CN109471715B - Method and device for scheduling transcoding task and storage medium - Google Patents
Method and device for scheduling transcoding task and storage medium Download PDFInfo
- Publication number
- CN109471715B CN109471715B CN201811084239.6A CN201811084239A CN109471715B CN 109471715 B CN109471715 B CN 109471715B CN 201811084239 A CN201811084239 A CN 201811084239A CN 109471715 B CN109471715 B CN 109471715B
- Authority
- CN
- China
- Prior art keywords
- transcoding
- task
- determining
- initial
- concurrency number
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012937 correction Methods 0.000 claims description 49
- 238000004364 calculation method Methods 0.000 claims description 28
- 238000012986 modification Methods 0.000 claims description 3
- 230000004048 modification Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 16
- 238000012545 processing Methods 0.000 description 8
- 238000013461 design Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000013178 mathematical model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
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
- G06F9/50—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
- G06F9/505—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 considering the load
-
- 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]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
- G06F9/5088—Techniques for rebalancing the load in a distributed system involving task migration
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention discloses a method for scheduling a transcoding task, which comprises the following steps: determining a transcoding multiple and an initial transcoding concurrency number corresponding to a current transcoding task, wherein the transcoding multiple is used for representing the execution efficiency of the current transcoding task; inputting the received first feedback input information and the second feedback input information into a target model to obtain a feedback output value; determining the optimal transcoding concurrency number corresponding to the current transcoding task under the condition that the transcoding multiple meets the corresponding set condition according to the feedback output value and the initial transcoding concurrency number; and scheduling the current transcoding task based on the optimal transcoding concurrency number. The invention also discloses a device for scheduling the transcoding task and a storage medium.
Description
Technical Field
The invention relates to the technical field of distributed transcoding, in particular to a method and a device for scheduling a transcoding task and a storage medium.
Background
Currently, in a distributed transcoding system, a scheduling policy based on a Central Processing Unit (CPU) load is generally adopted, that is, the number of tasks to be transcoded concurrently is adjusted according to a load condition of the CPU, or the number of tasks to be transcoded concurrently is controlled according to a constant empirical value.
However, there are some other factors that affect the number of concurrent transcoding tasks, in addition to the CPU load. Therefore, under the condition of not considering other influence factors, the task number of the concurrent transcoding determined only according to the load condition of the CPU is probably not the optimal task number of the concurrent transcoding, so that the concurrent transcoding efficiency of the transcoding system is reduced.
Disclosure of Invention
In view of the above, embodiments of the present invention are intended to provide a method, an apparatus, and a storage medium for scheduling a transcoding task, so as to at least solve the problem in the related art that it is difficult to effectively improve the concurrent transcoding efficiency of a transcoding system.
In order to achieve the above purpose, the technical solution of the embodiment of the present invention is realized as follows:
in a first aspect, an embodiment of the present invention provides a method for scheduling a transcoding task, where the method includes:
determining a transcoding multiple and an initial transcoding concurrency number corresponding to a current transcoding task, wherein the transcoding multiple is used for representing the execution efficiency of the current transcoding task;
inputting received first feedback input information and second feedback input information into a target model to obtain a feedback output value, wherein the first feedback input information is used for representing a first time length of the content to be transcoded corresponding to the current transcoding task, the second feedback input information is used for representing a second time length consumed by executing the transcoding task aiming at the content to be transcoded, and the feedback output value is used for adjusting the initial transcoding concurrency number;
determining the optimal transcoding concurrency number corresponding to the current transcoding task under the condition that the transcoding multiple meets the corresponding set condition according to the feedback output value and the initial transcoding concurrency number;
and scheduling the current transcoding task based on the optimal transcoding concurrency number.
In a second aspect, an embodiment of the present invention further provides a device for scheduling a transcoding task, where the device includes: the system comprises a first determining module, an obtaining module, a second determining module and a scheduling module; wherein,
the first determining module is used for determining a transcoding multiple and an initial transcoding concurrence number corresponding to the current transcoding task, wherein the transcoding multiple is used for representing the execution efficiency of the current transcoding task;
the obtaining module is configured to input received first feedback input information and second feedback input information into a target model to obtain a feedback output value, where the first feedback input information is used to represent a first time length of a content to be transcoded corresponding to the current transcoding task, the second feedback input information is used to represent a second time length consumed by executing a transcoding task for the content to be transcoded, and the feedback output value is used to adjust the initial transcoding concurrence number;
the second determining module is configured to determine, according to the feedback output value and the initial transcoding concurrency number, an optimal transcoding concurrency number corresponding to the current transcoding task when the transcoding multiple satisfies a corresponding set condition;
and the scheduling module is used for scheduling the current transcoding task based on the optimal transcoding concurrency number.
In the foregoing solution, the first determining module is specifically configured to: and obtaining a first calculation result based on the ratio of the first time length to the second time length, and determining the first calculation result as the transcoding multiple corresponding to the current transcoding task.
In the above solution, the apparatus further includes the following modules to determine the target model:
the third determining module is used for determining the initial model and the correction coefficient;
and the fourth determining module is used for determining the target model according to the initial model and the correction coefficient.
In the foregoing solution, the third determining module is specifically configured to: determining the actual transcoding multiple of the content to be transcoded and determining the average value of the transcoding multiple of all the content to be transcoded under the same transcoding concurrency number;
and obtaining a second calculation result based on the difference value between the actual transcoding multiple and the average value, and determining the second calculation result as the correction coefficient.
In the foregoing scheme, the fourth determining module is specifically configured to: and correcting the initial model according to the correction coefficient to determine the target model.
