CN110808869A - Method and system for testing influence of network cable length on network card performance - Google Patents

Method and system for testing influence of network cable length on network card performance Download PDF

Info

Publication number
CN110808869A
CN110808869A CN201910930776.6A CN201910930776A CN110808869A CN 110808869 A CN110808869 A CN 110808869A CN 201910930776 A CN201910930776 A CN 201910930776A CN 110808869 A CN110808869 A CN 110808869A
Authority
CN
China
Prior art keywords
server
network card
network
test
setting
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910930776.6A
Other languages
Chinese (zh)
Inventor
杨永峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Wave Intelligent Technology Co Ltd
Original Assignee
Suzhou Wave Intelligent Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Suzhou Wave Intelligent Technology Co Ltd filed Critical Suzhou Wave Intelligent Technology Co Ltd
Priority to CN201910930776.6A priority Critical patent/CN110808869A/en
Publication of CN110808869A publication Critical patent/CN110808869A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/50Testing arrangements
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00Arrangements for monitoring or testing data switching networks
    • H04L43/04Processing captured monitoring data, e.g. for logfile generation

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Mining & Analysis (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention discloses a test method and a test system for the influence of the network cable length on the network card performance.A same network card is installed on two servers, the two servers are connected in pair by the network cable with a certain length, and a test environment is configured; and running a network card performance detection command on the two servers to detect the performance of the network card. According to the scheme, the two servers are directly connected with each other through the network cable, the network card performance is tested under the network cables with different lengths, the influence of the network cable length on the network card performance is checked, and network card test cases are enriched.

