Multi-cloud heterogeneous resource management methods, devices, storage media and computer program products

Abstract

Embodiments of the present application provide a multi-cloud heterogeneous resource management method, device, storage medium and computer program product, the method comprising: a multi-cloud resource fusion manager acquiring relevant information of single-cloud resource topologies established by two or more single-cloud resource managers; managing the relevant information of each single-cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager being a root node; configuring time delay information between each leaf node and the root node on the multi-cloud resource fusion manager; the time delay information being measured and reported by each single-cloud resource manager.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a method, device, storage medium and computer program product for managing multi-cloud heterogeneous resources. Background Technology

[0002] Currently, multi-cloud (cross-cloud, cross-cloud service provider) environments in computing power networks offer applications a wider range of computing power supply. Differences in resource types, costs, and usage management methods among computing resources in multi-cloud scenarios increase the complexity of distributed application operation. In large-scale elastic scaling scenarios, when existing cloud resources are insufficient to meet application demands, elastic resource support across multiple clouds is required. For applications with latency requirements, flexible methods that approximate the data source are typically employed to meet these requirements.

[0003] Based on the above technical characteristics and requirements, there is an urgent need for an effective resource management method to support the application's resource requirements. Summary of the Invention

[0004] In view of this, embodiments of this application aim to provide a multi-cloud heterogeneous resource management method, device, storage medium, and computer program product.

[0005] The technical solution of this application embodiment is implemented as follows:

[0006] This application provides a multi-cloud heterogeneous resource management method, which is applied to a multi-cloud resource fusion manager and includes:

[0007] Retrieve information related to single-cloud resource topologies created by two or more single-cloud resource managers;

[0008] The relevant information of each single cloud resource topology is managed as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is the root node.

[0009] Configure latency information between each leaf node and the root node on the multi-cloud resource fusion manager; the latency information is measured and reported by each single cloud resource manager.

[0010] In one embodiment, the relevant information of the single cloud resource topology includes:

[0011] The single cloud resource manager constructs a single cloud resource topology map based on the distance between nodes, and provides information about each node in the resource topology map; the root node of the single cloud resource topology map is the single cloud resource manager.

[0012] The information of each node includes one or more of the following:

[0013] Resource type;

[0014] Resource quantity;

[0015] The maximum, minimum, and average latency between the node and the single cloud resource manager.

[0016] In one embodiment, the method further includes:

[0017] Receive single-cloud resource control policies sent by each single-cloud resource manager;

[0018] Based on the single-cloud resource control strategy, a resource utilization rate is configured for each type of resource in the single-cloud resource topology; the resource utilization rate is used to characterize the resources occupied by the multi-cloud resource fusion manager.

[0019] The single-cloud resource control strategy includes one or more of the following:

[0020] The types of tasks that a single cloud resource is willing to undertake;

[0021] Resource sharing rate is used to characterize the maximum amount of resources that a single cloud resource manager can authorize to a multi-cloud resource fusion manager;

[0022] Resource usage costs;

[0023] Resource cost coefficient;

[0024] The validity period of the strategy.

[0025] In one embodiment, the method further includes:

[0026] If the resource utilization rate is less than the resource sharing rate, and the absolute value of the difference between the two is less than or equal to a first threshold, negotiate with the single cloud resource manager to increase the single cloud's resource sharing rate.

[0027] If the resource utilization rate is less than the resource sharing rate, and the absolute value of the difference between the two is greater than or equal to the second threshold, negotiate with the single cloud resource manager to reduce the single cloud's resource sharing rate;

[0028] Wherein, the second threshold is greater than the first threshold.

[0029] In one embodiment, obtaining relevant information about single-cloud resource topologies established by two or more single-cloud resource managers includes:

[0030] Establish connections with two or more single-cloud resource managers respectively;

[0031] Negotiate the dimensions of single-cloud resource collection with each single-cloud resource manager;

[0032] Receive information related to the single-cloud resource topology sent by each single-cloud resource manager based on the negotiation result.

[0033] This application also provides a multi-cloud heterogeneous resource management method, which is applied to a single-cloud resource manager, including:

[0034] Send information about the established single-cloud resource topology to the multi-cloud resource fusion manager, so that the multi-cloud resource fusion manager can manage the information about the single-cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is the root node;

[0035] The latency information between the leaf node and the root node is measured and reported to the multi-cloud resource fusion manager.

[0036] In one embodiment, the method further includes:

[0037] Using the single cloud resource manager as the root node, a single cloud resource topology graph is constructed based on the distance between resource nodes; the resource nodes serve as leaf nodes of the root node.

[0038] The distance between two resource nodes in the single-cloud resource topology diagram is related to the IP addresses of the two resource nodes.

