CN109040156B - Soft load resource processing method and device based on container cloud - Google Patents

Abstract

The present invention provides a container cloud-based soft load resource processing method and device. The method includes: acquiring soft load queue lengths at multiple times in the soft load resource pool, where the soft load queue lengths at the multiple times include at least the soft load queue length at the current moment; and according to the soft load queue lengths at the multiple times The length acquires queue mutation information; the soft load resource is processed in units of soft load containers according to the queue mutation information. The embodiment of the present invention is based on the containerization technology, integrates the underlying resources, the soft load service and the application service share resources, and improves the resource utilization rate; the containerized soft load service makes up for the defect of the existing technology that cannot quickly deploy the soft load service, and uses the soft load service. The load container automatically expands or shrinks the soft load resources dynamically on a unit basis, reducing system service interruptions caused by high concurrency and high traffic or burst traffic.

Description

A method and device for processing soft load resources based on container cloud

technical field

The present invention relates to the technical field of load balancing, in particular to a container cloud-based soft load resource processing method and device.

Background technique

With the rapid development of Internet and cloud computing technology, the web application based on virtualization has become the most important and widespread application at present. At present, the amount of information exchange based on web applications is increasing exponentially. The application server is facing the pressure of a sharp increase in the number of visits, which brings extremely high requirements on its response capability and processing capability. Effective integration, data center resource control and scheduling play a decisive role in the normal operation of the business.

Due to the objective existence of server memory, CPU processing speed and other related factors, the soft load server cannot process all requests in a timely manner when business expansion, hotspot activities are launched or periodic business peaks, which will inevitably cause The soft load queue is blocked, the response is slow, the request is lost, and even the service cannot be accessed. In the business peak period of high concurrency and high traffic, the existing technology manually expands the soft load according to a certain strategy, and manually expands the soft load in units of virtual machines during business expansion, hotspot activity launch or periodic business peaks. , when the hotspot activity ends or the business peak returns to normal, then manually recover the soft load in units of virtual machines. The existing technology mainly manually expands and recovers soft loads based on experience, and is based on virtual machines, which cannot quickly respond to the requirements of soft load resources, resulting in unstable service access.

Specifically, the principle of the existing soft load resource processing method is shown in Figure 1. When a user performs large concurrent access to the application system, the hard load or LVS is used for hard load balancing first. Access the soft load. According to the current usage pressure of the soft load and the historical experience of operation and maintenance, the data center will manually deploy the soft load server of the data center in advance in units of virtual machines by the operation and maintenance personnel. In this way, it can be ensured to some extent that the business deployed in the data center will not cause problems such as downtime due to excessive soft load pressure due to excessive access volume.

Usually, the service access of the data center will fail in the following situations: 1) When the service access volume increases suddenly, the soft load of the existing technology adopts the virtual machine mode, which has a long deployment period and poor flexibility, which requires soft load. No timely response; 2) The launch of hot events or periodic business peaks, in these two cases, general business traffic generally lacks empirical values or is difficult to make early predictions based on experience values, and it is also impossible to make predictions based on current 3) Generally, there are many factors that affect the normal access of the service. The shortage of various resources caused by various factors will affect the normal operation and access of the service, and the online service cannot be normally provided to users. , when the above problems occur, the prior art can only perform passive processing when the fault occurs, and allocate resources to the overloaded soft load in units of virtual machines, which results in a waste of resources. In the case of serious failure, most users cannot access the business system, which is unacceptable for large or core systems.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a container cloud-based soft load resource processing method and device, which are used to solve the problems of complex resource deployment and resource waste caused by manual resource expansion and scaling in units of virtual machines in the existing soft load resource processing method.

An embodiment of the present invention provides a container cloud-based soft load resource processing method, including:

Acquiring soft load queue lengths at multiple times of the soft load resource pool, where the soft load queue lengths at the multiple times include at least the soft load queue length at the current moment;

Obtain queue mutation information according to the soft load queue lengths at the multiple times;

The soft load resources are processed in units of soft load containers according to the queue mutation information.

Optionally, the queue mutation information is obtained according to the soft load queue lengths at the multiple times, including:

The first queue mutation factor and the second queue mutation factor are obtained according to the soft load queue lengths at the multiple moments, the first queue mutation factor is the queue mutation factor before the current moment, and the second queue mutation factor is Including the queue mutation factor at the current moment;

Cohort mutation information is acquired according to the difference between the mutation factor of the first cohort and the mutation factor of the second cohort.

Optionally, the first cohort mutation factor is obtained according to the following formula:

The second cohort mutation factor is obtained according to the following formula:

Among them, ε1 represents the mutation factor of the first queue, ε2 represents the mutation factor of the second queue; n represents the number of acquired soft load queue lengths; x represents the soft load queue length at the current moment, and x _i represents the difference i from the current moment. soft load queue length.

Optionally, the processing of soft load resources in units of soft load containers according to the queue mutation information includes:

If the difference between the mutation factor of the second queue and the mutation factor of the second queue is greater than a first preset threshold, the soft load resource is expanded in units of soft load containers;

If the difference between the mutation factor of the first queue and the mutation factor of the second queue is greater than a first preset threshold, shrink the soft load resource in units of soft load containers;

Optionally, when the absolute value of the difference between the mutation factor of the first cohort and the mutation factor of the second cohort is less than a first preset threshold, the method further includes:

Obtain the weight value of resource processing according to the soft load queue length, concurrency and response time at the current moment;

If the weight value of the resource processing is greater than the second preset threshold, expand the soft load resource in units of soft load containers;

If the weight value of the resource processing is smaller than the third preset threshold, the soft load resource is scaled down in units of soft load containers.

Optionally, obtaining the weight value of resource processing according to the soft load queue length, concurrency and response time at the current moment includes:

Obtain the degree coefficient of the soft load queue length at the current moment, the degree coefficient of the concurrency amount, and the degree coefficient of the response time, respectively, according to the soft load queue length concurrency and the response time at the current moment;

The weight value of resource processing is obtained according to the degree coefficient of the soft load queue length at the current moment, the degree coefficient of the concurrency amount, and the degree coefficient of the response time.

An embodiment of the present invention provides a container cloud-based soft load resource processing device, including:

a soft-load queue length acquiring unit, configured to acquire soft-load queue lengths at multiple moments in the soft-load resource pool, where the soft-load queue lengths at the multiple moments include at least the soft-load queue length at the current moment;

a queue mutation information acquisition unit, configured to acquire queue mutation information according to the soft load queue lengths at the multiple times;

The processing unit is configured to process the soft load resources in units of soft load containers according to the queue mutation information.

Optionally, the queue mutation information acquisition unit includes:

a queue mutation factor acquisition module, configured to acquire a first queue mutation factor and a second queue mutation factor according to the soft load queue lengths at the multiple moments, where the first queue mutation factor is the queue mutation factor before the current moment, The second cohort mutation factor is the cohort mutation factor including the current moment;

A queue mutation information acquisition module, configured to acquire queue mutation information according to the difference between the first queue mutation factor and the second queue mutation factor.

An embodiment of the present invention provides an electronic device, including: a processor, a memory, and a bus; wherein,

The processor and the memory communicate with each other through the bus;

The processor is configured to call the program instructions in the memory to execute the above-mentioned method for processing soft load resources based on the container cloud.

An embodiment of the present invention provides a non-transitory computer-readable storage medium, where the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions cause the computer to execute the above-mentioned container cloud-based soft load resource processing method .

The container cloud-based soft load resource processing method and device provided by the embodiments of the present invention acquire soft load queue lengths at multiple times in the soft load resource pool, and the soft load queue lengths at multiple times include at least the soft load queue length at the current moment. Load queue length; obtain queue mutation information according to the soft load queue lengths at the multiple times; process soft load resources in units of soft load containers according to the queue mutation information. The embodiment of the present invention is based on the containerization technology, integrates the underlying resources, the soft load service and the application service share resources, and improves the resource utilization rate; the containerized soft load service makes up for the defect of the existing technology that cannot quickly deploy the soft load service, and uses the soft load service. The load container automatically expands or shrinks the soft load resources dynamically on a unit basis, reducing system service interruptions caused by high concurrency and high traffic or burst traffic.

