CN107463434A - Distributed task processing method and device - Google Patents
Distributed task processing method and device Download PDFInfo
- Publication number
- CN107463434A CN107463434A CN201710686163.3A CN201710686163A CN107463434A CN 107463434 A CN107463434 A CN 107463434A CN 201710686163 A CN201710686163 A CN 201710686163A CN 107463434 A CN107463434 A CN 107463434A
- Authority
- CN
- China
- Prior art keywords
- container
- language
- asynchronous
- run
- resources
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/466—Transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/54—Interprogram communication
- G06F9/542—Event management; Broadcasting; Multicasting; Notifications
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Devices For Executing Special Programs (AREA)
Abstract
The application aims to provide a distributed task processing method and equipment. Compared with the prior art, the method and the device have the advantages that the tasks to be processed are obtained through the distributed real-time message bus, the tasks to be processed are forwarded to the language runtime container, the language runtime container is utilized to execute the tasks to be processed, wherein, in the execution process, when the condition of parallel processing of asynchronous services occurs, a plurality of asynchronous call requests are respectively sent to the computing service component container and the resource service component container through the distributed real-time message bus, then, utilizing the language runtime container to receive and process the processing result of the computing service component container and the resource service component container for the asynchronous call request until the task to be processed is executed, therefore, the service processing capacity of the system is improved, the processing time of the complex service logic of the mobile interconnection scene is reduced, and low-delay response is achieved.
Description
Technical field
The application is related to computer realm, more particularly to a kind of distributed task scheduling treatment technology.
Background technology
Rise in that the big data correlation technique developed recently of internet is swift and violent, and in order to optimize Consumer's Experience, all trades and professions are all
It is necessary to use big data skill upgrading own service ability.By taking financial industry as an example, the IT application center of gravity of traditional bank is
From providing the depositing of standardization, borrowing, the standard products transactions service such as pay, it is increasingly turned to using mobile interchange equipment as main channel, according to
The main trend that data of giving oneself airs and intellectual technology provide individual scene service for client proposes.Compared to traditional Net silver application and hand
Machine Bank application, the requirement of mobile interchange scene application have following new feature:
1) passive response switchs to active predicting.Not only passive response, Er Qieyao are made in the transaction to client and information inquiry
The navigation patterns data of client are gathered at any time, integrate the newest transaction of each channel customer and other interaction datas, prediction client's production
Product and demand for services, the click behavior of client is followed to release the product and information of personalization in time.
2) real time mass.In real time from magnanimity such as the geographical position of Smartphone device or other wearable devices collection client
Device data, consumption preferences and subdivision crowd demand with reference to client, recommends the non-financial service of suitable third party, guides bank attached
Near site and self-service device service.
3) deepening continuously with displaying application, bank not only need collecting and processing lifting clothes on magnanimity new data
Business is horizontal, and the contact relation of client and bank will be no longer limited to Financial Demands, but the every aspect comprising clothing, food, lodging and transportion -- basic necessities of life, silver
Row there will be an opportunity to take advantage of own resource configuration of superiorities, there is provided it is more high-quality and timely financial service while, there is provided more fully
Comprehensive service for life.
Under such a big business background, the data service capabilities that bank's IT system needs to provide will improve than ever
Hundred times even thousand times.Therefore, it is necessary with distributed task scheduling treatment technology lifting traffic handing capacity.
The content of the invention
The purpose of the application is to provide a kind of distributed task scheduling processing method and equipment.
According to the one side of the application, there is provided a kind of distributed task scheduling processing method, wherein, this method includes:
Waiting task is obtained by distributed real-time messages bus, when the waiting task is forwarded into language operation
Container;
Container performs the waiting task when being run using the language, wherein, it is in the process of implementation, asynchronous when occurring
The situation of the parallel processing of service, by the distributed real-time messages bus respectively to calculating class serviced component container, resource
Class serviced component container initiates multiple asynchronous call requests;
Container reception and the calculating class serviced component container and resources-type clothes is handled when being run using the language
The result that business assembly container is asked for the asynchronous call, until the waiting task performs completion.
According to further aspect of the application, there is provided a kind of distributed task scheduling processing equipment, wherein, the equipment includes:
First device, for obtaining waiting task by distributed real-time messages bus, the waiting task is turned
Container when being sent to language operation;
Second device, for performing the waiting task using container during language operation, wherein, in implementation procedure
In, when the situation for the parallel processing of asynchronous service occur, by the distributed real-time messages bus respectively to calculating class service
Assembly container, resources-type serviced component container initiate multiple asynchronous call requests;
3rd device, during for being run using the language container reception and handle the calculating class serviced component container and
The result that the resources-type serviced component container is asked for the asynchronous call, until the waiting task has performed
Into.
According to the another aspect of the application, there is provided a kind of electronic equipment, including at least processor and memory cell, institute
Processor is stated to be configured to perform to give an order:
Waiting task is obtained by distributed real-time messages bus, when the waiting task is forwarded into language operation
Container;
Container performs the waiting task when being run using the language, wherein, it is in the process of implementation, asynchronous when occurring
The situation of the parallel processing of service, by the distributed real-time messages bus respectively to calculating class serviced component container, resource
Class serviced component container initiates multiple asynchronous call requests;
Container reception and the calculating class serviced component container and resources-type clothes is handled when being run using the language
The result that business assembly container is asked for the asynchronous call, until the waiting task performs completion.
Compared with prior art, the application obtains waiting task by distributed real-time messages bus, waits to locate by described
Container when reason task is forwarded to language operation, container performs the waiting task when being run using the language, wherein, holding
During row, when the situation for the parallel processing of asynchronous service occur, by the distributed real-time messages bus respectively to calculating
Class serviced component container, resources-type serviced component container initiate multiple asynchronous call requests, then, when being run using the language
Container reception simultaneously handles the calculating class serviced component container and the resources-type serviced component container for the asynchronous call
The result of request, until the waiting task performs completion, so as to the traffic handing capacity of lifting system, reduce movement
The processing time of scene complicated business logic is interconnected, accomplishes that low delay responds.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 shows a kind of distributed task scheduling process flow figure according to the application one embodiment;
Fig. 2 shows the program operation logic figure handled according to a kind of distributed task scheduling of one preferred embodiment of the application;
Fig. 3 shows a kind of distributed task scheduling process flow figure according to another embodiment of the application;
Fig. 4 shows a kind of distributed task scheduling processing equipment schematic diagram according to the application one embodiment;
Fig. 5 shows a kind of distributed task scheduling processing equipment schematic diagram according to another embodiment of the application.
