Cloud computing virtual machine scheduling method suitable for railway communication cloud

Abstract

The invention provides a cloud computing virtual machine scheduling algorithm suitable for railway communication cloud, and aims to solve the defects of an existing scheduling algorithm in processing the requirements of high real-time performance and high security in a railway communication system. According to the algorithm, accurate scheduling is performed based on the model and bandwidth attribute of the PCI network card, so that the virtual machine can directly access the physical network card to reduce delay and improve the data transmission rate. And meanwhile, the algorithm realizes network isolation between the virtual machines through physical switch configuration, so that the security of the system is guaranteed. When virtual machines are created in batches, the scheduling algorithm can schedule physical server nodes meeting topology requirements in batches according to a network topology structure defined by a user, and correct connection between the virtual machines and the network topology is ensured. Through the algorithm, the railway communication system can meet the requirements for low delay, high bandwidth, security isolation and batch scheduling in a complex network environment, and the efficiency and flexibility of virtual machine scheduling are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud computing, and in particular to a cloud computing virtual machine scheduling method suitable for a railway communication cloud. Background Art

[0002] Railway communication system is the core technology to ensure the safety of train operation, and has extremely strict requirements on network performance. With the advancement of railway modernization, a large amount of real-time data generated during train operation must be processed and transmitted in a very short time, which directly affects the safety and efficiency of train operation. Therefore, the railway communication system has put forward extremely high requirements on the low latency, high bandwidth, stability and reliability of the network. However, traditional cloud computing scheduling technology cannot fully meet these strict performance requirements.

[0003] In a cloud computing environment, virtual machine scheduling technology is often used to reasonably allocate server resources to improve efficiency, and virtual network technology is used to ensure flexibility and scalability. However, virtual networks have certain performance loss problems, especially in scenarios with high real-time requirements. This performance loss may have a serious impact on train operation. For example, increased data transmission delays may result in control instructions not being issued in a timely manner, affecting the safety of train operation.

[0004] In order to solve this delay problem, PCI pass-through technology is introduced in cloud computing environments. This technology allows virtual machines to directly access physical network card resources, avoiding performance loss in the virtualization layer. PCI pass-through technology bypasses the virtual network layer and directly maps physical network devices to virtual machines, greatly reducing data transmission delays and increasing data transmission rates. However, although PCI network card pass-through technology has a significant effect on performance improvement, it also brings new problems, especially in terms of network isolation and security.

[0005] Traditional virtual network technology can achieve isolation and security protection between virtual machines through security groups, but PCI pass-through technology does not support the security group function in virtual networks, which makes the isolation problem between virtual machines more complicated. In order to solve this problem, it is necessary to rely on the network isolation mechanism at the physical level. Network isolation is usually achieved by configuring physical switches, which puts higher requirements on network architecture design. In railway communication systems, due to the complex network environment and high security requirements, the configuration of the physical network must not only meet the isolation requirements, but also ensure rapid switching when a network failure occurs to ensure network continuity and high reliability.

[0006] In addition, in the railway communication system, the deployment location of the virtual machine must be closely related to the network topology. This means that in the scheduling process of the virtual machine, in addition to considering the load balancing and availability of resources, it is also necessary to accurately schedule the location of the virtual machine according to the specific network topology of the railway communication system. Through this scheduling, the virtual machine can correctly connect to the specified physical network card and network segment, thereby ensuring the isolation, real-time and high efficiency of the network.

[0007] Most of the existing cloud computing scheduling algorithms only allocate virtual machines to appropriate computing nodes based on resource requirements, load balancing and availability, which cannot meet the special requirements of railway communication systems for network performance and isolation. Especially in scenarios with complex network topologies such as railway communication systems, traditional scheduling algorithms cannot perform batch scheduling based on the connection requirements of network topology when creating virtual machines in batches, nor can they flexibly handle PCI network card properties when scheduling virtual machines. This makes the development of a customized virtual machine scheduling algorithm that can schedule according to PCI device properties and network topology a necessary means to solve these problems.

[0008] Therefore, in response to the special needs of the railway communication system, the present invention proposes a cloud computing virtual machine scheduling algorithm suitable for the railway communication cloud, which solves the shortcomings of the existing scheduling algorithms in terms of network performance, virtual machine isolation, and batch scheduling, and ensures that the system can achieve efficient virtual machine scheduling under the premise of safety and stability. Summary of the invention

[0009] The purpose of the present invention is to provide a cloud computing virtual machine scheduling method suitable for railway communication cloud in view of the shortcomings of the prior art, so as to solve the problems raised in the background technology.

[0010] To achieve the above object, the present invention provides the following technical solutions:

[0011] A cloud computing virtual machine scheduling method applicable to a railway communication cloud, the method comprising the following steps:

[0012] Step 1: Collect the hardware resource information of each physical server in the cloud platform, including basic information such as CPU, memory, PCI network card model, bandwidth, physical location, and network connection topology;

[0013] Step 2: The user inputs and defines the network topology of the railway communication system, wherein the topology includes the network type, topology form, device type and its network connection requirements. The defined network topology will determine the network connection and resource allocation between virtual machines.

[0014] Step 3: Generate a resource requirement list of the virtual machine based on the user-defined network topology and resource information of the physical server, the resource requirement list including the CPU, memory, PCI network card bandwidth, network interface type, connection relationship between virtual machines, etc. required by the virtual machine;

[0015] Step 4: Based on the resource requirement list of the virtual machine, the scheduling algorithm is used to select physical server nodes that meet the requirements. The algorithm first selects based on the PCI network card attributes (such as model and bandwidth) to ensure that the physical server meets the bandwidth and performance requirements of the virtual machine;

[0016] Step 5: After selecting the physical servers that meet the PCI network card attribute requirements, further select the physical servers according to the network topology requirements of the virtual machines through a batch scheduling algorithm to ensure that the network connection between the virtual machines meets the predefined topology structure;

[0017] Step 6: Create virtual machines in batches on the physical server nodes selected through the above screening steps, and establish a correct network connection between each virtual machine and its corresponding physical network card and network connection topology to ensure that the virtual machines can operate normally and meet the network performance and isolation requirements of the railway communication system;

[0018] Step 7: After completing the batch creation of virtual machines, the deployment information of the virtual machines is returned, including the physical server on which they run, the PCI network card used, and the network connection information for further management and maintenance.

[0019] As a preferred technical solution of the present invention: the scheduling algorithm includes the following formula to perform scheduling based on the PCI network card bandwidth:

[0020]

[0021] Among them, bwpci represents the bandwidth of the PCI network card of the current host node, and bwmin is the minimum bandwidth required by the virtual machine. The score of the PCI network card attribute is calculated by this formula, and the host nodes that meet the conditions are added to the schedulable list.

[0022] As a preferred technical solution of the present invention: the scheduling method extends the Nova scheduler to create a new filter class 'DPciPassthroughFilter', which filters the physical host nodes according to the model and bandwidth information of the PC1 network card.

[0023] As a preferred technical solution of the present invention: the filter class is implemented by inheriting the 'nova.scheduler.filters.BaseHostFilter' class and implementing the 'host_passes' method therein, and scheduling the nodes that meet the requirements by obtaining the PCI network card model and bandwidth information of each host node.

[0024] As a preferred technical solution of the present invention: the batch scheduling algorithm includes the following formula to perform scheduling based on network topology:

[0025]

[0026] Among them, di is the network distance between each host node, dideal is the ideal network distance, and the network topology matching degree of multiple host nodes is calculated by this formula to ensure that the scheduling result meets the network connection requirements.

[0027] As a preferred technical solution of the present invention: the batch scheduling algorithm extends the Nova scheduler, creates a batch filter class 'BaseBatchHostFilter', and batch filters the host node combinations that meet the network topology requirements through the interface 'hosts_passes'.

[0028] As a preferred technical solution of the present invention: the virtual machine resource requirement list includes the following information: CPU resource requirements, memory resource requirements, physical properties of the PCI network card, network connection relationships between virtual machines, etc.

[0029] As a preferred technical solution of the present invention: the scheduling algorithm combines the native scheduling algorithm of the cloud platform with the PCI network card attribute scheduling and network topology batch scheduling functions to calculate the optimal deployment location of the virtual machine in the physical server.

[0030] As a preferred technical solution of the present invention: when executing scheduling, according to the formula:

[0031] f(node s election) = α·f(pci s core)+β·ftopology m atch)

[0032] Among them, α and β are the weight coefficients of the matching degree between PCl attributes and network topology, respectively. The comprehensive score of each host node is calculated, and finally the node with the highest score is selected for virtual machine scheduling.

[0033] As a preferred technical solution of the present invention: the scheduling algorithm dynamically updates the resource status of the physical server in real time during the scheduling process, ensuring that the scheduling result can adapt to real-time changes in network and hardware resources.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. The present invention introduces PCI direct pass technology and accurately screens PCI network card attributes (such as bandwidth and model) during virtual machine scheduling, significantly reducing the delay problem in data transmission and improving network performance. By directly accessing the physical network card, the performance loss caused by the virtualization layer is avoided, ensuring that the virtual machines in the railway communication system can efficiently process and transmit big data, and realizing the real-time data processing requirements during train operation.

[0036] 2. Although PCI direct technology does not support traditional virtual network security group functions, the present invention ensures the isolation and security between virtual machines through the configuration of physical switches, combined with network topology and scheduling algorithms. When creating virtual machines in batches, the scheduling algorithm realizes the precise deployment and network isolation of virtual machines based on the network topology of the physical layer, ensuring the security requirements of the railway communication system.

[0037] 3. The present invention can not only perform scheduling based on PCI attributes, but also expand the batch scheduling function, so that it can batch schedule virtual machines according to the specific network topology of the railway communication system. Through the network topology matching algorithm, it ensures that the deployment of virtual machines meets the specific network connection requirements, improves the flexibility and accuracy of scheduling, and thus meets the high standard requirements of the railway communication system for real-time performance and reliability in complex network environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The present invention is a method flow chart of a cloud computing virtual machine scheduling method applicable to a railway communication cloud. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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.

[0040] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings and multiple embodiments.

[0041] Example 1: Virtual machine scheduling based on PCI network card attributes

[0042] See also Figure 1In the deployment of the railway communication cloud, a virtual machine needs to be used to process high-bandwidth video streaming data, with a bandwidth requirement of at least 10Gbps, and the virtual machine also needs low-latency network transmission. To meet this requirement, the system administrator defines a resource requirement list for the virtual machine, specifically describing the CPU, memory, and network card bandwidth requirements (above 10Gbps) required by the virtual machine.

[0043] First, the cloud platform collects resource information of all physical servers, including the model and bandwidth of PCI network cards. According to the PCI network card attribute scheduling algorithm in the claim, the following formula is used to calculate PCI bandwidth:

[0044]

[0045] Among them, bw pci bw is the bandwidth of the PCI network card on the physical server. min This formula scores the PCI network card bandwidth of all physical servers and only selects physical server nodes that meet the bandwidth requirement of 10 Gbps or above.

[0046] Through the filter 'DPciPassthroughFilter', physical server A with a bandwidth of 25Gbps is finally selected, and the virtual machine is scheduled to this server to ensure that the virtual machine can obtain sufficient network bandwidth to meet the efficient transmission of the video stream.

[0047] Example 2: Batch Scheduling Based on Network Topology

[0048] See also Figure 1 ,A railway communication system needs to deploy a set of virtual machines for real-time data synchronization and ,dispatching control between stations.

[0049] The system requires the network topology to be a star topology, the connection between virtual machines is communicated through a central server (master node), and the network transmission delay must be controlled within 10 milliseconds.

[0050] The administrator first defines the network topology of the system through the cloud platform, specifying the number of virtual machines, the network type (Ethernet) of each virtual machine, the device type (such as master node device, edge device, etc.) and the connection relationship.

[0051] Next, the cloud platform collects the network connection information of each physical server, including the physical distance between servers and network latency. According to the network topology requirements of the virtual machine, the scheduling algorithm matches the network topology using the following formula:

[0052]

[0053] Among them, di is the network distance between servers, d ideal The ideal network delay between virtual machines (10 milliseconds) is obtained through the batch scheduling algorithm BaseBatchHostFilter, which can meet the network delay requirements of virtual machines and conform to the star topology, and the virtual machines are batch-scheduled to these servers to ensure that each virtual machine can correctly connect to the master node device and meet the real-time data synchronization requirements.

[0054] Example 3: Scheduling of real-time adjustment of physical server resource status

[0055] See also Figure 1 ,In the railway communication cloud, as the real-time data transmission demand of ,train operation increases, the load of virtual machines on a certain server ,group gradually increases, resulting in resource usage approaching saturation.

[0056] At this time, the cloud platform needs to automatically adjust the deployment location of the virtual machine to avoid performance bottlenecks and maintain efficient operation of the system.

[0057] The cloud platform monitors the resource status of physical servers and finds that the CPU and memory usage of some servers exceeds 80%. According to the scheduling algorithm in the claim, the system will dynamically update the resource information of each physical server in real time and recalculate the optimal deployment location of the virtual machine. The comprehensive score is calculated using the following formula:

[0058] f(node s election) = α·f(pci s core)+β·f(topology m atch)

[0059] Among them, α and β are weight coefficients, reflecting the importance of PCl attributes and network topology, respectively.

[0060] This formula comprehensively considers the PCI network card bandwidth, network topology matching, and the current server load status. In the end, the system selected another physical server B, which has lower resource utilization and meets the network topology requirements.

[0061] The virtual machine automatically migrates to server B, maintaining the network performance of the railway communication system.

[0062] Example 4: Large-scale virtual machine deployment in railway communication cloud

[0063] See also Figure 1 A railway communication system needs to deploy a large-scale virtual machine group on a newly opened line to handle the big data analysis tasks generated during train operation. The system requires that all virtual machines must meet the bus topology and the network bandwidth requirement must be at least 20Gbps.

[0064] The administrator first defines the resource requirement list and bus topology of the virtual machine, and the cloud platform begins to collect resource information of the physical server. The scheduling algorithm first filters out physical server nodes with a bandwidth of 20Gbps or more through the 'DPciPassthroughFilter', and then, based on the bus network topology requirements, the batch scheduling algorithm selects the server node combination that can meet the network topology.

[0065] During the scheduling process, the cloud platform combines the PCI network card attributes and network topology structure and uses the following formula for comprehensive scoring

[0066] f(nod selection)=α·f(pciscore)+β·f(topology mach)

[0067] Finally, the system deployed a cluster of virtual machines in batches on multiple physical servers and automatically configured network connections to ensure that all virtual machines could be correctly connected according to the bus topology and meet the needs of big data analysis tasks.

[0068] Example 5: Fault Tolerance Mechanism in Railway Communication System

[0069] See also Figure 1 The high security and reliability of the railway communication system requires that when some physical servers fail, the virtual machines can be automatically migrated to other servers to maintain the normal operation of the system. To this end, the railway communication cloud deploys a scheduling algorithm based on the present invention to support automatic fault tolerance.

[0070] After a server C fails, the cloud platform automatically detects that the server is unavailable. The system monitors the resource status of the server and updates the resource information of other servers in real time. The scheduling algorithm is executed again, and the target server is reselected based on the resource status of the remaining available servers, PCI network card bandwidth, and network topology matching, and the affected virtual machines are automatically migrated to another server D that meets the conditions.

[0071] Through this fault-tolerant mechanism, the railway communication system can maintain service continuity when a server fails, and ensure that the network connection and performance of the virtual machine meet the preset requirements.

[0072] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in the field. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A cloud computing virtual machine scheduling method applicable to railway communication cloud, characterized in that: The method comprises the following steps: Step 1: Collect the hardware resource information of each physical server in the cloud platform, including basic information such as CPU, memory, PCI network card model, bandwidth, physical location, and network connection topology; Step 2: The user inputs and defines the network topology of the railway communication system, wherein the topology includes the network type, topology form, device type and its network connection requirements. The defined network topology will determine the network connection and resource allocation between virtual machines. Step 3: Generate a resource requirement list of the virtual machine based on the user-defined network topology and resource information of the physical server, wherein the resource requirement list includes the CPU, memory, PCI network card bandwidth, network interface type, and connection relationship between virtual machines required by the virtual machine; Step 4: Based on the resource requirement list of the virtual machine, a scheduling algorithm is used to select physical server nodes that meet the requirements. The algorithm first selects based on the PCI network card attributes; Step 5: After selecting the physical servers that meet the PCI network card attribute requirements, further select the physical servers through a batch scheduling algorithm according to the network topology requirements of the virtual machine; Step 6: Create virtual machines in batches on the physical server nodes selected through the above screening steps, and establish a correct network connection between each virtual machine and its corresponding physical network card and network connection topology to ensure that the virtual machines can operate normally and meet the network performance and isolation requirements of the railway communication system; Step 7: After the batch creation of virtual machines is completed, the deployment information of the virtual machines is returned, including the physical server on which they are running, the PCI network card used, and the network connection information.

2. The cloud computing virtual machine scheduling method applicable to the railway communication cloud according to claim 1 is characterized in that: The scheduling algorithm includes the following formula to perform scheduling based on PCI network card bandwidth: Among them, bw pci Indicates the bandwidth of the PCl network card of the current host node, bw min The minimum bandwidth required by the virtual machine is calculated by this formula to score the PCI network card attributes, and the host nodes that meet the conditions are added to the schedulable list.

3. The cloud computing virtual machine scheduling method applicable to the railway communication cloud according to claim 2 is characterized in that: The scheduling method extends the Nova scheduler to create a new filter class 'DPciPassthroughFilter', which filters the physical host nodes according to the model and bandwidth information of the PC1 network card.

4. The cloud computing virtual machine scheduling method according to claim 3, characterized in that: The filter class is implemented by inheriting the 'nova.scheduler.filters.BaseHostFilter' class and implementing the 'host_passes' method therein, and scheduling the nodes that meet the requirements by obtaining the PCI network card model and bandwidth information of each host node.

5. The cloud computing virtual machine scheduling method applicable to the railway communication cloud according to claim 1 is characterized in that: The batch scheduling algorithm includes the following formula to perform scheduling based on network topology: Among them, d i is the network distance between each host node, d ideal is the ideal network distance, and the network topology matching degree of multiple host nodes is calculated by this formula.

6. The cloud computing virtual machine scheduling method applicable to the railway communication cloud according to claim 5 is characterized in that: The batch scheduling algorithm extends the Nova scheduler, creates a batch filter class 'BaseBatchHostFilter', and batch filters the host node combinations that meet the network topology requirements through the interface 'hosts_passes'.

7. The cloud computing virtual machine scheduling method applicable to the railway communication cloud according to claim 1 is characterized in that: The virtual machine resource requirement list includes the following information: CPU resource requirements, memory resource requirements, physical properties of the PCI network card, and network connection relationships between virtual machines.

8. The cloud computing virtual machine scheduling method applicable to the railway communication cloud according to claim 1 is characterized in that: The scheduling algorithm combines the cloud platform's native scheduling algorithm with PCI network card attribute scheduling and network topology batch scheduling functions to calculate the optimal deployment location of the virtual machine in the physical server.

9. The cloud computing virtual machine scheduling method applicable to railway communication cloud according to claim 1 is characterized in that: When executing the scheduling, according to the formula: f(node s election)=α·f(pci s core)+β·f(topology m atch) Among them, α and β are the weight coefficients of the matching degree between PCl attributes and network topology, respectively. The comprehensive score of each host node is calculated, and finally the node with the highest score is selected for virtual machine scheduling.

10. The cloud computing virtual machine scheduling method applicable to the railway communication cloud according to claim 9 is characterized in that: The scheduling algorithm dynamically updates the resource status of the physical server in real time during the scheduling process, ensuring that the scheduling result can adapt to real-time changes in network and hardware resources.

Images