CN111124697A - Task synchronization and execution method facing distributed platform - Google Patents
Task synchronization and execution method facing distributed platform Download PDFInfo
- Publication number
- CN111124697A CN111124697A CN202010001872.5A CN202010001872A CN111124697A CN 111124697 A CN111124697 A CN 111124697A CN 202010001872 A CN202010001872 A CN 202010001872A CN 111124697 A CN111124697 A CN 111124697A
- Authority
- CN
- China
- Prior art keywords
- resource
- resource lock
- task sequence
- node
- task
- 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
Images
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
- G06F9/52—Program synchronisation; Mutual exclusion, e.g. by means of semaphores
- G06F9/526—Mutual exclusion algorithms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a task synchronization and execution method facing a distributed platform, aiming at realizing a synchronization mechanism among multi-task sequences of the distributed platform and ensuring mutually exclusive access of platform resources, so that the whole distributed platform can share the resources and stably run a series of tasks. The method comprises the following steps: for each node under the distributed platform, through interaction with a file system type registration center, competition is carried out to obtain a resource lock, and a synchronization mechanism is realized; and if the tasks of the whole task sequence all obtain the resource lock, performing multi-thread concurrent processing on the task sequence in an asynchronous execution mode. If the sequence does not completely acquire the resource lock or the competition fails, the processing is carried out by spin, rollback and other modes.
Description
Technical Field
The invention belongs to the field of distributed task processing, and particularly relates to a task synchronization and execution method for a distributed platform.
Background
With the rapid development of network and information technology, distributed system technology is increasingly used. In the field of aviation, airborne clouds are gaining attention, and a distributed architecture is established by taking airplanes as nodes, so that resources can be shared among the airplanes, and a series of tasks can be completed. However, due to the objective limitation of the platform, it is difficult to efficiently and reliably complete the requirement of multiple task sequences.
Disclosure of Invention
The invention aims to realize a synchronization mechanism among the multitask sequences of the distributed platform and ensure mutually exclusive access of platform resources, so that the whole distributed platform can share the resources and stably run a series of tasks.
The technical scheme of the invention is as follows:
the task synchronization and execution method facing the distributed platform comprises the following steps:
step 1) a task sequence execution module (computer software running at any distributed node) sends a request for acquiring a resource lock to a unified registration center, wherein the request comprises a randomly generated UUID corresponding to a current task sequence and resource information required by a certain subtask in the current task sequence;
step 2) verifying whether the UUID of the current task sequence is consistent with the UUID of a corresponding resource lock (corresponding to the resource information required by a certain subtask) recorded by the unified registration center;
step 3) if the two tasks are consistent (indicating that a certain subtask in the preamble of the task sequence obtains the resource lock), the resource lock is successfully obtained; step 5) is directly executed; if the UUID of the corresponding resource lock recorded by the unified registry is empty, the step 4) is executed firstly; if the resource lock is inconsistent (indicating that the corresponding resource is occupied by other task sequences currently), the resource lock acquisition is failed, and the subsequent steps are not executed;
step 4), the unified registration center receives the request and competitively creates a resource node directory in a multithreading mode; if the resource node directory is successfully created, the resource lock is successfully acquired, and the UUID of the current task sequence is written into a data bit corresponding to the resource node directory; if the creation of the resource node directory fails, a self-spinning operation is carried out, and the continuous competition is returned;
step 5) the task sequence execution module judges whether the resource locks required by all the subtasks of the task sequence are successfully contended, and if the contention is successful, the task sequence is executed; otherwise, the execution is started from the step 1) again, and the resource lock of the subsequent subtask of the task sequence is continuously contended.
Optionally, the resource information in step 1) includes a primary node ID, a resource category, and a secondary node ID. For example, a primary node-an airplane node, a secondary node-a functional device node (e.g., a weapon node).
Optionally, for the spin operation in step 4), if the spin operation has exceeded the upper limit of the number of times, it indicates that the acquiring of the resource lock fails, and terminates the request this time.