In the foregoing solution, the second determining module is specifically configured to: judging whether the posterior probability value determined by the target model is greater than a set expected value or not based on the feedback output value;
determining a correction value for the initial transcoding concurrence number when the posterior probability value determined by the target model is determined to be greater than a set expected value;
and adjusting the initial transcoding concurrency number corresponding to the current transcoding task according to the corrected value of the initial transcoding concurrency number to obtain the optimal transcoding concurrency number corresponding to the current transcoding task.
In a third aspect, an embodiment of the present invention further provides a scheduling apparatus for transcoding tasks, including a memory, a processor, and an executable program that is stored on the memory and can be executed by the processor, where the processor executes the steps of the scheduling method for transcoding tasks provided in the embodiment of the present invention when executing the executable program.
In a fourth aspect, an embodiment of the present invention further provides a storage medium, where an executable program is stored on the storage medium, and when the executable program is executed by a processor, the steps of the method for scheduling a transcoding task provided in the embodiment of the present invention are implemented.
The method, the device and the storage medium for scheduling the transcoding task provided by the embodiment of the invention determine the transcoding multiple and the initial transcoding concurrency number corresponding to the current transcoding task; inputting the received first feedback input information and the second feedback input information into a target model to obtain a feedback output value; determining the optimal transcoding concurrency number corresponding to the current transcoding task under the condition that the transcoding multiple meets the corresponding set condition according to the feedback output value and the initial transcoding concurrency number; and scheduling the current transcoding task based on the optimal transcoding concurrency number. Therefore, the optimal transcoding concurrency number corresponding to the current transcoding task is determined by introducing the factor of the transcoding multiple corresponding to the current transcoding task, so that the transcoding task is scheduled by the optimal transcoding concurrency number, the concurrent transcoding efficiency of a transcoding system can be effectively improved, and the utilization rate of system resources is maximized.
Drawings
Fig. 1 is a schematic flowchart illustrating an implementation process of a method for scheduling a transcoding task according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a specific implementation of a method for scheduling a transcoding task according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating an actual correspondence relationship between transcoding multiples and transcoding concurrency numbers of a concurrent transcoding task according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a design architecture for determining an optimal transcoding concurrency number according to an embodiment of the present invention;
fig. 5 is a functional structure diagram of a scheduling apparatus for transcoding tasks according to an embodiment of the present invention;
fig. 6 is a schematic hardware structure diagram of a scheduling apparatus for transcoding tasks according to an embodiment of the present invention.
Detailed Description
So that the manner in which the features and aspects of the embodiments of the present invention can be understood in detail, a more particular description of the embodiments of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. It should be understood by those skilled in the art that the technical solutions described in the embodiments of the present invention may be arbitrarily combined without conflict.
Fig. 1 is a schematic flowchart of an implementation process of a method for scheduling a transcoding task according to an embodiment of the present invention, where the method for scheduling a transcoding task is applicable to a server; as shown in fig. 1, an implementation process of a method for scheduling a transcoding task in the embodiment of the present invention may include the following steps:
step 101: and determining a transcoding multiple and an initial transcoding concurrency number corresponding to the current transcoding task.
In the embodiment of the invention, the transcoding multiple is used for representing the execution efficiency of the current transcoding task.
In this embodiment of the present invention, before performing this step 101, the method may further include: receiving first feedback input information and second feedback input information; the first feedback input information is used for representing a first time length of the content to be transcoded corresponding to the current transcoding task, and the second feedback input information is used for representing a second time length consumed by executing the transcoding task aiming at the content to be transcoded.
Here, for determining the transcoding multiple corresponding to the current transcoding task, the following method may be adopted: firstly, obtaining a first calculation result based on the ratio of the first duration to the second duration; and then, determining the first calculation result as a transcoding multiple corresponding to the current transcoding task.
Step 102: and inputting the received first feedback input information and the second feedback input information into the target model to obtain a feedback output value.
In this embodiment of the present invention, the feedback output value is used to adjust the initial transcoding concurrency number, and specifically, the feedback output value may be used to increase or decrease the initial transcoding concurrency number.
In this embodiment of the present invention, before performing this step 102, the method may further include: an object model is determined.
Here, for determining the target model, the following may be implemented: determining an initial model and a correction coefficient; and determining the target model according to the initial model and the correction coefficient.
Here, in determining the initial model, the initial model may be represented by a probability formula in the related art, for example, a bayesian estimation model in the related art may be used as the initial model, which is not limited herein. In practical application, the transcoding multiple is not only related to the number of concurrent processes of the current transcoder, but also related to a service scene of the content to be transcoded corresponding to the current transcoding task, such as a video resolution of a video file to be transcoded, so that when video resolutions corresponding to delivered transcoding tasks are different, the optimal transcoding concurrency number cannot be well predicted only based on a simple bayesian estimation model, at this time, the initial model needs to be corrected based on a correction coefficient to determine a target model, and then the optimal transcoding concurrency number is predicted based on the target model, so that accuracy of predicting the optimal transcoding concurrency number is improved.
Here, for the determination of the correction coefficient, the following may be implemented: firstly, determining the actual transcoding multiple of the content to be transcoded and determining the average value of the transcoding multiple of all the content to be transcoded under the condition of the same transcoding concurrence number; then, a second calculation result is obtained based on the difference between the actual transcoding multiple and the average value, and the second calculation result is determined as the correction coefficient.
Step 103: and determining the optimal transcoding concurrency number corresponding to the current transcoding task under the condition that the transcoding multiple meets the corresponding set condition according to the feedback output value and the initial transcoding concurrency number.
In the embodiment of the present invention, the specific implementation of step 103 may include the following steps:
firstly, judging whether the posterior probability value determined by the target model is greater than a set expected value or not based on the feedback output value; determining a correction value for the initial transcoding concurrence number when the posterior probability value determined by the target model is determined to be greater than a set expected value; and then, adjusting the initial transcoding concurrency number corresponding to the current transcoding task according to the corrected value of the initial transcoding concurrency number to obtain the optimal transcoding concurrency number corresponding to the current transcoding task.
