Load management method, device, system, electronic equipment and storage medium
By acquiring load attribute information and management rules from the shared database system, different types of loads can be distinguished and managed, thus solving the system instability problem caused by mixed loads and achieving a better operating state.
Patent Information
- Application Number
- CN202211678851.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-12-26
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2042-12-26
AI Technical Summary
Managing mixed workloads in a shared database system is difficult to achieve stable operation, leading to system overload or underload and affecting system stability.
By acquiring the attribute information of the target load and the preset load management rules, different types of loads are distinguished and matched with corresponding management methods. The load manager is used for systematic management, including attribute matching conditions and load management methods, and lifecycle is divided for control.
It enables the categorized management of different types of loads, improving the operational stability and efficiency of the database system and avoiding fluctuations in system status.
Smart Images

Figure CN115905185B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a load management method, device, system, electronic device and storage medium. Background Art
[0002] With the further development of the data era, users are increasingly inclined to integrate various database systems into a unified database system, that is, a shared database system. On the one hand, a shared database system is easy to maintain and use, and can provide convenient multi-source big data analysis. On the other hand, a shared database system often means less cost than multiple database systems. There are often many different types of workloads running in a shared database, that is, mixed loads. Mixed loads are a huge challenge to the stable operation of database systems. If mixed loads are not managed in an integrated manner without distinction, it will often lead to system overload or underload, or even fluctuations between the two states, which will have a great impact on the stability of the system. Summary of the invention
[0003] Embodiments of the present application provide a load management method, device, system, electronic device, and storage medium to improve the stability of a database system.
[0004] In a first aspect, an embodiment of the present application provides a load management method, comprising: obtaining attribute information of a target load and preset load management rules, wherein the load management rules include attribute matching conditions and load management methods; determining a target load management rule from the preset load management rules, wherein the attribute information of the target load satisfies the attribute matching conditions in the target load management rules; and executing the load management method in the target load management rules for the target load.
[0005] In the second aspect, an embodiment of the present application provides a load management device, including: an attribute information and load management rule acquisition module, used to obtain the attribute information of the target load and the preset load management rules, wherein the load management rules include attribute matching conditions and load management methods; a target load management rule determination module, used to determine the target load management rules from the preset load management rules, wherein the attribute information of the target load satisfies the attribute matching conditions in the target load management rules; a load management method execution module, used to execute the load management method in the target load management rules for the target load.
[0006] In a third aspect, an embodiment of the present application provides a database system, characterized in that it includes a front-end node and a computing node; the computing node is used to execute the target load; and the front-end node is used to implement the load management method provided in any embodiment of the present application.
[0007] In a fourth aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory, and the processor implements the method provided in any embodiment of the present application when executing the computer program.
[0008] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method provided in any embodiment of the present application is implemented.
[0009] Compared with the prior art, this application has the following advantages:
[0010] According to the technical solution provided by the embodiment of the present application, different types of loads are distinguished by using the attribute information of the load, and the load management rules are preset. For loads matching the same load management rule, they belong to the same category and can adopt the same load management method. Therefore, different types of loads can be matched with different load management methods for control and management, so as to control and manage the mixed loads in different categories, so as to achieve the purpose of making the system run better. Furthermore, the load, the attribute information of the load, and the load management method can all correspond to a life cycle, triggering the matching of the load management rules and the execution of the corresponding load management method in a specific life cycle, and then by dividing the life cycle, different categories of loads can be managed and controlled in different life cycles, so that the operation of the database system is more stable. In addition, the attribute information can include both the attribute information generated for creating the load (such as query) itself and the historical indicator information and current indicator information of the category to which the load belongs, so that the attribute information of the load can be collected in a multi-dimensional and comprehensive manner.
[0011] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present application will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in the present application and should not be regarded as limiting the scope of the present application.
[0013] Figure 1 A flow chart of a load management method provided in an embodiment of the present application.
[0014] Figure 2 A schematic diagram of life cycle division provided in an embodiment of the present application.
[0015] Figure 3 This is an example diagram of an application of the database system provided in an embodiment of the present application.
[0016] Figure 4 A schematic diagram of a load management device provided in an embodiment of the present application.
[0017] Figure 5 A block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0018] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.
[0019] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following related technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application.
[0020] The following terms are used in this article.
