WO2022257304A1 - Server tuning method, system and apparatus - Google Patents

Abstract

The present application discloses a server tuning method, system and apparatus. The method comprises: setting in advance a performance tuning policy for a target component within a server which affects server performance; acquiring performance parameters of the target component, and automatically determining whether the performance parameters are within a target parameter range of the target component; if not, then automatically performing performance tuning on the target component according to the performance tuning policy. Hence, in the present application, when the performance parameters of a target component is not within a target parameter range of the target component, performance tuning can be automatically performed on the target component, so as to improve the overall performance of the server. The operation speed of said type of automatic tuning means is relatively fast, allowing the real-time performance of whole server tuning to be relatively good.

Description

A server tuning method, system and device

This application claims the priority of the Chinese patent application with the application number 202110642462.3 and the title of the invention "a server optimization method, system and device" submitted to the China Patent Office on June 9, 2021, the entire contents of which are incorporated by reference In this application.

technical field

The present application relates to the field of server performance optimization, in particular to a server optimization method, system and device.

Background technique

In the server field, there are high requirements for business processing performance and user experience. At present, in order to improve business processing performance and user experience, it is usually necessary to improve the overall performance of the server, and in order to improve the overall performance of the server, it is usually necessary to perform system performance tuning on the entire server.

In the prior art, the system performance tuning of the whole server is usually manually tuned by engineers. For example, when the memory of the server is too high, unnecessary processes in the system are manually closed. However, this manual tuning method The operation speed is slow, resulting in poor real-time performance of server tuning.

Therefore, how to provide a solution to the above technical problems is a problem that those skilled in the art need to solve at present.

Contents of the invention

The purpose of this application is to provide a server tuning method, system and device, which can automatically perform performance tuning on the target component when the performance parameters of the target component are not within the target parameter range of the target component, so as to improve the overall performance of the server. Performance, the operation speed of this automatic tuning method is faster, which makes the real-time performance of the whole server tuning better.

In order to solve the above technical problems, the application provides a server tuning method, including:

Pre-set performance tuning strategies for target components in the server that affect server performance;

Obtaining the performance parameters of the target component, and automatically judging whether the performance parameters are within the target parameter range of the target component;

If not, automatically perform performance tuning on the target component according to the performance tuning policy.

Preferably, said target component comprises a central processing unit of said server;

Correspondingly, obtain the performance parameter of the target component, and automatically judge whether the performance parameter is within the target parameter range of the target component; if not, automatically perform performance on the target component according to the performance tuning strategy The tuning process includes:

Acquiring a first usage rate of the central processing unit, and judging whether the first usage rate is within the target range of the first usage rate of the central processing unit;

If not, adjusting the first usage rate within the first usage rate target range by controlling the number of received requests of the central processing unit.

Preferably, the receiving request of the central processor includes http request and non-http request;

Correspondingly, the process of adjusting the first utilization rate within the target range of the first utilization rate by controlling the number of received requests of the central processing unit includes:

By adjusting the TCP protocol parameters of the system, the number of non-http requests received by the central processor is controlled, and by adjusting the TCP protocol parameters and IP protocol parameters of the system, the number of http requests received by the central processor is controlled, so that the A first usage adjustment is within the first usage target range.

Preferably, the server tuning method also includes:

Pre-set by adjusting the TCP protocol parameters and IP protocol parameters of the system, so that the number of requests processed by the central processing unit at the same time is the largest and the hill climbing algorithm that the first utilization rate is within the first utilization rate target range;

Correspondingly, by adjusting the TCP protocol parameters of the system, the number of non-http requests received by the central processor is controlled, and by adjusting the TCP protocol parameters and IP protocol parameters of the system, the number of http requests received by the central processor is controlled, so that The process of adjusting the first usage rate within the target range of the first usage rate includes:

Using the hill-climbing algorithm, gradually adjust the values of the TCP protocol parameters and the IP protocol parameters until the maximum number of requests processed by the central processing unit at the same time is found, and the first usage rate is at the first usage rate. The optimal value within the rate target range.

Preferably, the target component also includes memory of the server;

Correspondingly, obtain the performance parameter of the target component, and automatically judge whether the performance parameter is within the target parameter range of the target component; if not, automatically perform performance on the target component according to the performance tuning strategy The process of tuning processing also includes:

Obtaining the second usage rate of the memory, and judging whether the second usage rate is within the target range of the second usage rate of the memory;

If not, adjusting the second utilization ratio within the second utilization ratio target range by closing the system process occupying the memory.

Preferably, the process of adjusting the second utilization rate within the target range of the second utilization rate by closing the system process occupying the memory includes:

Sort the system processes from large to small according to the space occupied by memory;

Starting from the system process that takes up the largest memory space, determine whether each system process is related to the business currently running on the server;

If there is a target system process unrelated to the service currently running on the server, shut down the target system process until the second usage rate is adjusted to be within the second usage rate target range.

Preferably, the target component also includes a network component of the server;

Correspondingly, obtain the performance parameter of the target component, and automatically judge whether the performance parameter is within the target parameter range of the target component; if not, automatically perform performance on the target component according to the performance tuning strategy The process of tuning processing also includes:

Obtaining the bandwidth occupancy rate of the network component, and judging whether the bandwidth occupancy rate is within the target range of the bandwidth occupancy rate of the network component;

If not, the bandwidth occupancy rate is adjusted within the bandwidth occupancy rate target range by replacing a network component with a larger bandwidth.

Preferably, the target component also includes a disk of the server;

Correspondingly, obtain the performance parameter of the target component, and automatically judge whether the performance parameter is within the target parameter range of the target component; if not, automatically perform performance on the target component according to the performance tuning strategy The process of tuning processing also includes:

Acquiring a third usage rate of the disk, and judging whether the third usage rate is within the target range of the third usage rate of the disk;

If not, adjusting the third usage rate within the target range of the third usage rate by upgrading the disk drive of the server or adjusting the RAID mode of the disk to a non-backup storage mode.

In order to solve the above technical problems, the present application also provides a server tuning system, including:

The preset module is used to pre-set performance tuning strategies for target components affecting server performance in the server;

A judging module, configured to obtain the performance parameters of the target component, and automatically judge whether the performance parameters are within the target parameter range of the target component; if not, execute the tuning module;

An tuning module, configured to automatically perform performance tuning on the target component according to the performance tuning strategy;

Wherein, the target component includes a central processing unit of the server;

Correspondingly, the judging module is specifically configured to obtain the first usage rate of the central processing unit, and judge whether the first usage rate is within the target range of the first usage rate of the central processing unit; if not, then Execute the tuning module;

The tuning module is specifically configured to adjust the first utilization ratio within the first utilization ratio target range by controlling the number of received requests of the central processing unit.

In order to solve the above technical problems, the present application also provides a server tuning device, including:

memory for storing computer programs;

A processor, configured to implement the steps of any one of the above server tuning methods when executing the computer program.

The present application provides a server tuning method, which pre-sets a performance tuning strategy for a target component in the server that affects server performance; obtains performance parameters of the target component, and automatically determines whether the performance parameter is within the target parameter range of the target component; If not, automatically perform performance tuning on the target component according to the performance tuning strategy. It can be seen that, when the performance parameters of the target component are not within the target parameter range of the target component, the application can automatically perform performance tuning processing on the target component to improve the overall performance of the server, and the operation speed of this automatic tuning method is relatively fast , so that the real-time performance of server tuning is better.

The present application also provides a server optimization system and device, which have the same beneficial effect as the above optimization method.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the prior art and the accompanying drawings that need to be used in the embodiments. Obviously, the accompanying drawings in the following description are only some of the present application. Embodiments, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

FIG. 1 is a flowchart of a server tuning method provided in an embodiment of the present application;

FIG. 2 is a specific schematic diagram of a server tuning method provided in an embodiment of the present application;

FIG. 3 is an optimization logic diagram of a central processing unit of a server provided in an embodiment of the present application;

FIG. 4 is a logic diagram for tuning the memory of a server provided in an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a server tuning system provided by an embodiment of the present application.

Detailed ways

The core of this application is to provide a server tuning method, system and device, which can automatically perform performance tuning on the target component when the performance parameters of the target component are not within the target parameter range of the target component, so as to improve the overall performance of the server. Performance, the operation speed of this automatic tuning method is faster, which makes the real-time performance of the whole server tuning better.

In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

Please refer to FIG. 1 . FIG. 1 is a flowchart of a server tuning method provided by an embodiment of the present application.

