CN104104551A - Cloud resource requirement assessment method and device - Google Patents
Cloud resource requirement assessment method and device Download PDFInfo
- Publication number
- CN104104551A CN104104551A CN201310113359.5A CN201310113359A CN104104551A CN 104104551 A CN104104551 A CN 104104551A CN 201310113359 A CN201310113359 A CN 201310113359A CN 104104551 A CN104104551 A CN 104104551A
- Authority
- CN
- China
- Prior art keywords
- service
- deployed
- cloud
- occupied
- cloud resource
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000011156 evaluation Methods 0.000 claims description 35
- 238000005516 engineering process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a cloud resource requirement assessment method. The method comprises the steps that a Benchmark test is performed on a service to be deployed, and change volume of cloud resource occupied during which volume of the service to be deployed is changed is confirmed; and the cloud resource required to be occupied by the service to be deployed is confirmed according to change volume of the service to be deployed and change volume of the occupied cloud resource. The invention also discloses a cloud resource requirement assessment device. The cloud resource required to be applied for the service to be deployed can be confirmed so that implementation cost of service deployment is controlled and utilization rate of the cloud resource is enhanced.
Description
Technical Field
The invention relates to a cloud computing technology, in particular to a cloud resource demand evaluation method and device.
Background
Cloud computing technology is increasingly widely applied, and a cloud management platform encapsulates Information Technology (IT) resources into cloud resources, allocates the cloud resources to clients according to requests of the clients, and performs charging.
At present, before a customer applies for cloud resources from a cloud management platform, the customer who needs to apply for the cloud resources according to deployment service computing often cannot perform accurate computing for the customer who lacks IT implementation experience, and subsequently the cloud resources applied for the customer need to be adjusted according to actual service requirements, if the cloud resources applied for the customer in the early stage are insufficient, the service operation performance is reduced, and the cloud resources need to be reapplied in the later stage, so that the workload is increased; if the cloud resources are applied too much in the earlier stage, the service deployment cost is increased, and meanwhile, the utilization rate of the cloud resources is reduced.
Therefore, how to determine the cloud resources occupied by the service to be deployed when the service is deployed so as to reasonably apply for the cloud resources, control implementation cost and improve the utilization rate of the cloud resources becomes a problem to be solved urgently.
Disclosure of Invention
In view of this, the present invention mainly aims to provide a method and an apparatus for evaluating cloud resource requirements, so as to ensure that cloud resources to be applied are accurately determined when a service is deployed, control implementation cost, and improve utilization rate of the cloud resources.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the invention provides a cloud resource demand evaluation method, which comprises the following steps:
performing a Benchmark (Benchmark) test on the service to be deployed, and determining the change amount of the cloud resources occupied when the service amount of the service to be deployed is changed;
and determining cloud resources required to be occupied by the service to be deployed according to the change amount of the service to be deployed and the change amount of the occupied cloud resources, and applying for the cloud resources for the service to be deployed according to the determined cloud resources required to be occupied.
Preferably, the determining, according to the change amount of the traffic to be deployed and the change amount of the cloud resource occupied by the traffic to be deployed, the cloud resource that the traffic to be deployed needs to occupy includes:
according to the change amount c of the traffic1And the amount of change z occupying cloud resources1Determining the cloud resource X to be occupied when the traffic of the service to be deployed is c1Is (z)1/c1)×c。
Preferably, the method further comprises:
determining that the service to be deployed needs to occupy according to the service volume of the historical deployment service with the same type as the service to be deployed, the cloud resources occupied by the historical deployment service and the utilization rate of the occupied cloud resourcesCloud resource X of2(ii) a Determining that the cloud resource X required to be applied for the service to be deployed is (a X X)1)+(b×X2) Wherein a and b are each X1And X2The corresponding weight.
Preferably, the determining, according to the traffic volume of the historical deployment service of the same type as the service to be deployed, the cloud resource occupied by the historical deployment service, and the utilization rate of the occupied cloud resource, the cloud resource that the service to be deployed needs to occupy includes:
according to the cloud resource T occupied by the historical deployment service, and the traffic volume of the historical deployment service is c2The utilization rate eta of the occupied cloud resources T determines the quantity z of the cloud resources required to be occupied by the business single service to be deployed2Is (T × η)/c2And according to the service list to be deployed, the cloud resource z is occupied2Determining cloud resource X required to be occupied by service to be deployed with traffic volume c2Is z2×c。
Preferably, the method further comprises:
when the cloud resource actually occupied by the service to be deployed is smaller than the determined cloud resource X, increasing the determined cloud resource X according to a preset amplitude1And X2The larger value of the intermediate value corresponds to the value of the weight;
when the number of cloud resources actually occupied by the service to be deployed is larger than that of the cloud resources X which are determined to be occupied, increasing the determined cloud resources X according to a preset amplitude1And X2The smaller of which corresponds to the value of the weight.