[0021] Workload: Workload refers to a class of queries or writes with similar or identical characteristics in the database that can be treated as the same set by the workload manager. Taking query as an example, the characteristics that can be used to distinguish queries into different workloads include attribute information such as the query request source, business priority, or performance target.
[0022] Workload Manager (WLM): One of the core components of a database. The load manager can monitor and control the database load using a variety of load management methods, so as to meet the query or write performance indicators as much as possible and make full use of system resources.
[0023] Template: A SQL template is formed by parameterizing and standardizing the query's Structured Query Language (SQL), which can be used to represent a class of queries. In a database, queries with the same pattern usually have the same or similar operating characteristics. SQL pattern has pattern aggregation and pattern macro-statistics functions. Based on the pattern aggregation function, similar queries can be classified according to the query's SQL text; based on pattern macro-statistics, comparisons of the mean and maximum values of indicators for various types of queries can be established.
[0024] Metric: Statistical information collected during the operation of the database system. Statistical information can be cluster-level statistical information, such as the CPU usage rate, etc.; or query-level statistical information. Among them, query-level statistical information can be historical statistical information of queries, such as the median execution time of queries with the same pattern in history; or it can be information collected in real time during query execution, such as the memory usage of the current query.
[0025] There are often many different types of workloads running in the database, that is, mixed workloads. These workloads include both online transaction processing (OLTP) type workloads and online analytical processing (OLAP) type workloads. Among them, the characteristics of OLTP type workloads are low resource overhead and short execution time, but high requirements for system response time (RT). The characteristics of OLAP type workloads are high resource consumption and long running time. In other words, users often have different performance requirements for different types of workloads. Inside the database, the workloads running at the same time often share the CPU, memory, disk input and output (IO) and other resources of the database system. For example, some OLAP type queries, such as business intelligence (BI) queries, often consume huge system resources. If the operation of this type of workload is not restricted, other concurrently running workloads in the database system will have to wait for it to release resources before they can be executed, thus affecting the overall performance of the database system.
[0026] The embodiment of the present application aims to provide a load management method, which uses the attribute information of the load to distinguish different types of loads, so as to match different load management methods to control and manage different types of loads, so as to achieve the purpose of making the system run better. Furthermore, the embodiment of the present application also provides a load manager that can execute the load management method of this embodiment to provide a unified load management component for the database system, systematically manage and control the load in the database, and achieve the purpose of making the database system run more stably in all aspects.
[0027] The load management method and load manager provided in the embodiments of the present application can be applied to a load management device. The load management device can be deployed on a physical server including an independent host, or on a virtual server (such as a cloud server) hosted by a host cluster.
[0028] Figure 1This is a flow chart of the load management method provided in the embodiment of the present application. Figure 1 As shown, the method includes steps S101 to S103.
[0029] Step S101: Acquire attribute information of a target load and preset load management rules, wherein the load management rules include attribute matching conditions and load management methods.
[0030] The target load can be any load running in the database system, which can be a query load or a write load. Queries with the same or similar attribute information can be regarded as the same type of query load, and writes with the same or similar attribute information can be regarded as the same type of write load.
[0031] The attribute information may be the attribute information itself that is queried or written, or the indicator information during runtime that is queried or written, or the historical indicator information that is queried or written. The embodiments of the present application do not limit this. As long as the information can distinguish different types of loads, it can be used as attribute information.
[0032] Exemplarily, OLAP-type loads and OLTP-type loads are different types of loads; point queries and join queries belong to different types of loads; ad-hoc mode processing and data extraction-transformation-load (ETL) mode processing belong to different types of loads; loads based on different statement types (such as select statements that return query results and insert statements that insert data) belong to different types of loads.
[0033] The load management rules can be understood as the rules for load management, that is, the load is managed and controlled in a rule-based manner. The load management rules can be set by the user or administrator based on the backend operation and maintenance end. The load management rules can be user-defined or system-built-in. It is understood that the loads matching the same load management rule belong to the same type of load.
[0034] The attribute matching condition (predicate) can be used to judge the matching of the attribute information of the target load. The loads that meet the attribute matching condition can be treated as the same type of load. The same load management rule can include one or more attribute matching conditions. Exemplarily, the loads that meet all the attribute matching conditions can be treated as the same type of load.
[0035] Load management methods (actions) are control measures that can be executed on target loads. For example: admission control, such as limiting the concurrency of a certain type of load; determining the scheduling order of queries; tuning execution parameters, such as selecting corresponding execution parameters according to the characteristics of different types of loads; resource management, such as resource evaluation, isolation, scheduling and resource restrictions between different loads; execution control, such as adjusting priority, termination, speed limit, etc.; forecasting, such as predicting subsequent loads and providing auto driving capabilities for them, including but not limited to auto indexing, auto dist key, auto sort key, etc. Among them, the same load management rule can include one or more load management methods.
[0036] It should be noted that the load management rules can be set according to the application scenario and actual needs, and the embodiments of the present application are not limited to this.
[0037] In addition, the embodiments of the present application do not limit the order of obtaining attribute information and load management rules. The attribute information can be obtained first and then the load management rules, or the load management rules can be obtained first and then the attribute information. Alternatively, the acquisition of attribute information and load management rules can be processed in parallel.
[0038] Step S102: determining a target load management rule from preset load management rules, wherein the attribute information of the target load satisfies the attribute matching condition in the target load management rule.
[0039] Exemplarily, there may be multiple preset load management rules. When the attribute information of the target load meets the attribute matching condition of one of the load management rules, the load management rule is the target load management rule, that is, the target load can be managed using the load management rule.
[0040] In one example, each preset load management rule can be traversed to match the target load management rule. In another example, based on the attribute information of the target load, a portion of the load management rules can be selected from all the preset load management rules as candidates for matching. For example, some load management rules can only be used when the query is just submitted, some load management rules can only be used when the query is executed, and some load management rules can only be used for queries within a certain resource group (usually all queries will belong to a specific resource group), then these load management rules can be used as candidates to match the target load without traversing each preset load management rule.
[0041] Step S103: executing the load management method in the target load management rule for the target load.
[0042] That is to say, the load management method (action) in the target load management rule is the means of controlling the target load, thereby achieving the purpose of controlling and managing different types of loads with different load management methods to achieve a better system operation state.
[0043] For example, the load management rule can be presented in the following form: If Predicate1 and Predicate2and..., then Action1 Action2... Wherein, Predicate1, Predicate2... represent load matching conditions, and Action1 Action2... represent load management methods. When the target load meets each attribute matching condition Predicate1, Predicate2..., the corresponding load management method Action1 Action2... is executed.
[0044] In one embodiment, the attribute matching condition (predicate) includes attribute information (property) to be matched, an attribute information operator (operator) and an attribute information operation value (value). In step S102, a target load management rule is determined from preset load management rules, including: taking any preset load management rule as a candidate load management rule, using the attribute information in the attribute matching condition of the candidate load management rule to match the corresponding target attribute information from the attribute information of the target load; based on the attribute information operator in the attribute matching condition of the candidate load management rule, operating the target attribute information to obtain the target attribute information operation value; when the target attribute information operation value is consistent with the attribute information operation value in the attribute matching condition of the candidate load management rule, determining the candidate load management rule as the target load management rule.
[0045] For example: in the attribute matching condition of the load management rule to be selected, the attribute information (property) is "${session.user}", that is, the user name attribute information needs to be matched, the attribute information operator (operator) is "equal", and the attribute information operation value (value) is "ABC". When the user name attribute information of the target load is ABC, the attribute information of the target load satisfies the attribute matching condition in the load management rule to be selected.
[0046] Exemplarily, the property information, the property information operator and the property information operation value constitute a complete property matching condition (predicate), wherein the property information is the most important information used to distinguish the load type.
[0047] Taking the target load as a query as an example, the attribute information is the query attribute information, that is, the attribute information of the target load is the attribute information of the target query corresponding to the target load. In one embodiment, the attribute information includes first attribute information, second attribute information and third attribute information, wherein the first attribute information is information generated to create the target query, the second attribute information is historical indicator information of each query under the query category to which the target query belongs, and the third attribute information is current indicator information of the target query.
[0048] Exemplarily, the first attribute information may include the query's own attributes generated when it is created, such as the user name (user) of the query sent, the address (IP) from which the query is sent, etc. The second attribute information may include historical statistical information of the pattern where the query SQL is located, for example, PATTERN_RT_P50 represents the median of the total execution time of the pattern where the query is located in history. Usually, this data can roughly determine the size of the query's consumed resources before the query is executed. The third attribute information can provide attribute information of real-time indicators for queries that have no historical data or inaccurate historical data, so that the query can be controlled after the query enters the database. The following table shows an example of the attribute information of a query.
