CN105610972A - Clustered task dispatching system - Google Patents
Clustered task dispatching system Download PDFInfo
- Publication number
- CN105610972A CN105610972A CN201610072921.8A CN201610072921A CN105610972A CN 105610972 A CN105610972 A CN 105610972A CN 201610072921 A CN201610072921 A CN 201610072921A CN 105610972 A CN105610972 A CN 105610972A
- Authority
- CN
- China
- Prior art keywords
- task
- instruction
- jvm
- server
- node server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45504—Abstract machines for programme code execution, e.g. Java virtual machine [JVM], interpreters, emulators
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- 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]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention discloses a clustered task dispatching system, which is characterized in processing of task scheduling. The clustered task dispatching system comprises instruction dispatching platforms, JVM (Java Virtual Machine) containers and a node server; the instruction dispatching platforms are interconnected through a network by a plurality of task servers, deploy zookeeper services are deployed at these task servers, and the zookeeper services return operation instructions according to task requirements; each JVM container is used for operating business services, and different operation instructions are correspondingly stored at the JVM containers and the business services; the node server receives an operation instructions from the instruction dispatching platforms or returns a sending instruction to the instruction dispatching platforms; the node server judges whether load conditions of the JVM containers which obtain the operation instructions are idle or busy; if the load conditions are idle, then the JVM containers process the task requirement according to the operation instruction; and if the load conditions are busy, then the node server temporarily stores the operation instructions in a waiting queue.
Description
Technical field
The application relates to a kind of task of network service sends system, is specifically related to a kind of task of concentrating typeSend system.
Background technology
With the lifting at a high speed of work network speed, also drive the diversity of network services. And the back of the body of network servicesAfter be to be realized by the collocation of hardware and software. Hardware aspect is framework, resource or the fortune of serverCalculation ability etc. Software aspect is that the calculation mechanism institutes such as task distribution and scheduling of resource realize.
At present, popular task scheduling platform comprises based on Quartz, based on Redis store tasksQueuing data, use crontab order, based on Mapduce Computational frame, IBMMQ message queueDeng. All there is the standalone version one process application of some defects: Quartz in these dispatching platforms, once occurThe delay situation of machine, cannot guarantee that task is correctly triggered, and can produce internal memory and overflow in the time of task excessive numberRisk, execution efficiency is low, there is not the mechanism of failover in poor fault tolerance. From Redis, readWhen task queue data, because contention data between each task processor may cause deadlock. Crontab joinsPutting is all independent writing on corresponding server, along with the refinement of service and the increase of task quantity, rightThe management of plan target becomes increasingly complex. And crontab is not to the plan target of moving reasonablyMonitoring mechanism. When server delay machine or have a power failure original task transfers cannot be completed to other servers.Mapduce Computational frame is to belong to off-line batch processing system, and the data of Mapduce Computational frame must be firstStorage, could computing, and storage and computing can not parallel runnings, do not support real-time processing.
Summary of the invention
Technical problems to be solved in this application are to provide the task of concentrating type to send system, and its feature existsSend platform, multiple JVM container and at least one JVM container in comprising instruction. Platform is sent in instructionSee through network by many task servers and interconnect, in these task servers, dispose zookeeperService, zookeeper service is returned to operating instruction according to mission requirements; Each JVM container is for operationOne business service, there is JVM container and affiliated business service in different operating instruction correspondences; At least oneNode server, node server is used for receiving mission requirements, and node server receives and comes from instruction tuneSend the operating instruction of platform or transmit transmission instruction to instruction and send platform, each node server arranges jointPoint numbering, bulk encoding and address information, node server is according to these of task search corresponding serviceJVM container, sends platform by these searched JVM containers to instruction and obtains operating instruction; NodeServer judges whether the load condition of the JVM container of obtaining operating instruction is idle or busy, if loadState is idle, and JVM container is processed mission requirements according to operating instruction, if load condition isBusy, node server is temporary in operating instruction in waiting list.
Compared with prior art, the application, can based on the coordination service of Zookeeper distributed application programFor ever-increasing task quantity, the more and more task definition of refinement, the task management becoming increasingly complexSituation under obtain and comprise following technique effect:
1) multiserver task scheduling, different business is distributed on different server and carries out, when task quantityWhen too high, can carry out concomitantly, improve execution efficiency. Trunking mode storage instruction, if whereinOne station server breaks down, and can ensure that other servers provide continual service, can not break down because of oneServer, and cause whole system collapse, guarantee reliable, stable in the process of implementation.
