CN111562922A - Method, system and electronic equipment for modularizing command line program and cloud-end method and system - Google Patents
Method, system and electronic equipment for modularizing command line program and cloud-end method and system Download PDFInfo
- Publication number
- CN111562922A CN111562922A CN202010353672.6A CN202010353672A CN111562922A CN 111562922 A CN111562922 A CN 111562922A CN 202010353672 A CN202010353672 A CN 202010353672A CN 111562922 A CN111562922 A CN 111562922A
- Authority
- CN
- China
- Prior art keywords
- task
- module
- command line
- queue
- execution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9532—Query formulation
-
- 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
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/50—Molecular design, e.g. of drugs
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Abstract
Provided are a method, a system and an electronic device for command line program modularization and cloud-end. The invention discloses a method for modularizing and cloud-terminating a command line program, which comprises the following steps: receiving an execution request input by a user; the execution request comprises a demand module and input parameters; and storing the execution request to form a new task, pushing the task corresponding to the execution request to a task queue, enabling the execution queue to acquire the task from the task queue when the execution queue in the command line program module is idle, and calling a corresponding computer from the computer cluster to run the task. The invention adopts a multi-level layered access protocol, and each level module of the command line program module is in cross cooperation, is called layer by layer and operates independently, and is matched together to complete the cooperative function of the command line tool software, thereby improving the flexibility and reducing the use threshold.
Description
Technical Field
The invention relates to a software tool application technology, in particular to a method, a system and electronic equipment for command line program modularization and cloud.
Background
Computer-aided drug molecular design (CADD) developed in a cross-consortium with the development of computer technology and the subjects of pharmaceutical chemistry, molecular biology, computational chemistry, etc., and came in the 20 actual 90 s. The discipline becomes an indispensable link in rational drug design, accelerates the efficiency of new drug development, becomes a perfect and emerging research field, and plays an increasingly important role in drug development. CADD is a tool software which is not easy to understand and conform to the habits of Chinese people, is basically monopolized abroad, and has high cost.
The common CADD tools mainly comprise molecular docking, receptor ligand interaction analysis, protein three-dimensional structure prediction, virtual screening, molecular dynamics simulation and the like. The operation process is complicated, the problem differentiation is large, and a professional person is required to accumulate the problems for many years to obtain an accurate and reliable structure. The CADD tool software is high in professional requirement and multiple in subjects, so that pharmaceutical research workers need to spend more time and energy to learn more subject knowledge of computers, the efficiency is reduced undoubtedly, and some scientific research workers cannot enjoy the convenience and the efficiency brought by CADD.
Disclosure of Invention
In order to overcome the defects of the prior art, one of the objectives of the present invention is to provide a method for modularizing and cloud-terminating a command line program, which can solve the problems of low efficiency and complex use in the prior art.
The second objective of the present invention is to provide a system for command line program modularization and cloud-end, which can solve the problems of low efficiency and complex use in the prior art.
The invention also aims to provide the electronic equipment, which can solve the problems of low efficiency and complex use in the prior art.
One of the purposes of the invention is realized by adopting the following technical scheme:
the method for modularizing and cloud-terminating the command line program comprises the following steps:
receiving an execution request input by a user; the execution request comprises a demand module and input parameters;
and storing the execution request to form a new task, pushing the task corresponding to the execution request to a task queue, enabling the execution queue to acquire the task from the task queue when the execution queue in the command line program module is idle, and calling a corresponding computer from the computer cluster to run the task.
Preferably, the method further comprises the following steps: and monitoring the running state of the command line modules of all computers in the computer cluster.
Preferably, the operation state at least includes whether the operation process is faulty, whether the running computer corresponds to the task which is running, and whether the operation is finished.
Preferably, the method further comprises the following steps: and monitoring the working state of the command line program module, wherein the working state comprises whether the task queue and the work queue are idle or not and whether the task queue and the tasks executed by the work queue are correct or not.
Preferably, the number of executors of the task queue and the execution queue is dynamically adjusted according to the running state of the computer and the working state of the command line program module.
Preferably, the execution request is stored in a database.
Preferably, the user selects the matched window at the webpage end to input the execution request.
