CN110737509B - Thermal migration processing method and device, storage medium and electronic equipment - Google Patents
Thermal migration processing method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN110737509B CN110737509B CN201910994946.7A CN201910994946A CN110737509B CN 110737509 B CN110737509 B CN 110737509B CN 201910994946 A CN201910994946 A CN 201910994946A CN 110737509 B CN110737509 B CN 110737509B
- Authority
- CN
- China
- Prior art keywords
- thermal migration
- virtual machine
- historical time
- time point
- time points
- 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
- 238000013508 migration Methods 0.000 title claims abstract description 203
- 230000005012 migration Effects 0.000 title claims abstract description 203
- 238000003672 processing method Methods 0.000 title claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 56
- 238000012545 processing Methods 0.000 claims abstract description 53
- 238000011156 evaluation Methods 0.000 claims abstract description 50
- 230000008569 process Effects 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000004590 computer program Methods 0.000 claims description 4
- 238000001089 thermophoresis Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The embodiment of the disclosure provides a thermal migration processing method, a thermal migration processing device, a storage medium and electronic equipment, and relates to the technical field of computers. The heat transfer treatment method comprises the following steps: acquiring internal dirty page generation rates of a source end virtual machine at a plurality of historical time points through a pseudo target end virtual machine corresponding to the source end virtual machine, and determining an idle bandwidth value of each historical time point; respectively determining thermal migration opportunity evaluation parameters corresponding to the historical time points according to the internal memory dirty page generation rate and the idle bandwidth value of each historical time point; and training a thermal migration opportunity determination model by using the thermal migration opportunity evaluation parameters corresponding to the historical time points so as to execute a thermal migration process at the thermal migration time points predicted by the trained thermal migration opportunity determination model. The technical scheme of the embodiment of the disclosure can accurately determine the opportunity of thermal migration.
Description
Technical Field
Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a thermal migration processing method, a thermal migration processing apparatus, a storage medium, and an electronic device.
Background
This section is intended to provide a background or context to the embodiments of the disclosure recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
In cloud computing resource management, Live Migration (Live Migration) is an important means for realizing resource allocation as an important function of Virtual Machine (Virtual Machine) saving and recovery. In reality, the live migration of the virtual machine is required in some scenarios, for example, the scenarios include system or hardware upgrade, cloud host load balancing, resource allocation, and the like.
When the thermal migration is needed, whether the thermal migration is suitable currently is generally judged according to manual experience. Although it can be determined through manual experience that factors such as memory change rate, CPU (Central Processing Unit) utilization rate, throughput of the internal and external networks and the like all affect whether live migration can be successfully executed, at present, a measurement standard cannot be accurately constructed. In this case, when live migration is performed by using manual experience, a problem that the live migration affects the cloud host service may occur.
Disclosure of Invention
In order to solve the problem that the live migration may affect the cloud host service, in some technologies, a low peak period with a small traffic volume may be selected for the live migration. However, periods of small traffic volume are often difficult to determine accurately. In other techniques, a deep learning technique may be used to determine the timing of the thermal migration, however, in these deep learning techniques, a feature space for thermal migration needs to be formed, the feature space includes important indexes that affect the thermal migration, and referring to fig. 1, these indexes are more in number, and in the process of actually determining the timing of the thermal migration, the operation complexity is higher.
Therefore, an improved thermal migration processing scheme is highly desirable to more accurately determine the timing of thermal migration.
In this context, embodiments of the present disclosure are intended to provide a thermal migration processing method, a thermal migration processing apparatus, a storage medium, and an electronic device.
According to a first aspect of the present disclosure, there is provided a thermal migration processing method including: acquiring internal dirty page generation rates of a source end virtual machine at a plurality of historical time points through a pseudo target end virtual machine corresponding to the source end virtual machine, and determining an idle bandwidth value of each historical time point; respectively determining thermal migration opportunity evaluation parameters corresponding to the historical time points according to the internal memory dirty page generation rate and the idle bandwidth value of each historical time point; and training a thermal migration opportunity determination model by using the thermal migration opportunity evaluation parameters corresponding to the historical time points so as to execute a thermal migration process at the thermal migration time points predicted by the trained thermal migration opportunity determination model.
Optionally, the executing the thermal migration process at the thermal migration time point predicted by the trained thermal migration opportunity determination model includes: acquiring internal dirty page generation rates of the source end virtual machine at a plurality of current time points through the pseudo target end virtual machine, and determining an idle bandwidth value of each current time point; respectively determining thermal migration opportunity evaluation parameters corresponding to the current time points according to the internal memory dirty page generation rate and the idle bandwidth value of each current time point; and processing the thermal migration opportunity evaluation parameters corresponding to the current time points by using the trained thermal migration opportunity determination model to determine thermal migration time points, and executing a thermal migration process at the thermal migration time points.
Optionally, the obtaining, by a pseudo target end virtual machine corresponding to a source end virtual machine, internal dirty page generation rates of the source end virtual machine at a plurality of historical time points includes: and for a target historical time point, reading the memory dirty page amount generated by the source end virtual machine in unit time through the pseudo target end virtual machine to serve as the memory dirty page generation rate of the target historical time point.
Optionally, the thermal migration processing method further includes: writing the read memory dirty pages into the empty equipment by the pseudo target end virtual machine aiming at the target historical time point; wherein the bare device discards written dirty pages of memory.
Optionally, the thermal migration processing method further includes: determining occupied bandwidth values aiming at the target historical time points; and calculating the difference value between the total bandwidth value and the occupied bandwidth value as the idle bandwidth value corresponding to the target historical time point.
Optionally, writing the read memory dirty page into the empty device by the pseudo target side virtual machine includes: and if the generation rate of the dirty memory pages at the target historical time point is greater than the idle bandwidth value at the target historical time point, the virtual machine at the pseudo target end reads the dirty memory pages in an iterative copy mode and writes the dirty memory pages into the idle device.
Optionally, the thermal migration processing method further includes: and calculating the ratio of the internal memory dirty page generation rate to the idle bandwidth value as a thermal migration opportunity evaluation parameter corresponding to the target historical time point.
According to a second aspect of the present disclosure, there is provided a thermal migration processing apparatus including: the data acquisition module is used for acquiring the internal memory dirty page generation rates of a source end virtual machine at a plurality of historical time points through a pseudo target end virtual machine corresponding to the source end virtual machine and determining the idle bandwidth value of each historical time point; the opportunity evaluation parameter determination module is used for respectively determining thermal migration opportunity evaluation parameters corresponding to the historical time points according to the memory dirty page generation rate and the idle bandwidth value of each historical time point; and the opportunity determination model training module is used for training the thermal migration opportunity determination model by using the thermal migration opportunity evaluation parameters corresponding to the historical time points so as to execute the thermal migration process at the thermal migration time points predicted by the thermal migration opportunity determination model after training.
Optionally, the timing determination model training module is configured to perform: acquiring internal dirty page generation rates of the source end virtual machine at a plurality of current time points through the pseudo target end virtual machine, and determining an idle bandwidth value of each current time point; respectively determining thermal migration opportunity evaluation parameters corresponding to the current time points according to the internal memory dirty page generation rate and the idle bandwidth value of each current time point; and processing the thermal migration opportunity evaluation parameters corresponding to the current time points by using the trained thermal migration opportunity determination model to determine thermal migration time points, and executing a thermal migration process at the thermal migration time points.
Optionally, the data acquisition module includes a dirty page generation rate acquisition unit.
Specifically, the dirty page generation rate acquisition unit is configured to perform: and for a target historical time point, reading the memory dirty page amount generated by the source end virtual machine in unit time through the pseudo target end virtual machine to serve as the memory dirty page generation rate of the target historical time point.
Optionally, the thermal migration processing apparatus further includes a dirty page processing module.
Specifically, the dirty page processing module is configured to perform: writing the read memory dirty pages into the empty equipment by the pseudo target end virtual machine aiming at the target historical time point; wherein the bare device discards written dirty pages of memory.
Optionally, the data obtaining module includes an idle bandwidth value calculating unit.
Specifically, the idle bandwidth value calculating unit is configured to perform: determining occupied bandwidth values aiming at the target historical time points; and calculating the difference value between the total bandwidth value and the occupied bandwidth value as the idle bandwidth value corresponding to the target historical time point.
Optionally, writing the read memory dirty page into the empty device by the pseudo target side virtual machine includes: and if the generation rate of the dirty memory pages at the target historical time point is greater than the idle bandwidth value at the target historical time point, the virtual machine at the pseudo target end reads the dirty memory pages in an iterative copy mode and writes the dirty memory pages into the idle device.
Optionally, the opportunity evaluation parameter determination module is configured to perform: and calculating the ratio of the internal memory dirty page generation rate to the idle bandwidth value as a thermal migration opportunity evaluation parameter corresponding to the target historical time point.
According to a third aspect of the present disclosure, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the thermal migration processing method of any one of the above embodiments.
According to a fourth aspect of the present disclosure, there is provided an electronic device comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the thermal migration processing method according to any one of the above embodiments via executing the executable instructions.
According to the thermal migration processing method, the thermal migration processing device, the storage medium and the electronic equipment, the internal memory dirty page generation rate of the source end virtual machine at each historical time point is determined by sending dirty pages to the pseudo target end virtual machine, the thermal migration opportunity evaluation parameters corresponding to each historical time point are determined by combining the idle bandwidth values of each historical time point, and the thermal migration opportunity determination model is trained by using the thermal migration opportunity evaluation parameters to obtain the trained thermal migration opportunity determination model. Therefore, when the thermal migration is required, the thermal migration timing determination model can be used for determining an appropriate thermal migration time point. On one hand, by adopting the scheme disclosed by the invention, the thermal migration time point can be accurately determined, and the influence of thermal migration on the cloud host service is controlled to an extremely low degree; on the other hand, the dirty page is sent to the virtual machine at the pseudo target end, the conventional thermal migration communication mode is reused in the pseudo migration mode, and the accuracy of dirty page statistics is guaranteed under the condition that the frequency of the cloud host is not reduced; in yet another aspect, the dirty page generation rate and the free bandwidth value are taken into consideration, and a model is combined to evaluate whether the time point is suitable for performing the hot migration, so that compared with a scheme that a large number of indexes are adopted in some technologies, the scheme disclosed by the invention is simple and effective.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
FIG. 1 illustrates a schematic of an indicator used in determining timing for thermal migration in some techniques;
FIG. 2 schematically illustrates a flow chart of a method of thermomigration processing according to an exemplary embodiment of the present disclosure;
FIG. 3 shows a schematic diagram of a thermomigration processing architecture according to an example embodiment of the present disclosure;
FIG. 4 schematically illustrates a block diagram of a thermal migration processing apparatus according to an exemplary embodiment of the present disclosure;
FIG. 5 schematically illustrates a block diagram of a data acquisition module according to an exemplary embodiment of the present disclosure;
FIG. 6 schematically illustrates a block diagram of a thermophoresis processing unit, according to another exemplary embodiment of the present disclosure;
FIG. 7 schematically illustrates a block diagram of a data acquisition module according to another exemplary embodiment of the present disclosure;
fig. 8 schematically shows a block diagram of an electronic device according to an exemplary embodiment of the present disclosure.
In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Detailed Description
The principles and spirit of the present disclosure will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given solely for the purpose of enabling those skilled in the art to better understand and to practice the present disclosure, and are not intended to limit the scope of the present disclosure in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be embodied as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.
According to an embodiment of the present disclosure, a thermal migration processing method, a thermal migration processing apparatus, a storage medium, and an electronic device are provided.
In this document, any number of elements in the drawings is by way of example and not by way of limitation, and any nomenclature is used solely for differentiation and not by way of limitation.
The principles and spirit of the present disclosure are explained in detail below with reference to several representative embodiments of the present disclosure.
Summary of The Invention
In determining when it is appropriate for a hot migration scenario, a time point with a small traffic volume is usually selected, but the time point has a large error and is not accurate enough. In addition, in some schemes for determining the heat migration opportunity by using a deep learning technology, the number of indexes to be considered is large, so that the algorithm complexity is high.
The inventor finds that when the hot migration time is determined, the generation condition of the dirty pages and the available bandwidth are two key factors, and the hot migration time is deduced by using the two factors, so that an accurate result can be obtained, the cloud host service cannot be influenced, and the processing process is simple.
Based on the above, the basic idea of the present disclosure is: determining the internal memory dirty page generation rate of the source end virtual machine at each historical time point by adopting a mode of sending dirty pages to the pseudo target end virtual machine, determining heat transfer opportunity evaluation parameters corresponding to each historical time point by combining the idle bandwidth value of each historical time point, and training a heat transfer opportunity determination model by using the heat transfer opportunity evaluation parameters to obtain a trained heat transfer opportunity determination model. Therefore, when the thermal migration is required, the thermal migration timing determination model can be used for determining an appropriate thermal migration time point.
Having described the general principles of the present disclosure, various non-limiting embodiments of the present disclosure are described in detail below.
Application scenario overview
It should be noted that the following application scenarios are merely illustrated to facilitate understanding of the spirit and principles of the present disclosure, and embodiments of the present disclosure are not limited in this respect. Rather, embodiments of the present disclosure may be applied to any scenario where applicable.
The method comprises the steps of obtaining internal dirty page generation rates of a source end virtual machine at a plurality of historical time points through a pseudo target end virtual machine corresponding to the source end virtual machine, and determining idle bandwidth values of the historical time points. And determining thermal migration opportunity evaluation parameters of each historical time point based on the memory dirty page generation rate and the idle bandwidth value, and training a thermal migration opportunity determination model by using the thermal migration opportunity evaluation parameters to obtain the trained thermal migration opportunity determination model. The thermal migration opportunity determination model is a model constructed based on a deep learning technology.
Under the condition that the thermal migration is required due to reasons such as hardware upgrading, load balancing and the like, the memory dirty page generation rates and the idle bandwidth values of a plurality of current time points can be acquired, corresponding thermal migration opportunity evaluation parameters are determined, the thermal migration opportunity evaluation parameters are input into the trained thermal migration opportunity determination model, so that a proper thermal migration time point is determined, and the thermal migration process is executed at the thermal migration time point.
Exemplary method
A method of a thermal migration process according to an exemplary embodiment of the present disclosure is described below with reference to fig. 2.
Fig. 2 schematically illustrates a flow chart of a method of thermomigration processing according to an exemplary embodiment of the present disclosure. Referring to fig. 2, a thermal migration processing method according to an exemplary embodiment of the present disclosure may include the steps of:
s22, acquiring internal dirty page generation rates of the source end virtual machine at a plurality of historical time points through a pseudo target end virtual machine corresponding to the source end virtual machine, and determining an idle bandwidth value of each historical time point.
The method and the system do not specially limit the service types of the related virtual machines, and do not limit the service range of the corresponding cloud host.
In an exemplary embodiment of the present disclosure, the source virtual machine is a virtual machine to be live migrated. Generally, a target-side virtual machine refers to a virtual machine that performs cloud service by replacing a source-side virtual machine after performing live migration, a pseudo target-side virtual machine in the exemplary embodiment of the present disclosure is not a real virtual machine, and the pseudo target-side virtual machine may implement pseudo migration by using an empty device, so as to count dirty pages in an internal memory of the source-side virtual machine.
In addition, a dirty memory page in the present disclosure refers to a memory page (page) with data errors or modified.
Specifically, a plurality of historical time points may be determined within a predetermined time. For example, the predetermined time may be a month, and a plurality of historical time points may be determined every ten minutes within a month. However, it should be understood that the interval between the historical time points and the predetermined time may be set to other values or forms, and the present disclosure is not limited thereto.
In the following, the internal dirty page generation rate at a historical time point is determined as an example, and the historical time point is referred to as a target historical time point. The target historical time point may be any one of a plurality of historical time points, and the determination process of the internal dirty page generation rate of other historical time points is similar.
And for the target historical time point, reading the memory dirty page amount generated by the source virtual machine in each unit time through the pseudo target virtual machine to serve as the memory dirty page generation rate of the target historical time point, wherein the unit of the memory dirty page generation rate can be MB/S. For example, the amount of dirty memory pages generated in the source virtual machine 1S is determined as the dirty memory page generation rate.
Specifically, a fork sub-process may be constructed for receiving the memory dirty page generated by the source end virtual machine, in a process of reading the memory dirty page amount generated by the source end virtual machine per unit time by the pseudo target end virtual machine.
After receiving the dirty memory page, the fork sub-process writes to a null device (/ dev/null), wherein the null device discards all written data, i.e., the null device discards the written dirty memory page.
The method has the advantages that a dirty page receiving end of the memory is forged through the fork subprocess, on one hand, the existing thermal migration communication mode can be reused, and the code complexity is reduced; on the other hand, the process of receiving dirty memory pages may be simplified.
Further, a free bandwidth value for the target historical point in time can be determined. Specifically, an occupied bandwidth value may be determined, and a difference between the total bandwidth value and the occupied bandwidth value may be calculated as an idle bandwidth value. The unit of the free bandwidth value is MB/S.
According to some embodiments of the present disclosure, in a process of utilizing the fork mechanism, if the dirty page generation rate at the target historical time point is greater than the free bandwidth value at the target historical time point, the dirty page in the memory may be read in an iterative copy manner and written into an empty device. Because the internal memory dirty pages may be generated in real time, the iterative copy process may be understood as reading the internal memory dirty pages generated in multiple times within a unit time. In addition, it should be noted that, for the last iteration process, the cloud host is not suspended, and only the operation of canceling the live migration is performed.
Fig. 3 is a schematic diagram illustrating a source end virtual machine sending a dirty page to a pseudo target end virtual machine according to an exemplary embodiment of the present disclosure. Referring to fig. 3, within the cloud host 30, the pseudo target end virtual machine 32 may obtain a dirty page in the source end virtual machine 31. Based on the above description, the pseudo target-side virtual machine 32 can be understood as a fork subprocess mechanism.
In the above, the memory dirty page generation rate and the free bandwidth value are determined by taking one historical time point as an example, and thus, the memory dirty page generation rates of all the historical time points and the free bandwidth values of all the historical time points can be obtained by adopting a similar process.
And S24, respectively determining thermal migration opportunity evaluation parameters corresponding to the historical time points according to the internal memory dirty page generation rate and the idle bandwidth value of each historical time point.
Still taking the target historical time point as an example, the ratio of the dirty page generation rate to the free bandwidth value at the target historical time point may be used as the evaluation parameter of the thermal migration time corresponding to the target historical time point.
S26, training a thermal migration opportunity determination model by using thermal migration opportunity evaluation parameters corresponding to the historical time points, so that a thermal migration process is executed at the thermal migration time points predicted by the trained thermal migration opportunity determination model.
In an exemplary embodiment of the present disclosure, the thermal migration opportunity determination model may be a deep learning-based model, and specifically, may be a prediction model constructed by using a tensrflow framework, and the present disclosure does not limit the structure of the model.
Specifically, a group of two-dimensional data can be constructed by taking time as an abscissa and taking the thermal migration opportunity evaluation parameters corresponding to the historical time points as an ordinate, the thermal migration opportunity determination model is used for finding out which time period the thermal migration opportunity evaluation parameter is relatively minimum, and the rule is determined by inputting data in a period of time. In this case, the above-described thermomigration opportunity determination model may be a regression prediction-based model, a kalman filter prediction model, a back propagation neural network model, or the like.
And training the thermal migration opportunity model by adopting the thermal migration opportunity evaluation parameters corresponding to the historical time points, then verifying the trained model by adopting a mode of manually inputting data, and applying the model to practice after the verification is passed.
When a live migration is required due to reasons such as hardware upgrade and load balancing, first, the pseudo target virtual machine may obtain the memory dirty page generation rates of the source virtual machine at multiple current time points, and determine the idle bandwidth value at each current time point. The specific process is similar to the process of determining the memory dirty page generation rate and the free bandwidth value at the historical time point in step S22, and is not described again.
Next, thermal migration timing evaluation parameters corresponding to each current time point can be respectively determined according to the internal dirty page generation rate and the free bandwidth value of each current time point. And then, processing the thermal migration opportunity evaluation parameters corresponding to the current time points by using the trained thermal migration opportunity determination model to determine thermal migration time points, and executing a thermal migration process at the thermal migration time points.
In summary, with the adoption of the thermal migration processing method according to the exemplary embodiment of the present disclosure, on one hand, by adopting the scheme of the present disclosure, the thermal migration time point can be accurately determined, and the influence of thermal migration on the cloud host service is controlled to a very low degree; on the other hand, the dirty page is sent to the virtual machine at the pseudo target end, the conventional thermal migration communication mode is reused in the pseudo migration mode, and the accuracy of dirty page statistics is guaranteed under the condition that the frequency of the cloud host is not reduced; in yet another aspect, the dirty page generation rate and the free bandwidth value are taken into consideration, and a model is combined to evaluate whether the time point is suitable for performing the hot migration, so that compared with a scheme that a large number of indexes are adopted in some technologies, the scheme disclosed by the invention is simple and effective.
Exemplary devices
Having introduced the method of a live migration process according to an exemplary embodiment of the present disclosure, a live migration process apparatus included in a server according to an exemplary embodiment of the present disclosure will be described next with reference to fig. 4 to 7.
Referring to fig. 4, the thermal migration processing apparatus 4 according to an exemplary embodiment of the present disclosure may include a data acquisition module 41, an opportunity evaluation parameter determination module 43, and an opportunity determination model training module 45.
Specifically, the data obtaining module 41 may be configured to obtain, by a pseudo target end virtual machine corresponding to a source end virtual machine, internal dirty page generation rates of the source end virtual machine at multiple historical time points, and determine an idle bandwidth value at each historical time point; the opportunity evaluation parameter determining module 43 may be configured to determine, according to the memory dirty page generation rate and the free bandwidth value at each historical time point, a thermal migration opportunity evaluation parameter corresponding to each historical time point respectively; the opportunity determination model training module 45 may be configured to train the thermal migration opportunity determination model by using the thermal migration opportunity evaluation parameters corresponding to the historical time points, so as to execute the thermal migration process at the thermal migration time point predicted by the thermal migration opportunity determination model after training.
By using the thermal migration processing device according to the exemplary embodiment of the disclosure, on one hand, the thermal migration time point can be accurately determined by using the scheme of the disclosure, and the influence of thermal migration on the cloud host service is controlled to a very low degree; on the other hand, the dirty page is sent to the virtual machine at the pseudo target end, the conventional thermal migration communication mode is reused in the pseudo migration mode, and the accuracy of dirty page statistics is guaranteed under the condition that the frequency of the cloud host is not reduced; in yet another aspect, the dirty page generation rate and the free bandwidth value are taken into consideration, and a model is combined to evaluate whether the time point is suitable for performing the hot migration, so that compared with a scheme that a large number of indexes are adopted in some technologies, the scheme disclosed by the invention is simple and effective.
According to an exemplary embodiment of the present disclosure, the timing determination model training module 45 may be configured to perform: acquiring internal dirty page generation rates of the source end virtual machine at a plurality of current time points through the pseudo target end virtual machine, and determining an idle bandwidth value of each current time point; respectively determining thermal migration opportunity evaluation parameters corresponding to the current time points according to the internal memory dirty page generation rate and the idle bandwidth value of each current time point; and processing the thermal migration opportunity evaluation parameters corresponding to the current time points by using the trained thermal migration opportunity determination model to determine thermal migration time points, and executing a thermal migration process at the thermal migration time points.
According to an exemplary embodiment of the present disclosure, referring to fig. 5, the data acquisition module 41 may include a dirty page generation rate acquisition unit 501.
Specifically, the dirty page generation rate obtaining unit 501 may be configured to perform: and for a target historical time point, reading the memory dirty page amount generated by the source end virtual machine in unit time through the pseudo target end virtual machine to serve as the memory dirty page generation rate of the target historical time point.
According to an exemplary embodiment of the present disclosure, referring to fig. 6, the thermal migration processing apparatus 6 may further include a dirty page processing module 61, compared to the thermal migration processing apparatus 4.
In particular, the dirty page processing module 61 may be configured to perform: writing the read memory dirty pages into the empty equipment by the pseudo target end virtual machine aiming at the target historical time point; wherein the bare device discards written dirty pages of memory.
According to an exemplary embodiment of the present disclosure, referring to fig. 7, the data acquisition module 41 may include an idle-bandwidth-value calculation unit 701.
Specifically, the idle bandwidth value calculating unit 701 may be configured to perform: determining occupied bandwidth values aiming at the target historical time points; and calculating the difference value between the total bandwidth value and the occupied bandwidth value as the idle bandwidth value corresponding to the target historical time point.
According to an exemplary embodiment of the present disclosure, writing the read memory dirty pages into the empty device by the pseudo target side virtual machine includes: and if the generation rate of the dirty memory pages at the target historical time point is greater than the idle bandwidth value at the target historical time point, the virtual machine at the pseudo target end reads the dirty memory pages in an iterative copy mode and writes the dirty memory pages into the idle device.
According to an exemplary embodiment of the present disclosure, the opportunity evaluation parameter determination module 43 may be configured to perform: and calculating the ratio of the internal memory dirty page generation rate to the idle bandwidth value as a thermal migration opportunity evaluation parameter corresponding to the target historical time point.
Since each functional module of the thermal migration processing apparatus according to the embodiment of the present disclosure is the same as that in the embodiment of the present invention, it is not described herein again.
Exemplary device
Having described the method and apparatus for thermal migration processing according to the exemplary embodiments of the present disclosure, an electronic device according to the exemplary embodiments of the present disclosure will be described. Among them, the electronic equipment of the exemplary embodiment of this disclosure includes one of the above-mentioned thermal migration processing apparatuses.
As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
In some possible embodiments, an electronic device according to the present disclosure may include at least one processing unit, and at least one memory unit. Wherein the storage unit stores program code that, when executed by the processing unit, causes the processing unit to perform the steps in the method for thermomigration processing according to various exemplary embodiments of the present disclosure described in the "methods" section above in this specification. For example, the processing unit may perform step S22 and step S26 as described in fig. 2.
An electronic device 800 according to this embodiment of the disclosure is described below with reference to fig. 8. The electronic device 800 shown in fig. 8 is only an example and should not bring any limitations to the functionality and scope of use of the embodiments of the present disclosure.
As shown in fig. 8, electronic device 800 is in the form of a general purpose computing device. The components of the electronic device 800 may include, but are not limited to: the at least one processing unit 810, the at least one memory unit 820, a bus 830 connecting different system components (including the memory unit 820 and the processing unit 810), and a display unit 840.
Wherein the storage unit stores program code that is executable by the processing unit 810 to cause the processing unit 810 to perform steps according to various exemplary embodiments of the present disclosure as described in the "exemplary methods" section above in this specification. For example, the processing unit 810 may perform steps S22 and S26 as described in fig. 2.
The storage unit 820 may include readable media in the form of volatile memory units such as a random access memory unit (RAM)8201 and/or a cache memory unit 8202, and may further include a read only memory unit (ROM) 8203.
The storage unit 820 may also include a program/utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 800 may also communicate with one or more external devices 900 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 800, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 800 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 850. Also, the electronic device 800 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 860. As shown, the network adapter 860 communicates with the other modules of the electronic device 800 via the bus 830. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Exemplary program product
In some possible embodiments, various aspects of the present disclosure may also be implemented in a form of a program product including program code for causing a terminal device to perform steps in a live migration processing method according to various exemplary embodiments of the present disclosure described in the above-mentioned "method" section of this specification when the program product is run on the terminal device, for example, the terminal device may perform steps S22 and S26 as described in fig. 2.
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. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical disk, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In addition, as technology advances, readable storage media should also be interpreted accordingly.
Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device over 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 (e.g., over the internet using an internet service provider).
It should be noted that although several modules or sub-modules of the thermophoresis processing apparatus are mentioned in the above detailed description, such division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the modules described above may be embodied in one module, in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module described above may be further divided into embodiments by a plurality of modules.
Further, while the operations of the disclosed methods are depicted in the drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
While the spirit and principles of the present disclosure have been described with reference to several particular embodiments, it is to be understood that the present disclosure is not limited to the particular embodiments disclosed, nor is the division of aspects, which is for convenience only as the features in such aspects may not be combined to benefit. The disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (14)
1. A thermal migration processing method is characterized by comprising:
acquiring internal dirty page generation rates of a source end virtual machine at a plurality of historical time points through a pseudo target end virtual machine corresponding to the source end virtual machine, and determining an idle bandwidth value of each historical time point; wherein the idle bandwidth value is the difference between the total bandwidth value and the occupied bandwidth value;
respectively determining thermal migration opportunity evaluation parameters corresponding to the historical time points according to the internal memory dirty page generation rate and the idle bandwidth value of each historical time point;
and training a thermal migration opportunity determination model by using the thermal migration opportunity evaluation parameters corresponding to the historical time points so as to execute a thermal migration process at the thermal migration time points predicted by the trained thermal migration opportunity determination model.
2. The method according to claim 1, wherein performing the thermal migration process at the thermal migration time point predicted by the trained thermal migration timing determination model includes:
acquiring internal dirty page generation rates of the source end virtual machine at a plurality of current time points through the pseudo target end virtual machine, and determining an idle bandwidth value of each current time point;
respectively determining thermal migration opportunity evaluation parameters corresponding to the current time points according to the internal memory dirty page generation rate and the idle bandwidth value of each current time point;
and processing the thermal migration opportunity evaluation parameters corresponding to the current time points by using the trained thermal migration opportunity determination model to determine thermal migration time points, and executing a thermal migration process at the thermal migration time points.
3. The live migration processing method according to claim 1 or 2, wherein obtaining, by a pseudo target end virtual machine corresponding to a source end virtual machine, the in-memory dirty page generation rates of the source end virtual machine at a plurality of historical time points includes:
and for a target historical time point, reading the memory dirty page amount generated by the source end virtual machine in unit time through the pseudo target end virtual machine to serve as the memory dirty page generation rate of the target historical time point.
4. The thermal migration processing method according to claim 3, further comprising:
writing the read memory dirty pages into the empty equipment by the pseudo target end virtual machine aiming at the target historical time point; wherein the bare device discards written dirty pages of memory.
5. The live migration processing method according to claim 4, wherein writing the read memory dirty pages into a blank device by the pseudo target side virtual machine includes:
and if the generation rate of the dirty memory pages at the target historical time point is greater than the idle bandwidth value at the target historical time point, the virtual machine at the pseudo target end reads the dirty memory pages in an iterative copy mode and writes the dirty memory pages into the idle device.
6. The thermal migration processing method according to claim 4, further comprising:
and calculating the ratio of the internal memory dirty page generation rate to the idle bandwidth value as a thermal migration opportunity evaluation parameter corresponding to the target historical time point.
7. A thermal migration processing apparatus, comprising:
the data acquisition module is used for acquiring the internal memory dirty page generation rates of a source end virtual machine at a plurality of historical time points through a pseudo target end virtual machine corresponding to the source end virtual machine and determining the idle bandwidth value of each historical time point; wherein the idle bandwidth value is the difference between the total bandwidth value and the occupied bandwidth value;
the opportunity evaluation parameter determination module is used for respectively determining thermal migration opportunity evaluation parameters corresponding to the historical time points according to the memory dirty page generation rate and the idle bandwidth value of each historical time point;
and the opportunity determination model training module is used for training the thermal migration opportunity determination model by using the thermal migration opportunity evaluation parameters corresponding to the historical time points so as to execute the thermal migration process at the thermal migration time points predicted by the thermal migration opportunity determination model after training.
8. The thermal migration processing apparatus according to claim 7, wherein the timing determination model training module is specifically configured to: acquiring internal dirty page generation rates of the source end virtual machine at a plurality of current time points through the pseudo target end virtual machine, and determining an idle bandwidth value of each current time point; respectively determining thermal migration opportunity evaluation parameters corresponding to the current time points according to the internal memory dirty page generation rate and the idle bandwidth value of each current time point; and processing the thermal migration opportunity evaluation parameters corresponding to the current time points by using the trained thermal migration opportunity determination model to determine thermal migration time points, and executing a thermal migration process at the thermal migration time points.
9. The thermophoresis processing device according to claim 7 or 8, wherein the data acquisition module includes:
and a dirty page generation rate obtaining unit, configured to read, by using the pseudo target end virtual machine, a memory dirty page amount generated by the source end virtual machine per unit time, as a memory dirty page generation rate of a target historical time point.
10. The thermal migration processing apparatus according to claim 9, further comprising:
the dirty page processing module is used for writing the read internal memory dirty pages into empty equipment through the virtual machine at the pseudo target end aiming at the target historical time point; wherein the bare device discards written dirty pages of memory.
11. The thermomigration processing device of claim 10, wherein the dirty page processing module is specifically configured to: and if the generation rate of the dirty memory pages at the target historical time point is greater than the idle bandwidth value at the target historical time point, the virtual machine at the pseudo target end reads the dirty memory pages in an iterative copy mode and writes the dirty memory pages into the idle device.
12. The migration processing apparatus according to claim 10, wherein the timing evaluation parameter determining module is specifically configured to: and calculating the ratio of the internal memory dirty page generation rate to the idle bandwidth value as a thermal migration opportunity evaluation parameter corresponding to the target historical time point.
13. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the thermomigration processing method of any one of claims 1 to 6.
14. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the method of thermomigration process of any of claims 1-6 via execution of the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910994946.7A CN110737509B (en) | 2019-10-18 | 2019-10-18 | Thermal migration processing method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910994946.7A CN110737509B (en) | 2019-10-18 | 2019-10-18 | Thermal migration processing method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110737509A CN110737509A (en) | 2020-01-31 |
| CN110737509B true CN110737509B (en) | 2022-04-19 |
Family
ID=69270105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910994946.7A Active CN110737509B (en) | 2019-10-18 | 2019-10-18 | Thermal migration processing method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110737509B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112783605B (en) * | 2021-01-27 | 2024-02-23 | 深信服科技股份有限公司 | Method, device, equipment and storage medium for thermomigration of virtual machine |
| CN115016891A (en) * | 2022-06-01 | 2022-09-06 | 阿里巴巴（中国）有限公司 | Thermomigration result prediction method, thermomigration method, electronic device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103365704A (en) * | 2012-03-26 | 2013-10-23 | 中国移动通信集团公司 | Memory pre-copying method in virtual machine migration, device executing memory pre-copying method and system |
| CN103955399A (en) * | 2014-04-30 | 2014-07-30 | 华为技术有限公司 | Migrating method and device for virtual machine, as well as physical host |
| CN107479944A (en) * | 2017-07-20 | 2017-12-15 | 上海交通大学 | Mix the adaptive thermophoresis dispatching method of virutal machine memory and system under cloud mode |
| CN108037980A (en) * | 2018-01-02 | 2018-05-15 | 腾讯科技（深圳）有限公司 | Control performs the method, apparatus and readable storage medium storing program for executing of live migration of virtual machine |
| JP2019057236A (en) * | 2017-09-22 | 2019-04-11 | 富士通株式会社 | Information providing program, information providing device, and information providing method |
-
2019
- 2019-10-18 CN CN201910994946.7A patent/CN110737509B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103365704A (en) * | 2012-03-26 | 2013-10-23 | 中国移动通信集团公司 | Memory pre-copying method in virtual machine migration, device executing memory pre-copying method and system |
| CN103955399A (en) * | 2014-04-30 | 2014-07-30 | 华为技术有限公司 | Migrating method and device for virtual machine, as well as physical host |
| CN107479944A (en) * | 2017-07-20 | 2017-12-15 | 上海交通大学 | Mix the adaptive thermophoresis dispatching method of virutal machine memory and system under cloud mode |
| JP2019057236A (en) * | 2017-09-22 | 2019-04-11 | 富士通株式会社 | Information providing program, information providing device, and information providing method |
| CN108037980A (en) * | 2018-01-02 | 2018-05-15 | 腾讯科技（深圳）有限公司 | Control performs the method, apparatus and readable storage medium storing program for executing of live migration of virtual machine |
Non-Patent Citations (2)
| Title |
|---|
| 基于动态调整阈值的虚拟机迁移算法;赵 春等;《计算机应用》;20170930;全文 * |
| 改进指数平滑预测的虚拟机自适应迁移策略;刘春霞等;《计算机系统应用》;20190331;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110737509A (en) | 2020-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9442791B2 (en) | Building an intelligent, scalable system dump facility | |
| US11790239B2 (en) | Deep learning testing | |
| US9367408B2 (en) | Optimizing placement plans for host failure in cloud computing environments | |
| US10671506B2 (en) | Evaluating fairness in devices under test | |
| CN110737509B (en) | Thermal migration processing method and device, storage medium and electronic equipment | |
| US10210296B2 (en) | Adaptive bug-search depth for simple and deep counterexamples | |
| US10380313B1 (en) | Implementation and evaluation of designs for heterogeneous computing platforms with hardware acceleration | |
| US9152584B2 (en) | Providing bus resiliency in a hybrid memory system | |
| US10761922B2 (en) | Method and system to decrease measured usage license charges for diagnostic data collection | |
| US10783059B2 (en) | Method and system to decrease measured usage license charges for diagnostic data collection | |
| US11334349B2 (en) | Removing feature flag-related codebase from applications | |
| CN110674044B (en) | Coverage rate acquisition method, system, equipment and medium for function automation test | |
| US20150154082A1 (en) | Provisioning memory in a memory system for mirroring | |
| WO2022227869A1 (en) | Locate neural network performance hot spots | |
| CN109783745B (en) | Method, device and computer equipment for personalized typesetting of pages | |
| JP6816824B2 (en) | Distributed systems, data management devices, data management methods, and programs | |
| US8966133B2 (en) | Determining a mapping mode for a DMA data transfer | |
| US11662906B2 (en) | Method, electronic device, and computer program product for upgrading storage system | |
| CN110908818A (en) | Verification method, device, equipment and storage medium | |
| CN104424060A (en) | Method and device for determining faults | |
| CN115454354B (en) | Data processing method, system, electronic device and storage medium | |
| JP7478037B2 (en) | Continuous integration system and continuous integration method | |
| CN116136813B (en) | Method, device and storage medium for simulating adaptive multi-model avionics signals | |
| KR102103591B1 (en) | Method for extracting test case with boundary value analysis and equivalence partitioning, and apparatus using the same | |
| CN115543813A (en) | Health code iteration test method and device, electronic equipment and storage medium |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 310052 Room 301, Building No. 599, Changhe Street Network Business Road, Binjiang District, Hangzhou City, Zhejiang Province Patentee after: Hangzhou NetEase Shuzhifan Technology Co.,Ltd. Address before: 310052 Room 301, Building No. 599, Changhe Street Network Business Road, Binjiang District, Hangzhou City, Zhejiang Province Patentee before: HANGZHOU LANGHE TECHNOLOGY Ltd. |
|
| CP01 | Change in the name or title of a patent holder |