A resource information management system for performance evaluation

Abstract

The present invention provides a performance evaluation resource information management system, which belongs to the field of resource management technology, and includes: an attribute determination module: obtaining resource information of performance evaluation resources, classifying all performance evaluation resources, and determining the basic attributes of each type of performance evaluation resources; an attribute matching module: extending the basic attributes of each type of performance evaluation resources, and performing matching analysis with preset resource nodes; an agent deployment module: binding the extended performance evaluation resource attributes with the binding attributes of the preset resource nodes based on the matching analysis results, and then deploying the node monitoring agent program of each preset resource node; an performance acquisition module: monitoring the data of each preset resource node based on the node monitoring agent program, and determining the overall performance; a strategy construction module: analyzing the resource information of all performance evaluation resources and determining the performance baseline, and then constructing the performance evaluation resource configuration strategy. The information management and optimal configuration of the performance evaluation resources are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of resource management, and in particular to a performance evaluation resource information management system. Background Art

[0002] With the development of information technology, enterprises and organizations have an increasing demand for efficient resource management. In particular, in complex computing environments, dynamic monitoring and optimal configuration of various resources are particularly important. Traditional performance evaluation resource management methods usually rely on manual configuration and static monitoring, lack intelligent resource classification and attribute extension methods, cannot adapt to changing business needs, and easily lead to resource waste or underutilization.

[0003] In the existing technology, most of the performance evaluation resource management systems only have basic monitoring functions, and lack dynamic expansion and intelligent matching of resource attributes. For example, the existing system cannot flexibly expand attributes and deploy node agents according to real-time resource usage, resulting in insufficient accuracy of performance evaluation and rationality of resource allocation, and cannot effectively improve the overall performance of the system.

[0004] Therefore, the present invention provides a performance evaluation resource information management system. Summary of the invention

[0005] The present invention provides a performance evaluation resource information management system, which is used to accurately match resource nodes and deploy monitoring agents through automatic classification and attribute expansion, obtain node performance in real time, and build optimization strategies based on analysis results to achieve dynamic adjustment of performance baselines and intelligent management of resource allocation, thereby greatly improving the overall performance and resource utilization of the system. The information management and optimal configuration of performance evaluation resources are systematically realized.

[0006] The present invention provides a performance evaluation resource information management system, comprising:

[0007] Attribute determination module: obtains resource information of all performance evaluation resources, classifies all performance evaluation resources based on a preset algorithm, and then determines the basic attributes of each type of performance evaluation resource;

[0008] Attribute matching module: Based on the preset extension method, the basic attributes of each type of performance evaluation resource are extended, and the extended performance evaluation resource attributes are matched and analyzed with the preset resource nodes;

[0009] Agent deployment module: based on the matching analysis results, the expanded performance evaluation resource attributes are bound to the node basic attributes of the corresponding matching preset resource nodes, and then the node monitoring agent program of each preset resource node is deployed;

[0010] Performance acquisition module: based on the node monitoring agent program of each preset resource node, monitors the data of each preset resource node, and then determines the overall performance of all preset resource nodes;

[0011] Strategy building module: Analyze the resource information of all performance evaluation resources and determine the performance baseline, and then build a performance evaluation resource allocation strategy based on the overall performance.

[0012] The present invention provides a performance evaluation resource information management system, an attribute determination module, comprising:

[0013] Threshold determination unit: determines the corresponding expansion requirements based on the basic attributes of each type of performance evaluation resource, and then determines the corresponding attribute expansion threshold:

[0014] ;in, is the attribute extension threshold corresponding to the basic attribute of the i-th type of performance evaluation resource, is the basic attribute value of the i-th type of performance evaluation resource, k is the total order of the expansion demand of the i-th type of performance evaluation resource, is the preset weight coefficient for controlling the nth order expansion coefficient of the i-th type of performance evaluation resource, is the nth order expansion coefficient of the i-th type of performance evaluation resource, is the preset expansion upper limit of the i-th type of performance evaluation resources;

[0015] Basic mapping unit: mapping based on the basic attributes of each type of performance evaluation resource and the preset attribute extension library, and then determining the extended attribute set corresponding to the basic attributes of each type of performance evaluation resource;

[0016] Level determination unit: monitors the resource usage of all performance evaluation resources, and determines the extended level corresponding to the basic attribute of each type of performance evaluation resource based on the resource usage of all performance evaluation resources and the attribute extension threshold corresponding to the basic attribute of each type of performance evaluation resource;

[0017] Attribute extension unit: performs attribute extension based on the extension level corresponding to the basic attribute of each type of performance evaluation resource and the extension attribute set corresponding to each type of performance evaluation resource in combination with a preset extension method.

[0018] The present invention provides a performance evaluation resource information management system, and the preset expansion method includes: physical expansion, logical expansion and mixed expansion.

[0019] The present invention provides a performance evaluation resource information management system, a level determination unit, comprising:

[0020] Coefficient determination subunit: monitors the resource usage of all performance evaluation resources, and determines the resource usage coefficient based on the resource usage of all performance evaluation resources:

[0021] ;in, is the resource utilization coefficient, is the resource usage of the i-th performance evaluation resource, is the total amount of resources for the i-th type of performance evaluation, is the preset additional evaluation factor for the i-th type of resources, is the preset dependency strength of the i-th type of performance evaluation resource with other performance evaluation resources, is the preset time adjustment factor of the i-th resource, m is the total number of performance evaluation resources, is the preset period adjustment factor, is a trigonometric function;

[0022] Level determination subunit: determines the extended level corresponding to the basic attribute of each type of performance evaluation resource based on the resource usage coefficient and the attribute extension threshold corresponding to the basic attribute of each type of performance evaluation resource.