The second purpose of the invention is realized by adopting the following technical scheme:
the system comprises a user input module, a request response and task monitoring module, a command line program module and an environment adaptation module which are sequentially connected; the user input module is used for a user to input an execution request; the environment adaptation module is used for monitoring the running states of all computers in the computer cluster; the request response and task monitoring module is used for receiving and storing the execution request, pushing the task corresponding to the execution request to a task queue, enabling the execution queue to obtain the task from the task queue when the execution queue in the command line program module is empty, and calling the corresponding computer to run the task by combining the running state of the computer.
Preferably, the request response and task monitoring module comprises a controller, a logic processing layer and a monitor; the controller is used for receiving an execution request of a user and distributing the execution request to the logic processing layer; the logic processing layer is used for scheduling the command line program module to run tasks based on the execution request, and the monitoring machine is used for monitoring the working state of the running command line program module, receiving the running states of all computers in the computer cluster and feeding back the running states to the controller.
The third purpose of the invention is realized by adopting the following technical scheme:
an electronic device having a memory, a processor and a computer readable program stored in the memory and executable by the processor, wherein the computer readable program when executed by the processor implements a method according to any one of the objects of the invention.
Compared with the prior art, the invention has the beneficial effects that:
the invention adopts a multi-level layered access protocol, and the modules of each level of the command line program module are in cross fusion cooperation, are called layer by layer and operate independently, and are matched together to complete the cooperative function of the command line tool software, thereby improving the flexibility and reducing the use threshold.
Drawings
FIG. 1 is a flow chart of a method for command line program modularization and cloud implementation of the present invention;
fig. 2 is a block diagram of a system for command line program modularization and cloud-end of the present invention.
Detailed Description
The invention will be further described with reference to the accompanying drawings and the detailed description below:
the invention discloses a method for modularizing and cloud-end processing a command line program, namely, a new algorithm program is quickly accessed into a system, deployed at the cloud end and split into enough simple fine granularity to form micro modules, and each module can complete the work required by research.
As shown in fig. 1, the present invention comprises the steps of:
s1: receiving an execution request input by a user; the execution request comprises a demand module and input parameters.
In the invention, the WEB webpage port is used for user input, so that the method is simpler and more operable, belongs to a user access layer and a user visual page layer, is simple to interact, and can complete the scheduling and use of one module of a complex command line program cooperative operation module only by inputting a small amount of parameter interaction by a user.
And a user visual interface layer above the deployed level based on the cloud. The user request is transmitted to the request response and task monitoring module, the result which is executed by the command line program cooperative operation module layer and accords with the protocol is displayed to the user, the intermediate report can be checked on line, and the command is sent to the request response processing and intelligent task monitoring layer at any time to require the termination of the operation of a certain module task of the command line program cooperative operation module layer. The parameter re-sending request can be adjusted to the request response processing and intelligent task monitoring layer to restart the task. The final result can be obtained. And another command line program cooperative operation module can be called online to start a new task according to a certain result. Different webpage user windows correspond to different command line programs to cooperatively operate the modules, so that the user interfaces are simple, clear and do not interfere with each other, the portable and simple interfaces avoid the common trouble that the traditional CADD software interface is complicated and messy, and a user needing a certain small function does not need to be disturbed by an unavailable function interface. The comfort level and the easy maintenance are improved. The user can select the module frequently needed by the user to work in the multiple command line program cooperation modules, and the webpage user window is collected, so that the user can conveniently use the module in the future work. Different command line program cooperative operation modules provide API interfaces represented on the API interface of the webpage user window layer, so that upstream and downstream scheduling among the command line program cooperative operation modules can be realized by associating a plurality of different webpage user windows, namely, the sequential scheduling among different modules of the command line program cooperative operation module layer is customized and configured according to the needs of users, the automation is high, and the efficiency is improved. However, it should be noted that the embodiment of the present invention is applied to CADD software, and in practical applications, not only can access a CADD program, but also the solution provided by the present invention can access any command line program.
