CN113886091A - Virtual machine migration method, system, equipment and storage medium - Google Patents

Abstract

The invention provides a virtual machine migration method, a virtual machine migration system, virtual machine migration equipment and a storage medium, wherein the method comprises the following steps: any host in the host group can collect the virtual machine load data of each host in the host group, under the condition that the virtual machine load data shows that the current host is an overloaded node, at least one non-overloaded target host is selected from the host group according to the virtual machine load data, at least one virtual machine is selected from the current host to the target host, and under the condition that the virtual machine load data shows that the current host is a non-overloaded node, the virtual machine migrated by other hosts is received and deployed at the current host. The problem of scheduling overload caused by centralized scheduling and migrating of the virtual machines by using the controller in the prior art can be solved, so that the problem of unavailability caused by waiting for migration of the virtual machines is avoided, the virtual machines can be more efficiently migrated in the host group, and the resource utilization rate of the virtual machines is improved.

Description

Virtual machine migration method, system, device and storage medium

technical field

The present invention relates to the field of network security, in particular to a virtual machine migration method, system, device and storage medium.

Background technique

With the development of computer technology, virtualization technology has been widely used. Among them, the most widely used is the virtualization segmentation technology, that is, running multiple virtual machines (Virtual Machine; VM) on one host, and between the host and multiple VMs, through the virtual machine monitor (Virtual Machine Monitor; VMM) Manage Central Processing Unit (CPU), memory, storage, network and other peripheral resources, VMM schedules and manages these physical resources, allocates these physical resources to multiple VMs, and realizes mutual isolation between VMs run.

The virtual machine is a simulated computer system with complete hardware system functions and running in an isolated environment, and is the object of resource scheduling. The host is the physical bearer of computing resources and the actual bearer of the virtual machine, such as a physical server. In order to effectively utilize the resources on each physical server in the cluster system and balance the load on each physical server, the virtual machine migration method is usually adopted to migrate some VMs on the physical server with more virtual machine load to other physical servers.

SUMMARY OF THE INVENTION

In view of the problems in the prior art, the purpose of the present invention is to provide a virtual machine migration method, system, device and storage medium, which overcomes the difficulties of the prior art and can solve the problem that the migration of virtual machines to a centralized scheduling mode is difficult to meet high load and large concurrency. To solve the problem of management and control requirements, improve the efficiency of virtual machine migration to improve resource utilization.

An embodiment of the present invention provides a virtual machine migration method, and the method is applied to a first host in a host group, including:

Collect virtual machine load data of each host in the host group;

When the virtual machine load data shows that the first host is an overloaded node, at least one second host that is not overloaded is selected from the host group according to the virtual machine load data, and at least one migrated virtual machine is selected from the first host and migrated out to the second host;

In the case that the virtual machine load data shows that the first host is a non-overloaded node, the migrated virtual machine migrated from at least one third host in the host group is received and deployed on the first host.

Optionally, the method further includes:

Before collecting the virtual machine load data of each host in the host group, receive an autonomous negotiation migration virtual machine instruction sent by the controller;

Collect virtual machine load data for each host in the host group, including:

Based on the virtual machine migration instruction through autonomous negotiation, it notifies the host group of its own virtual machine load data, and receives the virtual machine load data of each host.

Optionally, the method further includes:

determine the status threshold;

According to the comparison result between the virtual machine load data of each host in the host group and the state threshold, the load state of each host in the host group is determined, and the load state is overload or non-overload.

Optionally, the method further includes:

When it is determined according to the load state of each host in the host group that the proportion of overloaded nodes in the host group exceeds the upper limit value of the first target interval, a new host is started in the host group.

Optionally, when it is determined according to the load status of each host in the host group that the proportion of overloaded nodes in the host group exceeds the upper limit of the first target interval, starting a new host in the host group includes:

It is determined according to the virtual machine load data of each host in the host group that the global load degree of the host group exceeds the load degree threshold, and it is determined according to the load status of each host in the host group that the proportion of overloaded nodes in the host group exceeds the first target interval. In the case of the limit, start a new host in the host group.

Optionally, the method further includes:

If it is determined according to the virtual machine load data of each host in the host group that the global load degree of the host group exceeds the load degree threshold, and it is determined according to the load status of each host in the host group that the proportion of overloaded nodes in the host group does not exceed the first target interval In the case of the upper limit value, the upper limit value of the first target interval is updated according to the proportion of overloaded nodes in the host group.

Optionally, the method further includes:

When it is determined according to the load status of each host in the host group that the proportion of non-overloaded nodes in the host group exceeds the upper limit value of the second target interval, the idle hosts in the host group are shut down.

Optionally, when it is determined according to the load status of each host in the host group that the proportion of non-overloaded nodes in the host group exceeds the upper limit of the second target interval, shutting down the idle hosts in the host group includes:

According to the virtual machine load data of each host in the host group, it is determined that the global load degree of the host group does not exceed the load degree threshold, and according to the load status of each host in the host group, it is determined that the proportion of non-overloaded nodes in the host group exceeds the second target interval In the case of the upper limit value, shut down idle hosts in the host group.

Optionally, the method further includes:

According to the virtual machine load data of each host in the host group, it is determined that the global load degree of the host group does not exceed the load degree threshold, and according to the load status of each host in the host group, it is determined that the proportion of non-overloaded nodes in the host group does not exceed the second target. In the case of the upper limit value of the interval, the upper limit value of the second target interval is updated according to the proportion of non-overloaded nodes in the host group.

Optionally, when the virtual machine load data shows that the first host is an overloaded node, selecting at least one non-overloaded second host in the host group according to the virtual machine load data, including:

When the virtual machine load data shows that the first host is an overloaded node, obtain the overloaded load indicator type in the first host according to the virtual machine load data;

A second host that matches the load index type is selected from the candidate hosts that are identified as non-overloaded nodes in the host group.

Optionally, the method further includes:

Before selecting the second host matching the load index type from the candidate hosts identified as non-overloaded nodes in the host cluster, select non-overloaded nodes in the host cluster according to the virtual machine load data of each host to obtain a candidate host list;

Sort the candidate host list in descending order according to the matching degree between the candidate host and the load indicator type;

Select the second host that matches the load indicator type from the candidate hosts identified as non-overloaded nodes in the host cluster, including:

The second host is selected according to the virtual machine load data in each candidate host in the candidate host list obtained by descending order.

Optionally, the method further includes:

According to the migration result of its own virtual machine, update its own virtual machine load data and notify the host group of the updated virtual machine load data.

The embodiment of the present invention also provides a virtual machine migration system, the system is used for the first host in the host group, including:

The collection module collects the virtual machine load data of each host in the host group;

The migration module, when the virtual machine load data shows that the first host is an overloaded node, selects at least one second host that is not overloaded in the host group according to the virtual machine load data, and selects at least one second host from the first host to migrate out virtual machine and migrated out to the second host;

The migration module, when the virtual machine load data shows that the first host is a non-overloaded node, receives the migrated virtual machine migrated from at least one third host in the host group and deploys it on the first host.

The embodiment of the present invention also provides a virtual machine migration device, including:

processor;

a memory in which executable instructions for the processor are stored;

The processor is configured to execute the steps of the above virtual machine migration method by executing the executable instructions.

Embodiments of the present invention further provide a computer-readable storage medium for storing a program, and when the program is executed, the steps of the above-mentioned virtual machine migration method are implemented.

The purpose of the present invention is to provide a virtual machine migration method, system, device and storage medium. The method includes: any host in the host group can collect the virtual machine load data of each host in the host group, and when the virtual machine load data shows that the current host is In the case of an overloaded node, select at least one non-overloaded target host in the host group according to the virtual machine load data, and select at least one virtual machine from the current host to the target host, and the virtual machine resource load data shows that the current host is not overloaded. In the case of an overloaded node, virtual machines migrated from other hosts are received and deployed on the current host. This can solve the scheduling overload problem caused by using the controller to centrally schedule and migrate virtual machines in the prior art, thereby avoiding the unavailability problem caused by waiting for virtual machine migration, ensuring that virtual machines can be migrated more efficiently within the host group, and improving virtual machine resources. utilization.

Description of drawings

Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings.

1 is one of the flowcharts of a virtual machine migration method according to an embodiment of the present invention;

FIG. 2 is the second flowchart of the virtual machine migration method according to the embodiment of the present invention;

3 is the third flowchart of the virtual machine migration method according to the embodiment of the present invention;

4 is a fourth flowchart of a virtual machine migration method according to an embodiment of the present invention;

FIG. 5 is a fifth flowchart of a virtual machine migration method according to an embodiment of the present invention;

FIG. 6 is a sixth flowchart of a virtual machine migration method according to an embodiment of the present invention;

7 is a seventh flowchart of a virtual machine migration method according to an embodiment of the present invention;

FIG. 8 is the eighth flow chart of the virtual machine migration method according to the embodiment of the present invention;

9 is a ninth flow chart of a virtual machine migration method according to an embodiment of the present invention;

FIG. 10 is a tenth flow chart of a virtual machine migration method according to an embodiment of the present invention;

11 is an eleventh flowchart of a method for migrating a virtual machine according to an embodiment of the present invention;

12 is a twelfth flowchart of a virtual machine migration method according to an embodiment of the present invention;

13 is a thirteenth flowchart of a virtual machine migration method according to an embodiment of the present invention;

14 is one of the structural diagrams of a virtual machine migration system according to an embodiment of the present invention;

15 is the second structural diagram of a virtual machine migration system according to an embodiment of the present invention;

FIG. 16 is a third structural diagram of a virtual machine migration system according to an embodiment of the present invention;

FIG. 17 is a fourth structural diagram of a virtual machine migration system according to an embodiment of the present invention;

FIG. 18 is a fifth structural diagram of a virtual machine migration system according to an embodiment of the present invention;

FIG. 19 is a sixth structural diagram of a virtual machine migration system according to an embodiment of the present invention;

FIG. 20 is a seventh structural diagram of a virtual machine migration system according to an embodiment of the present invention;

FIG. 21 is the eighth structural diagram of the virtual machine migration system according to the embodiment of the present invention;

22 is the ninth structural diagram of the virtual machine migration system according to the embodiment of the present invention;

FIG. 23 is a schematic diagram of the operation of a virtual machine migration device according to an embodiment of the present invention.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.

The drawings are merely schematic illustrations of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repeated descriptions will be omitted. Some of the block diagrams shown in the figures are functional entities that do not necessarily necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, or in one or more hardware forwarding modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices .

In addition, the flow shown in the drawings is only an exemplary illustration, and does not necessarily include all steps. For example, some steps can be decomposed, and some steps can be combined or partially combined, and the actual execution order may be changed according to the actual situation. "First", "second" and similar words used in the detailed description do not denote any order, quantity or importance, but are only used to distinguish different components. It should be noted that the embodiments of the present invention and features in different embodiments may be combined with each other under the condition of no conflict.

In practical applications, it is found that when the platform creates and allocates virtual machines on each host node, it will consider whether the node resources meet the virtual machine requirements, which will lead to uneven distribution of virtual machines among nodes. The resources required by the virtual machines in a node are adjusted with the change of the business scale. When the number of virtual machines on a single node is too large, the nodes will be overloaded due to the competition for node resources, affecting or even interrupting the business. Therefore, automatic online migration of virtual machines in nodes according to changes in the load of each node is an effective method to solve the above problems.

Therefore, an existing method adopts a centralized scheduling method, and uses a controller to be responsible for the scheduling of virtual machine resources, especially the scheduling of computing resources. However, this method has the following problems: when the scale of the host group reaches a certain level, this centralized scheduling method will cause the controller to be congested, and it is difficult to meet the management and control requirements of high load and large concurrency, resulting in the need to wait for some virtual machines to migrate, thus affecting the Quality of service, reduced service capacity and resource utilization.

The embodiments of the present invention provide a virtual machine migration method, apparatus, device and storage medium, wherein the method includes: any host in the host group can collect virtual machine load data of each host in the host group;

When the virtual machine load data shows that the current host is an overloaded node, select at least one non-overloaded target host from the host group according to the virtual machine load data, and select at least one virtual machine from the current host to the target host;

When the virtual machine resource load data shows that the current host is a non-overloaded node, the virtual machines migrated from other hosts are received and deployed on the current host.

The embodiment of the present invention provides a technical solution, the host group can negotiate the migration strategy independently, avoid the bottleneck of the controller, avoid unnecessary service quality degradation, ensure the virtual machine migration efficiency, and improve the virtual machine resource utilization rate.

FIG. 1 is a flowchart of a method for migrating a virtual machine according to an embodiment of the present invention. The execution subject of the method is any host in the host group. For convenience of description, it is defined as the first host below. The hosts in the host group may specifically be physical servers, which are not limited herein.

Referring to FIG. 1, a virtual machine migration method provided by an embodiment of the present invention includes the following steps:

Step 110: Collect virtual machine load data of each host in the host group;

Step 120: When the virtual machine load data shows that the first host is an overloaded node, select at least one non-overloaded second host in the host group according to the virtual machine load data, and select at least one migrated virtual machine from the first host. host and migrate out to the second host;

Step 130: In the case that the virtual machine load data shows that the first host is a non-overloaded node, receive a migrated virtual machine migrated from at least one third host in the host group and deploy it on the first host.

Using the embodiment of the present invention, any host is allowed to collect the virtual machine load data of the host group, so that when its own host is an overloaded node, it can select a suitable second host to migrate out the virtual machine, or when its own host is not overloaded In the case of a node, the virtual machine migrated by the third host can be received and deployed. This can solve the scheduling overload problem caused by using the controller to centrally schedule and migrate virtual machines in the prior art, thereby avoiding the unavailability problem caused by waiting for virtual machine migration, ensuring that virtual machines can be migrated more efficiently within the host group, and improving virtual machine resources. utilization.

In an optional embodiment of the present invention, the virtual machine load data is the number of virtual machines deployed on the host or the resource consumption of running the virtual machines.

In an optional embodiment of the present invention, collecting the virtual machine load data of each host in the host group may specifically include:

In the case that the own virtual machine is overloaded or not overloaded, a request for obtaining virtual machine load data is sent to the host group, and the virtual machine load data fed back by each host in the host group is received.

This embodiment allows each host to timely collect virtual machine load data of each host according to its own virtual machine migration requirements, and implement virtual machine migration in and out according to the virtual machine load of other hosts, avoiding frequent virtual machine migration and improving virtual machine migration. Inbound and outbound efficiency.

In an optional embodiment of the present invention, each host may also announce its own virtual machine load data to the host group at a set time interval.

Referring to FIG. 2, a virtual machine migration method according to an optional embodiment of the present invention includes the following steps:

Step 210: Receive an autonomous negotiation migration virtual machine instruction sent by the controller;

Step 220: Notifying the host group of its own virtual machine load data based on the virtual machine migration instruction through autonomous negotiation, and receiving the virtual machine load data of each host;

Step 230: When the virtual machine load data shows that the first host is an overloaded node, select at least one non-overloaded second host in the host group according to the virtual machine load data, and select at least one migrated virtual machine from the first host. host and migrate out to the second host;

Step 240: In the case that the virtual machine load data shows that the first host is a non-overloaded node, receive a migrated virtual machine migrated from at least one third host in the host group and deploy it on the first host.

In this embodiment, the controller sends an autonomous negotiation and migration virtual machine instruction to each host in the host group, triggering each host to announce its own virtual machine load data to the host group, so that each host can obtain all virtual machines of each host in the host group. machine load data.

In an optional embodiment, referring to FIG. 3 , the virtual machine migration method may include the following steps:

Step 310: Collect virtual machine load data of each host in the host group;

Step 320: determine a state threshold;

Step 330: According to the comparison result between the virtual machine load data of each host in the host group and the state threshold, determine the load state of each host in the host group, and the load state is overload or non-overload;

Step 340: In the case where the virtual machine load data shows that the first host is an overloaded node, select at least one second host that is not overloaded in the host group according to the virtual machine load data, and select at least one migrated virtual machine from the first host. host and migrate out to the second host;

Step 350: In the case that the virtual machine load data shows that the first host is a non-overloaded node, receive a migrated virtual machine migrated from at least one third host in the host group and deploy it on the first host.

In this embodiment, the virtual machine load state of each host may be determined according to a comparison result between the virtual machine load data and the state threshold.

The state threshold may be preset.

In an optional embodiment, referring to FIG. 4 , the virtual machine migration method may include the following steps:

Step 410: Collect virtual machine load data of each host in the host group;

Step 420: determine a state threshold;

Step 430: According to the comparison result between the virtual machine load data of each host in the host group and the state threshold, determine the load state of each host in the host group, and the load state is overload or non-overload;

Step 440: in the case that the proportion of overloaded nodes in the host group exceeds the upper limit value of the first target interval according to the load status of each host in the host group, start a new host in the host group;

Step 450: When the virtual machine load data shows that the first host is an overloaded node, select at least one second host that is not overloaded in the host group according to the virtual machine load data, and select at least one migrated virtual machine from the first host. host and migrate out to the second host;

Step 460: In the case that the virtual machine load data shows that the first host is a non-overloaded node, receive a migrated virtual machine migrated from at least one third host in the host group and deploy it on the first host.

In this embodiment, a new host is started in the host group to migrate the virtual machine in, so as to release the load of the virtual machine in the overloaded node running at a high position.

In an optional embodiment, referring to FIG. 5 , the virtual machine migration method may include the following steps:

Step 510: Collect virtual machine load data of each host in the host group;

Step 520: determine a state threshold;

Step 530: According to the comparison result between the virtual machine load data of each host in the host group and the state threshold, determine the load state of each host in the host group, and the load state is overload or non-overload;

Step 540: In the case where it is determined according to the load status of each host in the host group that the proportion of non-overloaded nodes in the host group exceeds the upper limit of the second target interval, shut down the idle hosts in the host group;

Step 550: In the case where the virtual machine load data shows that the first host is an overloaded node, select at least one second host that is not overloaded in the host group according to the virtual machine load data, and select at least one migrated virtual machine from the first host. host and migrate out to the second host;

Step 560: In the case that the virtual machine load data shows that the first host is a non-overloaded node, receive a migrated virtual machine migrated from at least one third host in the host group and deploy it on the first host.

In this way, active hosts are released by shutting down idle hosts in the host group to save system resources.

In an optional embodiment, referring to FIG. 6 , the virtual machine migration method includes the following steps:

Step 610: Calculate the global load degree of the host group according to the virtual machine load data of each host in the host group;

Step 620: Determine whether the global load degree exceeds the load degree threshold;

Step 630: In the case where it is determined according to the virtual machine load data of each host in the host group that the global load degree of the host group exceeds the load degree threshold, it is determined according to the load status of each host in the host group that the proportion of overloaded nodes in the host group exceeds the th an upper limit of the target interval;

Step 640: Determine according to the virtual machine load data of each host in the host group that the global load degree of the host group exceeds the load degree threshold, and determine according to the load status of each host in the host group that the proportion of overloaded nodes in the host group exceeds the first target In the case of the upper limit of the interval, start a new host in the host group;

Step 650: In the case where it is determined according to the virtual machine load data of each host in the host group that the global load degree of the host group does not exceed the load degree threshold, determine the proportion of non-overloaded nodes in the host group according to the load status of each host in the host group Exceeds the upper limit of the second target interval;

Step 660: According to the virtual machine load data of each host in the host group, it is determined that the global load degree of the host group does not exceed the load degree threshold, and the proportion of non-overloaded nodes in the host group is determined according to the load status of each host in the host group. In the case of the upper limit value of the target interval, the idle host in the host group is shut down.

In this case, more precise decisions are made to power up new hosts and shut down idle hosts.

In an optional embodiment, referring to FIG. 7 , compared with FIG. 6 , the method further includes:

Step 710: According to the virtual machine load data of each host in the host group, it is determined that the global load degree of the host group exceeds the load degree threshold, and according to the load status of each host in the host group, it is determined that the proportion of overloaded nodes in the host group does not exceed the first. In the case of the upper limit value of the target interval, update the upper limit value of the first target interval according to the proportion of overloaded nodes in the host group;

Step 720: According to the virtual machine load data of each host in the host group, it is determined that the global load degree of the host group does not exceed the load degree threshold, and according to the load status of each host in the host group, it is determined that the proportion of non-overloaded nodes in the host group does not exceed the load degree threshold. In the case of the upper limit value of the second target interval, the upper limit value of the second target interval is updated according to the proportion of non-overloaded nodes in the host group.

In this way, the current proportion of overloaded nodes or the proportion of non-loaded nodes reflects the load status of the host group during this period, and the current proportion of overloaded nodes is used as the upper limit of the first target interval, or the current proportion of non-overloaded nodes is used as the second The upper limit value of the target interval, the updated upper limit value of the first target interval can be applied to the next decision process of turning on a new host, or the updated upper limit value of the second target interval can be applied to the next decision process of shutting down an idle host. This embodiment implements dynamic adjustment of the virtual machine of an overloaded node, thereby optimizing node resource configuration and improving load balancing.

In an optional embodiment of the present invention, referring to FIG. 8 , the virtual machine migration method includes the following steps:

Step 810: Collect virtual machine load data of each host in the host group;

Step 820: In the case where the virtual machine load data shows that the first host is an overloaded node, obtain the overloaded load indicator type in the first host according to the virtual machine load data;

Step 830: Select a second host matching the load index type from the candidate hosts identified as non-overloaded nodes in the host group, and select at least one migrated virtual machine from the first host and migrate it out to the second host.

The services provided by each virtual machine are different, and may specifically include central processing unit services, network transmission services, or memory services. The corresponding load indicator types include CPU overload, network overload, or memory overload. This is an example, and does not constitute a limitation on the range of load index types.

In this embodiment, the matching of the load indicator type with the host means that the virtual machine corresponding to the load indicator type has a strong resource dependence on the host, so as to ensure that the migrated virtual machine can run normally on the final second host , without causing excessive load on the second host or causing the problem that the second host cannot provide resources required for running the migrated virtual machine, thereby improving the success rate of virtual machine migration.

In an optional embodiment, referring to FIG. 9 , the virtual machine migration method may include the following steps:

Step 910: Collect virtual machine load data of each host in the host group;

Step 920: In the case where the virtual machine load data shows that the first host is an overloaded node, obtain the overloaded load indicator type in the first host according to the virtual machine load data;

Step 930: Select a non-overloaded node in the host group according to the virtual machine load data of each host to obtain a candidate host list;

Step 940: Describing the candidate host list according to the degree of matching between the candidate hosts and the load indicator type;

Step 950: Select a second host from the candidate host list obtained by descending sorting according to the virtual machine load data in each candidate host, and select at least one migrated virtual machine from the first host and migrate it out to the second host.

In this embodiment, the host can maintain a host list locally, and the host list can record the virtual machine load data and load index type of each host, so that the host that can receive the migrated virtual machine can be quickly identified and selected.

In an optional embodiment, referring to FIG. 10 , the virtual machine migration method may include the following steps:

Step 1010: Collect virtual machine load data of each host in the host group;

Step 1020: When the virtual machine load data shows that the first host is an overloaded node, select at least one second host that is not overloaded in the host group according to the virtual machine load data, and select at least one migrated virtual machine from the first host. host and migrate out to the second host;

Step 1030: In the case that the virtual machine load data shows that the first host is a non-overloaded node, receive a migrated virtual machine migrated from at least one third host in the host group and deploy it on the first host;

Step 1040: Update the load data of the own virtual machine and notify the host group of the updated load data of the virtual machine according to the migration result of the own virtual machine.

Using this embodiment, in the case that the virtual machine migrates in or out of its own host, by notifying the updated virtual machine load data to the host group in real time, each host in the host group can maintain the latest virtual machine load data, so that it can be timely. Determine the virtual machine migration strategy based on your own needs.

In an optional embodiment, referring to FIG. 11 , the virtual machine migration method may include the following steps:

Step 1110: the controller determines whether its own workload is overloaded within the target time period;

If so, go to step 1120: each host collects the virtual machine load data of each host in the host group, and calculates the global load degree and the proportion of high and low load hosts within the monitoring time, wherein the high load host corresponds to the above overloaded node, and the low load host corresponds to the above non-overloaded nodes;

Step 1130: Calculate the evaluation value of the load index whose load degree of the node exceeds the high threshold. If the evaluation value meets the overload requirement, it is determined that the host is overloaded by the index type (the overload index types are divided into CPU overload type, network overload type, and memory overload type. type, which is not limited here);

Step 1140: Calculate the evaluation value of the node whose load degree of the node is lower than the low threshold, and if the evaluation value meets the light load requirement, determine that the node is a light load node, and add it to the low load host list;

Step 1150: Arrange the list of low-load nodes in ascending order of load degree, and combine the global load degree to determine whether it is in the load balancing range, and if the global load degree is less than the lowest value of the reasonable range, calculate and obtain the set of non-load nodes to be migrated;

Step 1160: If the global load level is greater than the highest point in a reasonable range, enable a host.

in,

Node load degree = [Cpu|Mem|Band] _uesd *L _i

Where [Cpu|Mem|Band]used is the utilization rate of CPU, memory, and bandwidth, and Li is the corresponding weight.

In an optional embodiment, referring to FIG. 12 , the decision of the virtual machine to be migrated included in the virtual machine migration method includes the following steps:

Step 1210: Acquire high-load node information according to the high-load node list obtained by the node evaluation. For the specific node evaluation strategy, refer to the embodiment shown in FIG. 11, which will not be described in detail here;

Step 1220: According to the current node overload type, calculate the set of virtual machines to be screened that can relieve the overload condition of the node under a single migration;

Step 1230: Calculate the resource dependency of each virtual machine in the set of virtual machines to be screened, and sort them in descending order;

Step 1240: Calculate the CPU, memory, and bandwidth ratio of each virtual machine;

Step 1250: Select a virtual machine as the virtual machine to be migrated, calculate its resource ratio, and add it to the list of virtual machines to be migrated.

Among them, the resource dependency:

Vi is the resource utilization of a certain index of the virtual machine at time i, Ni is the resource utilization of the index of the node at time i, and the larger the R _type , the higher the dependence of the virtual machine on the resource of this index type of the node.

In an optional embodiment, referring to FIG. 13 , the target node decision included in the virtual machine migration method includes the following steps:

Step 1310 : According to the load-appropriate node list obtained by the node evaluation, sort by the load degree in ascending order to obtain the node list to be selected. For the specific node evaluation strategy, refer to the embodiment shown in FIG. 11 , which will not be described in detail here;

Step 1320: Calculate the matching degree between the virtual machine and the node in the candidate node list, and sort them in descending order;

Step 1330: Calculate the migration cost according to the order of matching degree;

Step 1340: Select the node with high matching degree and the smallest migration cost as the destination node.

FIG. 14 is a virtual machine migration system provided by an embodiment of the present invention. The system is used for a first host in a host group, including:

The collection module 1410 collects virtual machine load data of each host in the host group;

The migration module 1420, when the virtual machine load data shows that the first host is an overloaded node, selects at least one second host that is not overloaded in the host group according to the virtual machine load data, and selects at least one migration node from the first host. Exit the virtual machine and move it out to the second host;

The migration module 1430, when the virtual machine load data shows that the first host is a non-overloaded node, receives the migrated virtual machine migrated from at least one third host in the host group and deploys it on the first host.

Using the virtual machine migration system provided by the embodiment of the present invention allows any host to collect the virtual machine load data of the host group, so that when its own host is an overloaded node, it can select a suitable second host to migrate the virtual machine out, or When the own host is a non-overloaded node, the virtual machine migrated by the third host can be received and deployed. This can solve the scheduling overload problem caused by using the controller to centrally schedule and migrate virtual machines in the prior art, thereby avoiding the problem of unavailability caused by waiting for virtual machine migration, ensuring that virtual machines can be migrated more efficiently within the host group, and improving virtual machine resources. utilization.

For the implementation principle of the above modules, please refer to the relevant introduction in the virtual machine migration method, which will not be repeated here.

In an optional embodiment, the migration module 1420 is specifically configured to:

When the virtual machine load data shows that the first host is an overloaded node, obtain the overloaded load indicator type in the first host according to the virtual machine load data;

A second host that matches the load index type is selected from the candidate hosts that are identified as non-overloaded nodes in the host group.

In an optional embodiment, compared with FIG. 14 , the virtual machine migration system shown in FIG. 15 further includes:

The selecting module 1510 selects a non-overloaded node in the host group according to the virtual machine load data of each host before selecting the second host that matches the load index type from the candidate hosts identified as the non-overloaded node in the host group to obtain the candidate host list;

Sorting module 1520, which sorts the candidate host list in descending order according to the matching degree between the candidate hosts and the load indicator type;

The check-out module 1530 is specifically used to:

The second host is selected according to the virtual machine load data in each candidate host in the candidate host list obtained by descending order.

In an optional embodiment, compared with FIG. 14 , the virtual machine migration system shown in FIG. 16 further includes:

The receiving module 1610, before collecting the virtual machine load data of each host in the host group, receives an autonomous negotiation migration virtual machine instruction sent by the controller;

The collection module 1620 is specifically used to:

Based on the virtual machine migration instruction through autonomous negotiation, it notifies the host group of its own virtual machine load data, and receives the virtual machine load data of each host.

In an optional embodiment, compared with FIG. 14 , the virtual machine migration system shown in FIG. 17 further includes:

a state threshold determination module 1710, to determine a state threshold;

The load state determining module 1720 determines the load state of each host in the host group according to the comparison result between the virtual machine load data of each host in the host group and the state threshold, and the load state is overload or non-overload.

In an optional embodiment, compared with FIG. 14 , the virtual machine migration system shown in FIG. 18 further includes:

The host startup module 1810 starts a new host in the host group when it is determined according to the load status of each host in the host group that the proportion of overloaded nodes in the host group exceeds the upper limit of the first target interval.

In an optional embodiment, the host startup module 1810 is specifically configured to:

It is determined according to the virtual machine load data of each host in the host group that the global load degree of the host group exceeds the load degree threshold, and it is determined according to the load status of each host in the host group that the proportion of overloaded nodes in the host group exceeds the first target interval. In the case of the limit, start a new host in the host group.

In an optional embodiment, compared with FIG. 18 , the virtual machine migration system shown in FIG. 19 further includes:

The first update module 1910 is configured to determine that the global load degree of the host group exceeds the load degree threshold according to the virtual machine load data of each host in the host group, and determine that the proportion of overloaded nodes in the host group is low according to the load status of each host in the host group. When the upper limit value of the first target interval is exceeded, the upper limit value of the first target interval is updated according to the proportion of overloaded nodes in the host group.

In an optional embodiment, compared with FIG. 14 , the virtual machine migration system shown in FIG. 20 further includes:

The host shutdown module 2010 shuts down idle hosts in the host group when it is determined according to the load status of each host in the host group that the proportion of non-overloaded nodes in the host group exceeds the upper limit of the second target interval.

In an optional embodiment, the host shutdown module 2010 is specifically configured to:

According to the virtual machine load data of each host in the host group, it is determined that the global load degree of the host group does not exceed the load degree threshold, and according to the load status of each host in the host group, it is determined that the proportion of non-overloaded nodes in the host group exceeds the second target interval In the case of the upper limit value, shut down idle hosts in the host group.

In an optional embodiment, compared with FIG. 20 , the virtual machine migration system shown in FIG. 21 further includes:

The second update module 2110 is to determine, according to the virtual machine load data of each host in the host group, that the global load degree of the host group does not exceed the load degree threshold, and determine, according to the load status of each host in the host group, that the non-overloaded nodes in the host group occupy the If the ratio does not exceed the upper limit of the second target interval, the upper limit of the second target interval is updated according to the proportion of non-overloaded nodes in the host cluster.

In an optional embodiment, compared with FIG. 14 , the virtual machine migration system shown in FIG. 22 further includes:

The notification module 2210 updates the load data of its own virtual machine and notifies the updated virtual machine load data to the host group according to the migration result of its own virtual machine.

FIG. 23 is a schematic structural diagram of a virtual machine migration device of the present invention. An electronic device 2300 according to this embodiment of the present invention is described below with reference to FIG. 23 . The electronic device 2300 shown in FIG. 23 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present invention.

As shown in Figure 23, electronic device 2300 takes the form of a general purpose computing device. Components of the electronic device 2300 may include, but are not limited to, at least one processing unit 2310, at least one storage unit 2320, a bus 2330 connecting different platform components (including the storage unit 2320 and the processing unit 2310), a display unit 2340, and the like.

The storage unit stores program codes, which can be executed by the processing unit 2310, so that the processing unit 2310 executes the steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of this specification. For example, the processing unit 2310 may perform the steps shown in any of the embodiments of FIGS. 1-13 .

The storage unit 2320 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 2321 and/or a cache storage unit 2322 , and may further include a read only storage unit (ROM) 2323 .

The storage unit 2320 may also include a program/utility 2324 having a set (at least one) of program modules 2325 including, but not limited to, a processing system, one or more application programs, other program modules, and program data, An implementation of a network environment may be included in each or some combination of these examples.

The bus 2330 may be representative of one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local area using any of a variety of bus structures bus.

The electronic device 2300 may also communicate with one or more external devices 2350 (eg, keyboards, pointing devices, Bluetooth devices, etc.), with one or more devices that enable a user to interact with the electronic device 2300, and/or with Any device (eg, router, modem, etc.) that enables the electronic device 2300 to communicate with one or more other computing devices. Such communication may take place through input/output (I/O) interface 2360 . Also, the electronic device 2300 may communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network such as the Internet) through a network adapter 2370 . The network adapter 2370 may communicate with other modules of the electronic device 2300 through the bus 2330 . It should be understood that, although not shown, other hardware and/or software modules may be used in conjunction with electronic device 2300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage platform, etc.

Embodiments of the present invention further provide a computer-readable storage medium for storing a program, and the steps of the virtual machine migration method implemented when the program is executed. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes program code, when the program product runs on a terminal device, the program code is used to cause the terminal device to execute the above-mentioned description in this specification. The steps according to various exemplary embodiments of the present invention are described in the virtual machine migration method section.

The program product 800 for implementing the above method according to an embodiment of the present invention can adopt a portable compact disc read only memory (CD-ROM) and include program codes, and can be executed on a terminal device such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

A computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A readable storage medium can also be any readable medium other than a readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out the processes of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural programming Language - such as the "C" language or similar programming language. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server execute on. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (eg, using an Internet service provider business via an Internet connection).

To sum up, the purpose of the present invention is to provide a virtual machine migration method, system, device and storage medium, any host in the host group can collect the virtual machine load data of each host in the host group, and the virtual machine load data shows that the current host is overloaded In the case of a node, select at least one non-overloaded target host in the host group according to the virtual machine load data, and select at least one virtual machine from the current host to the target host, and the virtual machine resource load data shows that the current host is not overloaded. In the case of a node, receive virtual machines migrated from other hosts and deploy them on the current host. This can solve the scheduling overload problem caused by using the controller to centrally schedule and migrate virtual machines in the prior art, thereby avoiding the unavailability problem caused by waiting for virtual machine migration, ensuring that virtual machines can be migrated more efficiently within the host group, and improving virtual machine resources. utilization.

Allows any host to collect the virtual machine load data of the host group, so that when its own host is an overloaded node, it can select a suitable second host to migrate out the virtual machine, or when its own host is a non-overloaded node, it can Receive and deploy the virtual machine migrated from the third host. This can solve the scheduling overload problem caused by using the controller to centrally schedule and migrate virtual machines in the prior art, thereby avoiding the problem of unavailability caused by waiting for virtual machine migration, ensuring that virtual machines can be migrated more efficiently within the host group, and improving virtual machine resources. utilization.

The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be considered that the specific implementation of the present invention is limited to these descriptions. For those of ordinary skill in the technical field of the present invention, without departing from the concept of the present invention, some simple deductions or substitutions can be made, which should be regarded as belonging to the protection scope of the present invention.

Claims (15)

1. A virtual machine migration method is applied to a first host in a host cluster, and comprises the following steps:

collecting virtual machine load data of each host in the host group;

under the condition that the virtual machine load data show that the first host is an overloaded node, selecting at least one second host which is not overloaded in the host group according to the virtual machine load data, and selecting at least one migrated virtual machine in the first host and migrating the virtual machine to the second host;

and under the condition that the load data of the virtual machine shows that the first host is a non-overload node, receiving an immigrated virtual machine which is immigrated into at least one third host in the host group and deploying the immigrated virtual machine on the first host.

2. The virtual machine migration method according to claim 1, further comprising:

before collecting the virtual machine load data of each host in the host group, receiving an autonomous negotiation migration virtual machine instruction sent by a controller;

the collecting the virtual machine load data of each host in the host group includes:

and announcing own virtual machine load data to the host machine group based on the autonomous negotiation migration virtual machine instruction, and receiving the virtual machine load data of each host machine.

3. The virtual machine migration method according to claim 1, further comprising:

determining a state threshold;

and determining the load state of each host in the host group according to the comparison result between the virtual machine load data of each host in the host group and a state threshold, wherein the load state is overload or non-overload.

4. The virtual machine migration method according to claim 1, further comprising:

and under the condition that the overload node occupation ratio in the host cluster exceeds the upper limit value of a first target interval according to the load state of each host in the host cluster, starting a new host in the host cluster.

5. The virtual machine migration method according to claim 4, wherein, in a case that it is determined that the overload node percentage in the host cluster exceeds an upper limit value of a first target interval according to the load status of each host in the host cluster, starting a new host in the host cluster, includes:

and under the condition that the overall load degree of the host computer group exceeds a load degree threshold value according to the virtual machine load data of each host computer in the host computer group and the overload node occupation ratio in the host computer group exceeds an upper limit value of a first target interval according to the load state of each host computer in the host computer group, starting a new host computer in the host computer group.

6. The virtual machine migration method according to claim 5, further comprising:

under the condition that the overall load degree of the host computer group exceeds the load degree threshold value according to the virtual machine load data of each host computer in the host computer group and the overload node occupation ratio in the host computer group does not exceed the upper limit value of the first target interval according to the load state of each host computer in the host computer group, the upper limit value of the first target interval is updated according to the overload node occupation ratio in the host computer group.

7. The virtual machine migration method according to claim 1, further comprising:

and under the condition that the non-overload node occupation ratio in the host cluster exceeds the upper limit value of a second target interval according to the load state of each host in the host cluster, closing the idle host in the host cluster.

8. The method for migrating a virtual machine according to claim 7, wherein in a case that it is determined that the percentage of non-overloaded nodes in the host cluster exceeds an upper limit value of a second target interval according to the load status of each host in the host cluster, turning off an idle host in the host cluster includes:

and under the condition that the overall load degree of the host computer group does not exceed the load degree threshold value according to the virtual machine load data of each host computer in the host computer group and the non-overload node occupation ratio in the host computer group exceeds the upper limit value of a second target interval according to the load state of each host computer in the host computer group, closing the idle host computers in the host computer group.

9. The virtual machine migration method according to claim 8, further comprising:

and under the condition that the overall load degree of the host cluster is determined not to exceed the load degree threshold according to the virtual machine load data of each host in the host cluster, and the non-overload node occupation ratio in the host cluster is determined not to exceed the upper limit value of a second target interval according to the load state of each host in the host cluster, updating the upper limit value of the second target interval according to the non-overload node occupation ratio in the host cluster.

10. The method according to claim 1, wherein selecting at least one second non-overloaded host from the host group according to the virtual machine load data when the virtual machine load data indicates that the first host is an overloaded node, comprises:

under the condition that the virtual machine load data show that the first host is an overload node, acquiring the overload load index type in the first host according to the virtual machine load data;

and selecting a second host matched with the load index type from the candidate hosts which are determined as non-overload nodes in the host cluster.

11. The virtual machine migration method according to claim 10, further comprising:

before selecting a second host matched with the load index type from the candidate hosts identified as non-overload nodes in the host group, selecting the non-overload nodes in the host group according to the virtual machine load data of each host to obtain a candidate host list;

performing descending sorting on the candidate host list according to the matching degree between the candidate host and the load index type;

selecting a second host matched with the load index type from the candidate hosts identified as the non-overload nodes in the host cluster, wherein the selecting comprises the following steps:

and selecting the second host in the candidate host list obtained by descending sorting according to the load data of the virtual machines in the candidate hosts.

12. The virtual machine migration method according to claim 1, further comprising:

and updating the load data of the virtual machines per se according to the migration-in and migration-out results of the virtual machines per se and announcing the updated load data of the virtual machines to the host machine group.

13. A virtual machine migration system, for a first host in a cluster of hosts, comprising:

the collection module is used for collecting the virtual machine load data of each host in the host group;

the migration module selects at least one second host which is not overloaded in the host group according to the virtual machine load data under the condition that the virtual machine load data show that the first host is an overloaded node, and selects at least one migrated virtual machine in the first host and migrates the selected virtual machine to the second host;

and the immigration module is used for receiving the immigration virtual machine which is immigrated into at least one third host in the host group and deploying the immigration virtual machine in the first host under the condition that the load data of the virtual machine shows that the first host is a non-overload node.

14. A virtual machine migration apparatus, comprising:

a processor;

a memory having stored therein executable instructions of the processor;

wherein the processor is configured to perform the steps of the virtual machine migration method of any one of claims 1 to 12 via execution of the executable instructions.

15. A computer-readable storage medium storing a program which, when executed by a processor, performs the steps of the virtual machine migration method of any one of claims 1 to 12.

Images