Multi-data center business intelligent management and control method, system and related device

Through the front-layer detection and dynamic evaluation of data center availability, the preset traffic policy and LVS cluster configuration inspection are used to solve the problem of single point failure of the LVS load balancer, and the reasonable allocation of service traffic and the improvement of large-scale traffic processing capabilities are achieved. .

CN118945171APending Publication Date: 2024-11-12JIALIAN PAYMENTS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410848332.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-27
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Single point of failure of the LVS load balancer can cause system service interruption, lack of flexibility and difficulty in handling large-scale traffic.

Method used

Receive client requests through the front layer, perform data center survival detection, determine the target data center in the available data center according to the preset traffic control strategy, and check the internal configuration through the LVS cluster of the target data center to ensure business request processing, dynamic Evaluate data center availability, automatically exclude unavailable clusters, and share traffic.

Benefits of technology

It effectively avoids service interruptions caused by data center failure, ensures reasonable allocation of business traffic, improves the system's ability to handle large-scale traffic, and solves the impact of LVS single point failure.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118945171A_ABST
    Figure CN118945171A_ABST
Patent Text Reader

Abstract

The invention discloses a multi-data center service intelligent management and control method and system and a related device, which are used for solving the influence of LVS single-point fault and improving the large-scale traffic processing capability of the system. The method comprises the following steps: receiving a service request sent by a client through a front layer; survivability detection is carried out on each data center through the front layer, each data center is marked as available or unavailable according to a survivability detection result, and each data center is provided with an LVS cluster; determining a target data center in the available data centers through the front layer according to a preset traffic control strategy, and sending the service request to the target data center; checking whether internal LVS configuration is passed through an LVS cluster of the target data center, wherein the LVS cluster comprises at least two LVS nodes and at least two rear-end load nodes; and if the configuration is passed, processing the service request through the LVS cluster of the target data center.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of business data processing, and in particular to a method, system and related devices for intelligent management and control of multi-data center business. Background Art

[0002] Linux Virtual Server (LVS) is a high-performance network load balancing solution. LVS is designed to build large server clusters, allowing multiple servers to work together and appear as a single virtual server, thereby providing higher availability and scalability.

[0003] LVS is widely used in Web server clusters, database server clusters, mail server clusters and other scenarios. It can provide stable services and improve overall performance through load balancing. With the development of cloud computing and big data technology, LVS, as a mature load balancing technology, is still one of the important choices for building high-availability and high-performance network infrastructure.

[0004] In the prior art, the use of LVS lacks flexibility. LVS is the core component of load balancing. If the node where the LVS load balancer is located fails, it may cause service interruption of the entire system, which is a major defect for a business environment that relies on high availability. Summary of the invention

[0005] The present application provides a method, system and related devices for intelligent management and control of multi-data center services, which are used to solve the impact of LVS single point failure and improve the system's ability to handle large-scale traffic.

[0006] The first aspect of the present application provides a method for intelligent management and control of multi-data center services, including:

[0007] Receive the service request sent by the client through the front-end layer;

[0008] Performing a survival check on each data center through the front layer, and marking each data center as available or unavailable according to the survival check result, wherein each data center is provided with an LVS cluster;

[0009] Determine a target data center from available data centers through the front layer according to a preset traffic control strategy, and send the service request to the target data center;

[0010] Check whether the internal configuration passes through the LVS cluster of the target data center, wherein the LVS cluster includes at least two LVS nodes and at least two backend load nodes;

[0011] If the configuration is successful, the service request is processed by the LVS cluster of the target data center.

[0012] Optionally, performing a liveness check on each data center through the front layer, and marking each data center as available or unavailable according to a result of the liveness check, includes:

[0013] Access the port of each data center using a TCP connection through the front-end layer to detect whether the port of each data center is open;

[0014] Each data center is marked as available or unavailable according to the port detection result by the front layer.

[0015] Optionally, performing a liveness check on each data center through the front layer, and marking each data center as available or unavailable according to a result of the liveness check, includes:

[0016] Sending a service detection address to each data center through the front layer, and receiving a status code returned by each data center;

[0017] Each data center is marked as available or unavailable by the front layer according to the size of the status code.

[0018] Optionally, after the service request is processed by the LVS cluster of the target data center, the method further includes:

[0019] Detecting, by the front layer, whether a data center level fault occurs in the target data center;

[0020] If so, the front-end layer unloads or disables the back-end load nodes related to the target data center in all data centers, and forwards the service request to other available data centers.

[0021] Optionally, the method further includes:

[0022] receiving an uninstallation instruction sent by a user, wherein the uninstallation instruction carries an identifier of a silent data center;

[0023] The backend load nodes related to the silent data center in all data centers are unloaded according to the unloading instruction.

[0024] Optionally, the checking whether the internal LVS configuration is passed through the LVS cluster of the target data center includes:

[0025] Checking, through the LVS cluster of the target data center, whether there is at least one LVS node in a normal working state and at least one back-end load node in a normal working state;

[0026] If yes, it is determined that the internal configuration passes;

[0027] If not, it is determined that the internal configuration fails.

[0028] Optionally, the method further includes:

[0029] receiving configuration modification information through the front layer, and checking whether the configuration modification information is valid;

[0030] The effective configuration modification information is distributed to all back-end load nodes through the front-end layer.

[0031] A second aspect of the present application provides a system for intelligent management and control of multi-data center services, including:

[0032] A front layer and at least two data centers, each of the at least two data centers is provided with an LVS cluster, and the LVS cluster includes at least two LVS nodes and at least two back-end load nodes;

[0033] The front layer comprises:

[0034] A receiving unit, used for receiving a service request sent by a client;

[0035] A survival detection unit, configured to perform survival detection on each data center, and mark each data center as available or unavailable according to the result of the survival detection;

[0036] A determination unit, configured to determine a target data center from available data centers according to a preset traffic control strategy, and send the service request to the target data center;

[0037] The target data center includes:

[0038] A configuration checking unit, used to check whether the internal configuration of the LVS cluster is passed;

[0039] The processing unit is used to process the service request through the LVS cluster when the configuration is passed.

[0040] Optionally, the viability detection unit is specifically used for:

[0041] Use TCP connection to access the port of each data center to check whether the port of each data center is open;

[0042] Each data center is marked as available or unavailable according to the port detection result.

[0043] Optionally, the viability detection unit is further configured to:

[0044] Sending a service detection address to each data center, and receiving a status code returned by each data center;

[0045] Each data center is marked as available or unavailable according to the size of the status code.

[0046] Optionally, the front layer further includes: a first unloading unit;

[0047] The first unloading unit is specifically used for:

[0048] Detecting whether a data center level failure occurs in the target data center;

[0049] If so, the front-end layer unloads or disables the back-end load nodes related to the target data center in all data centers, and forwards the service request to other available data centers.

[0050] Optionally, the system further comprises: a second unloading unit;

[0051] The second unloading unit is specifically used for:

[0052] receiving an uninstallation instruction sent by a user, wherein the uninstallation instruction carries an identifier of a silent data center;

[0053] The backend load nodes related to the silent data center in all data centers are unloaded according to the unloading instruction.

[0054] Optionally, the configuration checking unit is specifically used for:

[0055] Check whether there is at least one LVS node in normal working state and at least one back-end load node in normal working state;

[0056] If yes, it is determined that the internal configuration passes;

[0057] If not, it is determined that the internal configuration fails.

[0058] Optionally, the front layer further includes: a configuration modification unit;

[0059] The configuration modification unit is used for:

[0060] receiving configuration modification information, and checking whether the configuration modification information is valid;

[0061] Distribute effective configuration modification information to all backend load nodes.

[0062] A third aspect of the present application provides a device for intelligent management and control of multi-data center services, the device comprising:

[0063] Processor, memory, input-output unit, and bus;

[0064] The processor is connected to the memory, the input and output unit, and the bus;

[0065] The memory stores a program, and the processor calls the program to execute the first aspect and any optional method for intelligent management and control of multi-data center services in the first aspect.

[0066] The fourth aspect of the present application provides a computer-readable storage medium, on which a program is stored. When the program is executed on a computer, the method for intelligent management and control of multi-data center services in the first aspect and any optional method in the first aspect is executed.