Optionally, when the resource lock acquisition fails, further determining whether a plurality of subtasks in the preamble of the current task sequence acquire another resource lock; if yes, releasing the other resource lock, and then terminating the request; if not, the request is directly terminated.
Optionally, the primary node is set as an airplane node, and the secondary node is set as a functional equipment node; the task sequence execution module runs on any airplane node of the distributed platform, and the unified registration center is carried on a set airplane node or a ground command center.
Optionally, the task sequence is executed in step 5), and multiple sub-tasks in the task sequence are executed in a multi-thread concurrent manner; and the dependent tasks are subjected to waiting suspension operation according to the time sequence relation among the subtasks, the result is returned after the execution of the current sequence subtask is finished, and at the moment, the suspended related subtasks are awakened to read the returned result and continue to execute the tasks.
Correspondingly, the invention also provides a distributed node, which comprises a processor and a program memory, wherein the program stored in the program memory can be loaded by the processor to execute the following steps:
step 1) sending a request for acquiring a resource lock to a unified registration center, wherein the request comprises a randomly generated UUID corresponding to a current task sequence and resource information required by a certain subtask in the current task sequence;
step 2) verifying whether the UUID of the current task sequence is consistent with the UUID of the corresponding resource lock recorded by the unified registration center;
step 3), if the resource lock is consistent with the resource lock, the resource lock is successfully acquired; step 5) is directly executed; if the UUID of the corresponding resource lock recorded by the unified registry is empty, the step 4) is executed firstly; if not, the resource lock acquisition is failed, the subsequent steps are not executed, and the request is terminated;
step 4) responding to the result of the unified registration center for competing and establishing the resource node catalog in a multithreading mode; if the resource node directory is successfully created, the resource lock is successfully acquired, and the UUID of the current task sequence is written into a data bit corresponding to the resource node directory; if the creation of the resource node directory fails, a self-spinning operation is carried out, and the continuous competition is returned;
step 5) judging whether the resource locks required by all the subtasks of the task sequence are successfully contended, and if the contention is successful, executing the task sequence; otherwise, the execution is started from the step 1) again, and the resource lock of the subsequent subtask of the task sequence is continuously contended.
The invention has at least the following advantages:
the invention provides a synchronization mechanism scheme aiming at a distributed platform such as an airborne cloud, wherein the task execution is limited by objective factors, and the synchronization mechanism scheme is used for solving the synchronization problem among a plurality of task sequences. Meanwhile, a reasonable release method is provided for the problem of resource lock release in the synchronization mechanism, so that the fault-tolerant capability of the whole platform is improved, and the phenomenon of deadlock is prevented.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
FIG. 2 is a diagram illustrating resource lock contention.
Detailed Description
The invention is further described in detail below with reference to the figures and examples.
The embodiment mainly comprises a synchronization mechanism realized by a multi-task sequence competition resource lock and a concurrent execution part inside the task sequence under the synchronization mechanism. For each node under the distributed platform, through interaction with a unified registration center (a file system type registration center), resource locks are obtained through competition, and a synchronization mechanism is realized; and if the tasks of the whole task sequence all obtain the resource lock, performing multi-thread concurrent processing on the task sequence in an asynchronous execution mode. If the sequence does not completely acquire the resource lock or the competition fails, the processing is carried out by spin, rollback and other modes. The overall execution flow is shown in fig. 1.
The utility model discloses a resource competition and task sequence internal subtask concurrent execution processing is carried out to the inside of task sequence that obtains all resources, can adopt asynchronous mode concurrent execution task, in the process of obtaining resources, resource competition and information registration after obtaining resources need to be carried out through unified registration center, the utility model mainly comprises that resource competition and task sequence internal subtask concurrent execution processing are carried out by using registration center mechanism, the utility model is characterized in that ① this embodiment realizes synchronous task execution aiming at distributed environment similar to airborne cloud, resource lock is carried out by using unified registration center, distributed lock competition is solved, and resource release and rollback problems are provided, ② subtasks adopt concurrent processing mode to realize subtask execution, ③ adopts timing release, error release, and release of resource in three modes.
And a task synchronous execution and resource lock competition part: aiming at the situation that a plurality of task sequences are executed in a distributed environment, the execution requirement of a certain task sequence can only be met due to the limitation of some objective factors, and a synchronization mechanism is met at the moment. When a plurality of task sequences need to use the same resource, a resource lock request is initiated firstly, a lock is acquired at a registration center end in a multithread resource competition mode, the task sequence acquiring the lock can continuously run downwards, partial resources acquiring or not acquiring the lock need to be subjected to failure rollback to release the acquired lock, a task sequence execution failure result is returned, and the competition of the resource lock is waited to be initiated again. FIG. 2 is a schematic diagram of resource lock contention, where the UUIDs are the same for the same airplane node; and adopting a file system tool zookeeper as a registration center, when the resource lock competition is successful, creating a directory of the resource, adding a UUID unique mark as the occupation of the resource, and waiting for obtaining the resource lock corresponding to the subtask with the same task sequence next time without competition again.
The concurrent processing of the subtasks realizes asynchronous execution: the task sequence acquiring all resource locks carries out task execution, and for the subtasks in the task sequence, the task execution sequence is controlled by time (each subtask is executed according to a set time sequence), so a multi-thread concurrent mode is adopted, but similar to a distributed environment such as an airborne cloud, task dependence occurs, namely, a return result after the execution of a preorder task is finished can be used as an input parameter of a subsequent task, so that the dependent task needs to be waited for suspension operation, the result is returned after the execution of the current order task is finished, and at this time, the suspended related task is awakened to read the return result and continue to execute the task.
The release of the resource lock is carried out by three types of timing release, error release and completion release. The timed release of the resource lock means that resources are released at a fixed time by calculating the duration of a task execution cycle so as to prevent the resource lock from being released unsuccessfully after the task is executed; the error release means that once the execution of the task fails, the execution of the subsequent task is terminated, and all resource locks are released; and releasing the resource lock after the task is normally executed.
As shown in fig. 1, the specific process of this embodiment is as follows:
step 1) a task sequence execution module sends a request for acquiring a resource lock to a unified registration center, wherein the request comprises a randomly generated UUID corresponding to a current task sequence and resource information (an airplane node ID, a resource type, a weapon node ID and the like) required by a certain subtask in the current task sequence;
step 2) verifying whether the UUID of the current task sequence is consistent with the UUID of the corresponding resource lock recorded by the unified registration center;
step 3), if the resource lock is consistent with the resource lock, the resource lock is successfully acquired; step 5) is directly executed; if the UUID of the corresponding resource lock recorded by the unified registry is empty, the step 4) is executed firstly; if the resource lock is inconsistent with the resource lock, the resource lock is not acquired, and the subsequent steps are not executed;
step 4), the unified registration center receives the request and competitively creates a resource node directory in a multithreading mode; if the resource node directory is successfully created, the resource lock is successfully acquired, and the UUID of the current task sequence is written into a data bit corresponding to the resource node directory; if the creation of the resource node directory fails, a self-spinning operation is carried out, and the continuous competition is returned; if the spinning operation exceeds the upper limit of times, the resource lock acquisition is failed, and the request is terminated; when the resource lock acquisition fails, whether a plurality of subtasks in the preorder of the current task sequence acquire other resource locks is further judged; if yes, releasing the other resource lock, and then terminating the request; if not, directly terminating the request;
step 5) the task sequence execution module judges whether the resource locks required by all the subtasks of the task sequence are successfully contended, and if the contention is successful, the task sequence is executed; otherwise, the execution is started from the step 1) again, and the resource lock of the subsequent subtask of the task sequence is continuously contended. The method comprises the following steps that multiple subtasks in a task sequence are executed in a multi-thread concurrent mode; and the dependent tasks are subjected to waiting suspension operation according to the time sequence relation among the subtasks, the result is returned after the execution of the current sequence subtask is finished, and at the moment, the suspended related subtasks are awakened to read the returned result and continue to execute the tasks.
Claims (10)
1. The task synchronization and execution method facing the distributed platform is characterized by comprising the following steps:
step 1) a task sequence execution module sends a request for acquiring a resource lock to a unified registration center, wherein the request comprises a randomly generated UUID corresponding to a current task sequence and resource information required by a certain subtask in the current task sequence;
step 2) verifying whether the UUID of the current task sequence is consistent with the UUID of the corresponding resource lock recorded by the unified registration center;
step 3), if the resource lock is consistent with the resource lock, the resource lock is successfully acquired; step 5) is directly executed; if the UUID of the corresponding resource lock recorded by the unified registry is empty, the step 4) is executed firstly; if the resource lock is inconsistent with the resource lock, the resource lock is not acquired, and the subsequent steps are not executed;
step 4), the unified registration center receives the request and competitively creates a resource node directory in a multithreading mode; if the resource node directory is successfully created, the resource lock is successfully acquired, and the UUID of the current task sequence is written into a data bit corresponding to the resource node directory; if the creation of the resource node directory fails, a self-spinning operation is carried out, and the continuous competition is returned;
step 5) the task sequence execution module judges whether the resource locks required by all the subtasks of the task sequence are successfully contended, and if the contention is successful, the task sequence is executed; otherwise, the execution is started from the step 1) again, and the resource lock of the subsequent subtask of the task sequence is continuously contended.
2. The distributed platform-oriented task synchronization and execution method according to claim 1, wherein: the resource information in the step 1) comprises a primary node ID, a resource category and a secondary node ID.
3. The distributed platform-oriented task synchronization and execution method according to claim 1, wherein: and for the spin operation in the step 4), if the spin operation exceeds the upper limit of times, the acquisition of the resource lock is failed, and the current request is terminated.
4. The distributed platform-oriented task synchronization and execution method according to claim 3, wherein: when the resource lock acquisition fails, whether a plurality of subtasks in the preorder of the current task sequence acquire other resource locks is further judged; if yes, releasing the other resource lock, and then terminating the request; if not, the request is directly terminated.
5. The distributed platform-oriented task synchronization and execution method according to claim 1, wherein: the primary node is an airplane node, and the secondary node is a functional equipment node; the task sequence execution module runs on any airplane node of the distributed platform, and the unified registration center is carried on a set airplane node or a ground command center.
6. The distributed platform-oriented task synchronization and execution method according to claim 1, wherein: executing the task sequence in the step 5), and executing a plurality of subtasks in the task sequence in a multi-thread concurrent mode; and the dependent tasks are subjected to waiting suspension operation according to the time sequence relation among the subtasks, the result is returned after the execution of the current sequence subtask is finished, and at the moment, the suspended related subtasks are awakened to read the returned result and continue to execute the tasks.
7. A distributed node comprising a processor and a program memory, characterized in that: the program memory stores a program that can be loaded by the processor to perform the steps of:
step 1) sending a request for acquiring a resource lock to a unified registration center, wherein the request comprises a randomly generated UUID corresponding to a current task sequence and resource information required by a certain subtask in the current task sequence;
step 2) verifying whether the UUID of the current task sequence is consistent with the UUID of the corresponding resource lock recorded by the unified registration center;
step 3), if the resource lock is consistent with the resource lock, the resource lock is successfully acquired; step 5) is directly executed; if the UUID of the corresponding resource lock recorded by the unified registry is empty, the step 4) is executed firstly; if not, the resource lock acquisition is failed, the subsequent steps are not executed, and the request is terminated;
step 4) responding to the result of the unified registration center for competing and establishing the resource node catalog in a multithreading mode; if the resource node directory is successfully created, the resource lock is successfully acquired, and the UUID of the current task sequence is written into a data bit corresponding to the resource node directory; if the creation of the resource node directory fails, a self-spinning operation is carried out, and the continuous competition is returned;
step 5) judging whether the resource locks required by all the subtasks of the task sequence are successfully contended, and if the contention is successful, executing the task sequence; otherwise, the execution is started from the step 1) again, and the resource lock of the subsequent subtask of the task sequence is continuously contended.
8. A distributed node according to claim 7, wherein: the resource information includes a primary node ID, a resource category, and a secondary node ID.
9. A distributed node according to claim 7, wherein: for the spin operation in the step 4), if the spin operation exceeds the upper limit of times, the acquisition of the resource lock is failed, and the current request is terminated; when the resource lock acquisition fails, whether a plurality of subtasks in the preorder of the current task sequence acquire other resource locks is further judged; if yes, releasing the other resource lock, and then terminating the request; if not, the request is directly terminated.
10. A distributed node according to claim 7, wherein: executing the task sequence in the step 5), and executing a plurality of subtasks in the task sequence in a multi-thread concurrent mode; and the dependent tasks are subjected to waiting suspension operation according to the time sequence relation among the subtasks, the result is returned after the execution of the current sequence subtask is finished, and at the moment, the suspended related subtasks are awakened to read the returned result and continue to execute the tasks.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010001872.5A CN111124697B (en) | 2020-01-02 | 2020-01-02 | Task synchronization and execution method for distributed platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010001872.5A CN111124697B (en) | 2020-01-02 | 2020-01-02 | Task synchronization and execution method for distributed platform |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111124697A true CN111124697A (en) | 2020-05-08 |
CN111124697B CN111124697B (en) | 2023-09-08 |
Family
ID=70507382
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010001872.5A Active CN111124697B (en) | 2020-01-02 | 2020-01-02 | Task synchronization and execution method for distributed platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111124697B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100023521A1 (en) * | 2008-07-28 | 2010-01-28 | International Business Machines Corporation | System and method for managing locks across distributed computing nodes |
CN101800763A (en) * | 2009-02-05 | 2010-08-11 | 威睿公司 | hybrid locking using network and on-disk based schemes |
CN104702655A (en) * | 2014-03-21 | 2015-06-10 | 杭州海康威视系统技术有限公司 | Cloud storage resource distribution method and system |
CN106325980A (en) * | 2015-06-30 | 2017-01-11 | 中国石油化工股份有限公司 | Multi-thread concurrent system |
CN106572130A (en) * | 2015-10-09 | 2017-04-19 | 阿里巴巴集团控股有限公司 | Method used for realizing distributed lock management and equipment thereof |
CN107133108A (en) * | 2017-04-27 | 2017-09-05 | 努比亚技术有限公司 | Implementation method, terminal, server and the computer-readable recording medium of distributed complex lock |
CN107608773A (en) * | 2017-08-24 | 2018-01-19 | 阿里巴巴集团控股有限公司 | task concurrent processing method, device and computing device |
CN108038005A (en) * | 2017-12-28 | 2018-05-15 | 广东蜂助手网络技术股份有限公司 | Shared resource access method, client, server-side, system based on zookeeper |
CN109753540A (en) * | 2018-12-03 | 2019-05-14 | 新华三云计算技术有限公司 | Shared resource access method, device and computer-readable storage medium |
CN109753364A (en) * | 2018-12-28 | 2019-05-14 | 北京明朝万达科技股份有限公司 | A kind of implementation method, equipment and the medium of network-based distributed lock |
CN110445864A (en) * | 2019-08-11 | 2019-11-12 | 西藏宁算科技集团有限公司 | The realization method and system of distributed lock under a kind of cloud computing environment |
-
2020
- 2020-01-02 CN CN202010001872.5A patent/CN111124697B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100023521A1 (en) * | 2008-07-28 | 2010-01-28 | International Business Machines Corporation | System and method for managing locks across distributed computing nodes |
CN101800763A (en) * | 2009-02-05 | 2010-08-11 | 威睿公司 | hybrid locking using network and on-disk based schemes |
CN104702655A (en) * | 2014-03-21 | 2015-06-10 | 杭州海康威视系统技术有限公司 | Cloud storage resource distribution method and system |
CN106325980A (en) * | 2015-06-30 | 2017-01-11 | 中国石油化工股份有限公司 | Multi-thread concurrent system |
CN106572130A (en) * | 2015-10-09 | 2017-04-19 | 阿里巴巴集团控股有限公司 | Method used for realizing distributed lock management and equipment thereof |
CN107133108A (en) * | 2017-04-27 | 2017-09-05 | 努比亚技术有限公司 | Implementation method, terminal, server and the computer-readable recording medium of distributed complex lock |
CN107608773A (en) * | 2017-08-24 | 2018-01-19 | 阿里巴巴集团控股有限公司 | task concurrent processing method, device and computing device |
CN108038005A (en) * | 2017-12-28 | 2018-05-15 | 广东蜂助手网络技术股份有限公司 | Shared resource access method, client, server-side, system based on zookeeper |
CN109753540A (en) * | 2018-12-03 | 2019-05-14 | 新华三云计算技术有限公司 | Shared resource access method, device and computer-readable storage medium |
CN109753364A (en) * | 2018-12-28 | 2019-05-14 | 北京明朝万达科技股份有限公司 | A kind of implementation method, equipment and the medium of network-based distributed lock |
CN110445864A (en) * | 2019-08-11 | 2019-11-12 | 西藏宁算科技集团有限公司 | The realization method and system of distributed lock under a kind of cloud computing environment |
Non-Patent Citations (1)
Title |
---|
刘芬;王芳;田昊;: "基于Zookeeper的分布式锁服务及性能优化", 计算机研究与发展, no. 1 * |
Also Published As
Publication number | Publication date |
---|---|
CN111124697B (en) | 2023-09-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US5193186A (en) | Processor system for executing processes in parallel under multitask, control method of waiting for event of process | |
JP3807588B2 (en) | Multi-thread processing apparatus, processing method, and computer-readable recording medium storing multi-thread program | |
US20070206611A1 (en) | Effective high availability cluster management and effective state propagation for failure recovery in high availability clusters | |
JPH1165863A (en) | Common resource managing method | |
WO2011137672A1 (en) | Method and device for task execution based on database | |
CN112527489A (en) | Task scheduling method, device and equipment and computer readable storage medium | |
US8190857B2 (en) | Deleting a shared resource node after reserving its identifier in delete pending queue until deletion condition is met to allow continued access for currently accessing processor | |
EP0365728A1 (en) | Resource access for a multiprocessing computer system | |
CN111258726A (en) | Task scheduling method and device | |
CN111459622A (en) | Method and device for scheduling virtual CPU, computer equipment and storage medium | |
CN111930492B (en) | Task flow scheduling method and system based on decoupling task data model | |
CN101189579A (en) | Behavioral model based multi-threaded architecture | |
CN111177164B (en) | Vehicle real-time information scheduling method based on timing task framework | |
CN110908968B (en) | Method, device, equipment and storage medium for avoiding frightened groups during file lock unlocking | |
CN115964176B (en) | Cloud computing cluster scheduling method, electronic equipment and storage medium | |
CN111124697A (en) | Task synchronization and execution method facing distributed platform | |
CN111930503A (en) | Resource lock acquisition method based on ETCD | |
Fan et al. | A scheduler for serverless framework base on kubernetes | |
CN112162840B (en) | Coroutine processing and management method based on interrupt reentry mechanism | |
CN115269136A (en) | Heterogeneous multi-core platform partition operating system safety scheduling method and system | |
CN111767155A (en) | Deadlock detection method, device, equipment and computer readable storage medium | |
CN113961364A (en) | Large-scale lock system implementation method and device, storage medium and server | |
CN112749020A (en) | Microkernel optimization method of Internet of things operating system | |
CN113094260A (en) | Distributed system time sequence relation modeling and simulation analysis method | |
CN112346835A (en) | Scheduling processing method and system based on coroutine |
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 |