The method of the invention is applied to a request response and task monitoring module, and the request response and task monitoring module receives an execution request of a user at a user input module (namely a webpage user window). The requirement module contained in the execution request comprises a webpage window selected by the user according to the purpose of the user. The web page windows are various, and the user can select the web page windows by himself. The user contacts a webpage user window, parameters required by an HTML webpage drawing command module are input, in order to simplify the complexity of CADD command program operation, the webpage is simplified, the number of input items is small, and one command line program module corresponds to one webpage user window. A user needs to realize a certain CADD function and only needs to request a certain command line program module, so that useless option interference is avoided. The webpage user window sends a request of a user to a certain command line module to a request response and task monitoring module.
S2: the execution request is stored to form a new task.
S3: pushing the task corresponding to the execution request to a task queue;
s4: judging whether an execution queue in the command line program module is idle, enabling the execution queue to obtain the task from the task queue when the execution queue is idle, calling a corresponding command line module of the computer from the computer cluster to run the task, and otherwise, continuously monitoring the state of the execution queue.
The environment adaptation module monitors the running states of all computers in the computer cluster and the running states of all computers in the computer cluster. The environment adaptation module accesses the command line program cooperative operation module to the device, determines a deployment environment, allocates operating computers, and controls the deployment cluster, so that different command line program cooperative operation modules work in suitable and different environments and work in computers with different performances, thereby saving computing resources and ensuring the maximum performance. Dynamically adding or unloading the module without stopping the machine, having high flexibility and high expansibility, monitoring the abnormal module and preventing the illegal module from being accessed and operated. The safety of the whole cloud cluster is guaranteed, and efficient operation is maintained.
And further, monitoring the working state of the command line program module, wherein the working state comprises whether the task queue and the work queue are idle or not and whether the task queue and the task executed by the work queue are correct or not.
And dynamically adjusting the number of the task queues and the number of the work queues according to the running state of the computer and the working state of the command line program module.
And the request response and task monitoring module stores the execution request. The request response and task monitoring module is a high-performance http framework, receives an execution request packet of a webpage user window, distributes the execution request packet to a command line program module (a command line program cooperative operation module) for execution, and ensures execution and monitoring of tasks, error warning and retry and resource recovery through a task monitoring layer. The method comprises the steps that a user window using request of a webpage is received through a controller and then is distributed to a logic processing layer, data generated in the middle are processed by a data layer, a scheduling command line program of the logic processing layer is executed by a cooperation module layer, protocol parameters are accessed, a starting file is prepared, and information is saved by the data layer. And sending a task starting signal to the intelligent task monitor, and starting a command line program to cooperate with a data layer of the operation module layer to store a specified module. And executing a specified command stored by the data layer, reading the stored input file and the environment configuration parameters, and the like. The intelligent task monitor inquires the task state according to the mode of time polling and increasing the time interval gradually, and processes various conditions of the task in time. And the intelligent task monitoring dynamically adjusts the number of monitors and the number of task executors according to the load condition of the cloud cluster computer. Only when the task performer is idle, the task performer will read the task performance request recorded in the data layer. With the increase of execution or the increase of execution time caused by the complex tasks, the increase of the number of task executors and the absence of idle executors, the number of task waiting executors can be increased, and the number of task executors is increased or the number of executors is recycled under the condition that the task monitoring ensures that a computer is not overloaded. When the executor has an error, the monitor is responsible for regulating and controlling, dynamically terminates the task executor, resets the task to the queue, and dynamically increases and decreases the newly-built task executor according to the situation. And finally, stable and efficient execution and completion of the task are ensured.
The execution request is stored in a database. The command line program module realizes the command line program set of the CADD requirement function, not only supports the CADD program, but also can access any program conforming to the protocol. And cooperatively calling a plurality of subprograms, matching with semi-empirical parameter self-adjustment, and forming a fixed parameter input standard, a starting standard, operation control, a calculation result format standard, a report and the like according to an access protocol. The multi-command-line program cooperation module is controlled by a central control script, environment switching, data and program initialization, main program scheduling, auxiliary program scheduling, intermediate data processing and conversion, multiplexing switch control, result reporting, molecular integration and other different modules are independently controlled by different multi-link control.
As shown in fig. 2, the present invention further provides a system for command line program modularization and cloud-end, which includes a user input module, a request response and task monitoring module, a command line program module and an environment adaptation module, which are connected in sequence; the user input module is used for a user to input an execution request; the environment adaptation module is used for monitoring the running states of all computers in the computer cluster; the request response and task monitoring module is used for receiving and storing the execution request, pushing the task corresponding to the execution request to a task queue, enabling the execution queue to obtain the task from the task queue when the execution queue in the command line program module is empty, and calling the corresponding computer to run the task by combining the running state of the computer.