2) in the time having new task to carry out, can manually increase the association attributes of configuration node container,The operational order of expansion platform, further refinement service content. Scheduler program can pass through container name simultaneouslyClaim, to instruction fetch in Zookeeper instruction thesaurus, then select corresponding container to enter according to command contentLine operate, can not cause the unavailable of system because of contention resource.
3) can be in real time monitor moving of task, abnormal task, start and stop at any time, ignoreOr rerun task.
4) before task run, can extract the data of separate sources, form and feature, change,Load, be put in waiting list, reduce the memory space of wrong data.
Certainly, arbitrary product of enforcement the application must not necessarily need to reach above-described all skills simultaneouslyArt effect.
Brief description of the drawings
Accompanying drawing described herein is used to provide further understanding of the present application, forms of the applicationPoint, the application's schematic description and description is used for explaining the application, does not form the application'sImproper restriction.
Fig. 1 is the configuration diagram that the task of the application's concentrating type is sent system.
Fig. 2 is the business schematic diagram of the application's instruction each module of sending platform.
Fig. 3 is the operation workflow figure of the application's FastLeaderElection.
Fig. 4 is the operation workflow figure of the application's zookeeper service configuration.
Fig. 5 is the business schematic diagram of the application's instruction each module of sending platform.
Detailed description of the invention
Below please coordinate drawings and Examples to describe the application's embodiment in detail, by this to the applicationThe implementation procedure how application technology means solve technical problem and reach technology effect can fully understand alsoImplement according to this.
Please refer to shown in Figure 1A and Figure 1B, it is the frame that the task of the application's concentrating type is sent systemStructure schematic diagram and principal and subordinate's task server schematic diagram. The task system of sending of the application's concentrating type comprises fingerPlatform 110, at least one node server 120 and JVM container 130 are sent in order. Platform 110 is sent in instructionBe to see through network by many task servers 111 to interconnect, in these task servers 111, disposeZookeeper service 112, zookeeper service 112 is returned to operating instruction according to mission requirements. Node clothesThe configurable multiple JVM containers 130 of business device 120. Each JVM container 130 is for moving business clothesBusiness, there is JVM container 130 and affiliated business service in different operating instruction correspondences. Node server120 for receiving mission requirements, and node server 120 receives the fortune that comes from instruction and send platform 110Row instruction or return send instruction to instruction send platform 110. Each node server 120 arranges nodeNumbering, bulk encoding and address information. Node server 120 is searched the JVM of corresponding service according to taskContainer 130, sends platform 110 by searched JVM container 130 to instruction and obtains operating instruction. AfterPlatform operator can be according to new task, manually increases quantity and the association attributes of node server 120.
Platform 110 is sent in instruction provides storage or the Message Processing of zookeeper service 112, message queueService etc. Instruction send platform 110 can see through distributed ETL (Extract, transformandload,Being called for short ETL) system realizes. For distinguishing the difference of entity machine and service, solid line right angle side in the drawingsThe service providing is provided piece, and solid line obtuse angle square represents entity machine.
These task servers 111 are more divided into monitoring module 1111, nucleus module according to function1112, card module 1113 and metadata management module 1114. Please coordinate shown in Fig. 2, it is thisThe business schematic diagram of each module of platform is sent in the instruction of application. Monitoring module 1111 is for monitoring this instructionWhether the working procedure of sending platform 110 is abnormal, when particularly between server operation, abnormal monitoring is with operationHistorical query.
Nucleus module 1112 for the message transmission between scheduling controlling instruction and those task servers 111 withException management and log management. Nucleus module 1112 use whats are looked into Consultation joint and are taken the JVM container that Service device matches130, And what zookeeper serve 112 Zhong huo instruction fetch, then instruction is put into and waited for waiting list.Nucleus module 1112 also can judge whether current task completes. If task completes, nucleus module 1112Finish this scheduling. Otherwise, nucleus module 1112 instruction of packing, nucleus module 1112 deposits instruction inIn zookeeper service 112, wait for and obtain next step operation. Metadata management module 1114 is for jointConfiguration, the configuration of external resource, the configuration of business scenario, the ETL step of some configuration, operation container are joinedPut, JAR wraps version management.
Card module 1113 is for the file transfer between server, file to storehouse, and storehouse is to storehouse, and storehouse is to literary compositionPart, file discovery, file transfer, data processing, Kettle process, streaming is calculated (StreamComputing)With file warehousing. Card module 1113 is for monitoring in real time long-range ftp server, by the road of fileFootpath, timing scan. Whether card module 1113 changes to judge long-range according to the modification time of fileWhether the file on ftp server has variation. If there is variation, takes out and put into database, by plug-in unit mouldPiece 1113 dispatch commands are determined next step operation. If not variation, card module 1113 continues prisonControl. Card module 1113 is for the number between home server, between home server and remote serverReportedly pass (upload, download etc.).
Wherein, host-host protocol comprises FTP (FileTransferProtocol, FTP), safety literary compositionPart host-host protocol (SecureFileTransferProtocol, SFTP) and SCTP (StreamControlTransmissionProtocol, SCTP). Card module 1113 is also for the treatment of file, rightThe business logic processing such as data are screened, merged, statistics. Kettle processes, and calls third party and increases incomeETL instrument (Kettle) carry out data processing. Kettle is divided into 4 bulks: Chef, Kitchen, SpoonWith Span. Chef-work (job) design tool (GUI mode), Kitchen-work (job) actuator (lifeMake line mode); Spoon-conversion (transform) design tool (GUI mode); Span-conversion(trasform) actuator (command line mode). Download Kettle compressed package in official website, decompress(ion), below executionScript: cdKettle; Chmod+x*.sh; Start graphic user interface Spoon, establishing resource storehouse, establishesMeter, operation conversion and operation.
Instruction is sent platform 110 except providing aforesaid service, separately disposes zookeeper service 112.Zookeeper service 112 is for selecting one as main task server from many task servers 111211, other not choosing is from task server 212. If dispose zookeeper service 112 and rightOuter net provides service, and needing in more than half task services is can normally move and can intercom mutually.In other words,, in existing in the situation of X platform task server 111, must dispose and be greater than appointing of (1+X/2) platformBusiness server 111, guarantee zookeeper service 112 can normally move. Those task servers111 see through a FastLeaderElection algorithm puts forward this main task server 211 mutually.The election mode of FastLeaderElection algorithm comprises the following steps, and please refer to shown in Fig. 3:
Step S310: elect oneself as candidate's task server by arbitrary task server, and notify itHis task server;
Step S320: other task servers are obtained after the notice of candidate's task server, task serverSelect whether agree to candidate server according to oneself state, and will select message passbackGive candidate's task server;
Step S330: whether the poll that candidate's task server is added up effective task server exceedes halfNumber;
Step S340: if exceed half, be new main task server by candidate's task server; WithAnd
Step S350: if position exceedes half, again select candidate's task server and walk accordinglySuddenly.
First, elect oneself as candidate's task server by arbitrary task server 111. Candidate's taskServer the pack server ID, the logic clock (logicalclock) that carry or watch state (looking), andTransmit described information to other task servers 111. Obtaining candidate at other task servers 111 appointsAfter the message status of business server, if when the state of watching of task server 111 own is activation, taskServer 111 also can return to the message status of self to candidate's task server.
Candidate's task server can judge task server 111 according to the logic clock of received message statusWhether be the polling server of suitable lattice. If be the task server 111 of suitable lattice, candidate server meetingBe effective by this poll. If the task server of uncomfortable lattice 111, described task server111 can not be recorded among effective ballot. When the poll of all ballots is greater than the task clothes that can voteThe half of the quantity of business device 111, elects candidate's task server 111 for main task server 211. InsteadIt, when the discontented half of ballot quantity, can re-execute step S310～S350, until select oneTill main task server 211.
Now, disposes zookeeper service 112 to the task server of each 111. Configuration zookeeperThe mode of service 112 please refer to shown in Fig. 4, and it is to comprise the following steps:
Step S410: main task server preloads the relative program of zookeeper service;
Step S420: the installation procedure of being served by main task server remote copy zookeeper is extremely from appointingBusiness server;
Step S430: from the installation procedure of task server operation zookeeper service and according to serverState information so that set the numbering of zookeeper service; And
Step S440: start zookeeper service from task server, and return to main task server.
Send platform 110 when instruction and complete after zookeeper service 112, it is saturating that platform 110 is sent in instructionCross task-scheduling operation, task-scheduling operation is for the treatment of the message queue of zookeeper service 112New client task. Complete instruction and send after the deployment of zookeeper service 112 of platform 110, jointPoint server 120 can start to receive the mission requirements from client. Please refer to Fig. 5, it is thisThe operation workflow figure that the mission requirements and instruction of application generates. The application's instruction generation and scheduling comprise withLower step:
Step S510: node server receives the mission requirements of client;
Step S520: node server is packaged as transmission instruction mission requirements, and forward sending instructionSend platform to instruction;
Step S530: instruction is sent platform and searched the JVM container of alignment processing according to sending instruction;
Step S540: the load condition that platform judges that JVM container is current is sent in instruction;
Step S550: if the load condition of JVM container is idle, JVM container is according to operating instructionMission requirements is processed; And
Step S560: if the load condition of JVM container is busy, node server refers to this operationOrder is temporary in waiting list, until the load condition of JVM container is idle.
Many node servers 120 are set, and task distribution is carried out at different node server 120Operation. In node configuration, introduce dispensing containers, each node correspondence multiple containers, for programMatched and searched. Node server 120 after obtaining the mission requirements of client, node server 120Mission requirements is packaged as to transmission instruction, and is forwarded to instruction and sends platform 110 sending an instruction. InstructionSend the zookeeper service 112 of platform 110 and search the JVM container 130 that has or not alignment processing.
If there is the JVM container 130 of corresponding with service, zookeeper service 112 further judges JVMThe load condition that container 130 is current. Described load condition refers to the operation of JVM container 130 and bearsCarry. In the time that the running load of JVM container 130 is too high, zookeeper service 112 can be held JVMThe load condition of device 130 is considered as busy. Otherwise zookeeper service 112 is defined as sky load conditionNot busy. If JVM container 130 is in the time of the free time, zookeeper service 112 requires JVM container130 process operating instruction. If JVM container 130 is when busy, zookeeper serves 112Operating instruction is temporary in waiting list, until the load condition of JVM container 130 changes to the free time.
Described device is corresponding with aforesaid method flow description, and weak point is chatted with reference to said method flow processState, repeat no longer one by one. Above-mentioned explanation illustrates and has described some preferred embodiments of the application, but asBefore described in, be to be understood that the application is not limited to disclosed herein form, should not regard as otherThe eliminating of embodiment, and can be used for various other combinations, amendment and environment, and can be at described hereinIn bright contemplated scope, change by technology or the knowledge of above-mentioned instruction or association area. And this areaThe spirit and scope that the change that personnel carry out and variation do not depart from the application, all should be appended in the applicationIn the protection domain of claim.
Claims (9)
1. the task of concentrating type is sent a system, it is characterized in that comprising:
Platform is sent in one instruction, sees through network and interconnects, in those tasks by many task serversIn server, dispose zookeeper service, this zookeeper service is returned to a fortune according to a mission requirementsRow instruction;
Multiple JVM containers, each this JVM container is used for moving a business service, this different fortuneRow instruction is corresponding there is this JVM container and affiliated this business service; And
At least one node server, this node server is used for receiving this mission requirements, this node serviceDevice reception comes from this instruction sends this operating instruction of platform or transmits transmission instruction to this instruction and adjustSend platform, each this node server arranges a node serial number, a bulk encoding and an address information,This node server is searched those JVM containers of corresponding service according to this task, by searched thoseJVM container is sent platform to this instruction and is obtained this operating instruction;
Wherein, this node server judgement obtains a load condition of this JVM container of this operating instructionWhether be idle or busy, if this load condition is idle, this JVM container is according to this operating instructionThis mission requirements is processed, if this load condition is busy, this node server is this operationInstruction is temporary in a waiting list.
2. the task of concentrating type is as claimed in claim 1 sent system, it is characterized in that this node server is realTime detect a load condition of those JVM containers, when this load condition of this JVM container is in skyIdle, this node server takes out operating instruction be sent to this JVM from this waiting list to be heldDevice.
3. the task of concentrating type is as claimed in claim 1 sent system, it is characterized in that those task serversMore divide into a monitoring module, a nucleus module, a card module and monobasic data management module.
