A time-accurate real-time parallel I / O task control method

Abstract

The present invention discloses a time-accurate real-time parallel I / O task control method, which comprises the following steps: constructing an I / O device information model, constructing a task information model, performing time predictability modeling according to a system's time predictability requirement, and constructing an execution model; constructing a linear programming model according to the I / O device information model, the task information model, and the execution model; modeling the I / O time accuracy into a linearized optimization target according to a time-accurate quality model, and integrating the optimization target with the linear programming model to obtain a time accuracy optimization problem model; solving the time accuracy optimization problem model to obtain an I / O allocation scheduling scheme, and performing real-time parallel I / O task control; the present invention can optimize the I / O time accuracy to the maximum extent by modeling the task information, time predictability, and time accuracy optimization targets into a linear programming model, and can be widely applied in the field of computer technology.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a time-accurate real-time parallel I / O task control method. Background Art

[0002] Real-time I / O control is a key area of research in computer science and engineering. It involves the design and implementation of input / output systems that operate with a high degree of temporal precision, ensuring that input and output operations occur at the exact time they are scheduled or expected, with minimal variability. Specifically, real-time requirements for I / O execution have two aspects: 1) temporal predictability, which requires that I / O tasks complete before their deadlines; and 2) temporal accuracy, which requires that I / O tasks begin executing at or near their ideal time. The need for real-time I / O control arises in many time-critical applications. For example, in real-time systems such as industrial process control systems, transportation systems, and defense systems, timely and accurate I / O is crucial to the proper operation and safety of the entire system. In audio and video processing, precise timing of I / O operations is required to ensure the synchronization of audio and video signal acquisition, processing, and playback.

[0003] To achieve real-time I / O control, several challenges must be overcome. First, a high-performance I / O subsystem must be designed and implemented that can respond to the large number of I / O requests generated in the system while supporting the accurate execution of I / O commands. In addition, a real-time scheduling algorithm must be developed that is compatible with the I / O subsystem to ensure that I / O operations are scheduled and executed at the ideal time as much as possible. Existing methods implement a hardware-based I / O subsystem, but only support queue-based scheduling and cannot achieve accurate I / O execution. Other methods implement an I / O subsystem that supports offline scheduling schemes, but the I / O task scheduling method they propose relies on heuristic algorithms and does not optimize the time accuracy of I / O. In addition, existing scheduling algorithms assume that there is only one available device for each type of I / O request, and therefore cannot support the accurate execution of parallel I / O.

[0004] However, since each time a file is written, the data must first be converted into character type and then all the characters are written to the file, this method of writing files is inefficient. If the file is large, it will take a long time to convert all the data into characters, which will seriously affect the speed of data processing. When reading data from a file, the read characters must first be converted into the required data format, so the efficiency of reading data from the file is also very low.

[0005] In summary, the shortcomings of existing scheduling algorithms are: (1) Heuristic and extensive scheduling cannot effectively optimize the time accuracy of tasks. The time accuracy of I / O tasks will significantly decrease as the system utilization increases. (2) Existing scheduling algorithms do not have resource allocation algorithms for multiple I / O devices, and thus cannot support the execution of parallel I / O tasks with time accuracy. Summary of the Invention

[0006] In view of this, an embodiment of the present invention provides a time-accurate real-time parallel I / O task control method to achieve refined scheduling of I / O tasks and I / O resource allocation that supports time accuracy.

