CN102890554A - Power supply management system and method - Google Patents
Power supply management system and method Download PDFInfo
- Publication number
- CN102890554A CN102890554A CN2011102066368A CN201110206636A CN102890554A CN 102890554 A CN102890554 A CN 102890554A CN 2011102066368 A CN2011102066368 A CN 2011102066368A CN 201110206636 A CN201110206636 A CN 201110206636A CN 102890554 A CN102890554 A CN 102890554A
- Authority
- CN
- China
- Prior art keywords
- use amount
- resource use
- virtual machine
- main frame
- grouping
- 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
Images
Abstract
The invention relates to a power supply management system and method. The method comprises the following steps of: triggering a control computer to generate power supply management commands for host machines; when the type of the power supply management commands is the first type, performing first grouping on virtual machines according to the resource usage amount occupied by the virtual machines in the host machines; performing dynamic migration on the virtual machines according to the first grouping of the virtual machines; closing the idle host machines after the completion of the dynamic migration of the virtual machines; when the type of the power supply management commands is the second type, opening the closed host machines and services thereof; performing second grouping on the virtual machines according to the resource usage amount occupied by the virtual machines in the host machines; and performing the dynamic migration on the virtual machines according to the second grouping of the virtual machines, and distributing all the virtual machines to all the host machines on average. The power supply consumption of the host machines can be saved by utilizing the power supply management system and method disclosed by the invention.
Description
Technical field
The present invention relates to a kind of power-supply management system and method.
Background technology
Along with the rise of virtual technology, a main frame container (Container) can be installed the configuration multiple host, and many virtual machines (Virtual Machine, VM) can be installed on the main frame (Host) usually.On general hardware configuration, each main frame all needs external power supply so that normal operation and service to be provided, because purpose and main services that each virtual machine exists are also different.
For example, one in intra-company the virtual machine as the network agent server, its use amount can be different because of company's commuter time, the work hours employee uses many, this moment, the volume of services of virtual machine was just heavy, and the host resource that uses (such as CPU, Memory, Network bandwidth) is just many, and the host resource that the quitting time uses then obviously reduces, many main frames are in idle condition substantially, cause the waste of power supply.
Summary of the invention
In view of above content, be necessary to provide a kind of power-supply management system, it can carry out dynamic migration to virtual machine according to the variation of the shared resource use amount of virtual machine in the main frame, and closes idle main frame.
In view of above content, be necessary to provide a kind of method for managing power supply, it can carry out dynamic migration to virtual machine according to the variation of the shared resource use amount of virtual machine in the main frame, and closes idle main frame.
A kind of power-supply management system, this system comprises:
The instruction generation module is used for triggering or the Event triggered mode by the time, triggers the generation of control computer to the power management instruction of main frame;
The instruction judge module, for the type of judging this power management instruction, the type of described power management instruction comprises the first kind and Second Type;
The grouping computing module is used for when the type of this power management instruction is the first kind, and the resource use amount shared according to virtual machine in the main frame carried out the grouping first time to virtual machine;
The dynamic migration module is used for according to the above-mentioned virtual machine grouping first time virtual machine being carried out dynamic migration;
The shutdown control module is used for closing idle main frame after finishing the virtual machine dynamic migration;
The start control module is used for when the type of this power management instruction is Second Type the main frame of open and close and service thereof;
Described grouping computing module also is used for behind the main frame and service thereof of open and close, and the resource use amount shared according to virtual machine in the main frame carried out the grouping second time to virtual machine; And
Described dynamic migration module also is used for according to the above-mentioned virtual machine grouping second time virtual machine being carried out dynamic migration, and all virtual machine mean allocation are arrived each main frame.
A kind of method for managing power supply, the method comprises the steps:
Instruction generates step, by time triggering or Event triggered mode, triggers the generation of control computer to the power management instruction of main frame;
The instruction determining step is judged the type of this power management instruction, and the type of described power management instruction comprises the first kind and Second Type;
Grouping calculation procedure one, when the type of this power management instruction was the first kind, the resource use amount shared according to virtual machine in the main frame carried out the grouping first time to virtual machine;
The dynamic migration step 1 according to the above-mentioned virtual machine grouping first time, is carried out dynamic migration to virtual machine;
Shutdown control step after finishing the virtual machine dynamic migration, is closed idle main frame;
Start control step, when the type of this power management instruction is Second Type, the main frame of open and close and service thereof;
Grouping calculation procedure two, behind the main frame and service thereof of open and close, the resource use amount shared according to virtual machine in the main frame carried out the grouping second time to virtual machine; And
The dynamic migration step 2 according to the above-mentioned virtual machine grouping second time, is carried out dynamic migration to virtual machine, and all virtual machine mean allocation are arrived each main frame.
