Host machine scheduling method and device, storage medium and electronic equipment
By obtaining the host usage and using DPU intelligent network card to automatically schedule, the problem of low migration efficiency between cloud host clusters and bare metal server clusters is solved, and efficient resource scheduling and utilization is achieved.
Patent Information
- Application Number
- CN202410958963.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-12
AI Technical Summary
In the prior art, the host migration efficiency between the cloud host cluster and the bare metal server cluster is inefficient, mainly because the two use different physical resources and cluster management strategies, resulting in complex and inefficient migration operations.
By obtaining the host usage of cloud host clusters and bare metal server clusters, using DPU intelligent network card to automatically schedule hosts, dispatch the hosts of resource-intensive clusters to sufficient resource clusters, and adjust the host hardware mode and cluster labels to Adapt to the target cluster.
It realizes automatic scheduling of hosts between different clusters without manual intervention, improves the efficiency of host migration between cloud host clusters and bare metal server clusters, and improves resource utilization.
Smart Images

Figure CN118939367A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of clusters, and in particular to a host scheduling method, device, storage medium, and electronic device. Background Art
[0002] A cloud host cluster can include multiple hosts, and a bare metal server cluster can also include multiple hosts. However, the two clusters use different physical resources and cluster management strategies, and resource management is complex.
[0003] When the demand for hosts in one cluster increases, the hosts in the other cluster may be idle. In the prior art, a large number of configurations are required to schedule the hosts in one cluster to be used in another cluster. However, this method makes the migration of hosts between different clusters complicated and has low migration efficiency. Summary of the invention
[0004] The present application provides a host scheduling method, device, storage medium and electronic device to solve the technical problem of low efficiency of host migration between cloud host clusters and bare metal server clusters caused by the use of different physical resources and cluster management strategies between different clusters.
[0005] In a first aspect, the present application provides a host scheduling method, comprising: obtaining the host usage of a cloud host cluster and the host usage of a bare metal server cluster; according to the host usage of the above-mentioned cloud host cluster and the host usage of the above-mentioned bare metal server cluster, scheduling the target host of the above-mentioned cloud host cluster to the above-mentioned bare metal server cluster or scheduling the above-mentioned target host of the above-mentioned bare metal server cluster to the above-mentioned cloud host cluster, wherein the above-mentioned target host is installed with a DPU smart network card.
[0006] In a second aspect, the present application provides a host scheduling device, including: an acquisition module, used to obtain the host usage of the cloud host cluster and the host usage of the bare metal server cluster; a scheduling module, used to schedule the target host of the cloud host cluster to the bare metal server cluster or schedule the target host of the bare metal server cluster to the cloud host cluster according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster, wherein the target host is installed with a DPU smart network card.
[0007] As an optional example, the acquisition module includes: an acquisition unit, used to obtain the total number of hosts and the number of idle hosts of the cloud host cluster and the bare metal server cluster; and determine the usage based on the total number of hosts and the number of idle hosts.
[0008] As an optional example, the acquisition unit includes: a determination subunit, used to determine that the usage situation is a shortage of host machine resources when the ratio of the number of idle host machines to the total number of host machines is less than a first preset threshold and the number of idle host machines continues to decrease; and to determine that the usage situation is a sufficient host machine resources when the ratio of the number of idle host machines to the total number of host machines is greater than a second preset threshold, wherein the second preset threshold is greater than the first preset threshold.
[0009] As an optional example, the above-mentioned scheduling module includes: a scheduling unit, which is used to schedule the above-mentioned target host machine of the above-mentioned bare metal server cluster to the above-mentioned cloud host cluster when the host machine resources of the above-mentioned cloud host cluster are scarce and the host machine resources of the above-mentioned bare metal server cluster are sufficient; or, when the host machine resources of the above-mentioned bare metal server cluster are scarce and the host machine resources of the above-mentioned cloud host cluster are sufficient, schedule the above-mentioned target host machine of the above-mentioned cloud host cluster to the above-mentioned bare metal server cluster.
[0010] As an optional example, the scheduling module includes: a first processing unit, used to adjust the hardware mode of the DPU network card of the target host machine to the mode of the cloud host cluster when scheduling the target host machine of the bare metal server cluster to the cloud host cluster; install the physical machine system of the cloud host cluster for the target host machine; adjust the cluster label of the target host machine to the cluster label of the cloud host cluster; and schedule the processed target host machine to the cloud host cluster.
[0011] As an optional example, the scheduling module includes: a second processing unit, used to format the target host when scheduling the target host of the cloud host cluster to the bare metal server cluster; adjust the hardware mode of the DPU network card of the target host to the mode of the bare metal server cluster; adjust the cluster label of the target host to the label of the bare metal server cluster; and schedule the processed target host to the bare metal server cluster.
[0012] As an optional example, the apparatus further includes: a deleting module, configured to delete the target host from the original cluster after scheduling the target host.
[0013] In a third aspect, the present application provides an electronic device comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the memory stores a computer program, and the processor is configured to implement any one of the host scheduling methods mentioned above when executing the computer program.
[0014] In a fourth aspect, the present application further provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute any of the above host scheduling methods of the present application.
[0015] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the solution provided by the embodiment of the present application, by obtaining the host usage of the cloud host cluster and the host usage of the bare metal server cluster; according to the host usage of the above cloud host cluster and the host usage of the above bare metal server cluster, the target host of the above cloud host cluster is scheduled to the above bare metal server cluster or the above target host of the above bare metal server cluster is scheduled to the above cloud host cluster, wherein the above target host is installed with a DPU smart network card, so that the host machines installed with the DPU smart network card of different clusters can be automatically scheduled between different clusters without manual intervention, thereby improving the efficiency of host migration between the cloud host cluster and the bare metal server cluster. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0018] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.
[0019] Figure 1 A flowchart of a host scheduling method provided in an embodiment of the present application;
[0020] Figure 2A schematic diagram of a host scheduling method provided in an embodiment of the present application;
[0021] Figure 3 A flowchart of another host scheduling method provided in an embodiment of the present application;
[0022] Figure 4 A flowchart of another host scheduling method provided in an embodiment of the present application;
[0023] Figure 5 A flowchart of another host scheduling method provided in an embodiment of the present application;
[0024] Figure 6 A flowchart of another host scheduling method provided in an embodiment of the present application;
[0025] Figure 7 A flowchart of another host scheduling method provided in an embodiment of the present application;
[0026] Figure 8 A schematic diagram of the structure of a host scheduling device provided in an embodiment of the present application;
[0027] Fig. 9 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0029] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.
[0030] In order to solve the technical problem in the prior art that different clusters use different physical resources and cluster management strategies, resulting in low efficiency in host migration between cloud host clusters and bare metal server clusters, the present application provides a host scheduling method that can achieve the effect of improving resource utilization.
[0031] Figure 1 A flowchart of a host scheduling method provided in an embodiment of the present application. Figure 1 As shown, the host scheduling method includes:
[0032] S102, obtaining the host usage of the cloud host cluster and the host usage of the bare metal server cluster;
[0033] S104, according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster, the target host of the cloud host cluster is scheduled to the bare metal server cluster or the target host of the bare metal server cluster is scheduled to the cloud host cluster, wherein the target host is installed with a DPU smart network card.
[0034] The target host in this embodiment is equipped with a data processing unit (DPU) smart network card, which can adjust the host system of the target host and the hardware information of the DPU network card, thereby adjusting the cluster adapted by the target host. The target host can be any idle host in the cluster.
[0035] In this embodiment, the host usage status obtained may be the number of idle hosts, or the ratio of idle hosts to total hosts. The number or ratio of idle hosts may be used to check whether host resources in the cluster are tight.
[0036] As another example, the number and proportion of idle hosts can be combined with the cluster tasks of the cluster to check whether the idle hosts of the cluster are tight, that is, whether the cluster tasks can be completed by the idle hosts and whether additional hosts are needed to complete them. If additional hosts are needed, it means that the cluster host resources are tight.
[0037] like Figure 2 As shown, Figure 2 In the example, the cloud host cluster includes multiple host machines, each of which is equipped with a DPU smart network card, while the bare metal server cluster includes multiple host machines, each of which is equipped with a DPU smart network card. There are host machines in use and idle host machines. For example, host machine 3 of the cloud host cluster is an idle host machine, and host machines 5 and host machines 6 of the bare metal server cluster are idle host machines. When the host machine resources of one cluster are tight, the host machines of another cluster can be scheduled to be used by the cluster. For example, the idle host machine 6 of the bare metal server cluster is scheduled to be used by the cloud host cluster. Since the DPU smart network card is installed on the idle host machine, the host machine system can be adjusted through the DPU smart network card to adapt to the bare metal server cluster.
[0038] As another example, in this embodiment, the host machines in the cluster can also be classified into core host machines. The core host machine is a host machine in the cluster that cannot be scheduled. There is no need to install a DPU smart network card on the host machine. In addition, the cluster also includes non-core host machines. The non-core host machines are installed with a DPU smart network card and can be scheduled between different clusters.
[0039] The solution provided in the embodiment of the present application obtains the host usage of the cloud host cluster and the host usage of the bare metal server cluster; according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster, the target host of the cloud host cluster is scheduled to the bare metal server cluster or the target host of the bare metal server cluster is scheduled to the cloud host cluster, wherein the target host is installed with a DPU smart network card, so that the host machines installed with the DPU smart network card in different clusters can be automatically scheduled between different clusters without manual intervention, thereby improving the efficiency of host migration between the cloud host cluster and the bare metal server cluster.
[0040] As an alternative example, Figure 3 As shown in the figure, obtaining the host usage of the cloud host cluster and the bare metal server cluster includes:
[0041] S302, obtaining the total number of hosts and the number of idle hosts in the cloud host cluster and the bare metal server cluster;
[0042] S304: Determine usage according to the total number of host machines and the number of idle host machines.
[0043] In this embodiment, the number of idle hosts in the cloud host cluster and the number of idle hosts in the bare metal server cluster can be obtained, as well as the total number of hosts in each cluster. The number of idle hosts is compared with the total number of hosts to obtain the proportion of idle hosts. The proportion can reflect the overall situation of the cluster, so the proportion can be used to determine whether the host resources of the cluster are tight.
[0044] As an alternative example, Figure 4 As shown, the usage is determined based on the total number of hosts and the number of idle hosts, including:
[0045] S402: When the ratio of the number of idle host machines to the total number of host machines is less than a first preset threshold and the number of idle host machines continues to decrease, it is determined that the usage situation is a shortage of host machine resources; when the ratio of the number of idle host machines to the total number of host machines is greater than a second preset threshold, it is determined that the usage situation is sufficient host machine resources, wherein the second preset threshold is greater than the first preset threshold.
[0046] In this embodiment, a first preset threshold and a second preset threshold can be set. The first preset threshold is used to indicate the lower limit of the proportion of idle host machines. If the proportion of idle host machines is less than the first preset threshold, it means that the number of idle host machines may not be enough. At this time, you can check whether the number of idle host machines is still decreasing and the proportion is still decreasing. If the number is still decreasing and the proportion is still decreasing, it can be determined that the host machine resources are in short supply. If the number increases and the proportion increases, it may be temporarily lower than the first preset threshold, and the target host machine may not be scheduled at this time. The second preset threshold is used to indicate the abundance of the proportion of idle host machines. If the proportion of idle host machines exceeds the second preset threshold, it means that there are many idle host machines and the resources are sufficient, and idle host machines can be provided to other clusters.
[0047] As an optional example, according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster, scheduling the target host of the cloud host cluster to the bare metal server cluster or scheduling the target host of the bare metal server cluster to the cloud host cluster includes: when the host resources of the cloud host cluster are scarce and the host resources of the bare metal server cluster are sufficient, scheduling the target host of the bare metal server cluster to the cloud host cluster; or, when the host resources of the bare metal server cluster are scarce and the host resources of the cloud host cluster are sufficient, scheduling the target host of the cloud host cluster to the bare metal server cluster.
[0048] In this embodiment, the target host machine of the cluster with sufficient resources can be scheduled to the cluster with scarce resources for use. The proportion of idle host machines in the cluster with sufficient resources is greater than the second preset threshold. The proportion of idle host machines in the cluster with scarce resources is less than the second preset threshold and the number and proportion of idle host machines are still decreasing. During scheduling, any one or more of the idle host machines can be scheduled to the cluster with scarce resources, or the host machines in the cluster can be divided into core host machines and non-core host machines, the non-core host machines are installed with DPU smart network cards, and the core host machines are not installed with DPU smart network cards. Schedule any one or more non-core host machines among the idle host machines to the cluster with scarce resources.
[0049] As an alternative example, Figure 5 As shown, according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster, scheduling the target host of the cloud host cluster to the bare metal server cluster or scheduling the target host of the bare metal server cluster to the cloud host cluster includes:
[0050] S502, when scheduling the target host of the bare metal server cluster to the cloud host cluster, adjusting the hardware mode of the DPU network card of the target host to the mode of the cloud host cluster;
[0051] S504, installing a physical machine system of the cloud host cluster for the target host machine;
[0052] S506, adjusting the cluster label of the target host machine to the cluster label of the cloud host cluster;
[0053] S508, scheduling the processed target host machine to the cloud host cluster.
[0054] In this embodiment, when the target host of the bare metal server cluster is scheduled to the cloud host cluster, the hardware mode of the DPU network card of the target host of the bare metal server cluster is adjusted to the cloud host cluster mode. After adjusting the hardware mode of the DPU network card, the physical machine system of the cloud host cluster is installed for the target host. After the physical machine system is installed, the cluster tag is modified to the cloud host cluster tag. After modifying the cloud host cluster tag, when the target host is restarted, the cloud host cluster tag can be passed to the relevant interface, and the interface returns the content of the cloud host cluster, and the physical machine system of the cloud host cluster is started, so as to join the cloud host cluster.
[0055] As an alternative example, Figure 6 As shown, according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster, scheduling the target host of the cloud host cluster to the bare metal server cluster or scheduling the target host of the bare metal server cluster to the cloud host cluster includes:
[0056] S602, when scheduling a target host machine of the cloud host cluster to the bare metal server cluster, formatting the target host machine;
[0057] S604, adjusting the hardware mode of the DPU network card of the target host machine to the mode of the bare metal server cluster;
[0058] S606, adjusting the cluster label of the target host to the label of the bare metal server cluster;
[0059] S608: Schedule the processed target host machine to the bare metal server cluster.
[0060] In this embodiment, when the target host of the cloud host cluster is scheduled to the bare metal server cluster, the target host of the cloud host cluster is first formatted, the cloud service running on it is deleted, and then the hardware mode of the DPU network card of the target host of the cloud host cluster is adjusted to the bare metal server cluster mode. After the hardware mode is adjusted, the cluster label is modified to the bare metal server cluster label. After modifying the bare metal server cluster label, when the target host is restarted, the bare metal server cluster label can be passed to the relevant interface, and the interface returns the content of the bare metal server cluster, so that it is added to the bare metal server cluster.
[0061] As an optional example, after scheduling the target host, the method further includes: deleting the target host in the original cluster. Deleting the target host in the original cluster prevents the target host from being used by multiple clusters.
[0062] Figure 7 It is a flow chart of this embodiment. The host machines of the cloud host cluster and the host machines of the bare metal server cluster will report the resource situation to the resource management module, and the resource management module will count the resource usage of the host machines. Determine which clusters have tight resources and which clusters have sufficient resources. The migration of the host machines is controlled by the control node. Through the data of resource statistics, the host machines in the cluster with sufficient resources are migrated to the cluster with tight resources. For example, if the target host machine of the bare metal server cluster is scheduled to the cloud host cluster, the scheduling node changes the host machine of the bare metal server cluster to the cloud host cluster, modifies the hardware mode of the DPU, reinstalls the host system, and then changes the cluster type of the host machine to complete the change of the host machine. Or when the host machine of the cloud host cluster is changed to the bare metal server cluster, the host machine is formatted, the hardware mode of the DPU is modified, the cluster type of the host machine is changed, and the change of the host machine is completed.
[0063] Figure 8 A schematic diagram of the structure of a host scheduling device provided in an embodiment of the present application.
[0064] like Figure 8 As shown, the host scheduling device includes:
[0065] An acquisition module 802 is used to acquire the host usage of the cloud host cluster and the host usage of the bare metal server cluster;
[0066] The scheduling module 804 is used to schedule the target host of the cloud host cluster to the bare metal server cluster or the target host of the bare metal server cluster to the cloud host cluster according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster, wherein the target host is installed with a DPU smart network card.
[0067] The target host in this embodiment is equipped with a data processing unit (DPU) smart network card, which can adjust the host system of the target host and the hardware information of the DPU network card, thereby adjusting the cluster adapted by the target host. The target host can be any idle host in the cluster.
[0068] In this embodiment, the host usage status obtained may be the number of idle hosts, or the ratio of idle hosts to total hosts. The number or ratio of idle hosts may be used to check whether host resources in the cluster are tight.
[0069] As another example, the number and proportion of idle hosts can be combined with the cluster tasks of the cluster to check whether the idle hosts of the cluster are tight, that is, whether the cluster tasks can be completed by the idle hosts and whether additional hosts are needed to complete them. If additional hosts are needed, it means that the cluster host resources are tight.
[0070] like Figure 2 As shown, Figure 2 In the example, the cloud host cluster includes multiple host machines, each of which is equipped with a DPU smart network card, while the bare metal server cluster includes multiple host machines, each of which is equipped with a DPU smart network card. There are host machines in use and idle host machines. For example, host machine 3 of the cloud host cluster is an idle host machine, and host machines 5 and host machines 6 of the bare metal server cluster are idle host machines. When the host machine resources of one cluster are tight, the host machines of another cluster can be scheduled to be used by the cluster. For example, the idle host machine 6 of the bare metal server cluster is scheduled to be used by the cloud host cluster. Since the DPU smart network card is installed on the idle host machine, the host machine system can be adjusted through the DPU smart network card to adapt to the bare metal server cluster.
[0071] As another example, in this embodiment, the host machines in the cluster can also be classified into core host machines. The core host machine is a host machine in the cluster that cannot be scheduled. There is no need to install a DPU smart network card on the host machine. In addition, the cluster also includes non-core host machines. The non-core host machines are installed with a DPU smart network card and can be scheduled between different clusters.
[0072] The solution provided in the embodiment of the present application obtains the host usage of the cloud host cluster and the host usage of the bare metal server cluster; according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster, the target host of the cloud host cluster is scheduled to the bare metal server cluster or the target host of the bare metal server cluster is scheduled to the cloud host cluster, wherein the target host is installed with a DPU smart network card, so that the host machines installed with the DPU smart network card in different clusters can be automatically scheduled between different clusters without manual intervention, thereby improving the efficiency of host migration between the cloud host cluster and the bare metal server cluster.
[0073] For other examples of this embodiment, please refer to the above examples and will not be described in detail here.
[0074] like Fig. 9 As shown, an embodiment of the present application provides an electronic device, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.
[0075] Memory 113, used for storing computer programs;
[0076] In one embodiment of the present application, the processor 111 is used to implement the host scheduling method provided by any of the aforementioned method embodiments when executing the program stored in the memory 113.
[0077] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, a host scheduling method provided by any of the aforementioned method embodiments is implemented.
[0078] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0079] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0080] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.
[0081] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A host scheduling method, characterized in that: include: Obtain the host usage of the cloud host cluster and the bare metal server cluster; According to the host usage of the cloud host cluster and the host usage of the bare metal server cluster, the target host of the cloud host cluster is scheduled to the bare metal server cluster or the target host of the bare metal server cluster is scheduled to the cloud host cluster, wherein the target host is installed with a DPU smart network card.
2. The method according to claim 1, characterized in that The obtaining of the host usage of the cloud host cluster and the host usage of the bare metal server cluster includes: Obtain the total number of hosts and the number of idle hosts of the cloud host cluster and the bare metal server cluster; The usage is determined according to the total number of host machines and the number of idle host machines.
3. The method according to claim 2, characterized in that Determining the usage according to the total number of host machines and the number of idle host machines includes: When the ratio of the number of idle host machines to the total number of host machines is less than a first preset threshold and the number of idle host machines continues to decrease, determining that the usage condition is that the host machine resources are in short supply; When the ratio of the number of idle host machines to the total number of host machines is greater than a second preset threshold, it is determined that the usage status is that the host machine resources are sufficient, wherein the second preset threshold is greater than the first preset threshold.
4. The method according to claim 1, characterized in that: The step of scheduling the target host of the cloud host cluster to the bare metal server cluster or scheduling the target host of the bare metal server cluster to the cloud host cluster according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster includes: When the host resources of the cloud host cluster are in short supply and the host resources of the bare metal server cluster are sufficient, scheduling the target host of the bare metal server cluster to the cloud host cluster; or, When the host resources of the bare metal server cluster are in short supply and the host resources of the cloud host cluster are sufficient, the target host of the cloud host cluster is scheduled to the bare metal server cluster.
5. The method according to claim 1, characterized in that The step of scheduling the target host of the cloud host cluster to the bare metal server cluster or scheduling the target host of the bare metal server cluster to the cloud host cluster according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster includes: When scheduling the target host of the bare metal server cluster to the cloud host cluster, adjusting the hardware mode of the DPU network card of the target host to the mode of the cloud host cluster; Installing the physical machine system of the cloud host cluster for the target host machine; Adjusting the cluster label of the target host machine to the cluster label of the cloud host cluster; The processed target host is dispatched to the cloud host cluster.
6. The method according to claim 1, characterized in that The step of scheduling the target host of the cloud host cluster to the bare metal server cluster or scheduling the target host of the bare metal server cluster to the cloud host cluster according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster includes: When scheduling the target host of the cloud host cluster to the bare metal server cluster, formatting the target host; Adjusting the hardware mode of the DPU network card of the target host machine to the mode of the bare metal server cluster; Adjusting the cluster label of the target host machine to the label of the bare metal server cluster; The processed target host is dispatched to the bare metal server cluster.
7. The method according to claim 5 or 6, characterized in that: After scheduling the target host, the method further includes: The target host is deleted from the original cluster.
8. A host scheduling device, characterized in that: include: The acquisition module is used to obtain the host usage of the cloud host cluster and the host usage of the bare metal server cluster; A scheduling module is used to schedule the target host of the cloud host cluster to the bare metal server cluster or the target host of the bare metal server cluster to the cloud host cluster according to the host usage of the cloud host cluster and the host usage of the bare metal server cluster, wherein the target host is installed with a DPU smart network card.
9. An electronic device, characterized in that: include: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor coupled to the at least one bus; At least one memory connected to the at least one bus, wherein a computer program is stored in the memory, and when the processor executes the computer program, the host scheduling method described in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the host scheduling method described in any one of claims 1 to 7 of the present application.