Same or analogous reference represents same or analogous part in accompanying drawing.
Embodiment
The application is described in further detail below in conjunction with the accompanying drawings.
In one typical configuration of the application, terminal, the equipment of service network and trusted party include one or more
Processor (CPU), input/output interface, network interface and internal memory.
Internal memory may include computer-readable medium in volatile memory, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM).Internal memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moved
State random access memory (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, magnetic disk storage or other magnetic storage apparatus or
Any other non-transmission medium, the information that can be accessed by a computing device available for storage.Defined according to herein, computer
Computer-readable recording medium does not include non-temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
Fig. 1 shows to be included according to a kind of distributed task scheduling process flow figure of the application one embodiment, this method
Step S11, step S12 and step S13.
Specifically, in step S11, equipment 1 obtains waiting task by distributed real-time messages bus, waits to locate by described
Container when reason task is forwarded to language operation;In step S12, wait to locate described in container execution when equipment 1 is run using the language
Reason task, wherein, in the process of implementation, when the situation for the parallel processing of asynchronous service occur, disappeared in real time by the distribution
Cease bus and initiate multiple asynchronous calls requests to calculating class serviced component container, resources-type serviced component container respectively;Step S13
In, container reception and handle the calculating class serviced component container and resources-type clothes when equipment 1 is run using the language
The result that business assembly container is asked for the asynchronous call, until the waiting task performs completion.
Here, the equipment 1, which includes but is not limited to the network equipment, is integrated formed equipment by network.Wherein, institute
Stating the network equipment includes a kind of electricity that according to the instruction for being previously set or storing, can carry out numerical computations and information processing automatically
Sub- equipment, its hardware include but is not limited to microprocessor, application specific integrated circuit (ASIC), programmable gate array (FPGA), numeral
Processor (DSP), embedded device etc..The network equipment its include but is not limited to computer, network host, single network clothes
The cloud that business device, multiple webserver collection or multiple servers are formed;Here, cloud is by based on cloud computing (Cloud
Computing a large amount of computers or the webserver) are formed, wherein, cloud computing is one kind of Distributed Calculation, by a group pine
Dissipate a virtual supercomputer of the computer collection composition of coupling.The network includes but is not limited to internet, wide area network, city
Domain net, LAN, VPN, wireless self-organization network (Ad Hoc networks) etc..Preferably, the equipment 1 can also be operation
Shell script on the network equipment.Certainly, those skilled in the art will be understood that the said equipment 1 is only for example, other
Equipment 1 that is existing or being likely to occur from now on is such as applicable to the application, should also be included within the application protection domain, and
This is incorporated herein by reference.
Preferably, container, the calculating class serviced component container and the resources-type serviced component during language operation
Container is realized based on Akka micro services software frame.
Here, by software platform based on the Akka micro services software frame, have the following advantages that:(1) role
(Actor) concurrency programming model preferably shields bottom communication details and thread task scheduling details, and programming is easier to.(2)
Performance is high, and single node is per second to complete 50,000,000 Message Processings.(3) resource requirement is low, and 2,500,000 Actor can be accommodated per GB internal memories
Entity object.(4) maturity is higher, is the bottom architecture software of Spark big data platforms, and JAX innovations were obtained in 2015 and are opened
Send out prize for technical achievement.(5) write based on powerful Scala language, coding realizes efficiency high, can be with other JVM language class libraries phases
Mutually call.(6) the gossip cluster communication agreements of amazon Dynamo systems are derived from, by amazon cloud service platforms
Long-term technology verifies that reliability is high;Cluster Sharding, Cluster Singleton, Distributed can be supported
The colony application scenarios such as Publish Subscribe, Distributed Data.(7) father and son's character object (Actor)
Regulator (Supervisor) pattern, father's character object, which can capture the exception of sub- character object and perform automatically, different restarts
Strategy, the fault-tolerance and service availability of system are greatly improved, reduce high availability written in code difficulty.(8) software is passed through
Router (router) and perform distributor (dispatcher) combination and realize that a variety of Actor are concurrent and load-balancing algorithm plan
Slightly.Such as polling dispatching (round robin), random schedule (random), broadcast (broadcast), uniformity Hash
(Consistent Hashing) etc..
Certainly, those skilled in the art will be understood that above-mentioned Akka micro services software frame (referring to www.akka.io) only
To illustrate, other micro services software frames that are existing or being likely to occur from now on, such as (one is based on Chrome to Node.Js
The platform that JavaScript is established when running, for the network application easily built fast response time, be easy to extension),
Finagle (Twitter is based on the RPC frameworks that support that Netty is developed is fault-tolerant, agreement is unrelated), (one is used Scala to Akka
The storehouse write, fault-tolerant, high scalability Java and Scala Actor models application is write for simplifying), RxJava (one
The individual response type expanding library realized on a java virtual machine, there is provided the asynchronous call and base realized based on observable sequences
In event programme), Vert.x (one based on JVM, lightweight, high performance application platform) etc., be such as applicable to the application,
It should be included within the application protection domain, and be incorporated herein by reference herein.
In step S11, equipment 1 obtains waiting task by distributed real-time messages bus, by the waiting task
Container when being forwarded to language operation.
Here, communication is realized by the distributed real-time messages bus.Container can be based on during the language operation
The Actor of Akka micro services software frames is realized.
Preferably, in step S11, equipment 1 obtains the pending of user equipment transmission by distributed real-time messages bus
Task.
Here, the user equipment includes but is not limited to:Smart mobile phone, the tablet personal computer of relative client are installed,
Open the computer of the Net silver page.For example, referring to Fig. 2, the web page resources of Web server can be obtained by the user equipment,
Establish the connection with the distributed real-time messages bus.Then, by the communication of the distributed real-time messages bus, obtain
The waiting task that the user equipment is sent.
Preferably, the waiting task includes remote service call request;Wherein, in step S11, equipment 1 is by dividing
Cloth real-time messages bus obtains remote service call request, and the remote service call request is converted into function call request
And container when being forwarded to language operation.
For example, referring to Fig. 2, the user equipment is initiated the remote service by the distributed real-time messages bus and adjusted
With request, after service broker receives the remote service call request, the remote service call request is first converted into letter
Number call request, then the function call request is forwarded to container when language is run.