[0023] The present invention provides a performance evaluation resource information management system, an agent deployment module, comprising:

[0024] Attribute acquisition unit: obtains node type information of each preset resource node, analyzes each type of node type information, and determines the node basic attributes corresponding to each type of node;

[0025] Attribute generation unit: merges the basic attributes of each preset resource node with the corresponding extended performance evaluation resource attributes, and generates comprehensive attributes;

[0026] Demand acquisition unit: generates attribute configuration information of each preset resource node based on the comprehensive attributes of each preset resource node, analyzes the attribute configuration information of each preset resource node, and further determines the monitoring requirements of each preset resource node;

[0027] Node deployment unit: determines the corresponding monitoring agent program based on the monitoring requirements of each preset resource node, and deploys the monitoring agent program to the preset resource node based on the preset deployment tool.

[0028] The invention provides a performance evaluation resource information management system and a monitoring agent program, including: a performance monitoring agent, a network monitoring agent and a security monitoring agent.

[0029] The present invention provides a performance evaluation resource information management system, a performance acquisition module, comprising:

[0030] Performance determination unit: Based on the monitoring agent program of each preset resource node, the monitoring agent obtains various indicator data of the preset resource node, and then determines the performance of each preset resource node:

[0031] Performance synthesis unit: Determines the total performance value of each type of resource based on the performance value of each preset resource node:

[0032] ;in, is the total efficiency value of the i-th type of resources, is the total number of nodes under the i-th type of resources, is the weight of the vth node under the i-th resource at time t, is the coefficient used to adjust the exponential decay factor in the overall performance value. is the value of the jth performance indicator in the vth node under the i-th resource type, is the weight of the vth node under the i-th resource related to the j-th performance indicator, is the total number of performance indicators under the i-th resource category, is the performance of the vth node under the i-th resource.

[0033] The present invention provides a performance evaluation resource information management system, a strategy building module, including:

[0034] Baseline determination unit: Analyze all performance evaluation resource information and determine the performance baseline based on the analysis results:

[0035] ;in, is the performance baseline, m is the total number of performance evaluation resources, is the dynamic weight of the i-th resource at time t, is the average value of the historical performance data of the i-th resource at the end time t, is the standard deviation of the historical performance data of the i-th resource at the end time t, is the adjustment coefficient of the i-th resource at time t, is a constant coefficient used to adjust resource efficiency fluctuations. is the performance fluctuation range difference of the i-th resource, is the time-dependent adjustment parameter, is the preset time reference point, where is the interaction coefficient between the i-th resource and the r-th resource:

[0036] ;in, is the interaction effect coefficient between the i-th resource and the r-th resource, is the interaction efficiency contribution between the i-th resource and the j-th resource at time t;

[0037] Performance comparison unit: compares the total performance of each type of resource with the performance baseline, and determines the priority of each type of resource based on the comparison results;

[0038] Policy determination unit: determines the resource allocation policy based on the priority of each type of resource.

[0039] The present invention provides a performance evaluation resource information management system, which can accurately match resource nodes and deploy monitoring agents through automatic classification and attribute expansion, obtain node performance in real time, and build optimization strategies based on analysis results to achieve dynamic adjustment of performance baselines and intelligent management of resource allocation, greatly improving the overall performance and resource utilization of the system. It can systematically achieve information management and optimal configuration of performance evaluation resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a structural diagram of a performance evaluation resource information management system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Example 1

[0044] like Figure 1 As shown, an embodiment of the present invention provides a performance evaluation resource information management system, including:

[0045] Attribute determination module: obtains resource information of all performance evaluation resources, classifies all performance evaluation resources based on a preset algorithm, and then determines the basic attributes of each type of performance evaluation resource;

[0046] Attribute matching module: Based on the preset extension method, the basic attributes of each type of performance evaluation resource are extended, and the extended performance evaluation resource attributes are matched and analyzed with the preset resource nodes;

[0047] Agent deployment module: based on the matching analysis results, the expanded performance evaluation resource attributes are bound to the node basic attributes of the corresponding matching preset resource nodes, and then the node monitoring agent program of each preset resource node is deployed;

[0048] Performance acquisition module: based on the node monitoring agent program of each preset resource node, monitors the data of each preset resource node, and then determines the overall performance of all preset resource nodes;

[0049] Strategy building module: Analyze the resource information of all performance evaluation resources and determine the performance baseline, and then build a performance evaluation resource allocation strategy based on the overall performance.

[0050] In this embodiment, the basic attributes of each type of performance evaluation resource refer to the basic characteristics or attributes of each type of resources determined after classifying all performance evaluation resources in the system, including the type, function, capacity, performance indicators, etc. of the resource, which are used to identify and distinguish different categories of performance evaluation resources.

[0051] In this embodiment, the performance evaluation resource attributes refer to various attribute information of the performance evaluation resource itself, including but not limited to basic attributes, which can reflect the actual use of the resource in the performance evaluation, such as response time, throughput, utilization rate, etc.

[0052] In this embodiment, the extended performance evaluation resource attribute is a new attribute obtained by extending the performance evaluation resource attribute based on the basic attribute through a preset extension method, including more specific parameters or characteristics, further describing the performance characteristics of the resource, so as to more accurately match the preset resource node. For example, for a server's memory resource, its basic attribute is capacity 32GB, type DDR4. In the extended attributes, timing parameters (CL16), dual-channel configuration, and voltage (1.35V) may be added;

[0053] In this embodiment, the node attributes of each preset resource node refer to the inherent characteristics or attributes of each preset resource node in the system, including the node's location, processing power, network bandwidth, storage capacity, operating system, etc., reflecting the physical or logical characteristics of the node.

[0054] In this embodiment, the overall efficiency of the preset resource nodes is based on the real-time data of each preset resource node obtained by the node monitoring agent. The system performs a comprehensive calculation on the efficiency of all preset resource nodes, and the obtained overall efficiency value can be used to judge the overall performance of the system resources.

[0055] In this embodiment, resource information of performance evaluation resources: a collection of detailed information of all performance evaluation resources in the system, including resource type, attribute, current status, historical data, etc. This information is the basic data of performance evaluation and is used to support the system's analysis and evaluation of resource performance;

[0056] In this embodiment, the performance evaluation resource allocation strategy is constructed in combination with the overall performance by analyzing the resource information of all performance evaluation resources in the system. In combination with the overall performance of all preset resource nodes, the system is able to construct a set of optimized resource allocation strategies, with the aim of allocating and using resources most efficiently in different performance evaluation tasks to achieve the best performance. For example, if system monitoring shows that the CPU load is evenly distributed but the memory usage of some nodes is too high, the configuration strategy may recommend transferring some high-memory usage tasks to nodes with lower memory usage, or increasing memory capacity to balance the load.

[0057] The beneficial effects of the above technical solution are: through automatic classification and attribute expansion, accurate matching of resource nodes and deployment of monitoring agents, real-time acquisition of node performance, and building optimization strategies based on analysis results, dynamic adjustment of performance baselines and intelligent management of resource allocation are achieved, which greatly improves the overall performance and resource utilization of the system. The information management and optimal configuration of performance evaluation resources are systematically realized.

[0058] Example 2

[0059] An embodiment of the present invention provides a performance evaluation resource information management system, an attribute determination module, including:

[0060] Threshold determination unit: determines the corresponding expansion requirements based on the basic attributes of each type of performance evaluation resource, and then determines the corresponding attribute expansion threshold:

[0061] ;in, is the attribute extension threshold corresponding to the basic attribute of the i-th type of performance evaluation resource, is the basic attribute value of the i-th type of performance evaluation resource, k is the total order of the expansion demand of the i-th type of performance evaluation resource, is the preset weight coefficient for controlling the nth order expansion coefficient of the i-th type of performance evaluation resource, is the nth order expansion coefficient of the i-th type of performance evaluation resource, is the preset expansion upper limit of the i-th type of performance evaluation resources;

[0062] Basic mapping unit: mapping based on the basic attributes of each type of performance evaluation resource and the preset attribute extension library, and then determining the extended attribute set corresponding to the basic attributes of each type of performance evaluation resource;

[0063] Level determination unit: monitors the resource usage of all performance evaluation resources, and determines the extended level corresponding to the basic attribute of each type of performance evaluation resource based on the resource usage of all performance evaluation resources and the attribute extension threshold corresponding to the basic attribute of each type of performance evaluation resource;

[0064] Attribute extension unit: performs attribute extension based on the extension level corresponding to the basic attribute of each type of performance evaluation resource and the extension attribute set corresponding to each type of performance evaluation resource in combination with a preset extension method.

[0065] In this embodiment, mapping based on the basic attributes of each type of performance evaluation resource and the preset attribute extension library means that the system will map based on the basic attributes of each type of performance evaluation resource using the preset attribute extension library. The attribute extension library is a database or list containing different extended attributes. Through this library, the system can find extended attributes that match the basic attributes of each type of performance evaluation resource. This mapping process ensures that the basic attributes can be associated with more advanced and specific attributes, thereby providing a basis for subsequent expansion. Assuming that the basic attribute of a certain type of performance evaluation resource is storage capacity (for example: 500GB), during the mapping process, the system can find extended attributes corresponding to the basic attribute in the attribute extension library, such as storage type (SSD or HDD), read and write speed, number of I / O operations, etc. These extended attributes further describe the specific characteristics of the storage capacity;

[0066] In this embodiment, the extended attribute set is generated by the system through the mapping process for each type of performance evaluation resource, referred to as the extended attribute set. This set contains all extended attributes associated with the basic attributes, and describes more detailed characteristics and performance indicators of the resource. The extended attribute set is the basis for further attribute extension and level determination. For example, for a resource with a storage capacity of 500GB, the extended attribute set that may be obtained through mapping includes: SSD type, read and write speed of 500MB / s, I / O operation times of 10,000 times per second, etc.

[0067] In this embodiment, resource usage is the current status and usage of all performance evaluation resources monitored by the system in real time, including resource usage frequency, load, response time, current availability, etc. Monitoring of resource usage can help the system dynamically adjust resource configuration and expand or reduce it when necessary. If the system detects that a resource with a storage capacity of 500GB is running at full capacity and the response time increases, the system will record the usage of this resource and may trigger further expansion operations;

[0068] In this embodiment, the expansion level is based on resource usage and an extension attribute set. The system determines the expansion level of each type of performance evaluation resource. The expansion level indicates the priority or urgency of the resource under current usage and expansion requirements. Different expansion levels trigger resource expansion operations of varying degrees. If storage resource usage indicates that the load is too high, and the extension attribute set shows that the read and write speeds need to be increased, the system may set the expansion level of the resource to high, thereby giving priority to expansion operations, which may include upgrading storage devices or increasing cache.