Preferably, the method further comprises:
determining a cloud resource X required to be applied by service predicted support running time (mxt) according to the increase rate y of the utilization rate of the cloud resource in the running time t of the service to be deployedm×tIs X [ (1+ y)t-1]。
The invention also provides a cloud resource demand evaluation device, which comprises: the device comprises a first determining module, a second determining module and a third applying module; wherein,
the first determining module is used for performing a Benchmark test on the service to be deployed and determining the change amount of the cloud resources occupied when the service amount of the service to be deployed is changed;
the second determining module is used for determining the cloud resource X required to be occupied by the service to be deployed according to the change amount of the service to be deployed and the change amount of the occupied cloud resource1；
And the third application module is used for applying for the cloud resources for the service to be deployed according to the determined cloud resources to be occupied.
Preferably, the second determining module is further configured to change the amount of traffic c according to the amount of traffic1And the amount of change z occupying cloud resources1Determining the cloud resource X to be occupied when the traffic of the service to be deployed is c1Is (z)1/c1)×c。
Preferably, the cloud resource demand evaluation apparatus further includes:
a fourth determining module, configured to determine, according to a traffic volume of a historical deployment service of the same type as the service to be deployed, a cloud resource occupied by the historical deployment service, and a utilization rate of the cloud resource occupied by the historical deployment service, a cloud resource X that the service to be deployed needs to occupy2；
The second determining module is further configured to determine that the cloud resource X required to be applied for the service to be deployed is (a × X)1)+(b×X2) Wherein a and b are each X1And X2The corresponding weight.
Preferably, the fourth determining module is further configured to deploy, according to the cloud resource T occupied by the historical deployment service and the traffic volume c of the historical deployment service2The utilization rate eta of the occupied cloud resources T determines the quantity z of the cloud resources required to be occupied by the business single service to be deployed2＝(T×η)/c2According to the waiting partCloud resource z is occupied for deploying business single business2Determining that a service to be deployed with a traffic volume of c needs to occupy a cloud resource X2Is z2×c。
Preferably, the fourth determining module is further configured to, when the cloud resource actually occupied by the service to be deployed is smaller than the determined cloud resource X, increase the determined cloud resource X by a preset range1And X2The larger value of the intermediate value corresponds to the value of the weight; when the number of cloud resources actually occupied by the service to be deployed is larger than the determined cloud resource X, increasing the determined cloud resource X according to a preset amplitude1And X2The smaller of which corresponds to the value of the weight.
Preferably, the fourth determining module is further configured to determine, according to an increase rate y of a utilization rate of cloud resources within a running time t of a service to be deployed, a cloud resource X that is required to be applied by the service to be expected to support a running time (mxt)m×tIs X [ (1+ y)t-1]。
According to the technical scheme provided by the invention, the cloud resource evaluation value X required to be applied for the service to be deployed is determined to be (a X X) according to the information of the service to be deployed and the information of the historical service to be deployed of the service with the same type as the service to be deployed in the Benchmark test1)+(b×X2) And when the occupied cloud resources are larger than or smaller than the evaluation value X during the trial operation of the service to be deployed, adjusting the weighted value a or b according to a preset amplitude to correspondingly reduce or increase the cloud resource evaluation value X to be occupied, so as to ensure that the cloud resources required to be applied can be accurately determined finally. And applying for the cloud resources according to the evaluation value X when the service is deployed, so that the condition that the application for the cloud resources is unreasonable when the service is deployed for the first time is avoided, the utilization rate of the cloud resources is improved, and the implementation cost is effectively controlled.
Drawings
FIG. 1 is a schematic flow chart of an implementation of a cloud resource demand assessment method according to the present invention;
fig. 2 is a schematic structural diagram of the cloud resource demand evaluation apparatus according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a schematic flow chart of an implementation of the cloud resource demand evaluation method of the present invention, as shown in fig. 1, including:
step 101: performing a Benchmark test on a service to be deployed, and determining the change amount of cloud resources occupied when the service amount of the service to be deployed is changed;
the cloud resources are resources of a cloud server packaged by a cloud management platform, and include but are not limited to: central Processing Unit (CPU) resources, memory resources, storage resources, and network bandwidth resources.
The CPU resource is measured by the main frequency of a CPU of a cloud server, the memory resource is measured by the memory capacity of the cloud server, the storage resource is measured by the storage capacity of a nonvolatile storage medium of the cloud server, the network bandwidth resource is measured by the network bandwidth used by the cloud server, and the change amount of the CPU resource, the memory resource, the storage resource and the network bandwidth resource is determined according to the change amount of the resource and the resource utilization rate.
Among them, the Benchmark test is a test performed according to the standard Performance Evaluation organization (SPEC, Standard Performance Evaluation Corporation) specifications.
Step 102: and determining cloud resources required to be occupied by the service to be deployed according to the change amount of the service to be deployed and the change amount of the occupied cloud resources, and requesting the cloud resources for the service to be deployed according to the determined cloud resources required to be occupied.
Preferably, the determining, according to the change amount of the traffic to be deployed and the change amount of the cloud resource occupied by the traffic to be deployed, the cloud resource that the traffic to be deployed needs to occupy includes:
according to the change amount c of the traffic1And the amount of change z occupying cloud resources1Determining the cloud resource X to be occupied when the traffic of the service to be deployed is c1Is (z)1/c1)×c。
For example, a benchmark test program is run on x cloud servers to be tested, which bear services to be deployed, and the benchmark test program loads configuration files of preset loads on the x cloud servers to simulate a scenario in which a cloud server supports services to be deployed with different traffic volumes, and the following data can be determined: the service volume of the service supported by the x cloud servers together is c1In time, the service occupies the CPU resource z of each cloud server11iMemory resource z12iStorage resource z13iAnd network bandwidth resource z14iWherein i is a positive integer and is not less than 1 and not more than x. Thus, based on said determined traffic c1And occupied cloud resources, and determining that the service with the traffic volume of c needs to occupy the CPU resource X11＝(z11/c1) X c, memory resource X is occupied12＝(z12/c1) X c, memory resource X is occupied13＝(z13/c1) X c, network bandwidth resource X is occupied14＝(z14/c1) X c; wherein, <math>
<mrow>
<msub>
<mi>z</mi>
<mn>11</mn>
</msub>
<mo>=</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>z</mi>
<mrow>
<mn>11</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>,</mo>
</mrow>
</math> <math>
<mrow>
<msub>
<mi>z</mi>
<mn>12</mn>
</msub>
<mo>=</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>z</mi>
<mrow>
<mn>12</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>,</mo>
</mrow>
</math> <math>
<mrow>
<msub>
<mi>z</mi>
<mn>13</mn>
</msub>
<mo>=</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>z</mi>
<mrow>
<mn>13</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>,</mo>
</mrow>
</math> <math>
<mrow>
<msub>
<mi>z</mi>
<mn>14</mn>
</msub>
<mo>=</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>z</mi>
<mrow>
<mn>14</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>.</mo>
</mrow>
</math>
the following description exemplifies the processing of determining the cloud resources that need to be occupied by the service to be deployed:
when x cloud servers bearing services to be deployed provide the same number of cloud resources, and it is determined that one cloud server supports a Web service with a service volume of 100 through a specbob 99 test program, the core main frequency of the cloud server 6 increases the utilization rate of a CPU of a 2 gigahertz (GHz, Gigabyte Hertz) by 5%, the memory occupies 1 Gigabyte (Gigabyte) by 1, the storage is unchanged, the network bandwidth occupies 10 megabits per second (Mbps), and assuming that the service volume of the services to be deployed needs to be supported by the x cloud servers is c, since the cloud servers provide the same number of cloud resources for the services to be deployed to occupy, the average service volume of each cloud server supporting the services with c/x, the services to be deployed need to occupy the cloud resources as follows:
CPU resource X11＝(c/x)×[(2×6GHz×5％)/100]×(x)；
Memory resourcesX12＝(c/x)×[(1GB×5％)/100]×(x)；
Storage resource X13(Web page storage amount/x) × (x);
network bandwidth resource X14＝(c/x)×(10Mbps/100)×(x)。
The cloud services provide the same amount of occupied services for the services to be deployed, so that the cloud resource occupation condition of each cloud server is approximately considered to be the same, and the change amount of the occupied cloud resources when the service volume of one cloud server is changed can be tested.
The operation result is subjected to integer selection, so that the condition that the cloud resource is not enough for the service to be deployed can be avoided.
Wherein, the storage resource X is unchanged due to the increase of the cloud server traffic and the storage13And storing the Web page storage amount of the current cloud server.
Preferably, the method further comprises:
determining cloud resources X required to be occupied by the service to be deployed according to the service volume of the historical deployment service with the same type as the service to be deployed, the cloud resources occupied by the historical deployment service and the utilization rate of the occupied cloud resources2(ii) a Determining that the cloud resource X required to be applied for the service to be deployed is (a X X)1)+(b×X2) Wherein a and b are each X1And X2The corresponding weight.
Preferably, the determining, according to the traffic volume of the historical deployment service of the same type as the service to be deployed, the cloud resource occupied by the historical deployment service, and the utilization rate of the occupied cloud resource, the cloud resource occupied by the service to be deployed includes:
according to the cloud resource T occupied by the historical deployment service and the service volume c of the historical deployment service2Determining the utilization rate eta of the occupied cloud resource T, and determining that the business form to be deployed needs to occupy the cloud resource z2Is (T × η)/c2And according to the service list to be deployed, the cloud resource z is occupied2Determining cloud resource X required to be occupied by service to be deployed with traffic volume c2Is z2×c。
The cloud management platform maintains information of the historical deployment service, wherein the information comprises service type information of the historical deployment service borne by a cloud server, cloud resource information of the historical deployment service occupying the cloud server, and utilization rate information of the occupied cloud resource.