In step S12, container performs the waiting task when equipment 1 is run using the language, wherein, performing
Cheng Zhong, when the situation for the parallel processing of asynchronous service occur, taken respectively to calculating class by the distributed real-time messages bus
Business assembly container, resources-type serviced component container initiate multiple asynchronous calls requests.
For example, container searches function definition during the language operation, program running example is created;Hold during the language operation
Device is mounted with distributed variable-frequencypump language interpreter, and the distributed variable-frequencypump language interpreter explains application code
And distributed parallel calls association service component to complete the waiting task to cooperate with;Preferably, at the distributed parallel
Language interpreter is managed by the specific markers in recognition application code, finds the situation of the parallel processing of asynchronous service.
Preferably, container when container is the operation of Zebra language during the language operation, the distributed variable-frequencypump language
Interpreter is Zebra language interpreters.
For example, referring to Fig. 2, Zebra language interpreters are performed Zebra script sentences by programming logic successively, are being held
During row, when the situation for the parallel processing of asynchronous service occur, while to calculate class component container A, resources-type assembly container
B, resources-type assembly container C initiates multiple asynchronous call requests, and the context (Context) of present procedure running example is switched
To the dormancy program example set for waiting micro services to call response.
Here, Zebra distributed variable-frequencypumps language supports distributed variable-frequencypump, and asynchronism callback can be handled very well and asked
Topic.Zebra language follows the design philosophy of MDA (Model Driven Architecture, executing model drive structure), can make
With different language and operation when container, in principle the business logic written in code of programmer once may operate in varying environment afterwards
(including departing from JVM), after carrying out suitable service abstraction, the optimization evolution of lower software framework will not have to business function code
Any influence.
Preferably, container performs the waiting task when being run using the language, including:Run using the language
When container syntax tree is parsed according to the pending task;Perform the syntax tree.
For example, container searches function definition during the Zebra language operation, the waiting task is resolved into Zebra
Syntax tree structure, create program running example.
Preferably, container is mounted with distributed variable-frequencypump language interpreter during the language operation;Wherein, described in execution
Syntax tree includes:During the syntax tree is performed, using the distributed variable-frequencypump language interpreter dynamic construction,
Perform and clear up sentence and perform tree.
If, can be by the present embodiment here, apply mechanically ANTLR father Terence Parr compiler language implementation pattern
The distributed variable-frequencypump language interpreter is referred to as the interpreter based on tree, and it is mainly based upon complete syntax tree and explained
Dynamic construction and cleaning sentence perform tree in implementation procedure, can effectively save memory source.Sentence performs tree and is considered as
It is the running example of syntax parsing tree object.
In step S13, when equipment 1 is run using the language container reception and handle it is described calculating class serviced component container
And the result that the resources-type serviced component container is asked for the asynchronous call, until the waiting task performs
Complete.
For example, container receives the calculating class serviced component appearance by the distributed message bus during language operation
The returning result of device and the resources-type serviced component container is simultaneously handled one by one, when handling each result message, the journey of association
Container (as shown in 7 in Fig. 2) when sort run example also switches back into operation, in corresponding syntax tree vertex ticks asynchronous call shape
State simultaneously is attempted to continue to perform backward, such as can not successively perform, then switch back into dormancy wait state.In the embodiment shown in Figure 2,
Until receiving complete (6-A), (6-B), (6-C) three result messages, program running example could continue down to hold without pausing
OK, whole call function logics and release procedure running example memory source are completed;Function implementing result is held when being run by Zebra
Device returns to service broker.
Preferably, methods described also includes:Equipment 1 will be waited to locate by the distributed real-time messages bus for described
The result of reason task is back to the user equipment.
For example, referring to Fig. 2, the user equipment initiates remote service calling by the distributed real-time messages bus please
Ask, after being disposed, service broker is by the distributed real-time messages bus by the processing knot of the remote service call request
Fruit is back to the user equipment.
Preferably, as shown in figure 3, methods described also includes step S14 ';In step S14 ', equipment 1 utilizes the calculating
Asynchronous call described in class serviced component container reception is asked, and the asynchronous call is asked into route distribution to calculating class component example
Perform, and the result asked for the asynchronous call is back to container when the language is run.
For example, referring to Fig. 2, calculate class component container A and receive service invocation request (4-A), directly forwarded by routeing
Container (6-A) when performing (4-A-1) to a component instance, and result being back into the operation of Zebra language.
Preferably, as shown in figure 3, methods described also includes step S15 ';In step S15 ', equipment 1 utilizes the resource
Asynchronous call described in class serviced component container reception is asked, and asynchronous call request is put into buffer queue, United Dispatching hair
The resources-type component instance for delivering to the free time is performed, and the result asked for the asynchronous call is back into the language
Container during operation.
For example, the asynchronous call received request is put into buffer queue by the resources-type serviced component container;If detection
Task can be distributed to the serviced component example for having idle, the resources-type serviced component container can ask the asynchronous call
Extracted from buffer queue;If detect in the absence of idle serviced component example, before no more than maximum instance number
Put, the resources-type serviced component container can also create new serviced component example with the task of distributing.
Preferably, the idle resources-type component instance performs the asynchronous call by following at least any one and asked
Ask:The resources-type component instance calls external web services to handle the asynchronous call and asked by asynchronous I/O;The resource
Class component example is asked by asynchronous call described in block type service call database service processing.
For example, referring to Fig. 2, resources-type assembly container B is connected to service invocation request (4-B), is put into inactive queue of task,
United Dispatching is sent to the component instance (4-B-1) of free time;Component instance calls external web services by asynchronous I/O and handled
Container (6-B) when result being back into the operation of Zebra language afterwards.Resources-type assembly container C is connected to service invocation request (4-C),
Inactive queue of task is put into, United Dispatching is sent to the component instance (4-C-1) of free time;Component instance passes through block type service
Container (6-C) when result being back into the operation of Zebra language after calling database service processing.
Fig. 4 shows a kind of distributed task scheduling processing equipment 1 according to the application one embodiment, wherein, equipment 1 includes the
One device 11, second device 12 and 3rd device 13.
Specifically, the first device 11 obtains waiting task by distributed real-time messages bus, waits to locate by described
Container when reason task is forwarded to language operation;Container performs described pending when the second device 12 is run using the language
Task, wherein, in the process of implementation, when the situation for the parallel processing of asynchronous service occur, pass through the distributed real-time messages
Bus initiates multiple asynchronous calls to calculating class serviced component container, resources-type serviced component container respectively asks;Described 3rd
Container reception and the calculating class serviced component container and resources-type service is handled when device 13 is run using the language
The result that assembly container is asked for the asynchronous call, until the waiting task performs completion.
Here, the equipment 1, which includes but is not limited to the network equipment, is integrated formed equipment by network.Wherein, institute
Stating the network equipment includes a kind of electricity that according to the instruction for being previously set or storing, can carry out numerical computations and information processing automatically
Sub- equipment, its hardware include but is not limited to microprocessor, application specific integrated circuit (ASIC), programmable gate array (FPGA), numeral
Processor (DSP), embedded device etc..The network equipment its include but is not limited to computer, network host, single network clothes
The cloud that business device, multiple webserver collection or multiple servers are formed;Here, cloud is by based on cloud computing (Cloud
Computing a large amount of computers or the webserver) are formed, wherein, cloud computing is one kind of Distributed Calculation, by a group pine
Dissipate a virtual supercomputer of the computer collection composition of coupling.The network includes but is not limited to internet, wide area network, city
Domain net, LAN, VPN, wireless self-organization network (Ad Hoc networks) etc..Preferably, the equipment 1 can also be operation
Shell script on the network equipment.Certainly, those skilled in the art will be understood that the said equipment 1 is only for example, other
Equipment 1 that is existing or being likely to occur from now on is such as applicable to the application, should also be included within the application protection domain, and
This is incorporated herein by reference.
Preferably, container, the calculating class serviced component container and the resources-type serviced component during language operation
Container is realized based on Akka micro services software frame.
Here, by software platform based on the Akka micro services software frame, have the following advantages that:(1) role
(Actor) concurrency programming model preferably shields bottom communication details and thread task scheduling details, and programming is easier to.(2)
Performance is high, and single node is per second to complete 50,000,000 Message Processings.(3) resource requirement is low, and 2,500,000 Actor can be accommodated per GB internal memories
Entity object.(4) maturity is higher, is the bottom architecture software of Spark big data platforms, and JAX innovations were obtained in 2015 and are opened
Send out prize for technical achievement.(5) write based on powerful Scala language, coding realizes efficiency high, can be with other JVM language class libraries phases
Mutually call.(6) the gossip cluster communication agreements of amazon Dynamo systems are derived from, by amazon cloud service platforms
Long-term technology verifies that reliability is high;Cluster Sharding, Cluster Singleton, Distributed can be supported
The colony application scenarios such as Publish Subscribe, Distributed Data.(7) father and son's character object (Actor)
Regulator (Supervisor) pattern, father's character object, which can capture the exception of sub- character object and perform automatically, different restarts
Strategy, the fault-tolerance and service availability of system are greatly improved, reduce high availability written in code difficulty.(8) software is passed through
Router (router) and perform distributor (dispatcher) combination and realize that a variety of Actor are concurrent and load-balancing algorithm plan
Slightly.Such as polling dispatching (round robin), random schedule (random), broadcast (broadcast), uniformity Hash
(Consistent Hashing) etc..
Certainly, those skilled in the art will be understood that above-mentioned Akka micro services software frame (referring to www.akka.io) only
To illustrate, other micro services software frames that are existing or being likely to occur from now on, such as (one is based on Chrome to Node.Js
The platform that JavaScript is established when running, for the network application easily built fast response time, be easy to extension),
Finagle (Twitter is based on the RPC frameworks that support that Netty is developed is fault-tolerant, agreement is unrelated), (one is used Scala to Akka
The storehouse write, fault-tolerant, high scalability Java and Scala Actor models application is write for simplifying), RxJava (one
The individual response type expanding library realized on a java virtual machine, there is provided the asynchronous call and base realized based on observable sequences
In event programme), Vert.x (one based on JVM, lightweight, high performance application platform) etc., be such as applicable to the application,
It should be included within the application protection domain, and be incorporated herein by reference herein.
The first device 11 obtains waiting task by distributed real-time messages bus, and the waiting task is turned
Container when being sent to language operation.
Here, communication is realized by the distributed real-time messages bus.Container can be based on during the language operation
The Actor of Akka micro services software frames is realized.
Preferably, the first device 11 pass through distributed real-time messages bus obtain user equipment send pending
Business.
Here, the user equipment includes but is not limited to:Smart mobile phone, the tablet personal computer of relative client are installed,
Open the computer of the Net silver page.For example, referring to Fig. 2, the web page resources of Web server can be obtained by the user equipment,
Establish the connection with the distributed real-time messages bus.Then, by the communication of the distributed real-time messages bus, obtain
The waiting task that the user equipment is sent.
Preferably, the waiting task includes remote service call request;Wherein, the first device 11 passes through distribution
Formula real-time messages bus obtains remote service call request, and the remote service call request is converted into function call request simultaneously
Container when being forwarded to language operation.
For example, referring to Fig. 2, the user equipment is initiated the remote service by the distributed real-time messages bus and adjusted
With request, after service broker receives the remote service call request, the remote service call request is first converted into letter
Number call request, then the function call request is forwarded to container when language is run.
Container performs the waiting task when second device 12 is run using the language, wherein, performing
Cheng Zhong, when the situation for the parallel processing of asynchronous service occur, taken respectively to calculating class by the distributed real-time messages bus
Business assembly container, resources-type serviced component container initiate multiple asynchronous calls requests.
For example, container searches function definition during the language operation, program running example is created;Hold during the language operation
Device is mounted with distributed variable-frequencypump language interpreter, and the distributed variable-frequencypump language interpreter explains application code
And distributed parallel calls association service component to complete the waiting task to cooperate with;Preferably, at the distributed parallel
Language interpreter is managed by the specific markers in recognition application code, finds the situation of the parallel processing of asynchronous service.
Preferably, container when container is the operation of Zebra language during the language operation, the distributed variable-frequencypump language
Interpreter is Zebra language interpreters.
For example, referring to Fig. 2, Zebra language interpreters are performed Zebra script sentences by programming logic successively, are being held
During row, when the situation for the parallel processing of asynchronous service occur, while to calculate class component container A, resources-type assembly container
B, resources-type assembly container C initiates multiple asynchronous call requests, and the context (Context) of present procedure running example is switched
To the dormancy program example set for waiting micro services to call response.
Here, Zebra distributed variable-frequencypumps language supports distributed variable-frequencypump, and asynchronism callback can be handled very well and asked
Topic.Zebra language follows the design philosophy of MDA (Model Driven Architecture, executing model drive structure), can make
With different language and operation when container, in principle the business logic written in code of programmer once may operate in varying environment afterwards
(including departing from JVM), after carrying out suitable service abstraction, the optimization evolution of lower software framework will not have to business function code
Any influence.
Preferably, container performs the waiting task when being run using the language, including:Run using the language
When container syntax tree is parsed according to the pending task;Perform the syntax tree.
For example, container searches function definition during the Zebra language operation, the waiting task is resolved into Zebra
Syntax tree structure, create program running example.
Preferably, container is mounted with distributed variable-frequencypump language interpreter during the language operation;Wherein, described in execution
Syntax tree includes:During the syntax tree is performed, using the distributed variable-frequencypump language interpreter dynamic construction,
Perform and clear up sentence and perform tree.
If, can be by the present embodiment here, apply mechanically ANTLR father Terence Parr compiler language implementation pattern
The distributed variable-frequencypump language interpreter is referred to as the interpreter based on tree, and it is mainly based upon complete syntax tree and explained
Dynamic construction and cleaning sentence perform tree in implementation procedure, can effectively save memory source.Sentence performs tree and is considered as
It is the running example of syntax parsing tree object.
When the 3rd device 13 is run using the language container reception and handle it is described calculating class serviced component container
And the result that the resources-type serviced component container is asked for the asynchronous call, until the waiting task performs
Complete.
For example, container receives the calculating class serviced component appearance by the distributed message bus during language operation
The returning result of device and the resources-type serviced component container is simultaneously handled one by one, when handling each result message, the journey of association
Container (as shown in 7 in Fig. 2) when sort run example also switches back into operation, in corresponding syntax tree vertex ticks asynchronous call shape
State simultaneously is attempted to continue to perform backward, such as can not successively perform, then switch back into dormancy wait state.In the embodiment shown in Figure 2,
Until receiving complete (6-A), (6-B), (6-C) three result messages, program running example could continue down to hold without pausing
OK, whole call function logics and release procedure running example memory source are completed;Function implementing result is held when being run by Zebra
Device returns to service broker.
Preferably, the equipment 1 includes the 6th device (not shown);6th device passes through described distributed real
When messaging bus, the user equipment will be back to for the result of the waiting task.
For example, referring to Fig. 2, the user equipment initiates remote service calling by the distributed real-time messages bus please
Ask, after being disposed, service broker is by the distributed real-time messages bus by the processing knot of the remote service call request
Fruit is back to the user equipment.
Preferably, as shown in figure 5, the equipment 1 also includes the 4th device 14 ';4th device 14 ' utilizes the meter
Asynchronous call request described in class serviced component container reception is calculated, asks route distribution real to class component is calculated the asynchronous call
Example is performed, and the result asked for the asynchronous call is back into container when the language is run.
For example, referring to Fig. 2, calculate class component container A and receive service invocation request (4-A), directly forwarded by routeing
Container (6-A) when performing (4-A-1) to a component instance, and result being back into the operation of Zebra language.
Preferably, as shown in figure 5, the equipment 1 also includes the 5th device 15 ';5th device 15 ' utilizes the money
Asynchronous call described in the class serviced component container reception of source is asked, and asynchronous call request is put into buffer queue, United Dispatching
Send to the resources-type component instance of free time and perform, and the result asked for the asynchronous call is back to institute's predicate
Container during speech operation.
For example, the asynchronous call received request is put into buffer queue by the resources-type serviced component container;If detection
Task can be distributed to the serviced component example for having idle, the resources-type serviced component container can ask the asynchronous call
Extracted from buffer queue;If detect in the absence of idle serviced component example, before no more than maximum instance number
Put, the resources-type serviced component container can also create new serviced component example with the task of distributing.
Preferably, the idle resources-type component instance performs the asynchronous call by following at least any one and asked
Ask:The resources-type component instance calls external web services to handle the asynchronous call and asked by asynchronous I/O;The resource
Class component example is asked by asynchronous call described in block type service call database service processing.
For example, referring to Fig. 2, resources-type assembly container B is connected to service invocation request (4-B), is put into inactive queue of task,
United Dispatching is sent to the component instance (4-B-1) of free time;Component instance calls external web services by asynchronous I/O and handled
Container (6-B) when result being back into the operation of Zebra language afterwards.Resources-type assembly container C is connected to service invocation request (4-C),
Inactive queue of task is put into, United Dispatching is sent to the component instance (4-C-1) of free time;Component instance passes through block type service
Container (6-C) when result being back into the operation of Zebra language after calling database service processing.
According to the another aspect of the application, there is provided a kind of electronic equipment, including at least processor and memory cell, institute
Processor is stated to be configured to perform to give an order:
Waiting task is obtained by distributed real-time messages bus, when the waiting task is forwarded into language operation
Container;
Container performs the waiting task when being run using the language, wherein, it is in the process of implementation, asynchronous when occurring
The situation of the parallel processing of service, by the distributed real-time messages bus respectively to calculating class serviced component container, resource
Class serviced component container initiates multiple asynchronous call requests;
Container reception and the calculating class serviced component container and resources-type clothes is handled when being run using the language
The result that business assembly container is asked for the asynchronous call, until the waiting task performs completion.
Compared with prior art, the application obtains waiting task by distributed real-time messages bus, waits to locate by described
Container when reason task is forwarded to language operation, container performs the waiting task when being run using the language, wherein, holding
During row, when the situation for the parallel processing of asynchronous service occur, by the distributed real-time messages bus respectively to calculating
Class serviced component container, resources-type serviced component container initiate multiple asynchronous call requests, then, when being run using the language
Container reception simultaneously handles the calculating class serviced component container and the resources-type serviced component container for the asynchronous call
The result of request, until the waiting task performs completion, so as to the traffic handing capacity of lifting system, reduce movement
The processing time of scene complicated business logic is interconnected, accomplishes that low delay responds.