Step 104: and scheduling the current transcoding task based on the optimal transcoding concurrency number.
By adopting the technical scheme of the embodiment of the invention, the optimal transcoding concurrency number corresponding to the current transcoding task is determined by introducing the transcoding multiple factor corresponding to the current transcoding task, so that the optimal transcoding concurrency number schedules the transcoding task, the concurrent transcoding efficiency of a transcoding system can be effectively improved, and the utilization rate of system resources is maximized.
The following describes in detail a specific implementation process of the method for scheduling a transcoding task according to an embodiment of the present invention.
Fig. 2 is a schematic flowchart of a specific implementation of a method for scheduling a transcoding task according to an embodiment of the present invention, where the method for scheduling a transcoding task is applicable to a server; as shown in fig. 2, a specific implementation flow of the method for scheduling a transcoding task may include the following steps:
step 201: first feedback input information and second feedback input information are received.
In the embodiment of the present invention, the first feedback input information may be used to represent a first time length of a content to be transcoded corresponding to a current transcoding task, and the second feedback input information may be used to represent a second time length consumed by executing a transcoding task for the content to be transcoded.
Step 202: and determining a transcoding multiple and an initial transcoding concurrency number corresponding to the current transcoding task.
Here, the transcoding multiple may be used to characterize the execution efficiency of the current transcoding task. In one example of the present invention, the transcoding multiple may be obtained by calculating a ratio between a first time length of the content to be transcoded corresponding to the current transcoding task and a second time length consumed for performing the transcoding task on the content to be transcoded. The content to be transcoded may be a media file that needs to be transcoded, for example, a video file that needs to be transcoded, which is not specifically limited herein.
It should be noted that fig. 3 is a schematic diagram of an actual corresponding relationship between a transcoding multiple and a transcoding concurrency number of a concurrent transcoding task provided by an embodiment of the present invention, in an actual application, in a distributed transcoding system, an approximate corresponding relationship between a transcoding multiple and a transcoding concurrency number of a concurrent transcoding task is shown in fig. 3, as can be seen from fig. 3, when a transcoding concurrency number reaches a critical value n, a load number of a CPU carried on a server approaches 100%, and at this time, if the size of the transcoding concurrency number n is continuously increased, the server consumes more time in scheduling of a concurrent process, and cannot provide sufficient computing resources, so that the efficiency of concurrent transcoding of the transcoding system is also reduced. Therefore, the embodiments of the present invention are in need of finding a method for determining an optimal transcoding concurrency number. How to determine the optimal transcoding concurrency number is described below in conjunction with the implementation of steps 203 to 205.
Step 203: and determining an initial model and a correction coefficient, and determining a target model according to the initial model and the correction coefficient.
In the embodiment of the present invention, when determining the initial model, the initial model may be represented by a probability formula in the related art, for example, a bayesian estimation model in the related art may be used as the initial model, which is not limited herein.
In the embodiment of the present invention, for determining the correction coefficient, the following method may be adopted: firstly, determining the actual transcoding multiple of the content to be transcoded and determining the average value of the transcoding multiple of all the content to be transcoded under the condition of the same transcoding concurrence number; then, a second calculation result is obtained based on the difference between the actual transcoding multiple and the average value, and the second calculation result is determined as the correction coefficient.
Here, for determining the target model, the following may be implemented: and correcting the initial model according to the correction coefficient to determine the target model.
Step 204: and inputting the first feedback input information and the second feedback input information into the target model to obtain a feedback output value.
In the embodiment of the present invention, the feedback output value is used to adjust the initial transcoding concurrency number.
Step 205: and determining the optimal transcoding concurrency number corresponding to the current transcoding task under the condition that the transcoding multiple meets the corresponding set condition according to the feedback output value and the initial transcoding concurrency number.
In this embodiment of the present invention, the specific implementation of step 205 may include the following steps: judging whether the posterior probability value determined by the target model is greater than a set expected value or not based on the feedback output value; determining a correction value for the initial transcoding concurrence number when the posterior probability value determined by the target model is determined to be greater than a set expected value; and adjusting the initial transcoding concurrency number corresponding to the current transcoding task according to the corrected value of the initial transcoding concurrency number to obtain the optimal transcoding concurrency number corresponding to the current transcoding task.
For the implementation of the above steps 203 to 205, a design architecture for determining the optimal transcoding concurrency number provided by the embodiment of the present invention shown in fig. 4 may be specifically adopted to implement the implementation.
The following describes an implementation process for determining the optimal transcoding concurrency number based on the design architecture shown in fig. 4 by using a specific example: firstly, inputting a current transcoding task into a scheduling module M, wherein the current transcoding task comprises at least one video transcoding task for example; secondly, the scheduling module M schedules all transcoding tasks to enter the transcoder T for concurrent transcoding according to the issued initial transcoding concurrency number C1, and simultaneously synchronizes the content to be transcoded corresponding to the current transcoding task, such as the first time length of a video file to be transcoded, which needs to be transcoded, as first feedback input information, namely feedback input 1, into the estimation module C, when the transcoder T completes a certain transcoding task, the server can synchronize the information of the completed transcoding task, such as the second time length consumed by executing the transcoding task, as second feedback input information, namely feedback input 2, into the estimation module C; next, after receiving the feedback input 1 and the feedback input 2, the estimation module C may determine, based on the feedback input 1 and the feedback input 2, a transcoding multiple corresponding to the current transcoding task, and output a feedback output value, at this time, the server may determine, based on the feedback output value, whether the posterior probability value determined by the estimation module C is greater than a set expected value, when it is determined that the posterior probability value determined by the estimation module C is greater than the set expected value, determine a corrected value of the initial transcoding concurrency number, when it is determined that the posterior probability value determined by the estimation module C is greater than the set expected value; and finally, the server adjusts the initial transcoding concurrency number C1 issued by the scheduling module M based on the corrected value of the initial transcoding concurrency number to obtain the optimal transcoding concurrency number, and the scheduling module M performs transcoding task scheduling again according to the optimal transcoding concurrency number.