Description of drawings

In order to illustrate the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are For some embodiments of the present invention, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

1 is a schematic diagram of a soft load resource processing method in the prior art;

2 is a schematic flowchart of a container cloud-based soft load resource processing method according to an embodiment of the present invention;

3 is a schematic diagram of a container cloud-based soft load resource processing method according to an embodiment of the present invention;

4 is a schematic structural diagram of a container cloud-based soft load resource processing apparatus according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

In the prior art, although it is possible to manually schedule soft load resources based on operation and maintenance experience and the usage of CPU and memory of soft load servers to ensure normal access to services, in most cases, it is difficult to predict concurrent requests for services. Due to the inability to dynamically expand and contract soft load resources in a timely manner, the service access failure of the data center and normal service resources cannot be fully utilized.

In the prior art, the soft load balancing elastic scaling capability is weak, and the deployment method is constructed in units of virtual machines, the expansion process is complicated, and the deployment time is long. Rapid deployment expansion and dynamic scheduling cannot be performed when business volume increases suddenly, resulting in business failures. At the same time, soft load balancing cannot automatically reduce capacity, and system resources are reserved and wasted to a certain extent.

FIG. 2 is a schematic flowchart of a method for processing soft load resources based on a container cloud according to an embodiment of the present invention.

It should be noted that the container cloud uses the container as the basic unit of resource segmentation and scheduling, encapsulates the entire software runtime environment, and provides a platform for building, publishing, and running distributed applications.

As shown in Figure 2, the method of this embodiment includes:

S21: Acquire soft load queue lengths at multiple times in the soft load resource pool, where the soft load queue lengths at the multiple times at least include the soft load queue length at the current moment;

It should be noted that the soft load resource pool in this embodiment of the present invention includes multiple soft load containers, and each soft load container (as shown in FIG. 3 ) runs a soft load service. The soft load queue stores pending concurrent requests, and the number of pending concurrent requests is the length of the soft load queue.

In practical applications, the host Master node obtains the soft load queue length at multiple times through the performance of the data center soft load resource pool and log data.

S22: Acquire queue mutation information according to the soft load queue lengths at the multiple times;

It is understandable that if there is a large difference in the length of the soft load queue between the current moment and the entire previous time period, it means that the service request volume changes greatly, and the soft load needs to be expanded or reduced. Therefore, in the embodiment of the present invention, the queue mutation information is obtained according to the soft load queue lengths at multiple times, and the soft load resource can be dynamically expanded or reduced according to the queue mutation information.

S23: Process soft load resources in units of soft load containers according to the queue mutation information;

It is understandable that the processing process of soft load resources includes expansion and reduction of soft load resources; expansion of soft load resources refers to adding a soft load container, and shrinking of soft load resources refers to reducing soft load. container.

In practical applications, if elastic scaling is required, the host Master node sends an elastic scaling command to the data center soft load resource pool to perform soft load scaling and records the elastic scaling event. If the data center soft load resource pool cannot meet the resource requirements required for elastic expansion, the super administrator is notified to expand the resource pool and perform elastic scheduling again.

The container cloud-based soft load resource processing method provided by the embodiments of the present invention is based on containerization technology, integrates underlying resources, shares resources with soft load services and application services, and improves resource utilization; containerized soft load services make up for existing The technology cannot quickly deploy soft load services. It automatically expands or shrinks soft load resources dynamically in units of soft load containers, reducing system service interruptions caused by high concurrency and high traffic or burst traffic.

In an optional implementation manner of the embodiment of the present invention, similar to the method in FIG. 2 , obtaining queue mutation information according to the soft load queue lengths at the multiple times includes:

The first queue mutation factor and the second queue mutation factor are obtained according to the soft load queue lengths at the multiple moments, the first queue mutation factor is the queue mutation factor before the current moment, and the second queue mutation factor is Including the queue mutation factor at the current moment;

Cohort mutation information is acquired according to the difference between the mutation factor of the first cohort and the mutation factor of the second cohort.

Specifically, the first cohort mutation factor is obtained according to the following formula:

The second cohort mutation factor is obtained according to the following formula:

Among them, ε1 represents the mutation factor of the first queue, ε2 represents the mutation factor of the second queue; n represents the number of acquired soft load queue lengths; x represents the soft load queue length at the current moment, and x _i represents the difference i from the current moment. soft load queue length.

For example, the current time is 12 o'clock, and the lengths of the soft load queues corresponding to the three times of 12 o'clock, 11 o'clock and 10 o'clock are obtained. The queue mutation factor excluding the current time 12 o'clock is calculated according to the calculation formula of the first queue mutation factor, and the queue mutation factor including the current time 12 o'clock is calculated according to the calculation formula of the second queue mutation factor.

Further, the processing of soft load resources in units of soft load containers according to the queue mutation information includes:

If the difference between the mutation factor of the second queue and the mutation factor of the second queue is greater than a first preset threshold, the soft load resource is expanded in units of soft load containers;

If the difference between the mutation factor of the first queue and the mutation factor of the second queue is greater than a first preset threshold, shrink the soft load resource in units of soft load containers;

Further, when the absolute value of the difference between the mutation factor of the first cohort and the mutation factor of the second cohort is less than a first preset threshold, the method further includes:

Obtain the weight value of resource processing according to the soft load queue length, concurrency and response time at the current moment;

If the weight value of the resource processing is greater than the second preset threshold, expand the soft load resource in units of soft load containers;

If the weight value of the resource processing is smaller than the third preset threshold, the soft load resource is scaled down in units of soft load containers.

It should be noted that the concurrency in the embodiment of the present invention refers to the number of concurrent requests being processed.

It is understandable that, when it is determined according to the queue mutation factor that there is no mutation in the soft load queue, the soft load resource is processed according to the soft load queue length, concurrency and response time at the current moment.

Specifically, obtaining the weight value of resource processing according to the soft load queue length, concurrency and response time at the current moment includes:

Obtain the degree coefficient of the soft load queue length at the current moment, the degree coefficient of the concurrency amount, and the degree coefficient of the response time, respectively, according to the soft load queue length concurrency and the response time at the current moment;

The weight value of resource processing is obtained according to the degree coefficient of the soft load queue length at the current moment, the degree coefficient of the concurrency amount, and the degree coefficient of the response time.

In practical applications, obtaining the degree coefficients of the above three indicators needs to be assigned according to the assignment reference table. This operation can be dynamically assigned by the administrator for different application scenarios and time periods. The assignment reference table is shown in Table 1:

Table 1 Assignment reference table

extremely important strongly important obviously important 9 7 5

Perform normalization processing according to the assignment reference table to obtain the degree coefficients corresponding to the above three indicators. x _{i_norm} is the degree coefficient of the index, and the specific calculation method is as follows:

where x _i represents the value of the i-th item in the assignment reference table.

For example, at the current moment, the soft load queue length is 10, the concurrency is 100, and the response time is 30 (unit is ms). According to the corresponding importance degree, the degree coefficients of the above three indicators are obtained. (Assume the importance of queue length: 9; the importance of concurrency: 7; the importance of response time: 5).

Therefore, the degree coefficient of the soft load queue length at the current moment is 9/21; the degree coefficient of the concurrency is 7/21; and the degree coefficient of the response time is 5/21. Add the three to get a value. Compare this value with the upper and lower thresholds.

In practical applications, the most appropriate upper and lower thresholds can be obtained after many experiments according to the actual operating conditions, or the administrator can manually specify the upper and lower thresholds according to the soft load requirements.

In practical applications, the backend soft load instance is updated by calling the hard load interface. Start the soft load instance and load information first, and then update the hard load information to ensure that there is no perception when the service is accessed.

The embodiment of the present invention combines the containerization technology to integrate the underlying resources, the soft load service and the application service share the resource pool, maximize the utilization of the resources of the data center, reduce the waste and redundancy of resources, and improve the resource utilization rate of the data center. For the container cloud environment of the data center, it has good promotion value. Containerizing soft-load services can realize dynamic expansion and elastic scaling of soft-load resources, effectively improve the response time of data centers, and quickly scale soft-load resources for large traffic and large concurrent services. And through the two-level judgment mechanism, the soft load usage is comprehensively considered, and the queue variation factor is added, which can make more accurate judgments on the soft load status, realize fine-grained elastic scaling of resources, and have strong performance in large-scale production environments. practical value.

FIG. 4 is a schematic structural diagram of a container cloud-based soft load resource processing apparatus according to an embodiment of the present invention. As shown in FIG. 4 , the apparatus of this embodiment includes a soft load queue length acquisition unit 41, a queue mutation information acquisition unit 42 and a processing unit 43, specifically:

The soft load queue length obtaining unit 41 is configured to obtain the soft load queue lengths at multiple moments of the soft load resource pool, and the soft load queue lengths at the multiple moments include at least the soft load queue length at the current moment;

a queue mutation information acquisition unit 42, configured to acquire queue mutation information according to the soft load queue lengths at the multiple moments;

The processing unit 43 is configured to process soft load resources in units of soft load containers according to the queue mutation information.

The container cloud-based soft load resource processing device provided by the embodiments of the present invention is based on containerization technology, integrates underlying resources, shares resources with soft load services and application services, and improves resource utilization; the containerized soft load service makes up for existing The technology cannot quickly deploy soft load services. It automatically expands or shrinks soft load resources dynamically in units of soft load containers, reducing system service interruptions caused by high concurrency and high traffic or burst traffic.

Further, the queue mutation information acquisition unit 42 includes:

a queue mutation factor acquisition module, configured to acquire a first queue mutation factor and a second queue mutation factor according to the soft load queue lengths at the multiple moments, where the first queue mutation factor is the queue mutation factor before the current moment, The second cohort mutation factor is the cohort mutation factor including the current moment;

A queue mutation information acquisition module, configured to acquire queue mutation information according to the difference between the first queue mutation factor and the second queue mutation factor.

The container cloud-based soft load resource processing apparatus according to the embodiment of the present invention can be used to execute the foregoing method embodiments, and the principles and technical effects thereof are similar, and details are not described herein again.

FIG. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

5, the electronic device includes: a processor (processor) 51, a memory (memory) 52 and a bus 53; wherein,

The processor 51 and the memory 52 communicate with each other through the bus 53;

The processor 51 is configured to call program instructions in the memory 52 to execute the container cloud-based soft load resource processing methods provided by the above method embodiments.

In addition, the above-mentioned logic instructions in the memory 52 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

This embodiment provides a computer program product, the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a computer, the computer program The container cloud-based soft load resource processing method provided by the above method embodiments can be executed.

This embodiment provides a non-transitory computer-readable storage medium, where the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions cause the computer to execute the container cloud-based storage medium provided by the above method embodiments. Soft load resource processing method.

The container cloud-based soft load resource processing method and device provided by the embodiments of the present invention acquire soft load queue lengths at multiple times in the soft load resource pool, and the soft load queue lengths at multiple times include at least the soft load queue length at the current moment. Load queue length; obtain queue mutation information according to the soft load queue lengths at the multiple times; process soft load resources in units of soft load containers according to the queue mutation information. The embodiment of the present invention is based on the containerization technology, integrates the underlying resources, the soft load service and the application service share resources, and improves the resource utilization rate; the containerized soft load service makes up for the defect of the existing technology that cannot quickly deploy the soft load service, and uses the soft load service. The load container automatically expands or shrinks the soft load resources dynamically on a unit basis, reducing system service interruptions caused by high concurrency and high traffic or burst traffic.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

It should be noted that the terms "comprising", "comprising" or any other variation thereof are intended to cover a non-exclusive inclusion such that a process, method, article or device comprising a series of elements includes not only those elements, but also includes no explicit Other elements listed, or those inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

In the description of the present invention, numerous specific details are set forth. It will be understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description. Similarly, it is to be understood that in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together into a single embodiment in order to simplify the present disclosure and to aid in the understanding of one or more of the various aspects of the invention. , figures, or descriptions thereof. However, this method of disclosure should not be construed to reflect the intention that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

The above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The recorded technical solutions are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions in the embodiments of the present invention.

Claims (7)

1. A soft load resource processing method based on a container cloud is characterized by comprising the following steps:

acquiring soft load queue lengths of a soft load resource pool at multiple moments, wherein the soft load queue lengths at the multiple moments at least comprise the soft load queue length at the current moment;

acquiring queue mutation information according to the soft load queue lengths at the multiple moments;

processing the soft load resources by taking the soft load container as a unit according to the queue mutation information;

wherein, the obtaining of the queue mutation information according to the soft load queue lengths at the multiple moments comprises:

acquiring a first queue mutation factor and a second queue mutation factor according to the soft load queue lengths at the multiple moments, wherein the first queue mutation factor is a queue mutation factor before the current moment, and the second queue mutation factor is a queue mutation factor including the current moment;

acquiring queue mutation information according to the difference value of the first queue mutation factor and the second queue mutation factor;

wherein the first queue mutation factor is obtained according to the following formula:

obtaining the second queue mutation factor according to the following formula:

wherein ε 1 represents a first cohort mutation factor and ε 2 represents a second cohort mutation factor; n represents the number of the obtained soft load queue lengths; x represents the soft load queue length at the current time, x_iRepresenting the soft load queue length at a difference i from the current time.

2. The method according to claim 1, wherein the processing soft load resources in units of soft load containers according to the queue break information comprises:

if the difference between the second queue mutation factor and the second queue mutation factor is larger than a first preset threshold value, carrying out capacity expansion on the soft load resource by taking a soft load container as a unit;

and if the difference between the first queue mutation factor and the second queue mutation factor is larger than a first preset threshold value, carrying out capacity reduction on the soft load resource by taking a soft load container as a unit.

3. The method of claim 2, wherein when the absolute value of the difference between the first queue mutation factor and the second queue mutation factor is less than a first preset threshold, the method further comprises:

acquiring a weight value of resource processing according to the length, the concurrency quantity and the response time of the soft load queue at the current moment;

if the weight value of the resource processing is larger than a second preset threshold value, carrying out capacity expansion on the soft load resource by taking a soft load container as a unit;

and if the weight value of the resource processing is smaller than a third preset threshold value, carrying out capacity reduction on the soft load resource by taking a soft load container as a unit.

4. The method according to claim 3, wherein the obtaining the weight value of the resource processing according to the soft load queue length, the concurrency amount and the response time at the current time comprises:

respectively acquiring a degree coefficient of the soft load queue length, a degree coefficient of the concurrency amount and a degree coefficient of the response time at the current moment according to the concurrency amount and the response time of the soft load queue length at the current moment;

and acquiring a weight value of resource processing according to the degree coefficient of the soft load queue length at the current moment, the degree coefficient of the concurrency quantity and the degree coefficient of the response time.

5. A container cloud-based soft load resource processing apparatus, comprising:

a soft load queue length obtaining unit, configured to obtain soft load queue lengths at multiple times of a soft load resource pool, where the soft load queue lengths at the multiple times at least include a soft load queue length at a current time;

a queue mutation information obtaining unit, configured to obtain queue mutation information according to the soft load queue lengths at the multiple times;

the processing unit is used for processing the soft load resources by taking the soft load container as a unit according to the queue mutation information;

wherein the queue mutation information acquiring unit includes:

a queue mutation factor obtaining module, configured to obtain a first queue mutation factor and a second queue mutation factor according to the soft load queue lengths at the multiple times, where the first queue mutation factor is a queue mutation factor before the current time, and the second queue mutation factor is a queue mutation factor including the current time;

the queue mutation information acquisition module is used for acquiring queue mutation information according to the difference value of the first queue mutation factor and the second queue mutation factor;

wherein the first queue mutation factor is obtained according to the following formula:

obtaining the second queue mutation factor according to the following formula:

wherein ε 1 represents a first cohort mutation factor and ε 2 represents a second cohort mutation factor; n represents the number of the obtained soft load queue lengths; x represents the soft load queue length at the current time, x_iIndicating the phase from the current timeThe soft load queue length of difference i.

6. An electronic device, comprising: a processor, a memory, and a bus; wherein,

the processor and the memory complete mutual communication through the bus;

the processor is configured to call program instructions in the memory to perform the container cloud based soft load resource handling method of any of claims 1-4.

7. A non-transitory computer readable storage medium storing computer instructions that cause the computer to perform the container cloud based soft load resource processing method of any one of claims 1-4.

Images