[0069] The beneficial effects of the above technical solution are: by introducing threshold control, basic mapping and level determination, accurate extension of resource attributes is achieved, the extension level is dynamically adjusted according to resource usage, and the extension attribute set is intelligently mapped to ensure the flexibility and accuracy of resource configuration. The degree of refinement of the extension process is controlled, and the efficiency and effectiveness of resource management are effectively improved.

[0070] Example 3

[0071] An embodiment of the present invention provides a performance evaluation resource information management system, wherein a preset expansion method includes: physical expansion, logical expansion, and mixed expansion.

[0072] In this embodiment, physical expansion refers to improving the capacity of performance evaluation resources by adding hardware resources. Common physical expansion includes increasing the number of CPU cores of the server, expanding memory capacity, adding storage devices, etc. For example, when the computing demand for a certain type of performance evaluation resource increases, the computing capacity of the system can be improved by adding more processors or increasing server memory to meet higher resource requirements;

[0073] In this embodiment, logical expansion refers to improving system performance by optimizing software configuration or increasing virtual resources. Common logical expansions include adjusting virtual machine configurations, optimizing database indexing strategies, allocating more bandwidth, etc. For example, when data processing tasks are heavy, you can speed up data retrieval by adjusting database indexing strategies, or increase virtual machine instances to share workloads, thereby improving the overall system response efficiency;

[0074] In this embodiment, hybrid expansion combines physical expansion and logical expansion to improve system performance by adjusting hardware and software resources at the same time. For example, when network traffic surges, the efficient operation of the network can be ensured by adding physical network interfaces (physical expansion) and optimizing load balancing strategies (logical expansion). In another case, in a cloud computing environment, users can respond to peak data storage and processing needs by combining adding virtual machine instances (logical expansion) and expanding underlying storage resources (physical expansion).

[0075] In this embodiment, the specific application of the three expansion methods is, for example, assuming that an enterprise's performance evaluation resource information management system needs to process a large number of data requests during business peak periods, and conventional configurations cannot meet the needs. Through physical expansion, the enterprise can increase the server's processor and memory to improve hardware performance; through logical expansion, the enterprise can adjust the application's thread pool size and database index strategy to better handle concurrent requests; through hybrid expansion, the enterprise can simultaneously increase the number of servers (physical expansion) and increase virtual machine instances (logical expansion) to ensure that the system can run efficiently and stably during peak periods.

[0076] The beneficial effects of the above technical solution are: through physical expansion, logical expansion and hybrid expansion, it effectively improves resource utilization and system flexibility, combines hardware resource expansion with software optimization, realizes dynamic configuration and intelligent evaluation of resources, breaks through the static limitations of traditional systems, and significantly improves the overall performance and responsiveness in complex environments.

[0077] Example 4

[0078] An embodiment of the present invention provides a performance evaluation resource information management system, a level determination unit, including:

[0079] Coefficient determination subunit: monitors the resource usage of all performance evaluation resources, and determines the resource usage coefficient based on the resource usage of all performance evaluation resources:

[0080] ;in, is the resource utilization coefficient, is the resource usage of the i-th performance evaluation resource, is the total amount of resources for the i-th type of performance evaluation, is the preset additional evaluation factor for the i-th type of resource, is the preset dependency strength of the i-th type of performance evaluation resource with other performance evaluation resources, is the preset time adjustment factor of the i-th resource, m is the total number of performance evaluation resources, is the preset period adjustment factor, is a trigonometric function;

[0081] Level determination subunit: determines the extended level corresponding to the basic attribute of each type of performance evaluation resource based on the resource usage coefficient and the attribute extension threshold corresponding to the basic attribute of each type of performance evaluation resource.

[0082] In this embodiment, the resource usage coefficient is a comprehensive indicator used to reflect the usage of a certain type of performance evaluation resource in the system, which is determined by multiple factors, mainly including the ratio of resource usage to total resource volume, and various preset adjustment factors, such as additional evaluation factor, time adjustment factor and dependency intensity;

[0083] In this embodiment, the preset additional evaluation factor is used to adjust the resource usage coefficient so that the coefficient is more in line with the evaluation requirements in a specific business scenario, and is set based on historical data, business importance or other key performance indicators. For example, in the evaluation of high-priority tasks, the factor can be appropriately increased to reflect the importance of the resource;

[0084] In this embodiment, the preset time adjustment factor is a parameter related to the time sensitivity of resource usage. For example, the usage of certain resources during peak hours has a greater impact on the overall system. Therefore, when calculating the resource usage coefficient, the usage of these time periods can be weighted by the preset time adjustment factor so that the coefficient can more accurately reflect the actual resource usage status.

[0085] In this embodiment, determining the extension level corresponding to the basic attributes of each type of performance evaluation resource based on the resource usage coefficient and the attribute extension threshold corresponding to the basic attributes of each type of performance evaluation resource is a core step of performing an extension evaluation on the basic attributes of each type of performance evaluation resource. The system first determines the resource usage coefficient, and then compares it with the preset attribute extension threshold for each type of resource. When the resource usage coefficient exceeds the threshold, the basic attributes of the resource are extended to a higher level according to preset rules to cope with higher load requirements. The extension levels include level one, level two, level three and level four. Level one extension: when the resource usage coefficient is slightly lower than the set threshold, basic extension is triggered. Level two extension: when the resource usage coefficient is significantly lower than the threshold, enhanced extension is triggered. Level three extension: when the resource usage coefficient is close to the limit or has a serious decline, advanced extension is triggered. Level four extension: when the resource usage coefficient is extremely low, emergency extension is triggered.