It should be noted that the estimation module C in the design framework provided in the embodiment of the present invention for determining the optimal transcoding concurrency number may be determined by using a mathematical model. The mathematical model used by the following determination estimation module C is explained below.
First, an initial model used by the estimation module C is determined, and when determining the initial model, the initial model may be represented by a probability formula in the related art, for example, a bayesian estimation model in the related art may be used as the initial model, which is not limited herein. The embodiment of the invention uses an initial dieThe model is explained by taking a Bayesian estimation model as an example, and the optimal transcoding concurrency number C is obtainediTo find the most suitable transcoding concurrency number C under the condition that a given transcoding multiple X is larger than XiIs recorded as the optimal transcoding concurrency number CiObey P (C)i| X > X), according to the bayes formula:
wherein X represents a transcoding multiple; x represents a condition value satisfied by the transcoding multiple; p (X > X) represents the probability that the transcoding multiple X is greater than X; p (C)i) Representing the probability when the transcoding concurrency number C is i; p (X > X | C)i) Representing the probability that the transcoding multiple X is greater than X if the transcoding concurrency number C is i.
It should be noted that the three probability values may be approximate values statistically obtained according to the transcoding actual result. When the solution is needed, the transcoding multiple X is calculated>x optimal transcoding concurrency number CiI.e. can be converted to finding a probability P (C)i| X > X) is greater than the maximum transcoding concurrency number C of the set expectation valuei。
However, in practical applications, the transcoding multiple is not only related to the number of concurrent processes of the current transcoder, but also related to a service scenario of the content to be transcoded corresponding to the current transcoding task, such as a video resolution of a video file to be transcoded, so that when video resolutions corresponding to delivered transcoding tasks are different, an optimal transcoding concurrent number cannot be well predicted only based on a simple bayesian estimation model, and at this time, the bayesian estimation model needs to be corrected to predict a more accurate optimal transcoding concurrent number.
Next, how to determine a correction coefficient to correct the above equation (1) based on the correction coefficient will be described.
In the embodiment of the invention, the difference value between the actual transcoding multiple of the content to be transcoded and the average value of the transcoding multiple of all the content to be transcoded under the same transcoding concurrency number can be calculated to be determined as the correction coefficient. Wherein the correction coefficient can be expressed by the following formula (2):
wherein M isiRepresenting the content to be transcoded, such as the actual transcoding multiple of a certain video file;
representing all contents to be transcoded under the same transcoding concurrence number, such as expected values of transcoding multiples of all video files; n represents the number of contents to be transcoded, such as video files;
representing the average of the transcoding multiples of all the contents to be transcoded under the same transcoding concurrency, such as all video files.
From the above formula (2), fixiThe larger the value of the value is, the actual transcoding multiple of the transcoding task is superior to the average level of the transcoding multiple of all transcoding tasks under the condition of the same transcoding concurrence number; fixiThe smaller the value of (A) is, the actual transcoding multiple of the transcoding task is represented to be worse than the average level of the transcoding multiple of all the transcoding tasks under the condition of the same transcoding concurrence number. Taking the content to be transcoded as a video file as an example, under a common condition, the higher the video resolution of the video file is, the lower the actual transcoding multiple of the video file is than the average level of the transcoding multiple of all the video files under the condition of the same transcoding concurrency number; the lower the video resolution of the video file, the higher the average level of the transcoding multiple of all video files for the same transcoding concurrency.
In the embodiment of the present invention, after determining the correction coefficient, the correction coefficient fix may be usediAnd (3) on the basis, correcting the formula (1), determining a target model, and determining the optimal transcoding concurrency number by using the target model. Wherein, the correction coefficient fixiBased on the above formula (1), the formula is correctedThe expression of (a) is as follows:
how to determine the optimal transcoding concurrency is explained below with a specific example based on the target model determined by the above equation (3). Assume that estimation module C in the design architecture shown in fig. 4 can build an entry as in table 1 below from feedback input 1 and feedback input 2: { taskid, convurency, speed, res, fix }, wherein taskid represents a unique identifier corresponding to a transcoding task, convurency represents the transcoding concurrency number of the environment where the transcoding task is located at the moment, speed represents a transcoding multiple, res represents the video resolution of a video file, and fix represents a correction parameter.
Firstly, determining the number of transcoding tasks input into a scheduling module M, namely, sending i transcoding tasks, i belongs to [0, N ], and counting the transcoding multiples of each transcoding task, wherein the process needs to be repeated for many times, and finally, the data shown in the table 1 is obtained:
TABLE 1
As shown in table 1, when the initial transcoding concurrence number corresponding to the transcoding task is 5, assuming that a corresponding set condition that a transcoding multiple (hereinafter referred to as a transcoding multiple) corresponding to the transcoding task needs to satisfy is that a required transcoding multiple is greater than 1, the server may determine a modified transcoding multiple according to the currently required transcoding multiple, where the modified transcoding multiple may be obtained by calculating a difference between the currently required transcoding multiple and a modification coefficient. After determining the modified transcoding multiple, the server may determine an optimal transcoding concurrency number based on the modified transcoding multiple and the initial transcoding concurrency number. Specifically, the transcoding task is determined to correspond toWhen the initial transcoding concurrency number of the four pieces of data is 5 and the transcoding multiple is required to be greater than 1, it may be determined that four pieces of data satisfy the initial transcoding concurrency number of 5 from the data shown in table 1, and then, it may be determined that the modified transcoding multiples corresponding to the four pieces of data are 1, 1.3, and 0.7, respectively, because the current transcoding multiples corresponding to the four pieces of data are 0.8, 0.5, and 1.1, respectively. Therefore, only the data with the transcoding task identification vid103 in the four data satisfies that the current corresponding transcoding multiple is greater than the modified transcoding multiple, and then P (X > X-fix) can be calculated accordinglyi|Ci)＝0.125，P(Ci)＝0.5，P(X＞x-fixi) 0.25, therefore, P (C) with a corresponding resolution of 720Pi|X＞x-fixi) When the transcoding multiple is greater than 1, and the initial transcoding concurrency is 5, the probability value that can meet the requirement is 0.25.
Obviously, the probability value is lower, so that the feedback output corresponding to the estimation module C is-1, at this time, the concurrent number issued by the scheduling module M is reduced, when the concurrent number issued by the scheduling module M is reduced to 4, the corresponding probability value at this time is recalculated, if it is detected that the recalculated probability value is too low to meet the requirement, the feedback output corresponding to the estimation module C is still-1, until an acceptable probability is found, and the transcoding multiple is greater than 1. If the required probability is met under the condition of a certain concurrency number, the feedback output corresponding to the estimation module C is +1, the concurrency number issued by the scheduling module M is increased, finally, the transcoding system keeps stable near the increased transcoding concurrency number, so that the transcoding system is converged, and at the moment, the determined transcoding concurrency number is the optimal transcoding concurrency number capable of meeting the transcoding multiple requirement.
Step 206: and scheduling the current transcoding task based on the optimal transcoding concurrency number.
By adopting the technical scheme of the embodiment of the invention, the optimal transcoding concurrency number corresponding to the current transcoding task is determined by introducing the transcoding multiple factor corresponding to the current transcoding task, so that the optimal transcoding concurrency number schedules the transcoding task, the concurrent transcoding efficiency of a transcoding system can be effectively improved, and the utilization rate of system resources is maximized.
In order to implement the foregoing method for scheduling a transcoding task, an embodiment of the present invention further provides a device for scheduling a transcoding task, where the device for scheduling a transcoding task is applicable to a server, and fig. 5 is a functional structure diagram of the device for scheduling a transcoding task provided in the embodiment of the present invention; as shown in fig. 5, the scheduling device of the transcoding task includes: a first determining module 51, an obtaining module 52, a second determining module 53 and a scheduling module 54. The functions of the program modules will be described below. Wherein,
the first determining module 51 is configured to determine a transcoding multiple and an initial transcoding concurrency number corresponding to a current transcoding task, where the transcoding multiple is used to represent execution efficiency of the current transcoding task;
the obtaining module 52 is configured to input received first feedback input information and second feedback input information into a target model, and obtain a feedback output value, where the first feedback input information is used to represent a first time length of a content to be transcoded corresponding to the current transcoding task, the second feedback input information is used to represent a second time length consumed by executing a transcoding task for the content to be transcoded, and the feedback output value is used to adjust the initial transcoding concurrence number;
the second determining module 53 is configured to determine, according to the feedback output value and the initial transcoding concurrency number, an optimal transcoding concurrency number corresponding to the current transcoding task when the transcoding multiple satisfies a corresponding setting condition;
and the scheduling module 54 is configured to schedule the current transcoding task based on the optimal transcoding concurrency number.
In this embodiment of the present invention, for the first determining module 51 to determine the transcoding multiple corresponding to the current transcoding task, the following method may be adopted: and obtaining a first calculation result based on the ratio of the first time length to the second time length, and determining the first calculation result as the transcoding multiple corresponding to the current transcoding task.
In this embodiment of the present invention, for the second determining module 53 determining, according to the feedback output value and the initial transcoding concurrency number, an optimal transcoding concurrency number corresponding to the current transcoding task when the transcoding multiple satisfies a corresponding setting condition, the following method may be adopted:
judging whether the posterior probability value determined by the target model is greater than a set expected value or not based on the feedback output value;
determining a correction value for the initial transcoding concurrence number when the posterior probability value determined by the target model is determined to be greater than a set expected value;
and adjusting the initial transcoding concurrency number corresponding to the current transcoding task according to the corrected value of the initial transcoding concurrency number to obtain the optimal transcoding concurrency number corresponding to the current transcoding task.
In an example of the present invention, the scheduling apparatus of the transcoding task further includes the following module for determining a target model:
the third determining module is used for determining the initial model and the correction coefficient;
and the fourth determining module is used for determining the target model according to the initial model and the correction coefficient.
Here, for the third determination module to determine the correction coefficient, the following may be implemented: determining the actual transcoding multiple of the content to be transcoded and determining the average value of the transcoding multiple of all the content to be transcoded under the same transcoding concurrency number;
and obtaining a second calculation result based on the difference value between the actual transcoding multiple and the average value, and determining the second calculation result as the correction coefficient.
Here, for the fourth determination module to determine the target model according to the initial model and the correction coefficient, the following may be implemented: and correcting the initial model according to the correction coefficient to determine the target model.
It should be noted that: the scheduling apparatus for a transcoding task provided in the foregoing embodiment only exemplifies the division of each program module when scheduling the transcoding task, and in practical applications, the processing allocation may be completed by different program modules according to needs, that is, the internal structure of the scheduling apparatus for a transcoding task is divided into different program modules to complete all or part of the processing described above. In addition, the scheduling apparatus for a transcoding task and the scheduling method embodiment for a transcoding task provided in the foregoing embodiments belong to the same concept, and specific implementation processes thereof are described in detail in the method embodiments and are not described in detail herein.
In practical applications, each of the program modules may be implemented by a CPU, a microprocessor Unit (MPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), or the like located on the server.
