Resource deployment method and device of service load, electronic equipment and storage medium

Abstract

The invention discloses a service load resource deployment method and device, electronic equipment and a storage medium, and relates to the field of information security or other related fields, and the method comprises the steps: obtaining the current deployment information and operation information of a service load in a financial system, the method comprises the following steps: acquiring first labeling information used for describing a category attribute and a performance attribute of a resource domain from a resource database of a resource pool, and acquiring resource demand data used for indicating a service load and second labeling information of an evictable attribute value, and generating a target deployment scheme based on the current deployment information, the operation information, the first annotation information and the second annotation information, and performing resource deployment again according to the target deployment scheme. According to the invention, the technical problem that the in-transit transaction is affected and the system performance is lost after the business load is expelled due to the fact that a conventional resource hybrid deployment mode cannot match a proper resource domain for the business load in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of information security technology or other related fields. Specifically, it relates to a method and apparatus for deploying resources for business workloads, electronic devices, and storage media. Background Technology

[0002] With the development of cloud computing technology, hybrid resource deployment has become a popular deployment method. Hybrid resource deployment can combine different types of resource domains to improve resource utilization and system performance.

[0003] In related technologies, the main approach is to directly mix and deploy loads based on their historical performance or trends. However, due to the different characteristics of different business loads, traditional resource mixing deployment methods cannot identify sensitive types of business loads. They only consider performance and capacity, which may improve resource utilization but may also cause sensitive businesses to be evicted, thus affecting transactions in transit. Moreover, the processing performance of the application system is actually impaired during the eviction process. If complex performance situations occur, the phenomenon of bad money driving out good money may occur.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a resource deployment method, apparatus, electronic device, and storage medium for business workloads, to at least solve the technical problem in the related art where traditional resource hybrid deployment methods cannot match suitable resource domains for business workloads, resulting in business workloads being evicted and affecting in-transit transactions and causing system performance loss.

[0006] According to one aspect of the present invention, a resource deployment method for business workloads is provided, comprising: acquiring current deployment information and operation information of N business workloads in a financial system, wherein the current deployment information refers to the current deployment relationship between the business workload and M resource domains, and the operation information is used to describe the resource occupancy data of the business workload on system operation resources, and N and M are both positive integers; acquiring first labeling information of the M resource domains from a resource database of a resource pool, wherein the first labeling information is used to describe the category attributes and performance attributes of the resource domains; acquiring second labeling information of the N business workloads, wherein the second labeling information is used to indicate the resource demand data and eviction attribute value of the business workload, and the eviction attribute refers to the degree of adaptability of the business workload to reallocation of system operation resources; generating a target deployment scheme based on the current deployment information, the operation information, the first labeling information and the second labeling information, and redeploying resources according to the target deployment scheme.

[0007] Further, the second labeling information of the service load is obtained through the following steps: For each service load, the load information of the service load is obtained from the metadata pool, wherein the load information includes at least: service requirement information, latency tolerance index, and reentrancy index; the eviction attribute value of the service load is calculated based on the latency tolerance index, the reentrancy index, and preset labeling rules; the service requirement information is parsed to obtain the resource requirement data of the service load; the second labeling information is generated based on the eviction attribute value and the resource requirement data, and the service load is labeled using the second labeling information.

[0008] Further, after labeling the business load using the second labeling information, the method further includes: creating a load type data table, wherein the load type data table is used to store the load type names of N business loads, and the load type data table includes at least the following fields: load type ID and load type name; obtaining a pre-stored delay description table in the financial system, wherein the delay description table includes at least the following fields: delay description ID, delay description name, and delay tolerance index; obtaining a pre-stored reentrancy table in the financial system, wherein the reentrancy table includes at least the following fields: reentrancy ID, reentrancy name, and reentrancy index; generating a business load configuration table based on the load type data table, the delay description table, and the reentrancy table, wherein the business load configuration table records N load configuration information entries, each load configuration information entry corresponds to one business load, and the load configuration information is used to indicate the delay description ID, the reentrancy ID, and the second labeling information corresponding to the load type ID.

[0009] Further, the first annotation information of the resource domain is obtained through the following steps: for each resource domain, obtaining basic information of the resource domain, wherein the basic information includes at least: performance information and usage description; analyzing the performance information and usage description to obtain analysis results, wherein the analysis results record at least the category attribute information and performance attribute information of the resource domain; generating the first annotation information based on the category attribute information and performance attribute information in the analysis results, and using the first annotation information to annotate the resource domain.

[0010] Furthermore, the basic information also includes: resource domain name; after annotating the resource domain using the first annotation information, it further includes: creating a resource domain configuration table, wherein the resource domain configuration table is used to record M resource domain configuration information, each resource domain configuration information corresponds to one resource domain, and the resource domain configuration information is used to indicate the first annotation information corresponding to the resource domain name of the resource domain; and storing the resource domain configuration table in the resource database in the resource pool.

[0011] Further, the step of generating a target deployment scheme based on the current deployment information, the operation information, the first annotation information, and the second annotation information includes: for each resource domain, determining all the service loads already deployed in the resource domain based on the current deployment information, and determining the operation characteristics of each service load based on the operation information, wherein the operation characteristics are used to indicate whether the system operation resources provided by the current resource domain can maintain the normal operation of the service load; determining the target loads to be evicted from the service loads already deployed in the resource domain based on the operation characteristics of the service loads and the second annotation information; and generating the target deployment scheme based on the first annotation information of all resource domains and all the target loads to be evicted.

[0012] Further, the step of generating the target deployment scheme based on the first annotation information of all the resource domains and all the target loads to be evicted includes: for each target load, determining the eviction time point and eviction tolerance duration based on the load configuration information corresponding to the target load recorded in the service load configuration table; determining the redeployment time point of the target load based on the eviction time point and the eviction tolerance duration; for each resource domain, calculating the remaining resources of the resource domain after the target load in the resource domain is to be evicted; determining the target resource domain to be deployed during the redeployment process of the target load based on the remaining resources of all the resource domains and the first annotation information; and generating the target deployment scheme based on the eviction time point, the target resource domain, and the redeployment time point.

[0013] According to another aspect of the present invention, a resource deployment apparatus for business loads is also provided, comprising: a first acquisition unit, configured to acquire current deployment information and operation information of N business loads in a financial system, wherein the current deployment information refers to the current deployment relationship between the business load and M resource domains, and the operation information is used to describe the data on the occupation of system operation resources by the business load, and N and M are both positive integers; a second acquisition unit, configured to acquire first labeling information of the M resource domains from a resource database of a resource pool, wherein the first labeling information is used to describe the category attributes and performance attributes of the resource domains; a third acquisition unit, configured to acquire second labeling information of the N business loads, wherein the second labeling information is used to indicate the resource demand data and eviction attribute value of the business load, and the eviction attribute refers to the degree of adaptability of the business load to the reallocation of system operation resources; and a deployment unit, configured to generate a target deployment scheme based on the current deployment information, the operation information, the first labeling information and the second labeling information, and redeploy resources according to the target deployment scheme.

[0014] Furthermore, the resource deployment device for the service load includes: a first acquisition module, configured to acquire load information of each service load from a metadata pool, wherein the load information includes at least: service requirement information, latency tolerance index, and reentrancy index; a calculation module, configured to calculate the eviction attribute value of the service load based on the latency tolerance index, the reentrancy index, and a preset labeling rule; a parsing module, configured to parse the service requirement information to obtain the resource requirement data of the service load; and a labeling module, configured to generate second labeling information based on the eviction attribute value and the resource requirement data, and use the second labeling information to label the service load.

[0015] Furthermore, the resource deployment device for the business load further includes: a first creation module, used to create a load type data table, wherein the load type data table is used to store the load type names of N business loads, and the load type data table includes at least the following fields: load type ID and load type name; a second acquisition module, used to acquire a latency description table pre-stored in the financial system, wherein the latency description table includes at least the following fields: latency description ID, latency description name, and latency tolerance index; a third acquisition module, used to acquire a reentrancy degree table pre-stored in the financial system, wherein the reentrancy degree table includes at least the following fields: reentrancy ID, reentrancy name, and reentrancy index; and a first generation module, used to generate a business load configuration table based on the load type data table, the latency description table, and the reentrancy degree table, wherein the business load configuration table records N load configuration information entries, each load configuration information entry corresponds to one business load, and the load configuration information is used to indicate the latency description ID, the reentrancy ID, and the second annotation information corresponding to the load type ID.

[0016] Furthermore, the resource deployment device for the business load further includes: a fourth acquisition module, used to acquire basic information of each resource domain, wherein the basic information includes at least performance information and usage description; an analysis module, used to analyze the performance information and usage description to obtain analysis results, wherein the analysis results record at least the category attribute information and performance attribute information of the resource domain; and a second generation module, used to generate the first annotation information based on the category attribute information and performance attribute information in the analysis results, and use the first annotation information to annotate the resource domain.

[0017] Furthermore, the basic information also includes: resource domain name; the resource deployment device for the service load further includes: a second creation module, used to create a resource domain configuration table, wherein the resource domain configuration table is used to record M resource domain configuration information, each resource domain configuration information corresponds to one resource domain, and the resource domain configuration information is used to indicate the first annotation information corresponding to the resource domain name of the resource domain; and a storage module, used to store the resource domain configuration table in the resource database in the resource pool.

[0018] Further, the deployment unit includes: a first determining module, configured to, for each resource domain, determine all the service loads already deployed in that resource domain based on the current deployment information, and determine the operating characteristics of each service load based on the operating information, wherein the operating characteristics are used to indicate whether the system operating resources provided by the current resource domain can maintain the normal operation of the service load; a second determining module, configured to, based on the operating characteristics of the service load and the second labeling information, determine the target load to be evicted from the service loads already deployed in the resource domain; and a third generating module, configured to, based on the first labeling information of all resource domains and all the target loads to be evicted, generate the target deployment scheme.

[0019] Further, the third generation module includes: a first determining submodule, used to determine the eviction time point and eviction tolerance duration for each target load based on the load configuration information corresponding to the target load recorded in the service load configuration table; a second determining submodule, used to determine the redeployment time point of the target load based on the eviction time point and the eviction tolerance duration; a calculation submodule, used to calculate the resource remaining status of each resource domain after the target load in the resource domain is to be evictioned; a third determining submodule, used to determine the target resource domain to be deployed during the redeployment process of the target load based on the resource remaining status of all resource domains and the first annotation information; and a generation submodule, used to generate the target deployment plan based on the eviction time point, the target resource domain, and the redeployment time point.

[0020] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the resource deployment method for the business load described in any one of the above embodiments.

[0021] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the resource deployment method for the workload described in any one of the preceding embodiments.

[0022] This invention proposes a resource deployment method for business workloads. First, it obtains the current deployment and operational information of N business workloads in a financial system. The current deployment information refers to the current deployment relationship between the business workload and M resource domains, while the operational information describes the resource occupancy data of the business workload. N and M are both positive integers. Next, it obtains the first labeling information of the M resource domains from the resource pool's resource database. The first labeling information describes the category and performance attributes of the resource domains. Then, it obtains the second labeling information of the N business workloads. The second labeling information indicates the resource requirement data and eviction attribute value of the business workload. The eviction attribute refers to the degree to which the business workload can adapt to the reallocation of system operational resources. Finally, based on the current deployment information, operational information, first labeling information, and second labeling information, a target deployment plan is generated, and resources are redeployed according to the target deployment plan.