[0049]
[0050]
[0051]
[0052] For example, a load has a life cycle. Taking a query as an example, the entire process from receiving a query to executing it in the database can be divided into six life cycles. These six life cycles include: before queuing (BEFORE_QUEUEING), during queuing (QUEUEING), before generating an execution plan (BEFORE_PLANNING), before distributing a plan (BEFORE_DISTRIBUTE_PLANNING), before scheduling (BEFORE_SCHEDULING), and during execution (RUNNING). Figure 2 As shown in the figure, BEFORE_QUEUEING and QUEUEING are used to submit queue nodes, QUEUEING and BEFORE_PLANNING are used to start execution nodes, BEFORE_PLANNING and BEFORE_DISTRIBUTE_PLANNING are used to generate execution plan nodes, BEFORE_DISTRIBUTE_PLANNING and BEFORE_SCHEDULING are used to generate task nodes, and BEFORE_SCHEDULING and RUNNING are used to start issuing task nodes.
[0053] Since the attribute information of the load can only be collected at different times, the attribute information has a corresponding life cycle, that is, the attribute information will only take effect within the corresponding life cycle. Please refer to the example in the above table.
[0054] In one embodiment, the method of the embodiment of the present application also includes: determining a first life cycle, wherein the first life cycle is the life cycle corresponding to the attribute information of the target load; when the first life cycle is consistent with the current life cycle of the target load, executing step S102 to determine the target load management rule from the preset load management rules.
[0055] In other words, the attribute information of the target load will only take effect within the corresponding life cycle, that is, the matching of the target load management rules is triggered in a specific life cycle.
[0056] In one embodiment, the method of the embodiment of the present application also includes: determining a first life cycle, wherein the first life cycle is a life cycle corresponding to the attribute information of the target load; when the first life cycle is a preset life cycle, executing step S102 according to a preset time period to determine the target load management rule from the preset load management rules.
[0057] The preset life cycle may be running (Running) or queuing (Queueing), thereby periodically triggering the matching of the target load management rule for the load in the Running or Queueing life cycle.
[0058] In one embodiment, the method of the embodiment of the present application also includes: determining a second life cycle, wherein the second life cycle is the life cycle corresponding to the load management method in the target load management rule; when the second life cycle is consistent with the current life cycle of the target load, executing the load management method in the target load management rule for the target load.
[0059] Load management methods (actions) can only take effect at a specific time, so load management methods also have a corresponding life cycle. The following table shows some load management methods and their corresponding life cycles.
[0060]
[0061] For example, the life cycle during which the load management rule takes effect is the intersection of all property and action life cycles.
[0062] According to the method of the embodiment of the present application, after the target load matches the corresponding target load management rule, the load management method corresponding to the target load management rule will be executed, so that the load management rule can be used to control and manage the same type of load, making the operating environment of the database system better. Furthermore, by dividing the life cycle, different types of loads can be managed and controlled in different life cycles, making the operation of the database system more stable.
[0063] An embodiment of the present application provides a database system, including a front-end node (RC) and a computing node, wherein the computing node is used to execute a target load; and the front-end node is used to implement a load management method of any embodiment of the present application.
[0064] Figure 3 This is an architecture diagram of the database system provided in the embodiment of the present application. It should be noted that the database system is only an exemplary application architecture of the above-mentioned load management method, and is not a limitation on the database system architecture. Figure 3 As shown, the front-end node implements the load management method of any embodiment of the present application based on the load manager.
[0065] The load manager includes a metric collection module (Metric Service) for obtaining the attribute information of the target load. In the database system, the metric collection module can be used as an offline monitoring data component. Even if the system is offline, users can view the basic resource monitoring data through the metric collection module. For example, the second attribute information (historical metric information of the load) is cleaned and analyzed by an external big data computing engine, and then imported into the memory of the metric collection module offline in a T+1 manner.
[0066] The indicator collection module is also used to periodically collect all system-level indicator information, including third attribute information (current indicator information of the load) and first attribute information (the load attribute information generated by creating the load). For example, query-level and cluster-level statistics are obtained from computing nodes (Workers) and processes (Executors).
