Computing Resource Scheduling Method, Apparatus, Electronic Device, and Storage Medium

Abstract

An embodiment of the present application discloses a computing resource scheduling method, apparatus, electronic device, and storage medium. The method includes: obtaining in real time the computing resource usage information of each processing unit in the DPI system; determining whether the DPI system needs to perform computing resource scheduling according to the computing resource usage information; if so, determining a scheduling plan according to the computing resource usage information, and performing computing resource scheduling on the DPI system according to the scheduling plan. Based on this, it is possible to determine in real time whether the DPI system needs to perform resource scheduling, and automatically generate a scheduling plan to complete resource scheduling when needed, improving the real-time performance of resource scheduling and avoiding the situation of manual scheduling after the system crashes.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of resource management, and in particular, to a computing resource scheduling method, apparatus, electronic device, and storage medium. Background Art

[0002] With the development of Internet technology, the number of devices and services in the Internet is increasing, and the traffic in the network is also increasing sharply. In order to strengthen the management of the network, network traffic is generally analyzed. Currently, the commonly used analysis method is the Deep Packet Inspection (DPI) technology.

[0003] Generally, the DPI system collects the traffic of each service in the Internet and then analyzes it. However, when the network traffic exceeds the maximum processing capacity of the DPI system, the DPI system will experience traffic jams or even packet loss, and may even cause the system to crash. For this situation, the DPI system can be expanded, but the current expansion usually occurs after the system crashes, and usually requires manual hardware expansion. This expansion method is not flexible enough and will also cause waste of the target resource specifications. Summary of the Invention

[0004] The embodiments of the present application provide a computing resource scheduling method, apparatus, electronic device, and storage medium to reduce the environmental requirements for computing resource scheduling and reduce the difficulty of computing resource scheduling.

[0005] In a first aspect, the embodiments of the present application provide a computing resource scheduling method, the method including:

[0006] Obtaining, in real time, the computing resource usage information of each processing unit in the DPI system;

[0007] Determining, according to the computing resource usage information, whether the DPI system needs to perform computing resource scheduling;

[0008] If needed, determining a scheduling plan according to the computing resource usage information, and performing computing resource scheduling on the DPI system according to the scheduling plan.

[0009] In a second aspect, the embodiments of the present application further provide a computing resource scheduling apparatus, the computing resource scheduling apparatus including:

[0010] An obtaining module, configured to obtain, in real time, the computing resource usage information of each processing unit in the DPI system;

[0011] A determining module, configured to determine, according to the computing resource usage information, whether the DPI system needs to perform computing resource scheduling;

[0012] A scheduling module, configured to determine a scheduling plan according to the computing resource usage information if necessary, and schedule the computing resources of the DPI system according to the scheduling plan.

[0013] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0014] One or more processors;

[0015] A storage device for storing one or more programs,

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the computing resource scheduling method provided in any embodiment of the present application.

[0017] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, characterized in that when the program is executed by a processor, it implements the computing resource scheduling method provided in any embodiment of the present application.

[0018] The technical solution of the embodiment of the present application determines whether the DPI system needs to perform computing resource scheduling by obtaining the computing resource usage information of each processing unit of the DPI system in real time. If necessary, a scheduling plan is determined according to the computing resource usage information, and the computing resources of the DPI system are scheduled according to the scheduling plan. Based on this, it can be determined in real time whether the DPI system needs to perform resource scheduling, and a scheduling plan can be automatically generated when needed to complete the resource scheduling, improving the real-time performance of resource scheduling and avoiding the situation of manual scheduling after the system crashes. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic flowchart of the computing resource scheduling method provided in Embodiment 1 of the present application;

[0020] Figure 2 It is a schematic diagram of an expansion method provided in Embodiment 1 of the present application;

[0021] Figure 3 It is a schematic flowchart of a process for determining whether the DPI system needs to perform computing resource scheduling provided in Embodiment 2 of the present application;

[0022] Figure 4 It is a schematic flowchart of a process for determining a scheduling plan provided in Embodiment 2 of the present application;

[0023] Figure 5 It is a schematic flowchart of a process for determining whether the DPI system needs to perform computing resource scheduling provided in Embodiment 2 of the present application;

[0024] Figure 6Schematic diagram of a computing resource scheduling device provided in the fourth embodiment of the present application;

[0025] Figure 7 Schematic diagram of an electronic device provided in the fifth embodiment of the present application Detailed implementation manners

[0026] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present application, rather than limiting the present application. In addition, it should be noted that for the convenience of description, only parts related to the present application are shown in the drawings rather than all the structures.