[0007] An aspect of an embodiment of the present invention provides a time-accurate real-time parallel I / O task control method, comprising:

[0008] Constructing an I / O device information model; wherein the content of the I / O device information model includes the type of I / O device and the number of I / O devices;

[0009] Constructing a task information model; wherein the content of the task information model includes I / O request cycle, task execution time, and ideal running time point;

[0010] Based on the system's time predictability requirements, time predictability modeling is performed to construct an execution model; the execution model is used to plan I / O tasks to complete before deadlines, and to plan I / O task instances released in each request cycle to complete execution before the next instance is released;

[0011] Constructing a linear programming model according to the I / O device information model, the task information model and the execution model;

[0012] Modeling I / O time accuracy as a linearized optimization target based on the time-accurate quality model, and integrating the optimization target with the linear programming model to obtain a time accuracy optimization problem model;

[0013] The time accuracy optimization problem model is solved to obtain an I / O allocation scheduling scheme, and real-time parallel I / O task control is performed based on the I / O allocation scheduling scheme.

[0014] Optionally, the constructing of the I / O device information model includes:

[0015] An I / O device set is constructed according to the types of I / O devices in the system and the number of I / O devices of the same type. Each element in the I / O device set is used to represent a set of I / O devices of one type.

[0016] Optionally, the constructing the task information model includes:

[0017] Construct a quality model for time accuracy based on the time accuracy interval of the task, the maximum accuracy that can be achieved when the task starts executing at the ideal time, and the minimum time accuracy that can be achieved when the task is completed before the deadline;

[0018] The running time, cycle, deadline, start time and quality model of the time accuracy of each task are obtained to construct a task information model.

[0019] Optionally, performing time predictability modeling and constructing an execution model based on the time predictability requirements of the system includes:

[0020] According to the requirement that each task instance must be completed before the deadline, a linear constraint expression is constructed to complete the time predictability modeling and obtain the execution model.

[0021] Optionally, constructing a linear programming model according to the I / O device information model, the task information model, and the execution model includes:

[0022] Assign each task instance to an I / O device for execution, and construct the first linear constraint for task execution;

[0023] For any two task instances assigned to the same I / O device, the execution time of each task instance cannot overlap, and the second linear constraint of task execution is constructed;

[0024] According to the adjustment of the first linear constraint and the second linear constraint, the constraint on the execution time of the task is obtained, thereby completing the construction of the linear programming model.

[0025] Optionally, the I / O time accuracy is modeled as a linearized optimization target based on the time-accurate quality model, and the optimization target is integrated with the linear programming model to obtain a time accuracy optimization problem model, including:

[0026] The I / O task instance is controlled to be scheduled and executed within the target time period at the ideal time point, thereby establishing a linear constraint between the ideal execution time and the specific execution time of the I / O task instance;

[0027] According to the linear constraint between the ideal execution time and the specific execution time, a linear constraint for the actual accuracy quality is constructed, and then the optimization target configuration of the linear programming model is completed to obtain a time accuracy optimization problem model.

[0028] Another aspect of the present invention provides a time-accurate real-time parallel I / O task control device, comprising:

[0029] The first module is used to construct an I / O device information model; wherein the content of the I / O device information model includes the type of I / O device and the number of I / O devices;

[0030] The second module is used to build a task information model; wherein the content of the task information model includes I / O request cycle, task execution time, and ideal running time point;

[0031] The third module is used to perform time predictability modeling and construct an execution model based on the system's time predictability requirements; the execution model is used to plan the completion of I / O tasks before the deadline and to plan the completion of I / O task instances released in each request cycle before the next instance is released;

[0032] A fourth module is configured to construct a linear programming model based on the I / O device information model, the task information model, and the execution model;

[0033] A fifth module is configured to model the I / O time accuracy into a linearized optimization target based on the time-accurate quality model, and integrate the optimization target with the linear programming model to obtain a time accuracy optimization problem model;

[0034] The sixth module is used to solve the time accuracy optimization problem model to obtain an I / O allocation scheduling solution, and perform real-time parallel I / O task control based on the I / O allocation scheduling solution.

[0035] Another aspect of an embodiment of the present invention further provides an electronic device, including a processor and a memory;

[0036] The memory is used to store programs;

[0037] The processor executes the program to implement the method described above.

[0038] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.

[0039] The present invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the above method.

[0040] An embodiment of the present invention first constructs an I / O device information model, then constructs a task information model, and then, based on the time predictability requirements of the system, performs time predictability modeling and constructs an execution model; then, based on the I / O device information model, the task information model and the execution model, a linear programming model is constructed; based on a time-accurate quality model, the I / O time accuracy is modeled into a linearized optimization target, and the optimization target is integrated with the linear programming model to obtain a time accuracy optimization problem model; finally, the time accuracy optimization problem model is solved to obtain an I / O allocation scheduling scheme, and real-time parallel I / O task control is performed based on the I / O allocation scheduling scheme; the present invention can optimize I / O time accuracy to the maximum extent by modeling task information, time predictability and time accuracy optimization targets into a linear programming model. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1 It is a flow chart of the overall steps of the present invention;

[0043] Figure 2 A function diagram of the task quality model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0045] In order to solve the problems existing in the prior art, an embodiment of the present invention provides a time-accurate real-time parallel I / O task control method, comprising:

[0046] Constructing an I / O device information model; wherein the content of the I / O device information model includes the type of I / O device and the number of I / O devices;

[0047] Constructing a task information model; wherein the content of the task information model includes I / O request cycle, task execution time, and ideal running time point;

[0048] Based on the system's time predictability requirements, time predictability modeling is performed to construct an execution model; the execution model is used to plan I / O tasks to complete before deadlines, and to plan I / O task instances released in each request cycle to complete execution before the next instance is released;

[0049] Constructing a linear programming model according to the I / O device information model, the task information model and the execution model;

[0050] Modeling I / O time accuracy as a linearized optimization target based on the time-accurate quality model, and integrating the optimization target with the linear programming model to obtain a time accuracy optimization problem model;

[0051] The time accuracy optimization problem model is solved to obtain an I / O allocation scheduling scheme, and real-time parallel I / O task control is performed based on the I / O allocation scheduling scheme.

[0052] Optionally, the constructing of the I / O device information model includes:

[0053] An I / O device set is constructed according to the types of I / O devices in the system and the number of I / O devices of the same type. Each element in the I / O device set is used to represent a set of I / O devices of one type.

[0054] Optionally, the constructing the task information model includes:

[0055] Construct a quality model for time accuracy based on the time accuracy interval of the task, the maximum accuracy that can be achieved when the task starts executing at the ideal time, and the minimum time accuracy that can be achieved when the task is completed before the deadline;

[0056] The running time, cycle, deadline, start time and quality model of the time accuracy of each task are obtained to construct a task information model.

[0057] Optionally, performing time predictability modeling and constructing an execution model based on the time predictability requirements of the system includes:

[0058] According to the requirement that each task instance must be completed before the deadline, a linear constraint expression is constructed to complete the time predictability modeling and obtain the execution model.

[0059] Optionally, constructing a linear programming model according to the I / O device information model, the task information model, and the execution model includes:

[0060] Assign each task instance to an I / O device for execution, and construct the first linear constraint for task execution;

[0061] For any two task instances assigned to the same I / O device, the execution time of each task instance cannot overlap, and the second linear constraint of task execution is constructed;

[0062] According to the adjustment of the first linear constraint and the second linear constraint, the constraint on the execution time of the task is obtained, thereby completing the construction of the linear programming model.

[0063] Optionally, the I / O time accuracy is modeled as a linearized optimization target based on the time-accurate quality model, and the optimization target is integrated with the linear programming model to obtain a time accuracy optimization problem model, including:

[0064] The I / O task instance is controlled to be scheduled and executed within the target time period at the ideal time point, thereby establishing a linear constraint between the ideal execution time and the specific execution time of the I / O task instance;

[0065] According to the linear constraint between the ideal execution time and the specific execution time, a linear constraint for the actual accuracy quality is constructed, and then the optimization target configuration of the linear programming model is completed to obtain a time accuracy optimization problem model.

