CN112445698A - Virtual service node performance test method, device and computer readable storage medium - Google Patents
Virtual service node performance test method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN112445698A CN112445698A CN201910833522.2A CN201910833522A CN112445698A CN 112445698 A CN112445698 A CN 112445698A CN 201910833522 A CN201910833522 A CN 201910833522A CN 112445698 A CN112445698 A CN 112445698A
- Authority
- CN
- China
- Prior art keywords
- service node
- interference
- virtual service
- performance
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000011056 performance test Methods 0.000 title claims description 11
- 238000012360 testing method Methods 0.000 claims abstract description 65
- 239000011159 matrix material Substances 0.000 claims description 36
- 238000012417 linear regression Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 9
- 230000002452 interceptive effect Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000014616 translation Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The embodiment of the invention provides a method, a device and a computer readable storage medium for testing the performance of a virtual service node, wherein the method is applied to a single virtual service node and comprises the following steps: generating an interference machine test script based on a preset interference parameter, wherein the interference machine test script is used for simulating an interference condition when the virtual service node runs; and under different interference conditions, determining the performance value of the virtual service node based on the statistic value of the service flow in the preset time.
Description
Technical Field
The present invention relates to the field of mobile communications technologies, and in particular, to a method and an apparatus for testing performance of a virtual service node, and a computer-readable storage medium.
Background
For a Service Function (SF) in a conventional data center, for example: load balancers, firewalls, network address translation, etc., because they use proprietary hardware devices, are typically tested by simulating the scenario in which they are actually used when testing their performance. The method is also used for testing the software business service sections deployed on the virtual machine.
The environment external interference of the current application deployment is less, and the deviation between the test value and the actual use value is smaller. However, in a virtualized environment, the service nodes are deployed in software on the virtual machines. Although the virtual machines are strictly isolated and run together without being aware of each other, a certain resource guarantee can be set, but the performance of the virtual machines is not completely isolated, and all the virtual machines on the same physical server actually share the underlying physical resources. When other virtual machines do not run, the ideal performance of the service node can be tested; however, when other virtual machines are operated, severe competition can be generated on hardware resources, performance of the service node is reduced, and the capacity of the service node is far from the ideal test value. As can be seen from the above, the performance of the service node in the presence of interference is difficult to be reflected truly by the related scheme.
Disclosure of Invention
In view of the above, embodiments of the present invention are intended to provide a method, an apparatus, and a computer-readable storage medium for testing performance of a virtual service node.
In order to achieve the above purpose, the technical solution of the embodiment of the present invention is realized as follows:
the embodiment of the invention provides a virtual service node performance test method, which is applied to a single virtual service node and comprises the following steps:
generating an interference machine test script based on a preset interference parameter, wherein the interference machine test script is used for simulating an interference condition when the virtual service node runs;
and under different interference conditions, determining the performance value of the virtual service node based on the statistic value of the service flow in the preset time.
Wherein, under different interference conditions, determining the performance value of the virtual service node based on the statistical value of the service traffic within the preset time includes:
in the test process, different interference conditions are obtained by modifying the numerical value of a preset interference parameter;
and under the corresponding interference condition, determining the performance value of the virtual service node under the interference condition according to the statistic value of the service flow in the preset time. Interference parameter
Wherein the presets include, but are not limited to, one or more of:
CPU occupancy rate x of physical server when virtual service node is not started1；
Storage utilization rate x when virtual service node on physical server is not started2；
I/O utilization x when virtual service node on physical server is not started3。
Optionally, the method further includes:
and establishing a performance model of the virtual service node under the interference condition based on the preset interference parameter and the performance value of the virtual service node.
Optionally, when the performance model of the virtual service node under the interference condition is established, the method includes:
fitting by adopting a piecewise-multivariate linear regression model, and then estimating parameters in the model by applying a least square method in each piecewise interval;
and each subsection interval is set according to the value of a preset interference parameter.
Wherein the preset interference parameters include: CPU occupancy rate x when virtual service node on physical server is not started1Storage utilization ratio x2And I/O usage x3Then, the equation corresponding to the multiple linear regression model in each segment interval is as follows:
Y＝b0+b1x1+b2x2+b3x3+e；
wherein Y is the performance of the virtual service node instance under interference conditions; b0Maximum performance value for the virtual service node instance under non-interfering conditions; b1、b2、b3Parameters of a multivariate linear model; e being modelsPrediction residuals obtained by the least squares method.
Based on the performance value of the virtual service node in the segmented interval and an equation corresponding to the multiple linear regression model, obtaining the following matrix:
Y＝BX+E；
wherein Y is an n multiplied by 1 matrix and is composed of various performance values obtained by testing in a segmented interval; x is an n X3 matrix and is formed by each interference parameter; b is a model parameter vector; e is an n multiplied by 1 matrix, is a residual error item quantity, obeys normal distribution, and n is the number of performance values in a segment interval;
and obtaining the value of B based on the matrix to obtain a performance model of the virtual service node in the segmentation interval.
The embodiment of the invention also provides a virtual service node performance testing device, which is applied to a single virtual service node and comprises the following steps:
the interference module is used for generating an interference machine test script based on a preset interference parameter and simulating an interference condition when the virtual service node operates;
and the determining module is used for determining the performance value of the virtual service node based on the statistic value of the service flow in the preset time under different interference conditions.
The embodiment of the invention also provides a virtual service node performance testing device, which comprises: a processor and a memory for storing a computer program capable of running on the processor,
wherein the processor is configured to perform the steps of the above method when running the computer program.
Embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-mentioned method.
The performance test method, device and computer readable storage medium of the virtual service node provided by the embodiment of the invention generate an interference machine test script based on the preset interference parameters, and the interference machine test script is used for simulating the interference condition when the virtual service node runs; and under different interference conditions, determining the performance value of the virtual service node based on the statistic value of the service flow in the preset time. The embodiment of the invention is applied to a single virtual service node, and considers the environmental interference when testing the performance of the virtual service node, thereby improving the effectiveness of the performance test of the service node under the interference condition, and more truly reflecting the performance of the service node by the test value.
In addition, the performance of the virtual service node interfered by a certain environment is predicted by establishing a virtual service node performance model, all interference conditions are not required to be traversed, and the usability is high.
Drawings
Fig. 1 is a first flowchart of a virtual service node performance testing method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a virtual service node performance apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a virtual service node performance apparatus according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a performance testing system of a virtual service node according to an embodiment of the present invention;
fig. 5 is a flowchart of a virtual service node performance testing method according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a virtual service node deployment structure according to an embodiment of the present invention.
Detailed Description
The invention is described below with reference to the figures and examples.
An embodiment of the present invention provides a method for testing performance of a virtual service node, as shown in fig. 1, where the method is applied to a single virtual service node, and includes:
step 101: generating an interference machine test script based on a preset interference parameter, wherein the interference machine test script is used for simulating an interference condition when the virtual service node runs;
step 102: and under different interference conditions, determining the performance value of the virtual service node based on the statistic value of the service flow in the preset time.
The embodiment of the invention considers the environmental interference when testing the performance of the virtual service node, improves the effectiveness of the performance test of the service node under the interference condition, and more truly reflects the performance of the service node by the test value.
In the embodiment of the present invention, the determining the performance value of the virtual service node based on the statistical value of the traffic flow within the preset time under different interference conditions includes:
in the test process, different interference conditions are obtained by modifying the numerical value of a preset interference parameter;
and under the corresponding interference condition, determining the performance value of the virtual service node under the interference condition according to the statistic value of the service flow in the preset time.
In the embodiment of the present invention, the preset interference parameters include, but are not limited to, one or more of the following:
CPU occupancy rate x of physical server when virtual service node is not started1；
Storage utilization rate x when virtual service node on physical server is not started2；
I/O utilization x when virtual service node on physical server is not started3。
In one embodiment, the method further comprises:
and establishing a performance model of the virtual service node under the interference condition based on the preset interference parameter and the performance value of the virtual service node.
In the embodiment of the present invention, when the performance model of the virtual service node is established under the interference condition, the method includes:
fitting by adopting a piecewise-multivariate linear regression model, and then estimating parameters in the model by applying a least square method in each piecewise interval;
and each subsection interval is set according to the value of a preset interference parameter.
In an embodiment of the present invention, the preset interference parameters include: CPU occupancy rate x when virtual service node on physical server is not started1Storage utilization ratio x2And I/O usage x3Within each of said segment intervalsThe equation corresponding to the multiple linear regression model is:
Y＝b0+b1x1+b2x2+b3x3+e；
wherein Y is the performance of the virtual service node instance under interference conditions; b0Maximum performance value for the virtual service node instance under non-interfering conditions; b1、b2、b3Parameters of a multivariate linear model; e is the prediction residual of the model, obtained by the least square method.
In the embodiment of the invention, based on the performance value of the virtual service node in the segmented interval and the equation corresponding to the multiple linear regression model, the following matrix is obtained:
Y＝BX+E；
wherein Y is an n multiplied by 1 matrix and is composed of various performance values obtained by testing in a segmented interval; x is an n X3 matrix and is formed by each interference parameter; b is a model parameter vector; e is an n multiplied by 1 matrix, is a residual error item quantity, obeys normal distribution, and n is the number of performance values in a segment interval;
and obtaining the value of B based on the matrix to obtain a performance model of the virtual service node in the segmentation interval.
In order to implement the foregoing method embodiment, an embodiment of the present invention further provides a virtual service node performance testing apparatus, as shown in fig. 2, where the apparatus is applied to a single virtual service node, and includes:
an interference module 201, configured to generate an interference machine test script based on a preset interference parameter, and configured to simulate an interference condition when the virtual service node operates;
a determining module 202, configured to determine, under different interference conditions, a performance value of the virtual service node based on a statistical value of service traffic within a preset time.
In this embodiment of the present invention, the determining module 202 determines the performance value of the virtual service node based on the statistical value of the traffic flow in the preset time under different interference conditions, including:
in the test process, different interference conditions are obtained by modifying the numerical value of a preset interference parameter;
and under the corresponding interference condition, determining the performance value of the virtual service node under the interference condition according to the statistic value of the service flow in the preset time.
In the embodiment of the present invention, the preset interference parameters include, but are not limited to, one or more of the following:
CPU occupancy rate x of physical server when virtual service node is not started1；
Storage utilization rate x when virtual service node on physical server is not started2；
I/O utilization x when virtual service node on physical server is not started3。
In one embodiment, as shown in fig. 3, the apparatus further comprises: a building module 203;
the establishing module 203 is configured to establish a performance model of the virtual service node under the interference condition based on the preset interference parameter and the performance value of the virtual service node.
In this embodiment of the present invention, when the establishing module 203 establishes the performance model of the virtual service node under the interference condition, the method includes:
fitting by adopting a piecewise-multivariate linear regression model, and then estimating parameters in the model by applying a least square method in each piecewise interval;
and each subsection interval is set according to the value of a preset interference parameter.
In an embodiment of the present invention, the preset interference parameters include: CPU occupancy rate x when virtual service node on physical server is not started1Storage utilization ratio x2And I/O usage x3Then, the equation corresponding to the multiple linear regression model in each segment interval is as follows:
Y＝b0+b1x1+b2x2+b3x3+e；
wherein Y is the performance of the virtual service node instance under interference conditions; b0For virtual service node instance to be absentMaximum performance value under interference conditions; b1、b2、b3Parameters of a multivariate linear model; e is the prediction residual of the model, obtained by the least square method.
In the embodiment of the present invention, the establishing module 203 obtains the following matrix based on the performance value of the virtual service node in the segment interval and the equation corresponding to the multiple linear regression model:
Y＝BX+E；
wherein Y is an n multiplied by 1 matrix and is composed of various performance values obtained by testing in a segmented interval; x is an n X3 matrix and is formed by each interference parameter; b is a model parameter vector; e is an n multiplied by 1 matrix, is a residual error item quantity, obeys normal distribution, and n is the number of performance values in a segment interval;
and obtaining the value of B based on the matrix to obtain a performance model of the virtual service node in the segmentation interval.
The embodiment of the invention also provides a virtual service node performance testing device, which comprises: a processor and a memory for storing a computer program capable of running on the processor,
wherein the processor is configured to execute, when running the computer program:
generating an interference machine test script based on a preset interference parameter, wherein the interference machine test script is used for simulating an interference condition when the virtual service node runs;
and under different interference conditions, determining the performance value of the virtual service node based on the statistic value of the service flow in the preset time.
When the performance value of the virtual service node is determined based on the statistical value of the service traffic within the preset time under different interference conditions, the processor is further configured to execute, when the computer program is run:
in the test process, different interference conditions are obtained by modifying the numerical value of a preset interference parameter;
and under the corresponding interference condition, determining the performance value of the virtual service node under the interference condition according to the statistic value of the service flow in the preset time.
Wherein the preset interference parameters include, but are not limited to, one or more of the following:
CPU occupancy rate x of physical server when virtual service node is not started1；
Storage utilization rate x when virtual service node on physical server is not started2；
I/O utilization x when virtual service node on physical server is not started3。
The processor is further configured to, when executing the computer program, perform:
and establishing a performance model of the virtual service node under the interference condition based on the preset interference parameter and the performance value of the virtual service node.
When the performance model of the virtual service node under the interference condition is established, the processor is further configured to execute, when the computer program is run:
fitting by adopting a piecewise-multivariate linear regression model, and then estimating parameters in the model by applying a least square method in each piecewise interval;
and each subsection interval is set according to the value of a preset interference parameter.
Wherein the preset interference parameters include: CPU occupancy rate x when virtual service node on physical server is not started1Storage utilization ratio x2And I/O usage x3Then, the equation corresponding to the multiple linear regression model in each segment interval is as follows:
Y＝b0+b1x1+b2x2+b3x3+e；
wherein Y is the performance of the virtual service node instance under interference conditions; b0Maximum performance value for the virtual service node instance under non-interfering conditions; b1、b2、b3Parameters of a multivariate linear model; e is the prediction residual of the model, obtained by the least square method.
Based on the performance value of the virtual service node in the segmented interval and an equation corresponding to the multiple linear regression model, obtaining the following matrix:
Y＝BX+E；
wherein Y is an n multiplied by 1 matrix and is composed of various performance values obtained by testing in a segmented interval; x is an n X3 matrix and is formed by each interference parameter; b is a model parameter vector; e is an n multiplied by 1 matrix, is a residual error item quantity, obeys normal distribution, and n is the number of performance values in a segment interval;
and obtaining the value of B based on the matrix to obtain a performance model of the virtual service node in the segmentation interval.
It should be noted that: in the apparatus provided in the foregoing embodiment, when performing the performance test of the virtual service node, only the division of each program module is illustrated, and in practical applications, the processing distribution may be completed by different program modules according to needs, that is, the internal structure of the device is divided into different program modules, so as to complete all or part of the processing described above. In addition, the apparatus provided in the above embodiments and the corresponding method embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments and are not described herein again.
In an exemplary embodiment, the embodiment of the present invention also provides a computer-readable storage medium, which may be a Memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface Memory, optical disc, or CD-ROM; or may be a variety of devices including one or any combination of the above memories, such as a mobile phone, computer, tablet device, personal digital assistant, etc.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs:
generating an interference machine test script based on a preset interference parameter, wherein the interference machine test script is used for simulating an interference condition when the virtual service node runs;
and under different interference conditions, determining the performance value of the virtual service node based on the statistic value of the service flow in the preset time.
When the performance value of the virtual service node is determined based on the statistical value of the service traffic in the preset time under different interference conditions, the computer program further executes, when executed by the processor:
in the test process, different interference conditions are obtained by modifying the numerical value of a preset interference parameter;
and under the corresponding interference condition, determining the performance value of the virtual service node under the interference condition according to the statistic value of the service flow in the preset time.
Wherein the preset interference parameters include, but are not limited to, one or more of the following:
CPU occupancy rate x of physical server when virtual service node is not started1；
Storage utilization rate x when virtual service node on physical server is not started2；
I/O utilization x when virtual service node on physical server is not started3。
The computer program, when executed by the processor, further performs:
and establishing a performance model of the virtual service node under the interference condition based on the preset interference parameter and the performance value of the virtual service node.
When the performance model of the virtual service node under the interference condition is established, the computer program is executed by the processor, and further executes:
fitting by adopting a piecewise-multivariate linear regression model, and then estimating parameters in the model by applying a least square method in each piecewise interval;
and each subsection interval is set according to the value of a preset interference parameter.
Wherein the preset interference parameters include: CPU occupancy rate x when virtual service node on physical server is not started1Storage utilization ratio x2And I/O usage x3Then, the equation corresponding to the multiple linear regression model in each segment interval is as follows:
Y＝b0+b1x1+b2x2+b3x3+e；
wherein Y is the performance of the virtual service node instance under interference conditions; b0Maximum performance value for the virtual service node instance under non-interfering conditions; b1、b2、b3Parameters of a multivariate linear model; e is the prediction residual of the model, obtained by the least square method.
Based on the performance value of the virtual service node in the segmented interval and an equation corresponding to the multiple linear regression model, obtaining the following matrix:
Y＝BX+E；
wherein Y is an n multiplied by 1 matrix and is composed of various performance values obtained by testing in a segmented interval; x is an n X3 matrix and is formed by each interference parameter; b is a model parameter vector; e is an n multiplied by 1 matrix, is a residual error item quantity, obeys normal distribution, and n is the number of performance values in a segment interval;
and obtaining the value of B based on the matrix to obtain a performance model of the virtual service node in the segmentation interval.
The invention is described below in conjunction with the scenario embodiments.
The Service-chain technology enables data messages to selectively pass through each Service node in sequence in a network according to Service requirements, and flexible and stable network services are provided for users. Service nodes in a conventional data center are dedicated hardware devices, and are deployed in a network through physical connection to complete various service services. The current Software Defined Networking (SDN) and Network Function Virtualization (NFV) technologies of cloud data center networks have prompted a completely new development of service chaining technologies. Service nodes (e.g., load balancers, firewalls, network address translations, etc.) are gradually transformed by traditional proprietary hardware into virtual service resource pools built by generic physical servers. The special software deployed on the virtual machine of the physical server provides service, so that the flexibility of service deployment is greatly improved, the service deployment time is shortened, and the resource utilization is more effective.
Software Service nodes are deployed on virtual machines of a server, and serious shared computing resource competition and performance interference can be generated among the virtual machines, so that load performance is greatly reduced and fluctuated, and a Service Level Agreement (SLA) applied by user load is greatly influenced. The real-time understanding of the performance of the service node operating under interference is a key to guarantee the quality of service for users. By accurately estimating the performance of the service node, the resource utilization rate of the physical server can be improved, so that the energy consumption of the data center is reduced.
Therefore, an embodiment of the present invention provides a method and a system for testing performance of a virtual service node in a service chain, where a system architecture of the method and the system is shown in fig. 4, and the method includes: the system comprises a tested device (namely a virtual service node), an interference issuing unit for issuing an interference machine test script, a service flow generating unit and a service monitoring unit at a Client (Client) side, and a service flow receiving unit and a service monitoring unit at a Server (Server) side.
The following describes an application of the system with reference to a performance test flowchart of a virtual service node shown in fig. 5, and includes the following specific steps:
the method comprises the following steps: building a performance test topology of the virtual service node;
as shown in fig. 6, which is a deployment structure diagram of a virtual service node (i.e., the device under test in fig. 4), the factor determining the performance of the service node is its software and hardware configuration. The hardware configuration comprises: the hardware model of the physical server and the hardware resources allocated to the service node, such as a CPU, a memory, a network card and the like. The software configuration is relatively complex, and can be mainly classified into Host OS software and version, Hypervisor software and version, network card delivery mode (SR-IOV or OVS), network card drive version and the like. The performance tested by the fixed software and hardware configuration is unchanged under the condition of no interference. Therefore, when a test environment is built, a real operation scene is simulated, and the same physical server configuration and software configuration are adopted.
Step two: deploying virtual service nodes;
here, the test virtual machine may be pulled on a physical server, on which the software service node is deployed. The hardware resources allocated by the virtual machine refer to a real operation scene.
Step three: issuing an interference test script;
here, the test jammer may be pulled up on a physical server and the jammer generation tool deployed thereon. And obtaining a corresponding interference machine test script according to the set interference parameters, and issuing the script to an interference generation tool on the interference machine to simulate the interference of the virtual service node during operation.
The service node performance mainly comprises three indexes of maximum newly-built connection number per second, maximum concurrent user number per second and maximum throughput per second. The maximum number of newly-built connections per second mainly consumes CPU resources, the maximum number of concurrent users per second mainly consumes storage resources (including cache and memory), and the maximum throughput per second mainly consumes network card I/O resources.
The performance interference of other virtual machines on the same physical server can be divided into CPU interference, storage interference and network card I/O interference. Defining the CPU interference parameter as the CPU occupancy rate x when the virtual service node on the physical server is not started1The storage interference parameter is the storage utilization rate x when the virtual service node on the physical server is not started2The I/O interference parameter of the network card is the I/O utilization rate x when the virtual service node on the physical server is not started3The actual interference is x1、x2And x3The combined value of (a). In CPU occupancy x1For example, the configuration parameters of the test script of the jammer can be obtained correspondingly, and the parameters are issued to the jammer, so that when the CPU occupancy rate of the physical server reaches a set value, the actual deployment environment of the virtual service node is completely simulated.
Step four: sending the service flow;
the service flow generation unit shown in fig. 4 simulates user behavior and initiates a service request of a certain pressure model to the device to be tested. According to the service performance index, the maximum number of newly-built connections per second, the maximum number of concurrent users per second, the maximum throughput per second or the superposition test of the three can be performed. And the Client terminal and the Server terminal serially connect the service monitoring units into the system, and count the number of newly-built connections, the number of concurrent users, the throughput, the success number and the failure number of the service processed on the nodes in real time.
Step five: stopping sending the service flow;
after the transmission is continued for a certain time, the flow is stopped. And calculating the maximum performance value of the service node under the interference condition according to the statistic value of the service monitoring unit during the flow duration.
Step six: modifying the interference parameters;
the modified interference parameter is the modified CPU occupancy rate x1Storage utilization ratio x2And I/O usage x3And repeating the third step to the fifth step until the performance value test under all the interference conditions is completed.
Step seven: and establishing a performance model of the service node under the interference condition according to the interference parameters and the performance value obtained by the test.
A nonlinear relation exists between the performance of the service node instance under the interference and the interference, the cost and the precision of the model are comprehensively considered, a piecewise-multivariate linear regression model is adopted for fitting, and then a least square method is applied in each interval to estimate parameters in the model. The so-called segmentation in this patent is the CPU occupancy x1Storage utilization ratio x2And I/O usage x3Is defined as assuming a CPU occupancy x of 30% ≦ CPU occupancy1Storage utilization rate x of less than or equal to 40 percent and less than or equal to 40 percent2The I/O utilization rate x is less than or equal to 50 percent and less than or equal to 40 percent3In the interval ≦ 50%, the performance of the service node instance under interference may be described in terms of a multivariate linear relationship to interference. The smaller the segmentation strength is, the higher the model accuracy is, and the selection can be performed according to actual needs.
In each subsection interval, a linear regression equation of the characteristic parameters of the system in performance and operation under the interference is established through a regression model as follows:
Y＝b0+b1x1+b2x2+b3x3+e；
where Y is the performance of the service node instance under interference, b0For maximum performance value of service node instance without interference, b1、b2、b3Is a multi-element linear modeThe parameter of type e is the prediction residual of the model. The parameters of the multivariate linear model can adopt a least square method. The basic idea is to sum the squared residuals Σ e2To a minimum.
∑e2＝∑(Y-b0-b1x1-b2x2-b3x3)2
Substituting the performance values tested in the segmentation interval in the step six into the model to obtain the following matrix:
Y＝BX+E；
wherein
In the formula, Y is an n multiplied by 1 matrix and is composed of various performance values obtained by testing in a segmented interval; x is an n X3 matrix consisting of individual interference parameters (X in each segment interval)1、x2、x3) Forming; b is a model parameter vector; e is an n multiplied by 1 matrix, is a residual error term quantity and follows normal distribution, and n is the number of performance values in a segment interval.
The parameter estimates thus obtained are:
B＝(X′X)-1X′Y；
wherein X' is the transpose of X; (X' X)-1Is the inverse of the matrix (X' X).
After the value of the matrix B is solved, the performance prediction model in the segment interval can be determined. When in use, only the interference value of the deployment environment of the service node instance is observed, namely the CPU occupancy rate x1Storage utilization ratio x2And I/O usage x3The performance of deploying the service node instance under this interference can be obtained.
The embodiment of the invention considers the environmental interference when testing the performance of the virtual service node, improves the effectiveness of the performance test of the service node under the interference condition, and more truly reflects the performance of the service node by the test value.
In addition, the performance of the virtual service node interfered by a certain environment is predicted by establishing a virtual service node performance model, all interference conditions are not required to be traversed, and the usability is high.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (10)
1. A virtual service node performance test method is applied to a single virtual service node and comprises the following steps:
generating an interference machine test script based on a preset interference parameter, wherein the interference machine test script is used for simulating an interference condition when the virtual service node runs;
and under different interference conditions, determining the performance value of the virtual service node based on the statistic value of the service flow in the preset time.
2. The method of claim 1, wherein the determining the performance value of the virtual service node based on the statistical value of the traffic flow in the preset time under different interference conditions comprises:
in the test process, different interference conditions are obtained by modifying the numerical value of a preset interference parameter;
and under the corresponding interference condition, determining the performance value of the virtual service node under the interference condition according to the statistic value of the service flow in the preset time. Interference parameter
3. The method of claim 1, wherein the presets include, but are not limited to, one or more of:
CPU occupancy rate x of physical server when virtual service node is not started1；
Storage utilization rate x when virtual service node on physical server is not started2；
I/O utilization x when virtual service node on physical server is not started3。
4. The method of claim 1, further comprising:
and establishing a performance model of the virtual service node under the interference condition based on the preset interference parameter and the performance value of the virtual service node.
5. The method of claim 4, wherein the establishing the performance model of the virtual service node under the interference condition comprises:
fitting by adopting a piecewise-multivariate linear regression model, and then estimating parameters in the model by applying a least square method in each piecewise interval;
and each subsection interval is set according to the value of a preset interference parameter.
6. The method of claim 5, wherein the preset interference parameters comprise: CPU occupancy rate x when virtual service node on physical server is not started1Storage utilization ratio x2And I/O usage x3Then, the equation corresponding to the multiple linear regression model in each segment interval is as follows:
Y＝b0+b1x1+b2x2+b3x3+e；
wherein Y is the performance of the virtual service node instance under interference conditions; b0Maximum performance value for the virtual service node instance under non-interfering conditions; b1、b2、b3Parameters of a multivariate linear model; e is the prediction residual of the model, obtained by the least square method.
7. The method of claim 6, wherein based on the performance values of the virtual service nodes in the segment interval and the corresponding equation of the multiple linear regression model, the following matrix is obtained:
Y＝BX+E；
wherein Y is an n multiplied by 1 matrix and is composed of various performance values obtained by testing in a segmented interval; x is an n X3 matrix and is formed by each interference parameter; b is a model parameter vector; e is an n multiplied by 1 matrix, is a residual error item quantity, obeys normal distribution, and n is the number of performance values in a segment interval;
and obtaining the value of B based on the matrix to obtain a performance model of the virtual service node in the segmentation interval.
8. A virtual service node performance testing device is applied to a single virtual service node and comprises the following components:
the interference module is used for generating an interference machine test script based on a preset interference parameter and simulating an interference condition when the virtual service node operates;
and the determining module is used for determining the performance value of the virtual service node based on the statistic value of the service flow in the preset time under different interference conditions.
9. A virtual service node performance testing apparatus, the apparatus comprising: a processor and a memory for storing a computer program capable of running on the processor,
wherein the processor is adapted to perform the steps of the method of any one of claims 1-7 when running the computer program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910833522.2A CN112445698A (en) | 2019-09-04 | 2019-09-04 | Virtual service node performance test method, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910833522.2A CN112445698A (en) | 2019-09-04 | 2019-09-04 | Virtual service node performance test method, device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112445698A true CN112445698A (en) | 2021-03-05 |
Family
ID=74734783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910833522.2A Pending CN112445698A (en) | 2019-09-04 | 2019-09-04 | Virtual service node performance test method, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112445698A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115118955A (en) * | 2022-05-25 | 2022-09-27 | 海南乾唐视联信息技术有限公司 | Service testing method, device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103368670A (en) * | 2013-07-05 | 2013-10-23 | 上海华为技术有限公司 | Method and device for generating simulated interference |
| CN107515779A (en) * | 2017-09-01 | 2017-12-26 | 周口师范学院 | Virtual machine performance interference metric system and method based on detector |
| CN108037979A (en) * | 2017-12-26 | 2018-05-15 | 云南大学 | Virtual machine performance based on the Bayesian network containing hidden variable declines appraisal procedure |
-
2019
- 2019-09-04 CN CN201910833522.2A patent/CN112445698A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103368670A (en) * | 2013-07-05 | 2013-10-23 | 上海华为技术有限公司 | Method and device for generating simulated interference |
| CN107515779A (en) * | 2017-09-01 | 2017-12-26 | 周口师范学院 | Virtual machine performance interference metric system and method based on detector |
| CN108037979A (en) * | 2017-12-26 | 2018-05-15 | 云南大学 | Virtual machine performance based on the Bayesian network containing hidden variable declines appraisal procedure |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115118955A (en) * | 2022-05-25 | 2022-09-27 | 海南乾唐视联信息技术有限公司 | Service testing method, device and storage medium |
| CN115118955B (en) * | 2022-05-25 | 2024-04-26 | 海南乾唐视联信息技术有限公司 | Service testing method and device and storable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110347596B (en) | Test method, device, system, electronic equipment and medium | |
| CN107534571B (en) | Method, system and computer readable medium for managing virtual network functions | |
| US20140122935A1 (en) | Diagnosing a Problem of a Software Product Running in a Cloud Environment | |
| Zeng et al. | EmuEdge: A hybrid emulator for reproducible and realistic edge computing experiments | |
| CN107749807B (en) | Network function verification method and verification system for NFV | |
| Caglar et al. | Intelligent, performance interference-aware resource management for iot cloud backends | |
| Teixeira et al. | Datacenter in a box: Test your SDN cloud-datacenter controller at home | |
| US11709978B1 (en) | Optimization of configurable distributed computing systems | |
| Nadeem et al. | An early evaluation and comparison of three private cloud computing software platforms | |
| CN116431282A (en) | Cloud virtual host server management method, device, equipment and storage medium | |
| US11546224B2 (en) | Virtual network layer for distributed systems | |
| De Simone et al. | A latency-driven availability assessment for multi-tenant service chains | |
| Alnazir et al. | Performance analysis of Cloud Computing for distributed data center using cloud-sim | |
| Khorsandroo et al. | An experimental investigation of SDN controller live migration in virtual data centers | |
| CN112445698A (en) | Virtual service node performance test method, device and computer readable storage medium | |
| Wu et al. | A resource design framework to realize intent-based cloud management | |
| CN114365461B (en) | System and method for providing traffic generation on a network device | |
| US20170134307A1 (en) | Method and system for mediated resource allocation | |
| US9668082B2 (en) | Virtual machine based on a mobile device | |
| Banerjee et al. | An approach toward amelioration of a new cloudlet allocation strategy using Cloudsim | |
| US20220358055A1 (en) | Method and apparatus for acquiring device information, storage medium and electronic device | |
| Qiu et al. | Performability analysis of a cloud system | |
| CN112348196A (en) | Distributed machine learning system and method of self-adaptive RDMA (remote direct memory Access) network | |
| CN110392129A (en) | The method of IPv6 client computer and IPv6 client computer and server communication | |
| Eden et al. | A survey of performance modeling and analysis issues in resource management across x86-based hypervisors in enterprise cloud computing deployments |
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 |