Preceding method can be carried out by electronic equipment (such as computer), and wherein this electronic equipment has display screen, one or more processor, the storer that has attached graphic user interface (GUI) and is kept at one or more modules, program or the instruction set that is used for carrying out these methods in the storer.In certain embodiments, this electronic equipment provides the several functions that comprises radio communication.
The instruction that is used for the execution preceding method can be included in the computer program that is configured to by one or more processors execution.
Compared to prior art, described power-supply management system and method, it can carry out dynamic migration to virtual machine according to the variation of the shared resource use amount of virtual machine in the main frame, and closes idle main frame, thereby saves the electrical source consumption of main frame.
Description of drawings
Fig. 1 is the applied environment synoptic diagram that the present invention controls computer.
Fig. 2 is the structural representation that the present invention controls computer.
Fig. 3 is the functional block diagram of power-supply management system.
Fig. 4 is the process flow diagram of the preferred embodiment of method for managing power supply of the present invention.
Fig. 5 is the synoptic diagram of certain main frame container.
Fig. 6 is under the power management instruction of first kind control, and each virtual machine among Fig. 5 is carried out synoptic diagram behind the dynamic migration.
Fig. 7 is under the power management instruction of Second Type control, and each virtual machine among Fig. 6 is carried out synoptic diagram behind the dynamic migration.
The main element symbol description
| The control computer | ?2 |
| Database | ?3 |
| Network | ?4 |
| Main frame | ?5 |
| Display device | ?20 |
| Input equipment | ?22 |
| Storer | ?23 |
| Power-supply management system | ?24 |
| Processor | ?25 |
| The instruction generation module | ?201 |
| The instruction judge module | ?202 |
| The grouping computing module | ?203 |
| The dynamic migration module | ?204 |
| The start control module | ?205 |
| The shutdown control module | ?206 |
Embodiment
As shown in Figure 1, be the applied environment synoptic diagram that the present invention controls computer.In the present embodiment, described control computer 2 links to each other with a plurality of main frames 5 by network 4, and links to each other with database 3 by the database connection.Described network 4 can be intranet (Intranet), also can be the communication network of internet (Internet) or other type, such as GPRS, Wi-Fi/WLAN, 3G/WCDMA, 3.5G/HSDPA etc.
Described control computer 2 is used for sending the power management instruction to main frame 5, and closes or open according to the Type Control main frame 5 of this power management instruction.
Described database 3 is used for the data of each virtual machine on the storage host 5 etc.Wherein, described virtual machine data includes, but not limited to name, identifier (Identifier, ID), the operating system (Operating System, OS) of using and the remark information etc. of virtual machine.
Consult shown in Figure 2ly, this control computer 2 comprises display device 20, input equipment 22, storer 23, power-supply management system 24 and the processor 25 that links to each other by data bus.
Described storer 23 is for the data such as program code of storing described power-supply management system 24.Described display device 20 is used for the virtual machine data of demonstration main frame 5 etc.Described input equipment 22 is used for the various data that the input user arranges, such as the remark information of virtual machine etc.
Described power-supply management system 24 is used for sending the power management instruction to main frame 5, and closes or open according to the Type Control main frame 5 of this power management instruction, and detailed process is following to be described.
In the present embodiment, described power-supply management system 24 can be divided into one or more modules, described one or more module is stored in the described storer 23 and is configured to and carried out by one or more processors (present embodiment is a processor 25), to finish the present invention.For example, consult shown in Figure 3ly, described power-supply management system 24 is divided into instruction generation module 201, instruction judge module 202, grouping computing module 203, dynamic migration module 204, start control module 205 and shutdown control module 206.The alleged module of the present invention is to finish the program segment of a specific function, is more suitable in describing the implementation of software in control computer 2 than program.
As shown in Figure 4, be the process flow diagram of the preferred embodiment of method for managing power supply of the present invention.
Step S10, instruction generation module 201 triggered or the Event triggered mode by the time, triggered the power management instruction that control computer 2 generates main frame 5.In the present embodiment, described time triggering mode is, when arriving the default time, send the power management instruction to main frame 5, for example, after coming off duty 2 hours, to the power management instruction of the main frame 5 transmission first kind, close idle main frame, be on duty front 1 hour, to the power management instruction of main frame 5 transmission Second Types, the main frame of open and close and service thereof.
Described Event triggered mode is, the shared resource use amount of virtual machine in a certain main frame is less than the first preset value (such as 40%), or the summation of the shared resource use amount of the virtual machine in the All hosts is during less than the second preset value (such as 200%), to the power management instruction of the main frame 5 transmission first kind, close idle main frame.The shared resource use amount of virtual machine in a certain main frame is greater than the 3rd preset value (such as 90%), or the summation of the shared resource use amount of the virtual machine in the All hosts is during greater than the 4th preset value (such as 500%), to the power management instruction of main frame 5 transmission Second Types, the main frame of open and close and service thereof.In the present embodiment, described resource use amount comprises, but be not limited to, CPU use amount, the network bandwidth (Network Bandwidth), hard disk usage space or internal memory use amount (Memory Usage), also can be the compound condition of above-mentioned resource use amount, such as CPU use amount and the network bandwidth.
Step S11, instruction judge module 202 is judged the type of this power management instruction.In the present embodiment, the type of described power management instruction comprises the first kind and Second Type.Wherein, the power management instruction of the first kind refers to, closes idle main frame, to save power supply.The power management instruction of Second Type refers to, the main frame of open and close and service thereof are to reduce the resource use amount of OL main frame.If the type of this power management instruction is the first kind, execution in step S21-S22 then; If the type of this power management instruction is Second Type, execution in step S31-S32 then.
Step S21, if the type of this power management instruction is the first kind, the resource use amount that the computing module 203 that then divides into groups is shared according to virtual machine in the main frame is carried out the grouping first time to virtual machine.Below illustrate the concrete steps that for the first time grouping is calculated.
Suppose the triggering of triggering mode employing time, the resource use amount adopts the CPU use amount, and the main frame container comprises four host computer (consulting shown in Figure 5), respectively called after Host01, Host02, Host03, Host04.Wherein, the virtual machine management program Hypervisor of Host01 is managing virtual machine VM01 and VM02, the virtual machine management program Hypervisor of Host02 is managing virtual machine VM03 and VM04, the virtual machine management program Hypervisor of Host03 is managing virtual machine VM05, and the virtual machine management program Hypervisor of Host04 is managing virtual machine VM06.
(a1) after coming off duty 2 hours, instruction generation module 201 sends the power management instruction of the first kind to above-mentioned four host computer (Host01, Host02, Host03, Host04), grouping computing module 203 obtains the shared CPU use amount of each virtual machine in these 4 main frames, be stored in CPU use amount tabulation (or being called the tabulation of first resource use amount), be assumed to be＜CPU Usage List1＞(VM01=20%, VM02=15%, VM03=5%, VM04=10%, VM05=30%, VM06=3%).
In the present embodiment, this grouping computing module 203 can obtain above-mentioned CPU use amount tabulation according to the current state of these 4 main frames.In other embodiments, CPU use amount tabulation also can be one group of empirical value (being preset value), is drawn according to actual observation by the keeper, as adds up in After Hours a period of time, the mean value of the shared CPU use amount of each virtual machine in the main frame.
(a2) grouping computing module 203 calculates the summation U that a CPU uses the shared CPU use amount of the virtual machine of All hosts in the tabulation
Total, according to the critical value U of predefined CPU use amount
Threshold, obtain the host number N that needs to keep open state
0In the present embodiment, represent the quantity (N=4) of All hosts with N, the critical value of supposing this CPU use amount is 80%, and it is 83% that the summation of the CPU use amount that the virtual machine in above-mentioned 4 main frames is shared can calculate, and then needs to keep the host number N of open state
0=int (U
Threshold÷ U
Total)+1=int (83% ÷ 80%)+1=2, wherein int () represents bracket function (Round Function).In other embodiments, this need to keep the host number N of open state
0Also can be an empirical value (being preset value), be drawn according to actual observation by the keeper, for example, can get N
0=3.
Then, grouping computing module 203 calculates the average CPU use amount Vavg1 of the main frame that needs the maintenance open state, wherein Vavg1=(U
Total÷ N
0).
(a3) grouping computing module 203 calculates the summation of the CPU use amount of different virtual machine combination in CPU use amount tabulation, and it is minimum and more than or equal to the combination of above-mentioned average CPU use amount Vavg1, as a grouping to find out summation.
(a4) if a CPU uses the CPU use amount of only remaining two virtual machines in the tabulation, computing module 203 end of packet of then dividing into groups are calculated, and it is to obtain at last the result that the grouping of finding in the step (a3) and a CPU use two remaining in tabulation virtual machines.If a CPU uses the CPU use amount that remains next or three above virtual machines in the tabulation, then the grouping of finding in the step (a3) is used the tabulation from a CPU to remove, then carry out N
0=N
0-1, and return step (a2).
Method according to above-mentioned steps (a1)-(a4), can calculate＜CPU Usage List1＞virtual machine of (20%, 15%, 5%, 10%, 30%, 3%) be grouped into (＜20%, 15%, 5%＞,＜10%, 30%, 3%＞), be that virtual machine VM01, VM02, VM03 are first group, virtual machine VM04, VM05, VM06 are second group.
Step S22, dynamic migration module 204 is carried out dynamic migration according to the virtual machine grouping first time that above-mentioned steps S21 calculates to virtual machine, and then, shutdown control module 206 is closed idle main frame.According to top example, virtual machine VM03 will be moved to Host01, and virtual machine VM05 and VM06 will be moved to Host02, and then Host03 and Host04 will be in idle condition, shutdown control module 206 is closed Host03 and Host04, and the virtual machine synoptic diagram behind the dynamic migration is consulted shown in 6.
In the present embodiment, dynamic migration module 204 is assigned to Host01 with first group virtual machine (VM01, VM02, VM03), and second group virtual machine (VM04, VM05, VM06) is assigned to Host02.In other embodiments, also can Random assignment, for example, dynamic migration module 204 is assigned to Host02 with first group virtual machine (VM01, VM02, VM03), and second group virtual machine (VM04, VM05, VM06) is assigned to Host01.
Step S31, if the type of this power management instruction is Second Type, main frame and the service thereof of the control module of then starting shooting 205 open and close.Then, the grouping computing module 203 resource use amount shared according to virtual machine in the main frame carried out the grouping second time to virtual machine.Below still continue to use the concrete steps that top for the second time grouping of example explanation is calculated.
(b1) be on duty front 1 hour, start control module 205 is opened the Host03 among Fig. 6 and Host04.Instruction generation module 201 sends the power management instruction of Second Type to above-mentioned four host computer (Host01, Host02, Host03, Host04), grouping computing module 203 obtains the shared CPU use amount of each virtual machine in these 4 main frames, be stored in the tabulation of the 2nd CPU use amount, be assumed to be＜CPU Usage List 2＞(VM01=25%, VM02=20%, VM03=25%, VM04=25%, VM05=50%, VM06=30%).
In the present embodiment, this grouping computing module 203 can obtain above-mentioned the 2nd CPU use amount tabulation (or being called the tabulation of Secondary resource use amount) according to the current state of these 4 main frames.In other embodiments, the 2nd CPU use amount tabulation also can be one group of empirical value, drawn according to actual observation by the keeper, and within a period of time after the statistics working, the mean value of the shared CPU use amount of each virtual machine in the main frame.
(b2) grouping computing module 203 calculates the summation U of the shared CPU use amount of the virtual machine of All hosts in the tabulation of the 2nd CPU use amount
Total, according to the quantity N of All hosts, calculate the average CPU use amount Vavg2 of All hosts, wherein Vavg2=(U
Total÷ N).
(b3) grouping computing module 203 calculates the summation of the CPU use amount of different virtual machine combination in the 2nd CPU use amount tabulation, and it is minimum and more than or equal to the combination of above-mentioned average CPU use amount Vavg2, as a grouping to find out summation.
(b4) if only be left the CPU use amount of two virtual machines in the tabulation of the 2nd CPU use amount, computing module 203 end of packet of then dividing into groups are calculated, and two remaining virtual machines are to obtain at last the result in the grouping of finding in the step (b3) and the tabulation of the 2nd CPU use amount.If remain the next one in the tabulation of the 2nd CPU use amount or (comprise three) more than three the CPU use amount of virtual machine, then the grouping of finding in the step (b3) is removed from the tabulation of the 2nd CPU use amount, then carry out N=N-1, and return step (b2).
Method according to above-mentioned steps (b1)-(b4), can calculate＜CPU Usage List2＞virtual machine of (25%, 20%, 25%, 25%, 50%, 30%) be grouped into (＜25%, 20%＞,＜25%, 25%＞,＜50%＞,＜30%＞), namely virtual machine VM01, VM02 are first group, virtual machine VM03, VM04 are second group, virtual machine VM05 is the 3rd group, and virtual machine VM06 is the 4th group.
Step S32, dynamic migration module 204 is carried out dynamic migration according to the virtual machine grouping second time that above-mentioned steps S31 calculates to virtual machine, and all virtual machine mean allocation are arrived each main frame.According to top example, the virtual machine VM06 of Host2 will be moved to Host04 among Fig. 6, and virtual machine VM05 will be moved to Host03, and the virtual machine VM03 of Host01 will be moved to Host02, and the virtual machine synoptic diagram behind the dynamic migration is consulted shown in 5.
In the present embodiment, dynamic migration module 204 is assigned to Host01 with first group virtual machine (VM01, VM02), second group virtual machine (VM03, VM04) is assigned to Host02, the 3rd group virtual machine (VM05) is assigned to Host03, and the 4th group virtual machine (VM06) is assigned to Host04.In other embodiments, also can Random assignment, for example, dynamic migration module 204 is assigned to Host02 with first group virtual machine (VM01, VM02), second group virtual machine (VM03, VM04) is assigned to Host03, the 3rd group virtual machine (VM05) is assigned to Host01, and the 4th group virtual machine (VM06) is assigned to Host04, and the virtual machine synoptic diagram behind the dynamic migration is consulted shown in Figure 7.
In the present embodiment, dynamic migration module 204 is CPU use amounts shared according to virtual machine in the main frame, and virtual machine is divided into groups to calculate.In other embodiments, described dynamic migration module 204 also can be according to other resource use amounts, such as the network bandwidth (Network Bandwidth), hard disk usage space, internal memory use amount (Memory Usage), or the compound condition of above-mentioned resource use amount, such as CPU use amount and the network bandwidth, calculate the grouping of virtual machine.
It should be noted that at last, above embodiment is only unrestricted in order to technical scheme of the present invention to be described, although with reference to preferred embodiment the present invention is had been described in detail, those of ordinary skill in the art is to be understood that, can make amendment or be equal to replacement technical scheme of the present invention, and not break away from the spirit and scope of technical solution of the present invention.
Claims (12)
1. a power-supply management system is characterized in that, this system comprises:
The instruction generation module is used for triggering or the Event triggered mode by the time, triggers the generation of control computer to the power management instruction of main frame;
The instruction judge module, for the type of judging this power management instruction, the type of described power management instruction comprises the first kind and Second Type;
The grouping computing module is used for when the type of this power management instruction is the first kind, and the resource use amount shared according to virtual machine in the main frame carried out the grouping first time to virtual machine;
The dynamic migration module is used for according to the above-mentioned virtual machine grouping first time virtual machine being carried out dynamic migration;
The shutdown control module is used for closing idle main frame after finishing the virtual machine dynamic migration;
The start control module is used for when the type of this power management instruction is Second Type the main frame of open and close and service thereof;
Described grouping computing module also is used for behind the main frame and service thereof of open and close, and the resource use amount shared according to virtual machine in the main frame carried out the grouping second time to virtual machine; And
Described dynamic migration module also is used for according to the above-mentioned virtual machine grouping second time virtual machine being carried out dynamic migration, and all virtual machine mean allocation are arrived each main frame.
2. power-supply management system as claimed in claim 1 is characterized in that, described time triggering mode is when arriving the first Preset Time, to the power management instruction of the main frame transmission first kind, to close idle main frame; When arriving the second Preset Time, to the power management instruction of main frame transmission Second Type, the main frame of open and close and service thereof;
Described Event triggered mode is, the shared resource use amount of virtual machine in a certain main frame is less than the first preset value, or the summation of the shared resource use amount of the virtual machine in the All hosts is during less than the second preset value, sends the power management instruction of the first kind to main frame, closes idle main frame; The shared resource use amount of virtual machine in a certain main frame is greater than the 3rd preset value, or the summation of the shared resource use amount of the virtual machine in the All hosts is during greater than the 4th preset value, to the power management instruction of main frame transmission Second Type, the main frame of open and close and service thereof.
3. power-supply management system as claimed in claim 1 is characterized in that, described grouping computing module carries out the grouping first time to virtual machine and comprises:
(a1) obtain the shared resource use amount of each virtual machine in the All hosts, be stored in the tabulation of first resource use amount;
(a2) calculate the summation U of the shared resource use amount of the virtual machine of All hosts in the tabulation of this first resource use amount
Total, definite host number N that needs to keep open state
0, then calculate the average resource use amount Vavg1 that need to keep the main frame of open state, wherein Vavg1=(U
Total÷ N
0);
(a3) in the tabulation of this first resource use amount, calculate the summation of the resource use amount of different virtual machine combination, it is minimum and more than or equal to the combination of above-mentioned average resource use amount Vavg1, as a grouping to find out summation; And
(a4) if only be left the resource use amount of two virtual machines in this first resource use amount tabulation, then end of packet is calculated, with two remaining in the grouping found in the step (a3) and the tabulation of this first resource use amount virtual machines as last group result; Or
If the resource use amount of the surplus next one or three above virtual machines in this first resource use amount tabulation then removes the grouping of finding in the step (a3) from the tabulation of first resource use amount, then carry out N
0=N
0-1, and return step (a2).
4. power-supply management system as claimed in claim 3 is characterized in that, this first resource use amount tabulation is one group of preset value, or obtains according to the current state of All hosts.
5. power-supply management system as claimed in claim 3 is characterized in that, this need to keep the host number N of open state
0Be a preset value, or according to the critical value U of predefined resource use amount
ThresholdObtain;
If the critical value U according to predefined resource use amount
ThresholdObtain, then need to keep the host number N of open state
0=int (U
Threshold÷ U
Total)+1, wherein, int () represents bracket function.
6. power-supply management system as claimed in claim 1 is characterized in that, described grouping computing module carries out the grouping second time to virtual machine and comprises:
(b1) obtain the shared resource use amount of each virtual machine in the All hosts, be stored in the tabulation of Secondary resource use amount;
(b2) calculate the summation U of the shared resource use amount of the virtual machine of All hosts in the tabulation of this Secondary resource use amount
Total, according to the quantity N of All hosts, calculate the average resource use amount Vavg2 of All hosts, wherein, Vavg2=(U
Total÷ N);
(b3) in the tabulation of this Secondary resource use amount, calculate the summation of the resource use amount of different virtual machine combination, it is minimum and more than or equal to the combination of above-mentioned average resource use amount Vavg2, as a grouping to find out summation; And
(b4) if only be left the resource use amount of two virtual machines in this Secondary resource use amount tabulation, then end of packet is calculated, with two remaining in the grouping found in the step (b3) and the tabulation of this Secondary resource use amount virtual machines as last group result; Or
If the resource use amount of the surplus next one or three above virtual machines in this Secondary resource use amount tabulation then removes the grouping of finding in the step (b3) from this Secondary resource use amount tabulation, then carry out N=N-1, and return step (b2).
7. a method for managing power supply is characterized in that the method comprises the steps:
Instruction generates step, by time triggering or Event triggered mode, triggers the generation of control computer to the power management instruction of main frame;
The instruction determining step is judged the type of this power management instruction, and the type of described power management instruction comprises the first kind and Second Type;
Grouping calculation procedure one, when the type of this power management instruction was the first kind, the resource use amount shared according to virtual machine in the main frame carried out the grouping first time to virtual machine;
The dynamic migration step 1 according to the above-mentioned virtual machine grouping first time, is carried out dynamic migration to virtual machine;
Shutdown control step after finishing the virtual machine dynamic migration, is closed idle main frame;
Start control step, when the type of this power management instruction is Second Type, the main frame of open and close and service thereof;
Grouping calculation procedure two, behind the main frame and service thereof of open and close, the resource use amount shared according to virtual machine in the main frame carried out the grouping second time to virtual machine; And
The dynamic migration step 2 according to the above-mentioned virtual machine grouping second time, is carried out dynamic migration to virtual machine, and all virtual machine mean allocation are arrived each main frame.
8. method for managing power supply as claimed in claim 7 is characterized in that, described time triggering mode is when arriving the first Preset Time, to the power management instruction of the main frame transmission first kind, to close idle main frame; When arriving the second Preset Time, to the power management instruction of main frame transmission Second Type, the main frame of open and close and service thereof;
Described Event triggered mode is, the shared resource use amount of virtual machine in a certain main frame is less than the first preset value, or the summation of the shared resource use amount of the virtual machine in the All hosts is during less than the second preset value, sends the power management instruction of the first kind to main frame, closes idle main frame; The shared resource use amount of virtual machine in a certain main frame is greater than the 3rd preset value, or the summation of the shared resource use amount of the virtual machine in the All hosts is during greater than the 4th preset value, to the power management instruction of main frame transmission Second Type, the main frame of open and close and service thereof.
9. method for managing power supply as claimed in claim 7 is characterized in that, the described step that virtual machine is carried out dividing into groups for the first time comprises:
(a1) obtain the shared resource use amount of each virtual machine in the All hosts, be stored in the tabulation of first resource use amount;
(a2) calculate the summation U of the shared resource use amount of the virtual machine of All hosts in the tabulation of this first resource use amount
Total, definite host number N that needs to keep open state
0, then calculate the average resource use amount Vavg1 that need to keep the main frame of open state, wherein Vavg1=(U
Total÷ N
0);
(a3) in the tabulation of this first resource use amount, calculate the summation of the resource use amount of different virtual machine combination, it is minimum and more than or equal to the combination of above-mentioned average resource use amount Vavg1, as a grouping to find out summation; And
(a4) if only be left the resource use amount of two virtual machines in this first resource use amount tabulation, then end of packet is calculated, with two remaining in the grouping found in the step (a3) and the tabulation of this first resource use amount virtual machines as last group result; Or
If the resource use amount of the surplus next one or three above virtual machines in this first resource use amount tabulation then removes the grouping of finding in the step (a3) from the tabulation of first resource use amount, then carry out N
0=N
0-1, and return step (a2).
10. method for managing power supply as claimed in claim 9 is characterized in that, this first resource use amount tabulation is one group of preset value, or obtains according to the current state of All hosts.
11. method for managing power supply as claimed in claim 9 is characterized in that, this need to keep the host number N of open state
0Be a preset value, or according to the critical value U of predefined resource use amount
ThresholdObtain;
If the critical value U according to predefined resource use amount
ThresholdObtain, then need to keep the host number N of open state
0=int (U
Threshold÷ U
Total)+1, wherein, int () represents bracket function.
12. method for managing power supply as claimed in claim 7 is characterized in that, the described step that virtual machine is carried out dividing into groups for the second time comprises:
(b1) obtain the shared resource use amount of each virtual machine in the All hosts, be stored in the tabulation of Secondary resource use amount;
(b2) calculate the summation U of the shared resource use amount of the virtual machine of All hosts in the tabulation of this Secondary resource use amount
Total, according to the quantity N of All hosts, calculate the average resource use amount Vavg2 of All hosts, wherein, Vavg2=(U
Total÷ N);
(b3) in the tabulation of this Secondary resource use amount, calculate the summation of the resource use amount of different virtual machine combination, it is minimum and more than or equal to the combination of above-mentioned average resource use amount Vavg2, as a grouping to find out summation; And
(b4) if only be left the resource use amount of two virtual machines in this Secondary resource use amount tabulation, then end of packet is calculated, with two remaining in the grouping found in the step (b3) and the tabulation of this Secondary resource use amount virtual machines as last group result; Or
If the resource use amount of the surplus next one or three above virtual machines in this Secondary resource use amount tabulation then removes the grouping of finding in the step (b3) from this Secondary resource use amount tabulation, then carry out N=N-1, and return step (b2).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102066368A CN102890554A (en) | 2011-07-22 | 2011-07-22 | Power supply management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102066368A CN102890554A (en) | 2011-07-22 | 2011-07-22 | Power supply management system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102890554A true CN102890554A (en) | 2013-01-23 |
Family
ID=47534076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011102066368A Pending CN102890554A (en) | 2011-07-22 | 2011-07-22 | Power supply management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102890554A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279076A (en) * | 2013-04-24 | 2013-09-04 | 深圳市生波尔机电设备有限公司 | Text language-based power supply control method and device |
| WO2016115956A1 (en) * | 2015-01-23 | 2016-07-28 | 中兴通讯股份有限公司 | Scheduling method and scheduling device for business system based on cloud computing |
| 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 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1752896A (en) * | 2005-11-08 | 2006-03-29 | 北京大学 | Power source management method of embedded equipment under operation system cooperation and its system |
| CN101154130A (en) * | 2006-09-30 | 2008-04-02 | 联想(北京)有限公司 | Virtual machine system and its power supply management method |
| US20100070784A1 (en) * | 2008-09-15 | 2010-03-18 | Vmware, Inc. | Reducing Power Consumption in a Server Cluster |
| CN101916207A (en) * | 2010-08-28 | 2010-12-15 | 华为技术有限公司 | Energy saving method, device and system under desktop virtual environment |
| CN102118407A (en) * | 2009-12-31 | 2011-07-06 | 联想(北京)有限公司 | Method for reducing running power consumption of cluster job system, node and system |
-
2011
- 2011-07-22 CN CN2011102066368A patent/CN102890554A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1752896A (en) * | 2005-11-08 | 2006-03-29 | 北京大学 | Power source management method of embedded equipment under operation system cooperation and its system |
| CN101154130A (en) * | 2006-09-30 | 2008-04-02 | 联想(北京)有限公司 | Virtual machine system and its power supply management method |
| US20100070784A1 (en) * | 2008-09-15 | 2010-03-18 | Vmware, Inc. | Reducing Power Consumption in a Server Cluster |
| CN102118407A (en) * | 2009-12-31 | 2011-07-06 | 联想(北京)有限公司 | Method for reducing running power consumption of cluster job system, node and system |
| CN101916207A (en) * | 2010-08-28 | 2010-12-15 | 华为技术有限公司 | Energy saving method, device and system under desktop virtual environment |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279076A (en) * | 2013-04-24 | 2013-09-04 | 深圳市生波尔机电设备有限公司 | Text language-based power supply control method and device |
| CN103279076B (en) * | 2013-04-24 | 2015-11-18 | 深圳市生波尔机电设备有限公司 | Based on power control method and the device of text language |
| WO2016115956A1 (en) * | 2015-01-23 | 2016-07-28 | 中兴通讯股份有限公司 | Scheduling method and scheduling device for business system based on cloud computing |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hsu et al. | Smoothoperator: Reducing power fragmentation and improving power utilization in large-scale datacenters | |
| CA2741088C (en) | Methods of achieving cognizant power management | |
| CN110677305B (en) | Automatic scaling method and system in cloud computing environment | |
| CN106133693B (en) | Moving method, device and the equipment of virtual machine | |
| CN107247651B (en) | Cloud computing platform monitoring and early warning method and system | |
| CN102045321B (en) | Flow control method and system for software downloading | |
| CN104486445A (en) | Distributed extendable resource monitoring system and method based on cloud platform | |
| CN103684916A (en) | Method and system for intelligent monitoring and analyzing under cloud computing | |
| CN106603618A (en) | Cloud platform-based application auto scaling method | |
| CN105024842A (en) | Method and device for capacity expansion of server | |
| CN104601492A (en) | Method and device for controlling business flow under NFV framework | |
| CN103412786A (en) | High performance server architecture system and data processing method thereof | |
| WO2016069038A1 (en) | Policy based workload scaler | |
| CN104252390A (en) | Resource scheduling method, device and system | |
| US9411344B2 (en) | Energy saving monitoring method and device | |
| CN112650575B (en) | Resource scheduling method, device and cloud service system | |
| CN103645795A (en) | Cloud computing data center energy saving method based on ANN (artificial neural network) | |
| CN105302641A (en) | Node scheduling method and apparatus in virtual cluster | |
| CN106528065B (en) | A kind of thread acquisition methods and equipment | |
| CN112579304A (en) | Resource scheduling method, device, equipment and medium based on distributed platform | |
| CN110647392A (en) | Intelligent elastic expansion method based on container cluster | |
| CN109726007B (en) | Container arrangement quota management method and device and container arrangement system | |
| CN104461731A (en) | Virtual machine resource recycling method and device in dynamic resource expanding | |
| CN102890554A (en) | Power supply management system and method | |
| CN103944940A (en) | Equipment and method for dynamically configuring proxy server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130123 |