[0066] Another aspect of the present invention provides a time-accurate real-time parallel I / O task control device, comprising:

[0067] The first module is used to construct an I / O device information model; wherein the content of the I / O device information model includes the type of I / O device and the number of I / O devices;

[0068] The second module is used to build a task information model; wherein the content of the task information model includes I / O request cycle, task execution time, and ideal running time point;

[0069] The third module is used to perform time predictability modeling and construct an execution model based on the system's time predictability requirements; the execution model is used to plan the completion of I / O tasks before the deadline and to plan the completion of I / O task instances released in each request cycle before the next instance is released;

[0070] A fourth module is configured to construct a linear programming model based on the I / O device information model, the task information model, and the execution model;

[0071] A fifth module is configured to model the I / O time accuracy into a linearized optimization target based on the time-accurate quality model, and integrate the optimization target with the linear programming model to obtain a time accuracy optimization problem model;

[0072] The sixth module is used to solve the time accuracy optimization problem model to obtain an I / O allocation scheduling solution, and perform real-time parallel I / O task control based on the I / O allocation scheduling solution.

[0073] Another aspect of an embodiment of the present invention further provides an electronic device, including a processor and a memory;

[0074] The memory is used to store programs;

[0075] The processor executes the program to implement the method described above.

[0076] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.

[0077] The present invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the above method.

[0078] The specific implementation process of the present invention is described in detail below with reference to the accompanying drawings:

[0079] like Figure 1 As shown, the overall implementation process of the present invention includes the following steps:

[0080] A. I / O device modeling: Model the I / O device information contained in the I / O subsystem, including the type of I / O device, the number of similar I / O devices, etc.

[0081] B. Task modeling: Model the I / O requests in the system into periodic I / O tasks, which include the I / O request cycle, execution time, ideal running time point, etc.

[0082] C. Modeling the time predictability requirement: Model the system's time predictability requirement, that is, to ensure that I / O tasks are completed before the deadline. The I / O task instances released in each request cycle need to be completed before the next instance is released.

[0083] D. Linear programming model integration: Integrate I / O devices and task information, meet the time predictability requirements and non-preemptive requirements, and build a linear programming model.

[0084] E. Modeling of time accuracy optimization problem: Based on the time-accurate quality model, I / O time accuracy is modeled as a linear optimization objective and integrated with the linear programming model in D.

[0085] F. Solve the model to obtain the I / O allocation and scheduling plan: By solving the linear programming model and maximizing the accuracy optimization goal in E, the allocation and scheduling plan of I / O tasks is obtained.

[0086] Optionally, in step A, this embodiment considers a system containing multiple I / O devices of the same type, represented as in Represents a device collection, which contains M I / O devices of the same type.

[0087] A periodic I / O task in step B can be expressed as τ i ={C i ,T i ,D i ,δ i ,Φ i}, where C i Represents the running time of the task, T i Represents the cycle of the I / O task, D i is the deadline of the task, generally equal to T i , δ i is the ideal start time of the task, Φ i is the quality model of time accuracy. The quality model of time accuracy can be expressed as Φ i ={θ i ,V i max ,V i min}, where θ i is the time accuracy interval of the task. If an I / O task is in the interval [δ i -θ i ,δ i +θ i ], it still has a certain degree of time accuracy; V i max is the maximum accuracy that the task can obtain when it starts executing at the ideal time, V i min It is the minimum time accuracy that can be achieved if the task is completed before the deadline.

[0088] The I / O task in each release cycle can be regarded as a task instance, such as task τ i The instances released in the jth cycle are denoted as in Representation instance The specific execution time of is obtained by solving the linear programming model; represents the ideal execution time of the instance; V i j Indicates the actual accuracy quality of the instance. In its accuracy range When the execution starts, Far from ideal time The mass of the task instance will be increased at a fixed rate from V i max Decay to V i min .