Description

Method and system for testing influence of network cable length on network card performance
Technical Field
The invention relates to the field of network card performance testing, in particular to a method and a system for testing the influence of network cable length on network card performance.
Background
In server hardware testing, network card performance and stability testing are always important. The network card comprises an onboard network card and an external plug-in independent network card, and generally, the test of the network card generally comprises tests of basic functions, basic information identification, pressure, performance and the like. For the performance test, the test cases are few, and the general cases are to test whether the bandwidth of the network card reaches the standard, whether packet loss exists or not, and the like. The influence of the length of the network cable on the performance is rarely involved in the test case.
Disclosure of Invention
In order to solve the above problems, the present invention provides a method and a system for testing the influence of the network cable length on the network card performance, which can test the influence of different network cable lengths on the network card performance.
The technical scheme of the invention is as follows: a method for testing the influence of the network cable length on the network card performance comprises the following steps:
s11, installing the same network cards on the two servers, connecting the two servers in pair by using a network cable with a certain length, and configuring a test environment;
s12, running a network card performance detection command on the two servers, and performing performance detection on the network card;
and S13, recording and displaying the detection result.
Further, in step S11, configuring the test environment specifically includes:
the following steps are performed on one of the servers,
s11-1, setting IP address and subnet mask;
s11-2, setting the maximum MTU value of the network card;
s11-3, setting the server as an auxiliary machine and operating in a server mode.
Further, in step S11, configuring the test environment specifically further includes:
the following steps are performed on another server,
s11-4, setting IP address and subnet mask;
s11-5, setting the maximum MTU value of the network card;
s11-6, setting the size of the communication window and the communication time length between the server and another server.
Further, step S11 includes detecting whether two servers ping, and if so, executing the following steps.
Further, the step S12 specifically includes:
s12-1, executing the/netserver command on one server;
s12-2, executing a/netperf-H xxx, xxx-l 1800- - -m 512k command on another server; xxx is the server IP address.
Further, step S13 includes running an ethyool-S eth | grep-E "fail | error | drop | crc" command to indicate whether an error occurs.
Further, still include:
s14, connecting the two servers by using the network cables with other lengths to be tested, and repeating the steps S12 and S13.
The invention also provides a system for testing the influence of the network cable length on the network card performance, which comprises two servers, wherein the two servers are provided with the same network card and are connected by a network cable;
wherein, be provided with on the first server:
the first environment configuration module is used for configuring a server test environment;
the first test operation module runs the test command and tests the performance of the network card;
the first result recording module records and displays the test result;
the first error reporting display module runs an error reporting checking command and displays error reporting information;
the second server is provided with:
the second environment configuration module is used for configuring the server test environment;
and the second test operation module operates the test command and tests the performance of the network card.
Furthermore, a first environment configuration script is configured on the first server, and a second environment configuration script is configured on the second server;
the first environment configuration module configures a first server environment by running a first environment configuration script, and is specifically configured to:
setting an IP address and a subnet mask;
setting the maximum MTU value of the network card;
setting the server as an auxiliary machine and operating in a server mode;
the second environment configuration module configures the second server environment by running a second environment configuration script, and is specifically configured to:
setting an IP address and a subnet mask;
setting the maximum MTU value of the network card;
and setting the size of a communication window and the communication time length between the server and another server.
Further, the air conditioner is provided with a fan,
the first test operation module operates a/netserver test command to test the performance of the network card;
the second test operation module runs a/netperf-H xxx.xxx.xxx.xxx.xxx-l 1800- - -m 512k test command to test the performance of the network card; xxx is the server IP address.
According to the method and the system for testing the influence of the network cable length on the network card performance, the two servers are directly connected in parallel through the network cable, the network card performance is tested under the network cables with different lengths, the influence of the network cable length on the network card performance is checked, and network card test cases are enriched.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings by way of specific examples, which are illustrative of the present invention and are not limited to the following embodiments.
Example one
The embodiment provides a method for testing the influence of the network cable length on the network card performance, which includes the steps of directly connecting two servers by using network cables with different lengths, setting a static IP (Internet protocol), and testing the influence of the network cable length on the network card performance.
The method comprises the following steps:
s11, installing the same network cards on the two servers, connecting the two servers in pair by using a network cable with a certain length, and configuring a test environment;
s12, running a network card performance detection command on the two servers, and performing performance detection on the network card;
and S13, recording and displaying the detection result.
In step S11, configuring the test environment for configuring the relevant test on the two servers, where the two servers set the same parameter values, and some network cards may have problems if they are not reinitialized, such as different MTU values, or different parameters such as gro and lro, which may affect performance. Therefore, before testing, the network card driver is reinstalled once, and the MTU is set.
Executing the following steps on one server to configure the test environment:
s11-1, setting IP address and subnet mask;
s11-2, setting the maximum MTU value of the network card; it should be noted that, the maximum MTU values of different network cards are different, and the relevant MTU values are set according to the type of the test network card;
and S11-3, setting the server as an auxiliary machine, and operating in a server mode, namely setting the server as a Client terminal.
And correspondingly, the other server is an SUT testing end, and the following environment configuration is specifically carried out:
s11-4, setting IP address and subnet mask; it should be noted that the IP addresses of the two servers are in the same network segment;
s11-5, setting the maximum MTU value of the network card, which is the same as the MTU value set by the upper server;
s11-6, setting the size of the communication window and the communication time length between the server and another server, so that the test machine will operate for 1800 seconds by communicating with the Client end in a window with 512k size every 1 second.
It should be noted that the test environment configuration may be performed by calling an environment configuration script.
The test method directly tests the mode of connecting and setting the static IP through the cross line of the network cable, more directly reflects the performance of the network card and prevents the interference of dhcp on other network ports of the switch or the network.
And after the test environment is configured, detecting whether the two servers ping, if so, executing the following steps. If not ping, it can check if the configuration is correct, etc.
In this embodiment, the step S12 of testing the performance of the network card through the netserver tool specifically includes the following steps:
s12-1, executing the/netserver command on one of the servers, wherein the command is executed on the Client server;
s12-2, executing a/netperf-H xxx, xxx-l 1800- - -m 512k command on another server; xxx is the IP address of the server, it should be noted that the command is executed at the test end server.
In this embodiment, step S13, besides recording and displaying the test result, runs an ethyool-S eth | grep-E "fail | error | drop | crc" command to display whether an error occurs.
After one network cable is tested, the two servers are connected in pair by using the network cables with other lengths, the steps S12 and S13 are repeated, and after all the network cables to be tested are tested, a conclusion can be summarized to judge the influence of the network cable length on the network card performance.
Example two
The embodiment provides a system for testing the influence of the network cable length on the network card performance, which comprises two servers, wherein the two servers are provided with the same network card, and the two servers are connected by a network cable.
Wherein, be provided with on the first server:
the first environment configuration module is used for configuring a server test environment;
the first test operation module runs the test command and tests the performance of the network card;
the first result recording module records and displays the test result;
the first error reporting display module runs an error reporting checking command and displays error reporting information;
it should be noted that the server is configured to operate in a server mode and is a Client side.
The second server is provided with:
the second environment configuration module is used for configuring the server test environment;
the second test operation module runs the test command and tests the performance of the network card;
it should be noted that the server is a testing end.
In order to perform environment configuration, a first environment configuration script is configured on the first server, and a second environment configuration script is configured on the second server.
The first environment configuration module configures a first server environment by running a first environment configuration script, and is specifically configured to:
setting an IP address and a subnet mask;
setting the maximum MTU value of the network card; it should be noted that, the maximum MTU values of different network cards are different, and the relevant MTU values are set according to the type of the test network card;
setting a first server as an auxiliary machine and operating in a server mode; namely, the first server is set as a Client terminal.
The second environment configuration module configures the second server environment by running a second environment configuration script, and is specifically configured to:
setting an IP address and a subnet mask; it should be noted that the IP addresses of the two servers are in the same network segment;
setting the maximum MTU value of the network card to be the same as the MTU value set by the first server;
and setting the size and the communication time length of the communication window between the second server and the first server, so that the testing machine communicates with the Client terminal for 1800 seconds in a window with the size of 512k every 1 second.
In this embodiment, the first test operation module runs the/netserver test command to test the performance of the network card; the second test operation module runs a/netperf-H xxx.xxx.xxx.xxx.xxx-l 1800- - -m 512k test command to test the performance of the network card; xxx is the server IP address.
In this embodiment, a netserver tool is used to directly test a mode of connecting and setting a static IP through a network cable cross line, which more directly reflects the performance of a network card and prevents interference of dhcp on other network ports of a switch or a network.
The above disclosure is only for the preferred embodiments of the present invention, but the present invention is not limited thereto, and any non-inventive changes that can be made by those skilled in the art and several modifications and amendments made without departing from the principle of the present invention shall fall within the protection scope of the present invention.