[0027] Embodiment 1

[0028] Figure 1 Schematic flowchart of a computing resource scheduling method provided in Embodiment 1 of the present application. This embodiment is applicable to the scenario of computing resource scheduling. The method can be executed by a computing resource scheduling device, which can be implemented in a hardware and / or software manner and is generally integrated in an electronic device such as a computer with data operation capabilities. The specific steps are as follows:

[0029] Step 101: Real-time obtain the computing resource usage information of each processing unit in the DPI system.

[0030] In this step, the DPI system refers to a deep packet inspection system. Among them, the DPI system contains multiple processing units. In a specific example, the processing unit can exist in the form of a virtual machine. It should be noted that each processing unit is a unit that can independently parse packets, and the resources it has can be various, such as CPU cores, RAM, and ROM.

[0031] In addition, the computing resource usage information refers to the usage information of each resource, which can specifically include the total amount and usage amount of the resources. In a specific example, the computing resource usage information of a certain processing unit is that there are a total of 4 CPU cores, and 2 are used; there is a total of 8G of RAM, and 4G is used; there is a total of 256G of ROM, and 125G is used.

[0032] Step 102: Determine whether the DPI system needs to perform computing resource scheduling according to the computing resource usage information.

[0033] In this step, the resource scheduling is mainly divided into two directions, one is expansion, and the other is contraction. It should be noted that both expansion and contraction have two methods, that is to say, there are four methods of resource scheduling, namely horizontal expansion, horizontal contraction, vertical expansion, and vertical contraction.

[0034] Specifically, reference can be made to Figure 2 ,Figure 2 This is a schematic diagram of an expansion method provided by Embodiment 1 of the present application. Vertical expansion refers to increasing the specifications of resources in a single processing unit, and horizontal expansion refers to increasing the processing units in the DPI system. It should be noted that Figure 2 In this embodiment, the elastic resource control center executes the method of this embodiment. Among them, the detection unit is used to execute the steps of step 101, the control unit is used to execute the steps of step 102 and step 103 to determine the scheduling plan, and the execution unit is used by the user to execute the scheduling steps in step 103.

[0035] Step 103: If necessary, determine the scheduling plan according to the computing resource usage information, and schedule the computing resources of the DPI system according to the scheduling plan.

[0036] Since in step 102, it will be determined whether the DPI system needs to perform computing resource scheduling. If needed, it will also be determined which mode of computing resource scheduling is required. Therefore, in this step, the scheduling plan in the corresponding mode can be determined according to the computing resource usage information.

[0037] In addition, when performing actual scheduling according to the scheduling plan, the heat physical resource orchestration engine can be used to achieve resource scheduling, which will be specifically described in other embodiments and will not be elaborated here.

[0038] It should be noted that when the scheduling action is executed too quickly, there may be a phenomenon of resource fluctuations, such as immediately scaling down after scaling up. To avoid such frequent scaling up and down, after step 103 is executed, a configurable hold time can be set. This hold time can be specifically embodied as a countdown. Before the countdown ends, scheduling of resources can be prohibited to avoid fluctuations.

[0039] In this embodiment, by judging whether the DPI system needs to perform computing resource scheduling according to the computing resource usage information of each processing unit of the DPI system obtained in real time. If needed, the scheduling plan is determined according to the computing resource usage information, and the computing resources of the DPI system are scheduled according to the scheduling plan. Based on this, it can be determined in real time whether the DPI system needs to perform resource scheduling, and when needed, the scheduling plan can be automatically generated to complete resource scheduling, improving the real-time performance of resource scheduling and avoiding the situation of manual scheduling after the system crashes.

