CN105187499B - A kind of distributed scheduling method and system based on zookeeper biplane data frameworks - Google Patents
A kind of distributed scheduling method and system based on zookeeper biplane data frameworks Download PDFInfo
- Publication number
- CN105187499B CN105187499B CN201510484542.5A CN201510484542A CN105187499B CN 105187499 B CN105187499 B CN 105187499B CN 201510484542 A CN201510484542 A CN 201510484542A CN 105187499 B CN105187499 B CN 105187499B
- Authority
- CN
- China
- Prior art keywords
- node
- tree
- dynamic
- zookeeper
- static
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
Abstract
The present invention relates to a kind of distributed scheduling method and system based on zookeeper biplane data frameworks, it is included in zookeeper and builds dynamic tree and Static Tree；It will be in the general configuration information storage to the nodal information of corresponding Static Tree of operation system；Business procedure generates interim dynamic node when starting in dynamic tree, will be in the attribute information setting to interim dynamic node of the business procedure；Distributed scheduler obtains Static Tree nodal information and dynamic tree nodal information respectively, optimal interim dynamic node is chosen according to scheduled selection principle, and then obtain corresponding business procedure, realizes the connection of distributed scheduler and the business procedure.The present invention indicates the logic load structure of load equalizer by Static Tree, real-time management and control is carried out to the operating condition of existing application by dynamic tree, the linkage of dynamic tree and Static Tree realizes the dynamic bind of logic load and actual motion, so that cloud system deployment and switching are efficiently, quickly, system flexibility is high.
Description
Technical field
The present invention relates to field of communication technology more particularly to a kind of distributions based on zookeeper biplane data frameworks
Formula dispatching method and system.
Background technology
As telecommunication service data service develops, flow calculates expense, enters an item of expenditure in the accounts and believe that control process increasingly requires real-time.Together
When, as the business demands such as orientation flow, intelligent pipeline and pipeline operation are gradually carried out, data traffic subdivision also become it is necessary it
Road.The requirement of real-time and data traffic subdivision will generate more service usage records, energy handled to existing BOSS systems
Power is challenged.
From another angle, as 4G business is constantly spread out, faster access speed generates more services and uses note
Record；Faster access speed will also result in the arrears risk of bigger simultaneously, need more timely flow control process；In addition faster
Access speed be also required to carry out careful division to the grade of service.So being needed from business in the subdivision of 4G epoch data traffics
More careful, demand is also more urgent.
The surge of business demand amount brings various problems, and the automatic linking and flexible switching between system are not easy to realize, and
Framework transition to business build there are larger impact, the synchronization of system, the promptness and operation system of system exception processing expand
The realization of the flexibility of appearance brings prodigious difficulty.The deployment of system and switching efficiency be not high, and system flexibility is low.
Therefore, data service is explosive growth to the requirement of the enabling capabilities of BOSS systems, faster, it is more acurrate, more close
Suitable building of supporting system is the basic demand of next-generation BOSS systems.
Invention content
It is a kind of bis- based on zookeeper the technical problem to be solved by the present invention is in view of the deficiencies of the prior art, provide
The distributed scheduling method and system of panel data framework.
ZooKeeper provides centralized service, including configuring maintenance, service name, distributed synchronization, group management.Son clothes
Business is usually used in Distributed Application.Availabilities of the Zookeeper in Distributed Application so that the realization of BOSS system cloud frameworks
More efficiently, flexibly.
The present invention uses biplane data framework using the zookeeper services of increasing income in zookeeper, and one quiet
The tree-shaped hierarchical structure (S) of state, hereinafter referred to as Static Tree, indicate the logic load structure of load equalizer；One dynamic
Tree-shaped hierarchical structure (D), hereinafter referred to as dynamic tree, to carry out real-time management and control to the operating condition of existing business procedure.
The technical solution that the present invention solves above-mentioned technical problem is as follows：One kind being based on zookeeper biplane data frameworks
Distributed scheduling method, include the following steps：
Step 1, the biplane data framework being made of dynamic tree and Static Tree is built in zookeeper；
Step 2, the general configuration information of operation system is stored into the nodal information of corresponding Static Tree；
Step 3, it is automatically registered to when the business procedure of operation system starts in zookeeper services, it is raw in dynamic tree
It, will be in the attribute information setting to interim dynamic node of the business procedure at unique interim dynamic node；
Step 4, distributed scheduler obtains Static Tree nodal information and dynamic tree nodal information respectively, according to scheduled
Selection principle chooses optimal interim dynamic node, obtains the corresponding business procedure of interim dynamic node, realizes distributed scheduling
The connection of program and the business procedure.
