Cluster-based network card intelligent scheduling method

Abstract

The invention provides a network card intelligent scheduling method based on a cluster, and the method comprises the steps: building a plurality of network resource pools, and deploying a plurality of synchronously created message queues in each network resource pool; using the corresponding network resource monitoring device to count the use condition of the network resources in each server to obtain a statistical result so as to distribute the network resources; the network management device screens out all network resource pools meeting requirements from all network resource pools according to the statistical result and the message queue; the network management device selects a target server for the to-be-scheduled virtual machine from all the network resource pools meeting the requirements, and issues a selection result to a network resource monitoring device corresponding to the target server; the network resource monitoring device dispatches the virtual machine to be dispatched to a target physical network card in a target server according to the scoring rule; the utilization rate of network resources is improved, and the phenomenon that the virtual machine fails to start up due to the fact that the network resources cannot be found is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of computer networks, and in particular to a method for intelligently scheduling network cards based on clusters. Background Art

[0002] Network virtualization technology improves resource utilization efficiency and network flexibility by building multiple independent virtual networks on the physical network. It achieves network isolation and security, supports on-demand expansion and dynamic adjustment, simplifies network management and reduces operational expenses, and plays a key role in modern network applications such as cloud computing and data centers. However, virtual machines and containers on the cloud have put forward higher requirements on the ease of use, functions and performance of network virtualization technology.

[0003] There are three ways of network virtualization: software simulation, virtio-based paravirtualization, and device passthrough. Device passthrough realizes network data plane acceleration, allowing physical devices of the high-speed serial computer expansion bus standard (PCIe, peripheral component interconnect express) to directly access the physical address allocated by the corresponding driver running in the virtual machine's in-machine operating system GuestOS.

[0004] Pure software simulation, the usage and experience of using the virtual network card in the guest system are exactly the same as on the physical machine (except for performance), and there is no need to modify the kernel driver or configuration.

[0005] The emergence of Single Root I / O Virtualization (SR-IOV) supports a single physical device to virtualize multiple virtual devices, and then directly connect the virtual devices to the virtual machines, so as to realize the application scenario of a single physical device supporting multiple virtual machines.

[0006] The virtual machine network usage modes include host mode, network address translation (NAT, Network Address Translation) mode, and bridge mode.

[0007] On the cloud infrastructure platform, faced with different types of physical network cards, different network virtualization strategies, and the way virtual machines use the network, if the operation and maintenance personnel manage network resources based on virtual machines, there will be management difficulties, network resources will not be released, network resource allocation is unreasonable, and other problems will lead to low network resource utilization. It will also cause repeated allocation of network resources, resulting in network congestion and the failure of virtual machine startup. Summary of the invention

[0008] The present invention provides a method for intelligently scheduling network cards under a cluster, the purpose of which is to improve the utilization rate of network resources and reduce the phenomenon of startup failure of virtual machines due to failure to find network resources.

[0009] In order to achieve the above-mentioned object, the present invention provides a method for intelligent scheduling of network cards under a cluster, which is applied to a cloud infrastructure platform. The cloud infrastructure platform includes a cluster consisting of multiple servers, a network management device, and multiple network resource monitoring devices. One network resource monitoring device corresponds to one server, and each server includes multiple physical network cards.

[0010] The network card intelligent scheduling method includes:

[0011] Obtain a list of servers in the cluster, network resources and virtualization types of each server, form multiple network resource pools of different types, and deploy multiple message queues created simultaneously in each network resource pool respectively, and the network resource monitoring device communicates with the network management device through the message queue;

[0012] For each server in the cluster, use the corresponding network resource monitoring device to collect statistics on the usage of network resources in the server, obtain statistical results, and allocate network resources according to the statistical results;

[0013] The network management device selects all network resource pools that meet the requirements of the virtual machines to be scheduled from all network resource pools according to the statistical results and the message queue;

[0014] The network management device selects a target server for the virtual machine to be scheduled from all network resource pools that meet the requirements of the virtual machine to be scheduled according to the scheduling strategy, and sends the selection result to the network resource monitoring device corresponding to the target server;

[0015] The network resource monitoring device schedules the virtual machine to be scheduled to the target physical network card in the target server according to the network type label and the number of physical network cards configured for the virtual machine to be scheduled and the scoring rule.

[0016] Furthermore, multiple different types of network resource pools are formed, including:

[0017] A plurality of shared bridging network resource pools and a plurality of exclusive transparent transmission network resource pools are respectively formed according to the virtualization type, and each network resource pool includes at least one message queue and a plurality of network resource monitoring devices.

[0018] Furthermore, the network card intelligent scheduling method also includes:

[0019] Divide the servers in the cluster into a control node and multiple computing nodes;

[0020] The network management device is deployed on the control node, and is used to collect and analyze the data of the servers on each computing node in the message queue, select a target server for the virtual machine to be scheduled in a shared bridge network resource pool or an exclusive transparent network resource pool that meets the needs of the virtual machine to be scheduled based on the analysis results, and schedule the virtual machine to be scheduled to the target server;

[0021] The network resource monitoring device is deployed on the computing node. The network resource monitoring device corresponds to the computing node one by one. It is used to collect statistics on the network resource usage of the server on the computing node, and report the network resource statistics of the server on each computing node to the network management device, and schedule the virtual machine to be scheduled to the target physical network card in the target server;

[0022] The message queue is deployed on the computing node, and the message queue corresponds to the computing node one by one.

[0023] Furthermore, message queues use distributed queue technology and asynchronous communication methods.

[0024] Further, the network management device includes a data center module and a scheduling service module;

[0025] The data center module communicates with each network resource monitoring device through a message queue to analyze the data collected from the servers on each computing node from each message queue;

[0026] The scheduling service module communicates with the data center module to select a target server for the virtual machine to be scheduled in a shared bridge network resource pool or an exclusive transparent network resource pool that meets the needs of the virtual machine to be scheduled according to the analysis results, and schedule the virtual machine to be scheduled to the target server.

[0027] Further, each network resource monitoring device includes a resource acquisition module and a resource allocation module;

[0028] The resource collection module is used to collect statistics on the usage of network resources on the computing nodes and store the statistical results in the message queue;

[0029] The resource allocation module is used to schedule the virtual machine to be scheduled to the target physical network card in the target server according to the statistical results, and is also used to segment or virtualize the physical network card according to different virtual types.

[0030] Specifically, the network resources on the computing nodes include:

[0031] The model of the physical network card, the usage of single-root input / output virtualization segmentation, the shared network I / O throughput, the number of shared network virtual machines allocated, and the average number of packet losses per hour.

[0032] Further, according to the analysis result, a target server is selected for the virtual machine to be scheduled in a shared bridge network resource pool or an exclusive transparent network resource pool that meets the requirements of the virtual machine to be scheduled, including:

[0033] Scoring all servers in the shared bridge network resource pool that meet the requirements of the virtual machine to be scheduled, respectively, to obtain a first scoring result, and selecting the server with the highest score in the first scoring result to obtain a first candidate server;

[0034] Scoring all servers in the exclusive transparent network resource pool that meet the needs of the virtual machine to be scheduled, respectively, to obtain a second scoring result, and selecting the server with the highest score in the second scoring result to obtain a second candidate server;

[0035] The scores of the first candidate server and the second candidate server are compared, and the server with the largest score is selected as the target server.

[0036] Further, the scoring calculation expression for scoring all servers in the shared bridge network resource pool that meet the needs of the virtual machine to be scheduled is:

[0037] Mark1=HVm*HW1+HIn*HW2+HLvn*HW3

[0038] Among them, Mark1 represents the first scoring result, HVm represents the allocated number of shared network virtual machines, HW1 represents the weight corresponding to the allocated number of shared network virtual machines, HIn represents the shared network I / O throughput, HW2 represents the weight corresponding to the shared network I / O throughput, HLvn represents the average number of packet losses per hour, and HW3 represents the weight corresponding to the average number of packet losses per hour.

[0039] Furthermore, the scoring calculation expression for scoring all servers in the exclusive transparent network resource pool that meet the needs of the virtual machine to be scheduled is:

[0040] Mark2=HWu*HW0+HWu*HW1

[0041] Among them, Mark2 represents the second scoring result, HWu represents the usage of a single input / output virtualization partition, and HW0 represents the weight corresponding to the usage of a single input / output virtualization partition.

[0042] The above scheme of the present invention has the following beneficial effects:

[0043] The present invention forms multiple network resource pools, and deploys multiple message queues created synchronously in each network resource pool respectively; for each server in the cluster, the corresponding network resource monitoring device is used to count the usage of network resources in the server, obtain statistical results, and allocate network resources according to the statistical results; the network management device selects all network resource pools that meet the needs of the virtual machines to be scheduled from all network resource pools according to the statistical results and the message queues; the network management device selects a target server for the virtual machine to be scheduled from all network resource pools that meet the needs of the virtual machines to be scheduled, and sends the selection result to the network resource monitoring device corresponding to the target server; the network resource monitoring device schedules the virtual machine to be scheduled to the target physical network card in the target server according to the network type label and the number of physical network cards configured for the virtual machine to be scheduled and the scoring rule; compared with the prior art, the present invention counts the load of each network resource pool according to the network resource monitoring device, and dynamically schedules the virtual machine to be scheduled to the optimal server by using the network control device, thereby improving the utilization rate of network resources and reducing the phenomenon that the virtual machine fails to start up due to the inability to find network resources.

[0044] Other beneficial effects of the present invention will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of a flow chart of an embodiment of the present invention;

[0046] Figure 2 is a structural diagram of an embodiment of the present invention;

[0047] Figure 3 The figure is a schematic diagram of the scheduling process of a virtual machine to be scheduled in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] In the description of the present invention, the terms “first”, “second” and “third” are used for descriptive purposes only and should not be understood as indicating or implying relative importance.

[0050] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installation", "connection" and "connection" should be understood in a broad sense, for example, it can be a locking connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0051] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0052] The present invention aims at solving the existing problems and provides a method for intelligently scheduling network cards based on clusters.

[0053] like Figure 1-3 As shown, an embodiment of the present invention provides a method for intelligent scheduling of network cards based on a cluster, which is applied to a cloud infrastructure platform. The cloud infrastructure platform includes a cluster consisting of multiple servers, a network management device, and multiple network resource monitoring devices. One network resource monitoring device corresponds to one server, and each server includes multiple physical network cards.

[0054] The network card intelligent scheduling method includes:

[0055] S1: Obtain a list of servers in the cluster, network resources and virtualization types of each server, form multiple network resource pools of different types, and deploy multiple message queues created simultaneously in each network resource pool respectively. The network resource monitoring device communicates with the network management device through the message queues;

[0056] S2: For each server in the cluster, use the corresponding network resource monitoring device to collect statistics on the usage of network resources in the server, obtain statistical results, and allocate network resources according to the statistical results;

[0057] S3: The network management device selects all network resource pools that meet the requirements of the virtual machines to be scheduled from all network resource pools according to the statistical results and the message queue;

[0058] S4, the network management device selects a target server for the virtual machine to be scheduled from all network resource pools that meet the requirements of the virtual machine to be scheduled according to the scheduling policy, and sends the selection result to the network resource monitoring device corresponding to the target server;

[0059] S5: The network resource monitoring device schedules the virtual machine to be scheduled to the target physical network card in the target server according to the network type label and the number of physical network cards configured for the virtual machine to be scheduled and the scoring rule.

[0060] Specifically, the cloud infrastructure platform also includes a cluster manager for centralized management of multiple target servers. The cluster function is enabled in the cluster manager, and it is ensured that all servers have joined the cluster. The intelligent scheduling function of the cluster's network card is enabled in the cluster manager, so that it can automatically manage and schedule network resources.

[0061] It should be noted that, in the embodiments of the present invention, a cluster is a unified computer composed of multiple servers with the same functions, which implement the same business and provide computing, network, storage and other resources to the outside world, and has the characteristics of scalability and high availability; a network resource pool is a group of physical network cards of servers into an independent network resource pool, and the servers in the network resource pool can be all the servers in the cluster or some of the servers in the cluster, and the resources in the network resource pool can be the physical network cards of all the servers in the cluster or some of the servers in the cluster. The advantage of resource pooling is that resources are allocated on demand, resources are unlimited, and a virtual resource pool can be expanded / reduced as needed.

[0062] In an embodiment of the present invention, the virtual machine starts the network automatic scheduling function, the prerequisite is that a network resource pool already exists in the cluster. If not, a network resource pool needs to be established. When the virtual machine is created, the corresponding network resource pool and the number of virtual network cards are selected according to the business type. When the virtual machine is started, virtual network resources are requested from the network management device according to the configuration file.

[0063] Specifically, multiple different types of network resource pools are formed, including:

[0064] A plurality of shared bridging network resource pools and a plurality of exclusive transparent transmission network resource pools are respectively formed according to the virtualization type, and each network resource pool includes at least one message queue and a plurality of network resource monitoring devices.

[0065] In an embodiment of the present invention, under the condition that the cluster function of the cloud infrastructure platform has been turned on, the operation and maintenance personnel create different types of network resource pools and generate message queues based on the actual business scale based on the cluster dimension, and then select the network virtualization type, and divide the network resource pool into a shared bridging network resource pool and an exclusive transparent network resource pool according to the usage scenario, and select some or all of the idle physical network cards in the cluster, and send the network resource pool creation information to the network management device and the network resource monitoring device.

[0066] Specifically, the network card intelligent scheduling method also includes:

[0067] Divide the servers in the cluster into a control node and multiple computing nodes;

[0068] The network management device is deployed on the control node, and is used to collect and analyze the data of the servers on each computing node in the message queue, select a target server for the virtual machine to be scheduled in a shared bridge network resource pool or an exclusive transparent network resource pool that meets the needs of the virtual machine to be scheduled based on the analysis results, and schedule the virtual machine to be scheduled to the target server;

[0069] The network resource monitoring device is deployed on the computing node. The network resource monitoring device corresponds to the computing node one by one. It is used to collect statistics on the network resource usage of the server on the computing node, and report the network resource statistics of the server on each computing node to the network management device, and schedule the virtual machine to be scheduled to the target physical network card in the target server;

[0070] The message queue is deployed on the computing node, and the message queue corresponds to the computing node one by one.

[0071] It should be noted that the network management device is a process or program installed on the control node, which is used to collect and analyze the data of the servers on each computing node in the message queue, and select the target server for the virtual machine to be scheduled in the shared bridge network resource pool or the exclusive transparent network resource pool that meets the needs of the virtual machine to be scheduled based on the analysis results, and schedule the virtual machine to be scheduled to the target server to maximize the performance of the network; the network resource monitoring device is a process or program installed on the computing node, which is used to count the network resource usage of the servers on the computing node, and report the network resource statistics of the servers on each computing node to the network management device, and schedule the virtual machine to be scheduled to the target physical network card in the target server.

[0072] Most preferably, the message queue uses distributed queue technology to ensure the reliability and high concurrency of communication between modules, while also being responsible for communication between modules through asynchronous communication.

[0073] Most preferably, the network management device includes a data center module and a scheduling service module;

[0074] The data center module communicates with each network resource monitoring device through a message queue to analyze the data collected from the servers on each computing node from each message queue;

[0075] The scheduling service module communicates with the data center module to select a target server for the virtual machine to be scheduled in a shared bridge network resource pool or an exclusive transparent network resource pool that meets the needs of the virtual machine to be scheduled according to the analysis results, and schedule the virtual machine to be scheduled to the target server.

[0076] In an embodiment of the present invention, when the network management device receives information for creating a network resource pool, it obtains a server list and a list of physical network cards and a virtualization type in each server, generates a network resource pool identifier corresponding to the virtualization type, and sends data carrying the network resource pool identifier, the list of physical network cards, and the virtualization type to the network resource monitoring device.

[0077] Most preferably, each network resource monitoring device includes a resource acquisition module and a resource allocation module;

[0078] The resource collection module is used to collect statistics on the usage of network resources on the computing nodes and store the statistical results in the message queue;

[0079] The resource allocation module is used to schedule the virtual machine to be scheduled to the target physical network card in the target server according to the statistical results, and is also used to segment or virtualize the physical network card according to different virtual types.

[0080] In an embodiment of the present invention, when the network resource monitoring device receives the information for creating a network resource pool and data carrying the network resource pool identifier, the physical network card list, and the virtualization type, the resource allocation module processes the network resource pool according to the virtualization type and the physical network card list; for an exclusive transparent network resource pool, the physical network card is divided into multiple independent network cards according to the model and configuration file of the physical network card, and the corresponding type labels are marked, and they are uniformly managed and scheduled by the network management device; for a shared bridge network resource pool, a corresponding virtual switch is created, bound to the specified physical network card, responsible for the network communication of the virtual machines on this server, and marked with the corresponding type label.

[0081] The network management device receives a request for virtual network resources from a virtual machine and preliminarily selects all network resource pools that meet the requirements based on the virtualization type tag. If not, it returns network resources that do not have this type of tag. The virtual machine fails to start and prompts whether to reselect the network type tag. For resource pools with different types of tags, the server's scoring criteria are different, and each type of indicator has a different fixed weight. The network resources on the computing node are used as indicators, including:

[0082] The model of the physical network card, the usage of single-root input / output virtualization segmentation, the shared network I / O throughput, the number of shared network virtual machines allocated, and the average number of packet losses per hour.

[0083] It should be noted that the usage of single-root input / output virtualization segmentation refers to the number of physical network cards in the same server after segmentation, and also refers to the number of spatial network cards in the same server;

[0084] Since the functions of physical network cards are different, the functions of different network card models are also different. Therefore, in order to determine the number of idle network cards, you need to first determine the model of the physical network card;

[0085] Shared network I / O throughput refers to the I / O throughput of the network card in the same server, which is averaged per hour;

[0086] The number of virtual machines allocated to a shared network refers to the number of virtual machines running on the same network card in the same server.

[0087] The average hourly packet loss rate refers to the number of packet losses of the network card in the same server.

[0088] In the embodiment of the present invention, when resources are sufficient, the optimal computing node is selected in the network resource pool, mainly based on the number of host physical network cards in the network resource pool, the number of idle sriov network cards after segmentation, the io throughput of the shared-bridge mode network card, and the average number of packet losses per hour. Each item is counted according to the idle resources. The more idle resources, the higher the score. The lower the io throughput and the number of packet losses, the higher the score. The server with the highest comprehensive score is selected, and the optimal server is selected to send a message to the network resource monitoring device.

[0089] Specifically, according to the analysis result, a target server is selected for the virtual machine to be scheduled in a shared bridge network resource pool or an exclusive transparent network resource pool that meets the requirements of the virtual machine to be scheduled, including:

[0090] Scoring all servers in the shared bridge network resource pool that meet the requirements of the virtual machine to be scheduled, respectively, to obtain a first scoring result, and selecting the server with the highest score in the first scoring result to obtain a first candidate server;

[0091] Scoring all servers in the exclusive transparent network resource pool that meet the needs of the virtual machine to be scheduled, respectively, to obtain a second scoring result, and selecting the server with the highest score in the second scoring result to obtain a second candidate server;

[0092] Compare the scores of the first candidate server and the second candidate server, and select the server with the largest score as the target server. The scheduling goal is to schedule the virtual machines to be scheduled to different physical network cards in the target server, so that all network card resources in the server can achieve dynamic load balancing.

[0093] Further, the scoring calculation expression for scoring all servers in the shared bridge network resource pool that meet the needs of the virtual machine to be scheduled is:

[0094] Mark1=HVm*HW1+HIn*HW2+HLvn*HW3

[0095] Among them, Mark1 represents the first scoring result, HVm represents the allocated number of shared network virtual machines, HW1 represents the weight corresponding to the allocated number of shared network virtual machines, HIn represents the shared network I / O throughput, HW2 represents the weight corresponding to the shared network I / O throughput, HLvn represents the average number of packet losses per hour, and HW3 represents the weight corresponding to the average number of packet losses per hour.

[0096] Furthermore, the scoring calculation expression for scoring all servers in the exclusive transparent network resource pool that meet the needs of the virtual machine to be scheduled is:

[0097] Mark2=HWu*HW0+HVm*HW1

[0098] Among them, Mark2 represents the second scoring result, HWu represents the usage of a single input / output virtualization partition, and HW0 represents the weight corresponding to the usage of a single input / output virtualization partition.

[0099] It should be noted that after the virtual machine to be scheduled is shut down, the network resource monitoring device monitors the shutdown of the virtual machine on the host, releases and recycles the network resources used by the virtual machine, reports to the network management device of the control node, and updates the network resource usage information on the node.

[0100] The embodiment of the present invention forms multiple network resource pools, and deploys multiple message queues created synchronously in each network resource pool; for each server in the cluster, the corresponding network resource monitoring device is used to count the usage of network resources in the server, obtain statistical results, and allocate network resources according to the statistical results; the network management device selects all network resource pools that meet the needs of the virtual machines to be scheduled from all network resource pools according to the statistical results and the message queues; the network management device selects a target server for the virtual machine to be scheduled from all network resource pools that meet the needs of the virtual machines to be scheduled, and sends the selection result to the network resource monitoring device corresponding to the target server; the network resource monitoring device schedules the virtual machine to be scheduled to the target physical network card in the target server according to the network type label and the number of physical network cards configured for the virtual machine to be scheduled according to the scoring rule; compared with the prior art, the embodiment of the present invention counts the load of each network resource pool according to the network resource monitoring device, and uses the network control device to dynamically schedule the virtual machine to be scheduled to the optimal server, thereby improving the utilization rate of network resources and reducing the phenomenon that the virtual machine fails to start up due to the inability to find network resources.

[0101] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for intelligent scheduling of network cards based on cluster, characterized in that: Applied to a cloud infrastructure platform, the cloud infrastructure platform includes a cluster consisting of multiple servers, a network management device, and multiple network resource monitoring devices, one network resource monitoring device corresponds to one server, and each server includes multiple physical network cards; The network card intelligent scheduling method comprises: Obtain a list of servers in the cluster, network resources and virtualization types of each server, form multiple network resource pools of different types, and deploy multiple message queues created simultaneously in each network resource pool, wherein the network resource monitoring device communicates with the network management device through the message queues; For each server in the cluster, using a corresponding network resource monitoring device to collect statistics on the usage of network resources in the server, obtain statistical results, and allocate network resources according to the statistical results; The network management device selects all network resource pools that meet the requirements of the virtual machines to be scheduled from all network resource pools according to the statistical results and the message queue; The network management device selects a target server for the virtual machine to be scheduled from all network resource pools that meet the requirements of the virtual machine to be scheduled according to the scheduling strategy, and sends the selection result to the network resource monitoring device corresponding to the target server; The network resource monitoring device schedules the virtual machine to be scheduled to the target physical network card in the target server according to the network type label and the number of physical network cards configured for the virtual machine to be scheduled and the scoring rule.

2. The method for intelligently scheduling network cards based on clustering according to claim 1, characterized in that: Build multiple network resource pools of different types, including: A plurality of shared bridging network resource pools and a plurality of exclusive transparent transmission network resource pools are respectively formed according to the virtualization type, and each network resource pool includes at least one message queue and a plurality of network resource monitoring devices.

3. The method for intelligently scheduling network cards based on clustering according to claim 2 is characterized in that: The network card intelligent scheduling method also includes: Dividing the servers in the cluster into a control node and multiple computing nodes; The network management device is deployed on the control node, and is used to collect and analyze the data of the servers on each computing node in the message queue, select a target server for the virtual machine to be scheduled in a shared bridge network resource pool or an exclusive transparent network resource pool that meets the requirements of the virtual machine to be scheduled based on the analysis result, and schedule the virtual machine to be scheduled to the target server; The network resource monitoring device is deployed on the computing node. The network resource monitoring device corresponds to the computing node one by one and is used to collect statistics on the network resource usage of the servers on the computing node, and report the network resource statistics results of the servers on each computing node to the network management device, and schedule the virtual machine to be scheduled to the target physical network card in the target server.

4. The method for intelligently scheduling network cards based on clustering according to claim 3 is characterized in that: The message queue adopts distributed queue technology and asynchronous communication mode.

5. The method for intelligently scheduling network cards based on clustering according to claim 4 is characterized in that: The network management device includes a data center module and a scheduling service module; The data center module communicates with each of the network resource monitoring devices through a message queue, and is used to analyze the data of the servers on each computing node collected from each message queue; The scheduling service module communicates with the data center module to select a target server for the virtual machine to be scheduled from a shared bridging network resource pool or an exclusive transparent network resource pool that meets the requirements of the virtual machine to be scheduled according to the analysis results, and schedule the virtual machine to be scheduled to the target server.

6. The method for intelligently scheduling network cards based on clustering according to claim 5, characterized in that: Each of the network resource monitoring devices includes a resource acquisition module and a resource allocation module; The resource collection module is used to collect statistics on the usage of network resources on the computing nodes and store the statistical results in the message queue; The resource allocation module is used to schedule the virtual machine to be scheduled to the target physical network card in the target server according to the statistical results, and is also used to segment or virtualize the physical network card according to different virtual types.

7. The method for intelligently scheduling network cards based on clustering according to claim 6, characterized in that: The network resources on the computing node include: The model of the physical network card, the usage of single-root input / output virtualization segmentation, the shared network I / O throughput, the number of shared network virtual machines allocated, and the average number of packet losses per hour.

8. The method for intelligently scheduling network cards based on clustering according to claim 7, characterized in that: According to the analysis result, a target server is selected for the virtual machine to be scheduled in a shared bridge type network resource pool or an exclusive transparent transmission type network resource pool that meets the requirements of the virtual machine to be scheduled, including: Scoring all servers in the shared bridge network resource pool that meet the requirements of the virtual machine to be scheduled, respectively, to obtain a first scoring result, and selecting the server with the highest score in the first scoring result to obtain a first candidate server; Scoring all servers in the exclusive transparent network resource pool that meet the requirements of the virtual machine to be scheduled, respectively, to obtain a second scoring result, and selecting the server with the highest score in the second scoring result to obtain a second server to be selected; The scores of the first candidate server and the second candidate server are compared, and the server with the largest score is selected as the target server.

9. The method for intelligently scheduling network cards based on clustering according to claim 8, characterized in that: The scoring calculation expression for scoring all servers in the shared bridge network resource pool that meet the needs of the virtual machines to be scheduled is: Mark1=HVm*HW1+HIn*HW2+HLvn*HW3 Among them, Mark1 represents the first scoring result, HVm represents the allocated number of shared network virtual machines, HW1 represents the weight corresponding to the allocated number of shared network virtual machines, HIn represents the shared network I / O throughput, HW2 represents the weight corresponding to the shared network I / O throughput, HLvn represents the average number of packet losses per hour, and HW3 represents the weight corresponding to the average number of packet losses per hour.

10. The method for intelligently scheduling network cards based on clustering according to claim 9, characterized in that: The scoring calculation expression for scoring all servers in the exclusive transparent network resource pool that meet the needs of the virtual machines to be scheduled is: Mark2=HWu*HW0+HVm*HW1 Among them, Mark2 represents the second scoring result, HWu represents the usage of single-root input / output virtualization segmentation, and HW0 represents the weight corresponding to the usage of single-root input / output virtualization segmentation.

Images