Claims (10)

1. A method for testing the influence of the network cable length on the network card performance is characterized by comprising the following steps:
s11, installing the same network cards on the two servers, connecting the two servers in pair by using a network cable with a certain length, and configuring a test environment;
s12, running a network card performance detection command on the two servers, and performing performance detection on the network card;
and S13, recording and displaying the detection result.
2. The method for testing the influence of the network cable length on the network card performance according to claim 1, wherein in step S11, configuring the test environment specifically includes:
the following steps are performed on one of the servers,
s11-1, setting IP address and subnet mask;
s11-2, setting the maximum MTU value of the network card;
s11-3, setting the server as an auxiliary machine and operating in a server mode.
3. The method for testing the influence of the network cable length on the network card performance according to claim 2,
it is characterized in that, in step S11, configuring the test environment further specifically includes:
the following steps are performed on another server,
s11-4, setting IP address and subnet mask;
s11-5, setting the maximum MTU value of the network card;
s11-6, setting the size of the communication window and the communication time length between the server and another server.
4. The method for testing the influence of the network cable length on the network card performance according to claim 2 or 3, wherein step S11 further comprises detecting whether the two servers ping, and if so, performing the following steps.
5. The method for testing the influence of the network cable length on the network card performance according to claim 2 or 3, wherein the step S12 specifically includes:
s12-1, executing the/netserver command on one server;
s12-2, executing a/netperf-H xxx, xxx-l 1800- - -m 512k command on another server; xxx is the server IP address.
6. The method for testing the influence of the network cable length on the network card performance as claimed in claim 5, wherein the step S13 further includes running an ethyool-S eth | grep-E "fail | error | drop | crc command to indicate whether an error occurs.
7. The method for testing the influence of the network cable length on the network card performance according to claim 5, further comprising:
s14, connecting the two servers by using the network cables with other lengths to be tested, and repeating the steps S12 and S13.
8. A test system for influence of network cable length on network card performance is characterized by comprising two servers, wherein the two servers are provided with the same network card and are connected by a network cable;
wherein, be provided with on the first server:
the first environment configuration module is used for configuring a server test environment;
the first test operation module runs the test command and tests the performance of the network card;
the first result recording module records and displays the test result;
the first error reporting display module runs an error reporting checking command and displays error reporting information;
the second server is provided with:
the second environment configuration module is used for configuring the server test environment;
and the second test operation module operates the test command and tests the performance of the network card.
9. The system for testing the influence of the network cable length on the network card performance according to claim 8, wherein a first environment configuration script is configured on a first server, and a second environment configuration script is configured on a second server;
the first environment configuration module configures a first server environment by running a first environment configuration script, and is specifically configured to:
setting an IP address and a subnet mask;
setting the maximum MTU value of the network card;
setting the server as an auxiliary machine and operating in a server mode;
the second environment configuration module configures the second server environment by running a second environment configuration script, and is specifically configured to:
setting an IP address and a subnet mask;
setting the maximum MTU value of the network card;
and setting the size of a communication window and the communication time length between the server and another server.
10. The system for testing the influence of the network cable length on the network card performance according to claim 8 or 9,
the first test operation module operates a/netserver test command to test the performance of the network card;
the second test operation module runs a/netperf-H xxx.xxx.xxx.xxx.xxx-l 1800- - -m 512k test command to test the performance of the network card; xxx is the server IP address.
CN201910930776.6A 2019-09-29 2019-09-29 Method and system for testing influence of network cable length on network card performance Pending CN110808869A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910930776.6A CN110808869A (en) 2019-09-29 2019-09-29 Method and system for testing influence of network cable length on network card performance

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910930776.6A CN110808869A (en) 2019-09-29 2019-09-29 Method and system for testing influence of network cable length on network card performance

Publications (1)

Publication Number Publication Date
CN110808869A true CN110808869A (en) 2020-02-18

Family

ID=69487919

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910930776.6A Pending CN110808869A (en) 2019-09-29 2019-09-29 Method and system for testing influence of network cable length on network card performance

Country Status (1)

Country Link
CN (1) CN110808869A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202634493U (en) * 2012-04-19 2012-12-26 浩利源电子(深圳)有限公司 Remote expansion USB wireless network card and computer connection structure
CN103441899A (en) * 2013-08-27 2013-12-11 上海斐讯数据通信技术有限公司 Performance testing method and system of wireless router
CN103490947A (en) * 2013-09-04 2014-01-01 清华大学 Testing device and method for MUE protocol of MVB network card
CN106059860A (en) * 2016-07-22 2016-10-26 浪潮电子信息产业股份有限公司 Method and device for testing network cards
CN106680592A (en) * 2017-02-25 2017-05-17 郑州云海信息技术有限公司 Method and system for detecting loss of Cable with arbitrary lengths
CN107370640A (en) * 2017-08-21 2017-11-21 太仓市同维电子有限公司 Automatically control the system and method that network interface card connection AP is tested

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202634493U (en) * 2012-04-19 2012-12-26 浩利源电子(深圳)有限公司 Remote expansion USB wireless network card and computer connection structure
CN103441899A (en) * 2013-08-27 2013-12-11 上海斐讯数据通信技术有限公司 Performance testing method and system of wireless router
CN103490947A (en) * 2013-09-04 2014-01-01 清华大学 Testing device and method for MUE protocol of MVB network card
CN106059860A (en) * 2016-07-22 2016-10-26 浪潮电子信息产业股份有限公司 Method and device for testing network cards
CN106680592A (en) * 2017-02-25 2017-05-17 郑州云海信息技术有限公司 Method and system for detecting loss of Cable with arbitrary lengths
CN107370640A (en) * 2017-08-21 2017-11-21 太仓市同维电子有限公司 Automatically control the system and method that network interface card connection AP is tested

Similar Documents

Publication Publication Date Title
AU2016337397B2 (en) Cloud based system and method for managing testing configurations for cable test devices
CN110995547A (en) Vehicle-mounted high-speed network testing system and method
US11637805B2 (en) Systems and methods of installing and operating devices without explicit network addresses
US20060218447A1 (en) Packet trace diagnostic system
CN106851513B (en) Method and system for testing electronic product
CN106803801B (en) System and method for applying aggregated cable test result data
US20070097872A1 (en) Network connection apparatus testing method
CN107959599B (en) Bus_off fault test system and test method
CN112468335B (en) IPRAN cloud private line fault positioning method and device
CN112311576B (en) OTA upgrading diagnosis method and device, wireless routing equipment and terminal equipment
US20140310604A1 (en) Network test instrument
CN106330483B (en) Information acquisition method, client device and server device
CN110650041A (en) IPRAN network fault positioning method and device
CN108322452A (en) Network closes rule detection method, device, equipment and medium
CN109743228B (en) Method and system for measuring position of sampling point
CN109218132B (en) Method for automatically testing stability of IPv6 of server
CN110808869A (en) Method and system for testing influence of network cable length on network card performance
EP2108968A1 (en) A method and a system for calibrating the parameters of a bus
US20190289056A1 (en) Method and Apparatus for Cross Layer Network Diagnostics and Self-Healing Platform for Point-to-Multipoint Networks
Cisco Confirming the Installation
CN107707420B (en) Method for testing network cable plugging and unplugging stability
CN108632109B (en) Network communication quality obtaining method, device and system
US20100110899A1 (en) Stressing a network device
Cisco Confirming the Installation
Cisco Confirming the Installation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20200218

RJ01 Rejection of invention patent application after publication