It should be noted that the application can be carried out in the assembly of software and/or software and hardware, for example, can adopt
With application specific integrated circuit (ASIC), general purpose computer or any other realized similar to hardware device.In one embodiment
In, the software program of the application can realize steps described above or function by computing device.Similarly, the application
Software program (including related data structure) can be stored in computer readable recording medium storing program for performing, for example, RAM memory,
Magnetically or optically driver or floppy disc and similar devices.In addition, some steps or function of the application can employ hardware to realize, example
Such as, coordinate as with processor so as to perform the circuit of each step or function.
In addition, the part of the application can be applied to computer program product, such as computer program instructions, when its quilt
When computer performs, by the operation of the computer, it can call or provide according to the present processes and/or technical scheme.
And the programmed instruction of the present processes is called, it is possibly stored in fixed or moveable recording medium, and/or pass through
Broadcast or the data flow in other signal bearing medias and be transmitted, and/or be stored according to described program instruction operation
In the working storage of computer equipment.Here, including a device according to one embodiment of the application, the device includes using
Memory in storage computer program instructions and processor for execute program instructions, wherein, when the computer program refers to
When order is by the computing device, method and/or skill of the plant running based on foregoing multiple embodiments according to the application are triggered
Art scheme.
It is obvious to a person skilled in the art that the application is not limited to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit herein or essential characteristic, the application can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, scope of the present application is by appended power
Profit requires rather than described above limits, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the application.Any reference in claim should not be considered as to the involved claim of limitation.This
Outside, it is clear that the word of " comprising " one is not excluded for other units or step, and odd number is not excluded for plural number.That is stated in device claim is multiple
Unit or device can also be realized by a unit or device by software or hardware.The first, the second grade word is used for table
Show title, and be not offered as any specific order.
Claims (21)
1. a kind of distributed task scheduling processing method, wherein, this method includes:
Waiting task is obtained by distributed real-time messages bus, held when the waiting task is forwarded into language operation
Device;
Container performs the waiting task when being run using the language, wherein, in the process of implementation, when there is asynchronous service
Parallel processing situation, by the distributed real-time messages bus respectively to calculate class serviced component container, resources-type clothes
Business assembly container initiates multiple asynchronous calls requests;
Container reception and the calculating class serviced component container and resources-type service group is handled when being run using the language
The result that part container is asked for the asynchronous call, until the waiting task performs completion.
2. according to the method for claim 1, wherein, methods described also includes:
Using asynchronous call request described in the calculating class serviced component container reception, the asynchronous call is asked into route distribution
Performed to class component example is calculated, and the result asked for the asynchronous call is back to when the language is run and held
Device.
3. according to the method for claim 1, wherein, methods described also includes:
Asked using asynchronous call described in the resources-type serviced component container reception, asynchronous call request is put into caching
Queue, United Dispatching sends to the resources-type component instance of free time and performed, and the processing knot that will be asked for the asynchronous call
Container when fruit is back to the language operation.
4. according to the method for claim 3, wherein, the idle resources-type component instance passes through following at least any one
Perform the asynchronous call request:
The resources-type component instance calls external web services to handle the asynchronous call and asked by asynchronous I/O;
The resources-type component instance is asked by asynchronous call described in block type service call database service processing.
5. method according to any one of claim 1 to 4, wherein, it is described to be obtained by distributed real-time messages bus
Waiting task includes:
The waiting task of user equipment transmission is obtained by distributed real-time messages bus;
Wherein, methods described also includes:
By the distributed real-time messages bus, set the user is back to for the result of the waiting task
It is standby.
6. method according to any one of claim 1 to 5, wherein, the waiting task calls including remote service
Request;
Wherein, it is described that waiting task is obtained by distributed real-time messages bus, the waiting task is forwarded to language
Container during operation, including:
Remote service call request is obtained by distributed real-time messages bus, the remote service call request is converted into letter
Number call request is simultaneously forwarded to container when language is run.
7. according to the method for claim 1, wherein, container performs the waiting task when being run using the language,
Including:
Container parses syntax tree according to the pending task when being run using the language;
Perform the syntax tree.
8. according to the method for claim 7, wherein, container is mounted with distributed variable-frequencypump language when the language is run
Interpreter;
Wherein, performing the syntax tree includes:
During the syntax tree is performed, using the distributed variable-frequencypump language interpreter dynamic construction, perform simultaneously
Cleaning sentence performs tree.
9. the method according to claim 11, wherein, container when container is the operation of Zebra language when the language is run, institute
It is Zebra language interpreters to state distributed variable-frequencypump language interpreter.
10. method according to any one of claim 1 to 9, wherein, container, the calculating class when language is run
Serviced component container and the resources-type serviced component container are realized based on Akka micro services software frame.
11. a kind of distributed task scheduling processing equipment, wherein, the equipment includes:
First device, for obtaining waiting task by distributed real-time messages bus, the waiting task is forwarded to
Container when language is run;
Second device, for performing the waiting task using container during language operation, wherein, in the process of implementation,
When the situation for the parallel processing of asynchronous service occur, by the distributed real-time messages bus respectively to calculating class serviced component
Container, resources-type serviced component container initiate multiple asynchronous call requests;
3rd device, container reception and the calculating class serviced component container and described is handled during for being run using the language
The result that resources-type serviced component container is asked for the asynchronous call, until the waiting task performs completion.
12. equipment according to claim 11, wherein, the equipment also includes:
4th device, for being asked using asynchronous call described in the calculating class serviced component container reception, by the asynchronous tune
Performed with request route distribution to class component example is calculated, and the result asked for the asynchronous call is back to institute
Container during predicate speech operation.
13. equipment according to claim 11, wherein, the equipment also includes:
5th device, for being asked using asynchronous call described in the resources-type serviced component container reception, by the asynchronous tune
Buffer queue is put into request, United Dispatching sends to the resources-type component instance of free time and performed, and will be for the asynchronous tune
The container when language is run is back to the result of request.
14. equipment according to claim 13, wherein, the idle resources-type component instance passes through following at least any
Item performs the asynchronous call request:
The resources-type component instance calls external web services to handle the asynchronous call and asked by asynchronous I/O;
The resources-type component instance is asked by asynchronous call described in block type service call database service processing.
15. the equipment according to any one of claim 11 to 14, wherein, it is described to be obtained by distributed real-time messages bus
Waiting task is taken to include:
The waiting task of user equipment transmission is obtained by distributed real-time messages bus;
Wherein, the equipment also includes:
6th device, for by the distributed real-time messages bus, will be returned for the result of the waiting task
It is back to the user equipment.
