Cloud host resource processing method and device

Abstract

The application discloses a cloud host resource processing method and device, and relates to the technical field of cloud computing. A specific embodiment of the method comprises the following steps: in response to detecting that a current resource usage value of an entity computing device meets a preset alert condition, determining an excess resource value of the entity computing device according to the current resource usage value; determining a target cloud host with a resource actual usage value greater than a resource commitment value from a plurality of cloud hosts deployed in the entity computing device, determining a resource limit value of the target cloud host according to the excess resource value and the resource actual usage value; and limiting resource usage of the target cloud host by using the resource limit value. The embodiment can limit resource occupation of a cloud host when the current resource usage value of an entity computing device meets an alert condition, thereby ensuring sufficient performance space to achieve resource commitment for each cloud host.

Description

Technical Field

[0001] This invention relates to the field of cloud computing technology, and in particular to a method and apparatus for processing cloud host resources. Background Technology

[0002] As a core computing resource in cloud computing, cloud servers support a large number of critical business operations for the vast majority of cloud users. In practical applications, fine-grained allocation and control of resources such as CPU (Central Processing Unit), memory, and network bandwidth are implemented to ensure that cloud servers can meet the service quality requirements of users. Regarding resources such as network bandwidth, the resource usage of each cloud server deployed on physical computing devices (such as physical servers) will fluctuate within a certain range. Some cloud servers may consume excessive resources, causing the total resource usage to exceed the warning threshold of the physical computing device, resulting in some cloud servers failing to fulfill their resource commitments. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a cloud host resource processing method and apparatus, which can limit the resource occupation of cloud hosts when the current resource usage value of physical computing devices meets the warning conditions, thereby ensuring sufficient performance space to fulfill resource commitments for each cloud host.

[0004] To achieve the above objectives, according to one aspect of the present invention, a cloud host resource processing method is provided.

[0005] The cloud host resource processing method of this invention includes: in response to detecting that the current resource usage value of a physical computing device meets a preset warning condition, determining the excess resource value of the physical computing device based on the current resource usage value; determining a target cloud host whose actual resource usage value is greater than the resource commitment value from multiple cloud hosts deployed on the physical computing device, determining a resource limit value for the target cloud host based on the excess resource value and the actual resource usage value; and restricting the resource usage of the target cloud host using the resource limit value.

[0006] Optionally, the warning condition includes: the current resource usage value of the physical computing device exceeds the warning threshold of the physical computing device; and determining the excess resource value of the physical computing device based on the current resource usage value includes: determining the difference between the current resource usage value and the warning threshold as the excess resource value.

[0007] Optionally, determining the resource limit value of the target cloud host based on the excess resource value and the actual resource usage value includes: dividing the excess resource value according to the allocation weight of the target cloud host to obtain the allocation value of each target cloud host; subtracting the allocation value of any target cloud host from the actual resource usage value of the target cloud host to obtain the alternative limit value; and determining the maximum value between the alternative limit value and the resource commitment value of the target cloud host as the resource limit value of the target cloud host.

[0008] Optionally, the cloud server resource processing method further includes: determining the excess ratio of the target cloud server as the quotient of the difference between the actual resource usage value and the resource commitment value of any target cloud server and the resource commitment value; and determining the excess ratio as the allocation weight of the target cloud server.

[0009] Optionally, the cloud host resource processing method further includes: determining the difference between the actual resource usage value and the resource commitment value of any target cloud host as the allocation weight of the target cloud host.

[0010] Optionally, in response to detecting that the current resource usage value of the physical computing device meets a preset warning condition, determining the excessive resource value of the physical computing device based on the current resource usage value includes: in response to the start of the current adjustment period and the detection that the current resource usage value of the physical computing device meets the warning condition, determining the excessive resource value of the physical computing device.

[0011] Optionally, resource limits can be used to restrict the resource usage of cloud hosts, including: within the current adjustment period, setting the resource limit of any target cloud host as the upper limit of the resource usage of that cloud host.

[0012] Optionally, resources include: network bandwidth, number of connections, or number of packet forwards; physical computing devices include: physical servers or computer clusters.

[0013] To achieve the above objectives, according to another aspect of the present invention, a cloud host resource processing apparatus is provided.

[0014] The cloud host resource processing apparatus of this invention includes: an over-computing unit, configured to determine an over-resource value of the physical computing device based on the current resource usage value in response to detecting that the current resource usage value of the physical computing device meets a preset warning condition; a limiting computing unit, configured to determine a target cloud host whose actual resource usage value is greater than the resource commitment value from multiple cloud hosts deployed on the physical computing device, and determine a resource limit value of the target cloud host based on the over-resource value and the actual resource usage value; and a resource limiting unit, configured to limit the resource usage of the target cloud host using the resource limit value.

[0015] Optionally, the warning condition includes: the current resource usage value of the physical computing device exceeds the warning threshold of the physical computing device; and the exceeding computing unit can also be used to: determine the difference between the current resource usage value and the warning threshold as the exceeding resource value.

[0016] Optionally, the limit calculation unit can also be used to: divide the excess resource value according to the allocation weight of the target cloud host to obtain the allocation value of each target cloud host; subtract the allocation value of the target cloud host from the actual resource usage value of any target cloud host to obtain the alternative limit value; and determine the maximum value between the alternative limit value and the resource commitment value of the target cloud host as the resource limit value of the target cloud host.

[0017] Optionally, the limiting calculation unit can also be used to: determine the excess ratio of the target cloud host as the quotient of the difference between the actual resource usage value and the resource commitment value of any target cloud host and the resource commitment value; and determine the excess ratio as the allocation weight of the target cloud host.

[0018] Optionally, the limiting calculation unit can also be used to: determine the difference between the actual resource usage value and the resource commitment value of any target cloud host as the allocation weight of that target cloud host.

[0019] Optionally, the over-computing unit can also be used to: determine the over-resource value of the physical computing device in response to the start of the current adjustment period and the detection that the current resource usage value of the physical computing device meets the warning condition.

[0020] Optionally, the resource limiting unit can also be used to: determine the resource limit value of any target cloud host as the upper limit of the resource usage value of that cloud host within the current adjustment period.

[0021] To achieve the above objectives, according to another aspect of the present invention, an electronic device is provided.

[0022] An electronic device according to the present invention includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the cloud host resource processing method provided by the present invention.

[0023] To achieve the above objectives, according to another aspect of the present invention, a computer-readable storage medium is provided.

[0024] The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the cloud host resource processing method provided by the present invention.

[0025] To achieve the above objectives, according to another aspect of the present invention, a computer program product is provided.

[0026] One computer program product of the present invention includes a computer program that, when executed by a processor, implements the cloud host resource processing method provided by the present invention.

[0027] According to the technical solution of the present invention, the embodiments described above have the following advantages or beneficial effects: When the current resource usage of a physical computing device meets a preset warning condition, the resource limiting system determines the excess resource value of the physical computing device based on the current resource usage value. It then identifies target cloud hosts from among the multiple cloud hosts deployed on the physical computing device whose actual resource usage value exceeds the promised resource value. Based on the excess resource value and the actual resource usage value, it determines the resource limit value for each target cloud host and finally uses the resource limit value to restrict the resource usage of the target cloud host. Through these steps, the system can limit the resource occupation of cloud hosts when the current resource usage value of the physical computing device meets the warning condition, thereby releasing occupied resources to maintain sufficient resource allocation space to meet the resource commitments made by each cloud host to users.

[0028] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0029] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein: Figure 1 This is a schematic diagram of the main steps of the cloud host resource processing method in an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the specific execution steps of the cloud host resource processing method in this embodiment of the invention; Figure 3 This is a schematic diagram of the system architecture of the first embodiment; Figure 4 This is a schematic diagram of the components of the cloud host resource processing device in an embodiment of the present invention; Figure 5 This is an exemplary system architecture diagram that can be applied thereto according to embodiments of the present invention; Figure 6 This is a schematic diagram of the electronic device structure used to implement the cloud host resource processing method in the embodiments of the present invention. Detailed Implementation

[0030] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0031] It should be noted that, unless otherwise specified, the embodiments of the present invention and the technical features thereof can be combined with each other.

[0032] Figure 1 This is a schematic diagram of the main steps of the cloud host resource processing method in an embodiment of the present invention.

[0033] like Figure 1 As shown, the cloud host resource processing method of this embodiment of the invention can be executed by a resource limiting system. The resource limiting system can be an original component (e.g., a network interface card) in the physical computing device, a new component in the physical computing device used to implement the cloud host resource limiting function, or a device outside the physical computing device that interacts with it. The specific execution steps of the cloud host resource processing method are as follows: Step S101: In response to detecting that the current resource usage value of the physical computing device meets a preset warning condition, the excess resource value of the physical computing device is determined based on the current resource usage value. In this step, the resource limiting system can calculate the excess resource value of the physical computing device when the current resource usage value of the physical computing device meets the warning condition.

[0034] Step S102: Determine the target cloud host whose actual resource usage exceeds the committed resource value from among multiple cloud hosts deployed on physical computing devices, and determine the resource limit value of the target cloud host based on the excess resource value and the actual resource usage value. In this step, the resource limiting system can select the target cloud host that exceeds the committed resource value from the cloud hosts deployed on physical computing devices and calculate the resource limit value for each target cloud host.

[0035] Step S103: Restrict the resource usage of the target cloud host using resource limit values. In this step, the resource limiting system can use resource limit values ​​to restrict the resource usage of the target cloud host, that is, use the resource limit values ​​as the upper limit of the resource usage value of the corresponding target cloud host.

[0036] By following the steps above, the resource usage of cloud hosts can be limited when the current resource usage of physical computing devices meets the warning conditions, thereby releasing the occupied resources to maintain sufficient resource allocation space to meet the resource commitments of each cloud host to users.

[0037] Figure 2 This is a schematic diagram illustrating the specific execution steps of the cloud host resource processing method in an embodiment of the present invention. See [link / reference]. Figure 2 .

[0038] Step S201: Configure the resource commitment values ​​for each cloud host in the resource limitation system. In this embodiment of the invention, the physical computing device can be a physical server or a computer cluster, and the cloud hosts are deployed on the physical computing device, which may include cloud virtual hosts, VPS (Virtual Private Server) servers, and cloud servers. Resources may include any elastically configurable resources used by the cloud host, such as CPU, memory, network bandwidth, number of connections (i.e., concurrent connections), and packet forwarding count (i.e., Packet Per Second, abbreviated as PPS). The following explanation uses network bandwidth as an example.

[0039] In this step, resource commitment values ​​for each cloud host are pre-configured. These commitment values ​​refer to the nominal resource values ​​that the cloud service provider promises to provide to cloud host users. The cloud host's resource usage will always meet these commitment values, regardless of actual needs. In practice, the actual resource usage of a cloud host may be greater than, equal to, or less than the committed resource values. For example, the resource commitment values ​​of each cloud host deployed on the physical computing device (e.g., network interface card) can generally be configured based on the device's resource limits (e.g., bandwidth limits). For instance, the sum of the committed resource values ​​of all cloud hosts can be configured to be slightly less than or equal to the physical computing device's resource limits; this slight difference can be quantified according to preset rules. Specifically, considering the extremely low probability that all cloud hosts will simultaneously meet their committed resource values ​​in a real-world scenario, the sum of the committed resource values ​​of all cloud hosts can also be configured to be slightly greater than the physical computing device's resource limits; this slight difference can be quantified according to preset rules. In specific applications, resource limits for each cloud host can also be pre-configured. Technical means can be used to prevent the actual resource usage of each cloud host from exceeding these limits, ensuring that the resource limits are greater than the committed resource values.

[0040] Step S202: The resource limiting system detects the current resource usage value of the physical computing device. Preferably, the resource limiting system can periodically perform detection and resource limiting adjustments based on multiple equal time interval adjustment cycles. In this step, the resource limiting system can perform detection of the current resource usage value of the physical computing device at the beginning of an adjustment cycle. If the resource limiting system detects that the current resource usage value of the physical computing device meets the warning condition, it proceeds to the next step; if it detects that the current resource usage value of the physical computing device does not meet the warning condition, it terminates the process of this adjustment cycle. Preferably, the warning condition may include: the current resource usage value of the physical computing device exceeds the warning threshold of the physical computing device.

[0041] Step S203: If the resource limiting system detects that the current resource usage of the physical computing device meets the warning condition, it can determine that the physical computing device has exceeded the resource value. In practical applications, the resource limiting system can determine the difference between the current resource usage value and the warning threshold as the resource exceeding value.

[0042] Step S204: The resource limiting system determines the target cloud host. In this step, the physical computing device can determine the target cloud host from multiple cloud hosts deployed on the physical computing device. That is, it traverses each cloud host and determines whether the actual resource usage of the cloud host is greater than its resource commitment value. If the actual resource usage is greater than its resource commitment value, it is determined as the target cloud host. It can be understood that the actual resource usage value refers to the resource usage value at the current moment. The current resource usage value of the target cloud host exceeds the resource commitment value, which is a case of excessive resource consumption. Subsequently, resource usage limits can be implemented on it to ensure sufficient resource allocation space.

[0043] Step S205: The resource limiting system determines the resource limit value for each target cloud host. In this step, the resource limiting system determines the resource limit value for each target cloud host based on the excess resource value and the actual resource usage value. As a preferred solution, the resource limiting system can first divide the above excess resource values ​​according to the allocation weight of the target cloud hosts to obtain the allocation value for each target cloud host. It can be understood that the allocation value of any target cloud host is the resource value that needs to be reduced for that target cloud host in the future, and the sum of the allocation values ​​of all target cloud hosts is equal to the above excess resource value. Therefore, if each target cloud host reduces its corresponding allocation value, the resource usage value of the physical computing device will drop to the warning threshold, thereby causing the physical computing device to fail to meet the warning condition. In specific applications, the ratio of the allocation weight of any target cloud host to the sum of the allocation weights of all target cloud hosts can be determined as the allocation ratio, and multiplying the allocation ratio by the excess resource value yields the allocation value of the corresponding target cloud host.

[0044] After obtaining the allocation values ​​for each target cloud host, the resource limiting system subtracts the allocated value from the actual resource usage of any target cloud host to obtain a candidate limit value. Finally, the maximum value between the candidate limit value and the resource commitment value of the target cloud host is determined as the resource limit value for that target cloud host. This resource limit value serves as the upper limit for the resource usage of the target cloud host within the current adjustment period. These steps simultaneously ensure a reduction in resource consumption of the target cloud host and maintain the resource performance represented by the resource commitment value.

[0045] In one embodiment, the allocation weight of each target cloud host can be determined by: determining the excess ratio of the target cloud host as the quotient of the difference between the actual resource usage and the committed resource value of any target cloud host and the committed resource value; and determining the excess ratio as the allocation weight of the target cloud host. This method is optimal, as it can allocate a larger resource reduction value to cloud hosts with higher excess ratios (indicating higher resource utilization), thereby more easily achieving the effect of releasing public resources. In another embodiment, the allocation weight of each target cloud host can be determined by: determining the difference between the actual resource usage and the committed resource value of any target cloud host as the allocation weight of the target cloud host. Furthermore, other applicable methods can be used to determine the allocation weight, such as determining the committed resource value of any target cloud host as the allocation weight of the target cloud host, or setting equal allocation weights for each target cloud host (i.e., the allocation value for each target cloud host is the average value of the excess resource value).

[0046] It should be noted that since the resource limit value of the target cloud host is selected as the maximum value between the alternative limit value and the resource commitment value, if the calculated alternative limit value of one or more target cloud hosts is less than the resource commitment value, the resource commitment value is actually used as the upper limit of resource usage. In this case, the resource usage value of the physical computing device (i.e., the sum of the resource usage values ​​of each cloud host) may still be greater than the warning threshold. Therefore, the resource limit value calculation and resource limit steps can be limited to be performed only once within an adjustment cycle.

[0047] Step S206: The resource limiting system uses resource limit values ​​to restrict the resource usage of the target cloud host. In this step, the resource limiting system can limit: within the current adjustment period, the resource limit value of any target cloud host is determined as the upper limit of the cloud host's resource usage. After the current adjustment period ends, the resource limit values ​​and corresponding resource limiting operations of that adjustment period are all ignored, and the resource limit judgment for the new adjustment period is executed.

[0048] In the technical solution of this invention embodiment, when the current resource usage value of a physical computing device is detected to meet a preset warning condition, the resource limiting system determines the excess resource value of the physical computing device based on the current resource usage value. It then identifies target cloud hosts from among multiple cloud hosts deployed on the physical computing device whose actual resource usage value exceeds the promised resource value. Based on the excess resource value and the actual resource usage value, it determines the resource limit value for each target cloud host and finally uses the resource limit value to restrict the resource usage of the cloud host. Through these steps, the resource occupation of target cloud hosts can be limited when the current resource usage value of the physical computing device meets the warning condition, thereby releasing occupied resources to maintain sufficient resource allocation space to meet the resource promises made by each cloud host to the user.

[0049] The first embodiment of the present invention is described below, see [link to previous description]. Figure 3 In the first embodiment, the physical computing device is a physical machine, the resource is network bandwidth, and the resource limiting system is the network interface card (NIC) in the physical machine.

[0050] As a core computing resource in cloud computing, cloud servers support a large number of critical business operations for the vast majority of cloud users. Thanks to virtualization technology, the two important computing power indicators, CPU and memory, can be clearly defined through instance specifications after being quantified. Users can choose different configurations as needed and adjust them according to business requirements. However, in addition to computing resources, since multiple cloud servers on the same physical machine share the hardware of the physical machine, the performance of important network hardware such as network cards also needs to be allocated to cloud servers according to certain rules and is part of the quality of cloud server product services, so that users have certain expectations for the various performance levels that can be achieved when using cloud servers.

[0051] The concept of QoS (Quality of Service) is not unique to the cloud server field, but rather originates from a general concept in network communication and service quality management. Its original definition and concepts can be traced back to earlier communication protocols and standards. However, the specific concept and application of QoS in cloud servers has gradually formed as cloud computing technology and services have continuously developed and improved. As an emerging technology service model, cloud computing's QoS requirements and management methods differ from traditional IT services; therefore, QoS needs to be defined and implemented specifically for the characteristics of cloud servers.

[0052] Cloud server QoS technology is a technique that uses fine-grained control over network traffic and resource allocation to ensure that cloud servers can meet users' required quality of service. It can allocate different priorities and resources to different business flows based on varying business needs, thereby optimizing network traffic and effectively utilizing resources. Common metrics include network bandwidth, number of connections, and packet forwarding per second (PPS). These metrics are limited by the server's hardware capabilities and related software implementation, thus having a certain upper limit.

[0053] For the same QoS metric, cloud server QoS can be set with two values: a limit value (the resource's absolute upper limit, which will never be exceeded) and a commitment value (the promised nominal value, ensuring that this commitment value will be achieved under any circumstances). Most cloud vendors support configuring QoS metrics with limit values, allowing different values ​​to be configured according to the server's specifications; larger specifications result in higher performance limits. Configuring only the limit value presents the following problems.

[0054] First, if the upper limit of the physical machine's capacity is used as the sum of the limit values ​​of all cloud hosts, it is equivalent to the limit value equaling the promised value, which can also achieve the performance promise. However, the performance of different hosts fluctuates differently at different times, and it is rare for all hosts to reach their limit values. This configuration method will cause resource waste in most cases.

[0055] Secondly, in order to avoid wasting resources, if cloud servers are configured with values ​​higher than the limits mentioned above, without any promised values, the performance that each cloud server can achieve is uncertain when performance contention occurs due to insufficient resources. For enterprise-level application customers, the inability to guarantee the lower limit of performance can lead to business instability.

[0056] This embodiment proposes a mechanism for implementing the QoS performance commitment value of cloud hosts. Based on the implementation of performance limit control, the proportion of each cloud host on the same physical machine that achieves the committed performance is statistically analyzed in near real-time. When the overall performance of the physical machine reaches a certain warning threshold, a temporary upper limit value is set for cloud hosts that exceed the committed value, using the excess proportion as a weight. By restricting hosts that exceed the committed value, public resources are released, the overall performance of cloud hosts is balanced, and each cloud host is guaranteed to at least achieve the performance commitment value as much as possible.

[0057] In practical applications, different specifications of cloud servers can be configured with different performance metric commitment values ​​and limits. Various combinations of specifications and quantities exist on a single physical machine, and various scheduling strategies can be used to balance the sold resources on each physical machine as much as possible. Depending on the balancing strategy, the sum of the commitment values ​​may be slightly higher than or equal to the physical machine's performance limit; this slight increase can be quantified according to preset rules.

[0058] First, the meanings of the relevant variables in the calculation process are defined as follows: (taking network bandwidth as an example)

[0059] B max-i The bandwidth limit (i.e. resource limit) configured for the i-th cloud host is a specification attribute that is configured and applied to the cloud host according to the specification.

[0060] B min-i : The bandwidth commitment value (i.e., resource commitment value) configured for the i-th cloud host; is a specification attribute that is configured according to the specifications and takes effect on the cloud host;

[0061] B actual-i The actual bandwidth value (i.e., actual resource usage and resource utilization) of the i-th cloud host is a collected value that fluctuates over time, ranging from 0 to B. max-i between;

[0062] B over-i The percentage by which the actual bandwidth of the i-th cloud server exceeds the promised bandwidth;

[0063] B limit-i : Temporary bandwidth limit (i.e., resource limit) for the i-th cloud host, which is temporarily configured and takes effect on the cloud host when the rate limit is triggered;

[0064] B nic This represents the maximum bandwidth of the network card, which depends on the network card model, such as 10Gb, 25Gb, 100Gb, etc.

[0065] Assume the alert rate for triggering temporary QoS restrictions is X%, and the corresponding alert threshold is B. nic If *X% is applied and the adjustment period is M seconds, then the resource limitation logic is as follows:

[0066] Every M seconds, query the current physical network card bandwidth utilization rate Y%, and the actual resource usage value is B. nic *Y%. If Y% < X%, no adjustment will be made. If Y% ≥ X%, a temporary adjustment will be triggered.

[0067] After triggering, the actual bandwidth B of all cloud hosts on the physical machine node is calculated. actual Find B actual >B min For cloud servers (i.e., cloud servers exceeding the promised value), calculate the excess percentage for each, B. over-i =(B actual-i -B min-i ) / B min-i (The host that exceeds the promised value, B) over-i It should be greater than 0).

[0068] To ensure that the overall bandwidth does not exceed the threshold X%, it is necessary to adjust B. over-i Set a temporary limit value B for cloud servers with a value greater than 0. limit-i Bandwidth needs to be released: B nic *(Y%-X%), this value represents the resource excess.

[0069] With B over-i To assign weights, B over-i The temporary bandwidth limit B that each host needs to adjust to if it is greater than 0. limit-i After calculating each one, a temporary limit value is configured for the corresponding cloud host, among which... These are alternative limit values.

[0070]

[0071]

[0072] When the next adjustment cycle arrives, the temporary limits and resource restrictions from the previous adjustment cycle are removed, and a similar check is performed again for the new adjustment cycle. An example is given below:

[0073] The maximum network bandwidth (bps) that a physical machine can use for network traffic is 100Gbps (B). nic =100), the alert ratio is set to 95%, meaning that when the network card bandwidth reaches 95Gbps (the alert threshold), a temporary QoS limit needs to be triggered, and the adjustment period is set to 10 seconds. There are 10 cloud hosts on the physical machine, all with the same specifications, all 8C16G (8 cores and 16G memory), with a bandwidth commitment of 10G and a maximum of 20G.

[0074] Assuming the first period's statistics show a current bandwidth utilization rate of 98%, exceeding the warning threshold of 95%, adjustments are triggered. Statistics show that 3 out of 10 cloud servers have actual bandwidth exceeding 10G, specifically 13G, 12G, and 11G, i.e., B... over-1 =30%, B over-2 =20%, B over-3 =10%, then the temporary limit values ​​for the 3 cloud servers are as follows: , , Set temporary limit values ​​for the three cloud servers according to the above calculations. In the next adjustment cycle, repeat the above judgment and calculation steps to update, cancel, or add temporary limit values.

[0075] This embodiment provides a dynamic adjustment mechanism that periodically calculates the percentage of cloud host QoS performance values ​​that exceed the promised performance values. When the overall resource utilization reaches a warning value, the cloud hosts that exceed the promised values ​​are the adjustment targets, and a temporary limit value is calculated with the excess percentage as the weight. By limiting the performance of cloud hosts that have met the promised performance, public resources are released to ensure that the remaining hosts have sufficient performance space to meet the promised values.

[0076] It should be noted that the technical solutions of this invention, including the collection, updating, analysis, processing, use, transmission, and storage of user personal information, all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0077] For the foregoing method embodiments, they are described as a series of actions for ease of description. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, and some steps may actually be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential for implementing the present invention.

[0078] To facilitate better implementation of the above-described solutions of the embodiments of the present invention, related apparatus for implementing the above-described solutions is also provided below.

[0079] Please see Figure 4 As shown, the cloud host resource processing device 400 provided in this embodiment of the invention may include: an over-computing unit 401, a limiting computing unit 402, and a resource limiting unit 403.

[0080] The over-computing unit 401 can be used to determine the over-resource value of the physical computing device based on the current resource usage value in response to detecting that the current resource usage value of the physical computing device meets a preset warning condition; the limiting computing unit 402 can be used to determine the target cloud host whose actual resource usage value is greater than the resource commitment value from multiple cloud hosts deployed on the physical computing device, and determine the resource limit value of the target cloud host based on the over-resource value and the actual resource usage value; the resource limiting unit 403 can be used to limit the resource usage of the target cloud host using the resource limit value.

[0081] In this embodiment of the invention, the warning condition includes: the current resource usage value of the physical computing device exceeds the warning threshold of the physical computing device; and the exceeding computing unit 401 can also be used to: determine the difference between the current resource usage value and the warning threshold as the exceeding resource value.

[0082] Preferably, the limiting calculation unit 402 can also be used to: divide the excess resource value according to the allocation weight of the target cloud host to obtain the allocation value of each target cloud host; subtract the allocation value of the target cloud host from the actual resource usage value of any target cloud host to obtain the alternative limiting value; and determine the maximum value between the alternative limiting value and the resource commitment value of the target cloud host as the resource limiting value of the target cloud host.

[0083] As a preferred embodiment, the limiting calculation unit 402 can also be used to: determine the excess ratio of the target cloud host as the quotient of the difference between the actual resource usage value and the resource commitment value of any target cloud host and the resource commitment value; and determine the excess ratio as the allocation weight of the target cloud host.

[0084] In one embodiment, the limiting calculation unit 402 can also be used to: determine the difference between the actual resource usage value and the resource commitment value of any target cloud host as the allocation weight of the target cloud host.

[0085] In an alternative technical solution, the over-computing unit 401 can also be used to: determine the over-resource value of the physical computing device in response to the start of the current adjustment cycle and the detection that the current resource usage value of the physical computing device meets the warning condition.

[0086] Furthermore, in this embodiment of the invention, the resource limiting unit 403 can also be used to: determine the resource limit value of any target cloud host as the upper limit of the resource usage value of the cloud host within the current adjustment period.

[0087] According to the technical solution of the present invention, when the current resource usage value of the physical computing device meets the warning condition, the resource occupation of the cloud host can be restricted, thereby releasing the occupied resources to maintain sufficient resource allocation space to meet the resource commitment value of each cloud host to the user.

[0088] Figure 5 An exemplary system architecture 500 is shown that can be applied to the cloud host resource processing method or cloud host resource processing apparatus of the present invention.

[0089] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, and 503, network 504, and server 505 (this architecture is merely an example; the components included in a specific architecture may be adjusted according to the specific application). Network 504 serves as the medium for providing a communication link between terminal devices 501, 502, and 503 and server 505. Network 504 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0090] Users can use terminal devices 501, 502, and 503 to interact with server 505 via network 504 to receive or send messages, etc. Various client applications, such as cloud management applications, can be installed on terminal devices 501, 502, and 503 (for example only).

[0091] Terminal devices 501, 502, and 503 can be various electronic devices with displays that support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0092] Server 505 can be a server that provides various services, such as a resource limiting server (for example only) that supports cloud management applications operated by users using terminal devices 501, 502, and 503. The resource limiting server can process received resource processing requests and feed back the processing results (e.g., whether the processing was successful - for example only) to terminal devices 501, 502, and 503.

[0093] It should be noted that the cloud host resource processing method provided in this embodiment of the invention is generally executed by server 505, and correspondingly, the cloud host resource processing device is generally set in server 505.

[0094] It should be understood that Figure 5 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0095] The present invention also provides an electronic device. The electronic device of this invention includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the cloud host resource processing method provided by the present invention.

[0096] The following is for reference. Figure 6 It shows a schematic diagram of the structure of a computer system 600 suitable for implementing an electronic device according to embodiments of the present invention. Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0097] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the computer system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0098] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0099] In particular, according to the embodiments disclosed in this invention, the processes described in the above main step diagrams can be implemented as computer software programs. For example, embodiments of this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the main step diagrams. In the above embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit 601, it performs the functions defined in the system of this invention.

[0100] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0102] The units described in the embodiments of the present invention can be implemented in software or hardware. The described units can also be located in a processor; for example, a processor can be described as including: an over-computing unit, a limited computing unit, and a resource limiting unit. The names of these units do not necessarily limit the unit itself; for example, the over-computing unit can also be described as "a unit that provides over-resource values ​​to the limited computing unit."

[0103] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to perform the following steps: in response to detecting that the current resource usage value of a physical computing device meets a preset warning condition, determining an excess resource value of the physical computing device based on the current resource usage value; determining a target cloud host from among multiple cloud hosts deployed on the physical computing device whose actual resource usage value is greater than the promised resource value, determining a resource limit value for the target cloud host based on the excess resource value and the actual resource usage value; and limiting the resource usage of the target cloud host using the resource limit value.

[0104] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the cloud host resource processing method provided by the present invention.

[0105] In the technical solution of this invention embodiment, when the current resource usage value of the physical computing device meets the warning condition, the resource occupation of the cloud host can be restricted, thereby releasing the occupied resources to maintain sufficient resource allocation space to meet the resource commitment value of each cloud host to the user.

[0106] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for processing cloud server resources, characterized in that, include: In response to the detection that the current resource usage value of the physical computing device meets a preset warning condition, the excessive resource value of the physical computing device is determined based on the current resource usage value; From multiple cloud hosts deployed on the physical computing device, a target cloud host whose actual resource usage value is greater than the resource commitment value is identified, and a resource limit value for the target cloud host is determined based on the excess resource value and the actual resource usage value. The resource limit value is used to restrict the resource usage of the target cloud host.

2. The method according to claim 1, characterized in that, The warning conditions include: the current resource usage value of the physical computing device exceeds the warning threshold of the physical computing device; and determining the excessive resource value of the physical computing device based on the current resource usage value includes: The difference between the current resource usage value and the warning threshold is determined as the resource excess value.

3. The method according to claim 1, characterized in that, Determining the resource limit value of the target cloud host based on the exceeded resource value and the actual resource usage value includes: The excess resource value is divided according to the allocation weight of the target cloud host to obtain the allocation value of each target cloud host; Subtract the allocated value of any target cloud host from its actual resource usage value to obtain an alternative limit value. The maximum value between the alternative limit value and the resource commitment value of the target cloud host is determined as the resource limit value of the target cloud host.

4. The method according to claim 3, characterized in that, The method further includes: The excess ratio of any target cloud host is determined by the quotient of the difference between the actual resource usage and the committed resource value and the committed resource value. The excess ratio is determined as the allocation weight of the target cloud host.

5. The method according to claim 1, characterized in that, The method further includes: The difference between the actual resource usage value and the committed resource value of any target cloud host is determined as the allocation weight of that target cloud host.

6. The method according to claim 1, characterized in that, The step of responding to the detection that the current resource usage value of the physical computing device meets a preset warning condition, and determining the excessive resource value of the physical computing device based on the current resource usage value, includes: In response to the start of the current adjustment period and the detection that the current resource usage value of the physical computing device meets the warning condition, it is determined that the physical computing device has exceeded the resource value.

7. The method according to claim 6, characterized in that, The method of limiting the resource usage of the cloud host using the resource limit value includes: During the current adjustment period, the resource limit value of any target cloud host is determined as the upper limit of the resource usage value of that cloud host.

8. The method according to claim 1, characterized in that, The resources include: network bandwidth, number of connections, or number of packet forwards; The physical computing device includes: a physical server or a computer cluster.

9. A cloud server resource processing device, characterized in that, include: The over-computing unit is configured to, in response to detecting that the current resource usage value of the physical computing device meets a preset warning condition, determine the over-resource value of the physical computing device based on the current resource usage value; A limiting computing unit is used to determine, from multiple cloud hosts deployed on the physical computing device, a target cloud host whose actual resource usage value is greater than the resource commitment value, and to determine the resource limit value of the target cloud host based on the excess resource value and the actual resource usage value. The resource limiting unit is used to limit the resource usage of the target cloud host using the resource limiting value.

10. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-8.

Images