CN110784504A

CN110784504A - Intelligent distributed system deployment method, system and storage medium

Info

Publication number: CN110784504A
Application number: CN201910812935.2A
Authority: CN
Inventors: 张鑫
Original assignee: Evergrande Intelligent Technology Co Ltd
Current assignee: Evergrande Intelligent Technology Co Ltd
Priority date: 2019-08-29
Filing date: 2019-08-29
Publication date: 2020-02-11

Abstract

The invention provides an intelligent distributed system deployment method, which comprises the following steps: a plurality of servers are arranged to be connected with one another, wherein one server is a dispatching center; placing a pre-compiled service performance requirement file in the dispatching center, wherein the service performance requirement file is used for explaining performance parameter requirements corresponding to services; the dispatching center obtains index parameters of other servers; calculating an adaptation server corresponding to each service according to a preset fuzzy algorithm, generating a relation table of the service and the adaptation server and storing the relation table; when a service request is made, the dispatching center receives the service request, searches an adaptive server corresponding to the service, and skips the service to the server for loading. The intelligent distributed system deployment method provided by the embodiment of the invention improves the utilization rate of system resources and the response speed.

Description

Intelligent distributed system deployment method, system and storage medium

Technical Field

The embodiment of the invention relates to the field of software engineering, in particular to a method, a device and a storage medium for deploying an intelligent distributed system.

Background

Distributed computing is a research direction in computer science, and researches how to divide a problem which needs huge computing power to solve into a plurality of small parts, then the parts are distributed to a plurality of computers to be processed, and finally the computing results are integrated to obtain a final result.

Distributed systems (distributed systems) are software systems built on top of a network. The distributed system has the natural advantages of parallelism, high fault tolerance, data equipment sharing, easy horizontal expansion and the like, and is widely suitable for large and medium-sized software projects.

At present, a container-based distributed system is gradually popular, and the bergenetes (k8s) from google has wide application in a container cluster management system, and has the following functions:

the method can be transplanted, namely, the method supports public cloud, private cloud, mixed cloud and multi-cloud.

The expansion is modular, plug-in, mountable and combinable.

Automatic deployment, automatic restart, automatic replication, and automatic expansion/expansion.

It is known that the performance of computer hardware is uneven, the currently mainstream cloud service, memory, CPU performance, hard disk capacity and performance, and network IO bandwidth efficiency are different, and the past deployment can only achieve the function of horizontal extension, and cannot differentiate the machine performance for automatic allocation.

Disclosure of Invention

In order to solve the above problem, an embodiment of the present invention provides an intelligent distributed system deployment method, including the following steps:

a plurality of servers are arranged to be connected with one another, wherein one server is a dispatching center;

placing a pre-compiled service performance requirement file in the dispatching center, wherein the service performance requirement file is used for explaining performance parameter requirements corresponding to services;

the dispatching center obtains index parameters of other servers;

calculating an adaptation server corresponding to each service according to a preset fuzzy algorithm, generating a relation table of the service and the adaptation server and storing the relation table;

when a service request is made, the dispatching center receives the service request, searches an adaptive server corresponding to the service, and skips the service to the server for loading.

Preferably, after the step of calculating an adaptation server corresponding to each service according to a preset fuzzy algorithm and generating a relationship table between the service and the adaptation server, the method further includes:

and the dispatching center distributes the stored relation table to each server.

Preferably, the performance parameters corresponding to the service include a hard disk space, a memory, a CPU performance, a required network bandwidth, a required network rate, a service range, and a service expected concurrency number.

Preferably, the server index parameter includes: bandwidth, time delay, hard disk space, memory space, CPU core number, CPU frequency, and the like.

Preferably, the step of calculating an adaptation server corresponding to each service according to a preset fuzzy algorithm and generating a relationship table between the service and the adaptation server includes:

starting from the first-order service of the service performance demand file, calculating an optimal server corresponding to the service by referring to the performance parameter demand corresponding to the service by using a preset fuzzy algorithm, and writing the optimal server serving as an association item of the service into a relation table;

and calculating the optimal servers corresponding to the other services to further improve the relation table until the optimal servers of all the services are calculated.

Preferably, the step of calculating the optimal server corresponding to the service by using a preset fuzzy algorithm with reference to the performance parameter requirement corresponding to the service includes:

the server is preset with the weight of each performance parameter requirement, the index parameters of each server are weighted and calculated by using the weight of each performance parameter requirement preset by the service to obtain the final weight score of each server, and the server with the highest weight score is set as the optimal server corresponding to the service.

Preferably, after the step of presetting the weight of each performance parameter requirement in the service, performing weighted calculation on the index parameter of each server by using the weight of each performance parameter requirement preset in the service to obtain the final weight score of each server, and setting the server with the highest weight score as the optimal server corresponding to the service, the method further includes:

and if the weight scores are the same, setting the servers with the same scores as the optimal servers corresponding to the services.

Preferably, when there is a service request, the scheduling center receives the service request, searches for an adaptive server corresponding to the service, and jumps to the server for loading, where the steps are as follows:

when a service is requested, the dispatching center receives the service request, searches the network address of the optimal server corresponding to the service in the relation table, and routes the service to the optimal server according to the network address;

and if two or more optimal servers exist, inquiring the states of the servers, and routing the service to the optimal server in an idle state.

An embodiment of the present invention further provides an intelligent distributed system, including:

the servers are connected with each other, and one server is a dispatching center;

a requirement module for placing a pre-compiled service performance requirement file in the dispatching center, wherein the service performance requirement file is used for explaining the performance parameter requirement corresponding to the service

The index module is used for the dispatching center to obtain index parameters of other servers;

the calculation module is used for calculating the adaptation servers corresponding to the services according to a preset fuzzy algorithm, generating a relation table of the services and the adaptation servers and storing the relation table;

and the service module is used for receiving the service request by the dispatching center when a service request is made, searching an adaptive server corresponding to the service, and skipping the service to the server for loading.

The present invention also provides a computer storage medium storing a computer program capable of being executed by at least one processor, the intelligent distributed system deployment method as described above

The intelligent distributed system deployment method, the intelligent distributed system deployment system and the storage medium provided by the embodiment of the invention can perform service performance requirement matching according to each performance index of the server and deploy the service with the highest matching degree to the corresponding server. The purpose of reasonably utilizing resources is achieved, and the utilization rate and the response speed of system resources are improved.

Drawings

FIG. 1 is a flow chart illustrating the steps of a method for deploying an intelligent distributed system according to the present invention;

FIG. 2 is an intelligent distributed apparatus of the present invention;

fig. 3 is a schematic diagram of a hardware structure of the computer device of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.

It should be understood that although the terms first, second, etc. may be used to describe the designated key in embodiments of the present invention, the designated key should not be limited to these terms. These terms are only used to distinguish specified keywords from each other. For example, the first specified keyword may also be referred to as the second specified keyword, and similarly, the second specified keyword may also be referred to as the first specified keyword, without departing from the scope of embodiments of the present invention.

The word "if" as used herein may be interpreted as referring to "at … …" or "when … …" or "corresponding to a determination" or "in response to a detection", depending on the context. Similarly, the phrase "if determined" or "if detected (a stated condition or time)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.

Referring to fig. 1, the present invention discloses a method for deploying an intelligent distributed system, including:

step S100 sets a plurality of servers to be connected to each other, wherein one server is a scheduling center.

The distributed system, namely a distributed server cluster, is a theoretical calculation model server form in which data and programs can be distributed to a plurality of servers instead of being located on one server, and geographic information data and database operations influenced by qi which are distributed dispersedly on a network are taken as research objects. The distributed system is beneficial to the distribution and optimization of tasks on the whole computer system, overcomes the defects of central host resource shortage and response bottleneck caused by the traditional centralized system, solves the problems of data isomerism, data sharing, complex operation and the like in the network GSIS, and is a great progress of the geographic information system technology. One of the main application scenarios of the distributed server cluster is to provide services for web applications. Web applications are the most important and widespread application form on the internet, and more applications adopt a B/S computing mode based on a Web server. As application complexity and users increase, the system capacity of web servers is facing significant challenges. The adoption of a large-capacity server instead of the original system causes huge expenses and cannot protect the original investment, and the method is not a real solution. The Web server clustering technology provides a good way for the continuous expansion of the system capacity of the Web server, and organizes a group of Web servers together in a certain form to form a single server influence so as to provide strong service capability. The system has high cost performance and good system reliability, and can be continuously expanded by adding servers, so that the web server clustering technology has become one of the key technologies for constructing large-scale web website systems.

The invention is mainly higher than the cluster system based on the distributor, namely a dispatching center, which can be set up from a server at the back end independently or can be established by a device specially, usually the distributor is located at the front end, the distributor at the front end is used as a proxy of the arriving request and is responsible for receiving all the arriving http requests in a centralized way, and the request of the client is distributed to the back end server in the cluster according to a specific load distribution and balance strategy.

Step S200 is to place a pre-compiled service performance requirement file in the scheduling center, where the service performance requirement file is used to describe a performance parameter requirement corresponding to a service.

For example, a game is just on line, most people need to register accounts in a webpage, a response server assigned to the registration function service needs to be high-performance, and needs to simultaneously respond to a great number of registration requests, the processing frequency requirement on the server is very high, and after the game runs for one or two years, the number of newly registered players generally becomes extremely small, so that the response server assigned to the registration function service can be low-frequency.

And step S300, the dispatching center acquires index parameters of other servers.

Specifically, there are two ways for the scheduling center to obtain the index parameters of each server. The first method is to add an automatic transmission instruction to the configuration information of each server, for example, a related command pull configuration notification IP (dispatch center) is added to the server a, and at this time, each server will transmit its index parameter to the dispatch center. The second mode is that because the server platform systems are the same, the index parameters of the servers are pulled by using the shell command, which is faster than the first mode.

Step S400, according to a preset fuzzy algorithm, calculating an adaptation server corresponding to each service, generating a relation table of the service and the adaptation server, and storing the relation table.

Specifically, a corresponding weight value is preset for each performance index parameter, and the weight value occupied by the performance index parameter correspondingly set for each service is different due to different requirements of each service, which is as follows as an example:

service name	CPU frequency weight ratio	CPU core number weight ratio
			Account registration	0.3	0.8
Account number charging	0.6	0.3

Wherein, a fractional interval is preset for the CPU frequency and the CPU core number, and the CPU frequency fractional interval is as follows

Interval(s)	CPU frequency	Score of
			1	2.8GHZ-3.0GHZ	2
2	3.0GHZ-3.2GHZ	4
			3	3.2GHZ-3.4GHZ	6
4	3.4GHZ or above	10

The CPU core number fraction interval is as follows:

if the CPU frequency of the server a is 3.0GHZ, the core number is 4 cores, the CPU frequency of the server B is 4GHZ, and the core number is 2 cores, then for the account registration service, the score weighted by the server a is 4 × 0.3+4 × 0.8 ═ 4.4 points, and the score weighted by the server B is 10 × 0.3+2 × 0.8 ═ 4.6 points, then the server B is the optimal server for the account registration service, and the IP address of the server B is used as the jump address of the account registration service, and is stored in association as the association item, and the account recharging service is the same as the server B. And sorting all the correlated data to generate a relation table.

Step S500, when there is a service request, the scheduling center receives the service request, searches for an adaptive server corresponding to the service, and jumps to the server for loading.

Specifically, when there is a service request, the scheduling center receives the service request, searches the relationship table formed in step S400, searches the optimal server corresponding to the service, and jumps to the server for loading and processing.

The intelligent distributed system deployment method provided by the embodiment of the invention can carry out service performance requirement matching according to each performance index of the server, and deploy the service with the highest matching degree to the corresponding server. The purpose of reasonably utilizing resources is achieved, and the utilization rate and the response speed of system resources are improved.

Optionally, after the step of calculating an adaptation server corresponding to each service according to a preset fuzzy algorithm and generating a relationship table between the service and the adaptation server, the method further includes:

Specifically, the storage relationship table of the general server is placed in the github, and the relevant command line is configured by the scheduling center and issued to all servers to pull the storage relationship table on the github, and exemplary codes are as follows:

pull name from githu

Optionally, the performance parameters corresponding to the service include a hard disk space, a memory, a CPU performance, a required network bandwidth, a required network rate, a service range, and a service expected concurrency number.

Optionally, the server index parameter includes: bandwidth, time delay, hard disk space, memory space, CPU core number, CPU frequency, and the like.

Optionally, the step S400 of calculating an adaptation server corresponding to each service according to a preset fuzzy algorithm, and generating a relationship table between the service and the adaptation server includes:

step S410, starting from the first-order service of the service performance demand file, calculating an optimal server corresponding to the service by referring to the performance parameter demand corresponding to the service by using a preset fuzzy algorithm, and writing the optimal server serving as an association item of the service into a relation table;

step S420 calculates the optimal servers corresponding to the other services to further improve the relationship table until the optimal servers of all the services are calculated.