In the above operation, whether the task queue is free or not, the tasks can be loaded, the tasks are queued in sequence, and the task performer, that is, the performance queue, takes the tasks out of the task queue to perform. When the execution queue is all busy, tasks need to wait in the task queue. As more and more tasks are waiting, it may be controlled to increase the number of executives of the execution queue. When the executor has errors and the like, the executor can be controlled to be replaced again, and a new executor is started.
Further, the request response and task monitoring module comprises a controller, a logic processing layer and a monitor; the controller is used for receiving an execution request of a user and distributing the execution request to the logic processing layer; the logic processing layer is used for scheduling the command line program module to run tasks based on the execution request, and the monitoring machine is used for monitoring the working state of the running command line program module, receiving the running states of all computers in the computer cluster and feeding back the running states to the controller.
In the invention, different command line program modules complete different CADD functions. According to the standard of an access protocol, an entry file with a fixed file designated as do.sh is included, parameters are transmitted according to a standard parameter transmission format, different execution program scripts and the like are automatically compiled by different modules according to different functions, for example, the implementation of a protein three-dimensional structure prediction module is realized, and the modules comprise flexible self-owned command scripts such as fasta2align.sh, pdb2align.sh, checkpeptide. Sh finally form a result file. And according to the access standard, generating a report and a download file at the end, so that the do.sh file has a generation command for operating a file result packet at the access position: tar-cjf result.
The environment adaptation monitors and deploys the control environment and the cloud cluster machine IP, if:
therefore, different command line modules can be controlled, and the cluster machines can be controlled. Task clearing time configuration, etc. are different. For example, molecular docking work in CADD is complex and complicated to operate, and reliable results can be obtained by multiple times of trial and error of expert-based parameter tuning with many years of work experience. The device can be accessed with a special molecular docking command line program to operate cooperatively. Expert's combination tuning experience is drawn in combination, and the docking site prediction, ligand receptor preparation, molecule docking execution and the like are completed automatically according to tuning parameters such as molecule size, molecule cavity position, size and the like. The user can complete the complex operation of the module layer and obtain the desired result only by clicking the start button on the web user window layer. The command line module layer tool only needs to be accessed according to the access standard interface. The device is provided with a plurality of CADD tool modules such as a molecule docking command line cooperative operation module, a command line protein three-dimensional structure prediction simplified operation module, a command line molecule interaction analysis simplified operation module, a command line macromolecule active site prediction module and the like, and can be continuously accessed with more new command line modules. The drug development efficiency of the user can be improved. The request response processing and intelligent task monitoring layer records the user operation records. The past result file may be selected to continue invoking other command line modules to run the task. Also facilitates the adjustment of results, and the like.
The webpage user window sends a request of a user for a certain command line module to a request response processing and intelligent task control monitoring layer. The method comprises the steps of recording a demand module requested by a user and inputting parameters to a database, pushing tasks in the database to a task queue, starting and maintaining an execution queue executor queue, determining the number of the execution queue according to the load condition of a machine, executing the queue to obtain the tasks, executing the tasks on a cluster machine where a specified module is located, and obtaining each command line program required by the environment configuration. And the execution queue and the task are monitored by adopting the golang co-operation scheduling, so that the consumed resources are less, and more computer resources can be left for the program execution of the core command line co-operation module layer.
According to the access standard, the central control script of the command line cooperative operation module is executed. The method comprises the steps of receiving incoming parameters, operating on a designated cluster machine, completing parameter transmission, input file acquisition, data processing, core program calling, result file generation and processing, copying files back to a request response processing and task monitoring layer only, and facilitating reading and downloading of a webpage user window layer. And the environment adaptation monitoring deployment layer controls the command line cooperative operation module to operate on which cloud cluster machines, and finds out the program with errors in operation in time. Increase and decrease of the control module, control of the module scale without stopping, and the like.
The invention also discloses an electronic device having stored thereon a memory, a processor, and a computer readable program stored in the memory and executable by the processor, which when executed by the processor implements a method according to the invention.