In order to implement the method for scheduling the transcoding task, the embodiment of the invention also provides a hardware structure of the device for scheduling the transcoding task. A scheduling apparatus of a transcoding task, which may be implemented in various forms of servers such as a cloud server, implementing an embodiment of the present invention will now be described with reference to the accompanying drawings. In the following, the hardware structure of the scheduling apparatus for transcoding tasks according to the embodiment of the present invention is further described, it is to be understood that fig. 6 only shows an exemplary structure of the scheduling apparatus for transcoding tasks, and not a whole structure, and a part of or a whole structure shown in fig. 6 may be implemented as needed.
Referring to fig. 6, fig. 6 is a schematic diagram of a hardware structure of a scheduling apparatus for transcoding tasks according to an embodiment of the present invention, which may be applied to the foregoing server running an application program in practical applications, where the scheduling apparatus 600 for transcoding tasks shown in fig. 6 includes: at least one processor 601, memory 602, user interface 603, and at least one network interface 604. The various components in the scheduler 600 of the transcoding task are coupled together by a bus system 605. It will be appreciated that the bus system 605 is used to enable communications among the components. The bus system 605 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 605 in fig. 6.
The user interface 603 may include, among other things, a display, a keyboard, a mouse, a trackball, a click wheel, a key, a button, a touch pad, or a touch screen.
It will be appreciated that the memory 602 can be either volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory.
The memory 602 in the embodiment of the present invention is used for storing various types of data to support the operation of the scheduling apparatus 600 of the transcoding task. Examples of such data include: any computer program for operating on the scheduling apparatus 600 for transcoding tasks, such as the executable program 6021 and the operating system 6022, may be included in the executable program 6021 to implement the scheduling method for transcoding tasks of the embodiments of the present invention.
The method for scheduling the transcoding task disclosed by the embodiment of the invention can be applied to the processor 601 or implemented by the processor 601. The processor 601 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the method for scheduling the transcoding task may be implemented by an integrated logic circuit of hardware in the processor 601 or instructions in the form of software. The processor 601 described above may be a general purpose processor, a DSP, or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Processor 601 may implement or execute the scheduling method, steps and logic block diagram of each transcoding task provided in the embodiments of the present invention. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method for scheduling the transcoding task provided by the embodiment of the present invention can be directly embodied as the execution of a hardware decoding processor, or the execution of the hardware decoding processor and a software module in the decoding processor is combined. The software module may be located in a storage medium located in the memory 602, and the processor 601 reads the information in the memory 602, and performs the steps of the method for scheduling the transcoding task provided by the embodiment of the present invention in combination with the hardware thereof.
In this embodiment of the present invention, the scheduling apparatus 600 for the transcoding task includes a memory 602, a processor 601, and an executable program 6021 that is stored on the memory 602 and can be executed by the processor 601, where when the processor 601 executes the executable program 6021, the: determining a transcoding multiple and an initial transcoding concurrency number corresponding to a current transcoding task, wherein the transcoding multiple is used for representing the execution efficiency of the current transcoding task; inputting received first feedback input information and second feedback input information into a target model to obtain a feedback output value, wherein the first feedback input information is used for representing a first time length of the content to be transcoded corresponding to the current transcoding task, the second feedback input information is used for representing a second time length consumed by executing the transcoding task aiming at the content to be transcoded, and the feedback output value is used for adjusting the initial transcoding concurrency number; determining the optimal transcoding concurrency number corresponding to the current transcoding task under the condition that the transcoding multiple meets the corresponding set condition according to the feedback output value and the initial transcoding concurrency number; and scheduling the current transcoding task based on the optimal transcoding concurrency number.
As an embodiment, the processor 601, when running the executable program 6021, implements: and obtaining a first calculation result based on the ratio of the first time length to the second time length, and determining the first calculation result as the transcoding multiple corresponding to the current transcoding task.
As an embodiment, the processor 601, when running the executable program 6021, implements: determining an initial model and a correction coefficient; and determining the target model according to the initial model and the correction coefficient.
As an embodiment, the processor 601, when running the executable program 6021, implements: determining the actual transcoding multiple of the content to be transcoded and determining the average value of the transcoding multiple of all the content to be transcoded under the same transcoding concurrency number; and obtaining a second calculation result based on the difference value between the actual transcoding multiple and the average value, and determining the second calculation result as the correction coefficient.
As an embodiment, the processor 601, when running the executable program 6021, implements: and correcting the initial model according to the correction coefficient to determine the target model.
As an embodiment, the processor 601, when running the executable program 6021, implements: judging whether the posterior probability value determined by the target model is greater than a set expected value or not based on the feedback output value; determining a correction value for the initial transcoding concurrence number when the posterior probability value determined by the target model is determined to be greater than a set expected value; and adjusting the initial transcoding concurrency number corresponding to the current transcoding task according to the corrected value of the initial transcoding concurrency number to obtain the optimal transcoding concurrency number corresponding to the current transcoding task.
In an exemplary embodiment, an embodiment of the present invention further provides a storage medium, which may be a storage medium such as an optical disc, a flash memory, or a magnetic disc, and may be a non-transitory storage medium.
In this embodiment of the present invention, the storage medium stores an executable program 6021, and when executed by the processor 601, the executable program 6021 implements: determining a transcoding multiple and an initial transcoding concurrency number corresponding to a current transcoding task, wherein the transcoding multiple is used for representing the execution efficiency of the current transcoding task; inputting received first feedback input information and second feedback input information into a target model to obtain a feedback output value, wherein the first feedback input information is used for representing a first time length of the content to be transcoded corresponding to the current transcoding task, the second feedback input information is used for representing a second time length consumed by executing the transcoding task aiming at the content to be transcoded, and the feedback output value is used for adjusting the initial transcoding concurrency number; determining the optimal transcoding concurrency number corresponding to the current transcoding task under the condition that the transcoding multiple meets the corresponding set condition according to the feedback output value and the initial transcoding concurrency number; and scheduling the current transcoding task based on the optimal transcoding concurrency number.
As an embodiment, the executable program 6021, when executed by the processor 601, implements: and obtaining a first calculation result based on the ratio of the first time length to the second time length, and determining the first calculation result as the transcoding multiple corresponding to the current transcoding task.
As an embodiment, the executable program 6021, when executed by the processor 601, implements: determining an initial model and a correction coefficient; and determining the target model according to the initial model and the correction coefficient.
As an embodiment, the executable program 6021, when executed by the processor 601, implements: determining the actual transcoding multiple of the content to be transcoded and determining the average value of the transcoding multiple of all the content to be transcoded under the same transcoding concurrency number; and obtaining a second calculation result based on the difference value between the actual transcoding multiple and the average value, and determining the second calculation result as the correction coefficient.
As an embodiment, the executable program 6021, when executed by the processor 601, implements: and correcting the initial model according to the correction coefficient to determine the target model.
As an embodiment, the executable program 6021, when executed by the processor 601, implements: judging whether the posterior probability value determined by the target model is greater than a set expected value or not based on the feedback output value; determining a correction value for the initial transcoding concurrence number when the posterior probability value determined by the target model is determined to be greater than a set expected value; and adjusting the initial transcoding concurrency number corresponding to the current transcoding task according to the corrected value of the initial transcoding concurrency number to obtain the optimal transcoding concurrency number corresponding to the current transcoding task.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or executable program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of an executable program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and executable program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by executable program instructions. These executable program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor with reference to a programmable data processing apparatus to produce a machine, such that the instructions, which execute via the computer or processor with reference to the programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These executable program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These executable program instructions may also be loaded onto a computer or reference programmable data processing apparatus to cause a series of operational steps to be performed on the computer or reference programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or reference programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only exemplary of the present invention and should not be taken as limiting the scope of the present invention, and any modifications, equivalents, improvements, etc. that are within the spirit and principle of the present invention should be included in the present invention.
Claims (7)
1. A method for scheduling a transcoding task, the method comprising:
determining an initial transcoding concurrency number corresponding to a current transcoding task;
inputting received first feedback input information and second feedback input information into a target model to obtain a feedback output value, wherein the first feedback input information is used for representing a first time length of the content to be transcoded corresponding to the current transcoding task, the second feedback input information is used for representing a second time length consumed by executing the transcoding task aiming at the content to be transcoded, and the feedback output value is used for adjusting the initial transcoding concurrency number;
obtaining a first calculation result based on the ratio of the first time length to the second time length, and determining the first calculation result as a transcoding multiple corresponding to the current transcoding task; the transcoding multiple is used for representing the execution efficiency of the current transcoding task;
determining the optimal transcoding concurrency number corresponding to the current transcoding task under the condition that the transcoding multiple meets the corresponding set condition according to the feedback output value and the initial transcoding concurrency number; judging whether the posterior probability value determined by the target model is greater than a set expected value or not based on the feedback output value;
determining a correction value for the initial transcoding concurrence number when the posterior probability value determined by the target model is determined to be greater than a set expected value;
adjusting the initial transcoding concurrency number corresponding to the current transcoding task according to the corrected value of the initial transcoding concurrency number to obtain the optimal transcoding concurrency number corresponding to the current transcoding task;
and scheduling the current transcoding task based on the optimal transcoding concurrency number.
2. The method for scheduling a transcoding task of claim 1, wherein the target model is determined by:
determining an initial model and a correction coefficient;
and determining the target model according to the initial model and the correction coefficient.
3. The method for scheduling a transcoding task according to claim 2, wherein the determining a modification factor comprises:
determining the actual transcoding multiple of the content to be transcoded and determining the average value of the transcoding multiple of all the content to be transcoded under the same transcoding concurrency number;
and obtaining a second calculation result based on the difference value between the actual transcoding multiple and the average value, and determining the second calculation result as the correction coefficient.
4. The method for scheduling a transcoding task according to claim 3, wherein the determining the target model according to the initial model and the correction coefficient comprises:
and correcting the initial model according to the correction coefficient to determine the target model.
5. An apparatus for scheduling transcoding tasks, the apparatus comprising: the system comprises a first determining module, an obtaining module, a second determining module and a scheduling module; wherein,
the first determining module is used for determining the initial transcoding concurrency number corresponding to the current transcoding task;
the obtaining module is configured to input received first feedback input information and second feedback input information into a target model to obtain a feedback output value, where the first feedback input information is used to represent a first time length of a content to be transcoded corresponding to the current transcoding task, the second feedback input information is used to represent a second time length consumed by executing a transcoding task for the content to be transcoded, and the feedback output value is used to adjust the initial transcoding concurrence number;
the first determining module is configured to obtain a first calculation result based on a ratio of the first duration to the second duration, and determine the first calculation result as a transcoding multiple corresponding to the current transcoding task; the transcoding multiple is used for representing the execution efficiency of the current transcoding task;
the second determining module is configured to determine, according to the feedback output value and the initial transcoding concurrency number, an optimal transcoding concurrency number corresponding to the current transcoding task when the transcoding multiple satisfies a corresponding set condition;
judging whether the posterior probability value determined by the target model is greater than a set expected value or not based on the feedback output value;
determining a correction value for the initial transcoding concurrence number when the posterior probability value determined by the target model is determined to be greater than a set expected value;
adjusting the initial transcoding concurrency number corresponding to the current transcoding task according to the corrected value of the initial transcoding concurrency number to obtain the optimal transcoding concurrency number corresponding to the current transcoding task;
and the scheduling module is used for scheduling the current transcoding task based on the optimal transcoding concurrency number.
6. A scheduling apparatus for transcoding tasks, comprising a memory, a processor and an executable program stored on the memory and capable of being executed by the processor, wherein the processor executes the executable program to perform the steps of the scheduling method for transcoding tasks according to any one of claims 1 to 4.