The beneficial effects of the invention are as follows：Biplane data framework is built in zookeeper of the present invention, is indicated by Static Tree
The logic load structure of load equalizer carries out real-time management and control, dynamic by dynamic tree to the operating condition of existing business procedure
The linkage of tree and Static Tree realizes the dynamic bind of logic load and actual motion, realizes automatic linking and spirit between system
Switching living, eliminates the influence that framework transition build business, the bridge using zookeeper as system communication so that be
System business structure becomes more efficiently, flexibly in startup and the monitoring process in switching and later stage；And it is deposited on zookeeper
The versatility configuration of system has been stored up, it is modified when the system configuration on a certain host modifications zookeeper Static Tree
Configuration is to All hosts node as it can be seen that realizing the synchronization of system configuration；The invention enables cloud system can carry out it is efficient, fast
The deployment and switching of speed, system flexibility are high.
Based on the above technical solution, the present invention can also be improved as follows.
Further, being implemented as the data framework of biplane is built in step 1 in zookeeper：According to business
The non-leaf nodes of the non-leaf nodes and leaf node and dynamic tree of Static Tree is generated in advance in the planning in system service pond.
Further, it when business procedure starts in step 3, registers in interim dynamic node to zookeeper services, it is interim dynamic
State node is named according to zookeeper path fashions.
Using the advantageous effect of above-mentioned further scheme：The Uniform Name service for realizing operation system cloud process, is convenient for
Management and monitoring to cloud operation system.
Further, above-mentioned technical proposal further includes creating or deleting the leaf section of Static Tree when carrying out load balancing configuration
Point.
Further, distributed scheduler obtains the general configuration information of operation system from Static Tree in step 4, driven
The attribute information that all business procedure of next stage subservice system are obtained in state tree, chooses optimal interim dynamic node, will face
When dynamic node title setting in the static node of Static Tree, completing being associated with for static node and dynamic node.
Further, when the business procedure being registered on zookeeper stops, the interim dynamic node on dynamic tree is deleted
Remove, by monitor interim dynamic node on dynamic tree there are situations, judge the operating condition of corresponding service system.
Further, above-mentioned technical proposal further includes operation system notice and repair process extremely, is implemented as：When next
When grade subservice system exception, distributed scheduler receives the notice of zookeeper, obtains each on Static Tree and dynamic tree
The status information of node searches Exceptional static burl according to the status information matched static tree node and dynamic tree node of acquisition
The corresponding dynamic tree node of point, optimal interim dynamic node is chosen according to scheduled selection principle, itself and static node are closed
Connection, carries out being switched fast for node, completes the abnormal of system and repairs.
Using the advantageous effect of above-mentioned further scheme：Realize operation system cloud node exception notice and automatically it is extensive
It is multiple.
Further, above-mentioned technical proposal further includes carrying out dynamic capacity-expanding to operation system, is implemented as：
Leaf node is added on zookeeper Static Trees, distributed scheduler receives the notice of zookeeper, in former business system
Under system program normal operation, optimal interim dynamic node is chosen according to scheduled selection principle, with newly-increased leaf node
It is associated, increases the service processing node of operation system, realize the automatic dilatation of operation system.
Using the advantageous effect of above-mentioned further scheme：Realize the convenient dilatation of system cloudization.
Another technical solution that the present invention solves above-mentioned technical problem is as follows：One kind being based on zookeeper double flat face datas
The distributed scheduling system of framework, including Static Tree module, dynamic tree module and distributed scheduling module；
The Static Tree module, is implemented in zookeeper, for arriving the general configuration information storage of operation system
In the nodal information of corresponding Static Tree；
The dynamic tree module, is implemented in zookeeper, is used for when the business procedure of operation system starts, raw
It, will be in the attribute information setting to interim dynamic node of the business procedure at unique interim dynamic node；
The distributed scheduling module, for obtaining Static Tree nodal information and dynamic tree nodal information respectively, according to pre-
Fixed selection principle chooses optimal interim dynamic node, obtains the corresponding business procedure of interim dynamic node, realizes distributed
The connection of scheduler program and the business procedure.
Based on the above technical solution, the present invention can also be improved as follows.
Further, when next stage subservice system exception, distributed scheduling module receives the notice of zookeeper,
The status information for obtaining each node on Static Tree and dynamic tree, according to the status information matched static tree node and dynamic tree of acquisition
Node searches the corresponding dynamic tree node of Exceptional static tree node, optimal interim dynamic is chosen according to scheduled selection principle
It is associated with static node, carries out being switched fast for node by node, completes the abnormal of system and repairs.
Further, when operation system dynamic capacity-expanding, leaf node is added on Static Tree, distributed scheduler receives
It is chosen to the notice of zookeeper according to scheduled selection principle optimal in former operation system normal program operation
Interim dynamic node is associated with newly-increased leaf node, is increased the service processing node of operation system, is realized operation system
Automatic dilatation.
Description of the drawings
Fig. 1 is a kind of distributed scheduling system block diagram based on zookeeper biplane data frameworks of the present invention；
Fig. 2 is a kind of distributed scheduling method flow diagram based on zookeeper biplane data frameworks of the present invention；
Fig. 3 is zookeeper biplanes data shelf composition of the present invention.
In attached drawing, parts list represented by the reference numerals are as follows：
1, Static Tree module, 2, dynamic tree module, 3, distributed scheduling module.
Specific implementation mode
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
As shown in Figure 1, a kind of distributed scheduling system based on zookeeper biplane data frameworks, including Static Tree
Module 1, dynamic tree module 2 and distributed scheduling module 3；The Static Tree module 1, is implemented in zookeeper, and being used for will
In the general configuration information storage to the nodal information of corresponding Static Tree of operation system；The dynamic tree module 2, is implemented in
In zookeeper, for when the business procedure of operation system starts, unique interim dynamic node being generated, by the business
In the attribute information setting to interim dynamic node of program；The distributed scheduling module 3, for obtaining static tree node respectively
Information and dynamic tree nodal information choose optimal interim dynamic node according to scheduled selection principle, obtain interim dynamic and save
The corresponding business procedure of point, realizes the connection of distributed scheduler and the business procedure.
As shown in Fig. 2, a kind of distributed scheduling method based on zookeeper biplane data frameworks, including walk as follows
Suddenly：
Step 1, the biplane data framework being made of dynamic tree and Static Tree is built in zookeeper, such as Fig. 3 institutes
Show.
Specifically, according to the planning of operation system service pool be generated in advance non-leaf nodes and the leaf node of Static Tree with
And the non-leaf nodes of dynamic tree.The Static Tree and dynamic tree include clustered node, domain node and tank node.Node level and
Naming rule such as table 1.
Table 1
The non-leaf nodes of Static Tree and dynamic tree is generated according to the planning in system service pond in advance, the leaf of Static Tree
Node is created and is deleted when management platform does load balancing configuration, and other times can only operate leaf node data.
Leaf node attribute in static structure is PERSISTENT, and serial number logical process number thereon is configured specified by foreground.
The leaf node of dynamic tree is created when business procedure starts, and business procedure is automatically deleted when stopping by server-side,
The data of leaf node can only be operated in operation.Leaf node attribute is EPHEMERAL in dynamic structure, thereon serial number
It is designated in being locally configured when installation kit is installed, it will not change after installation.
{ penult name } is the unique mark of corresponding business procedure on dynamic tree；Without particular/special requirement on Static Tree.
The penult name of dynamic tree is the unique mark of corresponding business procedure.
Step 2, the general configuration information of operation system is stored into the nodal information of corresponding Static Tree.
Step 3, it is automatically registered to when the business procedure of operation system starts in zookeeper services, it is raw in dynamic tree
It, will be in the attribute information setting to interim dynamic node of the business procedure at unique interim dynamic node.
Business procedure start when, register interim dynamic node to zookeeper service in, interim dynamic node according to
Zookeeper path fashions are named.
The attribute information of the wherein described business procedure include the CPU of host where the business procedure, memory, host ip,
The attribute informations such as present procedure port numbers.
When business procedure starts, the generic configuration obtained on static tree node is configured as startup, and load starts configuration, opens
The access that distributed scheduler is waited for after dynamic, carries out business processing.