16. the equipment according to any one of claim 11 to 15, wherein, the waiting task is adjusted including remote service
With request;
Wherein, the first device is used for:
Remote service call request is obtained by distributed real-time messages bus, the remote service call request is converted into letter
Number call request is simultaneously forwarded to container when language is run.
17. equipment according to claim 11, wherein, container performs described pending when being run using the language
Business, including:
Container parses syntax tree according to the pending task when being run using the language;
Perform the syntax tree.
18. equipment according to claim 17, wherein, container is mounted with distributed variable-frequencypump language when the language is run
Say interpreter;
Wherein, performing the syntax tree includes:
During the syntax tree is performed, using the distributed variable-frequencypump language interpreter dynamic construction, perform simultaneously
Cleaning sentence performs tree.
19. equipment according to claim 18, wherein, container is container when Zebra language is run when the language is run,
The distributed variable-frequencypump language interpreter is Zebra language interpreters.
20. the equipment according to any one of claim 11 to 19, wherein, container, the calculating when language is run
Class serviced component container and the resources-type serviced component container are realized based on Akka micro services software frame.
21. a kind of electronic equipment, including at least processor and memory cell, the processor is configured to perform to give an order:
Waiting task is obtained by distributed real-time messages bus, held when the waiting task is forwarded into language operation
Device;
Container performs the waiting task when being run using the language, wherein, in the process of implementation, when there is asynchronous service
Parallel processing situation, by the distributed real-time messages bus respectively to calculate class serviced component container, resources-type clothes
Business assembly container initiates multiple asynchronous calls requests;
Container reception and the calculating class serviced component container and resources-type service group is handled when being run using the language
The result that part container is asked for the asynchronous call, until the waiting task performs completion.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710686163.3A CN107463434B (en) | 2017-08-11 | 2017-08-11 | Distributed task processing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710686163.3A CN107463434B (en) | 2017-08-11 | 2017-08-11 | Distributed task processing method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107463434A true CN107463434A (en) | 2017-12-12 |
CN107463434B CN107463434B (en) | 2021-08-24 |
Family
ID=60548770
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710686163.3A Active CN107463434B (en) | 2017-08-11 | 2017-08-11 | Distributed task processing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107463434B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110083455A (en) * | 2019-05-07 | 2019-08-02 | 网易(杭州)网络有限公司 | Figure computation processing method, device, medium and electronic equipment |
CN110443512A (en) * | 2019-08-09 | 2019-11-12 | 北京思维造物信息科技股份有限公司 | A kind of regulation engine and regulation engine implementation method |
CN110489139A (en) * | 2019-07-03 | 2019-11-22 | 平安科技(深圳)有限公司 | A kind of real-time data processing method and its relevant device based on micro services |
CN110827125A (en) * | 2019-11-06 | 2020-02-21 | 兰州领新网络信息科技有限公司 | Periodic commodity transaction management method |
CN111177008A (en) * | 2019-12-31 | 2020-05-19 | 京东数字科技控股有限公司 | Data processing method and device, electronic equipment and computer storage medium |
CN112272231A (en) * | 2020-10-23 | 2021-01-26 | 杭州卷积云科技有限公司 | Edge cloud collaborative service arrangement method for intelligent manufacturing scene |
CN112379992A (en) * | 2020-12-04 | 2021-02-19 | 中国科学院自动化研究所 | Multi-agent task collaborative message transmission and exception handling method based on role |
CN113688602A (en) * | 2021-10-26 | 2021-11-23 | 中电云数智科技有限公司 | Task processing method and device |
US20220232069A1 (en) * | 2021-01-18 | 2022-07-21 | Vmware, Inc. | Actor-and-data-grid-based distributed applications |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1494017A (en) * | 2002-10-07 | 2004-05-05 | �Ҵ���˾ | Holder selector used in global network service structure and its selection method |
US20050097537A1 (en) * | 2003-10-30 | 2005-05-05 | Laura Joseph G. | System and method for distributed processing in COBOL |
CN1783019A (en) * | 2004-12-03 | 2006-06-07 | 微软公司 | Interface infrastructure for creating and interacting with web services |
US20060253548A1 (en) * | 2005-04-18 | 2006-11-09 | Research In Motion Limited | Method and system for hosting and executing a component application |
CN101295261A (en) * | 2008-06-25 | 2008-10-29 | 中国人民解放军国防科学技术大学 | Componentization context processing method facing general computation surroundings |
US20080276231A1 (en) * | 2007-05-03 | 2008-11-06 | Yunwu Huang | Method and apparatus for dependency injection by static code generation |
US20090241090A1 (en) * | 2008-03-20 | 2009-09-24 | Sap Ag | Extending the functionality of a host programming language |
US20100333091A1 (en) * | 2009-06-30 | 2010-12-30 | Sun Microsystems, Inc. | High performance implementation of the openmp tasking feature |
CN102611642A (en) * | 2012-02-27 | 2012-07-25 | 杭州闪亮科技有限公司 | System for processing nonsynchronous message and method for system to send message and monitor processing task |
CN105528290A (en) * | 2015-12-04 | 2016-04-27 | 中国航空综合技术研究所 | Construction method of script-based embedded software simulation and test integrated platform |
CN106657232A (en) * | 2016-09-29 | 2017-05-10 | 山东浪潮商用系统有限公司 | Distributed server configuration and service method thereof |
CN106777026A (en) * | 2016-12-08 | 2017-05-31 | 用友网络科技股份有限公司 | Support method, the apparatus and system of micro services framework affairs final consistency |
-
2017
- 2017-08-11 CN CN201710686163.3A patent/CN107463434B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1494017A (en) * | 2002-10-07 | 2004-05-05 | �Ҵ���˾ | Holder selector used in global network service structure and its selection method |
US20050097537A1 (en) * | 2003-10-30 | 2005-05-05 | Laura Joseph G. | System and method for distributed processing in COBOL |
CN1783019A (en) * | 2004-12-03 | 2006-06-07 | 微软公司 | Interface infrastructure for creating and interacting with web services |
US20060253548A1 (en) * | 2005-04-18 | 2006-11-09 | Research In Motion Limited | Method and system for hosting and executing a component application |
US20080276231A1 (en) * | 2007-05-03 | 2008-11-06 | Yunwu Huang | Method and apparatus for dependency injection by static code generation |
US20090241090A1 (en) * | 2008-03-20 | 2009-09-24 | Sap Ag | Extending the functionality of a host programming language |
CN101295261A (en) * | 2008-06-25 | 2008-10-29 | 中国人民解放军国防科学技术大学 | Componentization context processing method facing general computation surroundings |
US20100333091A1 (en) * | 2009-06-30 | 2010-12-30 | Sun Microsystems, Inc. | High performance implementation of the openmp tasking feature |
CN102611642A (en) * | 2012-02-27 | 2012-07-25 | 杭州闪亮科技有限公司 | System for processing nonsynchronous message and method for system to send message and monitor processing task |
CN105528290A (en) * | 2015-12-04 | 2016-04-27 | 中国航空综合技术研究所 | Construction method of script-based embedded software simulation and test integrated platform |
CN106657232A (en) * | 2016-09-29 | 2017-05-10 | 山东浪潮商用系统有限公司 | Distributed server configuration and service method thereof |
CN106777026A (en) * | 2016-12-08 | 2017-05-31 | 用友网络科技股份有限公司 | Support method, the apparatus and system of micro services framework affairs final consistency |
Non-Patent Citations (2)
Title |
---|
INFOQ: "恒丰银行微服务架构优化实践", 《HTTPS://WWW.SOHU.COM/A/158254316_355140》 * |
天道酬勤YXJ1: "案例:恒丰银行——运营风险监测系统", 《HTTP://WWW.360DOC.COM/CONTENT/17/0526/00/32626470_657536520.SHTML》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110083455B (en) * | 2019-05-07 | 2022-07-12 | 网易(杭州)网络有限公司 | Graph calculation processing method, graph calculation processing device, graph calculation processing medium and electronic equipment |
CN110083455A (en) * | 2019-05-07 | 2019-08-02 | 网易(杭州)网络有限公司 | Figure computation processing method, device, medium and electronic equipment |
CN110489139A (en) * | 2019-07-03 | 2019-11-22 | 平安科技(深圳)有限公司 | A kind of real-time data processing method and its relevant device based on micro services |
WO2021000410A1 (en) * | 2019-07-03 | 2021-01-07 | 平安科技(深圳)有限公司 | Real-time data processing method based on micro-service and related device therefor |
CN110443512A (en) * | 2019-08-09 | 2019-11-12 | 北京思维造物信息科技股份有限公司 | A kind of regulation engine and regulation engine implementation method |
CN110827125A (en) * | 2019-11-06 | 2020-02-21 | 兰州领新网络信息科技有限公司 | Periodic commodity transaction management method |
CN111177008A (en) * | 2019-12-31 | 2020-05-19 | 京东数字科技控股有限公司 | Data processing method and device, electronic equipment and computer storage medium |
CN112272231A (en) * | 2020-10-23 | 2021-01-26 | 杭州卷积云科技有限公司 | Edge cloud collaborative service arrangement method for intelligent manufacturing scene |
CN112272231B (en) * | 2020-10-23 | 2022-05-13 | 杭州卷积云科技有限公司 | Edge cloud collaborative service arrangement method for intelligent manufacturing scene |
CN112379992A (en) * | 2020-12-04 | 2021-02-19 | 中国科学院自动化研究所 | Multi-agent task collaborative message transmission and exception handling method based on role |
CN112379992B (en) * | 2020-12-04 | 2024-01-30 | 中国科学院自动化研究所 | Role-based multi-agent task cooperative message transmission and exception handling method |
US20220232069A1 (en) * | 2021-01-18 | 2022-07-21 | Vmware, Inc. | Actor-and-data-grid-based distributed applications |
CN113688602A (en) * | 2021-10-26 | 2021-11-23 | 中电云数智科技有限公司 | Task processing method and device |
Also Published As
Publication number | Publication date |
---|---|
CN107463434B (en) | 2021-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107463434A (en) | Distributed task processing method and device | |
Rausch et al. | Optimized container scheduling for data-intensive serverless edge computing | |
CN107479990A (en) | Distributed software service system | |
US10310908B2 (en) | Dynamic usage balance of central processing units and accelerators | |
US9251517B2 (en) | Optimizing service factors for computing resources in a networked computing environment | |
US9338226B2 (en) | Actor system and method for analytics and processing of big data | |
Jindal et al. | Function delivery network: Extending serverless computing for heterogeneous platforms | |
CN105045607A (en) | Method for achieving uniform interface of multiple big data calculation frames | |
CN109144699A (en) | Distributed task dispatching method, apparatus and system | |
US11956330B2 (en) | Adaptive data fetching from network storage | |
CN103064670A (en) | Method and system for innovation platform data management based on place net | |
Heidari et al. | Quality of Service (QoS)-driven resource provisioning for large-scale graph processing in cloud computing environments: Graph Processing-as-a-Service (GPaaS) | |
CN111352896B (en) | Artificial intelligence accelerator, equipment, chip and data processing method | |
CN105391777A (en) | Algorithm escrow PaaS platform for decoupling logic code and performance code | |
Barbieru et al. | Soft real-time hadoop scheduler for big data processing in smart cities | |
Cicconetti et al. | FaaS execution models for edge applications | |
Liu et al. | KubFBS: A fine‐grained and balance‐aware scheduling system for deep learning tasks based on kubernetes | |
Hung et al. | A new approach for task scheduling optimization in mobile cloud computing | |
CN103019813A (en) | Method for obtaining interactive strength of SaaS-based interactive program | |
Xu et al. | Practice of Alibaba cloud on elastic resource provisioning for large‐scale microservices cluster | |
US20230196182A1 (en) | Database resource management using predictive models | |
Chang et al. | Development of multiple big data analytics platforms with rapid response | |
Zhang et al. | A relationship-based VM placement framework of cloud environment | |
US11354592B2 (en) | Intelligent computation acceleration transform utility | |
Nivethitha et al. | Survey on architectural design principles for edge oriented computing systems |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP02 | Change in the address of a patent holder | ||
CP02 | Change in the address of a patent holder |
Address after: 250000 Luoyuan street, Lixia District, Jinan City, Shandong Province Patentee after: HENGFENG BANK CO.,LTD. Address before: 264001 No. 248, South Street, Zhifu District, Yantai City, Shandong Province Patentee before: HENGFENG BANK CO.,LTD. |