[0089] The time predictability modeling in step C requires that each task instance be completed before its deadline. The embodiment of the present invention constructs the following linear constraints:

[0090]

[0091] The linear model integration in step D includes the task instance allocation problem on multiple devices of the same type and the non-preemptive constraint on a single device. The task instance allocation problem requires that each task instance be assigned to an I / O device for execution. It means is assigned to device m for execution, otherwise is 0. Since an instance can only be executed on one device, this embodiment has the following linear constraints:

[0092]

[0093] For any two instances assigned to the same I / O device, the non-preemptive constraint requires that there should not be any overlap in the execution time between the instances. Representation instance With examples are executed on device m and Execute first, otherwise so For any two instances assigned to I / O device m, the present invention establishes the following constraints:

[0094]

[0095] Taking into account is a nonlinear term. The present invention replaces the above formula with the following linear constraint:

[0096]

[0097]

[0098]

[0099] Regarding the execution time of the task, this embodiment has the following constraints:

[0100]

[0101] Among them, T H Refers to the super period of all I / O tasks in the system.

[0102] In step E, the time accuracy optimization problem is modeled. The present invention schedules the execution of I / O task instances as close to their ideal time points as possible to maximize the time accuracy quality of the entire system. The quality model considered in this embodiment is as follows: Figure 2 As shown, the actual execution time The closer to the ideal time point, the higher the execution quality. express and The distance is the following linear constraint:

[0103]

[0104]

[0105] Considering that this embodiment minimizes To optimize the execution quality, there is no need to set an upper bound. This embodiment transforms the task quality model into a monotonically decreasing function based on Q, such as Figure 2 As shown:

[0106] This function is in When , it can be expressed as the following linear form:

[0107]

[0108] in, b=V i max , are constants. 0-1 variables express Start execution within the quality interval, i.e. otherwise is 0. Therefore, this embodiment obtains the value of V i j The following linear constraints:

[0109]

[0110]

[0111] The optimization objective of the linear programming model is set as:

[0112]

[0113] in, Represents a collection of task instances in the system.

[0114] In summary, the present invention has the following advantages:

[0115] 1. By modeling the task information, time predictability, and time accuracy optimization objectives into a linear programming model, the proposed scheduling solution can maximize the I / O time accuracy while ensuring time predictability.

[0116] 2. By modeling device information and combining it with the I / O scheduling algorithm to form a linear programming model, an I / O task allocation solution that can maximize time accuracy is given.

[0117] The methods proposed in this paper all have higher time accuracy. Through refined task scheduling, the present invention can effectively improve the time accuracy of I / O tasks. The methods of this invention can maintain extremely high time accuracy across different numbers of I / O devices, demonstrating that the I / O task allocation algorithm can effectively support the parallel execution of I / O tasks with time accuracy.

[0118] The following describes the specific application process of the method of the present invention in detail using a specific application scenario as an example:

[0119] For example, in emergency braking situations in current autonomous driving, the anti-lock braking system requires that multiple periodic I / O operations be completed strictly before the deadline to ensure safety. At the same time, if I / O operations are executed at or near the ideal time point, a shorter braking distance can be achieved. Specifically, the I / O device information in the vehicle is modeled according to the form in A, and the I / O tasks are modeled according to the form in B. Then, according to this method, a specific execution time plan for each periodic I / O operation is derived, and this plan is pre-loaded into the computing platform in the vehicle. When an emergency braking command occurs, each I / O command will be executed strictly according to the plan to obtain the time accuracy of the system I / O tasks.

[0120] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operation and logic flow presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0121] Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise indicated, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It will also be understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the ordinary skill of an engineer. Therefore, a person skilled in the art using ordinary skill will be able to implement the present invention set forth in the claims without undue experimentation. It will also be understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0122] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0123] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0124] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0125] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0126] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0127] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0128] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A time-accurate real-time parallel I / O task control method, characterized in that: include: Constructing an I / O device information model; wherein the content of the I / O device information model includes the type of I / O device and the number of I / O devices; Constructing a task information model; wherein the content of the task information model includes I / O request cycle, task execution time, and ideal running time point; Based on the system's time predictability requirements, time predictability modeling is performed to construct an execution model; the execution model is used to plan I / O tasks to complete before deadlines, and to plan I / O task instances released in each request cycle to complete execution before the next instance is released; Constructing a linear programming model according to the I / O device information model, the task information model and the execution model; Modeling I / O time accuracy as a linearized optimization target based on the time-accurate quality model, and integrating the optimization target with the linear programming model to obtain a time accuracy optimization problem model; The time accuracy optimization problem model is solved to obtain an I / O allocation scheduling scheme, and real-time parallel I / O task control is performed based on the I / O allocation scheduling scheme.

2. The time-accurate real-time parallel I / O task control method according to claim 1, characterized in that: The constructing of the I / O device information model includes: An I / O device set is constructed according to the types of I / O devices in the system and the number of I / O devices of the same type. Each element in the I / O device set is used to represent a set of I / O devices of one type.

3. The time-accurate real-time parallel I / O task control method according to claim 1, characterized in that: The constructing of the task information model includes: Construct a quality model for time accuracy based on the time accuracy interval of the task, the maximum accuracy that can be achieved when the task starts executing at the ideal time, and the minimum time accuracy that can be achieved when the task is completed before the deadline; The running time, cycle, deadline, start time and quality model of the time accuracy of each task are obtained to construct a task information model.

4. The time-accurate real-time parallel I / O task control method according to claim 1, characterized in that: According to the time predictability requirements of the system, time predictability modeling is performed and an execution model is constructed, including: According to the requirement that each task instance must be completed before the deadline, a linear constraint expression is constructed to complete the time predictability modeling and obtain the execution model.

5. The time-accurate real-time parallel I / O task control method according to claim 1, characterized in that: The constructing of a linear programming model according to the I / O device information model, the task information model and the execution model includes: Assign each task instance to an I / O device for execution, and construct the first linear constraint for task execution; For any two task instances assigned to the same I / O device, the execution time of each task instance cannot overlap, and the second linear constraint of task execution is constructed; According to the adjustment of the first linear constraint and the second linear constraint, the constraint on the execution time of the task is obtained, thereby completing the construction of the linear programming model.

6. The time-accurate real-time parallel I / O task control method according to claim 1, characterized in that: The I / O time accuracy is modeled as a linearized optimization target based on the time-accurate quality model, and the optimization target is integrated with the linear programming model to obtain a time accuracy optimization problem model, including: The I / O task instance is controlled to be scheduled and executed within the target time period at the ideal time point, thereby establishing a linear constraint between the ideal execution time and the specific execution time of the I / O task instance; According to the linear constraint between the ideal execution time and the specific execution time, a linear constraint for the actual accuracy quality is constructed, and then the optimization target configuration of the linear programming model is completed to obtain a time accuracy optimization problem model.

7. A time-accurate real-time parallel I / O task control device, characterized in that: include: The first module is used to construct an I / O device information model; wherein the content of the I / O device information model includes the type of I / O device and the number of I / O devices; The second module is used to build a task information model; wherein the content of the task information model includes I / O request cycle, task execution time, and ideal running time point; The third module is used to perform time predictability modeling and construct an execution model based on the system's time predictability requirements; the execution model is used to plan the completion of I / O tasks before the deadline and to plan the completion of I / O task instances released in each request cycle before the next instance is released; A fourth module is configured to construct a linear programming model based on the I / O device information model, the task information model, and the execution model; A fifth module is configured to model the I / O time accuracy into a linearized optimization target based on the time-accurate quality model, and integrate the optimization target with the linear programming model to obtain a time accuracy optimization problem model; The sixth module is used to solve the time accuracy optimization problem model to obtain an I / O allocation scheduling solution, and perform real-time parallel I / O task control based on the I / O allocation scheduling solution.

8. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images