4. the task of concentrating type is as claimed in claim 3 sent system, it is characterized in that this monitoring module forWhether monitoring this instruction, to send the working procedure of platform abnormal.
5. the task of concentrating type is as claimed in claim 3 sent system, it is characterized in that this nucleus module forDispatch message transmission and exception management between a control instruction and those task servers.
6. the task of concentrating type is as claimed in claim 3 sent system, it is characterized in that this card module forFile transfer, file between server arrive storehouse, and storehouse is to storehouse, and storehouse is to file, file discovery, fileTransmission, data processing, Kettle process, streaming is calculated (StreamComputing) and file warehousing.
7. the task of concentrating type is as claimed in claim 1 sent system, it is characterized in that this metadata management mouldPiece for the configuration of the configuration of the configuration of node configuration, operation container, external resource, business scenario,ETL arrangements of steps, JAR wrap version management.
8. the task of concentrating type is as claimed in claim 1 sent system, it is characterized in that this node server existsIn this operating instruction scheduling, occur extremely, this node server is temporary in an abnormal team this operating instructionIn row, until after described abnormal releasing, this node server is fetched this operation and referred to from this abnormal queueOrder.
9. the task of concentrating type is as claimed in claim 1 sent system, it is characterized in that from those task servicesIn device, select one and be assigned as a main task server, other is from task server, wherein those task clothesBusiness device sees through a FastLeaderElection algorithm and mutually puts forward this main task server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610072921.8A CN105610972B (en) | 2016-02-01 | 2016-02-01 | The task of concentrating type sends system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610072921.8A CN105610972B (en) | 2016-02-01 | 2016-02-01 | The task of concentrating type sends system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105610972A true CN105610972A (en) | 2016-05-25 |
| CN105610972B CN105610972B (en) | 2019-04-09 |
Family
ID=55990506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610072921.8A Active CN105610972B (en) | 2016-02-01 | 2016-02-01 | The task of concentrating type sends system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105610972B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106095483A (en) * | 2016-05-31 | 2016-11-09 | 乐视控股（北京）有限公司 | The Automation arranging method of service and device |
| CN106790595A (en) * | 2016-12-29 | 2017-05-31 | 上海理想信息产业（集团）有限公司 | A kind of Docker containers active load balancer and method |
| CN107229830A (en) * | 2017-06-01 | 2017-10-03 | 上海联影医疗科技有限公司 | Radiotherapy planning system and its task executing method |
| CN107479683A (en) * | 2017-08-15 | 2017-12-15 | 爱普（福建）科技有限公司 | A kind of serial computing method towards configuration software |
| CN107562525A (en) * | 2017-07-18 | 2018-01-09 | 东莞理工学院 | A Cooperative Scheduling Method Between Heterogeneous Platforms of Remote Sensing Image Processing |
| CN107844339A (en) * | 2017-11-15 | 2018-03-27 | 湖北盛天网络技术股份有限公司 | Method for scheduling task and plug-in unit and server |
| CN108614820A (en) * | 2016-12-09 | 2018-10-02 | 腾讯科技（深圳）有限公司 | The method and apparatus for realizing the parsing of streaming source data |
| CN108833532A (en) * | 2018-06-13 | 2018-11-16 | 中国联合网络通信集团有限公司 | Service processing method, device and system based on internet of things |
| CN108897627A (en) * | 2018-07-23 | 2018-11-27 | 南京叠嘉信息科技有限公司 | For the Docker dynamic dispatching algorithm of exemplary container |
| CN109286681A (en) * | 2018-11-08 | 2019-01-29 | 合肥帧讯软件有限公司 | Data exchange service software |
| CN109471727A (en) * | 2018-10-29 | 2019-03-15 | 北京金山云网络技术有限公司 | A task processing method, device and system |
| CN109600421A (en) * | 2018-11-16 | 2019-04-09 | 国网江苏省电力有限公司南京供电分公司 | The selection method of distributed computing resource in a kind of wireless cloud computing system |
| CN111352750A (en) * | 2020-03-04 | 2020-06-30 | 云南电网有限责任公司电力科学研究院 | Method and system for identifying multi-source image defect hidden danger of power transmission line |
| CN111459674A (en) * | 2020-03-31 | 2020-07-28 | 珠海格力电器股份有限公司 | Distributed service management method and system |
| CN111722981A (en) * | 2020-06-15 | 2020-09-29 | 武汉达梦数据库有限公司 | A real-time monitoring method and device for Hadoop cluster running ETL process |
| CN111782294A (en) * | 2020-06-28 | 2020-10-16 | 珠海豹趣科技有限公司 | Application program running method and device, electronic equipment and storage medium |
| CN111813573A (en) * | 2020-06-29 | 2020-10-23 | 中国平安人寿保险股份有限公司 | Communication method of management platform and robot software and related equipment thereof |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101719082A (en) * | 2009-12-24 | 2010-06-02 | 中国科学院计算技术研究所 | Method and system for dispatching application requests in virtual calculation platform |
| CN105159767A (en) * | 2015-09-06 | 2015-12-16 | 北京京东尚科信息技术有限公司 | Method and device for realizing distributed scheduling on the basis of zookeeper |
| US20160004450A1 (en) * | 2014-07-02 | 2016-01-07 | Hedvig, Inc. | Storage system with virtual disks |
-
2016
- 2016-02-01 CN CN201610072921.8A patent/CN105610972B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101719082A (en) * | 2009-12-24 | 2010-06-02 | 中国科学院计算技术研究所 | Method and system for dispatching application requests in virtual calculation platform |
| US20160004450A1 (en) * | 2014-07-02 | 2016-01-07 | Hedvig, Inc. | Storage system with virtual disks |
| CN105159767A (en) * | 2015-09-06 | 2015-12-16 | 北京京东尚科信息技术有限公司 | Method and device for realizing distributed scheduling on the basis of zookeeper |
Non-Patent Citations (1)
| Title |
|---|
| 许令波: "分布式服务框架 Zookeeper -- 管理分布式环境中的数据", 《HTTPS://WWW.IBM.COM/DEVELOPERWORKS/CN/OPENSOURCE/OS-CN-ZOOKEEPER/》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106095483A (en) * | 2016-05-31 | 2016-11-09 | 乐视控股（北京）有限公司 | The Automation arranging method of service and device |
| CN108614820B (en) * | 2016-12-09 | 2021-01-15 | 腾讯科技（深圳）有限公司 | Method and device for realizing streaming source data analysis |
| CN108614820A (en) * | 2016-12-09 | 2018-10-02 | 腾讯科技（深圳）有限公司 | The method and apparatus for realizing the parsing of streaming source data |
| CN106790595A (en) * | 2016-12-29 | 2017-05-31 | 上海理想信息产业（集团）有限公司 | A kind of Docker containers active load balancer and method |
| CN107229830A (en) * | 2017-06-01 | 2017-10-03 | 上海联影医疗科技有限公司 | Radiotherapy planning system and its task executing method |
| CN107562525A (en) * | 2017-07-18 | 2018-01-09 | 东莞理工学院 | A Cooperative Scheduling Method Between Heterogeneous Platforms of Remote Sensing Image Processing |
| CN107562525B (en) * | 2017-07-18 | 2020-05-26 | 东莞理工学院 | Cooperative scheduling method between remote sensing image processing heterogeneous platforms |
| CN107479683B (en) * | 2017-08-15 | 2019-12-20 | 爱普（福建）科技有限公司 | Serial computing method oriented to configuration software |
| CN107479683A (en) * | 2017-08-15 | 2017-12-15 | 爱普（福建）科技有限公司 | A kind of serial computing method towards configuration software |
| CN107844339B (en) * | 2017-11-15 | 2021-07-30 | 湖北盛天网络技术股份有限公司 | Task scheduling method, plug-in and server |
| CN107844339A (en) * | 2017-11-15 | 2018-03-27 | 湖北盛天网络技术股份有限公司 | Method for scheduling task and plug-in unit and server |
| CN108833532B (en) * | 2018-06-13 | 2021-11-30 | 中国联合网络通信集团有限公司 | Service processing method, device and system based on Internet of things |
| CN108833532A (en) * | 2018-06-13 | 2018-11-16 | 中国联合网络通信集团有限公司 | Service processing method, device and system based on internet of things |
| CN108897627A (en) * | 2018-07-23 | 2018-11-27 | 南京叠嘉信息科技有限公司 | For the Docker dynamic dispatching algorithm of exemplary container |
| CN109471727B (en) * | 2018-10-29 | 2021-01-22 | 北京金山云网络技术有限公司 | Task processing method, device and system |
| CN109471727A (en) * | 2018-10-29 | 2019-03-15 | 北京金山云网络技术有限公司 | A task processing method, device and system |
| CN109286681A (en) * | 2018-11-08 | 2019-01-29 | 合肥帧讯软件有限公司 | Data exchange service software |
| CN109600421A (en) * | 2018-11-16 | 2019-04-09 | 国网江苏省电力有限公司南京供电分公司 | The selection method of distributed computing resource in a kind of wireless cloud computing system |
| CN109600421B (en) * | 2018-11-16 | 2021-02-26 | 国网江苏省电力有限公司南京供电分公司 | Method for selecting distributed computing resources in wireless cloud computing system |
| CN111352750A (en) * | 2020-03-04 | 2020-06-30 | 云南电网有限责任公司电力科学研究院 | Method and system for identifying multi-source image defect hidden danger of power transmission line |
| CN111352750B (en) * | 2020-03-04 | 2023-08-18 | 云南电网有限责任公司电力科学研究院 | A method and system for hidden danger identification of multi-source image defects in transmission lines |
| CN111459674A (en) * | 2020-03-31 | 2020-07-28 | 珠海格力电器股份有限公司 | Distributed service management method and system |
| CN111722981A (en) * | 2020-06-15 | 2020-09-29 | 武汉达梦数据库有限公司 | A real-time monitoring method and device for Hadoop cluster running ETL process |
| CN111722981B (en) * | 2020-06-15 | 2021-05-07 | 武汉达梦数据库有限公司 | A real-time monitoring method and device for Hadoop cluster running ETL process |
| CN111782294A (en) * | 2020-06-28 | 2020-10-16 | 珠海豹趣科技有限公司 | Application program running method and device, electronic equipment and storage medium |
| CN111813573A (en) * | 2020-06-29 | 2020-10-23 | 中国平安人寿保险股份有限公司 | Communication method of management platform and robot software and related equipment thereof |
| CN111813573B (en) * | 2020-06-29 | 2022-09-20 | 中国平安人寿保险股份有限公司 | Communication method of management platform and robot software and related equipment thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105610972B (en) | 2019-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105610972A (en) | Clustered task dispatching system | |
| CN115328663B (en) | Method, device, equipment and storage medium for scheduling resources based on PaaS platform | |
| CN102880475B (en) | Based on the real-time event disposal system of cloud computing and method in computer software | |
| US8584136B2 (en) | Context-aware request dispatching in clustered environments | |
| US9569289B2 (en) | Generic distributed processing for multi-agent systems | |
| CN101571813B (en) | A master-slave scheduling method in a multi-machine cluster | |
| CN106375241B (en) | Batch data processing method, front-end system, host and batch data processing system | |
| CN113691611B (en) | Distributed high-concurrency transaction processing method, system, device, and storage medium of a blockchain | |
| US20240118935A1 (en) | Pod deployment method and apparatus | |
| US20150215394A1 (en) | Load distribution method taking into account each node in multi-level hierarchy | |
| CN108063813B (en) | Method and system for parallelizing password service network in cluster environment | |
| CN109918230A (en) | A kind of business board abnormal restoring method and system | |
| CN102571568B (en) | Task processing method and device | |
| CN103414712A (en) | Management system and method of distributed virtual desktop | |
| CN106817408A (en) | A kind of distributed server cluster dispatching method and device | |
| US8606908B2 (en) | Wake-up server | |
| CN104081355A (en) | Software bus | |
| CN104038390A (en) | Linux server cluster unified peripheral event monitoring method based on netlink | |
| CN105373563B (en) | Database switching method and device | |
| CN118509488A (en) | Terminal calculation power nano-tube method, platform, electronic equipment and storage medium | |
| CN104052677A (en) | Soft load balancing method and apparatus of single data source | |
| CN109257396A (en) | A kind of distributed lock dispatching method and device | |
| CN1694448A (en) | Methods, systems for disseminating status information to users of computer resources | |
| CN110365786A (en) | Job processing system, asynchronous operation dispatching method and computer equipment | |
| US20060224699A1 (en) | Methods and system for event transmission |
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 |