CN101222362B - Service scheduling method, device and service scheduling system - Google Patents
Service scheduling method, device and service scheduling system Download PDFInfo
- Publication number
- CN101222362B CN101222362B CN2008100023474A CN200810002347A CN101222362B CN 101222362 B CN101222362 B CN 101222362B CN 2008100023474 A CN2008100023474 A CN 2008100023474A CN 200810002347 A CN200810002347 A CN 200810002347A CN 101222362 B CN101222362 B CN 101222362B
- Authority
- CN
- China
- Prior art keywords
- service
- foreground
- unusual
- background server
- backstage
- 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.)
- Active
Links
Images
Abstract
The invention discloses a method for service dispatching, comprising the following steps of calculating the maximum abnormality rate of front desk service according to history operation records and determining standby resources of back end service for substituting the service of the front desk according to the maximum abnormality rate; in case of abnormal front desk service, calculating the required resources for resuming the service and invoking the calculated resources from the standby resources of the back end service to resume the abnormal front desk service. The invention discloses a service dispatching device and a service resuming system. Upon the application of the invention, the operation and maintenance cost can be reduced and different service can be operated on the same back end server so as to batter make use of the recourses.
Description
Technical field
The present invention relates to network application (Application) technical field, more particularly, the present invention relates to a kind of service scheduling method, device and service dispatching patcher.
Background technology
In large-scale service systems such as existing the Internet, all there is a series of server (Server) to come supporting.Moving a series of service on these servers, wherein some key service need provide higher service quality, in promptly needing to be controlled at service time to a certain degree.
For these key service, the hot backup system that can take 1: 1 is usually supported at present.Such as, suppose that certain key service needs 2 station servers to support, then need the backstage be provided with in addition 2 with the foreground server hardware on approaching server as alternate device.At ordinary times the most of the time, 2 background servers on backstage are in idle condition, but still are in running status.
In this 1: 1 backup scenario, owing to use approaching server and employing and 1: 1 the distributed number of preceding station server of hardware performance, in case the foreground server exception, background server can replace and move same service routine immediately, so service performance does not have any loss.But background server is in idle condition for a long time in 1: 1 the service backup mode, therefore can waste resource, is unfavorable for saving operation expense.
At present, also have a kind of 1 of cost: n that can save to serve backup scenario.This 1: in the service backup scenario of n, the background server that certain gap is arranged with foreground server hardware performance is used on the backstage, front-end server becomes 1 with background server: the distributed number of n, wherein n is greater than 1, and only moves the service of single kind in every background server.Such as, suppose that certain key service A needs 1 station server to support, server that n platform and foreground server hardware performance have certain gap then need be set in addition as alternate device on the backstage, and only move key service A in every background server, wherein n is greater than 1.This 1: in the service backup scenario of n, owing to adopted more hardware device, must also can take more hardware placement space, accordingly also can consume more surrounding resources, as power supply, facilities such as air-conditioning, and too much equipment obviously also can increase O﹠M cost, therefore 1: the service backup scenario of n also is unfavorable for reducing operation expense.
This shows that no matter be 1: 1 backup scenario or 1: the backup scenario of n all is unfavorable for reducing operation expense.
Summary of the invention
The embodiment of the invention proposes a kind of service scheduling method, to reduce operation expense.
The embodiment of the invention proposes a kind of service dispatch device, to reduce operation expense.
The embodiment of the invention also proposes a kind of service dispatch system, to reduce operation expense.
The technical scheme of the embodiment of the invention is as follows:
A kind of service scheduling method, described method comprises:
History log according to the foreground service calculates the maximum unusual probability of foreground service appearance, and determines to prepare to replace the backstage service standby resources amount of serving on described foreground according to described probability;
The service of described foreground has to calculate when unusual and recovers the stock number that described service needs, and calls this stock number that calculates to recover and should serve on unusual foreground from described backstage service standby resources amount.
A kind of service dispatch device, described service dispatch device comprises:
Standby resources amount determining unit is used for calculating the maximum unusual probability of foreground service appearance according to the history log of foreground service, and determines to prepare to replace the backstage service standby resources amount of serving on described foreground according to described probability;
The service recovery unit is used for calculating the stock number of recovering described service needs when foreground service has when unusual, and calls this stock number that calculates and serve to recover this unusual foreground from described backstage service standby resources amount.
A kind of service recovery system, described system comprise foreground server zone, background server group and service switch unit, wherein the foreground server zone by at least two platforms before station server form, the background server group is made up of at least two background servers; Wherein:
Described foreground server zone is used to move the foreground service;
Described service switch unit is used for calculating the stock number of recovering described service needs when foreground service has when unusual, and calls this stock number that calculates and serve to recover this unusual foreground from background server group standby resources amount;
Described background server group, be used to receive calling of service switch unit and recover to occur unusual foreground service, described background server group's standby resources amount is that the maximum unusual probability of foreground service that calculates according to foreground server zone history log is determined.
From technique scheme as can be seen, in embodiments of the present invention, at first the history log according to the foreground service calculates the maximum unusual probability of foreground service appearance, and determines to prepare to replace the backstage service standby resources amount of serving on described foreground according to this probability; And then from backstage service standby resources amount, call stock number to recover and to serve unusually.This shows, the embodiment of the invention had not both adopted 1: 1 backup scenario of cost costliness, do not adopt 1 simply: the n backup scenario yet, but at first determine to prepare to replace the backstage service standby resources amount of serving on the foreground according to probability, between resource backup and service quality, obtained dynamic equilibrium point, therefore can reduce operation expense better, and can guarantee service quality.
In addition, use after the embodiment of the invention, dispatch, can on same background server, operation difference simultaneously serve, thereby can utilize resource better by resource there being the service of conflict.And, to use after the embodiment of the invention, the human intervention degree is lower, can reduce operation personnel's labour intensity.
Description of drawings
Fig. 1 is the service scheduling method exemplary flow chart according to the embodiment of the invention;
Fig. 2 is the service dispatch device demonstrative structure figure according to the embodiment of the invention;
Fig. 3 is the demonstrative structure figure according to the service recovery system of the embodiment of the invention.
Embodiment
For making the purpose, technical solutions and advantages of the present invention express clearlyer, the present invention is further described in more detail below in conjunction with drawings and the specific embodiments.
In embodiments of the present invention, at first the history log according to the foreground service calculates the maximum unusual probability of foreground service appearance, and determines to prepare to replace the backstage service standby resources amount of serving on described foreground according to this probability; And then from backstage service standby resources amount, call stock number to recover and to serve unusually.
In addition, in embodiments of the present invention, as can the not rerun service of single kind of the background server of background server, but can move multiple service, and at preceding station server the background server quantity that dynamic dispatching office needs and the COS and the data resource of corresponding operation take place when unusual.
Fig. 1 is the service scheduling method exemplary flow chart according to the embodiment of the invention.
As shown in Figure 1, this method comprises:
Step 101: the history log according to the foreground service calculates the maximum unusual probability of foreground service appearance, and determines to prepare to replace the backstage service standby resources amount of serving on described foreground according to described probability.
Wherein, the preceding station server of operation foreground service can for one, more than two or two.The quantity of current station server is that two or two are when above, unusual probability appears in station server simultaneously before calculating all according to the history log of station server before each of operation foreground service, and determines the standby resources amount of backstage service according to described probability.Wherein, can be in real time or ground monitoring semireal time before station server running status and regulate and control these data desired by services resources, can also set up the dynamic listing of front end services and resource requirement.
Similarly, the background server of operation backstage service also can for one, more than two or two.When the quantity of background server during greater than one, the standby resources amount of background server is born jointly by each background server, and, but can on same background server, move multiple service as the service of single kind of can not reruning of the background server of background server.Similarly, can be in real time or the running status of ground monitoring semireal time background server and regulate and control these data desired by services resources, can also set up the available resources dynamic listing of background server.
Step 102: foreground service has to calculate when unusual and recovers the stock number that described service needs, and calls this stock number that calculates to recover and should serve on unusual foreground from described backstage service standby resources amount.
In the above flow process, preferably, when the service of at least two kinds of foregrounds occurs when unusual simultaneously, at first calculate and recover this at least two kinds of stock numbers that the foreground service needs, from backstage service standby resources amount, call the stock number that calculates and serve, wherein have at least a background server to move described at least two kinds simultaneously and unusual foreground service occurs to recover this at least two kinds of foregrounds.
Such as: suppose that A is arranged, three kinds of B, C service externally service simultaneously.For simplicity, can operate in respectively on Sa, Sb, the preceding station server of Sc three platforms.Daily monitoring record according to Sa, Sb, Sc service, can calculate the mortality of Sa, Sb, Sc respectively, promptly need background server to replace the probability of A, B, C service at once, can calculate before Sa, Sb, this three platform of Sc station server like this and occur unusual probability (normally opposite extreme situations) simultaneously, can determine to prepare to replace the minimum backstage service standby resources amount of foreground service according to this probability.Further, can also determine the concrete background server quantity N that needs according to the operational factor and the determined backstage service standby resources amount of background server.
Suppose all to dispose and to move A, B, three kinds of services of C on every background server, then any 1 background server can replace any service of online preceding station server at any time.It is unusual to suppose that foreground server S a takes place, after then inspecting available background server resource, discovery has N platform background server to use, (be assumed to be 0.5 after calculating the needed background server quantity of the replacement external service performance of Sa machine, then need 1 background server to get final product), then can send regulation and control instruction to the background server B1 in the background server available resources dynamic listing, the service of 1 background server is adjusted into A and externally service, upgrades background server available resources dynamic listing simultaneously.So far, finish the scheduling and the handoff procedure of 1 backup services.
If after foreground server S a is unusual, foreground server S b also takes place unusually, process above similar, need 1.5 background servers if calculate, another background server of dynamic dispatching B2 operation service B then, and upgrade background server available resources dynamic listing, finish corresponding service and scheduling of resource.A, the B service of supposing can move on a station server simultaneously, then can be just becomes running status at the B service dispatch of the background server B1 of operation service A, like this B2 and B1 simultaneously externally operation replace Sb and serve, upgrade the background server available resources simultaneously and tabulate.After Sa or the unusual reparation of Sb, can back scheduling said process and the corresponding the Resources list of renewal.
As seen, use after this flow process, can dynamically dispose the quantity and the type service of background server comparatively economically, can utilize the performance of background server to greatest extent, keep the normal service quality of front end simultaneously to greatest extent.
In addition, when the mutual conflict of unusual and described foreground service appears at least two kinds of foreground services, do not move the foreground service of described appearance conflict simultaneously, thereby avoid on same station server, moving simultaneously several services that conflict is arranged at same background server.
Particularly, because same background server need support multiple service, may run into the software that needs and the situation of data resource conflict, this just needs a conflict service deployment mechanism, is responsible for avoiding moving simultaneously on same station server several services that conflict is arranged.Statistics according to operation, can obtain a service list that higher failure rate is arranged, according to this dynamic listing, adjust the service that moves on the background server and the quantity of service, satisfy may abnormal conditions take place the time with this and finish the scheduling process that background server replaces service with the minimum time.For the service that conflict is arranged, can obtain the probability of failure of these services and relevant failure sequences probability (be A serve unusual back B service also can take place unusual usually), so just can obtain a failure rate service list that dynamically updates, can be in the Service Source of readiness thus a certain moment of dynamic dispatching.
The needed background server quantity of the embodiment of the invention is a dynamic numeral, can draw a predicted value according to recent quality of service monitor, is in the server resource of backup operation state according to this predicted value adjustment, or increases or subtract.
Based on above-mentioned analysis, the invention allows for a kind of service dispatch device.
Fig. 2 is the structural representation according to the service dispatch device of the embodiment of the invention.
As shown in Figure 2, this service dispatch device comprises:
Standby resources amount determining unit 201 is used for calculating the maximum unusual probability of foreground service appearance according to the history log of foreground service, and determines to prepare to replace the backstage service standby resources amount of serving on described foreground according to described probability;
The invention allows for a kind of service recovery system.
Fig. 3 is the structural representation according to the service recovery system of the embodiment of the invention.
As shown in Figure 3, this system comprises foreground server zone 301, background server group 302 and service switch unit 303, wherein foreground server zone 301 by at least two platforms before station server form, background server group 302 is made up of at least two background servers; Wherein:
Described foreground server zone 301 is used to move the foreground service;
Described service switch unit 303 is used for calculating the stock number of recovering described service needs when foreground service has when unusual, and calls this stock number that calculates and serve to recover this unusual foreground from background server group standby resources amount;
Described background server group 302, be used to receive calling of service switch unit 303 and recover to occur unusual foreground service, described background server group's standby resources amount is that the maximum unusual probability of foreground service that calculates according to foreground server zone history log is determined.
Preferably, service switch unit 303, unusual probability appearred in station server simultaneously before the history log of station server calculated all before each that is used for serving according to the described foreground of operation, and served the standby resources amount according to the definite backstage of preparing replacement described foreground service of described probability.
Preferably, service switch unit 303, be used for when at least two kinds of foreground service appearance are unusual, calculate and recovering the stock number that the service of described two kinds of foregrounds needs, and from described background server group standby resources amount, call this stock number that calculates with this unusual foreground service of recovery; Have at least this moment a background server to move described at least two kinds simultaneously among the described background server group and unusual foreground service occurs.
This service recovery system can further include service monitoring unit, foreground 304,
Service monitoring unit, described foreground 304 is used to monitor the operation conditions of foreground service, and sends warning message to described service switch unit 303 when the service appearance of described foreground is unusual, at this moment:
Described service switch unit 303 is used for calculating the stock number of recovering described unusual service needs in response to described warning message, and calls this stock number that calculates to recover service unusually from described background server group standby resources amount.
This service recovery system further comprises service monitoring unit, backstage 305,
Service monitoring unit, described backstage 305 is used for not moving the service of described appearance conflict simultaneously at same background server when the mutual conflict of unusual and described foreground service appears at least two kinds of foreground services.
In sum, in embodiments of the present invention, at first the history log according to the foreground service calculates the maximum unusual probability of foreground service appearance, and determines to prepare to replace the backstage service standby resources amount of serving on described foreground according to this probability; And then from backstage service standby resources amount, call stock number to recover and to serve unusually.This shows, the embodiment of the invention had not both adopted 1: 1 high backup scenario of cost, do not adopt 1 simply: the n backup scenario yet, but at first determine to prepare to replace the backstage service standby resources amount of serving on the foreground according to probability, between resource backup and service quality, obtained dynamic equilibrium point, therefore can reduce operation expense better, and can guarantee service quality.
In addition, use after the embodiment of the invention, the human intervention degree is lower, can reduce operation personnel's labour intensity.And, can on a background server, operation difference simultaneously serve after the application embodiment of the invention, can utilize resource better.
The above is preferred embodiment of the present invention only, is not to be used to limit protection scope of the present invention.Within the spirit and principles in the present invention all, any modification of being done, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (11)
1. a service scheduling method is characterized in that, described method comprises:
History log according to the foreground service calculates the maximum unusual probability of foreground service appearance, and determines to prepare to replace the backstage service standby resources amount of serving on described foreground according to described probability;
The service of described foreground has to calculate when unusual and recovers the stock number that described service needs, and calls this stock number that calculates to recover and should serve on unusual foreground from described backstage service standby resources amount.
2. service scheduling method according to claim 1 is characterized in that, the preceding station server that moves the service of described foreground is at least two;
Described history log according to the foreground service calculates the maximum unusual probability of foreground service appearance, and determines that according to described probability preparing to replace the backstage service standby resources amount of serving on described foreground is:
Unusual probability appears in station server simultaneously before calculating all according to the history log of station server before each of the described foreground of operation service, and determines to prepare to replace the backstage service standby resources amount of described foreground service according to described probability.