[0023] In this invention, when the load deployment of a financial system needs to be flexibly adjusted to reduce performance loss, the system determines which business loads in the current deployment relationship cannot meet the operational requirements of in-transit transactions and which resource domains require resource deployment adjustments based on the resource domain occupancy of business loads in the financial system. It then retrieves pre-labeled first annotation information for resource domains and pre-labeled second annotation information for business loads from the resource pool's resource database. The system analyzes the category and performance attributes of resource domains, the resource requirement data of business loads, and their eviction attribute values ​​to generate a target deployment scheme containing resource deployment adjustment strategies. Subsequently, resource deployment is redeployed. This invention labels business loads based on their reentrancy and latency tolerance, thereby selecting appropriate resource domains and resource mixing modes to rationally deploy or evict business loads. This improves system performance, reliability, and maintainability, thus solving the technical problem in related technologies where traditional resource mixing deployment methods cannot match suitable resource domains for business loads, leading to the eviction of business loads affecting in-transit transactions and causing system performance loss. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0025] Figure 1 This is a flowchart of an optional resource deployment method for service load according to an embodiment of the present invention;

[0026] Figure 2 This is a schematic diagram of an optional resource hybrid deployment system according to an embodiment of the present invention;

[0027] Figure 3This is a schematic diagram illustrating the interaction of various modules in an optional resource hybrid deployment system according to an embodiment of the present invention;

[0028] Figure 4 This is a schematic diagram of an optional resource deployment apparatus for business load according to an embodiment of the present invention;

[0029] Figure 5 This is a hardware structure block diagram of an electronic device (or mobile device) for a resource deployment method for business workloads according to an embodiment of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] To facilitate understanding of the present invention by those skilled in the art, some terms or nouns involved in the various embodiments of the present invention are explained below:

[0033] Business workload refers to the applications or services running on a computer system, such as web applications, database services, message queues, big data batch processing, microservices, etc.

[0034] Reentrancy refers to whether the basic unit of a business workload (such as a container) can be called or accessed concurrently multiple times without conflicts or errors. For some online businesses or microservices, the tolerance for repeated calls is low, while for some business workloads such as big data batch processing or offline computing, the reentrancy is high, and data can be processed repeatedly based on a defined dataset.

[0035] Business latency tolerance refers to the degree to which business load can tolerate request response time, i.e., whether it can tolerate a relatively long response time.

[0036] A resource domain refers to a group of computer resources, including computing resources, storage resources, network resources, etc.

[0037] Resource hybrid deployment refers to several deployment modes that combine different business load types, based on factors such as business response speed, disaster recovery level, and batch online operations, to fully utilize the current resource domain and resource pool.

[0038] It should be noted that the resource deployment method and apparatus for business loads in this invention can be used in the field of information security technology for the mixed resource deployment of financial business loads, and can also be used in any field other than information security for the mixed resource deployment of financial business loads. This invention does not limit the application field of the resource deployment method and apparatus for business loads.

[0039] It should be noted that all relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) involved in this invention are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, processing, transmission, provision, disclosure, use, and handling of such data must comply with the laws, regulations, and standards of the relevant regions, necessary confidentiality measures have been taken, and it does not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse. For example, this system has an interface with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained only after receiving consent from the aforementioned user or organization.

[0040] The information collection (e.g., user voice, video, and text collection) and analysis operations involved in this invention have provided users with corresponding operation entry points during execution, allowing users to choose to agree to or reject the automated decision results; if the user chooses to reject, the process enters the expert decision-making process.

[0041] The following embodiments of the present invention can be applied to various systems / applications / devices that require mixed resource deployment for software security vulnerability detection and source code testing for financial business workloads. They enable flexible resource deployment and resource domain adjustment based on the actual needs of financial business and system operation. The present invention subdivides and labels business types based on the reentrancy and latency tolerance of the business workload, thereby selecting appropriate resource domains and mixed resource configurations for deployment, and rationally deploying or removing business workloads to improve system resource utilization and performance.

[0042] The present invention will now be described in detail with reference to various embodiments.

[0043] Example 1

[0044] According to an embodiment of the present invention, an embodiment of a resource deployment method for business workloads is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0045] Figure 1 This is a flowchart of an optional resource deployment method for service load according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0046] Step S101: Obtain the current deployment and operation information of N business loads in the financial system, where N is a positive integer.

[0047] Step S102: Obtain the first annotation information of M resource domains from the resource database of the resource pool, wherein the first annotation information is used to describe the category attributes and performance attributes of the resource domains.

[0048] Step S103: Obtain the second labeling information of N service loads. The second labeling information is used to indicate the resource requirement data and eviction attribute value of the service load. The eviction attribute refers to the degree of adaptability of the service load to the reallocation of system operating resources.

[0049] Step S104: Generate a target deployment plan based on the current deployment information, operation information, first annotation information and second annotation information, and redeploy resources according to the target deployment plan.

[0050] Through the above steps, the current deployment and operation information of N business loads in the financial system can be obtained first. The current deployment information refers to the current deployment relationship between the business loads and M resource domains. The operation information describes the data on the usage of system operation resources by the business loads. N and M are both positive integers. Then, the first labeling information of the M resource domains is obtained from the resource pool's resource database. The first labeling information describes the category attributes and performance attributes of the resource domains. Then, the second labeling information of the N business loads is obtained. The second labeling information indicates the resource demand data and eviction attribute value of the business loads. The eviction attribute refers to the degree of adaptability of the business load to the reallocation of system operation resources. Finally, a target deployment plan is generated based on the current deployment information, operation information, first labeling information and second labeling information, and resources are redeployed according to the target deployment plan.

[0051] In this embodiment of the invention, when the load deployment of a financial system needs to be flexibly adjusted to reduce performance loss, the system determines which business loads in the current deployment relationship cannot meet the operational requirements of in-transit transactions and which resource domains require resource deployment adjustments based on the resource domain occupancy of business loads in the financial system. It then retrieves first annotation information for pre-labeled resource domains and second annotation information for pre-labeled business loads from the resource pool's resource database. The system analyzes the category and performance attributes of resource domains, the resource requirement data of business loads, and their eviction attribute values ​​to generate a target deployment scheme containing resource deployment adjustment strategies. Subsequently, resource deployment is redeployed. This invention labels business loads based on their reentrancy and latency tolerance, thereby selecting appropriate resource domains and resource mixing modes to rationally deploy or evict business loads. This improves system performance, reliability, and maintainability, thus solving the technical problem in related technologies where traditional resource mixing deployment methods cannot match suitable resource domains for business loads, leading to the impact on in-transit transactions and system performance loss after business loads are evicted.

[0052] The embodiments of the present invention will now be described in detail with reference to the steps described above.

[0053] The implementing entity of this invention can be a financial system. It can subdivide business types based on the reentrancy and latency tolerance of business loads, label business loads, and then select appropriate resource domains and resource hybrid configuration modes for deployment. At the same time, it can dynamically monitor resource usage and reasonably adjust or evict certain business loads based on operational characteristics.

[0054] Step S101: Obtain the current deployment and operation information of N business workloads in the financial system.

[0055] The current deployment information refers to the current deployment relationship between the business load and the M resource domains, while the operation information describes the data on the system operation resources occupied by the business load. Both N and M are positive integers.

[0056] It should be noted that a resource domain refers to a collection of resources, which can be classified according to factors such as resource type, performance, and capacity. For example, resource domains can be divided into x86 resource domains, ARM resource domains, and GPU resource domains. When defining the classification and performance of resource domains, factors such as resource type, performance, and capacity need to be considered. The x86 resource domain has higher performance and larger capacity, making it suitable for running CPU-intensive workloads, while the ARM resource domain is suitable for workloads in new technology transition and pilot areas.

[0057] Step S102: Obtain the first annotation information of M resource domains from the resource database of the resource pool, wherein the first annotation information is used to describe the category attributes and performance attributes of the resource domains.

[0058] Optionally, the first annotation information of a resource domain is obtained through the following steps: for each resource domain, obtaining basic information of the resource domain, wherein the basic information includes at least: performance information and usage description; analyzing the performance information and usage description to obtain analysis results, wherein the analysis results record at least the category attribute information and performance attribute information of the resource domain; generating first annotation information based on the category attribute information and performance attribute information in the analysis results, and using the first annotation information to annotate the resource domain.

[0059] It should be noted that performance information may include: CPU performance, storage performance, network performance, reliability, and usability, as shown in Table 1, which describes the basic information of common resource domains.

[0060] Table 1

[0061]

[0062]

[0063] Optionally, the basic information also includes: the resource domain name; after labeling the resource domain with the first labeling information, it also includes: creating a resource domain configuration table, wherein the resource domain configuration table is used to record M resource domain configuration information, each resource domain configuration information corresponds to a resource domain, and the resource domain configuration information is used to indicate the first labeling information corresponding to the resource domain name of the resource domain; and storing the resource domain configuration table in the resource database in the resource pool.

[0064] Step S103: Obtain the second labeling information of N service loads. The second labeling information is used to indicate the resource requirement data and eviction attribute value of the service load. The eviction attribute refers to the degree of adaptability of the service load to the reallocation of system operating resources.

[0065] It should be noted that load labeling is a preliminary step in load co-location, mainly used to label the reentrancy and latency tolerance of service loads. Optionally, the second labeling information of the service load is obtained through the following steps: For each service load, the load information of the service load is obtained from the metadata pool, wherein the load information includes at least: service requirement information, latency tolerance index, and reentrancy index; the eviction attribute value of the service load is calculated based on the latency tolerance index, reentrancy index, and preset labeling rules; the service requirement information is parsed to obtain the resource requirement data of the service load; the second labeling information is generated based on the eviction attribute value and resource requirement data, and the service load is labeled using the second labeling information.

[0066] Specifically, the reentrancy metric can be used to quantify the reentrancy of a service load. Reentrancy refers to the ability of a service load to be used simultaneously by multiple clients. In this embodiment of the invention, it can also refer to the degree to which a service load can tolerate being evicted or rescheduled under resource shortage conditions. A service load with a high reentrancy metric can tolerate being evicted or rescheduled to a greater extent and is less susceptible to the impact of resource shortages. Conversely, a service load with a low reentrancy metric can tolerate being evicted or rescheduled to a lesser extent and is more susceptible to the impact of resource shortages.

[0067] Another point to note is that latency tolerance can be used to quantify the latency tolerance of business load. Latency tolerance refers to the tolerance of business load in terms of response time (especially business latency). Latency can be roughly classified into: real-time, accuracy, timeliness, and controllability. Business loads with different tolerance levels need to be controlled to be completed within different specified time periods, otherwise it will affect the quality of financial business completion.

[0068] Before calculating the second annotation information to annotate the service load, this embodiment of the invention can first consider the characteristics of the service load and user needs, and separately mark the reentrancy and latency tolerance of the service load. That is, define the reentrancy index and latency tolerance index of the service load. For example, a marking or scoring method can be used to quantify the degree of reentrancy and latency tolerance using specified values, with higher numbers indicating higher levels. For example, reentrancy can be divided into three levels: high, medium, and low, corresponding to the values ​​3, 2, and 1 respectively for quantification and marking. Latency tolerance can be divided into five levels, corresponding to the values ​​5, 4, 3, 2, and 1 respectively, in descending order of latency tolerance.

[0069] Furthermore, in the step of calculating the evictable attribute value of the service load based on the latency tolerance index, the reentrancy index, and the preset labeling rules, the latency tolerance index and the reentrancy index obtained above can be accumulated, and the accumulated value can be used as the evictable attribute value of the service load, thereby generating the second labeling information.

[0070] The resource requirement data in the second annotation data is obtained by parsing the business requirement information of specific business workloads. It is determined by defining and classifying the resource types required by the business workload based on the actual situation of the business workload. For example, based on whether the business workload belongs to batch, online, online inference, offline learning, etc., it is determined that the business workload needs to use batch resources, online resources, online or offline resources, etc.

[0071] After marking and labeling business loads, it is necessary to integrate the labeling information of all business loads in the financial system to form a load configuration table. This table is used for reference and retrieval when the system performs mixed resource deployment and resource adjustment. Optionally, after labeling business loads using the second labeling information, the following steps are also included: creating a load type data table, which stores the load type names of N business loads. The load type data table includes at least the following fields: load type ID and load type name; obtaining a pre-stored latency description table in the financial system, which includes at least the following fields: latency description ID, latency description name, and latency tolerance index; obtaining a pre-stored reentrancy table in the financial system, which includes at least the following fields: reentrancy ID, reentrancy name, and reentrancy index; and generating a business load configuration table based on the load type data table, latency description table, and reentrancy table. The business load configuration table records N load configuration information entries, each corresponding to a business load. The load configuration information indicates the latency description ID, reentrancy ID, and second labeling information corresponding to the load type ID.

[0072] Specifically, the load type data table is shown in Table 2, the delay description table is shown in Table 3, and the reentrancy level table is shown in Table 4. The field names and data types of the data tables are specified.

[0073] Table 2

[0074] field name Data types illustrate Load_Type_ID int Load type ID, primary key Load_Type_Name varchar(50) Load type name

[0075] Table 3

[0076] field name Data types illustrate Delay_Description_ID int Delay Description ID, Primary Key Delay_Description_Name varchar(50) Delay Description Name Delay_Description_Score int Delay tolerance index

[0077] Table 4

[0078] field name Data types illustrate Tolerance_Level_ID int Reentrant ID, Primary Key Tolerance_Level_Name varchar(50) Reentrancy Names Tolerance_Level_Score int Reentrancy index

[0079] Based on the above table, a load configuration table as shown in Table 5 can be generated:

[0080] Table 5

[0081] field name Data types illustrate Load_ID int Business load ID, primary key Load_Name varchar(50) Service load name Load_Type_ID int Load type ID, foreign key Tolerance_Level_ID int Reentrant ID, Foreign Key Delay_Description_ID int Delay Description ID, Foreign Key Load_Score int Second annotation information

[0082] Step S104: Generate a target deployment plan based on the current deployment information, operation information, first annotation information and second annotation information, and redeploy resources according to the target deployment plan.

[0083] Optionally, step S104 includes: for each resource domain, determining all deployed service loads in the resource domain based on the current deployment information, and determining the operational characteristics of each service load based on the operational information, wherein the operational characteristics are used to indicate whether the system operational resources provided by the current resource domain can maintain the normal operation of the service load; determining the target load to be evicted among the deployed service loads in the resource domain based on the operational characteristics of the service load and the second labeling information; and generating a target deployment plan based on the first labeling information of all resource domains and all target loads to be evicted.

[0084] Optionally, the step of generating a target deployment plan based on the first labeling information of all resource domains and all target loads to be evicted includes: for each target load, determining the eviction time point and eviction tolerance duration based on the load configuration information corresponding to the target load recorded in the service load configuration table; determining the redeployment time point of the target load based on the eviction time point and eviction tolerance duration; for each resource domain, calculating the remaining resources of the resource domain after the target load in the resource domain is to be evicted; determining the target resource domain to be deployed during the redeployment process of the target load based on the remaining resources of all resource domains and the first labeling information; and generating a target deployment plan based on the eviction time point, the target resource domain, and the redeployment time point.

[0085] It should be noted that the target deployment scheme adopts a load balancing mode, which mixes different types of business loads with resource domains to achieve optimal performance and efficiency. The embodiments of this invention provide a load balancing mode table as shown in Table 6:

[0086] Table 6

[0087]

[0088] After resource deployment and reallocation, it is necessary to dynamically monitor resource usage to adjust and remove business loads as needed. Monitoring tools or automated systems can be used for this purpose; for example, monitoring tools can be used to monitor the usage of resources such as CPU, memory, and disk. This embodiment of the invention provides a resource monitoring table as shown in Table 7:

[0089] Table 7

[0090]

[0091]

[0092] The embodiments of the present invention have many beneficial effects, such as improving resource utilization and efficiency, improving the performance and efficiency of business load, improving system stability and reliability, and reducing system operating and maintenance costs. They have important practical application value for improving the overall performance and efficiency of the system and meeting users' real-time and accuracy requirements for business load.

[0093] The present invention will now be described in conjunction with another specific embodiment.

[0094] To overcome the problem of sensitive loads being mistakenly evicted under the current mixed deployment mode and to avoid the risk of performance loss during mixed resource scheduling, this invention proposes a resource hybrid deployment method. This method subdivides service types based on the reentrancy and latency tolerance of service loads and labels the service loads, thereby selecting appropriate resource domains and resource hybrid combination modes for deployment. At the same time, it dynamically monitors resource usage and rationally deploys or evicts service loads based on operational characteristics or changing operational characteristics.

[0095] Figure 2 This is a schematic diagram of an optional resource hybrid deployment system according to an embodiment of the present invention, such as... Figure 2 As shown, the system includes the following modules: load labeling module, business load deployment module, hybrid configuration mode selection module, resource domain classification module, and resource monitoring module.

[0096] Figure 3 This is a schematic diagram illustrating the interaction between modules in an optional resource hybrid deployment system according to an embodiment of the present invention, such as... Figure 3 As shown, the interaction flow includes:

[0097] 1. The interaction between the load labeling module and the business load.

[0098] The load labeling module obtains the reentrancy and latency tolerance of the business load from the application system metadata, calculates the eviction label value according to the rules, and labels it in the load for use by the subsequent business load deployment module. The business load deployment module also needs to record the reentrancy and latency tolerance of the business load so that it can select the appropriate resource domain and resource hybrid mode for deployment according to the characteristics of the business load and user needs.

[0099] 2. Interaction between the resource domain classification module and the business load deployment module.

[0100] The resource domain classification module needs to store the classification and performance of resource domains in a database or configuration file and label them in the resource pool for use by the subsequent workload deployment module. The workload deployment module needs to obtain the classification and performance of resource domains or their labels in order to select appropriate resource domains and resource mix patterns for deployment based on the characteristics of the workload and user needs.

[0101] 3. Interaction between the resource hybrid matching mode selection module and the business load deployment module.

[0102] The resource hybrid matching mode selection module needs to select a suitable resource hybrid matching mode for deployment based on the performance, capacity and business load requirements of the resource domain. That is, it simultaneously obtains the load label and attributes, matches them according to the mode provided by the resource hybrid matching module, forms an associated deployment cluster containing multiple loads, and deploys this group of associated loads into it according to the type of resource domain or resource pool.

[0103] 4. Interaction between the resource monitoring module and the business load deployment module.

[0104] The resource monitoring module needs to dynamically monitor resource usage, such as CPU, memory, and disk usage, and store the monitoring results in a database or configuration file for use by the subsequent workload deployment module. The workload deployment module needs to obtain resource and load monitoring results from the resource monitoring module so that it can rationally deploy or remove workloads based on real-time resource usage to achieve optimal performance and efficiency.

[0105] 5. The interaction between the business workload deployment module and the business workload.

[0106] Based on real-time monitoring and set eviction rules, the workload deployment module redeploys loads with high eviction flag values ​​to other available resource pools. For example, when resource pool 1 reaches its performance limit or a load in the resource pool experiences a surge in CPU usage, the workload deployment module triggers a load eviction action. If a load has the highest eviction flag value, the workload deployment module will prioritize eviction of this load to another resource pool.

[0107] The beneficial effects brought about by the embodiments of the present invention include at least the following four points.

[0108] 1. Improve resource utilization and efficiency: By selecting appropriate resource domains and resource mix modes for deployment based on the characteristics of the business load and user needs, and dynamically monitoring resource usage, business loads can be deployed or removed in a reasonable manner. This method can make full use of resources and improve resource utilization and efficiency.

[0109] 2. Improve the performance and efficiency of workloads: By selecting appropriate resource domains and resource mix modes for deployment based on the reentrancy and latency tolerance of workloads, and dynamically monitoring resource usage, the workloads can be deployed or evicted in a reasonable manner. This method can improve the performance and efficiency of workloads and meet users' requirements for real-time performance and accuracy.

[0110] 3. Improve system stability and reliability: By dynamically monitoring resource usage and rationally deploying or removing business loads, this method can prevent highly sensitive businesses from being removed from the system, prevent sensitive business jitter, thereby improving system stability and reliability and reducing the probability of system crashes and failures.

[0111] 4. Reduce system operating and maintenance costs: It can automate the hybrid deployment and scheduling of loads, significantly reducing the workload of operation and maintenance personnel caused by uneven resource distribution and resource fragmentation, thereby reducing system operating and maintenance costs, reducing resource waste and unnecessary operation and maintenance expenses.

[0112] The invention will now be described in conjunction with another alternative embodiment.

[0113] Example 2

[0114] The resource deployment device for service load provided in this embodiment includes multiple implementation units, each of which corresponds to a specific implementation step in Embodiment 1 above.

[0115] Figure 4 This is a schematic diagram of an optional service load resource deployment apparatus according to an embodiment of the present invention, such as... Figure 4 As shown, the device may include: a first acquisition unit 41, a second acquisition unit 42, a third acquisition unit 43, and a deployment unit 44.

[0116] The first acquisition unit 41 is used to acquire the current deployment information and operation information of N business loads in the financial system. The current deployment information refers to the current deployment relationship between the business load and M resource domains, and the operation information is used to describe the data on the occupation of system operation resources by the business load. N and M are both positive integers.

[0117] The second acquisition unit 42 is used to acquire first annotation information of M resource domains from the resource database of the resource pool, wherein the first annotation information is used to describe the category attributes and performance attributes of the resource domains.

[0118] The third acquisition unit 43 is used to acquire the second labeling information of N service loads. The second labeling information is used to indicate the resource requirement data and eviction attribute value of the service load. The eviction attribute refers to the degree to which the service load is adaptable to the reallocation of system operating resources.

[0119] Deployment unit 44 is used to generate a target deployment plan based on the current deployment information, operation information, first annotation information and second annotation information, and redeploy resources according to the target deployment plan.

[0120] The resource deployment device for the aforementioned business loads can first obtain the current deployment information and operation information of N business loads in the financial system through the first acquisition unit 41. The current deployment information refers to the current deployment relationship between the business loads and M resource domains, and the operation information is used to describe the data on the occupation of system operation resources by the business loads. N and M are both positive integers. Then, the second acquisition unit 42 obtains the first labeling information of the M resource domains from the resource database of the resource pool. The first labeling information is used to describe the category attributes and performance attributes of the resource domains. Then, the third acquisition unit 43 obtains the second labeling information of the N business loads. The second labeling information is used to indicate the resource demand data and eviction attribute value of the business loads. The eviction attribute refers to the degree of adaptability of the business loads to the reallocation of system operation resources. Finally, the deployment unit 44 generates a target deployment plan based on the current deployment information, operation information, first labeling information and second labeling information, and redeploys resources according to the target deployment plan.

[0121] In this embodiment of the invention, when the load deployment of a financial system needs to be flexibly adjusted to reduce performance loss, the system determines which business loads in the current deployment relationship cannot meet the operational requirements of in-transit transactions and which resource domains require resource deployment adjustments based on the resource domain occupancy of business loads in the financial system. It then retrieves first annotation information for pre-labeled resource domains and second annotation information for pre-labeled business loads from the resource pool's resource database. The system analyzes the category and performance attributes of resource domains, the resource requirement data of business loads, and their eviction attribute values ​​to generate a target deployment scheme containing resource deployment adjustment strategies. Subsequently, resource deployment is redeployed. This invention labels business loads based on their reentrancy and latency tolerance, thereby selecting appropriate resource domains and resource mixing modes to rationally deploy or evict business loads. This improves system performance, reliability, and maintainability, thus solving the technical problem in related technologies where traditional resource mixing deployment methods cannot match suitable resource domains for business loads, leading to the impact on in-transit transactions and system performance loss after business loads are evicted.

[0122] Optionally, the resource deployment device for the service load includes: a first acquisition module, used to acquire the load information of each service load from the metadata pool, wherein the load information includes at least: service requirement information, latency tolerance index, and reentrancy index; a calculation module, used to calculate the eviction attribute value of the service load based on the latency tolerance index, reentrancy index, and preset labeling rules; a parsing module, used to parse the service requirement information to obtain the resource requirement data of the service load; and a labeling module, used to generate second labeling information based on the eviction attribute value and resource requirement data, and use the second labeling information to label the service load.

[0123] Optionally, the resource deployment device for business loads further includes: a first creation module for creating a load type data table, wherein the load type data table stores the load type names of N business loads, and the load type data table includes at least the following fields: load type ID and load type name; a second acquisition module for acquiring a latency description table pre-stored in the financial system, wherein the latency description table includes at least the following fields: latency description ID, latency description name, and latency tolerance index; a third acquisition module for acquiring a reentrancy degree table pre-stored in the financial system, wherein the reentrancy degree table includes at least the following fields: reentrancy ID, reentrancy name, and reentrancy index; and a first generation module for generating a business load configuration table based on the load type data table, the latency description table, and the reentrancy degree table, wherein the business load configuration table records N load configuration information entries, each load configuration information entry corresponds to a business load, and the load configuration information is used to indicate the latency description ID, reentrancy ID, and second annotation information corresponding to the load type ID.

[0124] Optionally, the resource deployment device for the business workload further includes: a fourth acquisition module, used to acquire basic information of each resource domain, wherein the basic information includes at least: performance information and usage description; an analysis module, used to analyze the performance information and usage description to obtain analysis results, wherein the analysis results record at least the category attribute information and performance attribute information of the resource domain; and a second generation module, used to generate first annotation information based on the category attribute information and performance attribute information in the analysis results, and use the first annotation information to annotate the resource domain.

[0125] Optionally, the basic information also includes: resource domain name. The resource deployment device for the business load also includes: a second creation module for creating a resource domain configuration table, wherein the resource domain configuration table is used to record M resource domain configuration information, each resource domain configuration information corresponds to a resource domain, and the resource domain configuration information is used to indicate the first annotation information corresponding to the resource domain name of the resource domain; and a storage module for storing the resource domain configuration table in the resource database in the resource pool.

[0126] Optionally, the deployment unit includes: a first determining module, configured to, for each resource domain, determine all deployed service loads in that resource domain based on current deployment information, and determine the operational characteristics of each service load based on operational information, wherein the operational characteristics are used to indicate whether the system operational resources provided by the current resource domain can maintain the normal operation of the service load; a second determining module, configured to, based on the operational characteristics of the service loads and second labeling information, determine the target loads to be evicted from the deployed service loads in the resource domain; and a third generating module, configured to, based on the first labeling information of all resource domains and all target loads to be evicted, generate a target deployment scheme.

[0127] Optionally, the third generation module includes: a first determining submodule, used to determine the eviction time point and eviction tolerance duration for each target load based on the load configuration information corresponding to the target load recorded in the service load configuration table; a second determining submodule, used to determine the redeployment time point of the target load based on the eviction time point and the eviction tolerance duration; a calculation submodule, used to calculate the resource remaining status of each resource domain after the target load in the resource domain is to be evicted; a third determining submodule, used to determine the target resource domain to be deployed during the redeployment process of the target load based on the resource remaining status of all resource domains and the first annotation information; and a generation submodule, used to generate a target deployment plan based on the eviction time point, the target resource domain, and the redeployment time point.

[0128] The aforementioned resource deployment device for the workload may also include a processor and a memory. The first acquisition unit 41, the second acquisition unit 42, the third acquisition unit 43, the deployment unit 44, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0129] The aforementioned processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and by adjusting kernel parameters, a target deployment plan can be generated based on the current deployment information, runtime information, first annotation information, and second annotation information. Resources are then redeployed according to the target deployment plan.

[0130] The aforementioned memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0131] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program with the following method steps: obtaining current deployment information and operation information of N business loads in a financial system, wherein the current deployment information refers to the current deployment relationship between the business loads and M resource domains, and the operation information is used to describe the data on the occupancy of system operation resources by the business loads, and N and M are both positive integers; obtaining first labeling information of M resource domains from the resource database of the resource pool, wherein the first labeling information is used to describe the category attributes and performance attributes of the resource domains; obtaining second labeling information of N business loads, wherein the second labeling information is used to indicate the resource demand data and eviction attribute value of the business loads, and the eviction attribute refers to the degree of adaptability of the business loads to the reallocation of system operation resources; generating a target deployment scheme based on the current deployment information, operation information, first labeling information and second labeling information, and redeploying resources according to the target deployment scheme.

[0132] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to perform a resource deployment method for the service load of any one of the above embodiments.

[0133] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the resource deployment method for the service load of any one of the above embodiments.

[0134] Figure 5 This is a hardware structure block diagram of an electronic device (or mobile device) for a resource deployment method for workloads according to an embodiment of the present invention. Figure 5 As shown, an electronic device may include one or more ( Figure 5 The processor 502 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 504 for storing data may also be included. In addition, it may include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a keyboard, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 5 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, the electronic device may also include components that are more... Figure 5 The more or fewer components shown, or having the same Figure 5The different configurations shown.

[0135] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0136] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0137] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0138] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0139] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0140] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or 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 various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0141] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A resource deployment method for business workloads, characterized in that, include: Obtain the current deployment and operation information of N business loads in the financial system. The current deployment information refers to the current deployment relationship between the business load and M resource domains. The operation information is used to describe the data on the system operation resources occupied by the business load. N and M are both positive integers. Obtain first annotation information for M resource domains from the resource database of the resource pool, wherein the first annotation information is used to describe the category attributes and performance attributes of the resource domains; Obtain second labeling information for N of the service loads, wherein the second labeling information is used to indicate the resource requirement data and eviction attribute value of the service load, and the eviction attribute refers to the degree to which the service load is adaptable to reallocating system operating resources; A target deployment plan is generated based on the current deployment information, the operation information, the first annotation information, and the second annotation information, and resources are redeployed according to the target deployment plan.

2. The resource deployment method according to claim 1, characterized in that, The second labeling information of the service load is obtained through the following steps: For each of the service loads, the load information of the service load is obtained from the metadata pool, wherein the load information includes at least: service requirement information, latency tolerance index, and reentrancy index; The evictability attribute value of the service load is calculated based on the latency tolerance index, the reentrancy index, and the preset labeling rules; Parse the business requirement information to obtain the resource requirement data of the business load; The second labeling information is generated based on the evictable attribute value and the resource requirement data, and the second labeling information is used to label the service load.

3. The resource deployment method according to claim 2, characterized in that, After labeling the service load using the second labeling information, the method further includes: Create a load type data table, wherein the load type data table is used to store the load type names of N business loads, and the load type data table includes at least the following fields: load type ID and load type name; Obtain the pre-stored delay description table in the financial system, wherein the delay description table includes at least the following fields: delay description ID, delay description name, and the delay tolerance index; Obtain the reentrancy table pre-stored in the financial system, wherein the reentrancy table includes at least the following fields: reentrancy ID, reentrancy name, and the reentrancy index; A service load configuration table is generated based on the load type data table, the delay description table, and the reentrancy table. The service load configuration table records N load configuration information entries, each of which corresponds to a service load. The load configuration information is used to indicate the delay description ID, the reentrancy ID, and the second annotation information corresponding to the load type ID.

4. The resource deployment method according to claim 1, characterized in that, The first annotation information of the resource domain is obtained through the following steps: For each resource domain, obtain basic information about the resource domain, wherein the basic information includes at least: performance information and usage description; The analysis results are obtained by analyzing the performance information and usage description, wherein the analysis results record at least the category attribute information and performance attribute information of the resource domain; The first annotation information is generated based on the category attribute information and the performance attribute information in the analysis results, and the resource domain is annotated using the first annotation information.

5. The resource deployment method according to claim 4, characterized in that, The basic information also includes: the resource domain name, and after labeling the resource domain using the first labeling information, it also includes: Create a resource domain configuration table, wherein the resource domain configuration table is used to record M resource domain configuration information, each resource domain configuration information corresponds to one resource domain, and the resource domain configuration information is used to indicate the first annotation information corresponding to the resource domain name of the resource domain; The resource domain configuration table is stored in the resource database of the resource pool.

6. The resource deployment method according to claim 1, characterized in that, The steps of generating a target deployment plan based on the current deployment information, the operational information, the first annotation information, and the second annotation information include: For each resource domain, all the service loads deployed in the resource domain are determined based on the current deployment information, and the operating characteristics of each service load are determined based on the operating information, wherein the operating characteristics are used to indicate whether the system operating resources provided by the current resource domain can maintain the normal operation of the service load; Based on the operational characteristics of the service load and the second labeling information, the target load to be evicted is determined among the service loads already deployed in the resource domain; The target deployment scheme is generated based on the first labeling information of all the resource domains and all the target loads to be evicted.

7. The resource deployment method according to claim 6, characterized in that, The step of generating the target deployment scheme based on the first labeling information of all the resource domains and all the target loads to be evicted includes: For each target load, the eviction time and eviction tolerance duration are determined based on the load configuration information corresponding to the target load recorded in the service load configuration table. The redeployment time of the target load is determined based on the eviction time and the eviction tolerance duration; For each resource domain, after the target load is to be evicted from the resource domain, the remaining resources of the resource domain are calculated. Based on the remaining resource status of all resource domains and the first annotation information, the target resource domain to be deployed during the redeployment process is determined. The target deployment plan is generated based on the eviction time point, the target resource domain, and the redeployment time point.

8. A resource deployment device for business workloads, characterized in that, include: The first acquisition unit is used to acquire the current deployment information and operation information of N business loads in the financial system. The current deployment information refers to the current deployment relationship between the business load and M resource domains, and the operation information is used to describe the data of the business load's occupation of system operation resources. N and M are both positive integers. The second acquisition unit is used to acquire first annotation information of M resource domains from the resource database of the resource pool, wherein the first annotation information is used to describe the category attributes and performance attributes of the resource domains; The third acquisition unit is used to acquire second labeling information for N of the service loads, wherein the second labeling information is used to indicate the resource requirement data and eviction attribute value of the service load, and the eviction attribute refers to the degree of adaptability of the service load to the reallocation of system operating resources. The deployment unit is used to generate a target deployment plan based on the current deployment information, the operation information, the first annotation information and the second annotation information, and to redeploy resources according to the target deployment plan.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the resource deployment method for the workload as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the resource deployment method for the workload as described in any one of claims 1 to 7.

Images