When the business procedure being registered on zookeeper stops, the interim dynamic node on dynamic tree is deleted, and passes through prison
Control interim dynamic node on dynamic tree there are situations, judge the operating condition of corresponding service system.
Wherein the attribute of Static Tree leaf node and dynamic tree leaf node includes at least content as shown in Table 2.
Table 2
Step 4, distributed scheduler obtains Static Tree nodal information and dynamic tree nodal information respectively, according to scheduled
Selection principle chooses optimal interim dynamic node, obtains the corresponding business procedure of interim dynamic node, realizes distributed scheduling
The connection of program and the business procedure.
Specifically, distributed scheduler obtains the general configuration information of operation system from Static Tree, from dynamic tree
The attribute information for obtaining all business procedure of next stage subservice system is (including host CPU in interim dynamic node, interior
Deposit, the information such as host node number), optimal interim dynamic node is chosen, by the title setting of interim dynamic node to Static Tree
Static node in, being associated with for static node and dynamic node is completed, to the unicom and logical process of memory system.
Above-mentioned technical proposal further include by monitor interim dynamic node there are situations, judge the fortune of corresponding service system
Market condition.Distributed scheduler creates watcher in Fig. 2 tank nodes, to adjust routing in time in business procedure exception
Strategy carries out the related works such as abnormal restoring.(watcher can be all arranged in distributed scheduler on dynamic tree and Static Tree,
When business procedure exception, triggering is watcher on dynamic tree tank node, and when carrying out system dynamic capacity-expanding, triggering is quiet
Watcher on the tank node of state tree).
The business procedure of online flow independently builds pond according to service type, and corresponding distributed scheduler is also single
It is established on functional pool, (distributed scheduler function is identical, has individual distributed scheduler per one kind business procedure
Process) therefore what distributed scheduler setting wathcher monitored is interim dynamic node on Static Tree and dynamic tree, when
After business procedure is normal in business pond, corresponding interim dynamic node is automatically deleted in dynamic tree, is triggered on dynamic node
watcher.Zookeeper server-sides notify corresponding distributed scheduler, belonging to distributed scheduler reacquires
All child nodes of znode, and analyze most suitable interim dynamic node and update corresponding static node data, connection is established, is opened
Dynamic distribution routing.
Above-mentioned technical proposal further includes operation system notice and repair process extremely, is implemented as：When the sub- industry of next stage
When business system exception, distributed scheduler receives the notice of zookeeper, obtains each node on Static Tree and dynamic tree
Status information is searched Exceptional static tree node and is corresponded to according to the status information matched static tree node and dynamic tree node of acquisition
Dynamic tree node, optimal interim dynamic node is chosen according to scheduled selection principle, it is associated with static node, carry out
Node is switched fast, and is completed the abnormal of system and is repaired.
Above-mentioned technical proposal further includes carrying out dynamic capacity-expanding to operation system, is implemented as：Leaf is added on Static Tree
Child node, distributed scheduler receive the notice of zookeeper, in former operation system normal program operation, root
Optimal interim dynamic node is chosen according to scheduled selection principle, is associated with newly-increased leaf node, is increased operation system
Service processing node realizes the automatic dilatation of operation system.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent replacement, improvement and so on should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of distributed scheduling method based on zookeeper biplane data frameworks, which is characterized in that including walking as follows
Suddenly：
Step 1, the biplane data framework being made of dynamic tree and Static Tree is built in zookeeper；
Step 2, the general configuration information of operation system is stored into the nodal information of corresponding Static Tree；
Step 3, it is automatically registered to when the business procedure of operation system starts in zookeeper services, is generated only in dynamic tree
One interim dynamic node, will be in the attribute information setting to interim dynamic node of the business procedure；
Step 4, distributed scheduler obtains Static Tree nodal information and dynamic tree nodal information respectively, is obtained from dynamic tree
The attribute information of all business procedure of next stage subservice system is chosen most according to the attribute information of all business procedure
Excellent interim dynamic node obtains the corresponding business procedure of interim dynamic node, realizes distributed scheduler and the business journey
The connection of sequence.
2. a kind of distributed scheduling method based on zookeeper biplane data frameworks according to claim 1, feature
It is, builds being implemented as the data framework of biplane in step 1 in zookeeper：According to operation system service pool
Planning be generated in advance Static Tree non-leaf nodes and leaf node and dynamic tree non-leaf nodes.
3. a kind of distributed scheduling method based on zookeeper biplane data frameworks according to claim 1, feature
Be, in step 3 business procedure start when, register interim dynamic node to zookeeper service in, interim dynamic node according to
Zookeeper path fashions are named.
4. a kind of distributed scheduling method based on zookeeper biplane data frameworks according to claim 1, feature
It is, distributed scheduler obtains the general configuration information of operation system from Static Tree in step 4, is obtained from dynamic tree
The attribute information of all business procedure of next stage subservice system is chosen most according to the attribute information of all business procedure
Excellent interim dynamic node, will interim dynamic node title setting in the static node of Static Tree, complete static node with it is dynamic
The association of state node.
5. a kind of distributed scheduling method based on zookeeper biplane data frameworks according to claim 1, feature
It is, when the business procedure being registered on zookeeper stops, the interim dynamic node on dynamic tree is deleted, and passes through monitoring
On dynamic tree interim dynamic node there are situations, judge the operating condition of corresponding service system.
6. a kind of distributed scheduling method based on zookeeper biplane data frameworks according to claim 1, feature
It is, further includes operation system notice and repair process extremely, be implemented as：When next stage subservice system exception, point
Cloth scheduler program receives the notice of zookeeper, obtains the status information of each node on Static Tree and dynamic tree, according to obtaining
The status information matched static tree node and dynamic tree node taken searches the corresponding dynamic tree node of Exceptional static tree node, root
Optimal interim dynamic node is chosen according to scheduled selection principle, it is associated with static node, carries out being switched fast for node,
The abnormal of completion system is repaired.
7. a kind of distributed scheduling method based on zookeeper biplane data frameworks according to claim 1, feature
It is, further includes that dynamic capacity-expanding is carried out to operation system, be implemented as：Leaf node is added on Static Tree, distribution is adjusted
Degree program receives the notice of zookeeper, in former operation system normal program operation, according to scheduled selection principle
Optimal interim dynamic node is chosen, is associated with newly-increased leaf node, the service processing node of operation system is increased, is realized
The automatic dilatation of operation system.
8. a kind of distributed scheduling system based on zookeeper biplane data frameworks, which is characterized in that including Static Tree mould
Block, dynamic tree module and distributed scheduling module；
The Static Tree module, is implemented in zookeeper, for storing the general configuration information of operation system to correspondence
Static Tree nodal information in；
The dynamic tree module, is implemented in zookeeper, for when the business procedure of operation system starts, generating only
One interim dynamic node, will be in the attribute information setting to interim dynamic node of the business procedure；
The distributed scheduling module, for obtaining Static Tree nodal information and dynamic tree nodal information respectively, from dynamic tree
The attribute information for obtaining all business procedure of next stage subservice system is selected according to the attribute information of all business procedure
Optimal interim dynamic node is taken, the corresponding business procedure of interim dynamic node is obtained, realizes distributed scheduler and the industry
The connection for program of being engaged in.
9. a kind of distributed scheduling system based on zookeeper biplane data frameworks according to claim 8, feature
It is, when next stage subservice system exception, distributed scheduling module receives the notice of zookeeper, obtains Static Tree
It is searched according to the status information matched static tree node and dynamic tree node of acquisition with the status information of each node on dynamic tree
The corresponding dynamic tree node of Exceptional static tree node, optimal interim dynamic node is chosen according to scheduled selection principle, by it
It is associated with static node, carries out being switched fast for node, completed the abnormal of system and repair.
10. a kind of distributed scheduling system based on zookeeper biplane data frameworks according to claim 8, special
Sign is, when operation system dynamic capacity-expanding, leaf node is added on Static Tree, distributed scheduler receives
The notice of zookeeper chooses optimal face in former operation system normal program operation according to scheduled selection principle
When dynamic node, be associated with newly-increased leaf node, increase the service processing node of operation system, realize operation system from
Dynamic dilatation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510484542.5A CN105187499B (en) | 2015-08-07 | 2015-08-07 | A kind of distributed scheduling method and system based on zookeeper biplane data frameworks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510484542.5A CN105187499B (en) | 2015-08-07 | 2015-08-07 | A kind of distributed scheduling method and system based on zookeeper biplane data frameworks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105187499A CN105187499A (en) | 2015-12-23 |
| CN105187499B true CN105187499B (en) | 2018-07-17 |
Family
ID=54909339
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510484542.5A Active CN105187499B (en) | 2015-08-07 | 2015-08-07 | A kind of distributed scheduling method and system based on zookeeper biplane data frameworks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105187499B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106790595B (en) * | 2016-12-29 | 2020-12-22 | 上海理想信息产业（集团）有限公司 | Docker container active load balancing device and method |
| CN111163117B (en) * | 2018-11-07 | 2023-01-31 | 北京京东尚科信息技术有限公司 | Zookeeper-based peer-to-peer scheduling method and device |
| CN110351377A (en) * | 2019-07-17 | 2019-10-18 | 成都鑫芯电子科技有限公司 | A kind of multistage linking control method and system |
| CN114826877B (en) * | 2022-02-24 | 2023-07-14 | 苏州浪潮智能科技有限公司 | Asset alarm processing method, device, computer equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103916481A (en) * | 2014-04-17 | 2014-07-09 | 北京京东尚科信息技术有限公司 | Method and device for processing data |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW200827957A (en) * | 2006-12-21 | 2008-07-01 | Ind Tech Res Inst | Method for information transmission with backbone network and a position monitoring system for multiple robotic devices |
| US10324942B2 (en) * | 2013-07-26 | 2019-06-18 | Snap Inc. | Segment data visibility and management in a distributed database of time stamped records |
| CN104320433B (en) * | 2014-09-28 | 2018-11-23 | 北京京东尚科信息技术有限公司 | Data processing method and distributed data processing system |
| CN104486108A (en) * | 2014-12-08 | 2015-04-01 | 畅捷通信息技术股份有限公司 | Node configuration method base on Zookeeper and node configuration system based on Zookeeper |
-
2015
- 2015-08-07 CN CN201510484542.5A patent/CN105187499B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103916481A (en) * | 2014-04-17 | 2014-07-09 | 北京京东尚科信息技术有限公司 | Method and device for processing data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105187499A (en) | 2015-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105187499B (en) | A kind of distributed scheduling method and system based on zookeeper biplane data frameworks | |
| CN105959401B (en) | A kind of manufacturing service supply-demand mode and dynamic dispatching method based on super-network | |
| CN108287756A (en) | A kind of method and device of processing task | |
| CN102843418B (en) | A kind of resource scheduling system | |
| CN102984012B (en) | Management method and system for service resources | |
| CN104679595B (en) | A kind of application oriented IaaS layers of dynamic resource allocation method | |
| CN109492774A (en) | A kind of cloud resource dispatching method based on deep learning | |
| CN110147372A (en) | A kind of distributed data base Intelligent Hybrid storage method towards HTAP | |
| CN103150003A (en) | Information processing system, and its power-saving control method and device | |
| CN104753968B (en) | Cloud computing cross-region multiple data centers and its schedule management method | |
| Jia et al. | Reliability-aware dynamic service chain scheduling in 5G networks based on reinforcement learning | |
| CN109919365A (en) | A kind of electric vehicle paths planning method and system based on double decision searches | |
| CN108989399A (en) | A kind of cluster common data querying method, system, device and readable storage medium storing program for executing | |
| CN110198280A (en) | A kind of SDN link allocation method based on BP neural network | |
| CN110278257A (en) | A kind of method of mobilism configuration distributed type assemblies node label | |
| CN104767778A (en) | Task processing method and device | |
| Ali et al. | Dual algorithms for pure network problems | |
| CN108304168A (en) | A kind of edge calculations machine operating system | |
| CN108322525A (en) | A kind of industry multi-core network establishing method | |
| CN108574718A (en) | A kind of cloud host creation method and device | |
| CN106209390A (en) | Network device management and power-economizing method and resource management apparatus, route energy saver | |
| CN107122285A (en) | A kind of multithread process control Dynamic Announce and intelligence change System and method for | |
| CN102497410B (en) | Method for dynamically partitioning computing resources of cloud computing system | |
| CN103051478A (en) | Large-capacity telecommunication network management system as well as setting and application methods thereof | |
| Nam et al. | Green data center using centralized power-management of network and servers |
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 |