CN105337786A - Server performance detection method, apparatus and equipment - Google Patents

Abstract

Embodiments of the present invention provide a server performance detection method, device, and equipment. The method includes: the detection device sends a first detection message to the server under test, and the first detection message carries first information; the detection The device receives the first response message returned by the server under test corresponding to the first detection message, the first response message carries second information, and the second information and the first information have a mapping relationship; the detection device determines whether the tested server is in an available state; based on the detection device determining that the tested server is in an available state, the detection device acquires the first detection message and the first A first interval between response messages; the detection device determines the performance level of the server under test according to the first interval. In this way, the rationality and accuracy of the server performance detection result can be improved.

Description

A server performance detection method, device and equipment

technical field

The present invention relates to the field of communication technology, in particular to a server performance detection method, device and equipment.

Background technique

With the continuous development of information technology and the gradual increase of user access, the performance of a single server can no longer meet the access needs of a large number of users. At present, most of them provide users with stable and reliable network access services by deploying multiple groups of servers.

In order for these groups of servers to provide users with good access services, after receiving access requests from client users, the access requests can be distributed to multiple servers through service load balancing technology, and these multiple servers will respond together. The request should be accessed. It can be seen that the response to access requests mainly depends on the performance of the server allocated to the user during the load balancing process. If the performance of the server allocated to the user is good, the response time is short and the user experience is good; failure, it will prolong the response time and degrade the user experience. In order to obtain the service performance information of the server, there is currently a scheme for detecting the performance status of the server. The following takes the DNS service as an example to briefly introduce this performance detection scheme:

First, the load balancing device sends a detection message to a DNS server, and the detection message carries an identification code TransactionID. Then, the DNS server responds to the load balancing device and feeds back a response message to it, and the response message carries the identification code obtained by the DNS server from the detection message. Finally, the load balancing device judges the performance of the DNS server according to the identification code. This is mainly because, when the DNS server works normally, the identification code obtained by the DNS server should be consistent with the identification code in the detection packet. Therefore, if the load balancing device determines that the identification code carried in the response packet If the identification codes are the same, the server is considered available and can be allocated to users during the load balancing process; otherwise, the server is considered unavailable and cannot be allocated to users temporarily.

It can be seen from the above process that the current performance test is only to determine whether the server is available, but as we all know, the fact that the server can work normally does not mean that it can provide users with good services. In this way, if load balancing is performed only based on the current performance test results, the rationality of server allocation may be reduced, resulting in a long response time for the server to provide services to users, and in serious cases, it may not be able to provide services to users.

Contents of the invention

The server performance detection method, device and equipment provided by the embodiments of the present invention are used to improve the rationality and accuracy of the detection results when detecting the server performance.

For this reason, the embodiment of the present invention provides following technical scheme:

In a first aspect, a method for detecting server performance is provided, the method comprising:

The detection device sends a first detection message to the server under test, where the first detection message carries first information;

The detection device receives a first response message returned by the server under test corresponding to the first detection message, the first response message carries second information, and the second information and the first information There is a mapping relationship between them;

The detection device determines whether the server under test is in an available state;

Based on the detection device determining that the server under test is in an available state, the detection device acquires a first interval between the first detection message and the first response message;

The detection device determines the performance level of the server under test according to the first interval length.

In a first possible implementation manner of the first aspect, the detection device is configured with a preset database, and the preset database stores the first information. Then, when the detection device sends the first Before detecting the message, the method also includes:

The detection device reads the first information from the preset database, and uses the first information to generate the first detection message.

With reference to the first possible implementation of the first aspect, in the second possible implementation of the first aspect, the preset database also stores first-level information of the first information, and the detection The device determines the performance level of the server under test according to the first interval length, including:

The detection device determines the performance level of the server under test according to the first interval length and the first level information.

With reference to the second possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, the first level information is the access frequency or the network resource identified by the first information. The category to which the first information belongs is set.

With reference to any of the first to third possible implementations of the first aspect, in a fourth possible implementation of the first aspect, the preset database also stores the identity of the server under test identify the corresponding relationship with the first information, before the detection device sends the first detection message to the server under test, the method further includes:

The detection device selects the identity of the server under test from the corresponding relationship according to the first information.

With reference to any one of the first to fourth possible implementations of the first aspect, in a fifth possible implementation of the first aspect, based on the detection device determining that the server under test is in an available state, The method also includes:

The detection device sends a second detection message to the server under test, and the second detection message carries third information;

The detection device receives a second response message returned by the server under test corresponding to the second detection message, the second response message carries fourth information, and the fourth information and the third information There is a mapping relationship between them;

The detection device acquires a second interval between the second detection message and the second response message;

The detection device determines the performance level of the server under test according to the first interval length, including:

The detecting device determines the performance level of the server under test according to the second interval length, and uses the performance level determined according to the first interval length and the performance level determined according to the second interval length to calculate the the average performance rating of the server under test; or,

The detection device uses the first interval length and the second interval length to calculate an interval duration average value, and determines the performance level of the server under test according to the interval duration average value.

In combination with the first aspect or any of the first to fifth possible implementation manners of the first aspect, in a sixth possible implementation manner of the first aspect, the method further includes:

Based on the detection device determining that the server under test is in an unavailable state, return to the step of sending the first detection message to the server under test by the detection device until a preset condition is met; the preset condition is a preset condition Set the execution times or preset execution time length.

In combination with the first aspect or any of the first to sixth possible implementations of the first aspect, in a seventh possible implementation of the first aspect, the server under test is a DNS server, and the The first detection packet is a DNS request packet, the first response packet is a DNS response packet, the first information is a first domain name, and the second information is an IP address.

In a second aspect, a device for detecting server performance is provided, the device comprising:

A sending unit, configured to send a first detection message to the server under test, where the first detection message carries first information;

a receiving unit, configured to receive a first response message returned by the server under test corresponding to the first detection message, where the first response message carries second information, and the second information is the same as the first There is a mapping relationship between information;

A state determining unit, configured to determine whether the tested server is in an available state;

An obtaining unit, configured to obtain a first interval between the first detection message and the first response message based on the state determination unit determining that the server under test is in an available state;

A level determining unit, configured to determine the performance level of the server under test according to the first interval duration acquired by the acquiring unit.

In a first possible implementation manner of the second aspect, the device is configured with a preset database, and the preset database stores the first information, and the device further includes:

a reading unit, configured to read the first information from the preset database before the sending unit sends the first detection message to the server under test, and use the first information to generate The first detection message.

With reference to the first possible implementation of the second aspect, in the second possible implementation of the second aspect, the preset database also stores the first level information of the first information, then

The level determination unit is specifically configured to determine the performance level of the server under test according to the first interval duration and the first level information; the first level information is the network identified by the first information The resource is set by the access frequency or the category to which the first information belongs.

With reference to the first or second possible implementation of the second aspect, in a third possible implementation of the second aspect, the preset database also stores the identity of the server under test and the For the corresponding relationship of the first information, before the detection device sends the first detection message to the server under test, the device further includes:

A selection unit, configured to select the identity of the server under test from the corresponding relationship according to the first information before the sending unit sends the first detection message to the server under test.

With reference to the second or third possible implementation of the second aspect, in a fourth possible implementation of the second aspect, based on the state determination unit determining that the server under test is in an available state,

The sending unit is further configured to send a second detection message to the server under test, where the second detection message carries third information;

The receiving unit is further configured to receive a second response message returned by the server under test corresponding to the second detection message, the second response message carries fourth information, and the fourth information is related to the second detection message. There is a mapping relationship between the third information;

The acquiring unit is further configured to acquire a second interval between the second detection message and the second response message;

The level determining unit is specifically configured to determine the performance level of the server under test according to the second interval length, and use the performance level determined according to the first interval length and the performance level determined according to the second interval length. The performance level calculates the average value of the performance level of the server under test; or,

The level determining unit is specifically configured to use the first interval length and the second interval length to calculate an interval duration average, and determine the performance level of the server under test according to the interval interval average value.

With reference to the second aspect or any of the first to fourth possible implementation manners of the second aspect, in a fifth possible implementation manner of the second aspect, the sending unit is further configured to, based on the The state determination unit determines that the server under test is in an unavailable state, and continues to send the first detection message to the server under test until a preset condition is met; the preset condition is a preset number of executions or a preset Set the execution time length.

In a third aspect, a server performance detection device is provided, and the device includes: a processor, a memory, and a network interface;

The memory is used to store program instructions and data;

The processor is configured to read instructions and data stored in the memory, and perform the following operations:

triggering the network interface to send a first detection message to the server under test, where the first detection message carries first information;

Receive the first response message returned by the server under test corresponding to the first detection message through the network interface, the first response message carries second information, and the second information is consistent with the first There is a mapping relationship between information;

determining whether the tested server is in an available state;

Obtaining a first interval between the first detection message and the first response message based on determining that the server under test is in an available state;

Determine the performance level of the server under test according to the first interval length.

In a first possible implementation manner of the third aspect, the detection device is configured with a preset database, and the preset database stores the first information, and when the triggering the network interface sends a message to the server under test Before sending the first detection message, the processor is further configured to perform the following operations:

Reading the first information from the preset database, and using the first information to generate the first detection message.

With reference to the first possible implementation of the third aspect, in a second possible implementation of the third aspect, the preset database also stores first-level information of the first information, and the processing The controller determines the performance level of the server under test according to the first interval length, including:

Determine the performance level of the server under test according to the first interval length and the first level information; wherein, the first level information is the access frequency of network resources identified by the first information or the The category to which the first information belongs is set.

With reference to the first or second possible implementation of the third aspect, in a third possible implementation of the third aspect, the preset database also stores the identity of the server under test and the For the corresponding relationship of the first information, before the triggering of the network interface to send the first detection message to the server under test, the processor is further configured to perform the following operations:

Select the identity of the server under test from the corresponding relationship according to the first information.

With reference to any one of the first to third possible implementations of the third aspect, in a fourth possible implementation of the third aspect, based on determining that the server under test is in an available state, the processor Also used to do the following:

triggering the network interface to send a second detection message to the server under test, where the second detection message carries third information;

The second response message returned by the server under test corresponding to the second detection message is received through the network interface, the second response message carries fourth information, and the fourth information is the same as the third There is a mapping relationship between information;

Obtain a second interval between the second detection message and the second response message;

The determining the performance level of the server under test according to the first interval length includes:

Determine the performance level of the server under test according to the second interval length, and calculate the performance level of the server under test by using the performance level determined according to the first interval length and the performance level determined according to the second interval length. Performance Rating Mean; or,

Using the first interval length and the second interval length to calculate an interval duration average, and determine the performance level of the server under test according to the interval interval average value.

With reference to the third aspect or any of the first to fourth possible implementation manners of the third aspect, in a fifth possible implementation manner of the third aspect, the processor is further configured to perform the following operations:

Based on determining that the server under test is in an unavailable state, return to execute the operation of triggering the network interface to send a first detection message to the server under test until a preset condition is met; the preset condition is a preset The number of executions or the preset execution time length.

In the server performance detection method, device, and equipment of the embodiments of the present invention, when server performance detection is required, the detection device sends a first detection message to the server under test, and receives the first detection message returned by the server under test for the first detection message. Response message, so that the detection device can use the first detection message and the first response message to determine the working status of the server under test, and when the server under test is in an available state, according to the first detection message and the first The first interval between response messages determines the performance level of the server under test. This is mainly because the interval length can reflect the response speed of the server under test to a certain extent. Therefore, the embodiment of the present invention can combine the working status and response speed of the server under test to determine the more differentiated status of the server under test. The high performance level improves the accuracy of performance test results. In this way, the rationality of the load balancing device performing load balancing based on the performance detection results of the embodiments of the present invention is improved, thereby ensuring that the allocated servers can provide client users with access services of good quality.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments described in this application, and those skilled in the art can also obtain other drawings based on these drawings.

FIG. 1 is a schematic diagram of a network for DNS server performance detection in an embodiment of the present invention;

Fig. 2 is the schematic diagram of the recursive query of the embodiment of the present invention;

3 is a schematic flow diagram of a server performance detection method according to an embodiment of the present invention;

FIG. 4-1 is a schematic diagram of a timing sequence of a server performance detection process according to an embodiment of the present invention;

FIG. 4-2 is another schematic diagram of the sequence of the server performance detection process according to the embodiment of the present invention;

FIG. 4-3 is another schematic diagram of the sequence of the server performance detection process according to the embodiment of the present invention;

5 is a schematic diagram of the composition of a server performance detection device according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of a server performance detection device according to an embodiment of the present invention.

detailed description

In order to enable those skilled in the art to better understand the solution of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings and implementation manners.

Before introducing the technical solutions of the embodiments of the present invention, the specific application scenarios of the present invention will be explained first.

Service load balancing technology provides a cheap, effective and transparent method to expand the bandwidth of network devices and servers, increase throughput, strengthen network data processing capabilities, and improve network flexibility and availability. When load balancing is required, the load balancing device will distribute the client user's access requests to multiple servers, and these multiple servers will provide client users with access services in parallel.

In order to enable the server to provide good services for client users, at present, the server performance is mainly reflected through the server working status (which can be reflected as available status and unavailable status), and then the load balancing device uses the load balancing algorithm to start from the available status. Select the server assigned to the client user in Status Server. In the following, the existing server performance testing process will be explained in conjunction with the DNS (Domain Name System, Domain Name System) performance testing network schematic diagram shown in FIG.

First, under the condition of ensuring that the interface of the entire network is running normally (it can be understood that the interface status is UP), the load balancing device (128.18.52.51) uses the DNS protocol to initiate a DNS request to the DNS server under test (128.18.52.55) (that is, up The detection message in the text), for example, requesting access to the server corresponding to the domain name www.huawei.com, at this time, the DNS request carries at least the domain name requested for access and an identification code (the identification code is generated by the sender of the DNS request and used to identify query and response, and pair the corresponding query and response. The identification code can be marked as TransactionID).

Secondly, after receiving the DNS request, the DNS server under test performs the following three actions: first, perform domain name resolution to obtain the IP address of the server corresponding to the domain name; second, obtain the identification code in the DNS request; third, convert the IP address to and the identification code are added to the DNS response (that is, the response message above), and the DNS response is sent to the load balancing device.

Finally, after the load balancing device receives the DNS response, it judges whether the identification code in the response is consistent with the identification code in the request. If it is consistent, it determines that the working status of the DNS server under test is available; The working state of the DNS server is unavailable. Correspondingly, the load balancing device will modify the algorithm for assigning servers to users, and will not assign such unavailable DNS servers to users for the time being.

Based on the above-mentioned existing server performance detection scheme, it can be guaranteed that the server allocated to the user can provide the user with access service, but it cannot guarantee that the server can provide the user with good quality access service. The factors that affect the service quality of the server are illustrated below with examples.

The first factor is that the mapping relationship between the domain name and the IP address is not cached locally on the DNS server.

After the client receives the http://www.huawei.com entered by the user, it will send DNS to the DNS server assigned to the client by the load balancing device (the DNS server assigned to the client can be called a LocalDNS server). ask. Correspondingly, after the LocalDNS server receives the DNS request, it first checks whether there is a valid mapping relationship of www.huawei.com cached in its local cache:

If yes, perform domain name resolution directly according to the mapping relationship to obtain the IP address of the server corresponding to www.huawei.com. In this way, the LocalDNS server can respond to client requests in a short time and with less resource consumption, providing services for users. Provide high-quality access services.

If not, a recursive query is performed. For details, refer to the query schematic diagram shown in FIG. 2 . The LocalDNS server selects a root DNS server from the root DNS server list preconfigured on the machine, and sends a request to query www.huawei.com to it. Because the authoritative DNS server corresponding to the top-level domain is recorded in the root DNS server, in this example the root DNS server will return the IP address of the authoritative DNS server corresponding to the .com domain to the LocalDNS server. In this way, the LocalDNS server can continue to initiate a domain name resolution request for www.huawei.com to the authoritative DNS server corresponding to the .com domain, and the authoritative DNS server corresponding to the .com domain returns the IP address of the authorized domain server corresponding to huawei.com to the LocalDNS server address. Finally, the LocalDNS server continues to initiate a domain name resolution request for www.huawei.com to the authorized domain server corresponding to huawei.com, and the authorized domain server corresponding to huawei.com returns the IP address of the server corresponding to www.huawei.com to the LocalDNS server. Then, the resolved IP address is returned to the client browser through the LocalDNS server, and the browser initiates an HTTP GET command to port 80 of the server IP address corresponding to www.huawei.com. In this way, the server can respond to the client request and send It returns the content requested by the client user.

From the above recursive query process, it can be seen that when the LocalDNS server does not cache the mapping relationship between domain names and IP addresses locally, the LocalDNS server takes a long time and consumes more resources to respond to client requests, and the access quality provided to users is poor. .

The second factor is that the DNS server bears a large load.

When the DNS server is available, the amount of load on the server will also affect the quality of service of the server. In general, the amount of load on the server is inversely proportional to the length of the server's response, that is, the less the load on the server, the shorter the time it takes to respond to client requests; otherwise, the longer the response time. Still taking the performance testing network diagram shown in Figure 1 as an example, the load carried by the first DNS server (128.18.52.55) is close to full, and the second DNS server (128.18.52.56) is relatively idle. In the available state, during the load balancing process, the load balancing device may assign these two servers to the client. Generally, when a client sends an access request to its assigned server, it will not perform any weighting or restriction processing. In this way, it may cause new loads to be continuously added to the first DNS server, and new DNS requests will be continuously added. As a result, the first DNS server is overloaded or even crashed.

To sum up, it can be seen that the existing server performance detection scheme cannot correctly reflect the server performance, so it will affect the rationality of allocating servers to clients in the process of load balancing, resulting in the quality of services provided by the allocated servers for clients. Poor (such as long response time), high cost (such as resource consumption). The scheme of the embodiment of the present invention is proposed for this purpose, and aims to provide a new method for detecting server performance, improve the accuracy of detection results, thereby improving the rationality of the load balancing process, improving the service quality of the allocated servers, etc. Provide some technical support.

Referring to FIG. 3 , it shows a schematic flowchart of a server performance detection method according to an embodiment of the present invention, which may include the following steps:

Step 101, the detection device sends a first detection message to the server under test, where the first detection message carries first information.

In order to improve the accuracy of server performance detection, the embodiment of the present invention not only detects the working state of the server, but also detects the response speed of the server, and determines the performance level of the server according to the two aspects of information. Specifically, the response speed of the server can be reflected by the time it takes for the server to respond to the access request. To this end, the detection device can first send a first detection packet to the server under test, and wait for the response returned by the server under test for the first detection packet. For the first response, the interval between the first detection packet and the first response packet is used as the time for the server to respond to the access request.

As an example, the detection device may receive first information input from the outside, and generate a first detection message and send it to the server under test. Taking the server under test as a DNS server as an example, after receiving the external domain name www.huawei.com, the detection device can use the DNS protocol to generate a DNS request carrying at least the domain name www.huawei.com. Under such a solution, the detection device can use the externally specified first information to perform performance detection on the server under test. It should be noted that the first information can be input to the detection device by an external detection personnel through a command line, or can also be input to the detection device by an external device (such as a load balancing device, a client, etc.), which is not required in this embodiment of the present invention. Be specific.

Or, as an example, the detection device can also be configured with a preset database, and the first information is stored in the preset database, so that when performance detection is required, the detection device can read the first information from the preset data. information, generate a first detection packet and send it to the server under test. Taking the server under test as an example of a DNS server, the detection device can read the first information (for example, www.huawei.com) from the database after receiving the trigger information input from the outside, and use the DNS protocol to generate at least www.huawei. DNS requests for .com. With such a solution, the detection device can randomly read the first information from the database, and actively use the first information to perform performance detection on the server under test. It should be noted that the trigger information can be an externally input trigger instruction, or an externally input DNS request (the domain name carried by the DNS request is different from the domain name carried by the first detection message, such as the DNS The domain name carried in the request is www.baidu.com. After receiving the trigger information, the detection device reads the domain name www.huawei.com from the database, replaces www.baidu.com in the original DNS request, and generates the first detection packet ). Likewise, the trigger information may be input by an external device or an external inspector, and the embodiment of the present invention does not specifically limit the input source and expression form of the trigger information.

Step 102, the detection device receives a first response message returned by the server under test corresponding to the first detection message, the first response message carries second information, and the second information is consistent with the There is a mapping relationship between the first information.

After the detection device sends the first detection message to the server under test, it starts to wait for the first response message fed back by the server under test, wherein the first response message carries at least second information, and the second information is consistent with There is a mapping relationship between the first information in the first detection message. Still taking the server under test as a DNS server as an example, the first detection message is a DNS request, the first information is the domain name requested to access, the first response message is a DNS response message, and the second information is the server that provides services corresponding to the domain name IP address, the mapping relationship is the mapping relationship between domain names and IP addresses.

Step 103, the detection device determines whether the server under test is in an available state.

After the detection device sends the first detection message to the server under test and receives the first response message returned by the server under test, step 103 can be performed to determine whether the working state of the server under test is available.

As an example, the detection device may determine the working status of the server under test according to the identification code. That is, the first detection message carries an identification code in addition to the first information, and the first response message carries an identification code in addition to the second information. In this way, the detection device can follow the above introduction, according to The identification code judges whether the working status of the server under test is available, and the specific process will not be repeated here.

Or, as an example, the detection device may also determine the working state of the server under test according to the indication information input from the outside. Specifically, an external device (such as a load balancing device, a client, etc.) can judge the working status of the server under test according to the identification code carried in the first detection message and the first response message according to the above introduction, and Add the judgment result to the instruction information and send it to the detection device; or, after the external detection personnel know the working state of the server under test, they input the working state of the server under test into the detection device through the command line. Be specific.

Step 104: Based on the detection device determining that the server under test is in an available state, the detection device acquires a first interval between the first detection message and the first response message.

Step 105, the detection device determines the performance level of the server under test according to the first interval length.

After step 103, if the detection device determines that the server under test is in an available state, the detection device can obtain the first interval between the first detection message and the first response message, and then use the first interval to determine the tested server. The performance class of the server. Specifically, the shorter the interval time, the faster the response speed of the server under test and the better the performance; otherwise, the slower the response speed of the server under test and the worse the performance. If it is assumed that the lower the server performance level is, the better the server performance is, then the relationship Y=f(D) between the interval duration (D) and the performance level (Y) can be expressed as a proportional relationship Y=kD, where k is a proportional coefficient, It can be expressed as any positive number as required.

As an example, the server performance level can be divided into two levels, from low to high: good performance (can be defined as level 1), poor performance (can be defined as level 2), so that an interval can be set threshold, and when the first interval duration does not exceed the threshold, it is determined that the performance level of the server under test is good performance; when the first interval duration exceeds the threshold, it is determined that the performance level of the server under test is poor performance. Alternatively, a performance threshold can also be set, that is, after configuring the k value, calculate the performance value Y of the server under test corresponding to the first interval duration according to Y=kD, and determine the performance of the server under test when Y does not exceed the performance threshold The performance level is good; when Y exceeds the performance threshold, it is determined that the performance level of the server under test is poor performance. Specifically, the threshold setting, k value configuration, etc. may be determined according to actual usage requirements, which may not be specifically limited in this embodiment of the present invention.

In addition, considering that there may be many factors that affect the interval, such as whether there is a mapping relationship in the local cache of the server under test, the amount of load carried by the server under test, the processing capacity of the server under test itself, and the relationship between the server under test and the detection device. Therefore, as an example, the above-mentioned factors that affect the interval length can be combined arbitrarily, and the relationship between the interval length and the server performance level under each combination can be calculated, and the server performance level can be divided into multiple levels. For example, the performance of the final division from high to low is: excellent performance (can be defined as level 1), good performance (can be defined as level 2), medium performance (can be defined as level 3), poor performance (can be defined as level 4), and the thresholds between performance levels are set according to the statistical results of each combination, so that the performance level of the server under test can be determined in more detail. Specifically, the threshold for distinguishing performance levels can be embodied as an interval duration threshold, so that the detection device can compare the first interval duration with each interval duration threshold to determine the performance level of the server under test; or, the threshold for distinguishing performance levels It can also be embodied as a performance threshold. In this way, the detection device can use the configured k value and the first interval duration D to calculate the performance value Y of the server under test, and compare the performance value Y with each performance threshold to determine the value of the server under test. The performance class of the server. Specifically, the factors that affect the interval length, the combination of various factors, the divided performance level, the threshold setting, the k value configuration, etc. can all be determined according to actual usage requirements, which is not specifically limited in the embodiment of the present invention.

To sum up, in the embodiment of the present invention, after determining that the server under test is in an available state, the performance level of the server under test will be further clarified in combination with the interval between the detection message and the response message, because the interval time can vary to a certain extent. It reflects the response speed of the server under test to process the request, so the solution of the embodiment of the present invention can improve the accuracy of the server performance detection result, thereby improving the rationality of the load balancing device performing load balancing based on the performance detection result of the embodiment of the present invention, thereby ensuring that all The distribution server can provide client users with good quality access services.

It should be noted that the detection device in the embodiment of the present invention can be an independent device connected between the client and the server under test; or, the function of the detection device can also be integrated in the load balancing device without changing The connection relationship of the live network may not be specifically limited in this embodiment of the present invention.

In addition, it should also be noted that, as the example above, the server under test in the embodiment of the present invention can be embodied as a DNS server, or the server under test can also be embodied as a call center server, CDN (ContentDistributionNetwork, content distribution network) The content distribution server and the like in the server can cache the mapping relationship between the first information and the second information locally. If the server under test is a call center server, then the first detection message is a call request, the first information is the account number of the called user (generally can be embodied as the phone number of the called user), and the first response message is a call response, The second information is the client IP address corresponding to the called user, and the mapping relationship is the mapping relationship between the account and the IP address. If the server under test is a content distribution server, the first detection message is a content access request, the first information is the content information of the requested access (which can be embodied as the URL, keywords, titles, etc. corresponding to the content), and the first response message The text is the content access response, the second information is the IP address of the cache server, and the mapping relationship is the mapping relationship between the content information and the IP address of the cache server. It should be noted that the cache server can be understood as a local content source server The interaction point obtains the content corresponding to the content information from the content source server, and caches the content locally. Then, when the client accesses the cache server through the IP address provided by the content distribution server, the content corresponding to the content information can be obtained.

The following takes the DNS server as an example to explain the performance detection process of the embodiment of the present invention.

Example 1

For the DNS server under test, multiple domain names are saved in the preset database configured by the testing device, as shown in Table 1 below for details:

Numbering domain name 1 www.huawei.com 2 www.baidu.com 3 www.sina.com 4 www.cnki.net … …

Referring to the sequence diagram shown in Figure 4-1, the performance detection process of this embodiment may include the following steps:

1. The detection device receives an externally input DNS request, which carries the domain name www.sina.com, so that the detection device can be triggered to read a detection domain name from the preset database, for example, the read domain name is www .huawei.com (that is, the first information above).

2. The detection device changes the packet encapsulation mode of the DNS request, changing www.sina.com to www.huawei.com to form a new DNS request. As an example, the detection device may decapsulate the Queries field of the DNS request, and add the domain name used for detection to the Name of the Queries field to form a new DNS request.

3. The detection device sends a modified DNS request (that is, the first detection message above) to the DNS server under test. The request carries the domain name www.huawei.com and the identification code TransactionID.

4. The DNS server under test receives the DNS request sent by the detection device, performs domain name resolution to obtain the IP address that has a mapping relationship with www.huawei.com (that is, the second information above), and obtains the IP address and the DNS request from it. The identification code is added to the DNS response message (that is, the first response message above), and the DNS response message is sent to the detection device.

5. The detection device receives the DNS response message sent by the DNS server under test, and determines the following two information:

(1) The working status (S) of the DNS server under test can be obtained by comparing the identification codes, and will not be repeated here. As an example, when the DNS server under test is unavailable, S=0 may be recorded, and when the DNS server under test is available, S=1 may be recorded.

(2) Record the time of sending the DNS request and the time of receiving the DNS response message to obtain the interval duration Delay(D) (that is, the first interval duration above).

6. When determining that the DNS server under test is in an available state (i.e. S=1), the detection device uses the interval duration D to calculate the performance value Y=kD*S of the DNS server under test, wherein the value of k can be determined as required , generally taken as a positive number.

7. The detection device compares the calculated performance value Y with the preset performance threshold to obtain the performance level of the DNS server under test. In this way, the server performance detection process of the embodiment of the present invention is completed.

It should be noted that, after the detection device is triggered to perform performance detection, as described in Embodiment 1, only one domain name for detection is read from the preset database, and the domain name is used to perform performance detection on the DNS server under test; Alternatively, the performance test can also be performed in a loop, that is, according to the solution shown in Embodiment 1, after a performance test is completed using a read domain name, another domain name can be read from the preset database, and the read domain name can be continued. The test DNS server is used for performance testing, and so on, until each domain name in the database is used for performance testing, or until the performance testing process is stopped by the control. In this way, the performance detection results of at least two domain names can be averaged, and the average value can be used as the performance detection result of the DNS server under test, which further improves the accuracy of the performance detection results of the embodiment of the present invention.

In addition, it should be noted that, in the embodiment of the present invention, after a performance test is performed by using a certain domain name, the domain name may be read from the read database again, and then used to perform a performance test again. This is mainly because factors that affect server performance may change at any time. For example, the DNS server under test did not cache the mapping relationship between the domain name www.huawei.com and the IP address at the beginning, but when using the domain name www.huawei.com During a server performance testing process, the DNS server under test will obtain the mapping relationship through recursive query, and cache it locally on the DNS server under test, resulting in changes in factors affecting server performance; or, the DNS server under test Changes in load conditions, changes in the number of requests processed by the tested DNS server, changes in the network environment between the tested DNS server and the detection device, etc., may cause changes in the performance test results of the tested server. The same domain name is used to perform multiple performance tests on the DNS server under test. In this way, the accuracy of the performance test results of the embodiment of the present invention can be further improved. As an example, the last performance test result corresponding to a domain name can be used as the performance test result of the DNS server under test, or the average value of multiple performance test results corresponding to the domain name can be used as the performance test result of the DNS server under test , which may not be specifically limited in this embodiment of the present invention.

Example 2

For the DNS server under test, multiple domain names and the level information corresponding to each domain name are saved in the preset database configured by the detection device, as shown in Table 2 below for details:

Numbering domain name level information 1 www.huawei.com 1 2 www.baidu.com 2 3 www.sina.com 2 4 www.cnki.net 1 … … …

In this embodiment, a corresponding level information is also set for the domain name in the database, and the performance level of the server under test is determined in combination with the working status, interval time, and level information of the server under test. Referring to the sequence diagram shown in Figure 4-2, the performance detection process of this embodiment may include the following steps:

Steps 1 to 5 are the same as Steps 1 to 5 in Embodiment 1 above, and will not be repeated here.

6. When determining that the DNS server under test is in an available state (i.e. S=1), the detection device uses the interval duration D and the level information X to calculate the performance value Y=(kD+mX)*S of the DNS server under test, where k , The value of m can be determined according to the needs, and it is generally taken as a positive number.

7. The detection device compares the calculated performance value Y with the preset performance threshold to obtain the performance level of the DNS server under test. In this way, the server performance detection process of the embodiment of the present invention is completed.

Specifically, the level information of the domain name can be set according to the access frequency of the network resource identified by the domain name. As an example, the level information can be embodied as: commonly used (corresponding to level 1), less commonly used (corresponding to level 2), and rarely used (Corresponding to level 3, not shown in Table 2). Alternatively, the level information corresponding to the domain name can also be set according to the category to which the domain name belongs, that is, the levels of various service categories can be set according to the user's access habits. For example, if a user frequently visits communication technology websites, the service category can be set to level 1. In this way, when the server corresponding to a domain name can provide communication technology services for users, the level information of the domain name can be set to 1.

It should be noted that, in combination with Y=(kD+mX)*S, it can be known that the relationship between level information and performance level should be consistent with the relationship between interval duration and performance level, that is, if the interval duration and performance level If there is a proportional relationship, then there should be a proportional relationship between the level information and the performance level. In this case, the lower the level of information corresponding to the domain name (that is, the higher the frequency of access, or in line with user access habits), the shorter the interval between the detection message and the response message, and the higher the calculated server performance value Y is. The smaller the value, the lower the determined server performance level (that is, the better the performance).

In addition, the process of setting the level information for the domain name may be executed by the detection device, or may be executed by other external devices and loaded to the detection device, which is not specifically limited in this embodiment of the present invention.

In addition, it should be noted that the values of the coefficients k and m in Y=(kD+mX)*S can be configured according to actual needs. The following uses two specific scenarios as examples to explain how to configure the values of k and m.

Scenario 1: Configure the values of k and m to distinguish the impact of the interval duration and level information on the calculation server performance value Y, that is, set the weight of the interval duration and level information by configuring the values of k and m.

Scenario 2: When the interval time and the magnitude of the level information are inconsistent, configure the values of k and m to ensure the rationality of the calculated server performance value Y. For example, if the level information corresponding to a domain name is X=1, and the interval duration D=30ms, then the value of m can be configured as m=10, and the value of k can be configured as k=1. In this way, the calculated server performance The value Y=40 makes the performance value Y more reasonable. It should be noted that, in this way, in order to ensure the accuracy and consistency of the calculated performance values during the detection process, the values of k and m should be kept unchanged, unless the interval length and the magnitude of the level information occur due to changes in the existing network. When the value changes, the values of the two are adjusted.

It should be noted that, in order to further improve the accuracy of the performance test results of the embodiment of the present invention, this embodiment can also be described in Embodiment 1. After a performance test is completed by using a read domain name, it can also continue from Read another domain name from the preset database, and continue to perform performance testing on the DNS server under test, and so on, until each domain name in the database is used to perform a performance test, or until the process of performance testing is stopped by the control. Or, after using a certain domain name to perform a performance test, the domain name can be read from the read database again, and then used to perform a performance test again. In this regard, the embodiments of the present invention do not make specific limitations.

Example 3

On the basis of the above-mentioned embodiments, the preset database configured by the detection device may also store the identities of multiple servers, and the corresponding relationship between the identities of each server and the domain name. Of course, on the basis of Table 2 shown in Embodiment 2, the level information corresponding to each domain name can also be stored in the database, as shown in Table 3 below for details:

The performance testing process may include the following steps:

On the basis of the solutions shown in Embodiments 1 and 2 above, after the detection device performs step 1 to read the domain name for detection (that is, the first information in the above), it can also perform the following steps: the detection device according to the first information, and select the identity of the server under test from the corresponding relationships stored in the preset database. In this way, the detection device can send the modified DNS request to the server under test with the selected identity. It should be noted that the step of selecting the identity of the server under test can be performed before step 2, after step 2, or simultaneously with step 2, which is not specifically limited in this embodiment of the present invention, as long as the step 3 Select the server under test before.

That is to say, after the detection device determines the domain name used in the performance detection process, for example, the domain name used for detection is www.baidu.com, the identity of the server under test corresponding to the domain name can be searched from the preset database accordingly 1. Let the detection device know who the current object under test is, and then send a detection message to the server under test with ID 1. Alternatively, the detection device can also determine multiple domain names for detection, for example, if the domain names for detection are www.baidu.com and www.huawei.com, then the identity of the server under test corresponding to the two domain names can be searched accordingly 1, and then send a detection message to the server under test with identity 1 (in this case, the detection device sends two detection messages to the server under test successively, and the two detection messages carry different domain names respectively).

It should be noted that the servers under test with different identities may correspond to the same domain name, that is, multiple servers can perform domain name resolution on a certain domain name. As shown in Table 3 above, the tested servers with IDs 1 and 2 correspond to the domain name www.huawei.com. After the testing device determines the domain name www.huawei.com used in the performance testing process, it can use the domain name Carry out performance detection to the server under test of identity mark 1, 2 respectively, perhaps, also can preset detection rule, when this situation occurs, only utilize this domain name to carry out performance detection to the server under test specified by rule, the present invention implements For example, there is no specific limitation on this.

Similarly, in order to improve the accuracy of the performance test results of this embodiment of the present invention, this embodiment can also use different domain names to perform multiple performance tests on the same server under test as described in Embodiment 1, or use the same domain name Multiple performance tests are performed on the same server under test, which is not specifically limited in this embodiment of the present invention.

Example 4

As introduced above, the embodiments of the present invention can use different domain names to perform multiple performance tests on the same server under test, so as to improve the accuracy of the performance test results of the embodiments of the present invention. Taking the example in Table 3 as an example, the process of calculating the performance level of the server under test with identity 1 by using www.baidu.com and www.huawei.com is explained below.

Referring to the timing diagram shown in Figure 4-3, the performance detection process of this embodiment may include the following steps:

1. The detection device receives an externally input DNS request carrying the domain name www.sina.com, and is triggered to read a detection domain name from the preset database. For example, the read domain name is www.baidu.com (that is, the above-mentioned first message).

2. The detection device searches the preset database, selects the server ID 1 corresponding to the domain name www.baidu.com, and determines the DNS server with this ID as the DNS server to be tested.

3. The detection device changes the packet encapsulation mode of the DNS request, and changes www.sina.com to www.baidu.com to form a new DNS request.

4. The detection device sends a modified DNS request (that is, the first detection message above) to the DNS server under test, and the request carries the domain name www.baidu.com and the identification code TransactionID.

5. The DNS server under test receives the DNS request sent by the detection device, performs domain name resolution to obtain the IP address that has a mapping relationship with www.baidu.com (that is, the second information above), and obtains the IP address and the DNS request from it The identification code is added to the DNS response message (that is, the first response message above), and the DNS response message is sent to the detection device.

6. The detection device receives the DNS response message sent by the DNS server under test, and determines the following two information:

(1) The working status (S) of the DNS server under test can be obtained by comparing the identification codes, and will not be repeated here. As an example, when the DNS server under test is unavailable, S=0 may be recorded, and when the DNS server under test is available, S=1 may be recorded.

(2) Record the time of sending the first detection message and the time of receiving the first response message to obtain the interval duration Delay(D) (that is, the first interval duration above).

7. When the detection device determines that the DNS server under test is available, it uses Y=(kD+mX)*S to calculate the performance value Y1 of the DNS server under test corresponding to the first interval.

8. The detection device continues to read other domain names corresponding to the DNS server under test from the preset database, for example, the read domain name is www.huawei.com (that is, the third information in the embodiment of the present invention)

9. The detection device changes the packet encapsulation mode of the DNS request, and changes www.sina.com to www.huawei.com to form a new DNS request.

10. The detection device sends a modified DNS request (that is, the second detection message in the embodiment of the present invention) to the DNS server under test. The request carries the domain name www.huawei.com, an identification code (which can be compared with the first detection message The identification codes herein are the same or different, which is not specifically limited in this embodiment of the present invention).

11. The DNS server under test receives the DNS request sent by the detection device, performs domain name resolution to obtain the IP address that has a mapping relationship with www.huawei.com (that is, the fourth information above), and obtains the IP address and the DNS request from it. The identification code is added to the DNS response message (that is, the second response message in the embodiment of the present invention), and the DNS response message is sent to the detection device.

12. The detection device receives the DNS response message sent by the DNS server under test, records the time of sending the second detection message and the time of receiving the second response message, and obtains the interval duration Delay (D) (that is, in the embodiment of the present invention second interval). It should be noted that, in order to simplify the processing, after the last detection process determined that the server is in an available state, this detection process can no longer perform working status detection. Of course, in order to ensure the accuracy of the detection results, prevent the server from working during the two detection processes Changes in the status will affect the detection results. In this detection process, the identification code can also be used to detect the working status of the DNS server under test again, which is not specifically limited in this embodiment of the present invention.

13. When the detection device determines that the DNS server under test is available, it uses Y=(kD+mX)*S to calculate the performance value Y2 of the DNS server under test corresponding to the second interval.

14. The detection device calculates the performance average value Y=(Y1+Y2)/2, and compares the performance average value Y with the preset performance threshold to obtain the performance level of the DNS server under test. In this way, the server performance detection process of the embodiment of the present invention is completed.

In addition, as an example, after recording the first interval duration and the second interval duration, first use them to calculate the average interval duration, and then use Y=(kD+mX)*S to calculate the corresponding passive value of the interval duration average value. Measure the performance value Y3 of the DNS server, and compare Y3 with the preset performance threshold to obtain the performance level of the DNS server under test. Alternatively, after using the first interval to obtain the performance level of the DNS server under test and the second interval to obtain the performance level of the DNS server under test, the two performance levels are averaged, and the average value of the obtained performance level is used as the average value of the tested DNS server. The performance class of the server.

It should be noted that, as shown in this embodiment, the detection device can read other domain names from the preset database after calculating the performance value Y1 corresponding to the first interval duration (that is, after step 7); or, it can also After changing the packet encapsulation mode of the DNS request to obtain a new DNS request (that is, after any one of steps 3 to 7), read other domain names corresponding to the DNS server under test, which is not specifically limited in this embodiment of the present invention.

Example 5

In conjunction with the above introduction, it can be seen that the embodiment of the present invention only further uses the interval duration (or, utilizes the interval duration and level information) to determine the performance level of the server under test only when the working state of the server under test is in an available state; When the working state of the server under test is unavailable, it is determined that the server under test has failed and cannot provide access services temporarily. However, in the actual application process, the unavailable state of the server under test may be caused by a server failure, or by abnormal conditions such as flash disconnection and jitter. In order to further improve the accuracy of performance detection in the embodiments of the present invention and eliminate performance detection results errors caused by abnormal conditions, the detection device can also perform the following steps on the basis of the above embodiments: determine the server under test based on the detection device In the unavailable state, return to the step of the detection device sending the first detection message to the server under test until the preset condition is met; the preset condition is the preset execution times or the preset execution time length.

On the basis of the solution introduced in Embodiment 1 above, if the detection device records in step 5 that the working status of the DNS server under test is unavailable (i.e. S=0), as an example, the detection device can directly determine that the DNS server under test If the DNS server fails, stop the performance detection process, and temporarily no longer assign it to the client user; or, as another example, the detection device can return to step 3 and continue to send the changed DNS server to the tested DNS server. DNS request, check the working status of the tested DNS server again, if the detected DNS server is currently in an available state, then continue to perform the subsequent steps of determining the server performance level; if the detected DNS server is still currently unavailable , then judge whether the preset condition is currently satisfied, if so, stop the performance detection process, and temporarily no longer assign the tested DNS server to the client user; if not, continue to return to step 3 until the preset is satisfied until the condition.

Corresponding to the method shown in FIG. 3, an embodiment of the present invention also provides a server performance detection device. Referring to the schematic diagram shown in FIG. 5, the device may include:

A sending unit 201, configured to send a first detection message to the server under test, where the first detection message carries first information;

The receiving unit 202 is configured to receive a first response message returned by the server under test corresponding to the first detection message, where the first response message carries second information, and the second information is the same as the first detection message. There is a mapping relationship between information;

A state determination unit 203, configured to determine whether the server under test is in an available state;

An obtaining unit 204, configured to obtain a first interval between the first detection message and the first response message based on the state determination unit determining that the server under test is in an available state;

A level determining unit 205, configured to determine the performance level of the server under test according to the first interval length acquired by the acquiring unit.

To sum up, after the detection device in the embodiment of the present invention determines that the tested server is in an available state, it will further specify the performance level of the tested server in combination with the interval between the detection message and the response message, because the interval can be To a certain extent, it reflects the response speed of the server under test to process the request, so the solution of the embodiment of the present invention can improve the accuracy of the server performance detection result, thereby improving the rationality of the load balancing device performing load balancing based on the performance detection result of the embodiment of the present invention, and then Ensure that the assigned server can provide client users with good quality access services.

Optionally, the detection device can be configured with a preset database, and the preset database stores the first information, so that after the detection device is triggered, it can read the first information from the preset database and actively use The first information performs performance detection on the server under test. Correspondingly, the device further includes: a reading unit configured to read the first detection message from the server before the sending unit sends the first detection message to the server under test. Read the first information from the preset database, and use the first information to generate the first detection message.

For the specific process, refer to the introduction in Embodiment 1 above, and details will not be repeated here. In addition, after the detection device is triggered, it can only read the first information from the preset database, and use the first information to perform performance detection on the server under test; in addition, the detection device can also repeatedly read other information from the preset database. Information, perform multiple performance tests on the same server under test; or, use the same information to perform multiple performance tests on the same server under test, which is not specifically limited in this embodiment of the present invention, and will not be introduced here.

Optionally, the preset database also stores first level information of the first information, and the level determination unit is specifically configured to determine the The performance level of the server under test; the first level information is set according to the access frequency of the network resource identified by the first information or the category to which the first information belongs.

In this way, the detection device can determine the performance level of the server under test in combination with the working status, interval duration, and level information of the server under test. The specific process can be referred to the introduction in Embodiment 2 above, and will not be repeated here.

Optionally, the preset database also stores the correspondence between the identity of the server under test and the first information, and before the detection device sends the first detection message to the server under test, the The device further includes: a selection unit, configured to select the server under test from the corresponding relationship according to the first information before the sending unit sends the first detection message to the server under test of identity.

In this way, the detection device can actively perform performance detection on different servers. The specific process can be referred to the introduction in Embodiment 3 above, and will not be repeated here.

Optionally, based on the state determination unit determining that the server under test is in an available state,

The sending unit is further configured to send a second detection message to the server under test, where the second detection message carries third information;

The receiving unit is further configured to receive a second response message returned by the server under test corresponding to the second detection message, the second response message carries fourth information, and the fourth information is related to the second detection message. There is a mapping relationship between the third information;

The acquiring unit is further configured to acquire a second interval between the second detection message and the second response message;

The level determining unit is specifically configured to determine the performance level of the server under test according to the second interval length, and use the performance level determined according to the first interval length and the performance level determined according to the second interval length. The performance level calculates the average value of the performance level of the server under test; or,

The level determining unit is specifically configured to use the first interval length and the second interval length to calculate an interval duration average, and determine the performance level of the server under test according to the interval interval average value.

In this way, using a plurality of information read from the preset database (here can be embodied as the first information, the third information, of course, as an example, more information can also be read for performance testing, the implementation of the present invention This example is not limited) to perform multiple performance tests on the same server under test to improve the accuracy of the performance test results of the embodiment of the present invention. For the specific process, please refer to the introduction made in Embodiment 4 above, and will not repeat them here .

Optionally, the sending unit is further configured to continue to send the first detection message to the server under test based on the state determination unit determining that the server under test is in an unavailable state until a preset condition is met time; the preset condition is the preset execution times or the preset execution time length.

In this way, errors in performance test results caused by abnormal conditions can be eliminated, and the accuracy of the performance test results of the embodiment of the present invention can be improved. For the specific process, please refer to the introduction in Embodiment 5 above, and will not be repeated here.

It should be noted that the server performance detection device provided in this device embodiment can be integrated into a load balancing device and applied to the method embodiment shown in Figure 3 above to realize the function of the detection device. For other additional functions that can be realized by the server performance detection device, and other interaction processes with the DNS server to be tested, please refer to the description of the detection device in the method embodiments, and details will not be repeated here.

In addition, when the detection device provided by the above-mentioned embodiment performs server performance detection, it only uses the division of the above-mentioned functional modules as an example for illustration. The internal structure is divided into different functional modules to complete all or part of the functions described above.

The embodiment of the invention also provides a server performance detection device. Referring to the schematic diagram shown in FIG. 6 , the server performance detection device may include: a processor 301 , a memory 302 , a network interface 303 , and a bus system 304 .

The bus system 304 is used to couple various hardware components of the detection device together.

The network interface 303 is used to realize the communication connection between the detection device and at least one other network element, and may use the Internet, a wide area network, a local network, a metropolitan area network, and the like.

The memory 302 is used for storing program instructions and data.

The processor 301 is configured to read instructions and data stored in the memory 302, and perform the following operations:

triggering the network interface to send a first detection message to the server under test, where the first detection message carries first information;

Receive the first response message returned by the server under test corresponding to the first detection message through the network interface, the first response message carries second information, and the second information is consistent with the first There is a mapping relationship between information;

determining whether the tested server is in an available state;

Obtaining a first interval between the first detection message and the first response message based on determining that the server under test is in an available state;

Determine the performance level of the server under test according to the first interval length.

Wherein, the processor 301 may be an integrated circuit chip, which has a signal processing capability. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. These instructions can be realized and controlled by the cooperation of the processor therein, so as to execute the methods disclosed in the embodiments of the present invention. The above-mentioned processor can also be a general-purpose processor, a digital signal processor (Digital Signal Processing, DSP), an application specific integrated circuit (application specific integrated circuit), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices , Discrete hardware components.

Wherein, the above general processor may be a microprocessor or the processor may be any conventional processor, decoder and the like. The steps of the methods disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register.

Wherein, besides the data bus, the bus system 304 may also include a power bus, a control bus and a status signal bus. However, for clarity of illustration, the various buses are labeled as bus system 304 in FIG. 6 .

Optionally, the detection device is configured with a preset database, and the preset database stores the first information, and before the triggering of the network interface to send the first detection message to the server under test, the Processors are also used to:

Reading the first information from the preset database, and using the first information to generate the first detection message.

Optionally, the preset database also stores first-level information of the first information, and the processor performs the following operations to determine the performance level of the server under test:

Determine the performance level of the server under test according to the first interval length and the first level information; the first level information is the access frequency of network resources identified by the first information or the first The category to which the information belongs is set.

Optionally, the preset database also saves the corresponding relationship between the identity of the server under test and the first information, and before the triggering of the network interface to send the first detection message to the server under test , the processor is also used to:

Select the identity of the server under test from the corresponding relationship according to the first information.

Optionally, based on determining that the server under test is in an available state, the processor is further configured to perform the following operations:

triggering the network interface to send a second detection message to the server under test, where the second detection message carries third information;

The second response message returned by the server under test corresponding to the second detection message is received through the network interface, the second response message carries fourth information, and the fourth information is the same as the third There is a mapping relationship between information;

Obtain a second interval between the second detection message and the second response message;

The processor performs the following operations to determine the performance level of the server under test:

Determine the performance level of the server under test according to the second interval length, and calculate the performance level of the server under test by using the performance level determined according to the first interval length and the performance level determined according to the second interval length. Performance Rating Mean; or,

Using the first interval length and the second interval length to calculate an interval duration average, and determine the performance level of the server under test according to the interval interval average value.

Optionally, the processor is also configured to perform the following operations:

Based on determining that the server under test is in an unavailable state, return to the step of triggering the network interface to send a first detection message to the server under test until a preset condition is met; the preset condition is a preset The number of executions or the preset execution length.

It should be noted that the server under test in the embodiment of the present invention may be a DNS server, a call center server, a content distribution server, etc., and a server that can locally cache the mapping relationship between the first information and the second information. If the server under test is a DNS server, the first detection message is a DNS request message, the first response message is a DNS response message, the first information is a first domain name, and the second information for the IP address. If the server under test is a call center server, the first detection message is a call request, the first information is the account number of the called user, the first response message is a call response, and the second information is the client IP corresponding to the called user. address, the mapping relationship is the mapping relationship between accounts and IP addresses. If the server under test is a content distribution server, the first detection message is a content access request, the first information is the content information requested to be accessed, the first response message is a content access response, and the second information is the IP address of the cache server, The mapping relationship is a mapping relationship between the content information and the IP address of the cache server.

To sum up, after the detection device in the embodiment of the present invention determines that the server under test is in an available state, it will further clarify the performance level of the server under test in combination with the interval time between the detection message and the response message, because the interval time can be within To a certain extent, it reflects the response speed of the server under test to process the request, so the solution of the embodiment of the present invention can improve the accuracy of the server performance detection result, thereby improving the rationality of the load balancing device performing load balancing based on the performance detection result of the embodiment of the present invention, and then Ensure that the assigned server can provide client users with good quality access services. In addition, different domain names can be used to perform multiple performance tests on the same server under test, or the same domain name can be used to perform multiple performance tests on the same server under test, so as to further improve the accuracy of the server performance test results of the embodiment of the present invention .

It should be noted that the server performance detection device provided in this embodiment can be integrated into a load balancing device and applied to the method embodiment shown in FIG. 3 above to realize the function of the detection device. For other additional functions that can be realized by the server performance detection device, and other interaction processes with the DNS server to be tested, please refer to the description of the detection device in the method embodiments, and details will not be repeated here.

From the above description of the implementation manners, it can be seen that those skilled in the art can clearly understand that all or part of the steps in the methods of the above embodiments can be implemented by means of software plus a general hardware platform. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in storage media, such as ROM/RAM, disk , optical disk, etc., including several instructions to make a computer device (which may be a personal computer, a server, or a network communication device such as a media gateway) execute the methods described in various embodiments or some parts of the embodiments of the present invention.

It should be noted that each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. place. In particular, for the device and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for relevant parts, please refer to part of the description of the method embodiments. The device and system embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without creative effort.

The above descriptions are only optional implementations of the present invention, and are not intended to limit the protection scope of the present invention. It should be pointed out that those skilled in the art can make some improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims (12)

1. A server performance detection method, characterized in that the method comprises: The detection device sends a first detection message to the server under test, where the first detection message carries first information; The detection device receives a first response message returned by the server under test corresponding to the first detection message, the first response message carries second information, and the second information and the first information There is a mapping relationship between them; The detection device determines whether the server under test is in an available state; Based on the detection device determining that the server under test is in an available state, the detection device acquires a first interval between the first detection message and the first response message; The detection device determines the performance level of the server under test according to the first interval length. 2. The method according to claim 1, wherein the detection device is configured with a preset database, and the preset database stores the first information, and the first information is sent to the server under test by the detection device. Before a detection message, the method also includes: The detection device reads the first information from the preset database, and uses the first information to generate the first detection message. 3. The method according to claim 2, wherein the preset database also stores the first-level information of the first information, and the detection device determines the The performance level of the test server, including: The detection device determines the performance level of the server under test according to the first interval length and the first level information. 4 . The method according to claim 3 , wherein the first level information is set according to the frequency of network resources identified by the first information being accessed or the category to which the first information belongs. 5. The method according to claim 3 or 4, wherein, based on the detection device, it is determined that the server under test is in an available state, and the method further comprises: The detection device sends a second detection message to the server under test, and the second detection message carries third information; The detection device receives a second response message returned by the server under test corresponding to the second detection message, the second response message carries fourth information, and the fourth information and the third information There is a mapping relationship between them; The detection device acquires a second interval between the second detection message and the second response message; The detection device determines the performance level of the server under test according to the first interval length, including: The detecting device determines the performance level of the server under test according to the second interval length, and uses the performance level determined according to the first interval length and the performance level determined according to the second interval length to calculate the the average performance rating of the server under test; or, The detection device uses the first interval length and the second interval length to calculate an interval duration average value, and determines the performance level of the server under test according to the interval duration average value. 6. The method according to any one of claims 1 to 5, characterized in that the method further comprises: Based on the detection device determining that the server under test is in an unavailable state, return to the step of sending the first detection message to the server under test by the detection device until a preset condition is met; the preset condition is a preset condition Set the execution times or preset execution time length. 7. The method according to any one of claims 1 to 6, wherein the server under test is a DNS server, the first detection message is a DNS request message, and the first response message is In a DNS response message, the first information is a first domain name, and the second information is an IP address. 8. A server performance detection device, characterized in that the device comprises: A sending unit, configured to send a first detection message to the server under test, where the first detection message carries first information; a receiving unit, configured to receive a first response message returned by the server under test corresponding to the first detection message, where the first response message carries second information, and the second information is the same as the first There is a mapping relationship between information; A state determining unit, configured to determine whether the tested server is in an available state; An obtaining unit, configured to obtain a first interval between the first detection message and the first response message based on the state determination unit determining that the server under test is in an available state; A level determining unit, configured to determine the performance level of the server under test according to the first interval duration acquired by the acquiring unit. 9. The device according to claim 8, wherein, based on the state determination unit determining that the server under test is in an available state, The sending unit is further configured to send a second detection message to the server under test, where the second detection message carries third information; The receiving unit is further configured to receive a second response message returned by the server under test corresponding to the second detection message, the second response message carries fourth information, and the fourth information is related to the second detection message. There is a mapping relationship between the third information; The acquiring unit is further configured to acquire a second interval between the second detection message and the second response message; The level determining unit is specifically configured to determine the performance level of the server under test according to the second interval length, and use the performance level determined according to the first interval length and the performance level determined according to the second interval length. The performance level calculates the average value of the performance level of the server under test; or, The level determining unit is specifically configured to use the first interval length and the second interval length to calculate an interval duration average, and determine the performance level of the server under test according to the interval interval average value. 10. Apparatus according to claim 8 or 9, characterized in that, The sending unit is further configured to continue to send the first detection message to the server under test based on the state determination unit determining that the server under test is in an unavailable state until a preset condition is met; The preset condition mentioned above is the preset execution times or the preset execution time length. 11. A server performance detection device, characterized in that the device comprises: a processor, a memory, and a network interface; The memory is used to store program instructions and data; The processor is configured to read instructions and data stored in the memory, and perform the following operations: triggering the network interface to send a first detection message to the server under test, where the first detection message carries first information; Receive the first response message returned by the server under test corresponding to the first detection message through the network interface, the first response message carries second information, and the second information is consistent with the first There is a mapping relationship between information; determining whether the tested server is in an available state; Obtaining a first interval between the first detection message and the first response message based on determining that the server under test is in an available state; Determine the performance level of the server under test according to the first interval length. 12. The device according to claim 11, wherein based on determining that the server under test is in an available state, the processor is further configured to perform the following operations: triggering the network interface to send a second detection message to the server under test, where the second detection message carries third information; The second response message returned by the server under test corresponding to the second detection message is received through the network interface, the second response message carries fourth information, and the fourth information is the same as the third There is a mapping relationship between information; Obtain a second interval between the second detection message and the second response message; The determining the performance level of the server under test according to the first interval length includes: Determine the performance level of the server under test according to the second interval length, and calculate the performance level of the server under test by using the performance level determined according to the first interval length and the performance level determined according to the second interval length. Performance Rating Mean; or, Using the first interval length and the second interval length to calculate an interval duration average, and determine the performance level of the server under test according to the interval interval average value.