[0067] It can be seen from the above technical solutions that this application has the following advantages:

[0068] By centrally receiving business requests through the front-end layer and integrating a survival detection mechanism, the availability of each data center is dynamically evaluated, effectively avoiding service interruptions caused by data center failures. At the same time, the front-end layer uses a preset traffic control strategy to determine the target data center. The target data center uses an internal automated LVS cluster configuration check to quickly identify unavailable LVS clusters and automatically exclude them from traffic distribution, ensuring that business traffic can be reasonably allocated to the correct and available LVS cluster, effectively resolving the impact of LVS single-point failures. In addition, this application shares business traffic through multiple LVS clusters, effectively alleviating performance bottlenecks and improving the system's ability to handle large-scale traffic. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solution in the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0070] Figure 1 A flowchart of an embodiment of the method for intelligent management and control of multi-data center services provided by this application;

[0071] Figure 2 A schematic diagram of an embodiment of the survivability detection process in the method for intelligent management and control of multi-data center services provided in this application;

[0072] Figure 3 A flowchart of another embodiment of survivability detection in the method for intelligent management and control of multi-data center services provided by the present application;

[0073] Figure 4A schematic flow chart of an embodiment of automatically unloading or disabling a backend load node with a running failure in the method for intelligent management and control of multi-data center services provided by the present application;

[0074] Figure 5 A schematic flow chart of an embodiment of human intervention in business traffic in the method for intelligent management and control of multi-data center business provided by this application;

[0075] Figure 6 A flowchart of an embodiment of checking whether the LVS cluster configuration of the target data center is passed in the method for intelligent management and control of multi-data center services provided by the present application;

[0076] Figure 7 A flowchart of an embodiment of configuration modification management in the method for intelligent management and control of multi-data center services provided by the present application;

[0077] Figure 8 A schematic diagram of the structure of an embodiment of a system for intelligent management and control of multi-data center services provided by this application;

[0078] Fig. 9 A schematic diagram of the structure of an embodiment of the device for intelligent management and control of multi-data center services provided in this application. DETAILED DESCRIPTION

[0079] The present application provides a method, system and related devices for intelligent management and control of multi-data center services, which are used to solve the impact of LVS single point failure and improve the system's ability to handle large-scale traffic.

[0080] It should be noted that the method for intelligent management and control of multi-data center services provided in the present application can be applied to terminals and servers. For example, the terminal can be a smart phone or computer, tablet computer, smart TV, smart watch, portable computer terminal or a fixed terminal such as a desktop computer.

[0081] See also Figure 1 , Figure 1 An embodiment of a method for intelligent management and control of multi-data center services provided in this application includes:

[0082] S101, receiving a service request sent by a client through a front-end layer;

[0083] Data centers are dedicated facilities that centrally store and manage a large number of servers, network equipment, storage systems, and other key IT infrastructure. Data centers provide the necessary infrastructure for businesses to support the operation of business applications and the storage of data. With the rapid development of Internet business, users have higher and higher requirements for service availability, response speed, and stability. The traditional single data center model may not be able to meet user needs due to problems such as geographical location, network congestion, or local failures. Therefore, you can choose to set up different data centers in multiple geographical locations to provide more stable and efficient services by dispersing risks and optimizing resource allocation.

[0084] In this embodiment, all data centers are uniformly managed by the front-end layer, also known as the Global Traffic Manager (GTM), and the front-end layer is deployed as the total entrance for all business traffic, responsible for receiving and distributing all business requests from clients. Specifically, to realize the front-end layer as the total entrance for all business traffic, it is necessary to configure all business-related domain names through DNS to ensure that all resolution requests point to the IP address of the front-end layer GTM to achieve unified access to traffic.

[0085] When the front-end layer receives a service request sent by the client, the front-end layer, as the first contact point for the service request, needs to execute subsequent steps S102 to S105 to make intelligent decisions and distribute the service request to the most appropriate data center.

[0086] S102, performing a survivability test on each data center through the front layer, and marking each data center as available or unavailable according to the result of the survivability test, and an LVS cluster is set on each data center;

[0087] For each data center, an LVS cluster is set up on its data access zone DMZ. The LVS cluster can efficiently receive and distribute network traffic in the data access zone, and distribute incoming requests to multiple servers on the back end according to the load balancing algorithm. The data access zone DMZ is located between the external network and the internal network, and is used for security isolation to protect the internal network from direct external attacks. However, when a data center-level (computer room-level) failure occurs, the entire data center may not work. The data center-level failure specifically refers to a serious failure that affects the operation of the entire data center. Such failures may be caused by power outages, natural disasters, network problems, or security incidents. Data center-level failures can have a serious impact on the business continuity and data security of the enterprise, and therefore require an emergency response.

[0088] After receiving the service request sent by the client, the front-end layer performs a survivability check on each data center. The purpose of this survivability check is to quickly identify and respond to such data center-level failures to ensure that the service is not affected.

[0089] The front-end layer performs a survivability test on each data center and marks the availability status of the data center based on the results of the survivability test. The availability status can guide the front-end layer to intelligently allocate service requests to avoid invalid requests for unavailable resources. Specifically, the indicators of the survivability test may include network connectivity, service response time, hardware health status, etc., which are not limited here. Survivability means that the target data center can provide services to the outside world. The front-end layer marks the data center that passes the survivability test as available, and marks the data center that fails the survivability test as unavailable, so as to avoid sending traffic to an unavailable data center, reduce the risk of service interruption, and thus improve the overall service availability.

[0090] S103, determining a target data center from available data centers according to a preset traffic control strategy through the front-end layer, and sending the service request to the target data center;

[0091] The front-end layer ensures that only available data centers are included in the candidate list for traffic distribution through survivability detection. At this time, the front-end layer determines the target data center among the available data centers based on the preset traffic control strategy and the real-time status of the data center. The target data center refers to the data center that the front-end layer determines is most suitable for processing the business request based on the preset traffic control strategy and the real-time status of the data center. The front-end layer then sends the business request to the target data center.

[0092] It should be noted that the preset traffic control strategy is a set of well-defined rules and algorithms to guide the front-end layer on how to distribute incoming network traffic in a multi-data center environment. Enterprises can formulate traffic control strategies that meet their business goals based on business needs, service level agreements (SLAs), data center geographic locations, load capacity and other factors in the early stage. Through this preset traffic control strategy, the front-end layer can effectively direct business traffic to each data center (LVS cluster) according to the ideal percentage.

[0093] S104, checking whether the internal configuration is passed through the LVS cluster of the target data center, where the LVS cluster includes at least two LVS nodes and at least two backend load nodes;

[0094] In this embodiment, each LVS cluster includes at least two LVS nodes (1 master and 1 slave node) and at least two back-end load nodes to form a highly available load balancing cluster. Through the design of master-slave LVS nodes, it is ensured that when the master node fails, the slave node can take over the traffic to ensure the continuity of the service. Multiple back-end load nodes share the traffic, distribute requests according to the preset load balancing algorithm, and improve processing capabilities and response speed. Through the above-mentioned architectural design, the LVS cluster on each data center can process traffic independently, realize a true multi-data center multi-active architecture, and avoid single point failures. And the back-end load nodes can be divided into different groups, each group respectively represents the traffic of a specific data center, simplifying traffic management and improving efficiency.

[0095] After receiving the service request, the target data center needs to perform an internal configuration check on the LVS cluster, that is, the LVS cluster of the target data center self-checks whether the internal configuration has passed. If it has passed, step 105 is executed to ensure that the LVS cluster can correctly and efficiently process the upcoming service request. Specifically, the configuration check includes but is not limited to:

[0096] 1. Node status check: confirm whether each LVS node (including master node and slave node) is active and in normal working state;

[0097] 2. Load balancing configuration check: Check whether the load balancing algorithm and related parameter settings are correct, such as weight distribution, session persistence, etc.;

[0098] 3. Resource utilization check: confirm the resource usage of the backend load nodes (such as CPU, memory, network bandwidth) to avoid overload;

[0099] 4. Configuration consistency check: Ensure that the configurations of all LVS nodes and backend load nodes are consistent to avoid problems caused by configuration differences.