Various other modifications and changes may be made by those skilled in the art based on the above-described technical solutions and concepts, and all such modifications and changes should fall within the scope of the claims of the present invention.
Claims (10)
1. The method for modularizing and cloud-terminating the command line program is characterized by comprising the following steps of:
receiving an execution request input by a user; the execution request comprises a demand module and input parameters;
and storing the execution request to form a new task, pushing the task corresponding to the execution request to a task queue, enabling the execution queue to acquire the task from the task queue when the execution queue in the command line program module is idle, and calling a corresponding computer from the computer cluster to run the task.
2. The method of claim 1, further comprising the steps of: the operating states of all the computers in the computer cluster are monitored.
3. The method of claim 2, wherein the operational state includes at least whether a running process is faulty, whether a running computer corresponds to a task it is running on, and whether it is running finished.
4. The method of claim 2, further comprising the steps of: and monitoring the working state of the command line program module, wherein the working state comprises whether the task queue and the work queue are idle or not and whether the task queue and the tasks executed by the work queue are correct or not.
5. The method of claim 4, wherein the number of task queue and execution queue executors is dynamically adjusted based on the operating state of the computer and the operating state of the command line program module.
6. The method of claim 1, wherein the execution request is stored in a database.
7. The method of claim 1, wherein the user selects a matching window on the web page side to input the execution request.
8. The system is characterized by comprising a user input module, a request response and task monitoring module, a command line program module and an environment adaptation module which are sequentially connected; the user input module is used for a user to input an execution request; the environment adaptation module is used for monitoring the running states of all computers in the computer cluster; the request response and task monitoring module is used for receiving and storing the execution request, pushing the task corresponding to the execution request to a task queue, enabling the execution queue to acquire the task from the task queue when the execution queue in the command line program module is idle, and calling the corresponding computer to run the task by combining the running state of the computer.
9. The system of claim 8, wherein the request response and task monitoring module comprises a controller, a logical processing layer, and a monitor; the controller is used for receiving an execution request of a user and distributing the execution request to the logic processing layer; the logic processing layer is used for scheduling the command line program module to run tasks based on the execution request, and the monitoring machine is used for monitoring the working state of the running command line program module, receiving the running states of all computers in the computer cluster and feeding back the running states to the controller.
10. An electronic device having stored thereon a memory, a processor, and a computer readable program stored in the memory and executable by the processor, wherein the computer readable program, when executed by the processor, implements the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010353672.6A CN111562922A (en) | 2020-04-29 | 2020-04-29 | Method, system and electronic equipment for modularizing command line program and cloud-end method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010353672.6A CN111562922A (en) | 2020-04-29 | 2020-04-29 | Method, system and electronic equipment for modularizing command line program and cloud-end method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111562922A true CN111562922A (en) | 2020-08-21 |
Family
ID=72070653
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010353672.6A Pending CN111562922A (en) | 2020-04-29 | 2020-04-29 | Method, system and electronic equipment for modularizing command line program and cloud-end method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111562922A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112181622A (en) * | 2020-09-30 | 2021-01-05 | 苏州达家迎信息技术有限公司 | Task scheduling method and device, computer equipment and storage medium |
| CN112463144A (en) * | 2020-12-02 | 2021-03-09 | 苏州浪潮智能科技有限公司 | Distributed storage command line service method, system, terminal and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090083740A1 (en) * | 2007-09-20 | 2009-03-26 | Microsoft Corporation | Asynchronous execution of software tasks |
| CN102752387A (en) * | 2012-06-29 | 2012-10-24 | 用友软件股份有限公司 | Data storage processing system and data storage processing method |
| CN106371888A (en) * | 2015-07-22 | 2017-02-01 | 三星电子株式会社 | Storage device for supporting virtual machine, storage system including the storage device, and method of operating the same |
| CN107025139A (en) * | 2017-03-21 | 2017-08-08 | 北京天云融创软件技术有限公司 | A kind of high-performance calculation Scheduling Framework based on cloud computing |
| CN109634748A (en) * | 2018-12-12 | 2019-04-16 | 深圳前海微众银行股份有限公司 | Cluster resource dispatching method, device, equipment and computer readable storage medium |
| CN110069335A (en) * | 2019-05-07 | 2019-07-30 | 江苏满运软件科技有限公司 | Task processing system, method, computer equipment and storage medium |
| CN110781007A (en) * | 2019-10-31 | 2020-02-11 | 广州市网星信息技术有限公司 | Task processing method, device, server, client, system and storage medium |
-
2020
- 2020-04-29 CN CN202010353672.6A patent/CN111562922A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090083740A1 (en) * | 2007-09-20 | 2009-03-26 | Microsoft Corporation | Asynchronous execution of software tasks |
| CN102752387A (en) * | 2012-06-29 | 2012-10-24 | 用友软件股份有限公司 | Data storage processing system and data storage processing method |
| CN106371888A (en) * | 2015-07-22 | 2017-02-01 | 三星电子株式会社 | Storage device for supporting virtual machine, storage system including the storage device, and method of operating the same |
| CN107025139A (en) * | 2017-03-21 | 2017-08-08 | 北京天云融创软件技术有限公司 | A kind of high-performance calculation Scheduling Framework based on cloud computing |
| CN109634748A (en) * | 2018-12-12 | 2019-04-16 | 深圳前海微众银行股份有限公司 | Cluster resource dispatching method, device, equipment and computer readable storage medium |
| CN110069335A (en) * | 2019-05-07 | 2019-07-30 | 江苏满运软件科技有限公司 | Task processing system, method, computer equipment and storage medium |
| CN110781007A (en) * | 2019-10-31 | 2020-02-11 | 广州市网星信息技术有限公司 | Task processing method, device, server, client, system and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112181622A (en) * | 2020-09-30 | 2021-01-05 | 苏州达家迎信息技术有限公司 | Task scheduling method and device, computer equipment and storage medium |
| CN112463144A (en) * | 2020-12-02 | 2021-03-09 | 苏州浪潮智能科技有限公司 | Distributed storage command line service method, system, terminal and storage medium |
| CN112463144B (en) * | 2020-12-02 | 2022-11-11 | 苏州浪潮智能科技有限公司 | Distributed storage command line service method, system, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107291547B (en) | Task scheduling processing method, device and system | |
| US20080229320A1 (en) | Method, an apparatus and a system for controlling of parallel execution of services | |
| CN110888743B (en) | GPU resource using method, device and storage medium | |
| CN109614227B (en) | Task resource allocation method and device, electronic equipment and computer readable medium | |
| CN104123182B (en) | Based on the MapReduce task of client/server across data center scheduling system and method | |
| US20070024898A1 (en) | System and method for executing job step, and computer product | |
| CN111209077A (en) | Deep learning framework design method | |
| CN111562922A (en) | Method, system and electronic equipment for modularizing command line program and cloud-end method and system | |
| CN101751288A (en) | Method, device and system applying process scheduler | |
| CN114579288B (en) | Task processing method and device and computer equipment | |
| CN110113374B (en) | Method and device for executing tasks by streaming media server, storage medium and terminal equipment | |
| CN116541134B (en) | Method and device for deploying containers in multi-architecture cluster | |
| KR20220058850A (en) | Job processing methods, devices, instruments, systems and storage media | |
| CN112256414A (en) | Method and system for connecting multiple computing storage engines | |
| CN115373835A (en) | Task resource adjusting method and device for Flink cluster and electronic equipment | |
| Tang et al. | Nanily: A qos-aware scheduling for dnn inference workload in clouds | |
| EP4361808A1 (en) | Resource scheduling method and device and computing node | |
| EP0533787A1 (en) | Remote terminal interface as for a unix?tm operating system computer | |
| CN111444158A (en) | Long-short term user portrait generation method, device, equipment and readable storage medium | |
| CN114968567A (en) | Method, apparatus and medium for allocating computing resources of a compute node | |
| CN114816709A (en) | Task scheduling method, device, server and readable storage medium | |
| CN113946450A (en) | Self-adaptive authorized polling load balancing system for K8S micro service framework | |
| CN110928659B (en) | Numerical value pool system remote multi-platform access method with self-adaptive function | |
| CN109739634A (en) | A kind of atomic task execution method and device | |
| CN113760638A (en) | Log service method and device based on kubernets cluster |
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 |