[0040] Embodiment 2

[0041] For the specific processing process of determining whether the DPI system needs to perform computing resource scheduling, reference can be made to Figure 3 , Figure 3It is a schematic flowchart for determining whether a DPI system needs to schedule computing resources provided by Embodiment 2 of the present application. This embodiment mainly illustrates the expansion scenario.

[0042] As Figure 3 shown, in this embodiment, the process of determining whether a DPI system needs to schedule computing resources may include:

[0043] Step 301: For any processing unit, compare whether the computing resource usage information of the processing unit exceeds a first preset threshold. If it exceeds, determine that the processing unit of the DPI system needs to perform computing resource scheduling in the first mode.

[0044] In this embodiment, each processing unit is first analyzed. In this step, for any processing unit, it means that each processing unit will be compared in this step. It should be noted that since the computing resources include multiple resources, there will also be multiple sub-thresholds corresponding in the first preset threshold. That is to say, for various resources, there will be a corresponding sub-threshold.

[0045] When comparing whether the computing resource usage information of the processing unit exceeds the first preset threshold, it is necessary to separately compare whether the current usage information of each resource exceeds its corresponding sub-threshold. As long as one exceeds, it is determined to exceed.

[0046] Of course, sometimes with the implementation of scaling, the computing resource rules of each processing unit will be different. At this time, comparing the computing resource usage information may lose the meaning of comparison. Therefore, the computing resource usage information can be converted into a usage ratio. Correspondingly, sub-thresholds of ratios will be set for various resources, and the usage ratio can be used to compare with the corresponding sub-thresholds.

[0047] In a specific example, the computing resource usage information includes 4 CPU cores in total, 2 are used; 8G of RAM in total, 4G is used; 250G of ROM in total, 125G is used. After conversion to a ratio, the usage ratio of the CPU is 50%, the usage ratio of the RAM is 50%, and the usage ratio of the ROM is 50%. Correspondingly, in the first preset threshold, the sub-threshold set for the CPU is 70%, the sub-threshold of the RAM is 60%, and the sub-threshold of the ROM is 80%. After separate comparisons, none of them exceed the sub-threshold. At this time, it is determined that the computing resource usage information does not exceed the first preset threshold.

[0048] In addition, in this step, if it exceeds, it means that the computing resources of the exceeded single processing unit are tense, and there may be a phenomenon of processing congestion, and vertical expansion is required, that is, computing resource scheduling in the first mode. Therefore, if it exceeds, this step will determine that the processing unit of the DPI system needs to perform computing resource scheduling in the first mode.

[0049] Step 302: If the computing resource usage information of each processing unit does not exceed the first preset threshold, calculate the average value of the computing resource usage information of all processing units, and determine whether the average value exceeds the second preset threshold.

[0050] If the computing resource usage information of each processing unit does not exceed the first preset threshold, it indicates that the computing resources of a single processing unit are not tense. However, it cannot be excluded whether the overall DPI system is in a saturated state. It should be noted that the saturated state means that each processing unit is performing a certain amount of processing. If a new processing task comes at this time, it cannot be assigned to an idle processing unit.

[0051] Therefore, in this step, the average value of the computing resource usage information of all processing units will also be calculated. Since the computing resources include multiple resources, the average value in this step is calculated for each type of resource.

[0052] It should be noted that in this step, the computing resource usage information will be first converted into a usage ratio. If it has been converted into a usage ratio in the previous step, this step can directly obtain the usage ratios of the computing resources of each processing unit in the previous step, and then calculate the average value of the usage ratios of all processing units for any type of computing resource.

[0053] In addition, the second preset threshold will also include sub-thresholds corresponding to each computing resource. Similar to Step 301, when comparing, each type of computing resource should be compared separately. As long as there is a computing resource whose usage ratio exceeds the corresponding sub-threshold, it is determined that the average value exceeds the second preset threshold.

