CN109800137A - A kind of server performance test method and system - Google Patents
A kind of server performance test method and system Download PDFInfo
- Publication number
- CN109800137A CN109800137A CN201811489539.2A CN201811489539A CN109800137A CN 109800137 A CN109800137 A CN 109800137A CN 201811489539 A CN201811489539 A CN 201811489539A CN 109800137 A CN109800137 A CN 109800137A
- Authority
- CN
- China
- Prior art keywords
- test
- server
- node
- measured
- performance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
A kind of server performance test method, comprising the following steps: the test request sent from client is received, to extract the test assignment information of server to be measured from test request；Priority is determined according to test assignment information, to add test assignment in the corresponding task queue of priority；Task type and priority are determined according to test assignment information, for the test assignment distribution node in task queue；Determine the access information and test content information of server to be measured, according to test assignment information to configure to node；According to test content information, node is called to carry out pressure test access to server to be measured, to count the performance data about server to be measured obtained from node；If determining the performance threshold for obtaining server to be measured according to performance data, test assignment is completed, otherwise adjusts test content information, and continue to execute back survey.The application also proposes a kind of server performance test macro corresponding with the above method.
Description
Technical field
The present invention relates to server testing field more particularly to a kind of server performance test methods and system.
Background technique
At present when being tested for the property to the server with TCP or HTTP framework, most of user can be selected
The performance testing tools such as the JMeter or LoadRunner tool of Apache, to evaluate the performance threshold of current server.
But main problem, which exists in the prior art, is: when carrying out server performance test, can not determine that specific pressure is surveyed
Parameter is tried, to evaluate the performance threshold of current server.Existing way is: parameter is surveyed by manually adjusting pressure, with repeatedly
Execution performance test assignment, and then obtain more parts of performance data reports.After being compared to more parts of performance data reports, ability
It is final to determine the performance threshold for evaluating current server.
Due to manually adjusting the standard for pressing the mode for surveying parameter ununified, increasing the time cost of test and using door
Sill.
Summary of the invention
The purpose of the application is to solve the deficiencies in the prior art, provides a kind of server performance test method and system, energy
It is enough to obtain the time cost for reducing test and the effect using threshold.
To achieve the goals above, the following technical solution is employed by the application.
Firstly, the application proposes a kind of server performance test method, method includes the following steps:
S100 the test request sent from client is received) to extract server to be measured from the test request
Test assignment information；
S200 priority) is determined according to the test assignment information, to add in the corresponding task queue of the priority
Add the test assignment with unique identifying number；
S300 task type and priority) are determined according to the test assignment information, for the institute in the task queue
State test assignment distribution node；
S400 the access information and test content information of server to be measured are determined, according to the test assignment information) with right
The node is configured；
S500) according to the test content information, the node is called to carry out pressure test visit to the server to be measured
It asks, to count the performance data about the server to be measured obtained from the node；
S600) if determining the performance threshold for obtaining the server to be measured according to the performance data, the survey is completed
Trial business, otherwise adjusts the test content information, and continue to execute the step S500.
Further, in the above method of the application, the step S300 further includes following sub-step:
S310 the test assignment) is extracted from the task queue according to the priority；
S320) according to the task type of the test assignment, the method for salary distribution of node is determined, according to the method for salary distribution
For the test assignment distribution node.
Still further, the step S320 further includes following sub-step in the above method of the application:
S321) if the task type is intelligent task type, it is determined that the corresponding pre- establishing of the intelligent task type
Set quantity；
S322 the idle node for being no less than the preset configuration quantity) is determined from all nodes, and by the free time
Node be distributed to the test assignment.
Further, in the above method of the application, the step S400 further includes following sub-step:
S410) go out the access information and test content information of server to be measured from the test assignment information extraction；
S420) from the node for being equipped with docker mirror image in advance, the starting for being directed to the docker mirror image is obtained
Configuration file；
S430 the service to be measured) is configured in the starting configuration file according to the access information of the server to be measured
The IP address of device and port；
S440 remote process) is configured in the starting configuration file according to the test content information of the server to be measured
The interface of calling, the scheduling request so that node receives an assignment carry out pressure test access to the server to be measured.
Further, in the above method of the application, the step S500 further includes following sub-step:
S510) according to the task type of the test assignment, the node is controlled by way of remote procedure call and is opened
Dynamic docker mirror image；
S520 number of users and access frequency) are determined according to the test content；
S530) the docker mirror image is controlled to press the server to be measured according to the number of users and access frequency
Power test access, obtains the performance data of the server to be measured with statistics.
Still further, in the above method of the application, the step S510) further include following sub-step:
S511) when the task type be intelligent task type, then obtain the corresponding preset configuration number of intelligent task type
Amount；
S512) when the quantity of the node of current idle is more than the preset configuration quantity, pass through remote procedure call
Mode controls the node starting docker mirror image of the free time.
Further, in the above method of the application, the step S600 further includes following sub-step:
S610) according to the performance data, the corresponding TPS of the server to be measured and response time are determined；
S620) drawn in same reference axis the TPS about the time the first curve and the response time about when
Between the second curve；
S630) when crosspoint occur in first curve and second curve, S640 is thened follow the steps, step is otherwise executed
Rapid S650；
S640 it) according to the crosspoint, determines the performance threshold for obtaining the server to be measured, is appointed with completing the test
Business；
S650) increase the number of users in the test content information according to preset rules, and continue to execute the step
S500。
Further, in the above method of the application, in the step S600) after further comprise the steps of:
S700) according to the performance data and the performance threshold, the performance test for having the unique identifying number is generated
Report；
S800 performance test report) is sent to client to show.
Secondly, the system comprises the following modules: test request disclosed herein as well is a kind of server performance test macro
Receiving module, for receiving the test request sent from client, to extract server to be measured from the test request
Test assignment information；Test assignment adding module, for determining priority according to the test assignment information, described preferential
Addition has the test assignment of unique identifying number in the corresponding task queue of grade；Node distribution module, for according to the test
Mission bit stream determines task type and priority, for the test assignment distribution node in the task queue；Node is matched
Module is set, for determining the access information and test content information of server to be measured according to the test assignment information, to institute
Node is stated to be configured；Pressure test module, for calling the node to the clothes to be measured according to the test content information
Business device carries out pressure test access, to count the performance data about the server to be measured obtained from the node；Performance
Threshold determination module, if completing institute for determining the performance threshold for obtaining the server to be measured according to the performance data
Test assignment is stated, the test content information is otherwise adjusted, and is continued to execute described according to the test content information, calling institute
State node and pressure test access carried out to the server to be measured, with count obtained from the node about the service to be measured
The performance data of device.
Further, in the above system of the application, the node distribution module further includes following submodule: test is appointed
Business extraction module, for extracting the test assignment from the task queue according to the priority；The method of salary distribution determines
Module determines the method for salary distribution of node for the task type according to the test assignment, using according to the method for salary distribution as institute
State test assignment distribution node.
Still further, the method for salary distribution determining module further includes following submodule in the above system of the application:
Pinned task type distribution module is appointed if being pinned task type for the task type for the test
The node of default fixed quantity is distributed in business.
Still further, the method for salary distribution determining module further includes following submodule in the above system of the application:
Preset configuration quantity determining module, if being intelligent task type for the task type, it is determined that the intelligent task type
Corresponding preset configuration quantity；Intelligent Service type distribution module is no less than the pre- establishing for determining from all nodes
The idle node of quantity is set, and the node of the free time is distributed to the test assignment.
Further, in the above system of the application, the node configuration module further includes following submodule: test is appointed
Business information extraction modules, for going out the access information and test content letter of server to be measured from the test assignment information extraction
Breath；Configuration file obtains module, for obtaining and being directed to the docker from the node for being equipped with docker mirror image in advance
The starting configuration file of mirror image；Access information configuration module, for being opened according to the access information of the server to be measured described
IP address and the port of the server to be measured are configured in dynamic configuration file；Test content information collocation module, for according to institute
The test content information for stating server to be measured configures the interface of remote procedure call in the starting configuration file, so that institute
It states node to receive an assignment scheduling request, pressure test access is carried out to the server to be measured.
Further, in the above system of the application, the pressure test module further includes following submodule: mirror image is opened
Dynamic model block controls the node starting for the task type according to the test assignment by way of remote procedure call
Docker mirror image；Test content determining module, for determining number of users and access frequency according to the test content；Performance data
Statistical module presses the server to be measured according to the number of users and access frequency for controlling the docker mirror image
Power test access, obtains the performance data of the server to be measured with statistics.
Still further, the image starting module further includes following submodule in the above system of the application: fixed
Task start module is then controlled by way of remote procedure call pre- for being pinned task type when the task type
If the node of fixed quantity starts docker mirror image.
Further, in the above system of the application, the image starting module further includes following submodule:
Preset configuration quantity obtains module, for being intelligent task type when the task type, then obtains intelligent task
The corresponding preset configuration quantity of type；Intelligent task starting module, the quantity for the node in current idle is more than described pre-
When quantity is set in establishing, the node starting docker mirror image of the free time is controlled by way of remote procedure call.
Further, in the above system of the application, the performance threshold determining module further includes following submodule: property
Energy data determining module, for determining the corresponding TPS of the server to be measured and response time according to the performance data；It is bent
Line drafting module, for drawn in same reference axis the TPS about the time the first curve and the response time about
The second curve of time；Crosspoint determining module, for occurring crosspoint, then holding when first curve and second curve
Row determines otherwise the performance threshold for obtaining the server to be measured is executed to complete the test assignment according to the crosspoint
Increase the number of users in the test content information according to preset rules, and continue to execute according to the test content information, adjusts
Pressure test access is carried out to the server to be measured with the node, with count obtained from the node about described to be measured
The performance data of server；Performance threshold obtains module, for determining and obtaining the server to be measured according to the crosspoint
Performance threshold, to complete the test assignment；It returns and surveys module, for increasing in the test content information according to preset rules
Number of users, and continue to execute described according to the test content information, call the node to press the server to be measured
Power test access, to count the performance data about the server to be measured obtained from the node.
Further, in the above system of the application, the system further include: sending module is reported in performance test, is used for
Execution " if determining the performance threshold for obtaining the server to be measured according to the performance data, complete the test assignment,
Otherwise the test content information is adjusted, and continues to execute described according to the test content information, calls the node to institute
It states server to be measured and carries out pressure test access, to count the performance number about the server to be measured obtained from the node
According to " operation after, according to the performance data and the performance threshold, generate the performance test for having the unique identifying number
Report；Sending module is reported in performance test, is shown for performance test report to be sent to client.
Finally, the application also proposes a kind of computer readable storage medium, it is stored thereon with computer instruction.Above-metioned instruction
When being executed by processor, following steps are executed:
S100 the test request sent from client is received) to extract server to be measured from the test request
Test assignment information；
S200 priority) is determined according to the test assignment information, to add in the corresponding task queue of the priority
Add the test assignment with unique identifying number；
S300 task type and priority) are determined according to the test assignment information, for the institute in the task queue
State test assignment distribution node；
S400 the access information and test content information of server to be measured are determined, according to the test assignment information) with right
The node is configured；
S500) according to the test content information, the node is called to carry out pressure test visit to the server to be measured
It asks, to count the performance data about the server to be measured obtained from the node；
S600) if determining the performance threshold for obtaining the server to be measured according to the performance data, the survey is completed
Trial business, otherwise adjusts the test content information, and continue to execute the step S500.
Having the beneficial effect that for the application adjusts the test content information using the performance data obtained, and carries out
It returns and surveys, the performance threshold until determining server to be measured enables tester to get rid of heavy mechanical pressure and surveys parameter
Adjustment launches more energy onto the design of server architecture etc., to reduce the time cost of test and use threshold.
Detailed description of the invention
Fig. 1 show the flow chart of server performance test method disclosed in the present application；
Fig. 2 is shown in one embodiment of the application, and node distributes the flow chart of submethod；
Fig. 3 is shown in one embodiment of the application, the flow chart of method of salary distribution submethod；
Fig. 4 is shown in one embodiment of the application, and node configures the flow chart of submethod；
Fig. 5 is shown in one embodiment of the application, and pressure test accesses the flow chart of submethod；
Fig. 6 is shown in one embodiment of the application, the flow chart of image starting submethod；
Fig. 7 is shown in one embodiment of the application, and performance threshold determines the flow chart of submethod；
Fig. 8 show the structure chart of server performance test macro disclosed in the present application.
Specific embodiment
It is carried out below with reference to technical effect of the embodiment and attached drawing to the design of the application, specific structure and generation clear
Chu, complete description, to be completely understood by the purpose, scheme and effect of the application.It should be noted that the case where not conflicting
Under, the features in the embodiments and the embodiments of the present application can be combined with each other.
It should be noted that unless otherwise specified, when a certain feature referred to as " fixation ", " connection " are in another feature,
It can directly fix, be connected to another feature, and can also fix, be connected to another feature indirectly.In addition, this
The descriptions such as upper and lower, left and right used in application are only the mutual alignment pass relative to each component part of the application in attached drawing
For system.In the application and the "an" of singular used in the attached claims, " described " and "the" also purport
It is including most forms, unless the context clearly indicates other meaning.
In addition, unless otherwise defined, the technology of all technical and scientific terms used herein and the art
The normally understood meaning of personnel is identical.Term used in the description is intended merely to description specific embodiment herein, without
It is to limit the application.Term as used herein "and/or" includes the arbitrary of one or more relevant listed items
Combination.
It will be appreciated that though various elements may be described in this application using term first, second, third, etc., but
These elements should not necessarily be limited by these terms.These terms are only used to for same type of element being distinguished from each other out.For example, not taking off
In the case where the application range, first element can also be referred to as second element, and similarly, second element can also be referred to as
First element.Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When ".
Method flow diagram shown in referring to Fig.1, in one or more embodiments of the application, server performance test side
Method the following steps are included:
S100 the test request sent from client is received) to extract server to be measured from the test request
Test assignment information；
S200 priority) is determined according to the test assignment information, to add in the corresponding task queue of the priority
Add the test assignment with unique identifying number；
S300 task type and priority) are determined according to the test assignment information, for the institute in the task queue
State test assignment distribution node；
S400 the access information and test content information of server to be measured are determined, according to the test assignment information) with right
The node is configured；
S500) according to the test content information, the node is called to carry out pressure test visit to the server to be measured
It asks, to count the performance data about the server to be measured obtained from the node；
S600) if determining the performance threshold for obtaining the server to be measured according to the performance data, the survey is completed
Trial business, otherwise adjusts the test content information, and continue to execute the step S500.
Specifically, the server performance test method of the present embodiment can be applied in server-side, which can be
Server or computer.Client is also provided with simultaneously to test for providing to fill in the interface of test assignment information and send for user
The interface of request, the client can be browser or application software.Further, which includes: clothes to be measured
The access information and test content information of business device, further include the priority and task type of the test assignment.Wherein, access information
It can be IP address and the port of server to be measured；Test content information can be used for regulation number of users and access frequency, user
Number is the quantity of the test user to access in the test assignment to server to be measured, and access frequency refers to that server to be measured is every
The access times of second；Being provided with for priority is conducive to test assignment being allocated in the corresponding task queue of different priorities, so that
Task queue can manage multiple test assignments；Task type includes pinned task type and intelligent task type, for using
The different methods of salary distribution is test assignment distribution node.Performance data is used to indicate the performance of server to be measured, to performance data
It is counted, the performance threshold of available server to be measured, which is peak dot or the valley point of performance data.Further
, performance data can be response time, concurrent user number, the transaction response time, handling capacity, TPS (transaction response number per second),
Performance counter etc..Unique identifying number can obtain the test according to the unique identifying number and appoint for identifying test assignment, user
All data of business.The distribution of node refers to as test assignment distribution node, to use the node to the server to be measured
Carry out pressure test access.The configuration of node, for configuring the interface and test content information of server-side far call, with convenient
Server-side can carry out pressure test visit to the server to be measured according to the test content information with node described in far call
It asks.
Specifically, it when the server to TCP or HTTP framework is tested for the property, is saved using test assignment information
The distribution and configuration of point, and pressure test is carried out to server to be measured according to test content information using configured node in turn
Access to obtain the performance data of server to be measured from node in real time, and then is adjusted using the performance data obtained
The test content information survey, and the performance threshold until determining server to be measured enables tester to get rid of numerous
The mechanical test content information adjustment of weight, more energy is launched onto the design of server architecture etc., to reduce
The time cost of test and use threshold.
Further, the node of above-mentioned test assignment is distributed, referring to submethod flow chart shown in Fig. 2, in this Shen
In said one or multiple embodiments please, the step S300 further includes following sub-step:
S310 the test assignment) is extracted from the task queue according to the priority；
S320) according to the task type of the test assignment, the method for salary distribution of node is determined, according to the method for salary distribution
For the test assignment distribution node.
Specifically, the method for salary distribution of node is determined according to the task type of test assignment, can increase processing test assignment
Flexibility, handle test assignment in time, on the other hand so that node is fully utilized.This implementation
It is illustrated so that task type includes pinned task type and intelligent task type as an example in example.
Still further, referring to submethod flow chart shown in Fig. 3, the method for salary distribution corresponding for pinned task type,
In the said one or multiple embodiments of the application, the step S320 further includes following sub-step:
S321) if the task type is intelligent task type, it is determined that the corresponding pre- establishing of the intelligent task type
Set quantity；
S322 the idle node for being no less than the preset configuration quantity) is determined from all nodes, and by the free time
Node be distributed to the test assignment.
Specifically, the method for salary distribution of intelligent task type is on-fixed, can be carried out according to the data of idle node automatic
Extension, it is ensured that the test assignment of intelligent task type has an opportunity to obtain more node resources, so that the test assignment
It is rapidly completed, is also beneficial to the abundant use of node resource.In addition, passing through the setting of preset configuration quantity, it is ensured that test
Task obtains enough node resources and just starts to start, to guarantee the smooth execution of test assignment.Illustratively, server-side and
Node is provided by same server, number of nodes be server nucleus number, such as 24 cores server can there are 2 nodes to use respectively
In the performance data obtained from node for test assignment distribution node, statistics, others 22 nodes of section then can be in the free time
When be distributed to test assignment use.It is, of course, also possible to which configuration fixation can distribute to test and appoint by the server admin page
The quantity of the node of business.
Further, for the configuration of above-mentioned node, referring to submethod flow chart shown in Fig. 4, in the above-mentioned of the application
In one or more embodiments, the step S400 further includes following sub-step:
S410) go out the access information and test content information of server to be measured from the test assignment information extraction；
S420) from the node for being equipped with docker mirror image in advance, the starting for being directed to the docker mirror image is obtained
Configuration file；
S430 the service to be measured) is configured in the starting configuration file according to the access information of the server to be measured
The IP address of device and port；
S440 remote process) is configured in the starting configuration file according to the test content information of the server to be measured
The interface of calling, the scheduling request so that node receives an assignment carry out pressure test access to the server to be measured.
Specifically, the task queue of server-side can manage simultaneously executes multiple test assignments, and according to priority successively into
Row test.
When task distribution node, using third party's docker capacity technologies.Docker is that the application container of an open source is drawn
It holds up, allows developer that can be packaged their application and rely on packet into a transplantable container, be then published to any stream
On capable Linux machine, it also may be implemented to virtualize.Container is not have any connect between each other using sandbox mechanism completely
Mouthful.Therefore, the distribution of test assignment is carried out using docker capacity technologies, it can be ensured that carry out the section of pressure test access every time
Point environment it is clean with it is independent.
Specifically, in the server where node, docker mirror image is installed in advance, passes through modification docker mirror image
Start configuration file, the node environment that available test assignment is all answered.The node environment can guarantee in starting docker mirror
After the process of picture, test is carried out in the mode of remote procedure call (Remote Procedure Call, RPC) for server-side and is appointed
The scheduling of business, to carry out pressure test access to the server to be measured.
Further, above-mentioned pressure test access, submethod flow chart referring to Figure 5, in the above-mentioned of the application
In one or more embodiments, the step S500 further includes following sub-step:
S510) according to the task type of the test assignment, the node is controlled by way of remote procedure call and is opened
Dynamic docker mirror image；
S520 number of users and access frequency) are determined according to the test content；
S530) the docker mirror image is controlled to press the server to be measured according to the number of users and access frequency
Power test access, obtains the performance data of the server to be measured with statistics.
Specifically, for the scheduling of test assignment, that is, the node is called to carry out pressure test access to server to be measured,
Can in node docker mirror image provide application programming interface (Application Programming Interface,
API), the node start-up loading docker mirror image for being mounted with docker mirror image in advance is called by way of RPC；To docker mirror
As start completion, server-side can notify node to carry out with the number of users and access frequency to server to be measured in a manner of RPC
Pressure test access obtains the performance data of the server to be measured with statistics.
Likewise, having different image starting modes according to the difference of task type, the present embodiment is said by way of example
It is bright.
Still further, referring to submethod flow chart shown in fig. 6, feelings of the above-mentioned image starting in pinned task type
Under condition, in the said one or multiple embodiments of the application, the step S510) further include following sub-step:
S511) when the task type be intelligent task type, then obtain the corresponding preset configuration number of intelligent task type
Amount；
S512) when the quantity of the node of current idle is more than the preset configuration quantity, pass through remote procedure call
Mode controls the node starting docker mirror image of the free time.
Further, the determination of above-mentioned performance threshold, referring to submethod flow chart shown in Fig. 7, in the above-mentioned of the application
In one or more embodiments, the step S600 further includes following sub-step:
S610) according to the performance data, the corresponding TPS of the server to be measured and response time are determined；
S620) drawn in same reference axis the TPS about the time the first curve and the response time about when
Between the second curve；
S630) when crosspoint occur in first curve and second curve, S640 is thened follow the steps, step is otherwise executed
Rapid S650；
S640 it) according to the crosspoint, determines the performance threshold for obtaining the server to be measured, is appointed with completing the test
Business；
S650) increase the number of users in the test content information according to preset rules, and continue to execute the step
S500。
Specifically, about crosspoint: if server performance there are spike problem, the first curve and the second curve,
Increasing after adding number of users, necessarily resulting in the pressure access to server, response time necessarily slowly increases, i.e., and first
Curve is on the rise, and TPS can then be reduced, then the second curve has falling tendency, and final first curve and the second curve can go out
Existing crosspoint (such as TPS:800, time: 1.3 seconds), then it represents that when it is per second with 800 progress server access when, the sound of server
It answers duration that can start to increase, has reached 1.3 seconds, the downslide for being in response to speed of reflection.Only server has done access limitation
The processing of performance disaster tolerance is done, then overtime process will be gone to.Finally obtain the performance threshold of server to be measured are as follows: server is most
Big TPS and maximum response time.
Further, in the said one of the application or multiple embodiments, in the step S600) after further include step
It is rapid:
S700) according to the performance data and the performance threshold, the performance test for having the unique identifying number is generated
Report；
S800 performance test report) is sent to client to show.
The present embodiment by way of illustration, to the bulk flow of server performance test method provided in this embodiment
Journey is described in detail.
Illustratively, user fills in the IP address or station address of server to be measured, such as on client (browser)
Http:// www.xxx.com, to generate the access information of server to be measured；Fill in access frequency: 100, number of users: 1000, it hooks
Intelligent task type is selected, to generate the test content information of server to be measured；According to the access information and test content information
Generate test assignment information；It clicks " starting to test ", to generate the test request for having the test assignment information.
After server-side receives test request, one can be created uniquely to test assignment according to the test assignment information extracted
Then the test assignment is added in task queue by identification number；Later, server-side can return to the test assignment to client
Unique identifying number, to be used in subsequent performance test report.
Further, for the task dispatch thread of server when traversing task queue, discovery has an intelligent task type
Test assignment, then can first judge whether to be greater than preset configuration quantity by current idle number of nodes that (e.g., preset configuration quantity is set as
10), if it is not, then waiting；If so, the node starting docker mirror image can be controlled by way of remote procedure call, it is right
Http:// www.xxx.com (corresponded to access frequency with 100 test users per second: 100), carrying out 1000 in total
The test content information for testing user carries out pressure test access to the server to be measured, when test execution was by the 10th second,
1000 people whole loadeds, can carry out pressure test to the server to be measured with same test content information again
Access, it is to count the performance data about the server to be measured obtained from the node, the performance data is real-time
In the database at write service end, and server-side can draw first curve of the TPS about the time in same reference axis, and
Second curve of the response time about the time then can be again when crosspoint occur in first curve and second curve
The lasting access of pressure test in 1 minute is carried out to the server to be measured, is finally completed the test assignment；If working as described first
There is not crosspoint yet in curve and second curve, then increase the user in the test content information according to preset rules
Number carries out pressure test access to the server to be measured with updated test content information, until first curve and
There is crosspoint in second curve.
Finally, server-side generates the property for having the unique identifying number according to the performance data and the performance threshold
Energy test report, and the performance test being reported to, be sent to client shows.The performance test report can be very
The performance threshold of current server is got information about, that is, user can intuitively obtain the performance highest of server very much
It can threshold value (highest number of users and TPS).Further, by the performance threshold, the property of the server to be measured can be determined
Can, such as when number of users is greater than the highest number of users in performance threshold, the response time that can default to server will increase, very
To there is non-responsive state.
Referring to function structure chart shown in Fig. 8, in one or more embodiments of the application, server performance test system
System, which comprises the following modules: test request receiving module, for receiving the test request from client transmission, with from institute
State the test assignment information that server to be measured is extracted in test request；Test assignment adding module, for according to the test
Mission bit stream determines priority, to add in the corresponding task queue of the priority there is the test of unique identifying number to appoint
Business；Node distribution module, for determining task type and priority according to the test assignment information, for the task queue
In the test assignment distribution node；Node configuration module, for determining server to be measured according to the test assignment information
Access information and test content information, to be configured to the node；Pressure test module, for according in the test
Hold information, the node is called to carry out pressure test access to the server to be measured, to count from the pass that the node obtains
In the performance data of the server to be measured；Performance threshold determining module, if obtaining institute for determining according to the performance data
The performance threshold of server to be measured is stated, then completes the test assignment, otherwise adjusts the test content information, and continue to execute
It is described to call the node to carry out pressure test access to the server to be measured according to the test content information, to count
The performance data about the server to be measured obtained from the node.
Specifically, the server performance test method of the present embodiment can be applied in server-side, which can be
Server or computer.Client is also provided with simultaneously to test for providing to fill in the interface of test assignment information and send for user
The interface of request, the client can be browser or application software.Further, which includes: clothes to be measured
The access information and test content information of business device, further include the priority and task type of the test assignment.Wherein, access information
It can be IP address and the port of server to be measured；Test content information can be used for regulation number of users and access frequency, user
Number is the quantity of the test user to access in the test assignment to server to be measured, and access frequency refers to that server to be measured is every
The access times of second；Being provided with for priority is conducive to test assignment being allocated in the corresponding task queue of different priorities, so that
Task queue can manage multiple test assignments；Task type includes pinned task type and intelligent task type, for using
The different methods of salary distribution is test assignment distribution node.Performance data is used to indicate the performance of server to be measured, to performance data
It is counted, the performance threshold of available server to be measured, which is peak dot or the valley point of performance data.Further
, performance data can be response time, concurrent user number, the transaction response time, handling capacity, TPS (transaction response number per second),
Performance counter etc..Unique identifying number can obtain the test according to the unique identifying number and appoint for identifying test assignment, user
All data of business.The distribution of node refers to as test assignment distribution node, to use the node to the server to be measured
Carry out pressure test access.The configuration of node, for configuring the interface and test content information of server-side far call, with convenient
Server-side can carry out pressure test visit to the server to be measured according to the test content information with node described in far call
It asks.
Specifically, it when the server to TCP or HTTP framework is tested for the property, is saved using test assignment information
The distribution and configuration of point, and pressure test is carried out to server to be measured according to test content information using configured node in turn
Access to obtain the performance data of server to be measured from node in real time, and then is adjusted using the performance data obtained
The test content information survey, and the performance threshold until determining server to be measured enables tester to get rid of numerous
The mechanical test content information adjustment of weight, more energy is launched onto the design of server architecture etc., to reduce
The time cost of test and use threshold.
Further, in the above system of the application, the node distribution module further includes following submodule: test is appointed
Business extraction module, for extracting the test assignment from the task queue according to the priority；The method of salary distribution determines
Module determines the method for salary distribution of node for the task type according to the test assignment, using according to the method for salary distribution as institute
State test assignment distribution node.Specifically, the method for salary distribution of node is determined according to the task type of test assignment, can increase place
The flexibility for managing test assignment, handles test assignment in time, on the other hand, so that node obtains sufficient benefit
With.It is illustrated so that task type includes pinned task type and intelligent task type as an example in the present embodiment.
Still further, the method for salary distribution determining module further includes following submodule in the above system of the application:
Pinned task type distribution module, it is pre- for test assignment distribution if being pinned task type for the task type
If the node of fixed quantity.Specifically, the section of default fixed quantity is distributed by the test assignment to belong to pinned task type
Point, it is ensured that the test assignment obtains enough node resources, so as to smoothly completing for the test assignment.
Still further, the method for salary distribution determining module further includes following submodule in the above system of the application:
Preset configuration quantity determining module, if being intelligent task type for the task type, it is determined that the intelligent task type
Corresponding preset configuration quantity；Intelligent Service type distribution module is no less than the pre- establishing for determining from all nodes
The idle node of quantity is set, and the node of the free time is distributed to the test assignment.Specifically, intelligent task type
The method of salary distribution is on-fixed, can automatically be extended according to the data of idle node, it is ensured that intelligent task type
Test assignment has an opportunity to obtain more node resources, so that the test assignment is rapidly completed, is also beneficial to filling for node resource
Divide and uses.In addition, passing through the setting of preset configuration quantity, it is ensured that test assignment obtains enough node resources and just starts to open
It is dynamic, to guarantee the smooth execution of test assignment.Illustratively, server-side and node are provided by same server, and number of nodes is
The nucleus number of server, the server of such as 24 cores can be respectively used to as test assignment distribution node there are 2 nodes, and statistics is from section
The performance data obtained at point, others 22 nodes of section, then can be distributed to test assignment use during idle time.Certainly,
Can also be by the server admin page, the quantity of node of test assignment can be distributed to by configuring fixation.
Further, in the above system of the application, the node configuration module further includes following submodule: test is appointed
Business information extraction modules, for going out the access information and test content letter of server to be measured from the test assignment information extraction
Breath；Configuration file obtains module, for obtaining and being directed to the docker from the node for being equipped with docker mirror image in advance
The starting configuration file of mirror image；Access information configuration module, for being opened according to the access information of the server to be measured described
IP address and the port of the server to be measured are configured in dynamic configuration file；Test content information collocation module, for according to institute
The test content information for stating server to be measured configures the interface of remote procedure call in the starting configuration file, so that institute
It states node to receive an assignment scheduling request, pressure test access is carried out to the server to be measured.When task distribution node, using
Tripartite's docker capacity technologies.Docker is the application container engine of an open source, allows developer that can be packaged their application
And packet is relied on into a transplantable container, it is then published on the Linux machine of any prevalence, also may be implemented virtual
Change.Container is not have any interface between each other using sandbox mechanism completely.Therefore, it is carried out using docker capacity technologies
The distribution of test assignment, it can be ensured that every time carry out pressure test access node environment it is clean with it is independent.
Specifically, in the server where node, docker mirror image is installed in advance, passes through modification docker mirror image
Start configuration file, the node environment that available test assignment is all answered.The node environment can guarantee in starting docker mirror
After the process of picture, test is carried out in the mode of remote procedure call (Remote Procedure Call, RPC) for server-side and is appointed
The scheduling of business, to carry out pressure test access to the server to be measured.
Further, in the above system of the application, the pressure test module further includes following submodule: mirror image is opened
Dynamic model block controls the node starting for the task type according to the test assignment by way of remote procedure call
Docker mirror image；Test content determining module, for determining number of users and access frequency according to the test content；Performance data
Statistical module presses the server to be measured according to the number of users and access frequency for controlling the docker mirror image
Power test access, obtains the performance data of the server to be measured with statistics.Specifically, it for the scheduling of test assignment, that is, adjusts
Pressure test access is carried out to server to be measured with the node, the application programming that can be provided with docker mirror image in node
Interface (Application Programming Interface, API) is called by way of RPC and is mounted with docker in advance
The node start-up loading docker mirror image of mirror image；It is completed to docker image starting, server-side can notify node in a manner of RPC
Pressure test access is carried out to server to be measured with the number of users and access frequency, the server to be measured is obtained with statistics
Performance data.
Still further, the image starting module further includes following submodule in the above system of the application: fixed
Task start module is then controlled by way of remote procedure call pre- for being pinned task type when the task type
If the node of fixed quantity starts docker mirror image.Specifically, about crosspoint: if there are peak values to ask for server performance
Topic, then the first curve and the second curve, increase after adding number of users, necessarily resulting in the pressure access to server,
Response time necessarily slowly increases, i.e., the first curve is on the rise, and TPS can then be reduced, then the second curve has falling tendency,
Final first curve and the second curve will appear crosspoint (such as TPS:800, time: 1.3 seconds), then it represents that when per second with 800 times
When carrying out server access, the response time of server can start to increase, and reach 1.3 seconds, reflection is in response under speed
It is sliding.Only server has done access limitation and has done the processing of performance disaster tolerance, then overtime process will be gone to.It finally obtains to be measured
The performance threshold of server are as follows: the maximum TPS of server and maximum response time.
Further, in the above system of the application, the image starting module further includes following submodule:
Preset configuration quantity obtains module, for being intelligent task type when the task type, then obtains intelligent task
The corresponding preset configuration quantity of type；Intelligent task starting module, the quantity for the node in current idle is more than described pre-
When quantity is set in establishing, the node starting docker mirror image of the free time is controlled by way of remote procedure call.
The present embodiment by way of illustration, to the bulk flow of server performance test method provided in this embodiment
Journey is described in detail.
Illustratively, user fills in the IP address or station address of server to be measured, such as on client (browser)
Http:// www.xxx.com, to generate the access information of server to be measured；Fill in access frequency: 100, number of users: 1000, it hooks
Intelligent task type is selected, to generate the test content information of server to be measured；According to the access information and test content information
Generate test assignment information；It clicks " starting to test ", to generate the test request for having the test assignment information.
After server-side receives test request, one can be created uniquely to test assignment according to the test assignment information extracted
Then the test assignment is added in task queue by identification number；Later, server-side can return to the test assignment to client
Unique identifying number, to be used in subsequent performance test report.
Further, for the task dispatch thread of server when traversing task queue, discovery has an intelligent task type
Test assignment, then can first judge whether to be greater than preset configuration quantity by current idle number of nodes that (e.g., preset configuration quantity is set as
10), if it is not, then waiting；If so, the node starting docker mirror image can be controlled by way of remote procedure call, it is right
Http:// www.xxx.com (corresponded to access frequency with 100 test users per second: 100), carrying out 1000 in total
The test content information for testing user carries out pressure test access to the server to be measured, when test execution was by the 10th second,
1000 people whole loadeds, can carry out pressure test to the server to be measured with same test content information again
Access, it is to count the performance data about the server to be measured obtained from the node, the performance data is real-time
In the database at write service end, and server-side can draw first curve of the TPS about the time in same reference axis, and
Second curve of the response time about the time then can be again when crosspoint occur in first curve and second curve
The lasting access of pressure test in 1 minute is carried out to the server to be measured, is finally completed the test assignment；If working as described first
There is not crosspoint yet in curve and second curve, then increase the user in the test content information according to preset rules
Number carries out pressure test access to the server to be measured with updated test content information, until first curve and
There is crosspoint in second curve.
Finally, server-side generates the property for having the unique identifying number according to the performance data and the performance threshold
Energy test report, and the performance test being reported to, be sent to client shows.The performance test report can be very
The performance threshold of current server is got information about, that is, user can intuitively obtain the performance highest of server very much
It can threshold value (highest number of users and TPS).Further, by the performance threshold, the property of the server to be measured can be determined
Can, such as when number of users is greater than the highest number of users in performance threshold, the response time that can default to server will increase, very
To there is non-responsive state.
Further, in the above system of the application, the performance threshold determining module further includes following submodule: property
Energy data determining module, for determining the corresponding TPS of the server to be measured and response time according to the performance data；It is bent
Line drafting module, for drawn in same reference axis the TPS about the time the first curve and the response time about
The second curve of time；Crosspoint determining module, for occurring crosspoint, then holding when first curve and second curve
Row determines otherwise the performance threshold for obtaining the server to be measured is executed to complete the test assignment according to the crosspoint
Increase the number of users in the test content information according to preset rules, and continue to execute according to the test content information, adjusts
Pressure test access is carried out to the server to be measured with the node, with count obtained from the node about described to be measured
The performance data of server；Performance threshold obtains module, for determining and obtaining the server to be measured according to the crosspoint
Performance threshold, to complete the test assignment；It returns and surveys module, for increasing in the test content information according to preset rules
Number of users, and continue to execute described according to the test content information, call the node to press the server to be measured
Power test access, to count the performance data about the server to be measured obtained from the node.
Further, in the above system of the application, the system further include: sending module is reported in performance test, is used for
Execution " if determining the performance threshold for obtaining the server to be measured according to the performance data, complete the test assignment,
Otherwise the test content information is adjusted, and continues to execute described according to the test content information, calls the node to institute
It states server to be measured and carries out pressure test access, to count the performance number about the server to be measured obtained from the node
According to " operation after, according to the performance data and the performance threshold, generate the performance test for having the unique identifying number
Report；Sending module is reported in performance test, is shown for performance test report to be sent to client.
It should be appreciated that embodiments herein can be by computer hardware, the combination of hardware and software or by depositing
The computer instruction in non-transitory computer-readable memory is stored up to be effected or carried out.Standard program can be used in this method
Technology-include realized in computer program configured with the non-transitory computer-readable storage media of computer program, wherein
Configured in this way storage medium operates computer in a manner of specific and is predefined --- according to retouching in a particular embodiment
The method and attached drawing stated.Each program can with the programming language of level process or object-oriented come realize with computer system
Communication.However, if desired, the program can be realized with compilation or machine language.Under any circumstance, which can be compiling
Or the language explained.In addition, the program can be run on the specific integrated circuit of programming for this purpose.
Further, this method can be realized in being operably coupled to suitable any kind of computing platform, wrap
Include but be not limited to PC, mini-computer, main frame, work station, network or distributed computing environment, individual or integrated
Computer platform or communicated with charged particle tool or other imaging devices etc..The various aspects of the application can be to deposit
The machine readable code on non-transitory storage medium or equipment is stored up to realize no matter be moveable or be integrated to calculating
Platform, such as hard disk, optical reading and/or write-in storage medium, RAM, ROM, so that it can be read by programmable calculator, when
Storage medium or equipment can be used for configuration and operation computer to execute process described herein when being read by computer.This
Outside, machine readable code, or part thereof can be transmitted by wired or wireless network.When such media include combining microprocessor
Or when other data processors realization instruction or program of the step above, application as described herein includes that these and other are different
The non-transitory computer-readable storage media of type.When being programmed according to methods and techniques described herein, the application is also
Including computer itself.
Computer program can be applied to input data to execute function as described herein, to convert input data with life
At storing to the output data of nonvolatile memory.Output information can also be applied to one or more output equipments as shown
Device.In the application preferred embodiment, the data of conversion indicate physics and tangible object, including the object generated on display
Reason and the particular visual of physical objects are described.
Therefore, should be with descriptive sense rather than restrictive sense understands the specification and drawings.However, by apparent
It is:, can be to the application in the case where not departing from the broader spirit and scope of the application as described in claims
Make various modifications and change.
Other modifications are in spirit herein.Therefore, although disclosed technology may be allowed various modifications and substitution structure
It makes, but has shown that in the accompanying drawings and its some embodiments shown in being described in detail above.It will be appreciated, however, that not
It is intended to for the application to be confined to disclosed one or more concrete forms；On the contrary, its intention covers such as the appended claims
Defined in fall in all modifications, alternative constructions and equivalent in spirit and scope.
Claims (10)
1. a kind of server performance test method, which comprises the following steps:
S100 the test request sent from client is received) to extract the test of server to be measured from the test request
Mission bit stream；
S200 priority) is determined according to the test assignment information, to add tool in the corresponding task queue of the priority
There is the test assignment of unique identifying number；
S300 task type and priority) are determined according to the test assignment information, for the survey in the task queue
Trial business distribution node；
S400 the access information and test content information that server to be measured) is determined according to the test assignment information, to described
Node is configured；
S500) according to the test content information, the node is called to carry out pressure test access to the server to be measured, with
Count the performance data about the server to be measured obtained from the node；
S600 it) if determining the performance threshold for obtaining the server to be measured according to the performance data, completes the test and appoints
Business, otherwise adjusts the test content information, and continue to execute the step S500.
2. the method according to claim 1, wherein the step S300 further includes following sub-step:
S310 the test assignment) is extracted from the task queue according to the priority；
S320) according to the task type of the test assignment, determine the method for salary distribution of node, using according to the method for salary distribution as institute
State test assignment distribution node.
3. according to the method described in claim 2, it is characterized in that, the step S320 further includes following sub-step:
S321) if the task type is intelligent task type, it is determined that the corresponding preset configuration number of the intelligent task type
Amount；
S322 the idle node for being no less than the preset configuration quantity) is determined from all nodes, and by the section of the free time
Point is distributed to the test assignment.
4. the method according to claim 1, wherein the step S400 further includes following sub-step:
S410) go out the access information and test content information of server to be measured from the test assignment information extraction；
S420) from the node for being equipped with docker mirror image in advance, the starting obtained for the docker mirror image is configured
File；
S430 the server to be measured) is configured in the starting configuration file according to the access information of the server to be measured
IP address and port；
S440 remote procedure call) is configured in the starting configuration file according to the test content information of the server to be measured
Interface the scheduling request so that node receives an assignment carries out pressure test access to the server to be measured.
5. the method according to claim 1, wherein the step S500 further includes following sub-step:
S510) according to the task type of the test assignment, the node starting is controlled by way of remote procedure call
Docker mirror image；
S520 number of users and access frequency) are determined according to the test content；
S530 it) controls the docker mirror image and pressure survey is carried out to the server to be measured according to the number of users and access frequency
Examination access obtains the performance data of the server to be measured with statistics.
6. according to the method described in claim 5, the it is characterized in that, step S510) further include following sub-step:
S511) when the task type be intelligent task type, then obtain the corresponding preset configuration quantity of intelligent task type；
S512) when the quantity of the node of current idle is more than the preset configuration quantity, by way of remote procedure call
Control the node starting docker mirror image of the free time.
7. the method according to claim 1, wherein the step S600 further includes following sub-step:
S610) according to the performance data, the corresponding TPS of the server to be measured and response time are determined；
S620 the TPS) is drawn in same reference axis about the first curve of time and the response time about the time
Second curve；
S630) when crosspoint occur in first curve and second curve, S640 is thened follow the steps, it is no to then follow the steps
S650；
S640) according to the crosspoint, the performance threshold for obtaining the server to be measured is determined, to complete the test assignment；
S650) increase the number of users in the test content information according to preset rules, and continue to execute the step S500.
8. the method according to claim 1, wherein in the step S600) after further comprise the steps of:
S700 it) according to the performance data and the performance threshold, generates the performance test with the unique identifying number and reports；
S800 performance test report) is sent to client to show.
9. a kind of server performance test macro, which is characterized in that comprise the following modules:
Test request receiving module, for receiving the test request sent from client, to be extracted from the test request
The test assignment information of server to be measured；
Test assignment adding module, for determining priority according to the test assignment information, with corresponding in the priority
Addition has the test assignment of unique identifying number in task queue；
Node distribution module, for determining task type and priority according to the test assignment information, for the task team
The test assignment distribution node in column；
Node configuration module, for determining the access information and test content letter of server to be measured according to the test assignment information
Breath, to be configured to the node；
Pressure test module, for calling the node to press the server to be measured according to the test content information
Power test access, to count the performance data about the server to be measured obtained from the node；
Performance threshold determining module, if for determining the performance threshold for obtaining the server to be measured according to the performance data,
The test assignment is then completed, the test content information is otherwise adjusted, and is continued to execute described according to test content letter
Breath calls the node to carry out pressure test access to the server to be measured, with count obtained from the node about institute
State the performance data of server to be measured.
10. a kind of computer readable storage medium, is stored thereon with computer instruction, it is characterised in that the instruction is held by processor
It realizes when row such as the step of method described in any item of the claim 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811489539.2A CN109800137A (en) | 2018-12-06 | 2018-12-06 | A kind of server performance test method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811489539.2A CN109800137A (en) | 2018-12-06 | 2018-12-06 | A kind of server performance test method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109800137A true CN109800137A (en) | 2019-05-24 |
Family
ID=66556555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811489539.2A Pending CN109800137A (en) | 2018-12-06 | 2018-12-06 | A kind of server performance test method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109800137A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110460491A (en) * | 2019-07-05 | 2019-11-15 | 锐捷网络股份有限公司 | Performance test methods and device based on RDMA |
| CN110515819A (en) * | 2019-08-27 | 2019-11-29 | 深圳市网心科技有限公司 | Performance test methods, electronic equipment, scheduling system and medium |
| CN110620702A (en) * | 2019-09-19 | 2019-12-27 | 聚好看科技股份有限公司 | Pressure detection method, device and system for server |
| CN111159009A (en) * | 2019-11-29 | 2020-05-15 | 深圳智链物联科技有限公司 | Pressure testing method and device for log service system |
| CN111949546A (en) * | 2020-08-21 | 2020-11-17 | 山东英信计算机技术有限公司 | Operating system testing method, device, equipment and readable storage medium |
| CN112835792A (en) * | 2021-01-27 | 2021-05-25 | 湖南快乐阳光互动娱乐传媒有限公司 | Pressure testing system and method |
| CN113608974A (en) * | 2021-06-29 | 2021-11-05 | 济南浪潮数据技术有限公司 | Performance pressure measurement method and system of distributed storage system and related components |
| CN113835994A (en) * | 2020-06-24 | 2021-12-24 | 上海莉莉丝科技股份有限公司 | Golang language-based server stress testing system, method and computer-readable storage medium |
| WO2022088082A1 (en) * | 2020-10-30 | 2022-05-05 | 京东方科技集团股份有限公司 | Task processing method, apparatus and device based on defect detection, and storage medium |
| CN114500349A (en) * | 2021-12-27 | 2022-05-13 | 天翼云科技有限公司 | Cloud platform chaos testing method and device |
| CN114629888A (en) * | 2022-03-18 | 2022-06-14 | 中国农业银行股份有限公司 | Server load testing method and device |
| CN116107913A (en) * | 2023-04-06 | 2023-05-12 | 阿里云计算有限公司 | Test control method, device and system of single-node server |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6985940B1 (en) * | 1999-11-12 | 2006-01-10 | International Business Machines Corporation | Performance testing of server systems |
| US20160062880A1 (en) * | 2014-08-26 | 2016-03-03 | Cloudy Days Inc. Dba Nouvola | Methods and Systems for the Use of Synthetic Users To Performance Test Cloud Applications |
| CN106055464A (en) * | 2016-05-26 | 2016-10-26 | 努比亚技术有限公司 | Pressure testing device and method for data buffer clusters |
| CN107566214A (en) * | 2017-08-29 | 2018-01-09 | 微梦创科网络科技（中国）有限公司 | A kind of performance test methods and device |
| CN107908535A (en) * | 2017-11-13 | 2018-04-13 | 珠海金山网络游戏科技有限公司 | Distributed clients analogy method and device |
| CN108205477A (en) * | 2016-12-16 | 2018-06-26 | 上海仪电（集团）有限公司中央研究院 | Server stress test method |
| CN108376112A (en) * | 2018-02-09 | 2018-08-07 | 腾讯科技（深圳）有限公司 | Method for testing pressure, device and readable medium |
| CN108845949A (en) * | 2018-07-24 | 2018-11-20 | 浙江数链科技有限公司 | A kind of performance test methods and platform |
| CN108874637A (en) * | 2017-05-09 | 2018-11-23 | 北京京东尚科信息技术有限公司 | A kind of method of pressure test, system, electronic equipment and readable storage medium storing program for executing |
-
2018
- 2018-12-06 CN CN201811489539.2A patent/CN109800137A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6985940B1 (en) * | 1999-11-12 | 2006-01-10 | International Business Machines Corporation | Performance testing of server systems |
| US20160062880A1 (en) * | 2014-08-26 | 2016-03-03 | Cloudy Days Inc. Dba Nouvola | Methods and Systems for the Use of Synthetic Users To Performance Test Cloud Applications |
| CN106055464A (en) * | 2016-05-26 | 2016-10-26 | 努比亚技术有限公司 | Pressure testing device and method for data buffer clusters |
| CN108205477A (en) * | 2016-12-16 | 2018-06-26 | 上海仪电（集团）有限公司中央研究院 | Server stress test method |
| CN108874637A (en) * | 2017-05-09 | 2018-11-23 | 北京京东尚科信息技术有限公司 | A kind of method of pressure test, system, electronic equipment and readable storage medium storing program for executing |
| CN107566214A (en) * | 2017-08-29 | 2018-01-09 | 微梦创科网络科技（中国）有限公司 | A kind of performance test methods and device |
| CN107908535A (en) * | 2017-11-13 | 2018-04-13 | 珠海金山网络游戏科技有限公司 | Distributed clients analogy method and device |
| CN108376112A (en) * | 2018-02-09 | 2018-08-07 | 腾讯科技（深圳）有限公司 | Method for testing pressure, device and readable medium |
| CN108845949A (en) * | 2018-07-24 | 2018-11-20 | 浙江数链科技有限公司 | A kind of performance test methods and platform |
Non-Patent Citations (1)
| Title |
|---|
| 魏菲: "基于网站群管理平台的多机发布系统的设计与实现", 《《中国优秀硕士学位论文全文数据库 信息科技辑》》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110460491A (en) * | 2019-07-05 | 2019-11-15 | 锐捷网络股份有限公司 | Performance test methods and device based on RDMA |
| CN110515819A (en) * | 2019-08-27 | 2019-11-29 | 深圳市网心科技有限公司 | Performance test methods, electronic equipment, scheduling system and medium |
| CN110620702A (en) * | 2019-09-19 | 2019-12-27 | 聚好看科技股份有限公司 | Pressure detection method, device and system for server |
| CN110620702B (en) * | 2019-09-19 | 2021-06-01 | 聚好看科技股份有限公司 | Pressure detection method, device and system for server |
| CN111159009A (en) * | 2019-11-29 | 2020-05-15 | 深圳智链物联科技有限公司 | Pressure testing method and device for log service system |
| CN111159009B (en) * | 2019-11-29 | 2024-03-12 | 深圳智链物联科技有限公司 | Pressure testing method and device for log service system |
| CN113835994A (en) * | 2020-06-24 | 2021-12-24 | 上海莉莉丝科技股份有限公司 | Golang language-based server stress testing system, method and computer-readable storage medium |
| CN111949546A (en) * | 2020-08-21 | 2020-11-17 | 山东英信计算机技术有限公司 | Operating system testing method, device, equipment and readable storage medium |
| WO2022088082A1 (en) * | 2020-10-30 | 2022-05-05 | 京东方科技集团股份有限公司 | Task processing method, apparatus and device based on defect detection, and storage medium |
| CN112835792B (en) * | 2021-01-27 | 2023-03-03 | 湖南快乐阳光互动娱乐传媒有限公司 | Pressure testing system and method |
| CN112835792A (en) * | 2021-01-27 | 2021-05-25 | 湖南快乐阳光互动娱乐传媒有限公司 | Pressure testing system and method |
| CN113608974A (en) * | 2021-06-29 | 2021-11-05 | 济南浪潮数据技术有限公司 | Performance pressure measurement method and system of distributed storage system and related components |
| CN113608974B (en) * | 2021-06-29 | 2023-12-22 | 济南浪潮数据技术有限公司 | Performance pressure measurement method and system of distributed storage system and related components |
| CN114500349A (en) * | 2021-12-27 | 2022-05-13 | 天翼云科技有限公司 | Cloud platform chaos testing method and device |
| CN114500349B (en) * | 2021-12-27 | 2023-08-08 | 天翼云科技有限公司 | Cloud platform chaos testing method and device |
| CN114629888A (en) * | 2022-03-18 | 2022-06-14 | 中国农业银行股份有限公司 | Server load testing method and device |
| CN116107913A (en) * | 2023-04-06 | 2023-05-12 | 阿里云计算有限公司 | Test control method, device and system of single-node server |
| CN116107913B (en) * | 2023-04-06 | 2023-11-14 | 阿里云计算有限公司 | Test control method, device and system of single-node server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109800137A (en) | A kind of server performance test method and system | |
| CN110290189A (en) | A kind of container cluster management method, apparatus and system | |
| CN105074702B (en) | The Database Systems of single tenant and multi-tenant environment are provided | |
| CN104572444B (en) | A kind of game performance cloud test platform and its test method | |
| CN109889551A (en) | A kind of method of the Internet of Things cloud platform of Intelligent hardware access | |
| US20070299680A1 (en) | Systems and methods for integrating outsourcers | |
| US7660407B2 (en) | Systems and methods for scheduling contact center agents | |
| CN106484622A (en) | Method of testing, apparatus and system | |
| CN101322113B (en) | Grid computing control method for testing application program capacity of server and service method thereof | |
| CN110428555A (en) | Shared charging equipment gives back method and device | |
| CN108366021A (en) | A kind of method and system of the concurrent web page access business of processing | |
| CN106462461A (en) | System, device and methods for billing user for their consumption of mobile broadband services and virtualized cloud resources | |
| CN113037616B (en) | Interactive method and device for cooperatively controlling multiple robots | |
| CN109951545A (en) | The emerging system of adaptive container and cloud desktop and its method for obtaining cloud resource | |
| CN108881509A (en) | A kind of DNS query method and device based on HTTPDNS | |
| CN105847608A (en) | Routing device and method for call center | |
| WO2019062405A1 (en) | Application program processing method and apparatus, storage medium, and electronic device | |
| CN109327553A (en) | A kind of operation management system and method towards IaaS cloud platform | |
| CN110198339A (en) | A kind of edge calculations method for scheduling task based on QoE perception | |
| CN109753432A (en) | A kind of interface performance test method, apparatus, server and system | |
| CN109146271A (en) | Performance management method, apparatus, terminal and computer readable storage medium | |
| CN109872408A (en) | Method and apparatus for sending information | |
| CN111966556A (en) | Performance pressure measurement method and device, server and computer readable storage medium | |
| CN109726975A (en) | Project development method, apparatus, equipment and readable storage medium storing program for executing based on workflow | |
| JP2009517733A (en) | Grid computing system for testing server application program performance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190524 |
|
| RJ01 | Rejection of invention patent application after publication |