Specifically, when the historical deployment information includes the following data: when a cloud server supports Web services in a cloud environment, the Web services occupy T1And the utilization rate of the CPU resource is eta1Number T2And the utilization rate of the memory resource is eta2Number T3And the storage resource utilization rate is eta3And the number T4And the utilization rate of the network bandwidth resource is eta4. Determining that the Web service to be deployed with the traffic volume c needs to occupy the CPU resource X according to the data21＝(T1×η1/c2) X c, memory resource X is occupied22＝(T2×η2/c2) X c, memory resource X is occupied23＝(T3×η3/c2) X c, CPU resource X is occupied24＝(T4×η4/c2)×c。
Determining that the service to be deployed of the Web with the traffic volume c needs to occupy the cloud resource according to the information, for example, the following steps are performed:
supporting traffic c of x cloud servers in cloud environment2The historical Web service of (1), and the CPU resource provided by each cloud server is TliMemory resource is T2iThe storage resource is T3iAnd network bandwidth of T4iThe CPU resource utilization rate of each cloud server is etaliMemory utilization ratio of eta2iStorage resource utilization ratio of η3iNetwork bandwidth resource utilization ratio is eta respectively4iWherein i is a positive integer and is not less than 1 and not more than x. Then, the average cloud resources occupied by the single historical Web service on each cloud server is:
CPU resource Z21i＝(Tli×η1i)/c2；
Memory resource Z22i＝(T2i×η2i)/c2；
Storage resource Z23i＝(T3i×η3i)/c2；
Network bandwidth resource Z24i＝(T4i×η4i)/c2Wherein i is a positive integer and is not less than 1 and not more than x.
Correspondingly, the cloud resources of x cloud servers which are occupied by the single historical Web service are as follows:
CPU resource <math>
<mrow>
<msub>
<mi>Z</mi>
<mn>21</mn>
</msub>
<mo>=</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>Z</mi>
<mrow>
<mn>21</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>;</mo>
</mrow>
</math>
Amount of memory resources <math>
<mrow>
<msub>
<mi>Z</mi>
<mn>22</mn>
</msub>
<mo>=</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>Z</mi>
<mrow>
<mn>22</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>;</mo>
</mrow>
</math>
Amount of storage resources <math>
<mrow>
<msub>
<mi>Z</mi>
<mn>23</mn>
</msub>
<mo>=</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>Z</mi>
<mrow>
<mn>23</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>;</mo>
</mrow>
</math>
Amount of network bandwidth resourcesWherein i is a positive integer.
When the Web service traffic c is to be deployed, the cloud resources need to be occupied:
amount of CPU resources <math>
<mrow>
<msub>
<mi>X</mi>
<mn>21</mn>
</msub>
<mo>=</mo>
<mi>c</mi>
<mo>×</mo>
<msub>
<mi>Z</mi>
<mn>21</mn>
</msub>
<mo>=</mo>
<mi>c</mi>
<mo>×</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>Z</mi>
<mrow>
<mn>21</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>;</mo>
</mrow>
</math>
Test value of memory resource amount <math>
<mrow>
<msub>
<mi>X</mi>
<mn>22</mn>
</msub>
<mo>=</mo>
<mi>c</mi>
<mo>×</mo>
<msub>
<mi>Z</mi>
<mn>22</mn>
</msub>
<mo>=</mo>
<mi>c</mi>
<mo>×</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>Z</mi>
<mrow>
<mn>22</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>;</mo>
</mrow>
</math>
Amount of storage resources <math>
<mrow>
<msub>
<mi>X</mi>
<mn>23</mn>
</msub>
<mo>=</mo>
<mi>c</mi>
<mo>×</mo>
<msub>
<mi>Z</mi>
<mn>23</mn>
</msub>
<mo>=</mo>
<mi>c</mi>
<mo>×</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>Z</mi>
<mrow>
<mn>23</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>;</mo>
</mrow>
</math>
Amount of network bandwidth resources <math>
<mrow>
<msub>
<mi>X</mi>
<mn>24</mn>
</msub>
<mo>=</mo>
<mi>c</mi>
<mo>×</mo>
<msub>
<mi>Z</mi>
<mn>24</mn>
</msub>
<mo>=</mo>
<mi>c</mi>
<mo>×</mo>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>x</mi>
</munderover>
<msub>
<mi>Z</mi>
<mrow>
<mn>24</mn>
<mi>i</mi>
</mrow>
</msub>
<mo>;</mo>
</mrow>
</math>
Wherein, the method of assigning the value of the weight includes, but is not limited to, the following two methods:
the value space of the weights a and b meets the condition that a is more than 0 and less than 1, and a + b is 1;
weight of M is more than or equal to 0 and less than or equal to 1, and m + n is equal to 1.
Preferably, the method further comprises:
when the cloud resource actually occupied by the service to be deployed is smaller than the cloud resource X which is determined to be occupied, increasing the determined cloud resource X according to a preset amplitude1And X2The larger value of the intermediate value corresponds to the value of the weight;
when the number of cloud resources actually occupied by the service to be deployed is larger than that of the cloud resources X which are determined to be occupied, increasing the determined cloud resources X according to a preset amplitude1And X2The smaller of which corresponds to the value of the weight.