[0086] The beneficial effects of the above technical solution are: by introducing resource utilization coefficient calculation and multi-dimensional adjustment factors, the actual utilization of performance evaluation resources can be accurately reflected. Combined with the preset expansion threshold, the system can dynamically adjust the resource level, optimize resource allocation and utilization efficiency, thereby improving the performance evaluation accuracy and response speed of the overall system, and ensuring the best performance of resources in complex environments.

[0087] Example 5

[0088] An embodiment of the present invention provides a performance evaluation resource information management system, an agent deployment module, including:

[0089] Attribute acquisition unit: obtains node type information of each preset resource node, analyzes each type of node type information, and determines the node basic attributes corresponding to each type of node;

[0090] Attribute generation unit: merges the basic attributes of each preset resource node with the corresponding extended performance evaluation resource attributes, and generates comprehensive attributes;

[0091] Demand acquisition unit: generates attribute configuration information of each preset resource node based on the comprehensive attributes of each preset resource node, analyzes the attribute configuration information of each preset resource node, and further determines the monitoring requirements of each preset resource node;

[0092] Node deployment unit: determines the corresponding monitoring agent program based on the monitoring requirements of each preset resource node, and deploys the monitoring agent program to the preset resource node based on the preset deployment tool.

[0093] In this embodiment, the node type information refers to the relevant information of the category or type of each preset resource node, such as server, storage device, network device, etc. This information is the basis for the system to identify and classify resource nodes, and is used for subsequent attribute analysis and configuration. For example, in a data center, different types of servers (such as database servers, application servers) have different node type information, and this information is used to guide the system on how to monitor and manage them;

[0094] In this embodiment, the basic attributes of the node are the inherent attributes of each resource node, including basic hardware configurations such as CPU, memory, storage capacity, and performance indicators of the node. The system determines these basic attributes by analyzing the node type information as the basis for subsequent operations. For example, the basic attributes of a Web server node may include processor type, memory size, and network bandwidth, while the basic attributes of a database node may include storage capacity, I / O performance, etc.

[0095] In this embodiment, the basic attributes are merged with the corresponding extended performance evaluation resource attributes to generate a comprehensive attribute. The comprehensive attribute reflects the overall capabilities and characteristics of the node and is used to guide specific configuration and monitoring operations. For example, the basic attributes of the server are hardware specifications, while the corresponding extended performance evaluation resource attributes may be the installed operating system version and application. After this information is merged, it forms the comprehensive attributes of the server, which is used to more accurately meet business needs.

[0096] In this embodiment, the attribute configuration information of the node is generated based on the comprehensive attributes, which specifically describes how to configure and utilize the attributes of each resource node. Assuming there is a database server node, its attribute configuration information may include the following: CPU usage: monitor the processing power of the server to avoid overload, memory usage: track memory usage to prevent memory leaks or shortages, storage space: monitor the storage capacity of the database to ensure that data is not lost due to insufficient storage space, I / O performance: pay attention to the disk read and write speed to identify potential bottlenecks, network bandwidth: monitor data transmission speed and delay to ensure the timeliness of database response;

[0097] In this embodiment, the monitoring requirements are determined based on these configuration information, indicating the content and frequency of each resource node that needs to be monitored in actual operation. The monitoring requirements are usually composed of specific indicators (such as issuing an alarm when the CPU usage rate exceeds 90%), time requirements (such as collecting data every 5 minutes), and operational measures (such as automatically adjusting resource allocation when anomalies are found). For example, if the comprehensive attributes of a server show that its storage capacity is close to the upper limit, the system may generate a high-priority monitoring requirement to monitor the storage usage of the server in real time, and issue an alarm or automatically expand the capacity when necessary.

[0098] In this embodiment, the tool or platform for deploying the monitoring agent program to each resource node supports automated deployment and configuration management to ensure that the monitoring agent program can be quickly and accurately installed on the target node. For example, the system uses automated deployment tools such as Ansible, Puppet, and Chef to batch deploy the monitoring agent program to servers in the data center to achieve comprehensive monitoring of the entire resource pool.

[0099] The beneficial effects of the above technical solution are: by automatically analyzing and generating node attributes and monitoring requirements, the performance evaluation and management efficiency of resource nodes are significantly improved; by merging the basic attributes of the node with the binding attributes to generate comprehensive attributes, and configuring and deploying the monitoring agent based on this, accurate real-time monitoring is achieved, human intervention and errors are reduced, the adaptability and resource utilization of the system are improved, and it is suitable for complex and diverse network environments.

[0100] Example 6

[0101] The embodiment of the present invention provides a performance evaluation resource information management system and a monitoring agent program, including: a performance monitoring agent, a network monitoring agent and a security monitoring agent.

[0102] In this embodiment, the performance monitoring agent mainly focuses on the computing power and load status of resource nodes, and monitors key indicators such as CPU usage, memory usage, disk I / O operations, and application performance in real time. This agent can detect system bottlenecks and overload risks, and trigger alarms or automatic optimization measures when the threshold is reached. For example, CPU monitoring: monitors CPU usage. When the CPU usage of a server continues to exceed 90%, the performance monitoring agent will record the exception and notify the system administrator or automatically start the load balancing program. Memory monitoring: monitors memory usage. If the memory usage is close to 100%, the agent will start the garbage collection mechanism or schedule memory optimization tasks to prevent the system from crashing due to insufficient memory.

[0103] In this embodiment, the network monitoring agent is responsible for monitoring the network connection status and data transmission performance of the resource node, including real-time monitoring of bandwidth usage, network latency, packet loss rate, connection stability, etc., which helps to ensure the reasonable distribution of network traffic and the stability of data transmission. For example, when the network bandwidth usage of a node exceeds 85%, the network monitoring agent will trigger a warning and recommend speed limiting or priority adjustment to avoid network congestion. Delay monitoring: The agent continuously monitors the network latency of the node. When it finds that the network latency has increased significantly (such as exceeding 200ms), it will record the problem and recommend network optimization measures, such as changing the route or increasing the bandwidth;

[0104] In this embodiment, the security monitoring agent monitors the security status of resource nodes, including firewall rules, intrusion detection, user access records, abnormal activity monitoring, etc. This agent can respond quickly when potential security threats occur to prevent the system from being attacked or data leaks. For example, intrusion detection: If the security monitoring agent detects unauthorized access attempts or abnormal traffic (such as port scanning), it will immediately generate an alarm and automatically block suspicious IP addresses. Access record monitoring: The agent continuously monitors user access records. When abnormal access patterns are found (such as frequent logins by the same user in a short period of time), multi-factor authentication will be triggered or the user account will be locked.

[0105] In this embodiment, the deployment of agents refers to combining or customizing different types of monitoring agents (performance monitoring agents, network monitoring agents, and security monitoring agents) according to the specific needs of resource nodes to ensure that each resource node is monitored and managed in the most appropriate way. The integrated agent can be independently operated or a collection of multiple agent functions, configured according to the purpose and importance of the node. For example, the agent integration of the data center server: Demand analysis: The server in a data center is used to process a large number of computing tasks, and high network bandwidth and security are required at the same time. Therefore, these server nodes require powerful performance monitoring and network monitoring, supplemented by security monitoring to prevent potential threats. Agent selection: Performance monitoring agents (monitoring CPU, memory, I / O), network monitoring agents (monitoring bandwidth usage, network latency) and security monitoring agents (monitoring abnormal access, intrusion detection) are selected for these servers. Combined configuration: The performance monitoring agent and network monitoring agent are integrated into a comprehensive agent, and the security monitoring agent is deployed independently to ensure that the real-time performance monitoring and network monitoring are not affected. Deployment and implementation: The comprehensive agent and security monitoring agent are deployed to all server nodes, and data collection is set every minute and uploaded to the central management system to ensure that managers can understand the performance and security status of each node in a timely manner. Dynamic adjustment: According to the actual operation data of the server, it is found that the network latency is abnormally high in certain time periods, so the weight parameters of the network monitoring agent are adjusted, the monitoring frequency of network traffic is increased, and the bandwidth allocation strategy is optimized.

[0106] The beneficial effects of the above technical solution are: by integrating performance, network and security monitoring agents, a comprehensive performance evaluation system is created, which provides real-time and accurate resource management capabilities, embodies the seamless integration of multi-dimensional monitoring, improves the management efficiency of resource nodes, and ensures the optimal state of the overall system performance through dynamic adjustment and comprehensive evaluation.

[0107] Example 7

[0108] An embodiment of the present invention provides a performance evaluation resource information management system, a performance acquisition module, including:

[0109] Performance determination unit: Based on the monitoring agent program of each preset resource node, the monitoring agent obtains various indicator data of the preset resource node, and then determines the performance of each preset resource node:

[0110] Performance synthesis unit: Determines the total performance value of each type of resource based on the performance value of each preset resource node:

[0111] ;in, is the total efficiency value of the i-th type of resources, is the total number of nodes under the i-th type of resources, is the weight of the vth node under the i-th resource at time t, is the coefficient used to adjust the exponential decay factor in the overall performance value. is the value of the jth performance indicator in the vth node under the i-th resource type, is the weight of the vth node under the i-th resource related to the j-th performance indicator, is the total number of performance indicators under the i-th resource category, is the performance of the vth node under the i-th resource.

[0112] In this embodiment, the preset resource node refers to a specific resource unit that is pre-defined and needs to be monitored and managed in the performance evaluation resource information management system. These nodes can be servers, storage devices, network switches or virtual machines, etc. According to the needs and structure of the system, the pre-set resource units are easy to manage and monitor. Assuming that the performance evaluation system of a data center needs to monitor 100 servers, these servers are the preset resource nodes of the system. Each server may perform different tasks (such as database servers, application servers, file servers, etc.), so their monitoring requirements will also be different. These nodes are marked and defined as specific resource nodes in the system to facilitate targeted performance evaluation;

[0113] In this embodiment, various indicator data refer to various performance parameters or status information collected from preset resource nodes, including CPU utilization, memory usage, network bandwidth, response time, disk I / O, failure rate, etc., which are important bases for measuring the operating status and performance of resource nodes. The system collects these data in real time or periodically through the monitoring agent program to provide basic information for the performance determination unit. Assuming that the performance evaluation system of a data center needs to monitor 100 servers, these servers are the preset resource nodes of the system. Each server may perform different tasks (such as database servers, application servers, file servers, etc.), so their monitoring requirements will also be different. These nodes are marked and defined as specific resource nodes in the system to facilitate targeted performance evaluation. For the above 100 servers, the system will collect various indicator data through the monitoring agent programs (such as performance monitoring agents, network monitoring agents, and security monitoring agents) deployed on each server. For example, for a database server, the system may monitor its CPU utilization, memory usage, disk I / O speed, network traffic, and database query response time and other key indicators. These data are collected and transmitted to the performance determination unit, which calculates the performance value of the server based on these data.

[0114] The beneficial effects of the above technical solution are: by introducing a monitoring agent program to obtain multi-dimensional indicator data of each preset resource node, an accurate evaluation of the performance of each node is achieved. At the same time, the total performance value of each resource is summarized and analyzed by using the performance synthesis unit, and the exponential decay and weight adjustment methods are used to effectively improve the accuracy and response speed of the system in resource management and optimization decision-making, and significantly improve resource utilization efficiency and overall system performance.

[0115] Example 8

[0116] An embodiment of the present invention provides a performance evaluation resource information management system, a strategy building module, including:

[0117] Baseline determination unit: Analyze all performance evaluation resource information and determine the performance baseline based on the analysis results:

[0118] ;in, is the performance baseline, m is the total number of performance evaluation resources, is the dynamic weight of the i-th resource at time t, is the average value of the historical performance data of the i-th resource at the end time t, is the standard deviation of the historical performance data of the i-th resource at the end time t, is the adjustment coefficient of the i-th resource at time t, is a constant coefficient used to adjust resource efficiency fluctuations. is the performance fluctuation range difference of the i-th resource, is the time-dependent adjustment parameter, is the preset time reference point, where is the interaction coefficient between the i-th resource and the r-th resource:

[0119] ;in, is the interaction effect coefficient between the i-th resource and the r-th resource, is the interaction efficiency contribution between the i-th resource and the j-th resource at time t;

[0120] Performance comparison unit: compares the total performance of each type of resource with the performance baseline, and determines the priority of each type of resource based on the comparison results;

[0121] Policy determination unit: determines the resource allocation policy based on the priority of each type of resource.

[0122] In this embodiment, the preset time reference benchmark is a time node set in the performance evaluation process, which is used to compare and analyze the change trend of resource performance in different time periods. This benchmark is usually set based on the analysis results of historical data, which can reflect the performance of resource performance in different time periods and serve as a reference for evaluating current performance.

[0123] In this embodiment, the interaction coefficient refers to the degree of mutual influence between different types of resources. In performance evaluation, different resources (such as CPU and memory, network bandwidth and storage devices, etc.) may have mutual dependence or influence, and the interaction coefficient is used to quantify these influences to more accurately evaluate the performance of each type of resource;

[0124] In this embodiment, the interaction effect coefficient is a coefficient determined based on the specific interaction relationship between two different resource categories, and is used to measure the degree of influence of the interaction between resources on the overall performance. This coefficient is determined by analyzing and modeling the historical performance data of various types of resources, helping to identify positive or negative synergy between resources. For example, in a cloud computing environment, the interaction effect coefficient between the CPU and memory of a virtual machine is 0.6, indicating that when CPU resources are increased, memory performance will also be improved to a certain extent. This coefficient is obtained through modeling and analysis of a large amount of historical data, and can help optimize resource allocation strategies;

[0125] In this embodiment, the interaction performance contribution is the specific contribution of the interaction between two or more resources at a certain moment to the performance of a certain type of resource, reflecting the actual effect value of the mutual influence of different resources under specific conditions, helping to consider these mutual influence factors in resource management and optimization strategies and improve resource utilization efficiency. For example, in a certain application scenario, when the memory usage increases, the performance contribution of disk I / O decreases by 20%;

[0126] In this embodiment, the performance fluctuation range difference represents the performance fluctuation range of the resource at a certain point in time, that is, the difference between the upper and lower limits of the performance performance;

[0127] In this embodiment, the time-dependent adjustment parameter is a parameter that controls the rate of change of the performance baseline over time.

[0128] In this embodiment, the resource allocation strategy is determined based on the priority of each type of resource in the performance evaluation resource information management system. The strategy determination unit determines the resource allocation strategy based on the priority of each type of resource. The priority is determined based on the comparison result between the total performance value of each type of resource and its performance baseline. The system will give priority to allocating resources with higher performance, or give priority to optimizing resources with performance lower than the baseline to ensure the optimization of the performance of the entire system. For example, in a server cluster of a large enterprise, the performance evaluation system finds that the performance of the database server is lower than the performance baseline and has a higher priority. The system decides to allocate more memory and CPU resources to the database server to improve its performance and ensure the stable operation of the overall application system.

[0129] The beneficial effects of the above technical solution are: by introducing performance baselines, dynamic weights and interaction coefficients, accurately analyzing and predicting changes in resource performance, optimizing resource allocation strategies based on historical data and real-time adjustments, improving the accuracy and adaptability of performance management, effectively reducing resource waste and improving overall system efficiency.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A performance evaluation resource information management system, characterized in that: include: Attribute determination module: obtains resource information of all performance evaluation resources, classifies all performance evaluation resources based on a preset algorithm, and then determines the basic attributes of each type of performance evaluation resource; Attribute matching module: Based on the preset extension method, the basic attributes of each type of performance evaluation resource are extended, and the extended performance evaluation resource attributes are matched and analyzed with the preset resource nodes; Agent deployment module: based on the matching analysis results, the expanded performance evaluation resource attributes are bound to the node basic attributes of the corresponding matching preset resource nodes, and then the node monitoring agent program of each preset resource node is deployed; Performance acquisition module: based on the node monitoring agent program of each preset resource node, monitors the data of each preset resource node, and then determines the overall performance of all preset resource nodes; Strategy building module: Analyze the resource information of all performance evaluation resources and determine the performance baseline, and then build the performance evaluation resource allocation strategy based on the overall performance; Among them, the strategy building module includes: Baseline determination unit: Analyze all performance evaluation resource information and determine the performance baseline based on the analysis results: ;in, is the performance baseline, m is the total number of performance evaluation resources, is the dynamic weight of the i-th type of performance evaluation resource at time t, is the average value of the historical performance data of the i-th type of performance evaluation resource at the end time t, is the standard deviation of the historical performance data of the i-th type of performance evaluation resource at the end time t, is the adjustment coefficient of the i-th type of performance evaluation resource at time t, is a constant coefficient used to adjust resource efficiency fluctuations. is the performance fluctuation range difference of the i-th type of performance evaluation resource, is the time-dependent adjustment parameter of the i-th type of performance evaluation resource, is the preset time reference point, where is the interaction coefficient between the i-th type of performance evaluation resource and the r-th type of performance evaluation resource: ;in, is the interaction effect coefficient between the i-th type of performance evaluation resource and the r-th type of performance evaluation resource, is the interactive effectiveness contribution between the i-th type of effectiveness evaluation resource and the j-th type of effectiveness evaluation resource at time t; Performance comparison unit: compares the total performance of each type of performance evaluation resource with the performance baseline, and determines the priority of each type of performance evaluation resource based on the comparison result; Strategy determination unit: determines the resource allocation strategy based on the priority of each type of performance evaluation resource.

2. A performance evaluation resource information management system according to claim 1, characterized in that: Attribute determination module, including: Threshold determination unit: determines the corresponding expansion requirements based on the basic attributes of each type of performance evaluation resource, and then determines the corresponding attribute expansion threshold: ;in, is the attribute extension threshold corresponding to the basic attribute of the i-th type of performance evaluation resource, is the basic attribute value of the i-th type of performance evaluation resource, k is the total order of the expansion demand of the i-th type of performance evaluation resource, is the preset weight coefficient for controlling the nth order expansion coefficient of the i-th type of performance evaluation resource, is the nth order expansion coefficient of the i-th type of performance evaluation resource, is the preset expansion upper limit of the i-th type of performance evaluation resources; Basic mapping unit: mapping based on the basic attributes of each type of performance evaluation resource and the preset attribute extension library, and then determining the extended attribute set corresponding to the basic attributes of each type of performance evaluation resource; Level determination unit: monitors the resource usage of all performance evaluation resources, and determines the extended level corresponding to the basic attribute of each type of performance evaluation resource based on the resource usage of all performance evaluation resources and the attribute extension threshold corresponding to the basic attribute of each type of performance evaluation resource; Attribute extension unit: performs attribute extension based on the extension level corresponding to the basic attribute of each type of performance evaluation resource and the extension attribute set corresponding to each type of performance evaluation resource in combination with a preset extension method.

3. A performance evaluation resource information management system according to claim 2, characterized in that: The preset expansion methods include: physical expansion, logical expansion and mixed expansion.

4. The efficiency evaluation resource information management system according to claim 2, characterized in that: Level determination units, including: Coefficient determination subunit: monitors the resource usage of all performance evaluation resources, and determines the resource usage coefficient based on the resource usage of all performance evaluation resources: ;in, is the resource utilization coefficient, is the resource usage of the i-th performance evaluation resource, is the total amount of resources for the i-th type of performance evaluation, is the preset additional evaluation factor for the i-th type of resources, is the preset dependency strength of the i-th type of performance evaluation resource with other performance evaluation resources, is the preset time adjustment factor of the i-th resource, m is the total number of performance evaluation resources, is the preset period adjustment factor, is a trigonometric function; Level determination subunit: determines the extended level corresponding to the basic attribute of each type of performance evaluation resource based on the resource usage coefficient and the attribute extension threshold corresponding to the basic attribute of each type of performance evaluation resource.

5. The efficiency evaluation resource information management system according to claim 1, characterized in that: Agent deployment module, including: Attribute acquisition unit: obtains node type information of each preset resource node, analyzes each type of node type information, and determines the node basic attributes corresponding to each type of node; Attribute generation unit: merges the basic attributes of each preset resource node with the corresponding extended performance evaluation resource attributes, and generates comprehensive attributes; Demand acquisition unit: generates attribute configuration information of each preset resource node based on the comprehensive attributes of each preset resource node, analyzes the attribute configuration information of each preset resource node, and further determines the monitoring requirements of each preset resource node; Node deployment unit: determines the corresponding monitoring agent program based on the monitoring requirements of each preset resource node, and deploys the monitoring agent program to the preset resource node based on the preset deployment tool.

6. The efficiency evaluation resource information management system according to claim 1, characterized in that: Monitoring agents include: performance monitoring agent, network monitoring agent and security monitoring agent.

7. The efficiency evaluation resource information management system according to claim 1, characterized in that: Performance acquisition module, including: Performance determination unit: Based on the monitoring agent program of each preset resource node, the monitoring agent obtains various indicator data of the preset resource node, and then determines the performance of each preset resource node: Performance synthesis unit: Determines the total performance value of each type of resource based on the performance value of each preset resource node: ;in, is the total efficiency value of the i-th type of resources, is the total number of nodes under the i-th type of resources, is the weight of the vth node under the i-th resource at time t, is the coefficient used to adjust the exponential decay factor in the overall performance value. is the value of the jth performance indicator in the vth node under the i-th resource type, is the weight of the vth node under the i-th resource related to the j-th performance indicator, is the total number of performance indicators under the i-th resource category, is the performance of the vth node under the i-th resource.

Images