The server tuning methods include:

Step S1: Pre-set performance tuning strategies for target components in the server that affect server performance.

Specifically, this application first determines the components that affect the performance of the server (called target components) from the components in the server according to the working principles of the components in the server, and then sets the performance for the target components to guide the performance tuning of the target components. Tuning strategy to facilitate subsequent optimization of the performance of the target component.

Step S2: Obtain the performance parameter of the target component, and automatically judge whether the performance parameter is within the target parameter range of the target component; if not, execute step S3. Step S3: automatically perform performance tuning processing on the target component according to the performance tuning policy.

Specifically, during the working process of the server, the application obtains the performance parameters of the target component in real time, which can be monitored by monitoring tools, and then automatically compares the performance parameters of the target component with the target parameter range of the target component to automatically determine the target component Whether the performance parameter of the target component is within the target parameter range of the target component, if the performance parameter of the target component is within the target parameter range of the target component, it means that the performance of the target component is better and no optimization is needed; If it is within the parameter range, it means that the performance of the target component is not good enough, and the performance of the target component needs to be optimized, then the performance tuning process of the target component will be automatically performed according to the performance tuning strategy set in advance for the target component, so as to optimize the performance of the target component, and then Improve the overall performance of the server.

The present application provides a server tuning method, which pre-sets a performance tuning strategy for a target component in the server that affects server performance; obtains performance parameters of the target component, and automatically determines whether the performance parameter is within the target parameter range of the target component; If not, automatically perform performance tuning on the target component according to the performance tuning policy. It can be seen that, when the performance parameters of the target component are not within the target parameter range of the target component, the application can automatically perform performance tuning processing on the target component to improve the overall performance of the server, and the operation speed of this automatic tuning method is relatively fast , so that the real-time performance of server tuning is better.

On the basis of above-mentioned embodiment:

Please refer to FIG. 2 . FIG. 2 is a specific schematic diagram of a server tuning method provided in an embodiment of the present application.

As an optional embodiment, the target component includes a central processing unit of a server;

Correspondingly, obtain the performance parameters of the target component, and automatically judge whether the performance parameters are within the target parameter range of the target component; if not, automatically perform the performance tuning process on the target component according to the performance tuning strategy, including:

Acquiring the first utilization rate of the central processing unit, and judging whether the first utilization rate is within the target range of the first utilization rate of the central processing unit;

If not, the first usage rate is adjusted within the first usage rate target range by controlling the number of received requests of the central processing unit.

Specifically, the target component that affects server performance in this application includes the central processing unit (CPU) of the server, and then the tuning logic of the central processor is: to obtain the utilization rate of the central processing unit (called the first utilization rate), which can be specifically Use the top command (a server command) to detect the overall usage of the CPU, get the first usage rate of the CPU, and then judge whether the first usage rate of the CPU is within the target range of the first usage rate of the CPU (such as 0-80%), if the first utilization rate of the central processing unit is within the target range of the first utilization rate of the central processing unit, it indicates that the performance of the central processing unit is better and no optimization is needed; if the first utilization rate of the central processing unit The utilization rate is not within the target range of the first utilization rate of the CPU (more than 80%), indicating that the performance of the CPU is not good enough, and the performance of the CPU needs to be optimized, then it should be tuned according to the performance set in advance for the CPU The policy automatically performs performance tuning processing on the CPU, thereby optimizing the performance of the CPU.

More specifically, the performance tuning strategy set for the central processing unit is: adjust the first utilization rate of the central processing unit by controlling the number of received requests of the central processing unit, so as to adjust the first utilization rate of the central processing unit at the central processing unit The processor's first utilization rate target range, so as to realize the performance optimization of the central processing unit.

Please refer to FIG. 3 . FIG. 3 is a logic diagram for tuning a central processing unit of a server provided in an embodiment of the present application.

As an optional embodiment, the receiving request of the central processor includes http request and non-http request;

Correspondingly, the process of adjusting the first utilization rate within the target range of the first utilization rate by controlling the number of received requests of the central processing unit includes:

By adjusting the TCP protocol parameters of the system, the number of non-http requests received by the central processor is controlled, and by adjusting the TCP protocol parameters and IP protocol parameters of the system, the number of http requests received by the central processor is controlled to adjust the first usage rate at Within the first usage target range.

Specifically, the receiving request of the central processing unit of the present application includes http request (web page request) and non-http request (non-web page request), and non-http request needs to be provided to the center after TCP (Transmission Control Protocol, transmission control protocol) protocol analysis Processor processing, http requests need to be provided to the central processor for processing after being analyzed by the TCP protocol and IP (Internet Protocol) protocol, so by adjusting the TCP protocol parameters (net.ipv4.tcp_max_tw_buckets parameter) of the system, you can control The number of resolutions of non-http requests, so as to control the number of non-http requests provided to the central processor for processing, that is, to control the number of non-http requests received by the central processor; by adjusting the system's TCP protocol parameters and IP protocol parameters (net.ipv4.ip_local_port_range parameters), can control the number of http requests parsed, thereby controlling the number of http requests provided to the central processor for processing, that is, controlling the number of http requests received by the central processor, thereby controlling the number of received requests of the central processor, and then realizing the central processing The first utilization rate of the processor is adjusted to be within the first utilization rate target range of the CPU (specifically lower than 80%).

As an optional embodiment, the server tuning method also includes:

Preset the hill-climbing algorithm by adjusting the TCP protocol parameters and IP protocol parameters of the system, so that the number of requests processed by the central processor at the same time is the largest and the first utilization rate is within the target range of the first utilization rate;

Correspondingly, by adjusting the TCP protocol parameters of the system, the number of non-http requests received by the central processor is controlled, and by adjusting the TCP protocol parameters and IP protocol parameters of the system, the number of http requests received by the central processor is controlled, so that the first use The process of rate adjustment within the first utilization target range, including:

Using the hill-climbing algorithm, the values of the TCP protocol parameters and the IP protocol parameters are gradually adjusted until an optimal value is found that maximizes the number of requests processed by the central processing unit at the same time and the first utilization rate is within the target range of the first utilization rate.

Further, the application sets a hill-climbing algorithm in advance (the hill-climbing algorithm is a method of local selection, which adopts a heuristic method, and is an improvement to depth-first search, and uses feedback information to help generate a decision-making solution), and its specific algorithm The logic is: by adjusting the parameters of the TCP protocol and the IP protocol of the system, at the same time, the number of requests processed by the central processing unit is the largest, and the first utilization rate of the central processing unit is within the target range of the first utilization rate of the central processing unit.

Then the tuning logic of the central processing unit is specifically: obtain the first utilization rate of the central processing unit, and then judge whether the first utilization rate of the central processing unit is within the target range of the first utilization rate of the central processing unit, if the first utilization rate of the central processing unit The first utilization rate is not within the first utilization rate target range (0-80%) of the central processing unit, then utilizes the hill climbing algorithm to gradually adjust the values of the TCP protocol parameters and the IP protocol parameters of the system until the central processing unit is found to process simultaneously The number of requests is the largest, and the first utilization rate of the central processing unit is within the optimal value of the first utilization rate target range of the central processing unit, that is, under the condition that the central processing unit meets the utilization rate requirement (the first utilization rate of the central processing unit The utilization rate is less than 80%), and the performance of the CPU is optimized.

Please refer to FIG. 4 . FIG. 4 is a logic diagram for tuning a memory of a server provided in an embodiment of the present application.

As an optional embodiment, the target component also includes the memory of the server;

Correspondingly, the performance parameter of the target component is obtained, and it is automatically judged whether the performance parameter is within the target parameter range of the target component; if not, the process of automatically performing performance tuning on the target component according to the performance tuning strategy also includes:

Obtaining the second usage rate of the memory, and judging whether the second usage rate is within the target range of the second usage rate of the memory;

If not, the second utilization rate is adjusted within the second utilization rate target range by closing the system process that occupies the memory.

Specifically, the target component affecting the performance of the server in this application also includes the memory of the server, and the tuning logic of the memory is: to obtain the usage rate of the memory (called the second usage rate), which can be specifically obtained through the free-g command (a Server command) detects the overall usage of the memory, obtains the second usage of the memory, and then judges whether the second usage of the memory is within the target range (0-90%) of the second usage of the memory, if the second usage of the memory If the memory rate is within the target range of the second memory usage rate, it means that the memory performance is good and no optimization is needed; if the second memory usage rate is not within the second memory usage rate target range (more than 90%), it means that the memory performance is not enough Well, if the performance of the memory needs to be optimized, the memory performance is automatically tuned according to the performance tuning policy set in advance for the memory, so as to optimize the performance of the memory.

More specifically, the performance tuning strategy set for the memory is: adjust the second usage rate of the memory by shutting down the system process that occupies the memory, so as to adjust the second usage rate of the memory within the target range of the second usage rate of the memory , so as to achieve memory performance optimization.

As an optional embodiment, the process of adjusting the second usage rate within the target range of the second usage rate by closing the system process that occupies the memory includes:

Sort the system processes from large to small according to the space occupied by memory;

Starting from the system process that occupies the largest memory space, determine whether each system process is related to the business currently running on the server;

If there is a target system process unrelated to the service currently running on the server, the target system process is shut down until the second usage rate is adjusted to be within the second usage rate target range.

Specifically, the performance tuning strategy set for the memory is as follows: sort the system processes according to the space occupied by the memory from large to small, specifically through the ps aux --sort-rss|head command (a server command) Determine the size of the memory space occupied by the system processes, and sort the system processes in descending order of the space occupied by the memory space. It is understandable that closing the system process that occupies a larger memory space will reduce the second use of memory. The higher the rate, the more favorable it is, but shutting down the system processes related to the current business running on the server will affect the running of the server's current business. Therefore, this application starts with the system process that occupies the largest memory space, and sequentially judges whether each system process is related to the business currently running on the server. Related, if the currently judged system process is related to the business currently running on the server, the system process related to the current business running on the server will not be closed; The currently running business-independent system process (referred to as the target system process) ends and closes the system process until the second usage rate of the memory is adjusted to within the target range of the second usage rate of the memory (specifically, it may be lower than 80%).

As an optional embodiment, the target component also includes a network component of the server;

Correspondingly, the performance parameter of the target component is obtained, and it is automatically judged whether the performance parameter is within the target parameter range of the target component; if not, the process of automatically performing performance tuning on the target component according to the performance tuning strategy also includes:

Obtaining the bandwidth occupancy rate of the network component, and judging whether the bandwidth occupancy rate is within the target range of the bandwidth occupancy rate of the network component;

If not, the bandwidth occupancy rate is adjusted within the target range of the bandwidth occupancy rate by replacing a network component with a larger bandwidth.

Specifically, the target components affecting server performance of the present application also include network components of the server (such as switches, optical fibers, etc. that provide the server with a network environment), and then the tuning logic of the network components is: to obtain the bandwidth occupancy rate of the network components, Specifically, you can use the sar-n DEV command (a server command) to view the overall usage of network components, obtain the bandwidth occupancy rate of the network component, and then determine whether the bandwidth occupancy rate of the network component is within the target range of the bandwidth occupancy rate of the network component (0 -90%), if the bandwidth occupancy rate of the network component is within the target range of the bandwidth occupancy rate of the network component, it indicates that the performance of the network component is good and no optimization is required; if the bandwidth occupancy rate of the network component is not within the target bandwidth occupancy rate of the network component range (more than 90%), indicating that the performance of the network components is not good enough, and the performance of the network components needs to be optimized, then the performance of the network components will be automatically tuned according to the performance tuning strategy set in advance for the network components, thereby optimizing the network components performance.

More specifically, the performance tuning strategy set for the network component is: adjust the bandwidth occupancy rate of the network component by replacing a network component with a larger bandwidth (specifically, an alarm system can be triggered to prompt engineers to replace a network component with a larger bandwidth, or Design the server in advance to connect network components with different bandwidths. If the server does not meet the bandwidth occupancy requirements under the network components with smaller bandwidths (the bandwidth occupancy rate of the network components with smaller bandwidths is not within the bandwidth occupancy target range of this network component) , automatically switch to a network component with a larger bandwidth), so as to adjust the bandwidth occupancy rate of the network component within the target range of the bandwidth occupancy rate of the network component, so as to realize the performance optimization of the network component.

As an optional embodiment, the target component also includes a disk of the server;

Correspondingly, the performance parameter of the target component is obtained, and it is automatically judged whether the performance parameter is within the target parameter range of the target component; if not, the process of automatically performing performance tuning on the target component according to the performance tuning strategy also includes:

Obtaining the third usage rate of the disk, and judging whether the third usage rate is within the target range of the third usage rate of the disk;

If not, by upgrading the disk drive of the server or adjusting the RAID mode of the disk to a non-backup storage mode, the third utilization rate is adjusted within the target range of the third utilization rate.

Specifically, the target component affecting server performance in this application also includes the disk of the server, then the tuning logic of the disk is: obtain the third usage rate of the disk, specifically, the overall usage of the disk can be viewed through the iostat command (a server command) In this case, get the third usage rate of the disk, and then judge whether the third usage rate of the disk is within the target range (0-90%) of the third usage rate of the disk, if the third usage rate of the disk is within the third usage rate of the disk If it is within the target range, it means that the performance of the disk is good and there is no need to optimize it; if the third usage rate of the disk is not within the target range of the third usage rate of the disk (more than 90%), it means that the performance of the disk is not good enough, and the performance of the disk needs to be optimized. Then, according to the pre-set performance tuning strategy for the disk, the performance tuning process is automatically performed on the disk, thereby optimizing the performance of the disk.

More specifically, the performance tuning strategy set for the disk is: adjust the third utilization rate of the disk by upgrading the disk driver of the server, or adjust the RAID (Redundant Arrays of Independent Disks, disk array) mode of the disk to non-backup The storage mode is used to adjust the third usage ratio of the disk, so as to adjust the third usage ratio of the disk within the target range of the third usage ratio of the disk, so as to realize the performance optimization of the disk.

Please refer to FIG. 5 , which is a schematic structural diagram of a server tuning system provided by an embodiment of the present application.

This server tuning system includes:

The preset module 1 is used to pre-set performance tuning strategies for target components affecting server performance in the server;

Judgment module 2, used to obtain the performance parameters of the target component, and automatically determine whether the performance parameters are within the target parameter range of the target component; if not, then execute the tuning module 3;

The tuning module 3 is used to automatically perform performance tuning processing on the target component according to the performance tuning strategy;

Wherein, the target component includes the central processing unit of the server;

Correspondingly, the judging module 2 is specifically used to acquire the first utilization rate of the central processing unit, and judge whether the first utilization rate is within the target range of the first utilization rate of the central processing unit; if not, execute the tuning module 3;

The tuning module 3 is specifically configured to adjust the first utilization rate within the first utilization rate target range by controlling the number of received requests of the central processing unit.

For the introduction of the tuning system provided in this application, please refer to the above embodiments of the tuning method, and the present application will not repeat them here.

The present application also provides a server tuning device, including:

memory for storing computer programs;

The processor is configured to realize the steps of any one of the above server tuning methods when executing the computer program.

This application can use the domestic server CS5280H based on Haiguang CPU as a test prototype, deploy the server tuning device on the server CS5280H, and test the server tuning device to verify the tuning performance of the server tuning device.

For the introduction of the tuning device provided in the present application, please refer to the above-mentioned embodiments of the tuning method, and the present application will not repeat them here.

It should also be noted that in this specification, relative terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that these entities or operations There is no such actual relationship or order between the operations. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

The above description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (8)

1. A server tuning method, characterized in that, comprising:

   Pre-set performance tuning strategies for target components in the server that affect server performance;

   Obtaining the performance parameters of the target component, and automatically judging whether the performance parameters are within the target parameter range of the target component;

   If not, automatically perform performance tuning processing on the target component according to the performance tuning strategy;

   Wherein, the target component includes a central processing unit of the server;

   Correspondingly, obtain the performance parameter of the target component, and automatically judge whether the performance parameter is within the target parameter range of the target component; if not, automatically perform performance on the target component according to the performance tuning strategy The tuning process includes:

   Acquiring a first usage rate of the central processing unit, and judging whether the first usage rate is within the target range of the first usage rate of the central processing unit;

   If not, adjusting the first utilization rate within the first utilization rate target range by controlling the number of received requests of the central processing unit;

   The receiving request of the central processing unit includes http request and non-http request;

   Correspondingly, the process of adjusting the first utilization rate within the target range of the first utilization rate by controlling the number of received requests of the central processing unit includes:

   By adjusting the TCP protocol parameters of the system, the number of non-http requests received by the central processor is controlled, and by adjusting the TCP protocol parameters and IP protocol parameters of the system, the number of http requests received by the central processor is controlled, so that the A first usage adjustment is within the first usage target range.
2. The server tuning method according to claim 1, further comprising:

   Presetting the hill-climbing algorithm by adjusting the TCP protocol parameters and IP protocol parameters of the system, so that the number of requests processed by the central processing unit at the same time is the largest and the first utilization rate is within the target range of the first utilization rate;

   Correspondingly, by adjusting the TCP protocol parameters of the system, the number of non-http requests received by the central processor is controlled, and by adjusting the TCP protocol parameters and IP protocol parameters of the system, the number of http requests received by the central processor is controlled, so that The process of adjusting the first usage rate within the target range of the first usage rate includes:

   Using the hill-climbing algorithm, gradually adjust the values of the TCP protocol parameters and the IP protocol parameters until the maximum number of requests processed by the central processing unit at the same time is found, and the first usage rate is at the first usage rate. The optimal value within the rate target range.
3. The server tuning method according to claim 1, wherein the target component further comprises the memory of the server;

   Correspondingly, obtain the performance parameter of the target component, and automatically judge whether the performance parameter is within the target parameter range of the target component; if not, automatically perform performance on the target component according to the performance tuning strategy The process of tuning processing also includes:

   Obtaining the second usage rate of the memory, and judging whether the second usage rate is within the target range of the second usage rate of the memory;

   If not, adjusting the second utilization ratio within the second utilization ratio target range by closing the system process occupying the memory.
4. The server tuning method according to claim 3, wherein the process of adjusting the second utilization rate within the target range of the second utilization rate by closing the system process occupying the memory comprises:

   Sort the system processes from large to small according to the space occupied by memory;

   Starting from the system process that takes up the largest memory space, determine whether each system process is related to the business currently running on the server;

   If there is a target system process unrelated to the service currently running on the server, shut down the target system process until the second usage rate is adjusted to be within the second usage rate target range.
5. The server tuning method according to claim 1, wherein the target component further comprises a network component of the server;

   Correspondingly, obtain the performance parameter of the target component, and automatically judge whether the performance parameter is within the target parameter range of the target component; if not, automatically perform performance on the target component according to the performance tuning strategy The process of tuning processing also includes:

   Obtaining the bandwidth occupancy rate of the network component, and judging whether the bandwidth occupancy rate is within the target range of the bandwidth occupancy rate of the network component;

   If not, the bandwidth occupancy rate is adjusted within the bandwidth occupancy rate target range by replacing a network component with a larger bandwidth.
6. The server tuning method according to any one of claims 1-5, wherein the target component further comprises a disk of the server;

   Correspondingly, obtain the performance parameter of the target component, and automatically judge whether the performance parameter is within the target parameter range of the target component; if not, automatically perform performance on the target component according to the performance tuning strategy The process of tuning processing also includes:

   Acquiring a third usage rate of the disk, and judging whether the third usage rate is within the target range of the third usage rate of the disk;

   If not, adjusting the third usage rate within the target range of the third usage rate by upgrading the disk drive of the server or adjusting the RAID mode of the disk to a non-backup storage mode.
7. A server tuning system, characterized in that it comprises:

   The preset module is used to pre-set performance tuning strategies for target components affecting server performance in the server;

   A judging module, configured to obtain the performance parameters of the target component, and automatically judge whether the performance parameters are within the target parameter range of the target component; if not, execute the tuning module;

   An tuning module, configured to automatically perform performance tuning on the target component according to the performance tuning strategy;

   Wherein, the target component includes a central processing unit of the server;

   Correspondingly, the judging module is specifically configured to obtain the first usage rate of the central processing unit, and judge whether the first usage rate is within the target range of the first usage rate of the central processing unit; if not, then Execute the tuning module;

   The tuning module is specifically configured to adjust the first utilization rate within the target range of the first utilization rate by controlling the number of received requests of the central processing unit;

   The receiving request of the central processing unit includes http request and non-http request;

   Correspondingly, the process of adjusting the first utilization rate within the target range of the first utilization rate by controlling the number of received requests of the central processing unit includes:

   By adjusting the TCP protocol parameters of the system, the number of non-http requests received by the central processor is controlled, and by adjusting the TCP protocol parameters and IP protocol parameters of the system, the number of http requests received by the central processor is controlled, so that the A first usage adjustment is within the first usage target range.
8. A server tuning device, characterized in that it comprises:

   memory for storing computer programs;

   A processor, configured to implement the steps of the server tuning method according to any one of claims 1-6 when executing the computer program.

Images