[0067] Exemplarily, the indicator collection module is used to collect query-level indicator information from query statistical information resources (Query Metric Source), including: query history statistical information (QueryHistory Metric Source) obtained based on a template (pattern) and running query statistical information (Running Query Metric Source) obtained based on relevant statistics of running queries. The indicator collection module is also used to collect cluster-level indicator information from cluster statistical information resources (ClusterMetric Source), including: cluster history statistical information (Cluster History Metric Source) obtained based on instance-level historical statistics and node statistical information (Node Info Metric Source) obtained based on node status management and indicator processing.
[0068] The load manager also includes a rule service module (Rule Service) for obtaining preset load management rules and determining target load management rules from the preset load management rules, so as to perform rule management and efficient matching. Exemplarily, a user (or administrator) can set corresponding load management rules through the console (console) to perform rule management (REST). The load management rules will be stored in the rule service module on the front-end node and will be persisted in the metadata library of the database.
[0069] The load manager also includes an execution module, which is used to execute the load management method in the target load management rule for the target load. Exemplarily, the execution module may include an action event component (Action Event Factory) and an event handler (Event Handler).
[0070] The load manager main module at the top level of the load manager can match rules in the load-specific life cycle trigger rule service module, for example: determine the first life cycle, and when the first life cycle is consistent with the current life cycle of the target load, execute the target load management rules determined from the preset load management rules.
[0071] When the first life cycle is the preset life cycle, the load manager main module will also execute the target load management rules from the preset load management rules according to the preset time period, such as periodically matching the rules for queries that are running (Running) and queueing (Queueing), so as to achieve the purpose of controlling the executing queries.
[0072] After the target query matches the target load management rule, the execution module will be triggered to execute the load management method (Action) corresponding to the target load management rule, so as to manage and control a type of load corresponding to the target load management rule, making the system's operating environment better.
[0073] For example, Figure 3 As shown, the front-end nodes include the leader RC and the follower RC, which are connected in communication. The leader RC can obtain attribute information from the follower RC, such as cluster-level statistics, and send commands such as configuration modification to the follower RC. The leader RC can manage query-level and cluster-level loads, while the follower RC only manages query-level loads.
[0074] Corresponding to the method provided in the embodiment of the present application, the embodiment of the present application provides a load management device. Figure 4 As shown, the load management device may include: an attribute information and load management rule acquisition module 401, used to obtain the attribute information of the target load and the preset load management rules, wherein the load management rules include attribute matching conditions and load management methods; a target load management rule determination module 402, used to determine the target load management rules from the preset load management rules, wherein the attribute information of the target load satisfies the attribute matching conditions in the target load management rules; a load management method execution module 403, used to execute the load management method in the target load management rules for the target load.
[0075] In one embodiment, the load management device may include a life cycle determination module, which is used to determine a first life cycle, wherein the first life cycle is the life cycle corresponding to the attribute information of the target load; the target load management rule determination module 402 is used to execute the target load management rule determined from the preset load management rules when the first life cycle is consistent with the current life cycle of the target load.
[0076] In one embodiment, the target load management rule determination module 402 is used to determine the target load management rule from the preset load management rules according to a preset time period when the first life cycle is a preset life cycle.
[0077] In one embodiment, the life cycle determination module is also used to determine a second life cycle, wherein the second life cycle is the life cycle corresponding to the load management method in the target load management rule; the load management method execution module 403 is used to execute the load management method in the target load management rule for the target load when the second life cycle is consistent with the current life cycle of the target load.
[0078] In one implementation, the attribute information of the target load is the attribute information of the target query corresponding to the target load.
[0079] In one embodiment, the attribute information includes first attribute information, second attribute information and third attribute information, wherein the first attribute information is information generated to create a target query, the second attribute information is historical indicator information of each query under the query category to which the target query belongs, and the third attribute information is current indicator information of the target query.
[0080] In one embodiment, the attribute matching condition includes attribute information, attribute information operator and attribute information operation value, and the target load management rule determination module 402 is specifically used to: take any preset load management rule as the load management rule to be selected, and use the attribute information in the attribute matching condition of the load management rule to match the corresponding target attribute information from the attribute information of the target load; based on the attribute information operator in the attribute matching condition of the load management rule to be selected, operate the target attribute information to obtain the target attribute information operation value; when the target attribute information operation value is consistent with the attribute information operation value in the attribute matching condition of the load management rule to be selected, determine the load management rule to be selected as the target load management rule.
[0081] The functions of each module in each device in the embodiments of the present application can be found in the corresponding description in the above method, and have corresponding beneficial effects, which will not be repeated here.
[0082] Figure 5 FIG. 1 is a block diagram of an electronic device used to implement an embodiment of the present application. Figure 5 As shown, the electronic device includes: a memory 501 and a processor 502. The memory 501 stores a computer program that can be run on the processor 502. When the processor 502 executes the computer program, the method in the above embodiment is implemented. The number of the memory 501 and the processor 502 can be one or more.
[0083] The electronic device also includes:
[0084] The communication interface 503 is used to communicate with external devices and perform data exchange transmission.
[0085] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the memory 501, the processor 502 and the communication interface 503 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0086] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.
[0087] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present application when the program is executed by a processor.
[0088] An embodiment of the present application also provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present application.
[0089] An embodiment of the present application also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided in the embodiment of the application.
[0090] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the Advanced RISC Machines (ARM) architecture.
[0091] Optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example: Static RAM (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Sync Link DRAM (SLDRAM) and Direct Rambus RAM (DRRAM).
[0092] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
[0093] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.
[0094] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features.
[0095] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.
[0096] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or used in combination with these instruction execution systems, devices or apparatuses.
[0097] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.
[0098] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.
[0099] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A load management method, comprising: Acquire attribute information of the target load and preset load management rules, wherein the load management rules include attribute matching conditions and load management methods; Determining a target load management rule from the preset load management rules, wherein the attribute information of the target load satisfies an attribute matching condition in the target load management rule; For the target load, executing the load management method in the target load management rule; Wherein, the method further comprises: Determine a first life cycle, wherein the first life cycle is a life cycle corresponding to the attribute information of the target load; In a case where the first life cycle is consistent with the current life cycle of the target load, a target load management rule is determined from the preset load management rules.
2. The method according to claim 1, further comprising: Determine a second life cycle, wherein the second life cycle is a life cycle corresponding to the load management method in the target load management rule; When the second life cycle is consistent with the current life cycle of the target load, the load management method in the target load management rule is executed for the target load.
3. The method according to claim 1, wherein: The attribute information of the target load is the attribute information of the target query corresponding to the target load.
4. The method according to claim 3, wherein: The attribute information includes first attribute information, second attribute information and third attribute information, wherein the first attribute information is information generated to create the target query, the second attribute information is historical indicator information of each query under the query category to which the target query belongs, and the third attribute information is current indicator information of the target query.
5. The method according to claim 1, wherein: The attribute matching condition includes attribute information, attribute information operator and attribute information operation value, and determining a target load management rule from the preset load management rules includes: Taking any preset load management rule as a candidate load management rule, and matching corresponding target attribute information from the attribute information of the target load using the attribute information in the attribute matching condition of the candidate load management rule; Based on the attribute information operator in the attribute matching condition of the load management rule to be selected, operate the target attribute information to obtain a target attribute information operation value; When the target attribute information operation value is consistent with the attribute information operation value in the attribute matching condition of the load management rule to be selected, the load management rule to be selected is determined as the target load management rule.
6. A load management device, comprising: An attribute information and load management rule acquisition module, used to acquire the attribute information of the target load and preset load management rules, wherein the load management rules include attribute matching conditions and load management methods; A target load management rule determination module, used to determine a target load management rule from the preset load management rules, wherein the attribute information of the target load satisfies the attribute matching condition in the target load management rule; A load management mode execution module, used for executing the load management mode in the target load management rule for the target load; Wherein, the device further comprises: A first life cycle determination module, used to determine a first life cycle, wherein the first life cycle is a life cycle corresponding to the attribute information of the target load; The target load management rule execution module is used to execute the target load management rule determined from the preset load management rules when the first life cycle is consistent with the current life cycle of the target load.
7. A database system, characterized in that: It comprises a front-end node and a computing node; the computing node is used to execute the target load; the front-end node is used to implement the method described in any one of claims 1-5.
8. An electronic device comprising a memory, a processor and a computer program stored in the memory, wherein the processor implements the method according to any one of claims 1 to 5 when executing the computer program.
9. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.