[0054] Step 303: If the average value exceeds the second preset threshold, determine that the DPI system needs to perform computing resource scheduling in the second mode.

[0055] If the average value exceeds the second preset threshold, it indicates that the processing units of the DPI system are in a saturated state at this time, and horizontal expansion is required, that is, adding processing units with a certain computing resource specification, which is the computing resource scheduling in the second mode. Therefore, in this step, it is determined that the DPI system needs to perform computing resource scheduling in the second mode.

[0056] It should be noted that both vertical expansion and horizontal expansion in this embodiment can be implemented using the Heat physical resource orchestration engine. The Heat physical resource orchestration engine will orchestrate physical resources according to the scheduling plan. For the determination of the scheduling plan, reference can be made to Figure 4 , Figure 4 which is the flow diagram for determining the scheduling plan provided in Embodiment 2 of this application.

[0057] Such as Figure 4As shown in the figure, the process of determining the scheduling scheme provided in this embodiment may include:

[0058] Step 401: If it is determined that the processing unit of the DPI system needs to perform computing resource scheduling in the first mode, determine the target resource specification required for expanding the processing unit based on the computing resource usage information of the processing unit.

[0059] In this step, the target resource specification refers to the amount of resources required to expand the processing unit. Since computing resources include various resources, the target resource specification in this step may include the expansion amounts for various resources.

[0060] It should be noted that when determining the target resource specification in this step, it can be determined according to the pre-set specification levels. Specifically, different intervals of computing resource usage ratios can be pre-set corresponding to the specification levels, as shown in Table 1 below.

[0061] Table 1

[0062]

[0063]

[0064] It should be noted that in the example of Table 1, the interval is the interval of the usage ratio, and the level is the multiple relative to the total amount of resources of the processing unit.

[0065] That is to say, if the usage ratio of the CPU is in the interval (70%, 80%], the specification level for expanding the CPU is determined to be 0.5 times. If the total number of CPU cores is 4, then the number of CPU cores in the target resource specification is 4 * 0.5 = 2. Among them, for resources with integer amounts, such as the CPU, the calculated value needs to be rounded. For expansion, it can be rounded up, that is, adding 1 to the integer part and removing the decimal part.

[0066] Step 402: Determine the expansion of the processing unit according to the target resource specification as the scheduling scheme.

[0067] In this step, since in the foregoing process, it may involve performing computing resource scheduling in the first mode for multiple processing units, in the scheduling scheme, it is necessary to map each processing unit to the corresponding target resource specification.

[0068] Step 403: If it is determined that the DPI system needs to perform computing resource scheduling in the second mode, determine the initial resource specification based on the average value.

[0069] In this step, a multiple can be pre-set, such as two times. If the calculated average value is the usage ratio, then the average value can be multiplied by 2 and then multiplied by the average total amount of resources to obtain the final initial resource specification.

[0070] Step 404: Obtain the currently allocable resource specifications, and determine the target resource specifications based on the currently allocable resource specifications and the initial resource specifications.

[0071] Since the resources in the system total are limited, the initial resource specifications may not be satisfied. To avoid scheduling errors caused by the possible non - satisfaction of the initial resource specifications, in this step, it can first be determined whether the currently allocable resource specifications meet the initial resource specifications. If they do, the initial resource specifications are determined as the target resource specifications; if not, the initial resource specifications are reduced according to a preset adjustment level, and it is repeatedly determined whether the currently allocable resource specifications meet the reduced initial resource specifications.

[0072] Among them, the preset adjustment level refers to reducing the initial resource specifications according to a certain gradient. This gradient can be set to different values for different resources, or a unified reduction ratio can be set to achieve it. For example, each time it is reduced by 0.1.

[0073] Of course, since there are multiple resources included, as long as one of the resources cannot be satisfied, it will be determined that the currently allocable resource specifications do not meet the initial resource specifications. At this time, only the non - satisfied resource needs to be reduced, and it is not necessary to uniformly reduce the specifications of all resources.

[0074] Step 405: Determine the processing unit that increases the target resource specifications as the scheduling plan.

[0075] In this step, the processing unit that increases the target resource specifications refers to increasing the processing unit with the target resource specifications.

[0076] In addition, during specific expansion (i.e., when scheduling computing resources according to the scheduling plan), the Heat physical resource orchestration engine can be used. This engine will parse the scheduling plan into various types of resources required and query the resource management services of the corresponding clients (i.e., the clients that own the resources) for each type of resource, and then use a rest request to request the resource management services of the corresponding clients to create the corresponding resources to achieve expansion.

[0077] It should be noted that the specific implementation of the Heat physical resource orchestration engine can refer to the description of related technologies and will not be elaborated here.

[0078] Embodiment III

[0079] For the specific processing process of determining whether the DPI system needs to perform scheduling of computing resources, reference can be made to Figure 5 , Figure 5 which is a schematic flowchart of a process for determining whether the DPI system needs to perform scheduling of computing resources provided in Embodiment II of this application. This embodiment mainly describes the scaling - down scenario.

[0080] As shown Figure 5 in the figure, the process of determining whether the DPI system needs to schedule computing resources may include:

[0081] Step 501: For any processing unit, compare whether the computing resource usage information of the processing unit is lower than a third preset threshold. If it is lower, determine that the processing unit of the DPI system needs to perform computing resource scheduling in the third mode.

[0082] In this embodiment, each processing unit is analyzed first. In this step, for any processing unit, it means that each processing unit will be compared in this step. It should be noted that since the computing resources include multiple resources, there will also be multiple sub-thresholds corresponding to the third preset threshold. That is to say, for each type of resource, there will be a corresponding sub-threshold.

[0083] When comparing whether the computing resource usage information of the processing unit is lower than the third preset threshold, it is necessary to separately compare whether the current usage information of each type of resource is lower than its corresponding sub-threshold. Only when all resources are lower than their respective sub-thresholds will it be considered that the computing resource usage information of the processing unit is lower than the third preset threshold.

[0084] Of course, sometimes with the implementation of scaling, the computing resource rules of each processing unit may be different. At this time, comparing the computing resource usage information may lose the meaning of comparison. Therefore, the computing resource usage information can be converted into a usage ratio. Correspondingly, sub-thresholds for the ratio will be set for each type of resource, and the usage ratio can be used to compare with the corresponding sub-thresholds.

[0085] In a specific example, the computing resource usage information includes 4 CPU cores in total, with 2 cores used; 8G of RAM in total, with 4G used; 250G of ROM in total, with 125G used. After conversion to a ratio, the usage ratio of the CPU is 50%, the usage ratio of the RAM is 50%, and the usage ratio of the ROM is 50%. Correspondingly, in the third preset threshold, the sub-threshold set for the CPU is 20%, the sub-threshold for the RAM is 20%, and the sub-threshold for the ROM is 10%. After separate comparisons, none of them are lower than the sub-thresholds. At this time, it is determined that the computing resource usage information is not lower than the first preset threshold.

[0086] In addition, in this step, if it is determined that it is lower, it means that the computing resources of a single processing unit are too idle and need to be vertically scaled down to save system resources, that is, the computing resource scheduling in the third mode. Therefore, if it is lower, this step will determine that the processing unit of the DPI system needs to perform computing resource scheduling in the third mode.

[0087] Step 502: If the computing resource usage information of each processing unit is not lower than the third preset threshold, calculate the average value of the computing resource usage information of all processing units, and determine whether the average value is lower than the fourth preset threshold.

[0088] If the computing resource usage information of each processing unit is not lower than the third preset threshold, it indicates that the computing resources of a single processing unit are not idle. However, it cannot be excluded whether the overall DPI system is in an idle state. Therefore, in this step, the average value of the computing resource usage information of all processing units will also be obtained. For the specific details, please refer to the relevant content in Step 302, which will not be elaborated here.

[0089] Step 503: If the average value exceeds the fourth preset threshold, determine that the DPI system needs to perform computing resource scheduling in the fourth mode.

[0090] If the average value exceeds the fourth preset threshold, it indicates that the processing units of the DPI system are in an idle state at this time, and horizontal scaling down is required, that is, reducing the processing units with a certain computing resource specification, which is the computing resource scheduling in the fourth mode. Therefore, in this step, it is determined that the DPI system needs to perform computing resource scheduling in the fourth mode.

[0091] It should be noted that both vertical scaling down and horizontal scaling down in this embodiment can be implemented using the Heat physical resource orchestration engine. The Heat physical resource orchestration engine will perform physical resource orchestration according to the scheduling plan. For the determination of the scheduling plan, it can be as follows.

[0092] If it is determined that the processing units of the DPI system need to perform computing resource scheduling in the third mode, determine the target resource specification required for scaling down the processing units based on the computing resource usage information of the processing units; determine the target resource specification for scaling down the processing units as the scheduling plan.

[0093] If it is determined that the DPI system needs to perform computing resource scheduling in the fourth mode, determine the average resource specification that is currently idle based on the average value; determine the processing units that reduce the average resource specification as the scheduling plan.

[0094] It should be noted that in the computing resource scheduling in the fourth mode, the average resource specification that is idle refers to the average value of the resources that are idle in the processing units.

[0095] Embodiment 4

[0096] Figure 6The following is a schematic structural diagram of a computing resource scheduling device provided in Embodiment 4 of this application. The computing resource scheduling device provided in the embodiments of this application can execute the computing resource scheduling method provided in any embodiment of this application, and has corresponding functional modules and beneficial effects for executing the method. The device can be implemented in software and / or hardware. For example, Figure 6 As shown, the computing resource scheduling device specifically includes: an acquisition module 601, a determination module 602, and a scheduling module 603.

[0097] Among them, the acquisition module is used to obtain the computing resource usage information of each processing unit in the DPI system in real time;

[0098] The determination module is used to determine whether the DPI system needs to perform computing resource scheduling according to the computing resource usage information;

[0099] The scheduling module is used to, if necessary, determine a scheduling plan according to the computing resource usage information, and perform computing resource scheduling on the DPI system according to the scheduling plan.

[0100] In this embodiment, by judging whether the DPI system needs to perform computing resource scheduling according to the computing resource usage information of each processing unit in the DPI system obtained in real time, if necessary, a scheduling plan is determined according to the computing resource usage information, and computing resource scheduling is performed on the DPI system according to the scheduling plan. Based on this, it is possible to determine in real time whether the DPI system needs to perform resource scheduling, and automatically generate a scheduling plan to complete resource scheduling when needed, improving the real-time performance of resource scheduling and avoiding the situation of manual scheduling after the system crashes.

[0101] Embodiment 5

[0102] Figure 7 The following is a schematic structural diagram of an electronic device provided in Embodiment 5 of this application. For example, Figure 7 As shown, the electronic device includes a processor 710, a memory 720, an input device 730, and an output device 740; the number of processors 710 in the electronic device can be one or more. Figure 7 Taking one processor 710 as an example; the processor 710, the memory 720, the input device 730, and the output device 740 in the electronic device can be connected through a bus or other means. Figure 7 Taking connection through a bus as an example.

[0103] The memory 720, being a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the computing resource scheduling method in the embodiments of the present application (for example, the acquisition module 601, the determination module 602, and the scheduling module 603 in the computing resource scheduling device). The processor 710 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 720, that is, implements the above-mentioned computing resource scheduling method.

[0104] That is, real-time obtain the computing resource usage information of each processing unit in the DPI system;

[0105] Determine whether the DPI system needs to perform computing resource scheduling according to the computing resource usage information;

[0106] If needed, determine a scheduling plan according to the computing resource usage information, and perform computing resource scheduling on the DPI system according to the scheduling plan.

[0107] The memory 720 may mainly include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the terminal, etc. In addition, the memory 720 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some instances, the memory 720 may further include a memory remotely set relative to the processor 710, and these remote memories can be connected to the electronic device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0108] The input device 730 can be used to receive the computing resource usage information. The output device 740 may include a display device such as a display screen.

[0109] Embodiment Six

[0110] Embodiment Six of the present application further provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to execute a computing resource scheduling method when executed by a computer processor. The method includes:

[0111] Real-time obtain the computing resource usage information of each processing unit in the DPI system;

[0112] Determine whether the DPI system needs to perform computing resource scheduling according to the computing resource usage information;

[0113] If needed, determine a scheduling plan according to the computing resource usage information, and perform computing resource scheduling on the DPI system according to the scheduling plan.

[0114] Certainly, for a storage medium containing computer-executable instructions provided by an embodiment of the present application, the computer-executable instructions are not limited to the above method operations, and can also execute related operations in the computing resource scheduling method provided by any embodiment of the present application.

[0115] From the above description of the embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software and necessary general-purpose hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk, or optical disc of a computer, etc., including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present application.

[0116] It should be noted that in the above embodiments of the search device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present application.

[0117] Note that the above is only a preferred embodiment of the present application and the applied technical principle. Those skilled in the art will understand that the present application is not limited to the specific embodiments here, and various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments. Without departing from the concept of the present application, more other equivalent embodiments can be included, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A computing resource scheduling method, characterized in that, The method includes: Obtaining in real time the computing resource usage information of each processing unit in the DPI system; Determining whether the DPI system needs to perform computing resource scheduling according to the computing resource usage information; If needed, determining a scheduling plan according to the computing resource usage information, and performing computing resource scheduling on the DPI system according to the scheduling plan; Wherein, the determining whether the DPI system needs to perform computing resource scheduling according to the computing resource usage information includes: For any processing unit, comparing whether the computing resource usage information of the processing unit exceeds a first preset threshold. If it exceeds, determining that the processing unit of the DPI system needs to perform computing resource scheduling in the first mode; wherein, the computing resources include multiple resources, and there are multiple sub-thresholds corresponding to the multiple resources in the first preset threshold, and each resource corresponds to one sub-threshold; the computing resource scheduling in the first mode is vertical scaling; If the computing resource usage information of each processing unit does not exceed the first preset threshold, calculating the average value of the computing resource usage information of all processing units, and determining whether the average value exceeds a second preset threshold; wherein, each resource in the computing resources corresponds to an average value; If the average value exceeds the second preset threshold, determining that the DPI system needs to perform computing resource scheduling in the second mode; wherein, the computing resource scheduling in the second mode is horizontal scaling; Wherein, the determining a scheduling plan according to the computing resource usage information includes: If it is determined that the processing unit of the DPI system needs to perform computing resource scheduling in the first mode, determining the target resource specification required for scaling the processing unit based on the computing resource usage information of the processing unit; wherein, the target resource specification is determined by pre-setting specification levels corresponding to different intervals of computing resource usage ratios; Determining the scaling of the processing unit according to the target resource specification as the scheduling plan; Wherein, the determining a scheduling plan according to the computing resource usage information further includes: If it is determined that the DPI system needs to perform computing resource scheduling in the second mode, determining an initial resource specification based on the average value; Obtaining the currently available resource specification, and determining the target resource specification based on the currently available resource specification and the initial resource specification; Determining the processing units with the increased target resource specification as the scheduling plan; Wherein, the determining the target resource specification based on the currently available resource specification and the initial resource specification includes: Judging whether the currently available resource specification meets the initial resource specification. If it meets, determining the initial resource specification as the target resource specification; If it does not meet, reducing the initial resource specification according to a preset adjustment level, and repeating to judge whether the currently available resource specification meets the reduced initial resource specification; wherein, the preset adjustment level refers to reducing the initial resource specification according to a certain gradient, and the gradient is obtained by setting different values for different resources or setting a unified reduction ratio.

2. The method according to claim 1, characterized in that, Determining whether the DPI system needs to perform computing resource scheduling according to the computing resource usage information includes: For any processing unit, comparing whether the computing resource usage information of the processing unit is lower than a third preset threshold. If it is lower, determining that the processing unit of the DPI system needs to perform computing resource scheduling in the third mode; If the computing resource usage information of each processing unit is not lower than the third preset threshold, calculating the average value of the computing resource usage information of all processing units and determining whether the average value is lower than a fourth preset threshold; If the average value exceeds the fourth preset threshold, determining that the DPI system needs to perform computing resource scheduling in the fourth mode.

3. The method according to claim 2, characterized in that, Determining a scheduling plan according to the computing resource usage information includes: If it is determined that the processing unit of the DPI system needs to perform computing resource scheduling in the third mode, determining the target resource specification required for downsizing the processing unit based on the computing resource usage information of the processing unit; Determining the target resource specification for downsizing the processing unit as the scheduling plan.

4. The method according to claim 2, characterized in that, Determining a scheduling plan according to the computing resource usage information includes: If it is determined that the DPI system needs to perform computing resource scheduling in the fourth mode, determining the average resource specification that is currently idle based on the average value; Determining the processing units with the reduced average resource specification as the scheduling plan.

5. A computing resource scheduling device, characterized in that, The device includes: An acquisition module, configured to acquire the computing resource usage information of each processing unit in the DPI system in real time; A determination module, configured to determine whether the DPI system needs to perform computing resource scheduling according to the computing resource usage information; Wherein, the determination module includes: A first mode determination subunit, configured to, for any processing unit, compare whether the computing resource usage information of the processing unit exceeds a first preset threshold. If it exceeds, determining that the processing unit of the DPI system needs to perform computing resource scheduling in the first mode; wherein, the computing resources include multiple resources, and there are multiple sub-thresholds corresponding to the multiple resources in the first preset threshold, and each resource corresponds to one sub-threshold; the computing resource scheduling in the first mode is vertical expansion; A second mode determination subunit, configured to, if the computing resource usage information of each processing unit does not exceed the first preset threshold, calculate the average value of the computing resource usage information of all processing units and determine whether the average value exceeds a second preset threshold; wherein, each resource in the computing resources corresponds to an average value; if the average value exceeds the second preset threshold, determining that the DPI system needs to perform computing resource scheduling in the second mode; wherein, the computing resource scheduling in the second mode is horizontal expansion; A scheduling module, configured to, if necessary, determine a scheduling plan according to the computing resource usage information and perform computing resource scheduling on the DPI system according to the scheduling plan; Wherein, the scheduling module includes: The first-mode scheduling unit is configured to, if it is determined that the processing unit of the DPI system needs to perform computing resource scheduling in the first mode, determine the target resource specification required for expanding the processing unit based on the computing resource usage information of the processing unit; wherein, the target resource specification is determined by presetting specification levels corresponding to computing resource usage ratios in different intervals; and determine the scheduling plan as expanding the processing unit according to the target resource specification. The second-module scheduling unit is configured to, if it is determined that the DPI system needs to perform computing resource scheduling in the second mode, determine the initial resource specification based on the average value; obtain the currently allocable resource specification, and determine the target resource specification based on the currently allocable resource specification and the initial resource specification; and determine the scheduling plan as adding a processing unit with the target resource specification. Wherein, the second-module scheduling unit includes: The resource specification adjustment sub-unit is configured to determine whether the currently allocable resource specification meets the initial resource specification. If it meets, determine the initial resource specification as the target resource specification; if it does not meet, reduce the initial resource specification according to a preset adjustment level, and repeatedly determine whether the currently allocable resource specification meets the reduced initial resource specification; wherein, the preset adjustment level refers to reducing the initial resource specification according to a certain gradient, and this gradient is obtained by setting different values for different resources or setting a unified reduction ratio.

6. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the computing resource scheduling method according to any one of claims 1-4.

7. A computer-readable storage medium, on which a computer program is stored, characterized in that, When the program is executed by the processor, it implements the computing resource scheduling method according to any one of claims 1-4.

Images