[0100] In some specific embodiments, a total of three data centers are set up as an example, and the three data centers are A, B, and C. Each data data center is respectively provided with an LVS cluster in the data access area, and each LVS cluster has two LVS nodes and six backend load nodes, and each two backend load nodes form a group. Each group of backend load nodes in each data center respectively proxies the traffic of the three data centers A, B, and C, realizing a multi-data center multi-active architecture. The LVS cluster of each data center can receive and process traffic from other data centers. By grouping and managing the backend load nodes, the configuration of traffic management and routing policies can be simplified, making the traffic of each data center more clear and controllable.

[0101] S105: If the configuration is successful, the service request is processed through the LVS cluster of the target data center.

[0102] After the front-end layer determines the target data center and directs the received business requests to the target data center, the LVS cluster of the target data center will self-check whether the internal configuration has passed. After the internal configuration has passed, the load balancing capability of the LVS cluster will be used to intelligently distribute the business requests to the most appropriate back-end load nodes based on the current traffic and node status.

[0103] If the configuration fails, the LVS cluster in the target data center will not process the service request to avoid potential service interruption or performance degradation. At this time, the LVS cluster can be automatically troubleshooted and repaired until it passes the internal configuration check again, or the service request can be directly forwarded to other available data centers, which is not limited here.

[0104] In this embodiment, the front-end layer centrally receives service requests and integrates a survival detection mechanism to dynamically evaluate the availability of each data center, effectively avoiding service interruptions caused by data center failures. At the same time, the front-end layer uses a preset traffic control strategy to determine the target data center. The target data center uses an internal automated LVS cluster configuration check to quickly identify unavailable LVS clusters and automatically exclude them from traffic distribution, ensuring that business traffic can be reasonably allocated to the correct and available LVS cluster, effectively solving the impact of LVS single-point failures. In addition, this application shares business traffic through multiple LVS clusters, effectively alleviating performance bottlenecks and improving the system's ability to handle large-scale traffic.

[0105] In step S102, the survivability detection of the data center can be implemented through network connectivity. Figure 2 , Figure 2 In one embodiment of performing survivability detection on a data center, the method includes:

[0106] S201, access the port of each data center through the front layer using TCP connection to detect whether the port of each data center is open;

[0107] S202. Mark each data center as available or unavailable according to the port detection result through the front-end layer.

[0108] In this embodiment, the front-end layer can use the TCP handshake process to verify the openness of the port by attempting to initiate a TCP connection to a specific port configured for each data center (for example, HTTP default port 80 or HTTPS port 443). If the TCP connection is successfully established, it indicates that the port of the data center is open and the data center can receive service requests, so it can be preliminarily determined that there is no data center level failure.

[0109] The front-end layer marks the data center as available or unavailable based on the detection result of whether the port is open. An open port means that the corresponding service of the data center is running normally, so it is marked as "available"; if the port is closed or the TCP connection fails, the data center is marked as "unavailable". This survivability detection method is simple and direct, and can quickly identify whether there is a data center-level failure in the data center, thereby ensuring that only available data centers are used for traffic distribution in subsequent steps.

[0110] In step S102, the data center survival detection can also be implemented by configuring the service detection address. Figure 3 , Figure 3 In another embodiment of performing survivability detection on a data center, the method includes:

[0111] S301, sending a service detection address to each data center through the front layer, and receiving a status code returned by each data center;

[0112] S302. Mark each data center as available or unavailable according to the size of the status code through the front layer.

[0113] In this embodiment, the front-end layer simulates the request of real users by sending a specific business detection address (URL) to the data center to detect whether the data center can handle the business normally. The front-end layer receives the status code returned from the data center. If the status code returned by a data center is between 200-499, it usually means that the request is successful, and the front-end layer marks this data center as "available". If the returned status code is 500 or higher, it usually means that the server has encountered an error, and the front-end layer marks this data center as "unavailable". Through the business detection address, the front-end layer can more accurately simulate and evaluate the ability of the data center to handle actual business requests, and achieve more accurate survival detection.