7. A storage medium having stored thereon an executable program, wherein the executable program, when executed by a processor, implements the steps of the method of scheduling of transcoding tasks as claimed in any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811084239.6A CN109471715B (en) | 2018-09-17 | 2018-09-17 | Method and device for scheduling transcoding task and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811084239.6A CN109471715B (en) | 2018-09-17 | 2018-09-17 | Method and device for scheduling transcoding task and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109471715A CN109471715A (en) | 2019-03-15 |
| CN109471715B true CN109471715B (en) | 2021-10-29 |
Family
ID=65664702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811084239.6A Active CN109471715B (en) | 2018-09-17 | 2018-09-17 | Method and device for scheduling transcoding task and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109471715B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102325255A (en) * | 2011-09-09 | 2012-01-18 | 深圳市融创天下科技股份有限公司 | Multi-core CPU (central processing unit) video transcoding scheduling method and multi-core CPU video transcoding scheduling system |
| CN102790905A (en) * | 2012-08-03 | 2012-11-21 | 重庆大学 | Transcoding method from H.264/SVC(scalable video coding) to H.264/AVC(advanced video coding) based on video on demand system of P2PVoD |
| CN103702125A (en) * | 2013-12-23 | 2014-04-02 | 乐视网信息技术（北京）股份有限公司 | Method and system specific to fragment transcoding and scheduling |
| CN105992020A (en) * | 2015-07-24 | 2016-10-05 | 乐视云计算有限公司 | Video conversion resource distribution method and system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838779B (en) * | 2012-11-27 | 2019-02-05 | 深圳市腾讯计算机系统有限公司 | It is multiplexed the cloud code-transferring method and system, distributed document device of idle computing resources |
| US20140321532A1 (en) * | 2013-04-26 | 2014-10-30 | Devadutta Ghat | Techniques for coordinating parallel video transcoding |
| CN103731678B (en) * | 2013-12-30 | 2017-02-08 | 世纪龙信息网络有限责任公司 | Video file parallel transcoding method and system |
| CN107205164B (en) * | 2016-03-18 | 2020-09-01 | 百度在线网络技术（北京）有限公司 | Video transcoding method and device |
| US20170289558A1 (en) * | 2016-03-31 | 2017-10-05 | Le Holdings (Beijing) Co., Ltd. | Method and device for allocating a transcoding task |
| CN106375319A (en) * | 2016-09-06 | 2017-02-01 | 上海爱数信息技术股份有限公司 | Audio and video transcoding scheduling method, apparatus, device and system |
| CN106851336B (en) * | 2017-02-07 | 2020-04-14 | 上海网达软件股份有限公司 | Audio and video file transcoding method and system with dynamic resource allocation |
-
2018
- 2018-09-17 CN CN201811084239.6A patent/CN109471715B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102325255A (en) * | 2011-09-09 | 2012-01-18 | 深圳市融创天下科技股份有限公司 | Multi-core CPU (central processing unit) video transcoding scheduling method and multi-core CPU video transcoding scheduling system |
| CN102790905A (en) * | 2012-08-03 | 2012-11-21 | 重庆大学 | Transcoding method from H.264/SVC(scalable video coding) to H.264/AVC(advanced video coding) based on video on demand system of P2PVoD |
| CN103702125A (en) * | 2013-12-23 | 2014-04-02 | 乐视网信息技术（北京）股份有限公司 | Method and system specific to fragment transcoding and scheduling |
| CN105992020A (en) * | 2015-07-24 | 2016-10-05 | 乐视云计算有限公司 | Video conversion resource distribution method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109471715A (en) | 2019-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11709534B2 (en) | Method and apparatus for managing global chip power on a multicore system on chip | |
| US9575691B2 (en) | Scheduling user requests in a distributed resource system having a plurality of schedulers and coordinators | |
| US20170255496A1 (en) | Method for scheduling data flow task and apparatus | |
| US8595735B2 (en) | Holistic task scheduling for distributed computing | |
| CN103377407B (en) | Cloud method for processing business and relevant apparatus and system | |
| US9104491B2 (en) | Batch scheduler management of speculative and non-speculative tasks based on conditions of tasks and compute resources | |
| US11095531B2 (en) | Service-aware serverless cloud computing system | |
| US20180101404A1 (en) | Resource and latency estimation-based scheduling | |
| US20210298033A1 (en) | Priority Control Method and Data Processing System | |
| CN106293947A (en) | GPU CPU mixing resource allocation system and method under virtualization cloud environment | |
| US11531565B2 (en) | Techniques to generate execution schedules from neural network computation graphs | |
| CN109471715B (en) | Method and device for scheduling transcoding task and storage medium | |
| CN113434303A (en) | Batch-processed remote sensing image intelligent processing model prediction performance optimization system and method | |
| US20180101405A1 (en) | Resource and latency estimation-based scheduling in a distributed computing environment | |
| KR101674324B1 (en) | Task scheduling device and method for real-time control applications | |
| US20140380321A1 (en) | Energy efficient job scheduling | |
| CN107589985A (en) | A kind of two benches job scheduling method and system towards big data platform | |
| CN114546096A (en) | Base band chip, task scheduling method and terminal equipment | |
| CN114546730A (en) | Data recovery processing method, device and system | |
| Ali et al. | Mixed Criticality Reward-Based Systems Using Resource Reservation | |
| Wu et al. | An estimation of distribution algorithm to optimize the utility of task scheduling under fog computing systems | |
| CN111901423B (en) | Asynchronous task scheduling method and device based on automatic frequency conversion | |
| CN116954817A (en) | Virtual machine dynamic migration method and system based on dirty page rate prediction | |
| CN114186845A (en) | Method and device for executing index calculation task at fixed time | |
| CN114756353A (en) | Thread execution method and device, electronic equipment and computer readable storage medium |
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 |