[0039] In one embodiment, the method further includes:

[0040] Configure a corresponding single-cloud resource control strategy for each type of resource in the single-cloud resource topology;

[0041] Send the single-cloud resource control policy to the multi-cloud resource fusion manager;

[0042] The single-cloud resource control strategy includes one or more of the following:

[0043] The types of tasks that a single cloud resource is willing to undertake;

[0044] Resource sharing rate is used to characterize the maximum amount of resources that a single cloud resource manager can authorize to a multi-cloud resource fusion manager;

[0045] Resource usage costs;

[0046] Resource cost coefficient;

[0047] The validity period of the strategy.

[0048] In one embodiment, the method further includes:

[0049] The updated single-cloud resource control policy is sent to the multi-cloud resource fusion manager.

[0050] This application embodiment also provides a multi-cloud resource fusion manager, including: a first communication interface and a first processor; wherein,

[0051] The first communication interface is used to obtain information related to the single cloud resource topology established by two or more single cloud resource managers;

[0052] The first processor is used to manage the relevant information of each single cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is the root node;

[0053] Configure latency information between each leaf node and the root node on the multi-cloud resource fusion manager; the latency information is measured and reported by each single cloud resource manager.

[0054] This application also provides a multi-cloud resource fusion manager, including: a first processor and a first memory for storing computer programs capable of running on the processor.

[0055] Wherein, when the first processor is used to run the computer program, it executes the steps of the above method.

[0056] This application also provides a single-cloud resource manager, including: a second communication interface and a second processor; wherein,

[0057] The second communication interface is used to send information about the established single-cloud resource topology to the multi-cloud resource fusion manager, and the multi-cloud resource fusion manager manages the information about the single-cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is the root node;

[0058] The second processor is used to measure the latency information between the leaf node and the root node and report it to the multi-cloud resource fusion manager.

[0059] This application also provides a single-cloud resource manager, including: a second processor and a second memory for storing computer programs capable of running on the processor.

[0060] The second processor is used to execute the steps of the above method when running the computer program.

[0061] This application also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described method.

[0062] This application also provides a computer program product, including a computer program that implements the above-described method when executed by a processor.

[0063] The multi-cloud heterogeneous resource management method, device, storage medium, and computer program product provided in this application embodiment involve a multi-cloud resource fusion manager acquiring relevant information about single-cloud resource topologies established by two or more single-cloud resource managers; managing the relevant information of each single-cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager serving as the root node; configuring latency information between each leaf node and the root node on the multi-cloud resource fusion manager; and measuring and reporting the latency information by each single-cloud resource manager. This application embodiment enables the multi-cloud resource fusion manager to manage multiple single-cloud resources, and applications with latency requirements can refer to the latency information to call resources. Attached Figure Description

[0064] Figure 1 This is a schematic diagram of the multi-cloud heterogeneous resource management method described in the embodiments of this application. Figure 1 ;

[0065] Figure 2 This is a schematic diagram of the multi-cloud heterogeneous resource management system structure described in the embodiments of this application;

[0066] Figure 3 This is a schematic diagram of the structure of the single cloud resource topology diagram described in the embodiments of this application;

[0067] Figure 4 This is a schematic diagram of the multi-cloud heterogeneous resource management method described in the embodiments of this application. Figure 2 ;

[0068] Figure 5 This is a schematic diagram of the structure of the multi-cloud heterogeneous resource management device described in the embodiments of this application;

[0069] Figure 6 This is a schematic diagram of the single-cloud heterogeneous resource management device described in an embodiment of this application;

[0070] Figure 7 This is a schematic diagram of the structure of the multi-cloud resource fusion manager described in the embodiments of this application;

[0071] Figure 8 This is a schematic diagram of the structure of the single cloud resource manager described in the embodiments of this application. Detailed Implementation

[0072] The present application will now be described in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other. The present application will now be described in detail with reference to the accompanying drawings and embodiments.

[0073] This application provides a method for managing multi-cloud heterogeneous resources, such as... Figure 1 As shown, this method is applied to a multi-cloud resource fusion manager and includes:

[0074] Step 101: Obtain relevant information about the single-cloud resource topologies established by two or more single-cloud resource managers;

[0075] Step 102: Manage the relevant information of each single cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is the root node;

[0076] Step 103: Configure latency information between each leaf node and the root node on the multi-cloud resource fusion manager; the latency information is measured and reported by each single cloud resource manager.

[0077] The embodiments of this application can be accessed through... Figure 2 The system implementation shown is as follows: Figure 2 As shown, the system includes: a multi-cloud resource fusion manager and multiple ( Figure 2 Only one cloud resource manager is displayed in the middle; among them,

[0078] The multi-cloud resource fusion manager is responsible for managing resources from multiple clouds and includes: a fusion resource management unit, a resource policy management unit, and a detection unit; the fusion resource management unit is responsible for maintaining multi-cloud resource information, including resource logical topology, resource type, and resource availability; the resource policy management unit is responsible for maintaining the usage policy of fusion resources; and the detection unit is responsible for detecting resource node information.

[0079] The single-cloud resource manager is responsible for managing resources within a single cloud and includes: a resource information collection unit, a policy control unit, and a detection unit; the policy control unit is responsible for managing resource usage policies within the cloud; the detection unit is responsible for detecting resource node information; the resource information collection unit is responsible for collecting information based on cloud resources, including resource topology and node information, and synchronizing it to the multi-cloud resource fusion manager.

[0080] In this embodiment of the application, the relevant information of the single cloud resource topology includes:

[0081] The single cloud resource manager constructs a single cloud resource topology map based on the distance between nodes, and provides information about each node in the resource topology map; the root node of the single cloud resource topology map is the single cloud resource manager.

[0082] The information of each node includes one or more of the following:

[0083] Resource type;

[0084] Resource quantity;

[0085] The maximum, minimum, and average latency between the node and the single cloud resource manager.

[0086] The following is an example of constructing a single cloud resource topology diagram. The construction method is as follows:

[0087] Step 1: Set the single cloud resource manager as the root node;

[0088] Step 2: Place the node (one or more) closest to the single cloud resource manager into set A, and place the other nodes into set B. Set A and set B are the left and right leaf nodes of the single cloud resource manager, respectively. Figure 3 As shown;

[0089] Step 3: From set B, put the node that is closest to the single cloud resource manager into set B1, and put the other nodes into set B2. B1 and B2 are the left and right leaf nodes of B, respectively.

[0090] Step 4: If B2 is not empty, treat B2 as set B and continue to execute steps 3 and 4.

[0091] Here, the distance between two nodes is calculated by performing a bitwise XOR operation on the IP addresses of the two nodes. The value represented by the first non-zero bit of the XOR result is the distance between the two nodes. An example is shown below:

[0092] The IP address of the single cloud resource manager is 192.168.1.1, the IP address of node 1 is 192.168.1.15, and the IP address of node 2 is 192.168.3.6. Therefore, the distance between node 1 and the single cloud resource manager is expressed as: (192.168.1.1) xor (192.168.1.15) = 0.0.0.14, which is 8. The distance between node 2 and the single cloud resource manager is expressed as: (192.168.1.1) xor (192.168.3.6) = 0.0.2.7, which is 1024.

[0093] The information of each leaf node in the single-cloud resource topology diagram includes information about all nodes in the set of resource nodes it represents, including resource type (e.g., CPU, GPU, NPU, FPGA, etc.), resource quantity, and the latency of the node from the single-cloud resource manager (including maximum, minimum, and average latency). The node information can be formed by converging from the node farthest from the unit resource manager to the unit resource manager node. (Refer to the single-cloud resource topology.) Figure 3 The resource information of node B is formed by aggregating the resource information of nodes B1 and B2. The aggregation method is as follows:

[0094] The resource types of nodes B1 and B2 are merged to form the resource type of node B, and the resource quantities of nodes B1 and B2 are merged to form the resource quantity of node B.

[0095] The maximum latency of compute node B to the single cloud resource manager is max(B1,B2), and the minimum latency is min(B1,B2).

[0096] The average latency of node B from the single cloud resource manager is calculated as SUM(Bi resource quantity * Bi average latency) / SUM(Bi resource quantity), where i = 1, 2. The latency of each resource in node B1 or node B2 can be measured by the probe unit in the single cloud resource manager.

[0097] For example: If node B1 has 5 resources and the average latency of these 5 resources is 10ms; and node B2 has 10 resources and the average latency of these 10 resources is 15ms, then the average latency of node B is: (5*10+10*15) / 15.

[0098] As can be seen, the resource topology map in this application is established based on distance, which can well reflect the positional relationship between nodes.

[0099] In one embodiment of this application, the method further includes:

[0100] Receive single-cloud resource control policies sent by each single-cloud resource manager;

[0101] Based on the single-cloud resource control strategy, a resource utilization rate is configured for each type of resource in the single-cloud resource topology; the resource utilization rate is used to characterize the resources occupied by the multi-cloud resource fusion manager.

[0102] The single-cloud resource control strategy includes one or more of the following:

[0103] The types of tasks that a single cloud resource is willing to undertake;

[0104] Resource sharing rate is used to characterize the maximum amount of resources that a single cloud resource manager can authorize to a multi-cloud resource fusion manager;

[0105] Resource usage costs;

[0106] Resource cost coefficient;

[0107] The validity period of the strategy.

[0108] In one embodiment, the policy control unit in the single-cloud resource manager uniformly manages and configures resource sharing policies for each type of resource, and synchronizes them with the resource policy management unit in the multi-cloud resource fusion manager. The sharing policy includes: the types of tasks the single-cloud resource is willing to undertake, the resource sharing rate, the resource usage cost, the resource cost coefficient, and the validity period of the policy; wherein,

[0109] The types of tasks that the single cloud resource is willing to undertake may include: image recognition, streaming computing, large model training, etc.

[0110] Resource sharing rate: The upper limit of the proportion of resource management authorized by a single cloud resource manager to a multi-cloud resource manager; this value can be dynamically adjusted through negotiation between the policy control unit in the single cloud resource manager and the resource policy management unit in the multi-cloud resource fusion manager.

[0111] Resource usage cost: The basic unit price for using resources;

[0112] Resource cost coefficient: actual unit price of resource / usage cost, which can be set as a tiered cost coefficient based on the sharing rate;

[0113] The validity period of the strategy is recorded as an absolute time, marking the expiration time of this resource sharing strategy.

[0114] In this embodiment, the single-cloud resource manager can configure resource sharing policies for resources within the cloud and can update the resource sharing policies as needed, thus realizing flexible resource sharing. Furthermore, the unit resource manager achieves control over its own resources within the single cloud.

[0115] In one embodiment of this application, the method further includes:

[0116] If the resource utilization rate is less than the resource sharing rate, and the absolute value of the difference between the two is less than or equal to a first threshold, negotiate with the single cloud resource manager to increase the single cloud's resource sharing rate.

[0117] If the resource utilization rate is less than the resource sharing rate, and the absolute value of the difference between the two is greater than or equal to the second threshold, negotiate with the single cloud resource manager to reduce the single cloud's resource sharing rate;

[0118] Wherein, the second threshold is greater than the first threshold.

[0119] In one application example of this application, the resource policy management unit in the multi-cloud resource fusion manager establishes a global resource control policy table after receiving the single-cloud resource control policy sent by the single-cloud resource manager; it configures a resource utilization rate for each resource, where the resource utilization rate represents the resource occupied by the multi-cloud resource fusion manager; when the resource utilization rate is close to or reaches the sharing rate, it can negotiate with the single-cloud control policy unit to increase the resource sharing rate; similarly, when the resource utilization rate is much lower than the resource sharing rate, it can negotiate with the single-cloud control policy unit to decrease the resource sharing rate; the policy control unit can also proactively update the control policy for resources within the same cloud.

[0120] In this embodiment of the application, obtaining relevant information about the single-cloud resource topology established by two or more single-cloud resource managers includes:

[0121] Establish connections with two or more single-cloud resource managers respectively;

[0122] Negotiate the dimensions of single-cloud resource collection with each single-cloud resource manager;

[0123] Receive information related to the single-cloud resource topology sent by each single-cloud resource manager based on the negotiation result.

[0124] In one embodiment, the dimension of single-cloud resource collection refers to the attribute description of the resource, such as: CPU, storage, memory size, network bandwidth, etc.; after negotiation, both parties collect and return resource-related information (relevant information of single-cloud resource topology) according to the negotiation results. Cloud administrators, both single-cloud and multi-cloud administrators can set the dimension of resource collection.

[0125] This application also provides a method for managing multi-cloud heterogeneous resources, such as... Figure 4 As shown, this method is applied to a single cloud resource manager and includes:

[0126] Step 401: Send relevant information about the established single-cloud resource topology to the multi-cloud resource fusion manager, so that the multi-cloud resource fusion manager can manage the relevant information about the single-cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is the root node;

[0127] Step 402: Measure the latency information between the leaf node and the root node and report it to the multi-cloud resource fusion manager.

[0128] In this embodiment of the application, the method further includes:

[0129] Using the single cloud resource manager as the root node, a single cloud resource topology graph is constructed based on the distance between resource nodes; the resource nodes serve as leaf nodes of the root node.

[0130] The distance between two resource nodes in the single-cloud resource topology diagram is related to the IP addresses of the two resource nodes.

[0131] The construction method of the single cloud resource topology map is as described above and will not be detailed here.

[0132] In one embodiment of this application, the method further includes:

[0133] Configure a corresponding single-cloud resource control strategy for each type of resource in the single-cloud resource topology;

[0134] Send the single-cloud resource control policy to the multi-cloud resource fusion manager;

[0135] The single-cloud resource control strategy includes one or more of the following:

[0136] The types of tasks that a single cloud resource is willing to undertake;

[0137] Resource sharing rate is used to characterize the maximum amount of resources that a single cloud resource manager can authorize to a multi-cloud resource fusion manager;

[0138] Resource usage costs;

[0139] Resource cost coefficient;

[0140] The validity period of the strategy.

[0141] In one embodiment of this application, the method further includes:

[0142] The updated single-cloud resource control policy is sent to the multi-cloud resource fusion manager.

[0143] To implement the multi-cloud resource fusion manager side method embodiment, this application embodiment also provides a multi-cloud heterogeneous resource management device, such as... Figure 5 As shown, the device is applied to a multi-cloud resource fusion manager and includes:

[0144] The first communication unit 501 is used to obtain relevant information about the single cloud resource topology established by two or more single cloud resource managers;

[0145] The first processing unit 502 is used to manage the relevant information of each single cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is the root node;

[0146] Configure latency information between each leaf node and the root node on the multi-cloud resource fusion manager; the latency information is measured and reported by each single cloud resource manager.

[0147] In this embodiment of the application, the relevant information of the single cloud resource topology includes:

[0148] The single cloud resource manager constructs a single cloud resource topology map based on the distance between nodes, and provides information about each node in the resource topology map; the root node of the single cloud resource topology map is the single cloud resource manager.

[0149] The information of each node includes one or more of the following:

[0150] Resource type;

[0151] Resource quantity;

[0152] The maximum, minimum, and average latency between the node and the single cloud resource manager.

[0153] In the embodiments of this application,

[0154] The first communication unit 501 is also used to receive single-cloud resource control policies sent by each single-cloud resource manager;

[0155] The first processing unit 502 is further configured to configure resource utilization rate for each type of resource in the single cloud resource topology based on the single cloud resource control strategy; the resource utilization rate is used to characterize the resources occupied by the multi-cloud resource fusion manager.

[0156] The single-cloud resource control strategy includes one or more of the following:

[0157] The types of tasks that a single cloud resource is willing to undertake;

[0158] Resource sharing rate is used to characterize the maximum amount of resources that a single cloud resource manager can authorize to a multi-cloud resource fusion manager;

[0159] Resource usage costs;

[0160] Resource cost coefficient;

[0161] The validity period of the strategy.

[0162] In this embodiment of the application, the first processing unit 502 is further used for

[0163] If the resource utilization rate is less than the resource sharing rate, and the absolute value of the difference between the two is less than or equal to a first threshold, negotiate with the single cloud resource manager to increase the single cloud's resource sharing rate.

[0164] If the resource utilization rate is less than the resource sharing rate, and the absolute value of the difference between the two is greater than or equal to the second threshold, negotiate with the single cloud resource manager to reduce the single cloud's resource sharing rate;

[0165] Wherein, the second threshold is greater than the first threshold.

[0166] In this embodiment of the application, the first communication unit 501 acquires relevant information about single-cloud resource topologies established by two or more single-cloud resource managers, including:

[0167] Establish connections with two or more single-cloud resource managers respectively;

[0168] Negotiate the dimensions of single-cloud resource collection with each single-cloud resource manager;

[0169] Receive information related to the single-cloud resource topology sent by each single-cloud resource manager based on the negotiation result.

[0170] In practical applications, the first communication unit 501 can be implemented by the communication interface in the multi-cloud heterogeneous resource management device; the first processing unit 502 can be implemented by the processor in the multi-cloud heterogeneous resource management device.

[0171] It should be noted that the communication of the multi-cloud heterogeneous resource management device provided in the above embodiments is only illustrated by the division of the above program modules. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0172] To implement the single-cloud resource manager side method embodiment, this application embodiment also provides a single-cloud heterogeneous resource management device, such as... Figure 6 As shown, the device is applied to a single cloud resource manager and includes:

[0173] The second communication unit 601 is used to send relevant information about the established single-cloud resource topology to the multi-cloud resource fusion manager, so that the multi-cloud resource fusion manager can manage the relevant information about the single-cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is the root node;

[0174] The second processing unit 602 is used to measure the latency information between the leaf node and the root node and report it to the multi-cloud resource fusion manager.

[0175] In this embodiment of the application, the second processing unit 602 is further used for

[0176] Using the single cloud resource manager as the root node, a single cloud resource topology graph is constructed based on the distance between resource nodes; the resource nodes serve as leaf nodes of the root node.

[0177] The distance between two resource nodes in the single-cloud resource topology diagram is related to the IP addresses of the two resource nodes.

[0178] In the embodiments of this application,

[0179] The second processing unit 602 is further configured to configure a corresponding single-cloud resource control strategy for each type of resource in the single-cloud resource topology;

[0180] The second communication unit 601 is also used to send the single cloud resource control policy to the multi-cloud resource fusion manager;

[0181] The single-cloud resource control strategy includes one or more of the following:

[0182] The types of tasks that a single cloud resource is willing to undertake;

[0183] Resource sharing rate is used to characterize the maximum amount of resources that a single cloud resource manager can authorize to a multi-cloud resource fusion manager;

[0184] Resource usage costs;

[0185] Resource cost coefficient;

[0186] The validity period of the strategy.

[0187] In this embodiment of the application, the second processing unit 602 is further used for

[0188] The updated single-cloud resource control policy is sent to the multi-cloud resource fusion manager.

[0189] In practical applications, the second communication unit 601 can be implemented by the communication interface in the single-cloud heterogeneous resource management device; the second processing unit 602 can be implemented by the processor in the single-cloud heterogeneous resource management device.

[0190] It should be noted that the single-cloud heterogeneous resource management device provided in the above embodiments is only illustrated by the division of the above program modules during communication. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0191] Based on the hardware implementation of the above program modules, and in order to implement the method on the multi-cloud resource fusion manager side of the embodiments of this application, the embodiments of this application also provide a multi-cloud resource fusion manager, such as... Figure 7 As shown, the multi-cloud resource fusion manager 700 includes:

[0192] The first communication interface 701 is capable of exchanging information with the single cloud resource manager and / or other nodes on the network side;

[0193] The first processor 702 is connected to the first communication interface 701 to enable information interaction with the single cloud resource manager and / or other nodes on the network side, and to execute the methods provided by one or more technical solutions on the single cloud resource manager side when running a computer program;

[0194] The computer program is stored in the first memory 703.

[0195] Specifically, the first communication interface 701 is used to obtain relevant information about the single cloud resource topology established by two or more single cloud resource managers;

[0196] The first processor 702 is used to manage the relevant information of each single cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is the root node;

[0197] Configure latency information between each leaf node and the root node on the multi-cloud resource fusion manager; the latency information is measured and reported by each single cloud resource manager.

[0198] In this embodiment of the application, the relevant information of the single cloud resource topology includes:

[0199] The single cloud resource manager constructs a single cloud resource topology map based on the distance between nodes, and provides information about each node in the resource topology map; the root node of the single cloud resource topology map is the single cloud resource manager.

[0200] The information of each node includes one or more of the following:

[0201] Resource type;

[0202] Resource quantity;

[0203] The maximum, minimum, and average latency between the node and the single cloud resource manager.

[0204] In the embodiments of this application,

[0205] The first communication interface 701 is also used to receive single-cloud resource control policies sent by each single-cloud resource manager;

[0206] The first processor 702 is further configured to configure resource utilization rate for each type of resource in the single cloud resource topology based on the single cloud resource control strategy; the resource utilization rate is used to characterize the resources occupied by the multi-cloud resource fusion manager.

[0207] The single-cloud resource control strategy includes one or more of the following:

[0208] The types of tasks that a single cloud resource is willing to undertake;

[0209] Resource sharing rate is used to characterize the maximum amount of resources that a single cloud resource manager can authorize to a multi-cloud resource fusion manager;

[0210] Resource usage costs;

[0211] Resource cost coefficient;

[0212] The validity period of the strategy.

[0213] In this embodiment of the application, the first processor 702 is further used for

[0214] If the resource utilization rate is less than the resource sharing rate, and the absolute value of the difference between the two is less than or equal to a first threshold, negotiate with the single cloud resource manager to increase the single cloud's resource sharing rate.

[0215] If the resource utilization rate is less than the resource sharing rate, and the absolute value of the difference between the two is greater than or equal to the second threshold, negotiate with the single cloud resource manager to reduce the single cloud's resource sharing rate;

[0216] Wherein, the second threshold is greater than the first threshold.

[0217] In this embodiment of the application, the first communication interface 701 obtains relevant information about single-cloud resource topologies established by two or more single-cloud resource managers, including:

[0218] Establish connections with two or more single-cloud resource managers respectively;

[0219] Negotiate the dimensions of single-cloud resource collection with each single-cloud resource manager;

[0220] Receive information related to the single-cloud resource topology sent by each single-cloud resource manager based on the negotiation result.

[0221] It should be noted that the specific processing procedures of the first communication interface 701 and the first processor 702 can be understood by referring to the above method, and will not be repeated here.

[0222] Of course, in practical applications, the various components in the Multi-Cloud Resource Fusion Manager 700 are coupled together through the bus system 704. It can be understood that the bus system 704 is used to implement communication between these components. In addition to the data bus, the bus system 704 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 7 The general designated all buses as Bus System 704.

[0223] The first memory 703 in this embodiment is used to store various types of data to support the operation of the multi-cloud resource fusion manager 700. Examples of such data include any computer program used to operate on the multi-cloud resource fusion manager 700.

[0224] The methods disclosed in the embodiments of this application can be applied to the first processor 702, or implemented by the first processor 702. The first processor 702 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware or by instructions in the form of software in the first processor 702. The first processor 702 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The first processor 702 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in the first memory 703. The first processor 702 reads the information in the first memory 703 and completes the steps of the aforementioned method in combination with its hardware.

[0225] In an exemplary embodiment, the multi-cloud resource fusion manager 700 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned methods.

[0226] Based on the hardware implementation of the above program modules, and in order to implement the method on the single-cloud resource manager side of the embodiments of this application, the embodiments of this application also provide a single-cloud resource manager, such as... Figure 8 As shown, the single cloud resource manager 800 includes:

[0227] The second communication interface 801 is capable of exchanging information with the multi-cloud resource fusion manager and / or other nodes on the network side;

[0228] The second processor 802 is connected to the second communication interface 801 to enable information interaction with the multi-cloud resource fusion manager and / or other nodes on the network side, and to execute the methods provided by one or more technical solutions on the single-cloud resource manager side when running computer programs.

[0229] The computer program is stored in the second memory 803.

[0230] Specifically, the second communication interface 801 is used to send relevant information about the established single-cloud resource topology to the multi-cloud resource fusion manager, so that the multi-cloud resource fusion manager can manage the relevant information about the single-cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is the root node;

[0231] The second processor 802 is used to measure the latency information between the leaf node and the root node and report it to the multi-cloud resource fusion manager.

[0232] In this embodiment of the application, the second processor 802 is further used for

[0233] Using the single cloud resource manager as the root node, a single cloud resource topology graph is constructed based on the distance between resource nodes; the resource nodes serve as leaf nodes of the root node.

[0234] The distance between two resource nodes in the single-cloud resource topology diagram is related to the IP addresses of the two resource nodes.

[0235] In the embodiments of this application,

[0236] The second processor 802 is also configured to configure a corresponding single-cloud resource control strategy for each type of resource in the single-cloud resource topology;

[0237] The second communication interface 801 is also used to send the single cloud resource control policy to the multi-cloud resource fusion manager;

[0238] The single-cloud resource control strategy includes one or more of the following:

[0239] The types of tasks that a single cloud resource is willing to undertake;

[0240] Resource sharing rate is used to characterize the maximum amount of resources that a single cloud resource manager can authorize to a multi-cloud resource fusion manager;

[0241] Resource usage costs;

[0242] Resource cost coefficient;

[0243] The validity period of the strategy.

[0244] In this embodiment of the application, the second processor 802 is further used for

[0245] The updated single-cloud resource control policy is sent to the multi-cloud resource fusion manager.

[0246] It should be noted that the specific processing procedures of the second communication interface 801 and the second processor 802 can be understood by referring to the above method, and will not be repeated here.

[0247] Of course, in practical applications, the various components in the single-cloud resource manager 800 are coupled together through the bus system 804. It can be understood that the bus system 804 is used to implement communication between these components. In addition to the data bus, the bus system 804 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 8 The general labeled all buses as Bus System 804.

[0248] The second memory 803 in this embodiment is used to store various types of data to support the operation of the single cloud resource manager 800. Examples of such data include any computer program used to operate on the single cloud resource manager 800.

[0249] The methods disclosed in the embodiments of this application can be applied to, or implemented by, the second processor 802. The second processor 802 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by the integrated logic circuitry of the hardware or by instructions in the software form of the second processor 802. The second processor 802 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The second processor 802 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, specifically a second memory 803. The second processor 802 reads information from the second memory 803 and, in conjunction with its hardware, completes the steps of the aforementioned method.

[0250] In an exemplary embodiment, the single cloud resource manager 800 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned methods.

[0251] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as a first memory 703 storing a computer program, which can be executed by a first processor 702 of a multi-cloud resource fusion manager 700 to complete the steps described in the aforementioned multi-cloud resource fusion manager-side method. Another example is a second memory 803 storing a computer program, which can be executed by a second processor 802 of a single-cloud resource manager 800 to complete the steps described in the aforementioned single-cloud resource manager-side method. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.

[0252] For example, embodiments of this application also provide a computer program product, including a computer program that can be executed by the processor of a multi-cloud resource fusion manager 700 or a single-cloud resource manager 800 to perform the steps described in any of the foregoing methods.

[0253] It should be noted that terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0254] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0255] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application.

Claims

1. A method for managing multi-cloud heterogeneous resources, characterized in that, The method is applied to a multi-cloud resource fusion manager, and comprises: obtaining related information of a single-cloud resource topology established by two or more single-cloud resource managers; managing the related information of each single-cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is a root node; configuring time delay information between each leaf node and the root node on the multi-cloud resource fusion manager; the time delay information is measured and reported by each single-cloud resource manager.

2. The method of claim 1, wherein, The related information of the single-cloud resource topology comprises: a single-cloud resource topology graph constructed by a single-cloud resource manager based on distances between nodes and information of each node in the resource topology graph; the root node of the single-cloud resource topology graph is the single-cloud resource manager; wherein the information of each node comprises one or more of: a resource type; a resource quantity; a maximum value, a minimum value and an average value of a time delay of the node from the single-cloud resource manager.

3. The method of claim 1, wherein, The method further comprises: receiving a single-cloud resource control strategy sent by each single-cloud resource manager; configuring a resource usage rate for each type of resource in the single-cloud resource topology based on the single-cloud resource control strategy; the resource usage rate is used to represent a resource occupied by the multi-cloud resource fusion manager; wherein the single-cloud resource control strategy comprises one or more of: a task type that a single-cloud resource is willing to undertake; a resource sharing rate used to represent an upper limit of a resource authorized by a single-cloud resource manager to a multi-cloud resource fusion manager; a resource usage cost; a resource cost coefficient; a valid period of the strategy.

4. The method of claim 3, wherein, The method further comprises: in a case where the resource usage rate is less than the resource sharing rate and an absolute value of a difference between the two is less than or equal to a first threshold, negotiating with the single-cloud resource manager to increase the resource sharing rate of the single-cloud; in a case where the resource usage rate is less than the resource sharing rate and an absolute value of a difference between the two is greater than or equal to a second threshold, negotiating with the single-cloud resource manager to reduce the resource sharing rate of the single-cloud; wherein the second threshold is greater than the first threshold.

5. The method of claim 1, wherein, The obtaining of the related information of the single-cloud resource topology established by two or more single-cloud resource managers comprises: establishing a connection with two or more single-cloud resource managers respectively; negotiating with each single-cloud resource manager about a dimension of single-cloud resource collection; receiving related information of a single-cloud resource topology sent by each single-cloud resource manager based on a negotiation result.

6. A method for managing a plurality of cloud heterogeneous resources, the method comprising: The method is applied to a single-cloud resource manager, and comprises: sending related information of a single-cloud resource topology established by the single-cloud resource manager to a multi-cloud resource fusion manager, for the multi-cloud resource fusion manager to manage the related information of the single-cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is a root node; measuring time delay information between the leaf node and the root node and reporting the time delay information to the multi-cloud resource fusion manager.

7. The method of claim 6, wherein, The method further comprises: constructing a single-cloud resource topology graph based on distances between resource nodes with the single-cloud resource manager as a root node; the resource nodes are leaf nodes of the root node; The distance between two resource nodes in the single-cloud resource topology is related to IP addresses of the two resource nodes.

8. The method of claim 6, wherein, The method further comprises: configuring a corresponding single-cloud resource control policy for each type of resource in the single-cloud resource topology; sending the single-cloud resource control policy to the multi-cloud resource fusion manager; The single-cloud resource control policy comprises one or more of the following: a type of task that the single-cloud resource is willing to undertake; a resource sharing rate for representing an upper limit of resources authorized by the single-cloud resource manager to the multi-cloud resource fusion manager; a resource use cost; a resource cost coefficient; a validity period of the policy.

9. The method of claim 8, wherein, The method further comprises: sending the updated single-cloud resource control policy to the multi-cloud resource fusion manager.

10. A multi-cloud resource fusion manager, characterized in that, Comprise: a first communication interface and a first processor; wherein the first communication interface is configured to obtain information about a single-cloud resource topology established by two or more single-cloud resource managers; the first processor is configured to manage each single-cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is a root node; configure the latency information between each leaf node and the root node on the multi-cloud resource fusion manager; the latency information is measured and reported by each single-cloud resource manager.

11. A multi-cloud resource fusion manager, characterized in that, Comprise: a first processor and a first memory for storing a computer program capable of running on the processor, wherein the first processor is configured to execute the steps of the method of any one of claims 1 to 5 when running the computer program.

12. A single cloud resource manager, characterized by, Comprise: a second communication interface and a second processor; wherein the second communication interface is configured to send information about the established single-cloud resource topology to the multi-cloud resource fusion manager, for the multi-cloud resource fusion manager to manage the information about the single-cloud resource topology as a leaf node of the multi-cloud resource fusion manager; the multi-cloud resource fusion manager is a root node; the second processor is configured to measure and report the latency information between the leaf node and the root node to the multi-cloud resource fusion manager.

13. A single cloud resource manager, characterized by, Comprise: a second processor and a second memory for storing a computer program capable of running on the processor, wherein the second processor is configured to execute the steps of the method of any one of claims 6 to 9 when running the computer program.

14. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5, or to implement the steps of the method of any one of claims 6 to 9.

15. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1 to 5, or to implement the method of any one of claims 6 to 9.

Images