3. service scheduling method according to claim 2 is characterized in that, the background server that the backstage service of described foreground service is replaced in operation is at least two, and described backstage service standby resources amount is born jointly by each background server.
4. service scheduling method according to claim 3, it is characterized in that, in the described method, when the service of at least two kinds of foregrounds occurs when unusual simultaneously, calculate and recover the stock number that the service of described at least two kinds of foregrounds needs, from described backstage service standby resources amount, call the stock number that calculates and serve, wherein have at least a background server to move described at least two kinds simultaneously and unusual foreground service occurs to recover this at least two kinds of foregrounds.
5. service scheduling method according to claim 4 is characterized in that, when the mutual conflict of unusual and described foreground service appears at least two kinds of foreground services, does not move the foreground service of described appearance conflict simultaneously at same background server.
6. a service dispatch device is characterized in that, described service dispatch device comprises:
Standby resources amount determining unit is used for calculating the maximum unusual probability of foreground service appearance according to the history log of foreground service, and determines to prepare to replace the backstage service standby resources amount of serving on described foreground according to described probability;
The service recovery unit is used for calculating the stock number of recovering described service needs when foreground service has when unusual, and calls this stock number that calculates and serve to recover this unusual foreground from described backstage service standby resources amount.
7. service recovery system, it is characterized in that, described system comprises foreground server zone, background server group and service switch unit, wherein the foreground server zone by at least two platforms before station server form, the background server group is made up of at least two background servers; Wherein:
Described foreground server zone is used to move the foreground service;
Described service switch unit is used for calculating the stock number of recovering described service needs when foreground service has when unusual, and calls this stock number that calculates and serve to recover this unusual foreground from background server group standby resources amount;
Described background server group, be used to receive calling of service switch unit and recover to occur unusual foreground service, described background server group's standby resources amount is that the maximum unusual probability of foreground service that calculates according to foreground server zone history log is determined.
8. service recovery according to claim 7 system is characterized in that,
Described service switch unit, unusual probability appearred in station server simultaneously before the history log of station server calculated all before each that is used for serving according to the described foreground of operation, and determined to prepare to replace the background server group standby resources amount of described foreground service according to described probability.
9. service recovery according to claim 7 system is characterized in that,
Described service switch unit, be used for when at least two kinds of foreground service appearance are unusual, calculate and recover the stock number that the service of described at least two kinds of foregrounds needs, and from described background server group standby resources amount, call this stock number that calculates to recover this unusual foreground service;
Have at least a background server to move described at least two kinds simultaneously among the described background server group and unusual foreground service occurs.
10. according to claim 7,8 or 9 described service recovery systems, it is characterized in that described service recovery system further comprises service monitoring unit, foreground,
Service monitoring unit, described foreground is used to monitor the operation conditions of foreground service, and sends warning message to described service switch unit when the service appearance of described foreground is unusual,
Described service switch unit is used for calculating the stock number of recovering described unusual service needs in response to described warning message, and calls this stock number that calculates to recover service unusually from described background server group standby resources amount.
11., it is characterized in that described service recovery system further comprises service monitoring unit, backstage according to claim 7,8 or 9 described service recovery systems,
Service monitoring unit, described backstage is used for not moving the service of described appearance conflict simultaneously at same background server when the mutual conflict of unusual and described foreground service appears at least two kinds of foreground services.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008100023474A CN101222362B (en) | 2008-01-08 | 2008-01-08 | Service scheduling method, device and service scheduling system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008100023474A CN101222362B (en) | 2008-01-08 | 2008-01-08 | Service scheduling method, device and service scheduling system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101222362A CN101222362A (en) | 2008-07-16 |
| CN101222362B true CN101222362B (en) | 2011-10-26 |
Family
ID=39631953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2008100023474A Active CN101222362B (en) | 2008-01-08 | 2008-01-08 | Service scheduling method, device and service scheduling system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101222362B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853185B (en) * | 2009-03-30 | 2015-07-08 | 华为技术有限公司 | Blade server and service dispatching method thereof |
| CN103580902B (en) * | 2012-08-07 | 2015-01-14 | 腾讯科技（深圳）有限公司 | Computer information system and dynamic disaster recovery method thereof |
| US8838535B2 (en) * | 2012-10-05 | 2014-09-16 | Oracle International Corporation | Providing services across systems that manage distributed replicas |
| CN109936639A (en) * | 2017-12-15 | 2019-06-25 | 中兴通讯股份有限公司 | A kind of service calling method and server |
| CN109783173B (en) * | 2019-01-10 | 2022-04-19 | 北京北信源软件股份有限公司 | Client-oriented multi-server fast switching management method |
| CN113783908B (en) * | 2020-06-10 | 2023-06-27 | 腾讯科技（上海）有限公司 | Service calling method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1606277A (en) * | 2004-11-18 | 2005-04-13 | 上海交通大学 | Fast and highly effective extendible network protecting method |
| CN1937523A (en) * | 2006-08-09 | 2007-03-28 | 江苏移动通信有限责任公司 | Client service emergency system and its realizing method |
| CN1941714A (en) * | 2005-09-28 | 2007-04-04 | 中兴通讯股份有限公司 | Method for restoring multi-point failure service in grid network |
-
2008
- 2008-01-08 CN CN2008100023474A patent/CN101222362B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1606277A (en) * | 2004-11-18 | 2005-04-13 | 上海交通大学 | Fast and highly effective extendible network protecting method |
| CN1941714A (en) * | 2005-09-28 | 2007-04-04 | 中兴通讯股份有限公司 | Method for restoring multi-point failure service in grid network |
| CN1937523A (en) * | 2006-08-09 | 2007-03-28 | 江苏移动通信有限责任公司 | Client service emergency system and its realizing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101222362A (en) | 2008-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101222362B (en) | Service scheduling method, device and service scheduling system | |
| JP4509346B2 (en) | Method and system for executing dynamic load balance in wireless communication network and message processing system in wireless communication network | |
| CN102483644B (en) | Operational management method for information processing system and information processing system | |
| CN101394306B (en) | Seamless switching method for dual server system | |
| CN1527169A (en) | Redundant application station for process control system | |
| CN106603696B (en) | A kind of high-availability system based on super fusion basic framework | |
| CN103081439A (en) | Method of managing logical link and communication device | |
| CN101924650A (en) | Method for implementing services and intelligent server autonomy of failure information system | |
| CN101546189B (en) | Method for controlling real-time database system | |
| CN108052371A (en) | Railway TDCS/CTC systems and its application based on virtualization technology | |
| CN202870563U (en) | Distributed comprehensive monitoring system | |
| CN115202939A (en) | Nuclear power information system server main and standby redundant frame management system and method | |
| CN109101400A (en) | A kind of monitoring system of cloud computation data center whole machine cabinet server | |
| CN102158545A (en) | Resource pool management method and device | |
| CN100492297C (en) | Control method for implementing distribution type apparatus | |
| CN108234623B (en) | Automatic balance management method for data acquisition link of distribution network master station | |
| CN104484228A (en) | Distributed parallel task processing system based on Intelli-DSC (Intelligence-Data Service Center) | |
| CN102487332A (en) | Fault processing method, apparatus thereof and system thereof | |
| CN111614702B (en) | Edge calculation method and edge calculation system | |
| CN115037769B (en) | SOA-based air traffic control automation system and realization method thereof | |
| CN103873576A (en) | Monitoring and management method and system based on virtual system | |
| CN107682888B (en) | Cloud AC redundancy backup system and method | |
| CN108196441B (en) | Method for realizing hot standby redundancy for system application | |
| EP0855842A2 (en) | Method to reduce network operations cost | |
| JP2006318394A (en) | Management method for uninterruptible power supply device in network system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20151230 Address after: The South Road in Guangdong province Shenzhen city Fiyta building 518057 floor 5-10 Nanshan District high tech Zone Patentee after: Shenzhen Tencent Computer System Co., Ltd. Address before: Shenzhen Futian District City, Guangdong province 518044 Zhenxing Road, SEG Science Park 2 East Room 403 Patentee before: Tencent Technology (Shenzhen) Co., Ltd. |