Optionally, the step of calculating the optimal server corresponding to the service by using a preset fuzzy algorithm with reference to the performance parameter requirement corresponding to the service includes:

Optionally, after the step of presetting the weight of each performance parameter requirement in the service, performing weighted calculation on the index parameter of each server by using the weight of each performance parameter requirement preset in the service to obtain the final weight score of each server, and setting the server with the highest weight score as the optimal server corresponding to the service, the method further includes:

Optionally, in step S500, when there is a service request, the scheduling center receives the service request, searches for an adaptive server corresponding to the service, and jumps to the server for loading, where the step is as follows:

step S510, when there is a service request, the dispatching center receives the service request, searches the network address of the optimal server corresponding to the service in the relation table, and routes the service to the optimal server according to the network address;

in step S520, if two or more optimal servers exist, the states of the servers are queried, and the service is routed to the optimal server in the idle state.

Referring to fig. 2, the present invention further provides an intelligent distributed system, including:

Please refer to fig. 3, which is a schematic diagram of a hardware architecture of a computer device according to an embodiment of the present invention. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a preset or stored instruction. The computer device 2 may be a personal computer, a tablet computer, a mobile phone, a smartphone, or a rack server, a blade server, a tower server, or a cabinet server (including an independent server or a server cluster composed of a plurality of servers), and the like, and is configured to provide a virtual client. As shown, the computer device 2 includes, but is not limited to, at least, a pass-through systemA bus interconnecting the memory 21, the processor 22, the network interface 23, and intelligent distributed system20, wherein:

in this embodiment, the memory 21 includes at least one type of computer-readable storage medium including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (Secure Digital) SD Card, a Flash memory Card (Flash Card), etc. provided on the computer device 20, and of course, the memory 21 may also include both an internal storage unit and an external storage device of the computer device 2. In this embodiment, the memory 21 is used for storing an operating system and various application software installed in the computer device 2, for example Intelligent distributed system of air conditioner20, etc. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.

Processor 22 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data Processing chip in some embodiments. The processor 22 is typically used to control the overall operation of the computer device 2. In this embodiment, the processor 22 is used for executing program codes stored in the memory 21 or processing data, such as executing Intelligent distributed system20 to realize Intelligent distributed typeThe method of (1).

The network interface 23 may comprise a wireless network interface or a limited network interface, and the network interface 23 is typically used for establishing a communication connection between the computer device 2 and other electronic apparatuses. For example, the network interface 23 is used to connect the computer device 2 with an external terminal necklace, establish a data transmission channel and a communication connection between the computer device 2 and an external interrupt, and the like via a network. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.

In the present embodiment, the data stored in the memory 21 Intelligent distributed system20 may also be divided into one or more program modules that are stored in memory 21 and executed by one or more processors, such as processor 22 in this embodiment, to carry out the invention.

In addition, the present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor implements a corresponding function. The computer-readable storage medium of the present embodiment is used for storage Intelligent distributed system20, when executed by a processor, implement the invention Intelligent distributed typeA method.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.

The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims

1. A method for deploying an intelligent distributed system, comprising:

the dispatching center obtains index parameters of other servers;

2. The intelligent distributed system deployment method of claim 1, wherein after the step of calculating the adaptation servers corresponding to the services according to a preset fuzzy algorithm and generating the relationship table of the services and the adaptation servers, the method further comprises:

3. The intelligent distributed system deployment method of claim 1, wherein the performance parameters corresponding to the service include hard disk space, memory, CPU performance, required network bandwidth, required network rate, service range, and expected concurrency of services.

4. The intelligent distributed system deployment method of claim 1, wherein the server index parameters comprise: bandwidth, time delay, hard disk space, memory space, CPU core number, CPU frequency, and the like.

5. The intelligent distributed system deployment method of claim 1, wherein the step of calculating the adapted servers corresponding to the services according to a preset fuzzy algorithm and generating the relationship table of the services and the adapted servers comprises:

6. The intelligent distributed system deployment method of claim 5, wherein the step of computing the optimal server corresponding to the service with reference to the performance parameter requirements corresponding to the service using a pre-set fuzzy algorithm comprises:

7. The intelligent distributed system deployment method of claim 6, wherein the service is preset with weights of performance parameter requirements, and the step of performing weighted calculation on the index parameters of the servers by using the weights of the performance parameter requirements preset by the service to obtain final weight scores of the servers and setting the server with the highest weight score as the optimal server corresponding to the service further comprises:

8. The intelligent distributed system deployment method of claim 1, wherein when there is a service request, the dispatch center receives the service request, searches for an adaptive server corresponding to the service, and jumps to the server for loading, and the step of:

9. An intelligent distributed system, comprising:

10. A computer storage medium, characterized in that it stores a computer program that can be executed by at least one processor to perform the intelligent distributed system deployment method of claims 1 to 8.