[0114] After step S105, the front layer can automatically uninstall the failed data center, see Figure 4 , the method comprising:

[0115] S401, detecting whether a data center-level fault occurs in the target data center through the front-end layer;

[0116] S402: When a data center-level failure occurs in the target data center, the front-end layer unloads or disables the back-end load nodes related to the target data center in all data centers, and forwards the service request to other available data centers.

[0117] In this embodiment, after the front-end layer sends the service request to the LVS cluster of the target data center for processing, it will also monitor the operation of the target data center in real time and detect whether the target data center has a data center-level failure. If the front-end layer detects that the target data center has a data center-level failure, it will unload or disable the back-end load nodes related to the target data center in all data centers to ensure that the target data center will not receive new service requests. In addition, the service request originally sent to the faulty data center will be forwarded to other available data centers in real time to achieve a rapid response to the operation failure and ensure that the service request is processed in a timely manner.

[0118] In other specific embodiments, the front layer may also detect the operation status of the LVS cluster of the target data center and unload the faulty nodes, so as to timely identify the faulty load nodes that are not detected by the internal rules of the LVS cluster.

[0119] In addition, once the front-end layer detects an operational failure in the LVS cluster of the target data center, the alarm process is immediately triggered, and the operation and maintenance team or relevant personnel are quickly notified through preset notification channels (such as email, SMS, real-time application reminders, etc.), ensuring that the problem can be handled in a timely manner and minimizing the impact of the failure on the business.

[0120] In the method for intelligent management and control of multi-data center services provided in this application, human intervention in service traffic can also be achieved. Figure 5 , the method comprising:

[0121] S501, receiving an uninstallation instruction sent by a user, where the uninstallation instruction carries an identifier of a silent data center;

[0122] S502: The uninstall instruction uninstalls the backend load nodes related to the silent data center in all data centers.

[0123] In this embodiment, the user is allowed to manually issue an unloading instruction to control the state of the backend load nodes of a specific data center or a specific LVS cluster. The unloading instruction should contain a clear identification of the silent data center to ensure accurate execution of the unloading operation. The internal operation and maintenance system will receive and parse the unloading instruction, identify the silent data center and perform the unloading operation, that is, remove the backend load nodes related to the silent data center from all data centers, and stop sending new service requests to these nodes, thereby achieving the silence of the data center. Through this unloading mechanism, the user is allowed to manually unload the backend load nodes belonging to the silent data center from all data centers when the data center encounters a service failure that cannot be self-healed or silent maintenance is required, thereby effectively controlling the service traffic, ensuring the stability of the system and the continuity of the service, to meet different operation and maintenance requirements. It should be noted that in order to eliminate the problem of service unavailability caused by accidental unloading, the unloading instruction issued by the user cannot unload all data centers, and the internal operation and maintenance system will retain at least one LVS load node in at least one data center that is not unloaded.

[0124] In the above step S104, the LVS cluster configuration of the target data center can be checked by judging whether the working status of all nodes is normal. Figure 6 , the method comprising:

[0125] S601, check whether there is at least one LVS node in normal working state and at least one backend load node in normal working state in the LVS cluster of the target data center, if yes, execute step S602, if no, execute step S603;

[0126] S602, confirm that the internal configuration is passed;

[0127] S603: Determine that the internal configuration fails.

[0128] In this embodiment, the LVS cluster of the target data center will conduct a comprehensive inspection of the internal LVS nodes and the back-end load nodes to determine whether there is at least one LVS node in normal working condition and at least one back-end load node in normal working condition. If so, step S602 is executed to determine that the internal configuration of the LVS cluster passes. If it is found in step S601 that the working status of all nodes is abnormal, step S603 is executed to determine that the internal configuration of the LVS cluster does not pass, and exclude it from the traffic distribution until the problem is resolved and re-checked, ensuring that only the LVS cluster with the correct internal configuration will process the business traffic, thereby ensuring the high availability and stability of the entire system.

[0129] Configuration failure (node ​​is not in normal working state) may be caused by several key reasons, including automatic unloading or disabling of backend load nodes triggered by operation failure of LVS cluster, and manual unloading operation performed by users based on specific operation and maintenance considerations. Whether it is automatic or manual unloading, once the LVS cluster self-check internal configuration fails, the LVS cluster will not process the current business request. Through such a process, the system can flexibly respond to various failure situations, reduce the impact of single point failure on the business, and improve the reliability and elasticity of the overall service.

[0130] The method for intelligent management and control of multi-data center services provided in this application also includes a method for configuration modification management, please refer to Figure 7 , the method comprising:

[0131] S701, receiving configuration modification information through the front layer, and checking whether the configuration modification information is valid;

[0132] S702. Distribute the effective configuration modification information to all back-end load nodes through the front-end layer.

[0133] In this embodiment, a configuration center is also provided on the front-end layer. When the configuration of all LVS load back-end nodes needs to be modified, only the corresponding modification needs to be made in the configuration center. After the user saves the configuration modification information, the front-end layer automatically determines whether the configuration modification information is valid, specifically, whether there are errors such as spelling errors of configuration keywords, configuration syntax errors, configuration inclusion file path errors, and illegal port occupation in the configuration modification information. If the configuration modification information is invalid, it will not take effect, and the back-end load node will maintain the original configuration or roll back to the last known valid configuration state. If the front-end layer determines that the configuration modification information is valid, it will automatically distribute the configuration modification information to all relevant back-end load nodes to ensure that these configurations take effect safely, thereby ensuring the security and uniformity of the configuration.

[0134] See also Figure 8 , Figure 8 An embodiment of the system for intelligent management and control of multi-data center services provided by the present application includes:

[0135] The front layer and at least two data centers are provided with LVS clusters, and the LVS clusters include at least two LVS nodes and at least two back-end load nodes;

[0136] The front layer includes:

[0137] The receiving unit 801 is used to receive a service request sent by a client;

[0138] A liveness detection unit 802 is used to perform liveness detection on each data center and mark each data center as available or unavailable according to the result of the liveness detection;

[0139] A determination unit 803 is configured to determine a target data center from available data centers according to a preset traffic control policy, and send the service request to the target data center;

[0140] Target data centers include

[0141] Configuration checking unit 804, used to check whether the internal configuration of the LVS cluster is passed;

[0142] The processing unit 805 is configured to process the service request through the LVS cluster when the inspection result of the configuration inspection unit is that the configuration is passed.

[0143] Optionally, the liveness detection unit 802 is specifically configured to:

[0144] Use TCP connection to access the port of each data center to check whether the port of each data center is open;

[0145] Each data center is marked as available or unavailable based on the port detection results.

[0146] Optionally, the liveness detection unit 802 is further configured to:

[0147] Send the service detection address to each data center and receive the status code returned by each data center;

[0148] Each data center is marked as available or unavailable based on the size of the status code.

[0149] Optionally, the front layer further includes: a first unloading unit 806;

[0150] The first unloading unit 806 is specifically used for:

[0151] Detect whether a data center-level failure occurs in the target data center;

[0152] If so, the front-end layer unloads or disables the back-end load nodes related to the target data center in all data centers, and forwards the service request to other available data centers.

[0153] Optionally, the system further includes: a second unloading unit 807;

[0154] The second unloading unit 807 is specifically used for:

[0155] receiving an uninstallation instruction sent by a user, wherein the uninstallation instruction carries an identifier of a silent data center;

[0156] Unload the backend load nodes related to the silent data center in all data centers according to the unloading instruction.

[0157] Optionally, the configuration checking unit 804 is specifically configured to:

[0158] Check whether there is at least one LVS node in normal working state and at least one back-end load node in normal working state;

[0159] If yes, it is determined that the internal configuration passes;

[0160] If not, it is determined that the internal configuration fails.

[0161] Optionally, the front layer further includes: a configuration modification unit 808;

[0162] The configuration modification unit 808 is used to:

[0163] Receive configuration modification information and check whether the configuration modification information is valid;

[0164] Distribute effective configuration modification information to all backend load nodes.

[0165] In this embodiment, the functions of each unit are the same as those described above. Figures 1 to 7 The steps in the method embodiment shown correspond to each other and will not be repeated here.

[0166] This application also provides a device for intelligent management and control of multi-data center services, see Fig. 9 , Fig. 9 An embodiment of a device for intelligent management and control of multi-data center services provided in this application includes:

[0167] Processor 901, memory 902, input and output unit 903, bus 904;

[0168] The processor 901 is connected to the memory 902, the input and output unit 903 and the bus 904;

[0169] The memory 902 stores a program, and the processor 901 calls the program to execute any of the above methods for intelligent management and control of multi-data center services.

[0170] The present application also relates to a computer-readable storage medium on which a program is stored, wherein when the program is executed on a computer, the computer is enabled to execute any of the above methods for intelligent management and control of multi-data center services.

[0171] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0172] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0173] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0174] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0175] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

Claims

1. A method for intelligent management and control of multi-data center services, characterized in that: The method comprises: Receive the service request sent by the client through the front-end layer; Performing a survival check on each data center through the front layer, and marking each data center as available or unavailable according to the survival check result, wherein each data center is provided with an LVS cluster; Determine a target data center from available data centers through the front layer according to a preset traffic control strategy, and send the service request to the target data center; Check whether the internal configuration passes through the LVS cluster of the target data center, wherein the LVS cluster includes at least two LVS nodes and at least two backend load nodes; If the configuration is successful, the service request is processed by the LVS cluster of the target data center.

2. The method according to claim 1, characterized in that The performing a survivability test on each data center through the front layer, and marking each data center as available or unavailable according to the result of the survivability test, includes: Access the port of each data center using a TCP connection through the front-end layer to detect whether the port of each data center is open; Each data center is marked as available or unavailable according to the port detection result by the front layer.

3. The method according to claim 1, characterized in that Performing a survivability check on each data center through the front layer, and marking each data center as available or unavailable according to the result of the survivability check, including: Sending a service detection address to each data center through the front layer, and receiving a status code returned by each data center; Each data center is marked as available or unavailable by the front layer according to the size of the status code.

4. The method according to claim 1, characterized in that After the service request is processed by the LVS cluster of the target data center, the method further includes: Detecting, by the front layer, whether a data center level fault occurs in the target data center; If so, the front-end layer unloads or disables the back-end load nodes related to the target data center in all data centers, and forwards the service request to other available data centers.

5. The method according to claim 1, characterized in that: The method further comprises: receiving an uninstallation instruction sent by a user, wherein the uninstallation instruction carries an identifier of a silent data center; The backend load nodes related to the silent data center in all data centers are unloaded according to the unloading instruction.

6. The method according to any one of claims 1 to 5, characterized in that The step of checking whether the internal LVS configuration is passed through the LVS cluster of the target data center includes: Checking, through the LVS cluster of the target data center, whether there is at least one LVS node in a normal working state and at least one back-end load node in a normal working state; If yes, it is determined that the internal configuration passes; If not, it is determined that the internal configuration fails.

7. The method according to any one of claims 1 to 5, characterized in that The method further comprises: receiving configuration modification information through the front layer, and checking whether the configuration modification information is valid; The effective configuration modification information is distributed to all back-end load nodes through the front-end layer.

8. A system for intelligent management and control of multi-data center services, characterized in that: The system comprises: a front layer and at least two data centers, each of the at least two data centers is provided with an LVS cluster, and the LVS cluster comprises at least two LVS nodes and at least two back-end load nodes; The front layer comprises: A receiving unit, used for receiving a service request sent by a client; A survival detection unit, configured to perform survival detection on each data center, and mark each data center as available or unavailable according to the result of the survival detection; A determination unit, configured to determine a target data center from available data centers according to a preset traffic control strategy, and send the service request to the target data center; The target data center includes: A configuration checking unit, used to check whether the internal configuration of the LVS cluster is passed; The processing unit is used to process the service request through the LVS cluster when the configuration is passed.

9. A device for intelligent management and control of multi-data center services, characterized in that: The device comprises: Processor, memory, input-output unit, and bus; The processor is connected to the memory, the input and output unit, and the bus; The memory stores a program, and the processor calls the program to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a program stored thereon, wherein the program, when executed on a computer, performs the method according to any one of claims 1 to 7.