the method for the flow control between Fig. 3 and Fig. 4 shows according to the Liang Ge data center of the embodiment of the present invention.
As shown in Figure 3, in a data center a, monitoring resource module Real-time Monitoring Data center resources running status (step 302).
When event manager module finds that operation problem appears in a resource applied (step 303), by inquiry correlation data storehouse (step 304), determine the Another Application (step 305) of another data center (such as data center x) relevant to the application that resource goes wrong.
Control request message (step 306) to the data center x transmitted traffic running this Another Application, ask to carry out flow control to the business datum produced between above-mentioned two methods.
If confirm to start flow control (step 307 be), then between Liang Ge data center (data center a and data center x), carry out flow control (step 308).
In addition, as shown in Figure 4, in one of data center be associated (such as data center x), the flow control solicited message (step 402) that other data centers of real-time listening send.
When by receiving flow control solicited message and confirming that operation problem (step 403 be) appears in the resource performance of the other side data center, by inquiring about the business service level database (step 405) of relevant application, determine the corresponding discharge control strategy (step 404) for this business.
Flow control (step 406) is started after confirming.
Then, Liang Ge data center (such as data center a and x) between carry out flow control (step 407).
In addition, as shown in Figure 5, to different correlation ranks and business-level, between data center, different flow control policy can be adopted.As example in Fig. 5, adopt four kinds of flow control policy: stream interface driver 1, stream interface driver 2, stream interface driver 3 and stream interface driver 4.For correlation and the low region of business-level, low controlling cost and the flow control policy of complexity can be adopted.For the region in correlation and business-level, control cost in can adopting and the flow control policy of complexity.For correlation and the high region of business-level, high controlling cost and the flow control policy of complexity can be adopted.Stream interface driver 4 is for the replenishment strategy outside above situation.Adaptable flow control policy has: such as, traffic shaping, traffic forwarding strategy and reaction type flow control policy etc. based on priority.
For carrying out real-time performance protection to data center resource (network, server and storage system) in distributive data center and system for cloud computing; to the present invention proposes in different pieces of information in the heart, carry out flow control based on the correlation between application.When the resource of a data center be in operation go wrong or fault time, the resource of the data center be associated and real-time traffic are controlled, thus ensure the service quality of integrated service, avoid the waste of resource between data center and due to interrelated and hydraulic performance decline that is that cause simultaneously.
According to the present invention, set up in distributive data center and system for cloud computing and manage the database that is preserved the business correlation of the application between data center.Correlation (relation and grade) in business correlation table record different pieces of information wherein at heart between different application.And real-time update and management are carried out to this table.
According to the present invention, the runnability of Monitoring Data center resources, finds and the performance issue at management data center.Particularly, when performance issue appears in a data center, the real-time traffic managed between its with the data center be associated transmits.
The invention provides a kind of coherency management platform in distributive data center network.When performance issue appears in the data center of in integrated service, what ensure to affect the resource performance of the data center be associated minimizes, and improves the resource utilization between data center simultaneously.
Be enumerated above some specific embodiments and illustrate the present invention in detail, this a few example only illustrates the use of principle of the present invention and implementation method thereof, but not limitation of the present invention, without departing from the spirit and scope of the present invention, those skilled in the art can also make various distortion and improvement.Therefore, the present invention should not limited by above-described embodiment, and should be limited by claims and equivalent thereof.
Claims (7)
1. the method that traffic controls between different pieces of information center, comprising:
Determine the business correlation between multiple application of running respectively in different pieces of information in the heart, and be stored into correlation data storehouse; And
When the resource monitoring the application that data center runs be in operation break down time, determine to run another data center applying relevant Another Application to described by inquiry correlation data storehouse, and control request to another data center's transmitted traffic described, ask the business datum to producing between a described application and described Another Application to carry out flow control.
2. method according to claim 1, also comprises:
The data center receiving described flow control request determines corresponding flow control policy according to the service class of described business datum.
3. method according to claim 1, also comprises:
The data center receiving described flow control request determines corresponding flow control policy according to the business correlation level between a described application and described Another Application.
4. according to the method in claim 2 or 3, also comprise:
According to determined flow control policy, flow control is carried out to described business datum
5. method according to claim 1, is characterized in that,
Described business correlation determines according to the grade of the business interface existed between the two methods run respectively in the heart in different pieces of information.
6. method according to claim 1, is characterized in that,
Described business correlation be for the two methods run respectively in the heart in different pieces of information between business datum, obtain according to the statistical calculations model of correlation.
7. the equipment that traffic controls between different pieces of information center, comprising:
Determine the business correlation between multiple application of running respectively in different pieces of information in the heart, and be stored into the unit in correlation data storehouse; And
When the resource monitoring the application that data center runs be in operation break down time, determine to run another data center applying relevant Another Application to described by inquiry correlation data storehouse, and control request to another data center's transmitted traffic described, ask the unit business datum produced between a described application and described Another Application being carried out to flow control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410165565.5A CN105099939A (en) | 2014-04-23 | 2014-04-23 | Method and device for implementing flow control among different data centers |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410165565.5A CN105099939A (en) | 2014-04-23 | 2014-04-23 | Method and device for implementing flow control among different data centers |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105099939A true CN105099939A (en) | 2015-11-25 |
Family
ID=54579522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410165565.5A Pending CN105099939A (en) | 2014-04-23 | 2014-04-23 | Method and device for implementing flow control among different data centers |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105099939A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106453132A (en) * | 2016-12-14 | 2017-02-22 | 深圳市深信服电子科技有限公司 | Dispatching method in hybrid cloud environment and flow control equipment |
| CN106453118A (en) * | 2016-11-11 | 2017-02-22 | 深圳市深信服电子科技有限公司 | Flow control method and flow control system |
| CN106789265A (en) * | 2016-12-27 | 2017-05-31 | 北京五八信息技术有限公司 | The clustering method and device of a kind of service cluster |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100061238A1 (en) * | 2008-09-11 | 2010-03-11 | Avanindra Godbole | Methods and apparatus for flow control associated with multi-staged queues |
| CN101917331A (en) * | 2008-09-11 | 2010-12-15 | 丛林网络公司 | Systems, methods, and apparatus for a data centre |
| US20120222019A1 (en) * | 2012-05-01 | 2012-08-30 | Concurix Corporation | Control Flow Graph Operating System Configuration |
| CN103259739A (en) * | 2012-02-15 | 2013-08-21 | 株式会社日立制作所 | Load balancing device and load balancing method |
| CN103281251A (en) * | 2013-06-18 | 2013-09-04 | 北京百度网讯科技有限公司 | Data transmission method and system between data centers and subsystem of data transmission system |
-
2014
- 2014-04-23 CN CN201410165565.5A patent/CN105099939A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100061238A1 (en) * | 2008-09-11 | 2010-03-11 | Avanindra Godbole | Methods and apparatus for flow control associated with multi-staged queues |
| CN101917331A (en) * | 2008-09-11 | 2010-12-15 | 丛林网络公司 | Systems, methods, and apparatus for a data centre |
| CN103259739A (en) * | 2012-02-15 | 2013-08-21 | 株式会社日立制作所 | Load balancing device and load balancing method |
| US20120222019A1 (en) * | 2012-05-01 | 2012-08-30 | Concurix Corporation | Control Flow Graph Operating System Configuration |
| CN103281251A (en) * | 2013-06-18 | 2013-09-04 | 北京百度网讯科技有限公司 | Data transmission method and system between data centers and subsystem of data transmission system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106453118A (en) * | 2016-11-11 | 2017-02-22 | 深圳市深信服电子科技有限公司 | Flow control method and flow control system |
| CN106453132A (en) * | 2016-12-14 | 2017-02-22 | 深圳市深信服电子科技有限公司 | Dispatching method in hybrid cloud environment and flow control equipment |
| CN106789265A (en) * | 2016-12-27 | 2017-05-31 | 北京五八信息技术有限公司 | The clustering method and device of a kind of service cluster |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105940377B (en) | Methods, systems, and computer readable media for cloud-based virtualization orchestrators | |
| CN107979635A (en) | System, method and storage medium based on micro services | |
| CN106603598A (en) | Method for processing service request and apparatus thereof | |
| CN107800743B (en) | Cloud desktop system, cloud management system and related equipment | |
| CN102143088B (en) | Method and equipment for forwarding data based on security socket layer (SSL) virtual private network (VPN) | |
| EP3076290B1 (en) | Method and device for remotely updating application program | |
| CN113282462B (en) | Information processing method applied to block chain and big data platform | |
| US10454909B2 (en) | Key negotiation method and system, network entity and computer storage medium | |
| CN105471700B (en) | A kind of methods, devices and systems of Message Processing | |
| CN105978938A (en) | Service processing equipment service status determining method and scheduling equipment | |
| CN103457802A (en) | Information transmission system and method | |
| CN104793982A (en) | Method and device for establishing virtual machine | |
| CN105099939A (en) | Method and device for implementing flow control among different data centers | |
| CN110855424B (en) | Method and device for synthesizing asymmetric flow xDR in DPI field | |
| CN104869064A (en) | Flow table updating method and device | |
| CN104702647A (en) | Information request method and information request system | |
| US20180081746A1 (en) | Application message processing system, method, and application device | |
| CN112364365A (en) | Industrial data encryption method, edge server and computer readable storage medium | |
| CN105812278A (en) | Service quality control method and device in software defined network | |
| CN105335376A (en) | Stream processing method, device and system | |
| CN105335362B (en) | The processing method and system of real time data, instant disposal system for treating | |
| CN108829709A (en) | Distributed database management method, apparatus, storage medium and processor | |
| CN109714208A (en) | A kind of equipment is included in method, storage medium and the electronic equipment of network management | |
| US10445080B2 (en) | Methods for adaptive placement of applications and devices thereof | |
| EP3435615B1 (en) | Network service implementation method, service controller, and communication system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151125 |