CN116866224A - Multi-server network card performance test method and related components - Google Patents
Multi-server network card performance test method and related components Download PDFInfo
- Publication number
- CN116866224A CN116866224A CN202310864925.XA CN202310864925A CN116866224A CN 116866224 A CN116866224 A CN 116866224A CN 202310864925 A CN202310864925 A CN 202310864925A CN 116866224 A CN116866224 A CN 116866224A
- Authority
- CN
- China
- Prior art keywords
- server
- client
- internet protocol
- network card
- network
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000011056 performance test Methods 0.000 title claims abstract description 41
- 238000012360 testing method Methods 0.000 claims abstract description 45
- 238000004891 communication Methods 0.000 claims abstract description 22
- 230000003068 static effect Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 11
- 230000006855 networking Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0817—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
- H04L43/0888—Throughput
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/50—Testing arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Abstract
The invention discloses a network card performance test method of multiple servers and related components, which relate to the field of network card test, wherein the network card performance test method is respectively linked with a server side server and a plurality of client side servers through a switch, all available internet protocol addresses in a network section where the server side server is positioned are determined through the switch, the internet protocol addresses are respectively distributed for the client side servers, the firewall of the servers is controlled to be closed, and when the client side servers send data packets to the server side server through the switch, the data throughput of the network communication is sent to the client side servers so that the client side servers can determine the network card performance of the client side servers. By setting the switch, the flexibility of the network can be improved, and the complexity of the wiring environment of the server side server is reduced; by setting the server as the same network segment, various problems caused by different network environments can be effectively avoided, and the result of the network card performance test is more in line with the real performance of the network card.
Description
Technical Field
The invention relates to the field of network card testing, in particular to a multi-server network card performance testing method and related components.
Background
With the development of network technology, the servers, computers and other devices in various industries need to execute various networking services by means of a network card, so that the performance and stability of the network card directly affect the quality of the network and the execution efficiency of the service. In order to test the performance of a network card in the prior art, a server to be tested is generally used as a client to be connected to a server serving as a server through a network cable, the client sends a data packet to the server through a network, and the performance of the network card of the client is determined based on the throughput of network data in unit time. The method can be normally used when the number of the clients is small, but when a user needs to test the network card performance of a plurality of clients, the following two problems exist:
1. all clients need to be linked with the server through network cables, and a large number of network cables lead to a complex wiring environment at the server.
2. Because the network environment where each server is located is different, network delay, network load and network management difficulty may be increased due to the network environment when testing the performance of the network card, so that the final network card performance test result does not conform to the actual performance of the network card.
Disclosure of Invention
The invention aims to provide a network card performance test method and related components of a multi-server, which can improve the flexibility of a network, do not need a client server to be connected to a server, and reduce the complexity of the wiring environment of the server; and the problems of increased network delay, increased network load and increased network management difficulty caused by different network environments can be effectively avoided, so that the network card performance test result is more in line with the actual performance of the network card.
In order to solve the technical problems, the present invention provides a multi-server network card performance test method, which is applied to a processor in an exchanger, wherein the exchanger is respectively linked with a server and a plurality of client servers, and the multi-server network card performance test method comprises:
determining a network segment where the server of the server is located;
determining all available internet protocol addresses in the network segment;
respectively distributing different internet protocol addresses to the client servers in all available internet protocol addresses;
controlling the firewalls of the server and each client server to be closed;
When a network data packet sent by the client server is received, the network data packet is sent to the server, and the data throughput between the client server and the server is determined;
and sending the data throughput to the client server so that the client server can determine the network card performance of the client server according to the data throughput.
In one aspect, allocating a different ip address to each of the client servers among all available ip addresses includes:
s21: taking any unallocated client server as a current client server;
s22: assigning a random one of said internet protocol addresses to said current client server among said internet protocol addresses available;
s23: taking the rest of the Internet protocol addresses as new available Internet protocol addresses;
s24: judging whether the unassigned client-side server exists or not; if yes, returning to S21; if not, the step of controlling the firewall of the server and each client server to be closed is carried out.
In one aspect, before assigning a random one of the internet protocol addresses to the current client server, further comprising:
judging whether the number of the available internet protocol addresses is 0;
if not, entering a step of distributing one random internet protocol address to the current client server;
if yes, in the static internet protocol addresses, different static internet protocol addresses are allocated for the current client server and other unassigned client servers one by one.
In one aspect, allocating a different ip address to each of the client servers among all available ip addresses includes:
for any one of the client servers, determining the number of network card ports to be tested of the client server;
and distributing the internet protocol addresses with the same number as the network card ports to be tested in all available internet protocol addresses.
In one aspect, before allocating the internet protocol addresses with the same number of network card ports to be tested, the method further includes:
judging whether the number of ports of the client server connected to the switch is consistent with the number of ports of the network card to be tested of the client server;
If yes, the step of distributing the internet protocol addresses with the same number as the network card ports to be tested is entered.
In one aspect, sending the data throughput to the client server includes:
and sending the network data flow of the client server passing through the switch in a preset time to the client server so that the client server can determine the network card performance of the client server according to the data throughput.
In one aspect, allocating different internet protocol addresses to the client servers respectively includes:
respectively distributing different first internet protocol addresses and second internet protocol addresses for the client servers; wherein the first internet protocol address is any one of all available internet protocol addresses, and the second internet protocol address is a fixed networking protocol address corresponding to the client server one by one;
after each client server is respectively allocated with a different internet protocol address, the method further comprises the following steps:
judging whether network communication between the client server and the switch itself is normal when the first internet protocol address is utilized;
If yes, a step of controlling the firewall closing of the server side server and each client side server is entered;
if not, switching the client server to the second internet protocol address, and entering a step of controlling the firewall of the server and each client server to be closed.
The application also provides a multi-server network card performance test system, which is applied to a processor in an exchanger, wherein the exchanger is respectively linked with a server and a plurality of client servers, and the multi-server network card performance test system comprises:
the network segment determining unit is used for determining the network segment where the server side server is located;
an address determination unit for determining all available internet protocol addresses in the network segment;
the distribution unit is used for distributing different internet protocol addresses to the client servers respectively in all available internet protocol addresses;
the control unit is used for controlling the firewall of the server and each client server to be closed;
a data throughput determining unit, configured to, when receiving a network data packet sent by the client server, send the network data packet to the server, and determine a data throughput between the client server and the server;
And the sending unit is used for sending the data throughput to the client server so that the client server can determine the network card performance of the client server according to the data throughput.
The application also provides a network card performance test device of the multi-server, which comprises:
a memory for storing a computer program;
and the processor is used for realizing the steps of the multi-server network card performance testing method when executing the computer program.
The application also provides a switch, which comprises a switch body and the network card performance testing device of the multi-server;
the switch is connected with the network card performance testing device of the multi-server.
The present application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the multi-server network card performance test method described above.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required in the prior art and the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a connection method of multiple servers in the prior art;
FIG. 2 is a flow chart of a method for testing the performance of a multi-server network card;
FIG. 3 is a schematic diagram of a connection method of multiple servers according to the present application;
FIG. 4 is a flowchart of another method for testing performance of a multi-server network card according to the present application;
fig. 5 is a schematic structural diagram of a multi-server network card performance test system according to the present application;
fig. 6 is a schematic structural diagram of a multi-server network card performance testing device according to the present application.
Detailed Description
The core of the application is to provide a network card performance test method and related components of multiple servers, which can improve the flexibility of the network, does not need to connect client servers to server servers, and reduces the complexity of the wiring environment of the server servers; and the problems of increased network delay, increased network load and increased network management difficulty caused by different network environments can be effectively avoided, so that the network card performance test result is more in line with the actual performance of the network card.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Currently, the tools for testing the performance of the network card are mainly netperf and IPerf, which are used for transmission of TCP (Transmission Control Protocol ) or UDP (User Datagram Protocol, user datagram protocol), and detect the receiving rate and the sending rate of network data in a server to determine the performance of the network card. In the prior art, referring to fig. 1, fig. 1 is a schematic diagram of a connection manner of multiple servers in the prior art, and a common method for testing performance of a network card is as follows: two or more servers are connected through a network cable, one server is used as a server side, all other servers are used as client sides, corresponding IP (Internet Protocol ) addresses are set for each server, all the client sides are connected to the server side, then a netperf or IPerf program is executed in the client side, and network data are sent to the server side so as to test the network card performance of the client side. However, the number of clients in the application is large, the network cable connection is complicated, and the inconvenience is brought to the performance test of the network card. Therefore, how to realize a simple, convenient, safe and efficient performance test method is a technical problem to be solved at present.
In order to solve the above technical problems, please refer to fig. 2 and 3, fig. 2 is a flowchart of a multi-server network card performance testing method provided by the present application, fig. 3 is a schematic diagram of a multi-server connection method provided by the present application, the network card performance testing method is applied to a processor in a switch, the switch is respectively linked with a server and a plurality of client servers, and the multi-server network card performance testing method comprises:
s1: determining a network segment where a server of a server side is located;
in order to avoid interference caused by network communication during the network card testing process, such as router limitation, network bridging limitation, bandwidth limitation, signal roaming limitation, wireless interference and the like caused by that the server belongs to different network segments, all client servers and server servers need to be arranged in the same network segment, that is, in the same physical layer, so that the client servers and the server servers can directly communicate. The method for determining the network segment where the server is located can be determined by acquiring the IP address of the server itself, or can be determined by acquiring the network mask of the server. For example, assuming that the IP address of the server is 192.168.1.1, the network segment of the server is 192.168.X.x, where X is the default value of the network segment.
S2: determining all available internet protocol addresses in the network segment;
s3: respectively distributing different internet protocol addresses for each client server in all available internet protocol addresses;
in order to set both the client server and the server in the same network segment, since there are a plurality of IP addresses in one network segment or physical segment, the IP address of each client server may be changed to the IP address in the network segment in which the server is located with the network segment in which the server is located as a reference, so that the servers are located in the same network segment. In consideration of that other running devices may exist in the network segment where the server is located, the devices may occupy a certain number of IP addresses, so, in order to reasonably set the IP addresses of the client servers, to avoid that multiple devices use the same IP address, it is necessary to find all unused idle IP addresses in the network segment where the server is located, and then randomly allocate a different idle IP address to each client server, or allocate different idle IP addresses to each client server according to a certain sequence, so that each client server and the server are located in the same network segment, and it is convenient to enable each client server to directly communicate with the server subsequently.
S4: controlling the firewalls of the server and each client server to be closed;
the firewall is used for controlling and filtering network data entering and exiting the server, preventing illegal or malicious access to the server, and obviously helping the security and stability of the server. However, when the network card performance test is performed, the firewall may intercept the data packet sent by the client server to the server, so that the communication between the client server and the server fails or is unstable; even if the data packet passes through the firewall, the communication between the client server and the server is successful, but the firewall needs to verify the data packet, so that the communication efficiency and quality are also affected, namely the detection result of the performance of the network card is affected; furthermore, firewalls may also result in increased complexity of the network topology between the client server and the server, resulting in increased difficulty in overall management and maintenance. Therefore, in order to detect the real performance of the network card, the firewalls of the server and the client server need to be closed before the network card is tested. Of course, in addition to the switch closing the firewall in each server, the server may also automatically close its firewall after determining that it is assigned to an IP address.
In addition, because certain potential safety hazards are brought after the firewall is closed, such as illegal or malicious access, the network credibility between the client server and the server can be determined before the firewall is closed, and the firewall is closed when the network credibility is completely credible; or other security measures such as encryption, authentication, and monitoring may be employed after the firewall is closed.
S5: when a network data packet sent by a client server is received, the network data packet is sent to a server, and the data throughput between the client server and the server is determined;
s6: and sending the data throughput to the client server so that the client server can determine the network card performance of the client server according to the data throughput.
After the client server is arranged in the same network segment as the server and the network credibility between the client server and the server is determined, the network card performance test can be performed after the respective firewall is closed. By combining the above, the overall flow of the network card performance test can be determined: firstly, installing a network card to be tested into a slot of a client server, confirming the network card to be tested in the client server, after determining that the server and a switch are normal, selecting whether to upgrade the firmware version of the network card according to the needs of a user, and installing a corresponding network card system driver (generally, the more the firmware version and the system driver are newer, the higher the lifting of the network card is, but the time required for upgrading and updating is required, and the variable number is increased, so that the firmware version or the system driver of the network card is required to be not updated before the test is determined according to the needs of the user). And then the client server and the server are connected with the network card port and the switch port through network cables, or the wireless port of the switch is connected in a wireless communication mode, so that the client server can acquire the IP addresses of the server in the same network segment, namely, the client server can freely select among available IP addresses according to the needs of clients or environmental requirements and the like. In addition, the client server and the ports of the server need to be decompressed and installed by selecting a netperf version tool, related file configuration information is set, when in actual test, each server closes a firewall, opens a port function to perform netperf test, the client server operates netservers, the server operates netperf, and after the test is completed, each client server performs log collection of data throughput from the switch so as to determine the performance of the network card needing to be tested.
In addition, the application connects the client server and the server by arranging the switch, because the switch can carry out quick forwarding according to the MAC (Media Access Control Address ) address table, the conflict domain can be reduced, the network throughput and the network efficiency can be improved, and the detection of the network card performance is more fit with the real performance. In addition, the switch can support simultaneous communication of multiple network types, and can select proper media and speed according to different devices and distances, such as Ethernet, optical fiber, wireless network and the like, so that client servers of multiple different network types can be connected to the switch, and the universality of the whole network card performance test environment is obviously improved. And the switch can also support various security functions, such as MAC address filtering, port security, ACL (Access Control List ) authentication, 802.1X authentication and other rated functions, and can effectively prevent illegal or malicious access or attack after the firewalls of the client server and the server are closed, thereby effectively protecting the security of the client server and the server. Finally, the cost of the switch is generally lower than that of the router, and maintenance is simpler, so that the safety, stability and reliability of the performance test of the network card can be remarkably improved by arranging the switch.
In summary, the server and the plurality of client servers are respectively linked through the switch, and the following steps are executed by using the switch: determining all available internet protocol addresses in a network segment where a server is located, then respectively distributing different internet protocol addresses for each client server, and controlling the firewalls of the server and each client server to be closed; when the client side server sends the data packet to the server side server through the switch, the data throughput of the network communication is sent to the client side server, so that the client side server can determine the network card performance of the client side server. By setting the switch, the flexibility of the network can be improved, the client servers are not required to be connected to the server, and the complexity of the wiring environment of the server is reduced; in addition, the switch sets each client server and the server as the same network segment, so that the problems of increased network delay, increased network load and increased network management difficulty caused by different network environments can be effectively avoided, and the result of the network card performance test is more in line with the real performance of the network card.
Based on the above embodiments:
in some embodiments, each client server is assigned a different internet protocol address from among all available internet protocol addresses, including:
s21: taking any unallocated client server as a current client server;
s22: among the available internet protocol addresses, assigning a random one of the internet protocol addresses to the current client server;
s23: taking the rest of the internet protocol addresses as new available internet protocol addresses;
s24: judging whether unallocated client servers exist or not; if yes, returning to S21; if not, the step of controlling the firewall closing of the server and each client server is entered.
In order to accurately allocate each client server to different available IP addresses, in the application, among all client servers which are not allocated with an IP address in the same network section with the server, one client server is randomly selected as a current client server needing to be allocated with the IP address, and then one IP address is selected from all available free IP addresses in the network section where the server is located to be allocated to the current client server, and because the free IP address is not used by any device, the IP address of the current client server can be ensured not to conflict with the IP address of any other device. When selecting the IP address, one of all available free IP addresses may be randomly selected and allocated to the current client server, or the smallest or largest IP address among the available IP addresses may be allocated to the current client server according to the order of from big to small or from small to big, or the IP address may be allocated to the current client server according to the importance of different IP addresses (for example, a user may consider a certain specific IP address as having higher importance), which is not limited by the detailed step of how to allocate the IP address. After the first current client server is assigned an IP address, each of the remaining client servers sequentially selects an IP address from all available free IP addresses remaining according to the same procedure as the first client server until each client server obtains an IP address in the same network segment as the server. Based on this, since the IP address allocated to the client server each time is a free unused IP address, each client server can be accurately allocated to a different available IP address.
In some embodiments, before assigning the random one internet protocol address to the current client server, further comprising:
judging whether the number of available internet protocol addresses is 0;
if not, entering a step of distributing a random internet protocol address to the current client server;
if yes, in the static internet protocol addresses, different static internet protocol addresses are allocated one by one for the current client server and other client servers which are not allocated.
In order to avoid the occurrence of communication failure between the client server and the server, in the present application, considering that the number of IP addresses in one network segment is limited, if the number of devices in the same network segment is particularly large, or the number of client servers needing to perform network card performance test is particularly large, it may happen that the IP addresses in the network segment where the server is located are all allocated, but there is still a situation that some client servers are not allocated with IP addresses. In order to avoid communication failure between the client servers not assigned with the IP addresses and the server, after detecting that the IP addresses in the network segment where the server is located are all assigned, the application respectively assigns a preset static IP address to all the subsequent client servers not assigned with the IP addresses. Specifically, the static IP address is available to each client server, and a static IP address may be preset for each client server as a standby IP address, where the static IP address is not necessarily an IP address located in the same network segment with the server, but in order to avoid situations of increasing network delay, increasing network load, and increasing network management difficulty when communication is performed across the network segments as much as possible, the static IP address needs to be set as an IP address when the network delay, the network load, and the network management difficulty are all the lowest. In practical application, the static IP address is used as an alternative item, and the IP address allocated by the switch is still used under normal conditions, because the IP address allocated by the switch has stronger randomness, the IP address can be called as a dynamic IP address and is used for distinguishing the static IP address; when the exchanger distributes all the dynamic IP addresses, if there are client servers not distributed with dynamic IP addresses, the static IP addresses preset by the exchanger are used for communicating with the server servers. Based on the method, the situation that communication failure exists between the client server and the server can be avoided.
In some embodiments, each client server is assigned a different internet protocol address from among all available internet protocol addresses, including:
for any client server, determining the number of network card ports to be tested of the client server;
among all available internet protocol addresses, the same number of internet protocol addresses as the number of ports of the network card to be tested are allocated.
In order to correctly test the performance of the network card, in the present application, considering that there are some network cards in the client server with relatively more functions, there may be a case that one network card has a plurality of network ports, for this case, if only 1 IP address is allocated to the network card, this is equivalent to allocating the same IP address to all network ports in the network card, and then the case of IP address collision may also occur, which causes that the client server cannot communicate with the server or the communication is unstable. Therefore, for such a multi-port network card, it is necessary to consider it as a plurality of single-port network cards, that is, each network port of the network card needs to be allocated an idle IP address in the same network segment as the server. Based on this, for each network card, the same number of IP addresses as the number of network ports of the network card need to be allocated to the network card, so that the performance of the network card can be correctly tested.
In some embodiments, before allocating the same number of internet protocol addresses as the number of network card ports to be tested, the method further comprises:
judging whether the number of ports of the client server connected to the switch is consistent with the number of ports of the network card to be tested of the client server;
if yes, the step of distributing the internet protocol addresses with the same number as the ports of the network card to be tested is entered.
In order to effectively test the performance of the network card, when one network card has a plurality of network ports, if only one network port or a few network ports are tested, the bandwidth, delay, packet loss and single port performance of the tested ports can be only obtained. It can be seen that if the integrity of the network card is to be tested, only one or a few network ports are not available, so that in order to effectively test the performance of the network card, the subsequent testing step needs to be performed when the number of network ports connected to the switch is identical to the total number of network ports on the network card. For the network card with multiple network ports, the stability, compatibility, failure rate, total data throughput, data pressure and other parameters of the whole network card are required to be determined by combining the performances of the multiple network ports during testing, so that the performance of the network card can be effectively and comprehensively determined.
In some embodiments, sending the network data packet to the server side server comprises:
and sending the network data flow of the client server passing through the switch in the preset time to the client server so that the client server can determine the network card performance of the client server according to the network data flow.
In order to simply determine the performance of the network card, in the present application, it is considered that when the client server transmits the network data packet to the server through the switch, the transmission speed of the network data packet depends on the network data uploading speed of the client server, and when the client server acquires the feedback data generated by the server according to the network data packet through the switch, the acquisition speed of the feedback data depends on the network data downloading speed of the client server. Because the uploading speed and the downloading speed of the network data are directly proportional to the performance of the network card in the client server, the network data flow in unit time can be calculated according to the uploading speed and the downloading speed of the network data in unit time of the client server, further, the total network data flow in a period of time can be continuously detected based on the network data flow for the test result to be more fit with the actual situation, the performance of the network card is determined according to the total network data flow detected in the period of time, and it is understood that the larger the total network data flow is, the stronger the performance of the network card is under the condition of fixed time. In summary, the network card performance can be determined simply.
In some embodiments, assigning different internet protocol addresses to respective client servers includes:
respectively distributing different first internet protocol addresses and second internet protocol addresses for each client server; the first internet protocol address is any one of all available internet protocol addresses, and the second internet protocol address is a fixed networking protocol address corresponding to the client server one by one;
after each client server is respectively allocated with a different internet protocol address, the method further comprises the following steps:
judging whether network communication between a client server and a switch per se is normal or not when the first internet protocol address is utilized;
if yes, the step of controlling the firewall closing of the server and each client server is entered;
if not, switching the client server into a second Internet protocol address, and entering a step of controlling the firewall of the server and each client server to be closed.
In order to flexibly replace the IP addresses of the client servers, the present application combines the above embodiments, and uses the free IP address/dynamic IP address in the same network segment as the server as the first internet protocol address (first IP address), and uses the static IP address previously set for each client server as the second internet protocol address (second IP address). Under normal circumstances, the switch allocates a first IP address to each client server, that is, selects one of all the free IP addresses in the same network segment as the server to allocate to each client server, and when there are client servers to which the first IP addresses are not allocated after the allocation of the first IP addresses, the second IP addresses of the client servers to which the first IP addresses are not allocated are allocated as standby options to the corresponding client servers, so as to avoid communication failure between the client servers and the server. In an abnormal situation, a situation may occur that a certain first internet protocol address is allocated to a plurality of client servers at the same time, and a situation may also occur that when a switch allocates the first internet protocol address, an incorrect IP address is allocated to a certain client server due to interference or other reasons, in this case, in order to avoid a communication failure between the client server that allocates the incorrect IP address or the same IP address and the server, a second internet protocol address is used to cover the current IP addresses of the client servers, so as to ensure successful communication between the client server and the server. Similarly, if the second internet protocol address of a client server is incorrectly assigned to another client server, or the second internet protocol address fails, the switch may also temporarily assign a first internet protocol address to that client server. Based on this, through flexible coverage and allocation between the first internet protocol address and the second internet protocol address, the IP address of each client server can be flexibly replaced, and successful communication between the client server and the server is ensured.
Further, as a simple example, assuming that there are two client servers, and the network segment where the server is located is 1.1.X.x, different second internet protocol addresses, that is, static IP addresses, may be set in advance for the two client servers, and for the client server a, there is:
TYPE＝Ethernet
NAME＝eth*A
DEVICE＝eth*A
ONBOOT＝yes
BOOTPROTO＝static
IPADDR＝1.1.1.1
NETASK＝255.255.255.0
for client server B, there are:
TYPE＝Ethernet
NAME＝eth*B
DEVICE＝eth*B
ONBOOT＝yes
BOOTPROTO＝static
IPADDR＝1.1.1.2
NETASK＝255.255.255.0
in practical applications, it is also necessary to assign the two client servers a first internet protocol address, i.e. a dynamic IP address, for both client servers AB:
TYPE＝Ethernet
NAME＝eth*
DEVICE＝eth*
ONBOOT＝yes
BOOTPROTO＝hdcp
for the network card performance test flow of the two client servers, please refer to fig. 4, fig. 4 is a flow chart of another network card performance test method of multiple servers provided by the present application. The graph side-to-side assignment refers to two client servers, each of which needs to perform the following steps: 1. connecting a network port of the network card to the switch; 2. installing or updating a network card driver according to the requirements of a user; 3. determining that each network port on the network card is normal; 4. setting a preset network port configuration file for each network port; 5. closing a firewall of the client server; 6. opening the network ports of the network card; 7. executing netperf program starts to test performance of network card.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a multi-server network card performance test system according to the present application, which is applied to a processor in a switch, wherein the switch is respectively linked with a server and a plurality of client servers, and the multi-server network card performance test system comprises:
a network segment determining unit 21, configured to determine a network segment where the server is located;
an address determination unit 22 for determining all available internet protocol addresses in the network segment;
a first allocation unit 23, configured to allocate different internet protocol addresses to the client servers respectively from all available internet protocol addresses;
a control unit 24, configured to control the firewalls of the server and the client servers to be closed;
a data throughput determining unit 25, configured to, when receiving a network data packet sent by the client server, send the network data packet to the server, and determine a data throughput between the client server and the server;
and a sending unit 26, configured to send the data throughput to the client server, so that the client server determines its own network card performance according to the data throughput.
For a detailed description of the multi-server network card performance test system provided by the present application, please refer to an embodiment of the multi-server network card performance test method, and the detailed description is omitted herein.
The basis of the above embodiment is:
in some embodiments, the dispensing unit 23 comprises:
a selecting unit, configured to take any one of the unassigned client servers as a current client server;
a second allocation unit for allocating a random one of the available internet protocol addresses to the current client server;
an updating unit for taking the remaining internet protocol addresses as new available internet protocol addresses;
a judging unit for judging whether there is an unassigned client server; if yes, triggering a selection unit; if not, the control unit 24 is triggered.
In some embodiments, further comprising:
a number available judging unit for judging whether the number of available internet protocol addresses is 0 before assigning a random one of the internet protocol addresses to the current client server; if not, triggering a second distribution unit; if yes, triggering a static allocation unit;
And the static allocation unit is used for allocating different static internet protocol addresses one by one for the current client server and other client servers which are not allocated in the static internet protocol addresses.
In some embodiments, the dispensing unit 23 comprises:
the port number determining unit is used for determining the number of ports of the network card to be tested of the client server for any one of the client servers;
and the third distribution unit is used for distributing the internet protocol addresses with the same number as the ports of the network card to be tested in all available internet protocol addresses.
In some embodiments, further comprising:
the port number judging unit is used for judging whether the port number of the client server connected to the switch is consistent with the port number of the network card to be tested of the client server before the Internet protocol addresses with the same number as the port number of the network card to be tested are allocated; if yes, triggering a third distribution unit.
In some embodiments, the sending unit 26 is specifically configured to:
and sending the network data flow of the client server passing through the switch in the preset time to the client server so that the client server can determine the network card performance of the client server according to the data throughput.
In some embodiments, the dispensing unit 23 comprises:
a fourth allocation unit, configured to allocate different first internet protocol addresses and second internet protocol addresses to each client server respectively; the first internet protocol address is any one of all available internet protocol addresses, and the second internet protocol address is a fixed networking protocol address corresponding to the client server one by one;
a communication judging unit for judging whether the network communication between the client server and the switch itself is normal when the first internet protocol address is utilized after different internet protocol addresses are allocated to the respective client servers; if yes, the control unit 24 is triggered; if not, triggering a switching unit;
a switching unit for switching the client server to the second internet protocol address, triggering the control unit 24.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a multi-server network card performance testing device according to the present application, including:
a memory 31 for storing a computer program;
the processor 32 is configured to implement the steps of the multi-server network card performance test method as described above when executing the computer program.
For a detailed description of the multi-server network card performance testing device provided by the present application, please refer to an embodiment of the multi-server network card performance testing method, and the detailed description is omitted herein.
The application also provides a switch, which comprises a switch body and the network card performance testing device of the multi-server;
the exchanger is connected with the network card performance testing device of the multiple servers.
For a detailed description of the switch provided by the present application, please refer to an embodiment of the above-mentioned multi-server network card performance testing method, and the detailed description of the present application is omitted herein.
The application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the steps of the multi-server network card performance testing method when being executed by a processor.
For a detailed description of a computer readable storage medium provided in the present application, please refer to an embodiment of the above multi-server network card performance testing method, and the detailed description is omitted herein.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
It should also be noted that in this specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to 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 (11)
1. The network card performance test method of the multi-server is characterized by being applied to a processor in a switch, wherein the switch is respectively linked with a server and a plurality of client servers, and the network card performance test method of the multi-server comprises the following steps:
determining a network segment where the server of the server is located;
determining all available internet protocol addresses in the network segment;
respectively distributing different internet protocol addresses to the client servers in all available internet protocol addresses;
controlling the firewalls of the server and each client server to be closed;
when a network data packet sent by the client server is received, the network data packet is sent to the server, and the data throughput between the client server and the server is determined;
and sending the data throughput to the client server so that the client server can determine the network card performance of the client server according to the data throughput.
2. The method for testing performance of a multi-server network card according to claim 1, wherein each of the client servers is assigned a different internet protocol address among all available internet protocol addresses, respectively, comprising:
S21: taking any unallocated client server as a current client server;
s22: assigning a random one of said internet protocol addresses to said current client server among said internet protocol addresses available;
s23: taking the rest of the Internet protocol addresses as new available Internet protocol addresses;
s24: judging whether the unassigned client-side server exists or not; if yes, returning to S21; if not, the step of controlling the firewall of the server and each client server to be closed is carried out.
3. The multi-server network card performance test method of claim 2, further comprising, prior to assigning a random one of said internet protocol addresses to said current client server:
judging whether the number of the available internet protocol addresses is 0;
if not, entering a step of distributing one random internet protocol address to the current client server;
if yes, in the static internet protocol addresses, different static internet protocol addresses are allocated for the current client server and other unassigned client servers one by one.
4. The method for testing performance of a multi-server network card according to claim 1, wherein each of the client servers is assigned a different internet protocol address among all available internet protocol addresses, respectively, comprising:
for any one of the client servers, determining the number of network card ports to be tested of the client server;
and distributing the internet protocol addresses with the same number as the network card ports to be tested in all available internet protocol addresses.
5. The multi-server network card performance test method of claim 4, further comprising, prior to assigning the same number of internet protocol addresses as the number of network card ports to be tested:
judging whether the number of ports of the client server connected to the switch is consistent with the number of ports of the network card to be tested of the client server;
if yes, the step of distributing the internet protocol addresses with the same number as the network card ports to be tested is entered.
6. The multi-server network card performance testing method of claim 1, wherein transmitting the data throughput to the client server comprises:
And sending the network data flow of the client server passing through the switch in a preset time to the client server so that the client server can determine the network card performance of the client server according to the data throughput.
7. The method for testing the performance of a multi-server network card according to any one of claims 1 to 6, wherein assigning different internet protocol addresses to the client servers respectively comprises:
respectively distributing different first internet protocol addresses and second internet protocol addresses for the client servers; wherein the first internet protocol address is any one of all available internet protocol addresses, and the second internet protocol address is a fixed networking protocol address corresponding to the client server one by one;
after each client server is respectively allocated with a different internet protocol address, the method further comprises the following steps:
judging whether network communication between the client server and the switch itself is normal when the first internet protocol address is utilized;
if yes, a step of controlling the firewall closing of the server side server and each client side server is entered;
If not, switching the client server to the second internet protocol address, and entering a step of controlling the firewall of the server and each client server to be closed.
8. The utility model provides a network card performance test system of multiserver which characterized in that is applied to the treater in the switch, the switch links with server and a plurality of customer end server respectively, the network card performance test system of multiserver includes:
the network segment determining unit is used for determining the network segment where the server side server is located;
an address determination unit for determining all available internet protocol addresses in the network segment;
the distribution unit is used for distributing different internet protocol addresses to the client servers respectively in all available internet protocol addresses;
the control unit is used for controlling the firewall of the server and each client server to be closed;
a data throughput determining unit, configured to, when receiving a network data packet sent by the client server, send the network data packet to the server, and determine a data throughput between the client server and the server;
And the sending unit is used for sending the data throughput to the client server so that the client server can determine the network card performance of the client server according to the data throughput.
9. A multi-server network card performance testing device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the multi-server network card performance test method according to any one of claims 1 to 7 when executing the computer program.
10. A switch, comprising a switch body, and further comprising the multi-server network card performance testing device according to claim 9;
the switch is connected with the network card performance testing device of the multi-server.
11. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and the computer program when executed by a processor implements the steps of the multi-server network card performance test method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310864925.XA CN116866224A (en) | 2023-07-14 | 2023-07-14 | Multi-server network card performance test method and related components |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310864925.XA CN116866224A (en) | 2023-07-14 | 2023-07-14 | Multi-server network card performance test method and related components |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116866224A true CN116866224A (en) | 2023-10-10 |
Family
ID=88233765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310864925.XA Pending CN116866224A (en) | 2023-07-14 | 2023-07-14 | Multi-server network card performance test method and related components |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116866224A (en) |
-
2023
- 2023-07-14 CN CN202310864925.XA patent/CN116866224A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11706102B2 (en) | Dynamically deployable self configuring distributed network management system | |
| US10652202B2 (en) | Network address translating router for mobile networking | |
| US7159016B2 (en) | Method and apparatus for configuring an endpoint device to a computer network | |
| US7360242B2 (en) | Personal firewall with location detection | |
| US7890658B2 (en) | Dynamic address assignment for access control on DHCP networks | |
| US7440415B2 (en) | Virtual network addresses | |
| US20090019536A1 (en) | Automatic ip network determination and configuration for edge devices | |
| US11075980B2 (en) | Method for operating a node cluster system in a network and node cluster system | |
| US20070016670A1 (en) | Determining data flows in a network | |
| US20050125511A1 (en) | Intelligent local proxy for transparent network access from multiple physical locations | |
| CN116866224A (en) | Multi-server network card performance test method and related components | |
| EP1479191B1 (en) | System and method for intercepting network access | |
| CN107070725A (en) | A kind of method that server two-level management intermodule communication is shaken hands | |
| CN109451074B (en) | Server load balancing processing method based on portal protocol | |
| CN113328922A (en) | Communication method and device across multiple local area networks | |
| CN104954187A (en) | Method and device for determining state of CPE (customer premise equipment) | |
| WO2022254517A1 (en) | Communication system and communication control method | |
| TWI732708B (en) | Network security system and network security method based on multi-access edge computing | |
| CN115086219B (en) | Virtual router determining method, device and computer readable storage medium | |
| CN108512686B (en) | Multi-device data transmission method, device and system | |
| JP2017059868A (en) | Address management device and communication system | |
| CN116708373A (en) | DHCP conflict detection method and configuration method applied to switch |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |