Resource allocation tuning method in cloud desktop environment and cloud desktop system

Abstract

The invention discloses a resource allocation tuning method in a cloud desktop environment and a cloud desktop system, and the method comprises the steps: a server selects a target scene standardization test coverage path matched with a current scene from standardization test coverage paths of a plurality of scenes, and distributes the target scene standardization test coverage path to each cloud desktop client; each cloud desktop client simulates and executes operation steps in a target scene standardization test coverage path, synchronously records a resource consumption condition, obtains a test result and feeds back the test result to the server; the server calculates the performance score of each cloud desktop client based on the obtained test result; and on the basis of the performance scores of all the cloud desktop clients and the resource consumption condition of the server, determining and executing a resource dynamic tuning scheme, including opening / closing part of the cloud desktop clients, or maintaining the use state of the existing cloud desktop clients. According to the invention, by simulating the actual use scene of the user, the dynamic adjustment and optimization of the cloud desktop resources are realized, and the user experience and the resource utilization rate are effectively improved.

Description

Technical Field

[0001] The present invention belongs to the field of cloud computing, and in particular relates to a resource allocation and tuning method in a cloud desktop environment and a cloud desktop system. Background Art

[0002] With the development of cloud computing technology, cloud desktop, as a new desktop service model, provides users with a more flexible and efficient computing environment. However, how to ensure the resource allocation and user experience of cloud desktop under multi-user concurrent use has become an urgent problem to be solved.

[0003] Existing cloud desktop services often ignore the diversity and complexity of users' actual usage scenarios, resulting in unreasonable resource allocation and uneven user experience. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides a resource allocation optimization method and a cloud desktop system in a cloud desktop environment. The technical problem to be solved by the present invention is achieved through the following technical solutions:

[0005] In a first aspect, an embodiment of the present invention provides a method for optimizing resource allocation in a cloud desktop environment, the method comprising:

[0006] The server selects a target scenario standardized test coverage path that matches the current scenario from among the standardized test coverage paths of multiple scenarios generated in advance, and distributes it to each cloud desktop client; wherein the standardized test coverage path of any scenario includes the operation steps and resource requirement indicators when the sample cloud desktop client used for testing performs a typical application task of the scenario;

[0007] Each cloud desktop client uses the received standardized test coverage path of the target scenario as a test task, simulates the execution of the operation steps therein, and simultaneously records the actual resource consumption, obtains the test results and feeds them back to the server;

[0008] The server calculates the performance score of each cloud desktop client in the current scenario based on the obtained test results;

[0009] The server determines and executes a dynamic resource optimization plan based on the performance scores of all cloud desktop clients and the resource consumption of the server, including: turning on / off some cloud desktop clients, or maintaining the use status of existing cloud desktop clients.

[0010] In one embodiment of the present invention, the standardized test coverage path of any scenario is formed by processing the recorded data after recording the operation sequence and resource consumption of the sample cloud desktop client when executing the typical application task of the scenario using a recording module embedded in the sample cloud desktop client; the operation sequence includes operation steps; the resource consumption includes CPU usage, memory usage and network usage.

[0011] In one embodiment of the present invention, the server calculates the performance score of each cloud desktop client in the current scenario based on the obtained test results, including:

[0012] For any cloud desktop client, the server performs weighted summation of each item in the test result based on the test result of the cloud desktop client and the weight of each item in the test result to obtain a performance score of the cloud desktop client in the current scenario; wherein each item in the test result includes CPU usage, memory usage and network usage.

[0013] In one embodiment of the present invention, the server determines and executes a dynamic resource optimization scheme based on the performance scores of all cloud desktop clients and the resource consumption of the server, including:

[0014] The server obtains the CPU usage rate, memory usage rate and network usage rate of the server based on its own resource consumption, and obtains the performance index of the server by weighted summation using the weights of each item;

[0015] The server determines and executes a dynamic resource optimization solution according to a magnitude relationship between the performance index and a performance index threshold.

[0016] In one embodiment of the present invention, the server determines and executes a resource dynamic tuning solution according to a magnitude relationship between the performance index and the performance index threshold, including:

[0017] If the performance index is less than the performance index threshold, the performance index is detected again after each cloud desktop client is opened until the performance index reaches the performance index threshold, and the opening of new cloud desktop clients is stopped;

[0018] If the performance index is greater than the performance index threshold, determine the closing order of the cloud desktop clients according to the performance scores of all cloud desktop clients, and detect the performance index again after each cloud desktop client is closed until the performance index reaches the performance index threshold, and then stop closing new cloud desktop clients;

[0019] If the performance index is equal to the performance index threshold, the use status of the existing cloud desktop client is maintained.

[0020] In one embodiment of the present invention, determining the shutdown order of the cloud desktop clients according to the performance scores of all the cloud desktop clients includes:

[0021] The closing order of the cloud desktop clients is obtained according to the performance scores of all cloud desktop clients from low to high.

[0022] In one embodiment of the present invention, the performance index threshold is 0.8.

[0023] In a second aspect, an embodiment of the present invention provides a cloud desktop system, the system comprising:

[0024] A server and multiple cloud desktop clients, the cloud desktop system adopts the resource allocation and optimization method in the cloud desktop environment of the first aspect to achieve resource allocation and optimization in different scenarios.

[0025] Beneficial effects of the present invention:

[0026] In the solution provided by the embodiment of the present invention, by simulating the actual user usage scenario, dynamic adjustment and optimization of cloud desktop resources are achieved, effectively improving user experience and resource utilization. At the same time, through standardized usage verification scenarios, the performance of cloud desktops can be more accurately evaluated and monitored, providing powerful decision support for administrators. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of a process for optimizing resource allocation in a cloud desktop environment provided by an embodiment of the present invention;

[0028] Figure 2 A schematic diagram of the working principle of the resource allocation optimization method in a cloud desktop environment provided by an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of the structure of a cloud desktop system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The present invention is further described in detail below with reference to specific embodiments, but the embodiments of the present invention are not limited thereto.

[0031] In a first aspect, an embodiment of the present invention provides a resource allocation optimization method in a cloud desktop environment, such as Figure 1 As shown, the method may include the following steps:

[0032] S1, the server selects a target scenario standardized test coverage path that matches the current scenario from among the standardized test coverage paths of multiple scenarios generated in advance, and distributes it to each cloud desktop client;

[0033] The standardized test coverage path of any scenario includes the operation steps and resource requirement indicators when the sample cloud desktop client used for testing performs typical application tasks of the scenario;

[0034] In the embodiment of the present invention, for different scenarios such as finance, medical treatment, and teaching, corresponding tests can be performed using sample cloud desktop clients respectively, so as to determine the standardized test coverage path of the corresponding scenario.

[0035] Specifically, the standardized test coverage path of any scenario is formed by processing the recorded data after recording the operation sequence and resource consumption of the sample cloud desktop client when the sample cloud desktop client executes the typical application task of the scenario using a recording module embedded in the sample cloud desktop client;

[0036] The recording module can be completed based on existing technologies; the typical application tasks can be using Excel, watching videos, etc.

[0037] The operation sequence includes operation steps; the resource consumption includes CPU usage, memory usage and network usage. When recording the operation sequence of the sample cloud desktop client executing a typical application task in the scenario, the recording module will synchronously record the expected response time of each step to ensure that the operation sequence is carried out normally.

[0038] Those skilled in the art will appreciate that the CPU usage rate indicates the CPU resource usage, and has a value range of 0 to 1, and may also be expressed as a percentage.

[0039] Memory usage indicates the usage of memory resources. The value range is 0 to 1 and can also be expressed as a percentage.

[0040] The network usage rate indicates the usage of network bandwidth, which can be the ratio of the actual used bandwidth to the total bandwidth in Mbps, and the value range is 0 to 1.

[0041] S2, each cloud desktop client uses the received standardized test coverage path of the target scenario as a test task, simulates the execution of the operation steps therein, and simultaneously records the actual resource consumption, obtains the test results and feeds them back to the server;

[0042] During the execution of the method of the embodiment of the present invention, each cloud desktop client will monitor its internal resource usage in real time and send the monitoring data to the server. Therefore, after receiving the standardized test coverage path of the target scenario, each cloud desktop client will execute the test task and record its actual resource consumption, including CPU usage, memory usage and network usage, and feed these back to the server as test results.

[0043] It can be seen that in the embodiment of the present invention, the target scenario standardized test coverage path is used as a standardized scenario test case to collect the resource consumption of all cloud desktop clients in the process of executing the target scenario standardized test coverage path, so as to facilitate the subsequent analysis of whether the resource allocation is reasonable and make corresponding adjustments.

[0044] At the same time, during the entire process, the server will also collect its own resource consumption in real time.

[0045] S3, the server calculates the performance score of each cloud desktop client in the current scenario based on the obtained test results;

[0046] In an optional implementation manner, S3 may include the following steps:

[0047] For any cloud desktop client, the server performs weighted summation of each item in the test result based on the test result of the cloud desktop client and the weight of each item in the test result to obtain a performance score of the cloud desktop client in the current scenario;

[0048] The test results include CPU usage, memory usage, and network usage.

[0049] Specifically, for the three items of CPU utilization, memory utilization and network utilization, corresponding weights may be pre-stored in the server. For ease of understanding, the embodiment of the present invention uses α, β and γ to represent the weights corresponding to the three items respectively, and the values ​​are all between 0 and 1, and the sum is 1. The specific numerical value of each weight can be set according to the importance of each item in the performance evaluation in actual conditions. For example, if the CPU performance has the greatest impact, α>β>γ can be set; if the network bandwidth has the greatest impact, γ>α>β can be set, and so on.

[0050] Through weighted summation, each cloud desktop client has a performance score between 0 and 1 in the current scenario.

[0051] S4, the server determines and executes a dynamic resource optimization plan based on the performance scores of all cloud desktop clients and the resource consumption of the server, including: turning on / off some cloud desktop clients, or maintaining the use status of existing cloud desktop clients.

[0052] In an optional implementation manner, S4 may include the following steps:

[0053] S41, the server obtains the CPU usage, memory usage and network usage of the server based on its own resource consumption, and obtains the performance index of the server by weighted summation using the weights of each item;

[0054] In this step, the process of obtaining the CPU usage, memory usage and network usage of the server based on its own resource consumption is understood in the prior art and will not be described in detail here.

[0055] The weights corresponding to CPU utilization, memory utilization, and network utilization are exactly α, β, and γ mentioned above.

[0056] The calculation formula of the performance index can be expressed as:

[0057] SPI=

[0058] α*server CPU usage + β*server memory usage + γ*server network usage;

[0059] Here, SPI represents the performance index of the server.

[0060] S42: The server determines and executes a dynamic resource optimization solution according to a relationship between the performance index and a performance index threshold.

[0061] By calculating the SPI value through S41, a value between 0 and 1 can be obtained to reflect the current server performance. The closer the SPI is to 1, the closer the server performance is to the limit; the closer the SPI is to 0, the greater the server performance potential is.

[0062] In the embodiment of the present invention, a performance index threshold between 0 and 1 may be pre-set according to the situation, such as 0.8, and a dynamic resource optimization scheme may be determined and executed according to the relationship between the performance index and the performance index threshold.

[0063] In an optional implementation manner, the server determines and executes a resource dynamic tuning solution according to a magnitude relationship between the performance index and a performance index threshold, including:

[0064] 1) If the performance index is less than the performance index threshold, the performance index is detected again after each cloud desktop client is opened until the performance index reaches the performance index threshold, and the opening of new cloud desktop clients is stopped;

[0065] If the performance index is less than the performance index threshold, it means that the server performance still has great potential, and a new cloud desktop client can be opened to fully utilize the server resources.

[0066] In an embodiment of the present invention, different types of cloud desktop clients can be selected for opening, such as a cloud desktop client with a CPU-4G memory or a cloud desktop client with a CPU-8G memory, etc. Each time a new cloud desktop client is opened, the performance index of the server is calculated again. If the performance index threshold is not reached, the new cloud desktop client continues to be opened. If the performance index threshold is reached, the new cloud desktop client is stopped from being opened. The process is repeated until the performance index reaches the performance index threshold.

[0067] 2) If the performance index is greater than the performance index threshold, determine the closing order of the cloud desktop clients according to the performance scores of all cloud desktop clients, and detect the performance index again after each cloud desktop client is closed until the performance index reaches the performance index threshold, and then stop closing new cloud desktop clients;

[0068] If the performance index is greater than the performance index threshold, it means that the server performance is close to the limit. In order to achieve better resource utilization, some cloud desktop clients need to be closed. Some cloud desktop clients with poor performance can be selected according to the performance scores of all cloud desktop clients to determine the closing order of a cloud desktop client. According to the closing order of the cloud desktop clients, the performance index of the server is calculated again each time a cloud desktop client is closed. If the performance index threshold is not reached, the next cloud desktop client is closed. If the performance index threshold is reached, the cloud desktop client is stopped from being closed. The process is repeated until the performance index reaches the performance index threshold.

[0069] Wherein, determining the closing order of the cloud desktop clients according to the performance scores of all the cloud desktop clients includes:

[0070] The closing order of the cloud desktop clients is obtained according to the performance scores of all cloud desktop clients from low to high.

[0071] That is, the order of the cloud desktop clients sorted from low to high in terms of performance scores is the order in which the cloud desktop clients are closed.

[0072] 3) If the performance index is equal to the performance index threshold, the use status of the existing cloud desktop client is maintained.

[0073] It is understandable that if the performance index of the server is equal to the performance index threshold, it means that the current resource allocation is relatively reasonable, and the use status of the existing cloud desktop client can be maintained.

[0074] In the embodiment of the present invention, the server may issue an instruction to the administrator to prompt the administrator to manually execute the dynamic resource optimization solution, or the server may automatically execute the dynamic resource optimization solution by calling a corresponding program, which is reasonable.

[0075] The working principle of the method of the embodiment of the present invention is shown in FIG. Figure 2 Understood, no further details will be given here.

[0076] In the resource allocation and tuning method under the cloud desktop environment provided by the embodiment of the present invention, first, the server selects the target scenario standardized test coverage path that matches the current scenario from the standardized test coverage paths of multiple scenarios generated in advance, and distributes it to each cloud desktop client; secondly, each cloud desktop client uses the received target scenario standardized test coverage path as a test task, simulates the execution of the operation steps therein, and synchronously records the actual resource consumption, obtains the test results and feeds them back to the server; then the server calculates the performance score of each cloud desktop client in the current scenario based on the obtained test results; finally, the server determines and executes the resource dynamic tuning plan based on the performance scores of all cloud desktop clients and the resource consumption of the server, including: turning on / off some cloud desktop clients, or maintaining the use status of existing cloud desktop clients. The embodiment of the present invention realizes the dynamic adjustment and optimization of cloud desktop resources by simulating the actual use scenarios of users, effectively improving the user experience and resource utilization. At the same time, through standardized use verification scenarios, the performance of cloud desktops can be more accurately evaluated and monitored, providing strong decision support for administrators.

[0077] In a second aspect, corresponding to the above method embodiment, the embodiment of the present invention further provides a cloud desktop system, such as Figure 3 As shown, the system includes:

[0078] A server and multiple cloud desktop clients; the cloud desktop system adopts the resource allocation and optimization method in the cloud desktop environment described in the first aspect to achieve resource allocation and optimization in different scenarios.

[0079] For the specific processing process of the system resource allocation and tuning, please refer to the relevant content of the first aspect and will not be repeated here.

[0080] The cloud desktop system provided by the embodiment of the present invention realizes dynamic adjustment and optimization of cloud desktop resources of all cloud desktop clients in the system by simulating the resource consumption of users actually using the scenario for different scenarios, effectively improving user experience and resource utilization. At the same time, through standardized usage verification scenarios, the performance of cloud desktops can be more accurately evaluated and monitored, providing powerful decision-making support for administrators.

[0081] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification.

[0082] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0083] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A resource allocation optimization method in a cloud desktop environment, characterized in that: The method comprises: The server selects a target scenario standardized test coverage path that matches the current scenario from among the standardized test coverage paths of multiple scenarios generated in advance, and distributes it to each cloud desktop client; wherein the standardized test coverage path of any scenario includes the operation steps and resource requirement indicators when the sample cloud desktop client used for testing performs a typical application task of the scenario; Each cloud desktop client uses the received standardized test coverage path of the target scenario as a test task, simulates the execution of the operation steps therein, and simultaneously records the actual resource consumption, obtains the test results and feeds them back to the server; The server calculates the performance score of each cloud desktop client in the current scenario based on the obtained test results; The server determines and executes a dynamic resource optimization plan based on the performance scores of all cloud desktop clients and the resource consumption of the server, including: turning on / off some cloud desktop clients, or maintaining the use status of existing cloud desktop clients.

2. The method according to claim 1, characterized in that The standardized test coverage path of any scenario is formed by processing the recorded data after using a recording module embedded in the sample cloud desktop client to record the operation sequence and resource consumption of the sample cloud desktop client when executing typical application tasks of the scenario; the operation sequence includes operation steps; the resource consumption includes CPU usage, memory usage and network usage.

3. The method according to claim 2, characterized in that The server calculates the performance score of each cloud desktop client in the current scenario based on the obtained test results, including: For any cloud desktop client, the server performs weighted summation of each item in the test result based on the test result of the cloud desktop client and the weight of each item in the test result to obtain a performance score of the cloud desktop client in the current scenario; wherein each item in the test result includes CPU usage, memory usage and network usage.

4. The method according to claim 3, characterized in that: The server determines and executes a dynamic resource optimization scheme based on the performance scores of all cloud desktop clients and the resource consumption of the server, including: The server obtains the CPU usage rate, memory usage rate and network usage rate of the server based on its own resource consumption, and obtains the performance index of the server by weighted summation using the weights of each item; The server determines and executes a dynamic resource optimization solution according to a magnitude relationship between the performance index and a performance index threshold.

5. The method according to claim 4, characterized in that The server determines and executes a resource dynamic tuning scheme according to a magnitude relationship between the performance index and a performance index threshold, including: If the performance index is less than the performance index threshold, the performance index is detected again after each cloud desktop client is opened until the performance index reaches the performance index threshold, and the opening of new cloud desktop clients is stopped; If the performance index is greater than the performance index threshold, determine the closing order of the cloud desktop clients according to the performance scores of all cloud desktop clients, and detect the performance index again after each cloud desktop client is closed until the performance index reaches the performance index threshold, and then stop closing new cloud desktop clients; If the performance index is equal to the performance index threshold, the use status of the existing cloud desktop client is maintained.

6. The method according to claim 5, characterized in that The step of determining the closing order of the cloud desktop clients according to the performance scores of all the cloud desktop clients includes: The closing order of the cloud desktop clients is obtained according to the performance scores of all cloud desktop clients from low to high.

7. The method according to claim 5, characterized in that The performance index threshold is 0.

8.

8. A cloud desktop system, characterized in that: The cloud desktop system comprises a server and multiple cloud desktop clients, wherein the cloud desktop system adopts the resource allocation and optimization method in the cloud desktop environment described in any one of claims 1 to 7 to realize resource allocation and optimization in different scenarios.

Images