Wherein the determined cloud resource X is increased by a preset amplitude1And X2And the larger value or the smaller value corresponds to the value of the weight, and the cloud resources X which are determined to be occupied can be correspondingly increased or decreased, so that the cloud resources X which are applied for adjustment can be applied to the cloud management platform according to the adjusted cloud resources X which are determined to be occupied when the service to be deployed is run in a trial mode.
Preferably, the method further comprises:
determining a cloud resource X required to be applied by service predicted support operation time (mxt) according to an increase rate y of the utilization rate of the cloud resource within t time after the service to be deployed operatesm×tIs X [ (1+ y)t-1]。
Fig. 2 is a schematic diagram of a composition structure of the cloud resource demand evaluation apparatus of the present invention, and as shown in fig. 2, the cloud resource demand evaluation apparatus includes: a first determining module 21, a second determining module 22 and a third applying module 23; wherein,
the first determining module 21 is configured to perform a Benchmark test on a service to be deployed, and determine a change amount of cloud resources occupied when a service amount of the service to be deployed is changed;
the second determining module 22 is configured to determine, according to the change amount of the traffic to be deployed and the change amount of the occupied cloud resource, the cloud resource that needs to be occupied by the traffic to be deployed;
the third application module 23 is configured to apply for cloud resources for the service to be deployed according to the determined cloud resources that need to be occupied.
Preferably, the second determining module 22 is further configured to change the amount of traffic c according to the amount of traffic1And the amount of change z occupying cloud resources1Determining the cloud resource X to be occupied when the traffic of the service to be deployed is c1Is (z)1/c1)×c。
Preferably, the cloud resource demand evaluation apparatus further includes:
a fourth determining module 24, configured to determine, according to the traffic volume of the historical deployment service of the same type as the service to be deployed, the cloud resources occupied by the historical deployment service, and the utilization rate of the occupied cloud resources, cloud resources X that the service to be deployed needs to occupy2；
The second determining module 22 is further configured to determine that the cloud resource X required to be applied for the service to be deployed is (a × X)1)+(b×X2) Wherein a and b are each X1And X2The corresponding weight.
Preferably, the second determining module 22 is further configured to deploy the service according to the historical deployment service, the cloud resource T occupied by the historical deployment service, and the traffic volume c of the historical deployment service2Determining the utilization rate eta of the occupied cloud resources T, and determining the quantity z of the occupied cloud resources z for the operation of the to-be-deployed service single service2＝(T×η)/c2And operating and occupying cloud resources z according to the single service volume of the service to be deployed2Determining cloud resources X required to be occupied by operation of to-be-deployed service with traffic volume c2Is z2×c。
Preferably, the fourth determining module 24 is further configured to, when the cloud resource actually occupied by the service to be deployed is smaller than the cloud resource X determined to be occupied, increase the determined cloud resource X by a preset range1And X2The larger value of the intermediate value corresponds to the value of the weight; when the cloud resource actually occupied by the service to be deployed is larger than the cloud resource X which is determined to be occupied, increasing the determined cloud resource X according to a preset amplitude1And X2The smaller of which corresponds to the value of the weight.
Preferably, the fourth determining module 24 is further configured to determine, according to the increase rate y of the utilization rate of the cloud resource at t time after the service to be deployed runs, the cloud resource X that the service is expected to support the application required by the running time (mxt)m×tIs X [ (1+ y)t-1]。
The cloud resource demand evaluation device provided by the embodiment of the invention can be modularly embedded into a server of a cloud management platform, and can also be used as an independent server in the cloud management platform.
Examples
In this embodiment, the method of the present invention is further described in detail by taking an example of deploying a mail system on a cloud server in a cloud environment.
In the embodiment, the purpose of evaluating the cloud resources required by the service to be deployed is achieved by embedding the cloud resource requirement evaluation module in the cloud management platform.
The cloud resource demand evaluation module maintains corresponding service models for different types of services to be deployed, and the service models comprise service volume c to be deployed, determined according to Benchmark test of the services to be deployed1Change amount z of temporal occupation cloud resource1And determining that the single historical deployment service with the same type as the service to be deployed occupies the cloud resource z according to the information of the historical deployment service with the same type as the service to be deployed2The information of (1).
When a user logs in a cloud management platform to issue a service requirement for deploying a mail system, typically, the service requirement includes: maximum number of concurrent users supported, maximum attachment size, maximum response time, and desired mail service software. The cloud resource demand evaluation module determines a corresponding service model according to the service demand information, takes the maximum number of concurrent users as the traffic c, and determines that the mail system to be deployed needs to occupy the cloud resources X according to the corresponding model1＝(z1/c1) X c, determining that the mail system to be deployed needs to occupy the cloud resource X2＝z2X c is Z1And Z2Correspondingly distributing weights a and b, thereby determining the cloud resource X (a X X) required to be applied by the mail system to be deployed1)+(b×X2)；
The cloud resource demand evaluation module feeds the cloud resource evaluation value X to be occupied back to the client through the cloud management platform, the client can also modify the evaluation value X, and the client applies for the cloud resource in batches to the cloud management platform according to the modified evaluation value X;
correspondingly, when a mail system is deployed on the applied cloud resources and is in trial operation, if the cloud resources applied according to the evaluation value X are smaller than or larger than the cloud resources required by the actual operation of the mail system, the cloud resource demand evaluation module adjusts the value of the weight a or b according to a preset amplitude so as to correspondingly increase or reduce the evaluation value X of the cloud resources required to be occupied, and applies for updating the applied cloud resources to the cloud management platform according to the evaluation value;
further, when the mail system is expanded, according to the increase rate y of the utilization rate of the cloud resources of the mail system during the operation time t, determining the cloud resources X (1+ y) which are expected to be occupied by the support operation time (mxt) after the expansion of the mail systemtCorrespondingly, the cloud resource X needs to be applied to the cloud management platform againm×tIs X [ (1+ y)t-1」。
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 (12)
1. A cloud resource demand assessment method is characterized by comprising the following steps:
performing a Benchmark test on the service to be deployed, and determining the change amount of cloud resources occupied when the service amount of the service to be deployed is changed;
and determining cloud resources required to be occupied by the service to be deployed according to the change amount of the service to be deployed and the change amount of the occupied cloud resources, and applying for the cloud resources for the service to be deployed according to the determined cloud resources required to be occupied.
2. The method according to claim 1, wherein the determining, according to the change amount of the traffic to be deployed and the change amount of the occupied cloud resources, the cloud resources that the traffic to be deployed needs to occupy includes:
according to the change amount c of the traffic1And the amount of change z occupying cloud resources1Determining the cloud resource X to be occupied when the traffic of the service to be deployed is c1Is (z)1/c1)×c。
3. The method of claim 1, further comprising:
determining cloud resources X required to be occupied by the service to be deployed according to the service volume of the historical deployment service with the same type as the service to be deployed, the cloud resources occupied by the historical deployment service and the utilization rate of the occupied cloud resources2(ii) a Determining that the cloud resource X required to be applied for the service to be deployed is (a X X)1)+(b×X2) Wherein a and b are each X1And X2The corresponding weight.
4. The method according to claim 3, wherein the determining, according to the traffic volume of the historical deployment service of the same type as the service to be deployed, the cloud resources occupied by the historical deployment service, and the utilization rate of the occupied cloud resources, the cloud resources that the service to be deployed needs to occupy includes:
according to the cloud resource T occupied by the historical deployment service, and the traffic volume of the historical deployment service is c2The utilization rate eta of the occupied cloud resources T determines the quantity z of the cloud resources required to be occupied by the business single service to be deployed2Is (T × η)/c2And according to the service list to be deployed, the cloud resource z is occupied2Determining cloud resource X required to be occupied by service to be deployed with traffic volume c2Is z2×c。
5. The method of claim 4, further comprising:
when the cloud resource actually occupied by the service to be deployed is smaller than the determined cloud resource X, increasing the determined cloud resource X according to a preset amplitude1And X2The larger value of the intermediate value corresponds to the value of the weight;
when the number of cloud resources actually occupied by the service to be deployed is larger than that of the cloud resources X which are determined to be occupied, increasing the determined cloud resources X according to a preset amplitude1And X2The smaller of which corresponds to the value of the weight.
6. The method of claim 1, 2, 3, 4, or 5, further comprising:
determining a cloud resource X required to be requested by service predicted support running time (mxt) according to an increase rate y of the utilization rate of the cloud resource within the running time t of the service to be deployedm×tIs X [ (1+ y)t-1]。
7. A cloud resource demand evaluation apparatus, comprising: the device comprises a first determining module, a second determining module and a third applying module; wherein,
the first determining module is used for performing a Benchmark test on the service to be deployed and determining the change amount of the cloud resources occupied when the service amount of the service to be deployed is changed;
the second determining module is used for determining the cloud resources occupied by the service to be deployed according to the change amount of the service to be deployed and the change amount of the occupied cloud resources;
and the third application module is used for applying for the cloud resources for the service to be deployed according to the determined cloud resources to be occupied.
8. The cloud resource demand evaluation apparatus of claim 7,
the second determining module is further configured to change the traffic volume according to the change amount c1And occupy cloud resourcesAmount of change of source z1Determining the cloud resource X to be occupied when the traffic of the service to be deployed is c1Is (z)1/c1)×c。
9. The cloud resource demand evaluation device of claim 7, wherein the cloud resource demand evaluation device further comprises:
a fourth determining module, configured to determine, according to a traffic volume of a historical deployment service of the same type as the service to be deployed, a cloud resource occupied by the historical deployment service, and a utilization rate of the cloud resource occupied by the historical deployment service, a cloud resource X that the service to be deployed needs to occupy2；
The second determining module is further configured to determine that the cloud resource X required to be applied for the service to be deployed is (a × X)1)+(b×X2) Wherein a and b are each X1And X2The corresponding weight.
10. The cloud resource demand evaluation apparatus of claim 9,
the fourth determining module is further configured to deploy, according to the cloud resource T occupied by the historical deployment service and the traffic volume c of the historical deployment service2The utilization rate eta of the occupied cloud resources T determines the quantity z of the cloud resources required to be occupied by the business single service to be deployed2＝(T×η)/c2And according to the service list to be deployed, the cloud resource z is occupied2Determining that a service to be deployed with a traffic volume of c needs to occupy a cloud resource X2Is z2×c。
11. The cloud resource demand evaluation apparatus of claim 10,
the fourth determining module is further configured to, when the cloud resource actually occupied by the service to be deployed is smaller than the determined cloud resource X, increase the determined cloud resource X by a preset range1And X2The larger value of the intermediate value corresponds to the value of the weight; when the number of cloud resources actually occupied by the service to be deployed is larger than the determined cloud resource XIncreasing the determined cloud resource X according to a preset amplitude1And X2The smaller of which corresponds to the value of the weight.
12. The cloud resource demand evaluation apparatus of claim 9, 10 or 11,
the fourth determining module is further configured to determine, according to the increase rate y of the utilization rate of the cloud resource at the service operation time t to be deployed, a cloud resource X which is required to be applied by the service predicted support operation time (mxt)m×tIs X × "(1 + y)t-1]。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310113359.5A CN104104551B (en) | 2013-04-02 | 2013-04-02 | Cloud resource need assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310113359.5A CN104104551B (en) | 2013-04-02 | 2013-04-02 | Cloud resource need assessment method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104104551A true CN104104551A (en) | 2014-10-15 |
| CN104104551B CN104104551B (en) | 2018-03-23 |
Family
ID=51672372
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310113359.5A Active CN104104551B (en) | 2013-04-02 | 2013-04-02 | Cloud resource need assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104104551B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105511863A (en) * | 2015-11-30 | 2016-04-20 | 中电科华云信息技术有限公司 | Method and system determining service deploy form according to application service attribute identification |
| CN105549907A (en) * | 2015-12-11 | 2016-05-04 | 国云科技股份有限公司 | Method for computing needed virtual machine disk IOPS according to business variables |
| CN107957945A (en) * | 2017-11-29 | 2018-04-24 | 平安科技（深圳）有限公司 | Monetary fund system automatic performance test method, device, equipment and storage medium |
| CN108076029A (en) * | 2016-11-14 | 2018-05-25 | 平安科技（深圳）有限公司 | The building method and device of Workforce Management system |
| CN109040156A (en) * | 2017-06-08 | 2018-12-18 | 中国移动通信集团浙江有限公司 | A kind of soft load resource processing method and processing device based on container cloud |
| CN109992408A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | A kind of resource allocation methods, device, electronic equipment and storage medium |
| CN109995677A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | Resource allocation methods, device and storage medium |
| CN115022320A (en) * | 2022-05-31 | 2022-09-06 | 中国银行股份有限公司 | Method, device, equipment and medium for determining cloud resource server |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1529436A (en) * | 2003-09-28 | 2004-09-15 | 中兴通讯股份有限公司 | Transmission channel treating resource managment method |
| CN101504620A (en) * | 2009-03-03 | 2009-08-12 | 华为技术有限公司 | Load balancing method, apparatus and system of virtual cluster system |
| CN101894050A (en) * | 2010-07-28 | 2010-11-24 | 山东中创软件工程股份有限公司 | Method, device and system for flexibly scheduling JEE application resources of cloud resource pool |
| CN101986274A (en) * | 2010-11-11 | 2011-03-16 | 东软集团股份有限公司 | Resource allocation system and resource allocation method in private cloud environment |
| CN102004671A (en) * | 2010-11-15 | 2011-04-06 | 北京航空航天大学 | Resource management method of data center based on statistic model in cloud computing environment |
| CN102231685A (en) * | 2011-06-17 | 2011-11-02 | 中兴通讯股份有限公司 | Test method, server and system |
| CN102469023A (en) * | 2010-11-19 | 2012-05-23 | 中国移动通信集团公司 | Scheduling method, unit and system based on cloud computing |
| CN102546700A (en) * | 2010-12-23 | 2012-07-04 | 中国移动通信集团公司 | Resource scheduling and resource migration methods and equipment |
| US8219358B2 (en) * | 2008-05-09 | 2012-07-10 | Credit Suisse Securities (Usa) Llc | Platform matching systems and methods |
-
2013
- 2013-04-02 CN CN201310113359.5A patent/CN104104551B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1529436A (en) * | 2003-09-28 | 2004-09-15 | 中兴通讯股份有限公司 | Transmission channel treating resource managment method |
| US8219358B2 (en) * | 2008-05-09 | 2012-07-10 | Credit Suisse Securities (Usa) Llc | Platform matching systems and methods |
| CN101504620A (en) * | 2009-03-03 | 2009-08-12 | 华为技术有限公司 | Load balancing method, apparatus and system of virtual cluster system |
| CN101894050A (en) * | 2010-07-28 | 2010-11-24 | 山东中创软件工程股份有限公司 | Method, device and system for flexibly scheduling JEE application resources of cloud resource pool |
| CN101986274A (en) * | 2010-11-11 | 2011-03-16 | 东软集团股份有限公司 | Resource allocation system and resource allocation method in private cloud environment |
| CN102004671A (en) * | 2010-11-15 | 2011-04-06 | 北京航空航天大学 | Resource management method of data center based on statistic model in cloud computing environment |
| CN102469023A (en) * | 2010-11-19 | 2012-05-23 | 中国移动通信集团公司 | Scheduling method, unit and system based on cloud computing |
| CN102546700A (en) * | 2010-12-23 | 2012-07-04 | 中国移动通信集团公司 | Resource scheduling and resource migration methods and equipment |
| CN102231685A (en) * | 2011-06-17 | 2011-11-02 | 中兴通讯股份有限公司 | Test method, server and system |
Non-Patent Citations (1)
| Title |
|---|
| 孔俊: "企业私有云计算平台资源分配研究与设计", 《万方学位论文数据库》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105511863A (en) * | 2015-11-30 | 2016-04-20 | 中电科华云信息技术有限公司 | Method and system determining service deploy form according to application service attribute identification |
| CN105549907A (en) * | 2015-12-11 | 2016-05-04 | 国云科技股份有限公司 | Method for computing needed virtual machine disk IOPS according to business variables |
| CN108076029B (en) * | 2016-11-14 | 2021-05-04 | 平安科技（深圳）有限公司 | Method and device for building scheduling management system |
| CN108076029A (en) * | 2016-11-14 | 2018-05-25 | 平安科技（深圳）有限公司 | The building method and device of Workforce Management system |
| CN109040156B (en) * | 2017-06-08 | 2021-06-22 | 中国移动通信集团浙江有限公司 | Soft load resource processing method and device based on container cloud |
| CN109040156A (en) * | 2017-06-08 | 2018-12-18 | 中国移动通信集团浙江有限公司 | A kind of soft load resource processing method and processing device based on container cloud |
| CN107957945B (en) * | 2017-11-29 | 2019-06-25 | 平安科技（深圳）有限公司 | Monetary fund system automatic performance test method, device, equipment and storage medium |
| CN107957945A (en) * | 2017-11-29 | 2018-04-24 | 平安科技（深圳）有限公司 | Monetary fund system automatic performance test method, device, equipment and storage medium |
| CN109992408A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | A kind of resource allocation methods, device, electronic equipment and storage medium |
| CN109995677A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | Resource allocation methods, device and storage medium |
| CN109995677B (en) * | 2018-01-02 | 2022-11-29 | 中国移动通信有限公司研究院 | Resource allocation method, device and storage medium |
| CN115022320A (en) * | 2022-05-31 | 2022-09-06 | 中国银行股份有限公司 | Method, device, equipment and medium for determining cloud resource server |
| CN115022320B (en) * | 2022-05-31 | 2024-03-01 | 中国银行股份有限公司 | Cloud resource server determination method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104104551B (en) | 2018-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104104551B (en) | Cloud resource need assessment method and device | |
| CN108965485B (en) | Container resource management method and device and cloud platform | |
| WO2016119412A1 (en) | Resource scaling method on cloud platform and cloud platform | |
| CN102307241B (en) | Cloud calculation resource disposition method based on dynamic prediction | |
| US20180027061A1 (en) | Method and apparatus for elastically scaling virtual machine cluster | |
| CN108415772B (en) | Container-based resource adjustment method, device and medium | |
| TW201424305A (en) | CDN load balancing in the cloud | |
| CN105897484A (en) | Traffic management device, server and method | |
| CN106293868A (en) | In a kind of cloud computing environment, virtual machine expands capacity reduction method and scalable appearance system | |
| CN106125888B (en) | The efficient power-economizing method of the utilization of resources in cloud data center based on virtual machine (vm) migration | |
| Chen et al. | Latency minimization for mobile edge computing networks | |
| WO2014029262A1 (en) | Network and user behavior based time-shifted mobile data transmission | |
| CN109413158A (en) | Data transmission method for uplink, data processing method, car-mounted terminal and server | |
| Ramadhan et al. | Experimental model for load balancing in cloud computing using throttled algorithm | |
| WO2013082742A1 (en) | Resource scheduling method, device and system | |
| CN102075367B (en) | Method and system for controlling downloading of patch packet, client and server | |
| CN113467939A (en) | Capacity management method, device, platform and storage medium | |
| CN114553723A (en) | Operation method, system, medium and equipment of artificial intelligence training platform | |
| CN109117244B (en) | Method for implementing virtual machine resource application queuing mechanism | |
| CN109783221B (en) | Virtual machine resource allocation method and device and resource server | |
| CN113055199B (en) | Gateway access method and device and gateway equipment | |
| CN107203256B (en) | Energy-saving distribution method and device under network function virtualization scene | |
| CN104866331B (en) | The method and apparatus of application is installed, called on mobile terminals | |
| CN105426228A (en) | OpenStack virtual machine placement method facing streaming media live broadcasting and video transcoding | |
| CN106874108B (en) | Technology for minimizing number of micro clouds in mobile cloud computing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |