CN112015518B - Method and system for realizing real-time migration of multiple virtual machines in incremental deployment SDN environment - Google Patents
Method and system for realizing real-time migration of multiple virtual machines in incremental deployment SDN environment Download PDFInfo
- Publication number
- CN112015518B CN112015518B CN202010879713.5A CN202010879713A CN112015518B CN 112015518 B CN112015518 B CN 112015518B CN 202010879713 A CN202010879713 A CN 202010879713A CN 112015518 B CN112015518 B CN 112015518B
- Authority
- CN
- China
- Prior art keywords
- migration
- sdn
- node
- virtual machines
- sdn forwarding
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45595—Network integration; Enabling network access in virtual machine instances
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention belongs to the field of computer networks, and provides a method for realizing real-time migration of multiple virtual machines in an incremental deployment SDN environment, wherein the method for realizing real-time migration of the multiple virtual machines comprises the steps of binding virtual machines which are injected by the same SDN forwarding node and have the same target node into a migration task; acquiring migration task related parameters, and solving a migration problem model of the multiple virtual machines based on the original dual to obtain the size of real-time controllable flow on a corresponding link and whether the controllable flow starts to be transmitted or not; gradually increasing the quantity of SDN forwarding nodes in a known network topology, updating migration tasks and continuously solving a migration problem model of the multiple virtual machines until all the migration tasks are completed, and obtaining the real-time controllable flow size of all links and whether the controllable flow size starts to be transmitted; the multi-virtual machine migration problem model is that the sum of all controllable flows in the known network topology is the maximum or the total bandwidth allocated to the controllable flows is the maximum.
Description
Technical Field
The invention belongs to the field of computer networks, and particularly relates to a method and a system for realizing real-time migration of multiple virtual machines in an incremental SDN deployment environment.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Software Defined Network (SDN) is a new Network innovation architecture proposed by the research group of the CLean State topic of stanford university, usa, and is an implementation mode of Network virtualization. The core technology OpenFlow separates the control plane and the data plane of the network equipment, thereby realizing the flexible control of network flow, enabling the network to be more intelligent as a pipeline, and providing a good platform for the innovation of a core network and application. SDN is a strong candidate for next generation backbone networks. It separates control from forwarding and thus has a very strong flow control capability. The inventor finds that large-scale deployment of the pure SDN requires more time, migration instantaneity of multiple virtual machines is poor, and utilization rate of network traffic of a network topology system is low.
Disclosure of Invention
In order to solve the above problems, the present invention provides a method and a system for implementing real-time migration of multiple virtual machines in an incremental deployment SDN environment, which can minimize the impact of virtual machine migration on the performance of a known network topology system, reduce the time for real-time migration of multiple virtual machines, and improve the utilization rate of network traffic of the network topology system.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a method for realizing real-time migration of multiple virtual machines in an incremental deployment SDN environment.
A method for realizing real-time migration of multiple virtual machines in an incremental deployment SDN environment comprises the following steps:
binding virtual machines which are injected by the same target node and the same SDN forwarding node into a migration task;
acquiring migration task related parameters, and solving a migration problem model of the multiple virtual machines based on the original dual to obtain the real-time controllable flow size on the corresponding link and whether the controllable flow starts to be transmitted or not;
gradually increasing the quantity of SDN forwarding nodes in a known network topology, updating migration tasks and continuously solving a migration problem model of the multiple virtual machines until all the migration tasks are completed, and obtaining the real-time controllable flow size of all links and whether the controllable flow size starts to be transmitted;
the multi-virtual machine migration problem model is that the sum of all controllable flows in the known network topology is the maximum or the total bandwidth allocated to the controllable flows is the maximum.
The invention provides a system for realizing real-time migration of multiple virtual machines in an incremental deployment SDN environment.
A system for realizing real-time migration of multiple virtual machines in an incremental deployment SDN environment comprises:
the migration task acquisition module is used for binding the virtual machines which are injected by the same target node and the same SDN forwarding node into one migration task;
the migration problem model solving module is used for acquiring relevant parameters of a migration task, and solving a migration problem model of the multiple virtual machines based on the original dual to obtain the size of real-time controllable flow on a corresponding link and whether the controllable flow starts to be transmitted or not;
the migration task updating module is used for gradually increasing the number of SDN forwarding nodes in a known network topology, updating the migration tasks and continuously solving the migration problem model of the multiple virtual machines until all the migration tasks are completed to obtain the real-time controllable flow size of all the links and whether the controllable flow size starts to be transmitted or not;
the multi-virtual machine migration problem model is that the sum of all controllable flows in the known network topology is the maximum or the total bandwidth allocated to the controllable flows is the maximum.
A third aspect of the invention provides a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in a method for implementing live migration of multiple virtual machines in an incrementally deployed SDN environment as described above.
A fourth aspect of the invention provides a computer apparatus.
A computer apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the program implementing the steps in implementing a method for live migration of multiple virtual machines in an incrementally deployed SDN environment as described above.
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps that virtual machines which are the same in target node and injected by the same SDN forwarding node are bound into a migration task; the method comprises the steps of solving a multi-virtual machine migration problem model based on original dual, wherein the multi-virtual machine migration problem model is that the sum of all controllable flows in a known network topology is maximum or the total bandwidth allocated to the controllable flows is maximum, gradually increasing the quantity of SDN forwarding nodes in the known network topology, updating migration tasks and continuously solving the multi-virtual machine migration problem model until all the migration tasks are completed to obtain the real-time bandwidth of all migration paths, so that the influence of virtual machine migration on the performance of the known network topology system is minimized, the real-time migration time of the multi-virtual machine is shortened, and the utilization rate of network traffic of the network topology system is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Figure 1 is a high level system architecture diagram of an incremental deployment SDN of an embodiment of the invention;
fig. 2 is a flowchart of a method for implementing real-time migration of multiple virtual machines in an incremental deployment SDN environment according to an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
The embodiment aims to solve the problem of multi-virtual machine real-time migration in an incremental deployment SDN environment, and aims to minimize the influence of virtual machine migration on system performance, wherein the index is mathematically expressed to minimize the total migration time of a series of virtual machines. In the problem to be solved, the migration of multiple virtual machines can be performed simultaneously under the condition that the network bandwidth allows, and the method for realizing the shortest migration time is to maximize the total migration rate of each time period.
Referring to fig. 2, the method for implementing real-time migration of multiple virtual machines in an incremental deployment SDN environment according to this embodiment includes:
step 1: binding virtual machines which are injected by the same target node and the same SDN forwarding node into a migration task;
step 2: acquiring migration task related parameters, and solving a migration problem model of the multiple virtual machines based on the original dual to obtain the size of real-time controllable flow on a corresponding link and whether the controllable flow starts to be transmitted or not;
and step 3: gradually increasing the quantity of SDN forwarding nodes in a known network topology, updating migration tasks and continuously solving a migration problem model of the multiple virtual machines until all the migration tasks are completed, and obtaining the real-time controllable flow size of all links and whether the controllable flow size starts to be transmitted;
the multi-virtual machine migration problem model is that the sum of all controllable flows in the known network topology is the maximum or the total bandwidth allocated to the controllable flows is the maximum.
In this embodiment, B4 topology is used as a research object. B4 is a wide area network topology between data centers, which is spanned by google, and includes 12 data centers and 19 links.
In the following, only 3 SDN forwarding nodes are deployed in the B4 topology, and the remaining 9 nodes are all traditional forwarding nodes as an example: the deployment location of SDN forwarding nodes in the topology is given. Modeling is carried out on the real-time migration problem of the multiple virtual machines, and then solving is carried out.
Migration rate ms of certain virtual machine i in certain time period i The single virtual machine migration model proposed in the 2015 document of wang et al, infocom:
ms i ＝l i -d i ,
wherein l i The bandwidth required for the migration of the virtual machine i,d i representing the dirty page rate of virtual machine i. Based on the above formula, the total migration rate of all virtual machines in the time period topology can be expressed as follows:
where m represents the number of virtual machines to be migrated, x i Indicating whether virtual machine i is migrated at this time. Due to the limited SDN forwarding nodes, flow control granularity in a pure SDN environment cannot be made in an incrementally deployed SDN environment. In this embodiment, the SDN forwarding nodes may implement control of the legacy network nodes by injecting the legacy forwarding nodes on the shortest path tree. Virtual machines injected by the same SDN forwarding node and having the same destination node are bundled as one migration task. One migration task comprises a plurality of virtual machines which need to be migrated simultaneously. One migration task is the smallest controllable unit in this embodiment, where all virtual machines are migrated together when it starts to migrate. For a certain migration task k, it is assumed that there are z virtual machines. Then the total migration rate ms for task k k Can be derived as follows:
wherein d is k Represents the sum of the dirty page rates, l, of all the virtual machines in the migration task k k Representing the total bandwidth allocated to task k, boolean variable X k Indicating whether migration task k started to migrate at this point,
representing the set of transmission paths for the migration task k.
Based on the binding of the virtual machines and the migration rate of the migration tasks, the embodiment models the mixed integer programming problem as follows:
l k ≤βX k ，k＝1，...，K (3)，
X k ∈{0，1}，k＝1，...，K (5)，
where x (P) represents the controllable flow size on link e, β represents a sufficiently large constant,
a set of transmission paths representing a migration task k, which is
I.e. starting point u k And end point is t k Is determined by the set of paths taken by the flow. E represents a link set;
and migrating the transmission path set of the task. K is the total number of migration tasks.
Constraint (1) ensures that the sum of all uncontrollable flows g (e) and controllable flows on link e does not exceed link capacity c (e). Constraint (2) then represents the bandwidth that should be allocated to migration task k. Constraint (3) ensures X k With a value of 0, the bandwidth allocated to task k is 0. Constraint (4) ensures that the controllable traffic size on link e cannot be negative. While the last constraint specifies a domain for the argument. When a new task arrives or an old task ends, we will start withThe updated set of migration tasks is recalculated as input to the optimization problem.
In practical cases, the dirty page rate d k Is much smaller than the bandwidth l k The value of (c). Thus, the objective function is simplified to
Then, the intermediate variable l is removed k I convert the above mixed integer programming problem into a linear programming problem as follows:
where b (e) = c (e) -g (e) represents the available bandwidth of the controllable stream on link e. The objective function of the linear programming described above represents the sum of all the controllable flows in the network topology, or the total bandwidth allocated to the controllable flows. In fact, the post-conversion problem is typically a maximum multiple commodity flow problem. A number of approximation algorithms have been proposed to solve it quickly. The present embodiment solves the linear programming problem after simplification based on the fully polynomial time approximation algorithm proposed by Garg et al. The method is based on the original dual, and the problem of the largest commodity flow can be solved quickly without considering the number of the commodity flows.
The above mathematical description addresses the problem of maximizing the total migration rate at a time. The method solves the problem of minimum total migration time of the multiple virtual machines, and the virtual machine migration rate at each moment needs to be maximized as much as possible. And when one migration task finishes transmission, taking the newly added virtual machine migration task and the unfinished virtual machine migration task at the moment as new inputs of the algorithm, and repeatedly running the migration algorithm described in the previous section.
In addition to minimizing the total migration time or maximizing the migration rate, the present embodiment also considers the influence of the SDN forwarding node deployment location on the total migration time. The total migration rate of the multiple virtual machines is also related to the deployment location of the SDN forwarding nodes.
Then, in several network topologies with a small number of nodes, under the condition that the number of SDN forwarding nodes is fixed, the present embodiment performs an exhaustive manner to study the influence of the deployment position of the SDN forwarding nodes on the migration time of the virtual machine. In the embodiment, algorithms are operated for various conditions, and the total migration time is calculated. Based on the experiments, the access degree of the node and the distance between the node and other SDN forwarding nodes have great influence on the total migration time of the multiple virtual machines. We find that the greater the in-out of a node, the higher the likelihood of being deployed SDN forwarding nodes, and the further a node is from other SDN forwarding nodes, the higher the likelihood of being deployed SDN forwarding nodes. Then, in a complex topology, several combinations with the highest in-degree and the farthest distance are selected preferentially to carry out experiments, and the combination with the smallest total migration time is selected as a deployment scheme of the SDN forwarding node.
In this embodiment, under the condition that the deployment manner is not changed, an influence relationship of the number of SDN forwarding nodes in the topology on the total migration time of the multiple virtual machines is given:
on the basis that the deployment position of the SDN forwarding node and the topology do not change, a new SDN forwarding node is added in the original topology based on the SDN node deployment mode in the embodiment. Finally, the influence of the SDN node number on the total migration time is researched by taking the SDN forwarding node number as a coordinate horizontal axis and taking the total migration time of the multiple virtual machines as a vertical axis. The more SDN forwarding nodes, the higher the performance of the network topology, and the smaller the migration time as a whole.
The method comprises the steps of realizing real-time migration of multiple virtual machines in an incremental deployment SDN environment, modeling the real-time migration problem of the multiple virtual machines into a mixed integer programming problem, then simplifying the mixed integer programming problem into a linear programming problem, and finally solving the problem by using an original dual method. It is obtained whether each stream starts transmission during the corresponding time period. The result is a matrix, with a value of 1, corresponding to the streaming. 0 is not transmitted at this time.
The SDN control nodes in the incremental deployment SDN topology are limited, and the traditional forwarding nodes using the traditional OSPF protocol exist, and the flow cannot be controlled in a fine-grained manner like the SDN environment, so that the method for solving the real-time migration problem of the multiple virtual machines in the incremental deployment SDN is completely different from that in a pure SDN environment.
Only part of SDN nodes are deployed in the whole topology, the rest nodes are traditional forwarding nodes, an SDN controller in the topology can only directly control data forwarding of the SDN forwarding nodes, the flow control function is realized through forwarding tables stored in the SDN forwarding nodes, the rest traditional forwarding nodes run based on an OSPF protocol, the SDN forwarding nodes and the SDN central controller are not aware of the existence of the SDN forwarding nodes, the SDN controller has a certain method for knowing the current OSPF weight and the current flow size of each link in the network, the SDN forwarding nodes are modified to determine the flow between the SDN forwarding nodes and all other nodes in the network, and the deployment positions and the number of the SDN forwarding nodes are researched.
And adding a column in a forwarding table stored by the SDN forwarding node to record forwarding nodes which can reach the IP address of the destination node in the network.
When a data packet is processed by the SDN forwarding node, the SDN forwarding node determines the next hop by performing longest prefix matching on the IP address of the destination node, and increments the value of a counter corresponding to the destination node according to the length of the packet.
The method for the SDN controller to know the current OSPF weight and the flow size of each link in the network is characterized in that: in a conventional network environment running the OSPF protocol, network nodes exchange network available bandwidth information of links with each other, so that the SDN controller can obtain current OSPF weights and traffic sizes of each link in the network.
The flow control capability of the whole incremental deployment SDN topology can be enhanced by reasonably deploying the SDN forwarding nodes, the possibility of deploying the SDN forwarding nodes at each node in the topology is calculated, and the SDN forwarding nodes are deployed by selecting the nodes with the highest possibility values.
The value of the likelihood of deploying the SDN forwarding node at a node is calculated according to the degree of access of the node and the distance between the node and other SDN forwarding nodes, specifically, the greater the degree of access of a node, the higher the likelihood of being deployed with the SDN forwarding node, and the further a node is from the position of other SDN forwarding nodes, the higher the likelihood of being deployed with the SDN forwarding node.
Each SDN forwarding node simultaneously controls the controllable flows injected by the node, other controllable flows are controlled by other SDN forwarding nodes, the flows injected by the SDN forwarding nodes are bundled into a plurality of migration tasks, and the migration of the multiple virtual machines is controlled by taking the migration tasks as a minimum unit.
Assume that all links in the topology have a weight of 1 and that for each node therein the OSPF protocol generates a shortest path tree. Given a flow that passes through a legacy forwarding node and is routed along the shortest path, the flow is a controllable flow if and only if it passes through or originates from a SDN forwarding node, otherwise the flow is referred to as an uncontrollable flow.
An SDN forwarding node u injects a flow if and only if the following two conditions are met at the same time: 1) Node u is on the OSPF routing path of the flow. 2) The flow first passes through node u before passing through all other SDN forwarding nodes.
The flows are from the virtual machine migration process, once a virtual machine starts to migrate, corresponding flows are generated on the path between the virtual machine migration starting point and the target node, and the fact that the virtual machine is migrated completely means that all corresponding flows are transmitted to the target node.
When the deployment mode of the SDN forwarding nodes is unchanged, the more SDN forwarding nodes are deployed, the larger the formalized throughput rate of the topology becomes, and the finer the control granularity of the flow becomes.
The throughput rate of the incremental deployment SDN topology is the ratio of the throughput rate of the incremental deployment SDN topology to the throughput rate of the corresponding pure SDN topology, the value is between 0 and 1, and the closer to 1 represents that the throughput rate is closer to the pure SDN topology, the stronger the control capability of the flow and the virtual machine migration is.
The method and the device solve the problem of real-time migration of multiple virtual machines in the incremental deployment SDN environment, and prove the possibility that the incremental deployment SDN realizes partial SDN functions and serves as an SDN cheap substitute from a certain angle. Meanwhile, the embodiment also considers the influence of the deployment position of the SDN forwarding node on the migration rate of the virtual machine.
Example two
The embodiment provides a system for realizing real-time migration of multiple virtual machines in an incremental deployment SDN environment, which includes:
(1) The migration task acquisition module is used for binding the virtual machines which are injected by the same SDN forwarding node and are the same target node into one migration task;
(2) The migration problem model solving module is used for acquiring relevant parameters of a migration task, and solving a migration problem model of the multiple virtual machines based on the original dual to obtain the size of real-time controllable flow on a corresponding link and whether the controllable flow starts to be transmitted or not;
(3) The migration task updating module is used for gradually increasing the number of SDN forwarding nodes in a known network topology, updating the migration tasks and continuously solving the migration problem model of the multiple virtual machines until all the migration tasks are completed to obtain the real-time controllable flow size of all the links and whether the controllable flow size starts to be transmitted or not;
the multi-virtual machine migration problem model is that the sum of all controllable flows in the known network topology is the maximum or the total bandwidth allocated to the controllable flows is the maximum.
The multi-virtual machine migration problem model further comprises: the real-time bandwidth of any link is not larger than the available bandwidth of the controllable stream on the link.
The multi-virtual machine migration problem model further comprises: the controllable flow size of any link is not less than 0.
Specifically, the method comprises the following steps:
where b (e) = c (e) -g (e) represents the available bandwidth of the controllable stream on link e. c (e) is link capacity; g (e) is an uncontrolled flow; x (P) represents the controllable flow size on link e,
a transmission path set of the migration task; e denotes a link set.
Specifically, in the process of gradually increasing the number of SDN forwarding nodes in the known network topology, a value of the possibility of deploying the SDN forwarding nodes at the node is calculated according to the degree of entrance and exit of the node in the known network topology and the distances between the node and other SDN forwarding nodes.
The larger the access of a node is, the higher the possibility of being deployed with SDN forwarding nodes. The further a node is from the location of other SDN forwarding nodes, the higher the likelihood that an SDN forwarding node will be deployed.
Each SDN forwarding node simultaneously controls the controllable flows injected by the SDN forwarding node, other controllable flows are controlled by other SDN forwarding nodes, the flows injected by the SDN forwarding nodes are bundled into a plurality of migration tasks, and the migration tasks are used as minimum units to control the migration of the multiple virtual machines.
The system for implementing the real-time migration of multiple virtual machines in the incremental deployment SDN environment of this embodiment corresponds to the method for implementing the real-time migration of multiple virtual machines in the incremental deployment SDN environment of the first embodiment, where each module for implementing the real-time migration of multiple virtual machines in the incremental deployment SDN environment corresponds to a specific implementation process of each step in the method for implementing the real-time migration of multiple virtual machines in the incremental deployment SDN environment, and as is specific to the first embodiment, the description is not repeated here.
The embodiment binds the same target node and the virtual machines injected by the same SDN forwarding node into one migration task; the method comprises the steps of solving a multi-virtual machine migration problem model based on original dual, wherein the multi-virtual machine migration problem model is that the sum of all controllable flows in a known network topology is maximum or the total bandwidth allocated to the controllable flows is maximum, gradually increasing the quantity of SDN forwarding nodes in the known network topology, updating migration tasks and continuously solving the multi-virtual machine migration problem model until all the migration tasks are completed to obtain the real-time bandwidth of all migration paths, so that the influence of virtual machine migration on the performance of the known network topology system is minimized, the real-time migration time of the multi-virtual machine is shortened, and the utilization rate of network traffic of the network topology system is improved.
EXAMPLE III
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, where the program, when executed by a processor, implements the steps in the method for implementing live migration of multiple virtual machines in an incremental deployment SDN environment as described in the first embodiment.
The embodiment binds the same target node and virtual machines injected by the same SDN forwarding node into one migration task; the method comprises the steps of solving a multi-virtual machine migration problem model based on original dual, wherein the multi-virtual machine migration problem model is that the sum of all controllable flows in a known network topology is maximum or the total bandwidth allocated to the controllable flows is maximum, gradually increasing the quantity of SDN forwarding nodes in the known network topology, updating migration tasks and continuously solving the multi-virtual machine migration problem model until all the migration tasks are completed to obtain the real-time bandwidth of all migration paths, so that the influence of virtual machine migration on the performance of the known network topology system is minimized, the real-time migration time of the multi-virtual machine is shortened, and the utilization rate of network traffic of the network topology system is improved.
Example four
The present embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the program to implement the steps in the method for implementing live migration of multiple virtual machines in an incremental deployment SDN environment as described in the first embodiment.
The embodiment binds the same target node and the virtual machines injected by the same SDN forwarding node into one migration task; the method comprises the steps of solving a multi-virtual machine migration problem model based on original dual, wherein the multi-virtual machine migration problem model is that the sum of all controllable flows in a known network topology is maximum or the total bandwidth allocated to the controllable flows is maximum, gradually increasing the quantity of SDN forwarding nodes in the known network topology, updating migration tasks and continuously solving the multi-virtual machine migration problem model until all the migration tasks are completed to obtain the real-time bandwidth of all migration paths, so that the influence of virtual machine migration on the performance of the known network topology system is minimized, the real-time migration time of the multi-virtual machine is shortened, and the utilization rate of network traffic of the network topology system is improved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A method for realizing real-time migration of multiple virtual machines in an incremental deployment SDN environment is characterized by comprising the following steps:
binding virtual machines which are injected by the same target node and the same SDN forwarding node into a migration task;
acquiring migration task related parameters, and solving a migration problem model of the multiple virtual machines based on the original dual to obtain the size of the real-time controllable stream on the corresponding link and whether the controllable stream starts to be transmitted or not;
gradually increasing the quantity of SDN forwarding nodes in a known network topology, updating migration tasks and continuously solving a migration problem model of the multiple virtual machines until all the migration tasks are completed, and obtaining the real-time controllable flow size of all links and whether the controllable flow size starts to be transmitted;
the multi-virtual machine migration problem model is that the sum of all controllable flows in a known network topology is maximum or the total bandwidth allocated to the controllable flows is maximum;
when one migration task finishes transmission, taking a newly added virtual machine migration task and an unfinished virtual machine migration task at the moment as new inputs, and repeatedly running an algorithm for solving a multi-virtual machine migration problem model;
in the process of gradually increasing the number of SDN forwarding nodes in the known network topology, calculating a value of the possibility of deploying the SDN forwarding nodes at the node according to the entrance and exit of the node in the known network topology and the distances between the node and other SDN forwarding nodes;
the greater the in-out of a node is, the higher the probability of being deployed with an SDN forwarding node;
the farther a node is from the positions of other SDN forwarding nodes, the higher the possibility that the SDN forwarding nodes are deployed;
and selecting the node with the largest access degree and the farthest position from other SDN forwarding nodes, and deploying the SDN forwarding nodes.
2. The method for implementing multi-virtual machine live migration in an incrementally deployed SDN environment as recited in claim 1, wherein the multi-virtual machine migration problem model further comprises: the real-time bandwidth of any link is not larger than the available bandwidth of the controllable stream on the link.
3. The method for implementing multi-virtual machine live migration in an incrementally deployed SDN environment as recited in claim 1, wherein the multi-virtual machine migration problem model further comprises: the controllable flow size of any link is not less than 0.
4. The method for implementing the live migration of multiple virtual machines in the incremental deployment SDN environment of claim 1, wherein each SDN forwarding node simultaneously controls controllable flows injected by the SDN forwarding node, other controllable flows are controlled by other SDN forwarding nodes, flows injected by the SDN forwarding nodes are bundled into several migration tasks, and the migration tasks are used as a minimum unit to control the migration of the multiple virtual machines.
5. A system for realizing real-time migration of multiple virtual machines in an incremental deployment SDN environment is characterized by comprising the following steps:
the migration task acquisition module is used for binding the virtual machines which are injected by the same target node and the same SDN forwarding node into one migration task;
the migration problem model solving module is used for acquiring relevant parameters of a migration task, and solving a migration problem model of the multiple virtual machines based on the original dual to obtain the size of the real-time controllable stream on the corresponding link and whether the controllable stream starts to be transmitted or not;
the migration task updating module is used for gradually increasing the number of SDN forwarding nodes in a known network topology, updating the migration tasks and continuously solving the migration problem model of the multiple virtual machines until all the migration tasks are completed to obtain the real-time controllable flow size of all the links and whether the controllable flow size starts to be transmitted or not;
the multi-virtual machine migration problem model is that the sum of all controllable flows in the known network topology is the maximum or the total bandwidth allocated to the controllable flows is the maximum;
when one migration task finishes transmission, taking a virtual machine migration task newly added at the moment and an unfinished virtual machine migration task as new inputs, and repeatedly running an algorithm for solving a multi-virtual machine migration problem model;
in the process of gradually increasing the number of SDN forwarding nodes in the known network topology, calculating a value of the possibility of deploying the SDN forwarding nodes at the node according to the entrance and exit of the node in the known network topology and the distances between the node and other SDN forwarding nodes;
the greater the access of a node, the higher the probability of being deployed with SDN forwarding nodes;
the farther a node is from the positions of other SDN forwarding nodes, the higher the possibility that the SDN forwarding nodes are deployed;
and selecting the node with the largest in-out degree and the farthest distance from the positions of other SDN forwarding nodes, and deploying the SDN forwarding nodes.
6. A computer readable storage medium having stored thereon a computer program, which when executed by a processor, performs the steps of implementing a method for live migration of multiple virtual machines in an incrementally deployed SDN environment as claimed in any one of claims 1 to 4.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps in implementing a method for live migration of multiple virtual machines in an incrementally deployed SDN environment as claimed in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010879713.5A CN112015518B (en) | 2020-08-27 | 2020-08-27 | Method and system for realizing real-time migration of multiple virtual machines in incremental deployment SDN environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010879713.5A CN112015518B (en) | 2020-08-27 | 2020-08-27 | Method and system for realizing real-time migration of multiple virtual machines in incremental deployment SDN environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112015518A CN112015518A (en) | 2020-12-01 |
| CN112015518B true CN112015518B (en) | 2022-11-25 |
Family
ID=73502666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010879713.5A Active CN112015518B (en) | 2020-08-27 | 2020-08-27 | Method and system for realizing real-time migration of multiple virtual machines in incremental deployment SDN environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112015518B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112600827B (en) * | 2020-12-10 | 2021-10-29 | 中国科学院深圳先进技术研究院 | Virtual service migration method and system based on incremental minimum cost maximum flow |
| CN112601232B (en) * | 2020-12-10 | 2022-04-26 | 中国科学院深圳先进技术研究院 | Load balancing multi-service migration method and system based on minimum cost and maximum flow |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104935628A (en) * | 2015-04-20 | 2015-09-23 | 电子科技大学 | Method of migrating a plurality of associated virtual machines among a plurality of data centers |
| CN105610715A (en) * | 2016-03-14 | 2016-05-25 | 山东大学 | Cloud data center multi-virtual machine migration scheduling method based on SDN (Software Defined Network) |
| CN106681815A (en) * | 2016-12-27 | 2017-05-17 | 中山大学 | Concurrent migration method of virtual machines |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI531908B (en) * | 2014-04-24 | 2016-05-01 | A method of supporting virtual machine migration with Software Defined Network (SDN) |
-
2020
- 2020-08-27 CN CN202010879713.5A patent/CN112015518B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104935628A (en) * | 2015-04-20 | 2015-09-23 | 电子科技大学 | Method of migrating a plurality of associated virtual machines among a plurality of data centers |
| CN105610715A (en) * | 2016-03-14 | 2016-05-25 | 山东大学 | Cloud data center multi-virtual machine migration scheduling method based on SDN (Software Defined Network) |
| CN106681815A (en) * | 2016-12-27 | 2017-05-17 | 中山大学 | Concurrent migration method of virtual machines |
Non-Patent Citations (3)
| Title |
|---|
| Live Migration Planning of Virtual Machines in Hybrid SDN;Qin Y et al.;《IEEE International Symposium on Parallel and Distributed Processing with Applications》;20170101;第1161-1163页 * |
| Qin Y et al..Live Migration Planning of Virtual Machines in Hybrid SDN.《IEEE International Symposium on Parallel and Distributed Processing with Applications》.2017,第620-636页. * |
| SDN控制器放置优化技术研究与系统实现;齐月震;《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》;20190815(第08期);第22-23页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112015518A (en) | 2020-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109039942B (en) | Network load balancing system and balancing method based on deep reinforcement learning | |
| CN108260169B (en) | QoS guarantee-based dynamic service function chain deployment method | |
| CN103870340B (en) | Data processing method, control node and stream calculation system in stream calculation system | |
| CN110601973B (en) | Route planning method, system, server and storage medium | |
| CN103119900B (en) | Communication system, control appliance, node control method and node control program | |
| US20160036707A1 (en) | Flow Based Network Service Insertion | |
| CN112015518B (en) | Method and system for realizing real-time migration of multiple virtual machines in incremental deployment SDN environment | |
| CN104468357B (en) | Multipolarity method, the multilevel flow table processing method and processing device of flow table | |
| CN105656771B (en) | A kind of service path determines methods, devices and systems | |
| CN105357124B (en) | A kind of MapReduce bandwidth optimization methods | |
| JP5943431B2 (en) | Network, data transfer node, communication method and program | |
| JP2017511073A (en) | Path selection in hybrid networks | |
| JPWO2012108382A1 (en) | COMMUNICATION SYSTEM, CONTROL DEVICE, COMMUNICATION NODE, AND COMMUNICATION METHOD | |
| CN104954270A (en) | Techniques for aggregating hardware routing resources in a multi-packet processor networking system | |
| CN111211987B (en) | Method and system for dynamically adjusting flow in network, electronic equipment and storage medium | |
| CN108965141A (en) | A kind of calculation method and device of Multi-path route tree | |
| CN107517155A (en) | A kind of software defined network, node, path calculation method and device | |
| CN105634974A (en) | Route determining method and apparatus in software-defined networking | |
| WO2015195013A1 (en) | Automated placement of measurement endpoint nodes in a network | |
| CN111340192A (en) | Network path allocation model training method, path allocation method and device | |
| CN110262988A (en) | For controlling the method and system of network routing | |
| CN105453494B (en) | Virtual shortest path tree is established and the method and path-calculating element of processing | |
| Xiao et al. | An efficient algorithm for dynamic shortest path tree update in network routing | |
| CN112039767A (en) | Multi-data center energy-saving routing method and system based on reinforcement learning | |
| CN110417576B (en) | Deployment method, device, equipment and storage medium of hybrid software custom network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |