CN104991822A - Memory management method and apparatus - Google Patents
Memory management method and apparatus Download PDFInfo
- Publication number
- CN104991822A CN104991822A CN201510377321.8A CN201510377321A CN104991822A CN 104991822 A CN104991822 A CN 104991822A CN 201510377321 A CN201510377321 A CN 201510377321A CN 104991822 A CN104991822 A CN 104991822A
- Authority
- CN
- China
- Prior art keywords
- computing node
- physical memory
- virtual machine
- occupancy
- takies
- 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.)
- Pending
Links
Abstract
The invention discloses a memory management method and apparatus. The method comprises the steps of: for each computing node in a cloud computing system, monitoring a physical memory occupied by each virtual machine on the computing node and calculating the physical memory occupation rate of the computing node; and if the calculated physical memory occupation rate is greater than a preset first occupation rate threshold value, migrating the virtual machine with highest physical memory occupation rate on the computing node to other computing nodes. Through the technical scheme provided by the invention, the physical memory of the computing node is prevented from being exhausted, and the processing performance of each virtual machine running on the computing node is ensured, so that the user experience of the cloud computing system is improved.
Description
Technical field
The present invention relates to cloud computing technology, in espespecially a kind of cloud computing system, and the method and apparatus of managing internal memory.
Background technology
In cloud computing system, extensively adopt Intel Virtualization Technology, specifically, cloud computing system comprises mass data center, and each data center comprises a large amount of computing node as server, and every platform computing node is provided with one or more virtual machines.In existing cloud computing system, the physical memory of each virtual machine shared computation node on a computing node, when on computing node, namely initial setting up increases a virtual machine newly, for the maximum free physical memory of virtual machine initial setting up, that is, virtual machine uses physical memory to be less than or equal to its maximum free physical memory in running.
In order to improve the utilization factor of computing node, the summation of the maximum free physical memory of each virtual machine that usual computing node is arranged is greater than the physical memory of computing node, like this, the physical memory used when each virtual machine on computing node close to or when equaling its maximum free physical memory, the physical memory of computing node can be caused to exhaust, the handling property of computing node decreases, the handling property of each virtual machine correspondingly computing node run also decreases, thus have impact on the Consumer's Experience of cloud computing system.
Summary of the invention
In order to solve the problems of the technologies described above, the invention provides a kind of method and apparatus of managing internal memory, the physical memory of computing node can be avoided to exhaust, ensure the handling property of each virtual machine that computing node runs.
In order to reach the object of the invention, the invention discloses a kind of method of managing internal memory, comprising:
Each computing node in cloud computing system: monitor the physical memory that on computing node, each virtual machine takies, and calculate the physical memory occupancy of computing node;
If the physical memory occupancy calculated is greater than the first occupancy threshold value pre-set, computing node will take the maximum virtual machine (vm) migration of physical memory to other computing nodes.
The physical memory that on described supervision computing node, each virtual machine takies comprises:
Monitor according to the Looking Out Time that pre-sets the physical memory that each process of described each virtual machine takies, and calculate the physical memory that each virtual machine takies respectively; Wherein, virtual machine saves as the summation of the physical memory that its each process takies in taking.
Other computing nodes described are the idle computing node of an internal memory, and wherein, the idle computing node of described internal memory is the computing node that the physical memory occupancy calculated is less than the second occupancy threshold value pre-set.
In one embodiment of the invention, the idle computing node of described internal memory comprises two or more; Describedly to comprise computing node taking the maximum virtual machine (vm) migration of physical memory to other computing nodes:
By the described maximum virtual machine (vm) migration of physical memory that takies to the idle computing node of the internal memory that physical memory occupancy is minimum.
In another embodiment of the present invention, the idle computing node of described internal memory comprises two or more; Describedly to comprise computing node taking the maximum virtual machine (vm) migration of physical memory to other computing nodes:
The described maximum virtual machine priority migration of physical memory that takies is in the idle computing node of the minimum internal memory of the physical memory occupancy of same data center to current computing node.
The invention also discloses a kind of device of managing internal memory, comprise monitor unit and processing unit, wherein,
Monitor unit, for for each computing node in cloud computing system: monitor the physical memory that on computing node, each virtual machine takies, and calculate the physical memory occupancy of computing node;
Processing unit, when the physical memory occupancy for calculating when monitor unit is greater than the first occupancy threshold value pre-set, computing node will take the maximum virtual machine (vm) migration of physical memory to other computing nodes.
Described monitor unit is specifically for each computing node in cloud computing system: monitor according to the Looking Out Time pre-set the physical memory that each process of described each virtual machine takies, and calculates the physical memory that each virtual machine takies respectively; Wherein, virtual machine saves as the summation of the physical memory that its each process takies in taking.
Other computing nodes described are the idle computing node of an internal memory, and wherein, the idle computing node of described internal memory is the computing node that the physical memory occupancy calculated is less than the second occupancy threshold value pre-set.
In one embodiment of the invention, the idle computing node of described internal memory comprises two or more; Described processing unit specifically for: when the physical memory occupancy that monitor unit calculates is greater than the first occupancy threshold value pre-set, by the described maximum virtual machine (vm) migration of physical memory that takies to the idle computing node of the minimum internal memory of physical memory occupancy.
In another embodiment of the present invention, the idle computing node of described internal memory comprises two or more; Described processing unit specifically for: when the physical memory occupancy that monitor unit calculates is greater than the first occupancy threshold value pre-set, the described maximum virtual machine priority migration of physical memory that takies is in the idle computing node of the minimum internal memory of the memory usage of same data center to current computing node.
Compared with prior art, technical solution of the present invention comprises: each computing node in cloud computing system: monitor the physical memory that on computing node, each virtual machine takies, and calculate the physical memory occupancy of computing node; If the physical memory occupancy calculated is greater than the first occupancy threshold value pre-set, computing node will take the maximum virtual machine (vm) migration of physical memory to other computing nodes.Pass through technical solution of the present invention, achieve when detecting that the physical memory of computing node will exhaust, namely when the occupancy of physical memory is greater than the first occupancy threshold value, by the virtual machine (vm) migration of computing node on other computing nodes, the physical memory avoiding computing node exhausts, ensure that the handling property of each virtual machine that computing node runs, thus improve the Consumer's Experience of cloud computing system.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from instructions, or understand by implementing the present invention.Object of the present invention and other advantages realize by structure specifically noted in instructions, claims and accompanying drawing and obtain.
Accompanying drawing explanation
Accompanying drawing is used to provide the further understanding to technical solution of the present invention, and forms a part for instructions, is used from and explains technical scheme of the present invention, do not form the restriction to technical solution of the present invention with the embodiment one of the application.
Fig. 1 is the process flow diagram of the method for managing internal memory of the present invention;
Fig. 2 is the composition structural representation of the device of managing internal memory of the present invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly understand, hereinafter will be described in detail to embodiments of the invention by reference to the accompanying drawings.It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combination in any mutually.
Can perform in the computer system of such as one group of computer executable instructions in the step shown in the process flow diagram of accompanying drawing.Further, although show logical order in flow charts, in some cases, can be different from the step shown or described by order execution herein.
Fig. 1 is the process flow diagram of the method for managing internal memory of the present invention, as shown in Figure 1, comprising:
Step 101: each computing node in cloud computing system: monitor the physical memory that on computing node, each virtual machine takies, and calculate the occupancy of the physical memory of computing node.Wherein,
Monitor that the physical memory that on computing node, each virtual machine takies comprises:
Monitor according to the Looking Out Time pre-set the physical memory that each process of each virtual machine takies, and calculate the physical memory that each virtual machine takies respectively; Here, virtual machine saves as the summation of the physical memory that its each process takies in taking.The physical memory that each process takies can be obtained by the system interface of the physical memory taken for monitoring process that operates in that operating system on computing node provides or function.
The physical memory occupancy of computing node is the summation of the physical memory that on it, each virtual machine takies and the ratio of its physical memory.
Looking Out Time can be a minute level, as 1 minute or 5 minutes etc.
Step 102: if the physical memory occupancy calculated is greater than the first occupancy threshold value pre-set, computing node will take the maximum virtual machine (vm) migration of physical memory to other computing nodes.Wherein,
First occupancy threshold value can be number percent, as 90% or 95% etc.
In cloud computing system, how virtual machine is moved to another computing node from a computing node, belong to the conventional techniques means of those skilled in the art, the protection domain be not intended to limit the present invention, repeats no more herein.
Other computing nodes in step 102 are the idle computing node of an internal memory, and here, the idle computing node of internal memory is the computing node that the occupancy calculated is less than the second occupancy threshold value pre-set.Similarly, the second occupancy can be number percent, as 50% or 60%.
In one embodiment of the invention, when the idle computing node of internal memory comprises two or more, comprise computing node taking the maximum virtual machine (vm) migration of physical memory to other computing nodes in step 102: computing node will take the maximum virtual machine (vm) migration of physical memory to the idle computing node of the internal memory that physical memory occupancy is minimum.
In another embodiment of the present invention, when the idle computing node of internal memory comprises two or more, comprise computing node taking the maximum virtual machine (vm) migration of physical memory to other computing nodes in step 102: be in the minimum internal memory free time computing node of the memory usage of same data center by computing node taking the maximum virtual machine priority migration of physical memory to current computing node.Here for example,
Suppose that the idle computing node of internal memory comprises first node, Section Point and the 3rd node, there are two kinds of scenes, scene 1: first node and current computing node are in same data center, Section Point and the 3rd node are all in different pieces of information center with current computing node, scene 2: first node, Section Point and the 3rd node are all in different pieces of information center with current computing node, wherein, the 3rd node is the computing node that physical memory occupancy is minimum.
In scene 1, if the occupancy of the physical memory of current computing node is greater than the first occupancy threshold value, then will wherein take the maximum virtual machine (vm) migration of physical memory to first node.
In scene 2, if the occupancy of the physical memory of current computing node is greater than the first occupancy threshold value, computing node will take the maximum virtual machine (vm) migration of physical memory to the 3rd node.
Fig. 2 is the composition structural representation of the device of managing internal memory of the present invention, and this device is arranged in the equipment at network management system place of cloud computing system, wherein, network management system for each equipment of monitoring and configure in cloud computing system as computing node.As shown in Figure 2, comprise monitor unit and processing unit, wherein,
Monitor unit, for for each computing node in cloud computing system: monitor the physical memory that on computing node, each virtual machine takies, and calculate the physical memory occupancy of computing node.
Processing unit, when the physical memory occupancy for calculating when monitor unit is greater than the first occupancy threshold value pre-set, computing node will take the maximum virtual machine (vm) migration of physical memory to other computing nodes.
Monitor unit specifically for each computing node in cloud computing system: monitor the physical memory that each process of each virtual machine takies according to the Looking Out Time pre-set, and calculates the physical memory that each virtual machine takies respectively; Wherein, virtual machine saves as the summation of the physical memory that its each process takies in taking.
It should be noted that, other computing nodes are the idle computing node of an internal memory, and wherein, the idle computing node of internal memory is the computing node that the physical memory occupancy calculated is less than the second occupancy threshold value pre-set.
In one embodiment of the invention, when the idle computing node of internal memory comprises two or more, processing unit specifically for: when the physical memory occupancy that monitor unit calculates is greater than the first occupancy threshold value pre-set, the maximum virtual machine (vm) migration of physical memory will be taken to the idle computing node of the minimum internal memory of physical memory occupancy.
In another embodiment of the present invention, when the idle computing node of internal memory comprises two or more, processing unit specifically for: when the physical memory occupancy that monitor unit calculates is greater than the first occupancy threshold value pre-set, be in the idle computing node of the minimum internal memory of the memory usage of same data center by taking the maximum virtual machine priority migration of physical memory to current computing node.
Although the embodiment disclosed by the present invention is described above, the embodiment that described content only adopts for ease of understanding the present invention, and be not used to limit the present invention.Those of skill in the art belonging to any the present invention; under the prerequisite not departing from the spirit and scope disclosed by the present invention; any amendment and change can be carried out in the form implemented and details; but scope of patent protection of the present invention, the scope that still must define with appending claims is as the criterion.
Claims (10)
1. a method for managing internal memory, is characterized in that, comprising:
Each computing node in cloud computing system: monitor the physical memory that on computing node, each virtual machine takies, and calculate the physical memory occupancy of computing node;
If the physical memory occupancy calculated is greater than the first occupancy threshold value pre-set, computing node will take the maximum virtual machine (vm) migration of physical memory to other computing nodes.
2. method according to claim 1, is characterized in that, the physical memory that on described supervision computing node, each virtual machine takies comprises:
Monitor according to the Looking Out Time that pre-sets the physical memory that each process of described each virtual machine takies, and calculate the physical memory that each virtual machine takies respectively; Wherein, virtual machine saves as the summation of the physical memory that its each process takies in taking.
3. method according to claim 1, it is characterized in that, other computing nodes described are the idle computing node of an internal memory, and wherein, the idle computing node of described internal memory is the computing node that the physical memory occupancy calculated is less than the second occupancy threshold value pre-set.
4. method according to claim 3, is characterized in that, the idle computing node of described internal memory comprises two or more; Describedly to comprise computing node taking the maximum virtual machine (vm) migration of physical memory to other computing nodes:
By the described maximum virtual machine (vm) migration of physical memory that takies to the idle computing node of the internal memory that physical memory occupancy is minimum.
5. method according to claim 3, is characterized in that, the idle computing node of described internal memory comprises two or more; Describedly to comprise computing node taking the maximum virtual machine (vm) migration of physical memory to other computing nodes:
The described maximum virtual machine priority migration of physical memory that takies is in the idle computing node of the minimum internal memory of the physical memory occupancy of same data center to current computing node.
6. a device for managing internal memory, is characterized in that, comprises monitor unit and processing unit, wherein,
Monitor unit, for for each computing node in cloud computing system: monitor the physical memory that on computing node, each virtual machine takies, and calculate the physical memory occupancy of computing node;
Processing unit, when the physical memory occupancy for calculating when monitor unit is greater than the first occupancy threshold value pre-set, computing node will take the maximum virtual machine (vm) migration of physical memory to other computing nodes.
7. device according to claim 6, it is characterized in that, described monitor unit is specifically for each computing node in cloud computing system: monitor according to the Looking Out Time pre-set the physical memory that each process of described each virtual machine takies, and calculates the physical memory that each virtual machine takies respectively; Wherein, virtual machine saves as the summation of the physical memory that its each process takies in taking.
8. device according to claim 6, it is characterized in that, other computing nodes described are the idle computing node of an internal memory, and wherein, the idle computing node of described internal memory is the computing node that the physical memory occupancy calculated is less than the second occupancy threshold value pre-set.
9. device according to claim 8, is characterized in that, the idle computing node of described internal memory comprises two or more; Described processing unit specifically for: when the physical memory occupancy that monitor unit calculates is greater than the first occupancy threshold value pre-set, by the described maximum virtual machine (vm) migration of physical memory that takies to the idle computing node of the minimum internal memory of physical memory occupancy.
10. device according to claim 8, is characterized in that, the idle computing node of described internal memory comprises two or more; Described processing unit specifically for: when the physical memory occupancy that monitor unit calculates is greater than the first occupancy threshold value pre-set, the described maximum virtual machine priority migration of physical memory that takies is in the idle computing node of the minimum internal memory of the memory usage of same data center to current computing node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510377321.8A CN104991822A (en) | 2015-06-30 | 2015-06-30 | Memory management method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510377321.8A CN104991822A (en) | 2015-06-30 | 2015-06-30 | Memory management method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104991822A true CN104991822A (en) | 2015-10-21 |
Family
ID=54303638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510377321.8A Pending CN104991822A (en) | 2015-06-30 | 2015-06-30 | Memory management method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104991822A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279071A (en) * | 2015-10-28 | 2016-01-27 | 浪潮(北京)电子信息产业有限公司 | Virtual machine performance data acquisition method and system, and cloud computing platform |
| CN106230649A (en) * | 2016-09-20 | 2016-12-14 | 杭州迪普科技有限公司 | session resource management method and device |
| CN107301092A (en) * | 2016-04-15 | 2017-10-27 | 中移(苏州)软件技术有限公司 | A kind of cloud computing resource pool energy saving of system method, apparatus and system |
| CN107589981A (en) * | 2017-09-07 | 2018-01-16 | 北京百悟科技有限公司 | A kind of dynamic power management and dynamic resource scheduling method and device |
| CN107977264A (en) * | 2016-10-24 | 2018-05-01 | 阿里巴巴集团控股有限公司 | The dispatching method and device of a kind of virutal machine memory resource |
| CN109189574A (en) * | 2018-08-16 | 2019-01-11 | 郑州云海信息技术有限公司 | A kind of load equilibration scheduling method and system based on virtualization memory load monitoring |
| CN111813507A (en) * | 2020-07-22 | 2020-10-23 | 山东超越数控电子股份有限公司 | Method, system, equipment and medium for high availability of virtual machine based on sanlock |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101452406A (en) * | 2008-12-23 | 2009-06-10 | 北京航空航天大学 | Cluster load balance method transparent for operating system |
| CN101593133A (en) * | 2009-06-29 | 2009-12-02 | 北京航空航天大学 | Load balancing of resources of virtual machine method and device |
| CN102724277A (en) * | 2012-05-04 | 2012-10-10 | 华为技术有限公司 | Virtual machine thermomigration method, virtual machine arrangement method, server and cluster system |
| CN103077082A (en) * | 2013-01-08 | 2013-05-01 | 中国科学院深圳先进技术研究院 | Method and system for distributing data center load and saving energy during virtual machine migration |
| CN103888501A (en) * | 2012-12-24 | 2014-06-25 | 华为技术有限公司 | Virtual machine migration method and device |
-
2015
- 2015-06-30 CN CN201510377321.8A patent/CN104991822A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101452406A (en) * | 2008-12-23 | 2009-06-10 | 北京航空航天大学 | Cluster load balance method transparent for operating system |
| CN101593133A (en) * | 2009-06-29 | 2009-12-02 | 北京航空航天大学 | Load balancing of resources of virtual machine method and device |
| CN102724277A (en) * | 2012-05-04 | 2012-10-10 | 华为技术有限公司 | Virtual machine thermomigration method, virtual machine arrangement method, server and cluster system |
| CN103888501A (en) * | 2012-12-24 | 2014-06-25 | 华为技术有限公司 | Virtual machine migration method and device |
| CN103077082A (en) * | 2013-01-08 | 2013-05-01 | 中国科学院深圳先进技术研究院 | Method and system for distributing data center load and saving energy during virtual machine migration |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279071A (en) * | 2015-10-28 | 2016-01-27 | 浪潮(北京)电子信息产业有限公司 | Virtual machine performance data acquisition method and system, and cloud computing platform |
| CN107301092A (en) * | 2016-04-15 | 2017-10-27 | 中移(苏州)软件技术有限公司 | A kind of cloud computing resource pool energy saving of system method, apparatus and system |
| CN107301092B (en) * | 2016-04-15 | 2020-11-10 | 中移(苏州)软件技术有限公司 | Energy-saving method, device and system for cloud computing resource pool system |
| CN106230649A (en) * | 2016-09-20 | 2016-12-14 | 杭州迪普科技有限公司 | session resource management method and device |
| CN106230649B (en) * | 2016-09-20 | 2019-07-09 | 杭州迪普科技股份有限公司 | Session resource management method and device |
| CN107977264A (en) * | 2016-10-24 | 2018-05-01 | 阿里巴巴集团控股有限公司 | The dispatching method and device of a kind of virutal machine memory resource |
| CN107589981A (en) * | 2017-09-07 | 2018-01-16 | 北京百悟科技有限公司 | A kind of dynamic power management and dynamic resource scheduling method and device |
| CN109189574A (en) * | 2018-08-16 | 2019-01-11 | 郑州云海信息技术有限公司 | A kind of load equilibration scheduling method and system based on virtualization memory load monitoring |
| CN111813507A (en) * | 2020-07-22 | 2020-10-23 | 山东超越数控电子股份有限公司 | Method, system, equipment and medium for high availability of virtual machine based on sanlock |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104991822A (en) | Memory management method and apparatus | |
| US20170337086A1 (en) | Method, Apparatus, and System for Adjusting Deployment Location of Virtual Machine | |
| US9392050B2 (en) | Automatic configuration of external services based upon network activity | |
| KR101814560B1 (en) | Virtual machine migration management method, apparatus, and system | |
| KR102134547B1 (en) | Risk identification method, risk identification device, and cloud risk identification device and system | |
| JP2011180889A (en) | Network resource management system, device, method and program | |
| CN111181850B (en) | Data packet flooding suppression method, device and equipment and computer storage medium | |
| CN104283951A (en) | Method and device for migrating instances and system | |
| CN110647392A (en) | Intelligent elastic expansion method based on container cluster | |
| EP3310093A1 (en) | Traffic control method and apparatus | |
| CN103399791A (en) | Method and device for migrating virtual machines on basis of cloud computing | |
| CN111418187A (en) | Scalable statistics and analysis mechanism in cloud networks | |
| CN110471769B (en) | Resource management method and device for virtual machine | |
| CN105094278A (en) | information processing method and device | |
| US11455293B2 (en) | Counting method, counter and storage medium | |
| CN105701128A (en) | Query statement optimization method and apparatus | |
| CN111400241B (en) | Data reconstruction method and device | |
| CN106775925B (en) | Quota processing method and device for CPU of virtual machine | |
| CN116938953A (en) | Block chain-based data processing method and device, electronic equipment and storage medium | |
| CN106878356B (en) | Scheduling method and computing node | |
| CN104866375A (en) | Virtual machine migration method and apparatus | |
| CN111124669A (en) | Operation method, system, terminal and storage medium of distributed SaaS software | |
| CN109165135B (en) | Data management method, computer readable storage medium and terminal equipment | |
| CN108429704B (en) | Node resource allocation method and device | |
| CN113992378A (en) | Safety monitoring method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151021 |