CN107276855A - A kind of automatically-monitored method of server stress based on linux system - Google Patents

Abstract

The invention discloses an automatic monitoring method for server pressure based on a Linux system, which comprises the following steps: editing the server pressure monitoring program; setting the running times and running interval time of the server pressure monitoring program; The command is integrated into the shell script; run the shell script to obtain the status data of the current system; output the status of Turbo and EIST. The present invention monitors the CPU operating state in real time by running the server pressure monitoring program to judge the current operating pressure of the server, and displays it in real time, and monitors the current health state of the system by checking the response system log at a certain frequency, thereby realizing unattended and achieving The purpose of automatic server pressure monitoring.

Description

A method for automatic monitoring of server pressure based on Linux system

technical field

The invention relates to an automatic monitoring method for server pressure based on a Linux system, belonging to the technical field of server monitoring.

Background technique

With the continuous improvement of the information society, informatization has made great progress in all walks of life in society, and the progress of informatization has made the use of computers more popular in society.

With the wide application of informatization and digitization, the business of the background server has also shown an exponential growth, which ensures that the server can run for a long time under high-load work pressure, and the quality requirements of the server are more stringent. During the operation of the server, the CPU As the core part of server computing, the load pressure of general CPU operation can also be regarded as the load pressure of the entire server during operation. The real-time frequency and load status of the core during the general CPU operation are the performance display of the CPU pressure.

Therefore, during the development and testing process, the server system stress test is an essential item, but there is no method for performing a stress test on the server system at present.

Contents of the invention

In view of the shortcomings of the above technologies, an embodiment of the present invention provides an automatic monitoring method for server pressure based on a Linux system, which can realize automatic monitoring of the state of the server system.

The technical scheme that the embodiment of the present invention solves its technical problem to take is:

A method for automatically monitoring server pressure based on a Linux system, comprising the following steps:

Edit server pressure monitoring program;

Set the running times and running interval of the server pressure monitoring program;

Write a shell script and integrate the commands of the server pressure monitoring program into the shell script;

Run the shell script to obtain the status data of the current system;

Output the status of Turbo and EIST.

Optionally, the server pressure monitoring program includes at least the following processes:

The process of obtaining CPU information and CPU operation mode under the system;

The process of obtaining the operating frequency of the CPU under the system;

The process of outputting frequency information;

The process of outputting CPU core information;

The process of outputting the CPU overclocking status;

The process of outputting the CPU energy-saving state.

Optionally, the running times of the server pressure monitoring program is 100-10000 times.

Optionally, the running interval of the server pressure monitoring program is 8-20 seconds.

Optionally, the status data of the current system is obtained by reading the /proc/cpuinfo file under the system in real time using a server pressure monitoring program.

Optionally, the running process of the shell script includes the following steps:

Run the detection program to detect system information;

CPU core frequency information storage file;

Annotate the log information;

Count the duplicates;

Check the number of running times entered by the user, if there is input running times data, call the return value of the total running times program, otherwise use the default number of times;

Check the user input running time interval data, if there is input running time interval data, call the return value of the main program running time interval program, otherwise use the default time;

Read the proc/cpuinfo file to obtain information about the number of CPU cores;

Read the proc/cpuinfo file to obtain CPU model name information and CPU frequency information,

If the CPU frequency return value is 1, the output acquisition fails;

Obtain the Turbo and EIST status of the CPU obtained by the system from the BIOS;

Record CPU standard frequency;

Record the number of CPU cores;

Record CPU Turbo status;

Record CPU EIST status;

Record CPU Hyper status;

Run the server pressure monitoring program cyclically according to the running times data and running time interval data, and finally output the current pressure status of the system and check the system log information.

Optionally, the detection procedures include the following procedures:

A program to obtain CPU information and CPU operating mode in the system;

A program to obtain the operating frequency of the CPU in the system;

Programs that output frequency information;

A program that outputs CPU core information;

A program that outputs the CPU overclocking status;

A program that outputs the CPU power saving status.

Optionally, the states of Turbo and EIST are obtained through the SCELNX_64 output bios option, and output in text form.

The technical solutions provided by the embodiments of the present invention have the following beneficial effects:

The scheme of the embodiment of the present invention is based on the Linux operating system, uses shell scripts, and obtains the nominal frequency in the model name by reading /proc/cpuinfo under the system in real time, and obtains each core dynamic frequency in cpu MHz, and outputs the bios option through SCELNX_64 to obtain Turbo and The state of EIST monitors the negative pressure state of the system through the real-time changes of these parameters, and outputs the state data in text form, which can realize the automatic monitoring of the server system state, avoid the negligence caused by manual monitoring, and realize the automatic server pressure test , greatly saving labor costs and time costs, and can be completed without the operator having too much technical experience.

The solution of the embodiment of the present invention is to monitor the CPU operating status in real time by running the server pressure monitoring program to judge the current operating pressure of the server and display it in real time, and to monitor the current health status of the system by checking the response system log at a certain frequency, thereby realizing unattended operation And can achieve the purpose of server pressure automatic monitoring.

Description of drawings

The present invention will be described below in conjunction with the accompanying drawings.

FIG. 1 is a schematic flowchart of a method for automatically monitoring server pressure based on a Linux system provided by an embodiment of the present invention.

detailed description

In order to clearly illustrate the technical features of this solution, the present invention will be described in detail below through specific implementation modes and in conjunction with the accompanying drawings. The following disclosure provides many different embodiments or examples for implementing different structures of the present invention. To simplify the disclosure of the present invention, components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and/or letters in different instances. This repetition is for the purpose of simplicity and clarity and does not in itself indicate a relationship between the various embodiments and/or arrangements discussed. It should be noted that components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and processes are omitted herein to avoid unnecessarily limiting the present invention.

FIG. 1 is a schematic flowchart of a method for automatically monitoring server pressure based on a Linux system provided by an embodiment of the present invention.

Referring to Fig. 1, a kind of server pressure automatic monitoring method based on Linux system of the embodiment of the present invention, it comprises the following steps:

S1, edit the server pressure monitoring program; the server pressure monitoring program includes the following processes: the process of obtaining CPU information and CPU operating mode under the system, the process of obtaining the CPU operating frequency under the system, the process of outputting frequency information, and the process of outputting CPU core information process, the process of outputting the CPU overclocking state, and the process of outputting the CPU energy saving state.

S2, setting the running times and running intervals of the server pressure monitoring program; the running times of the server pressure monitoring program is preferably set to 100-10000 times, and its default value is 1000 times; the running time interval of the server pressure monitoring program is preferably The setting is 8~20S, and the default value is 10S.

S3, write a shell script, and integrate the commands of the server pressure monitoring program into the shell script.

S4, run the shell script, use the server pressure monitoring program to read the /proc/cpuinfo file under the system in real time to obtain the status data of the current system.

The /proc/cpuinfo file contains sections of data for each processor on the system.

There are 6 entries in the proc/cpuinfo description that apply to multi-core and hyperthreading (HT) technology checks: processor, vendor id, physical id, siblings, core id, and cpu cores; the processor entry includes a unique identifier for this logical processor , the physical id entry contains a unique identifier for each physical package, the coreid entry holds a unique identifier for each core, the siblings entry lists the number of logical processors located in the same physical package, and the cpu cores entry contains The number of cores in .

S5, output the state of Turbo and EIST. The states of Turbo and EIST are obtained through the SCELNX_64 output bios option, and are output in text form.

Optionally, the running process of the shell script includes the following steps:

Run the detection program to detect system information;

CPU core frequency information storage file;

Annotate the log information;

Count the duplicates;

Check the number of running times entered by the user, if there is input running times data, call the return value of the total running times program, otherwise use the default number of times;

Check the user input running time interval data, if there is input running time interval data, call the return value of the main program running time interval program, otherwise use the default time;

Read the proc/cpuinfo file to obtain information about the number of CPU cores;

Read the proc/cpuinfo file to obtain CPU model name information and CPU frequency information,

If the CPU frequency return value is 1, the output acquisition fails;

Obtain the Turbo and EIST status of the CPU obtained by the system from the BIOS;

Record CPU standard frequency;

Record the number of CPU cores;

Record CPU Turbo status;

Record CPU EIST status;

Record CPU Hyper status;

Run the server pressure monitoring program cyclically according to the running times data and running time interval data, and finally output the current pressure status of the system and check the system log information.

Described detection program can be encapsulated in editable Toolbox tool box, realizes the inspection to system BMClog, system firewall, system log information etc. by the Toolbox tool box of editing, and detection program comprises following program:

A program to obtain CPU information and CPU operating mode in the system;

A program to obtain the operating frequency of the CPU in the system;

Programs that output frequency information;

A program that outputs CPU core information;

A program that outputs the CPU overclocking status;

A program that outputs the CPU power saving status.

The embodiment of the present invention judges the current operating pressure of the server by monitoring the operating state of the CPU in real time, and displays it in real time, and monitors the current health status of the system by checking the response system log at a certain frequency, so as to realize unattended and automatic monitoring of server pressure. The setting of program running times and running time interval can be realized through the Total Times and Single Sleep Time defined in the main program, where total times is used to define the total running times of the main program, and Single Sleep Time is used to set the time interval for running the main program .

The whole process of the embodiment of the present invention mainly utilizes the shell (providing the user interface) script to read /proc/cpuinfo under the system in real time, obtain the nominal frequency in the model name, obtain each core dynamic frequency in cpu MHz, and output bios through SCELNX_64 option to get the status of Turbo and EIST. , monitor the negative pressure status of the system through the real-time changes of these parameters, and output the status data in text form, which realizes the automatic monitoring of the server system status and avoids the negligence caused by manual monitoring.

The above is only a preferred embodiment of the present invention. For those of ordinary skill in the art, without departing from the principle of the present invention, some improvements and modifications can also be made, and these improvements and modifications are also considered as the present invention. protection scope of the invention.

Claims (8)

1. a kind of server pressure automatic monitoring method based on Linux system, it is characterized in that, comprises the following steps: Edit server pressure monitoring program; Set the running times and running interval of the server pressure monitoring program; Write a shell script and integrate the commands of the server pressure monitoring program into the shell script; Run the shell script to obtain the status data of the current system; Output the status of Turbo and EIST. 2. a kind of server pressure automatic monitoring method based on Linux system according to claim 1, is characterized in that, described server pressure monitoring program at least comprises the following process: The process of obtaining CPU information and CPU operation mode under the system; The process of obtaining the operating frequency of the CPU under the system; The process of outputting frequency information; The process of outputting CPU core information; The process of outputting the CPU overclocking status; The process of outputting the CPU energy-saving state. 3 . The method for automatic monitoring of server pressure based on Linux system according to claim 1 , characterized in that, the running times of the server pressure monitoring program are 100 to 10,000 times. 4 . 4 . The method for automatically monitoring server pressure based on Linux system according to claim 1 , wherein the running interval of the server pressure monitoring program is 8-20 seconds. 5. A kind of server pressure automatic monitoring method based on Linux system according to claim 1, it is characterized in that, the state data of described current system utilizes server pressure monitoring program to read the /proc/cpuinfo file under the system in real time to obtain. 6. a kind of server pressure automatic monitoring method based on Linux system according to claim 1, is characterized in that, the operation process of described shell script comprises the following steps: Run the detection program to detect system information; CPU core frequency information storage file; Annotate the log information; Count the duplicates; Check the number of running times entered by the user, if there is input running times data, call the return value of the total running times program, otherwise use the default number of times; Check the user input running time interval data, if there is input running time interval data, call the return value of the main program running time interval program, otherwise use the default time; Read the proc/cpuinfo file to obtain information about the number of CPU cores; Read the proc/cpuinfo file to obtain CPU model name information and CPU frequency information, If the CPU frequency return value is 1, the output acquisition fails; Obtain the Turbo and EIST status of the CPU obtained by the system from the BIOS; Record CPU standard frequency; Record the number of CPU cores; Record CPU Turbo status; Record CPU EIST status; Record CPU Hyper status; Run the server pressure monitoring program cyclically according to the running times data and running time interval data, and finally output the current pressure status of the system and check the system log information. 7. a kind of server pressure automatic monitoring method based on Linux system according to claim 6, is characterized in that, described detection program comprises following program: A program to obtain CPU information and CPU operating mode in the system; A program to obtain the operating frequency of the CPU in the system; Programs that output frequency information; A program that outputs CPU core information; A program that outputs the CPU overclocking status; A program that outputs the CPU power saving status. 8. according to a kind of automatic monitoring method of server pressure based on Linux system according to any one of claim 1-7, it is characterized in that, the state of described Turbo and EIST is obtained by SCELNX_64 output bios option, and output in text form .