CN107301092A - A kind of cloud computing resource pool energy saving of system method, apparatus and system - Google Patents
A kind of cloud computing resource pool energy saving of system method, apparatus and system Download PDFInfo
- Publication number
- CN107301092A CN107301092A CN201610236186.XA CN201610236186A CN107301092A CN 107301092 A CN107301092 A CN 107301092A CN 201610236186 A CN201610236186 A CN 201610236186A CN 107301092 A CN107301092 A CN 107301092A
- Authority
- CN
- China
- Prior art keywords
- virtual network
- network node
- node
- integrated
- resource
- 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.)
- Granted
Links
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
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
-
- 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
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/485—Task life-cycle, e.g. stopping, restarting, resuming execution
- G06F9/4856—Task life-cycle, e.g. stopping, restarting, resuming execution resumption being on a different machine, e.g. task migration, virtual machine migration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/503—Resource availability
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a kind of cloud computing resource pool energy saving of system method, this method includes：When the resource overall availability of all virtual network nodes is less than the first predetermined threshold value, virtual network node to be integrated is determined；The virtual network service on virtual network node to be integrated is migrated to destination virtual network node.The present invention further simultaneously discloses a kind of cloud computing resource pool energy saving of system device, and a kind of cloud computing resource pool energy saving of system system.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of cloud computing resource pool energy saving of system method,
Apparatus and system.
Background technology
With flourishing for cloud computing, it is widely applied in all trades and professions.And it is used as cloud computing base
The virtual network of plinth Core Feature, has also obtained vast software defined network (Software Defined
Network, SDN) manufacturer positive support and promotion.At present, from the performance of cloud computing resources cell system (such as
Bandwidth, central processing unit (Central Processing Unit, CPU), internal memory) and stability (High Availabitity)
Upper to consider, virtual network service is generally deployed in independent server or SDN equipment, huge to support
Virtual machine cluster is to the network bandwidth and other network functions (such as load balancing, fire wall, VPN
(Virtual Private Network, VPN)) demand.And during the implementation of project actual deployment, from cloud computing
Consider on resource pool system capacity and scalability, undertake server or the SDN equipment meetings of virtual network service
There are many；Even when business scale increases, understand with trunking mode deployment services device or SDN equipment (with
It is referred to as virtual network node down) so that the energy consumption more and more higher of cloud computing resources cell system.
In order to reduce the energy consumption of cloud computing resources cell system, correlation technique provides cloud computing resources cell system section
Energy mode, one kind is to consider from aspect of performances such as CPU, internal memories, virtual in a physical machine by operating in
Machine, is migrated to another physical machine, so as to integrate virtual machine cluster, reduces the energy of cloud computing resources cell system
Consumption.Another is from the aspect of virtual machine, by the virtual machine (vm) migration in same virtual network to same
In physical machine, the purpose integrated based on virtual switch the communication tunnel virtual machine is reached, so that
Virtual machine cluster is integrated, the energy consumption of cloud computing resources cell system is reduced.
But there are the following problems for the cloud computing resource pool energy saving of system mode that correlation technique is provided：Cloud computing is provided
Source cell system includes computing resource and Internet resources, the cloud computing resource pool energy saving of system side that correlation technique is provided
Formula, reduced by only the energy consumption that resource is calculated in cloud computing resources cell system, that is, reduced by only cloud computing resource pool
Energy consumption in system needed for virtual machine, does not reduce the energy consumption of Internet resources in cloud computing resources cell system, i.e.,
Do not reduce the energy consumption in cloud computing resources cell system needed for virtual network node.
The content of the invention
In view of this, the embodiment of the present invention is expected to provide a kind of cloud computing resource pool energy saving of system method, device
And system, to reduce the energy consumption of cloud computing resources cell system.
A kind of cloud computing resource pool energy saving of system method, methods described includes：
When the resource overall availability of all virtual network nodes is less than the first predetermined threshold value, determines and wait to integrate
Virtual network node；
The virtual network service on the virtual network node to be integrated is migrated to destination virtual network node
On.
Wherein, it is described to determine virtual network node to be integrated, be specially：According to each virtual network
The resource utilization of node, virtual network node to be integrated is determined from all virtual network nodes.
Wherein, the virtual network service by the virtual network node to be integrated, migrates empty to target
Intend on network node, including：
Judge the resource total surplus value of all virtual network nodes, if treat whole more than or equal to described
Close the resource occupation value of virtual network node；
When confirming that the resource total surplus value is more than or equal to the resource occupation value, void is treated described
The virtual network service on virtual network node is integrated, is migrated to destination virtual network node.
It is wherein, described when confirming that the resource total surplus value is more than or equal to the resource occupation value,
Void migrates the virtual network service on the virtual network node to be integrated to destination virtual network node,
Including：
When confirming that the resource total surplus value is more than or equal to the resource occupation value, treated according to described
The resource occupation value of the virtual network service on virtual network node is integrated, and it is non-to be integrated described virtual
The resources left value of network node, destination virtual is selected out from the non-virtual network node to be integrated
Network node；
The virtual network service is migrated to the destination virtual network from the virtual network node to be integrated
Node.
Wherein, the virtual network service by the virtual network node to be integrated, migrates empty to target
Intend on network node, in addition to：The void not migrated is not present on the virtual network node to be integrated
When intending network service, the control virtual network node to be integrated enters energy saver mode.
Further, methods described also includes：Surpass in the resource overall availability of all virtual network nodes
When crossing the second predetermined threshold value, standby virtual network node is added in cloud computing resources cell system.
A kind of cloud computing resource pool energy saving of system device, described device includes：
Confirm module, during for the resource overall availability in all virtual network nodes less than the first predetermined threshold value,
Determine virtual network node to be integrated；
Transferring module, for migrating the virtual network service on the virtual network node to be integrated to mesh
Mark on virtual network node.
Wherein, the confirmation module, specifically for the resource utilization according to each virtual network node,
Virtual network node to be integrated is determined from all virtual network nodes.
Wherein, the transferring module, the resource total surplus specifically for judging all virtual network nodes
Value, if more than or equal to the resource occupation value of the virtual network node to be integrated；Described in confirming
It is empty by the virtual network section to be integrated when resource total surplus value is more than or equal to the resource occupation value
Virtual network service on point, is migrated to destination virtual network node.
Wherein, the transferring module, is specifically additionally operable to be more than or equal in the confirmation resource total surplus value
During the resource occupation value, according to the resource of the virtual network service on the virtual network node to be integrated
Take value, and the non-virtual network node to be integrated resources left value, non-wait to integrate from described
Virtual network node in select out destination virtual network node；The virtual network service is treated whole from described
Virtual network node is closed to migrate to the destination virtual network node.
A kind of cloud computing resource pool energy saving of system system, the system includes：Virtual network controls node and extremely
Few two virtual network nodes；Wherein,
The virtual network controls node is low for the resource overall availability in all virtual network nodes
When the first predetermined threshold value, virtual network node to be integrated is determined；By the virtual network node to be integrated
On virtual network service, migrate to destination virtual network node.
A kind of cloud computing resource pool energy saving of system method provided in an embodiment of the present invention, apparatus and system, in institute
When the resource overall availability for having virtual network node is less than the first predetermined threshold value, virtual network to be integrated is determined
Node；The virtual network service on virtual network node to be integrated is migrated to destination virtual network node.
In this way, the scale for integrating virtual network node in cloud computing resources cell system can be realized, cloud computing resources are reduced
The energy consumption of cell system, improves the effect of cloud computing resource pool energy saving of system emission reduction.
Brief description of the drawings
Fig. 1 illustrates for a kind of flow of cloud computing resource pool energy saving of system method provided in an embodiment of the present invention
Figure；
Fig. 2 is a kind of structural representation of cloud computing resource pool energy saving of system device provided in an embodiment of the present invention
Figure；
Fig. 3 is a kind of structural representation of cloud computing resource pool energy saving of system system provided in an embodiment of the present invention
One；
Fig. 4 is a kind of structural representation of cloud computing resource pool energy saving of system system provided in an embodiment of the present invention
Two；
A kind of structure for cloud computing resource pool energy saving of system system specific embodiment that Fig. 5 provides for the present invention is shown
It is intended to；
A kind of flow for cloud computing resource pool energy saving of system method specific embodiment that Fig. 6 provides for the present invention is shown
It is intended to.
Embodiment
In embodiments of the present invention, threshold is preset less than first in the resource overall availability of all virtual network nodes
During value, virtual network controls node determines virtual network node to be integrated；Virtual network controls node will be treated
The virtual network service on virtual network node is integrated, is migrated to destination virtual network node.
Below in conjunction with the accompanying drawings and specific embodiment, the present invention is described in more detail.
Fig. 1 illustrates for a kind of flow of cloud computing resource pool energy saving of system method provided in an embodiment of the present invention
Figure, as shown in figure 1, this method includes：
Step 101：When the resource overall availability of all virtual network nodes is less than the first predetermined threshold value, really
Make virtual network node to be integrated.
Specifically, this step can be, total in the resource of all virtual network nodes of cloud computing resources cell system
When utilization rate is less than the first predetermined threshold value, virtual network controls node is all virtual from cloud computing resources cell system
Virtual network node to be integrated is determined in network node.
It should be noted that, in actual applications, the virtual network controls node can be realized by server.
Wherein, the virtual network node can be the server or SDN equipment of carrying virtual network service.
It should be noted that, it is unconfirmed go out all virtual network nodes resource overall availability less than first preset
In the case of threshold value, before this step, cloud computing resource pool energy saving of system side provided in an embodiment of the present invention
Method, can also include：Judge the resource overall availability of all virtual network nodes whether less than the first default threshold
Value.It may thereby determine that out whether the resource overall availability of virtual network node in cloud computing resources cell system is low
In the first predetermined threshold value so that virtual network controls node knows virtual network section in cloud computing resources cell system
The situation of the portfolio of point.
Specifically, whether the resource overall availability for judging all virtual network nodes is less than the first default threshold
Value, can include, virtual network controls node judge all virtual network nodes bandwidth overall availability whether
Less than predetermined threshold value one；Virtual network controls node judges that the CPU overall availabilities of all virtual network nodes are
It is no to be less than predetermined threshold value two；Virtual network controls node judges the internal memory overall availability of all virtual network nodes
Whether predetermined threshold value three is less than；It is less than predetermined threshold value one in bandwidth overall availability, CPU overall availabilities are less than pre-
If threshold value two, and internal memory overall availability, when being less than predetermined threshold value three, virtual network controls node confirms all void
The resource overall availability for intending network node is less than the first predetermined threshold value, otherwise, and virtual network controls node confirms
The resource overall availability of all virtual network nodes is not less than the first predetermined threshold value.
Wherein, the predetermined threshold value one, predetermined threshold value two and predetermined threshold value three can be entered according to the actual requirements
Row is set.Such as it is that the bandwidth of all virtual network nodes is total in cloud computing resources cell system in actual demand
Utilization rate is less than m%, when CPU overall availabilities are less than n%, and internal memory overall availability less than k%, that is, needs whole
The scale of virtual network node in cloud computing resources cell system is closed, the energy consumption of cloud computing resources cell system is reduced
In the case of, the predetermined threshold value one may be configured as m%, and predetermined threshold value two may be configured as n%, predetermined threshold value
Three may be configured as k%.It should be noted that, predetermined threshold value one, predetermined threshold value two and predetermined threshold value three can phases
Together, it can also differ.Wherein, virtual network node A, virtual net are included in all virtual network nodes
Network node B and virtual network node C, virtual network node A bandwidth utilization rate are A%, virtual network
Node B bandwidth utilization rate is B%, in the case that virtual network node C bandwidth utilization rate is C%,
The bandwidth overall availability of all virtual network nodes is A%+B%+C%, i.e., all virtual network nodes
Bandwidth overall availability be A%, B% and C% sum.
Specifically, described in this step 101 determines virtual network node to be integrated, Ke Yiwei, virtually
Network control node is according to the resource utilization of each virtual network node, from all virtual network nodes really
Make virtual network node to be integrated.I.e. virtual network controls node is according to each in cloud computing resources cell system
The resource utilization of virtual network node, is determined from all virtual network nodes of cloud computing resources cell system
Go out virtual network node to be integrated.
It should be noted that, cloud computing resource pool energy saving of system method provided in an embodiment of the present invention can also be wrapped
Include：Virtual network node reports the resource of this node to make every prefixed time interval to virtual network controls node
With rate；Virtual network controls node receives the resource utilization of each virtual network node.
Wherein, the prefixed time interval can be configured according to practical situations.Such as in practical application
In, the resource utilization of virtual network node is reported to virtual network controls node every time interval T1,
Virtual network controls node can be controlled in real time, the energy in cloud computing resources cell system needed for virtual network node
In the case of consumption, the prefixed time interval is that may be configured as T1.
Such as, in actual applications, the resource statistics on virtual network node acts on behalf of Agent, every T1 to void
Intend bandwidth utilization rate, CPU usage and memory usage that network control node reports this node, virtual net
Network control node receives bandwidth utilization rate, CPU usage and the memory usage of each virtual network node.
Specifically, the virtual network controls node is according to the resource utilization of each virtual network node, from
Virtual network node to be integrated is determined in all virtual network nodes, can be included, virtual network controls section
Order of the point according to the current resource utilization of each virtual network node from big to small, to each virtual network
Node is ranked up；Virtual network controls node is by all virtual network nodes, current resource utilization
Minimum virtual network node confirms as virtual network node to be integrated.
Step 102：The virtual network service on virtual network node to be integrated is migrated to destination virtual net
On network node.
Specifically, this step can be, virtual network controls node is by the void on virtual network node to be integrated
Intend network service, migrate to destination virtual network node.
Wherein, the virtual network service can be fire wall, VPN, virtual router etc..
Specifically, this step can include, and virtual network controls node judges the money of all virtual network nodes
Whether source total surplus value is more than or equal to the resource occupation value of virtual network node to be integrated；Confirming to be somebody's turn to do
When resource total surplus value is more than or equal to the resource occupation value, virtual network controls node will be waited to integrate void
Intend the virtual network service on network node, migrate to destination virtual network node.
Specifically, whether the resource total surplus value for judging all virtual network nodes is more than or equal to and treats
The resource occupation value of virtual network node is integrated, can be included, virtual network controls node judges all void
Whether the broadband total surplus value for intending network node is more than or equal to the broadband occupancy of virtual network node to be integrated
Value；Virtual network controls node judge the CPU total surpluses value of all virtual network nodes whether be more than or
CPU equal to virtual network node to be integrated takes value；Virtual network controls node judges all virtual nets
Whether the internal memory total surplus value of network node is more than or equal to the EMS memory occupation amount of virtual network node to be integrated
Value；In broadband, total surplus value is more than or equal to broadband occupancy value, and CPU total surplus values are more than or equal to
When CPU takes value, and internal memory total surplus value more than or equal to EMS memory occupation value, virtual network controls
Node confirms that the resource total surplus value of all virtual network nodes is more than or equal to virtual network node to be integrated
Resource occupation value, otherwise, virtual network controls node confirms that the resource of all virtual network nodes is always remained
Margin value is not more than or is not equal to the resource occupation value of virtual network node to be integrated.
Such as, the broadband total surplus value can be represented with W ', the broadband value of each virtual network node
It can be represented with W, the total number of the virtual network node of cloud computing resources cell system can be represented with n, n
For natural number, the broadband of each virtual network node, which takes value, can use WnRepresent, then broadband total surplus
Value W '=W*n- (W1+W2+W3+……+Wn)；The CPU total surpluses value can be used
CPU ' represents that the CPU values of each virtual network node can be represented with CPU, each virtual network section
The CPU of point, which takes value, can use CPUnRepresent, then CPU total surpluses value CPU '=CPU*n- (CPU1
+CPU2+CPU3+……+CPUn)；The internal memory total surplus value can use MEM ' expressions, often
The internal memory value of individual virtual network node can represent with MEM, the EMS memory occupation of each virtual network node
Value can use MEMnRepresent, then internal memory total surplus value MEM '=MEM*n- (MEM1+MEM2
+MEM3+……+MEMn)。
Specifically, it is described when confirming that the resource total surplus value is more than or equal to the resource occupation value, it is empty
Intend network control node by the virtual network service on virtual network node to be integrated, migrate to destination virtual net
On network node, it can include, when confirming that the resource total surplus value is more than or equal to the resource occupation value,
Virtual network controls node is according to the resource occupation amount of the virtual network service on virtual network node to be integrated
Value, and non-virtual network node to be integrated resources left value, from non-virtual network node to be integrated
In select out destination virtual network node；Virtual network controls node is virtual from waiting to integrate by virtual network service
Network node is migrated to destination virtual network node.
Specifically, the non-virtual network node to be integrated is empty except integration is treated in all virtual network nodes
Intend the virtual network node beyond network node.Such as all virtual network nodes include virtual network node A,
Virtual network node B and virtual network node C, if virtual network node A is confirmed as virtual net to be integrated
Network node, then virtual network node B and virtual network node C are non-virtual network node to be integrated.
It should be noted that, when confirming that the resource total surplus value is more than or equal to the resource occupation value, and
Select out before destination virtual network node, described resource total surplus value in confirmation is more than or equal to the money
Source take value when, virtual network controls node by the virtual network service on virtual network node to be integrated,
Migrate to destination virtual network node, can also include, virtual network controls node, which is calculated, to be waited to integrate virtually
The resource occupation value of each virtual network service on network node；Virtual network controls node is according to virtual net
The order of the resource occupation value of network service from big to small, treats each virtual net on integration virtual network node
Network service is ranked up.
Specifically, the virtual network controls node takes according to the virtual network on virtual network node to be integrated
The resource occupation value of business, and non-virtual network node to be integrated resources left value, wait to integrate from non-
Virtual network node in select out destination virtual network node, by virtual network service from virtual net to be integrated
Network node is migrated to destination virtual network node, Ke Yiwei, and virtual network controls node judges to wait to integrate virtually
With the presence or absence of the virtual network service not migrated on network node；When there is the virtual network service not migrated,
Virtual network controls node is according to the ranking results of virtual network service, in the virtual network service never migrated
Select out the maximum virtual network service of resource occupancy value；Virtual network controls node takes the virtual network
The resources left value of the resource occupation value of business and non-virtual network node to be integrated is compared, and will
Resources left value is more than or equal to the non-virtual network to be integrated of the resource occupation value of virtual network service
Node is used as destination virtual network node to be selected；Virtual network controls node selectes a destination virtual net to be selected
Network node is used as destination virtual network node；Virtual network controls node is by the virtual network service from waiting to integrate
Virtual network node is migrated to destination virtual network node；Virtual network controls node updates destination virtual network
The resources left value of node；The return execution of virtual network controls node is described to judge virtual network section to be integrated
With the presence or absence of the virtual network service not migrated on point.
Specifically, this step can also include, and the void not migrated is not present on virtual network node to be integrated
When intending network service, the virtual network controls node control virtual network node to be integrated enters energy saver mode.
Specifically, the virtual network controls node control virtual network node to be integrated enters energy saver mode,
Can be that virtual network controls node closes the virtual network node to be integrated；This is such as closed to wait to integrate virtually
The power supply of network node so that the virtual network node to be integrated stops service.
Specifically, the virtual network controls node control virtual network node to be integrated enters energy saver mode,
Or can be, the virtual network controls node control virtual network node no-load run to be integrated.
In this way, the scale for integrating virtual network node in cloud computing resources cell system can be realized, cloud computing is reduced
The energy consumption of resource pool system, improves the effect of cloud computing resource pool energy saving of system emission reduction.
It should be noted that, cloud computing resource pool energy saving of system method provided in an embodiment of the present invention can also be wrapped
Include, when the resource overall availability of all virtual network nodes is more than the second predetermined threshold value, virtual network controls
Standby virtual network node is added in cloud computing resources cell system by node.So as in virtual network section
When the portfolio of point is larger, the scale of virtual network node in extension cloud computing resources cell system.
In order to realize the above method, the invention discloses a kind of cloud computing resource pool energy saving of system device.
Fig. 2 is a kind of structural representation of cloud computing resource pool energy saving of system device provided in an embodiment of the present invention
Figure, as shown in Fig. 2 the cloud computing resource pool energy saving of system device includes：
Module 201 is confirmed, for the resource overall availability in all virtual network nodes less than the first default threshold
During value, virtual network node to be integrated is determined；
Transferring module 202, for by the virtual network service on the virtual network node to be integrated, migrating
To destination virtual network node.
Further, the confirmation module 201, specifically for the resource according to each virtual network node
Utilization rate, virtual network node to be integrated is determined from all virtual network nodes.
Further, the transferring module 202, the resource specifically for judging all virtual network nodes
Total surplus value, if more than or equal to the resource occupation value of the virtual network node to be integrated；True
It is empty to wait to integrate virtually by described when recognizing the resource total surplus value more than or equal to the resource occupation value
Virtual network service on network node, is migrated to destination virtual network node.
Further, the transferring module 202, is specifically additionally operable to be more than in the confirmation resource total surplus value
Or during equal to the resource occupation value, according to the virtual network service on the virtual network node to be integrated
Resource occupation value, and the non-virtual network node to be integrated resources left value, from described non-
Destination virtual network node is selected out in virtual network node to be integrated；By the virtual network service from institute
Virtual network node to be integrated is stated to migrate to the destination virtual network node.
In actual applications, the confirmation module 201 and transferring module 202 can be by servers
Central processing unit (Central Processing Unit, CPU), microprocessor (Micro Processor Unit,
MPU), digital signal processor (Digital Signal Processor, DSP) or field programmable gate
Array (Field Programmable Gate Array, FPGA) etc. is realized.
In order to realize the above method, the invention discloses a kind of cloud computing resource pool energy saving of system system.
Fig. 3 is a kind of structural representation of cloud computing resource pool energy saving of system system provided in an embodiment of the present invention
One, as shown in figure 3, the cloud computing resource pool energy saving of system system includes：Virtual network controls node 301
And at least two virtual network nodes 302；Wherein,
The virtual network controls node 301, for always being used in the resource of all virtual network nodes
When rate is less than the first predetermined threshold value, virtual network node to be integrated is determined；By the virtual network to be integrated
Virtual network service on node, is migrated to destination virtual network node.
It should be noted that, as shown in figure 4, the virtual network controls node 301 can include, above-mentioned institute
The confirmation module 201 and transferring module 202 stated.The confirmation module 201, in all virtual network sections
When the resource overall availability of point is less than the first predetermined threshold value, virtual network node to be integrated is determined；It is described to move
Shifting formwork block 202, for migrating the virtual network service on the virtual network node to be integrated to target
On virtual network node.
In actual applications, the virtual network controls node 301 and virtual network node 302 can be by taking
Business device is realized.
In actual applications, the confirmation module 201 and transferring module 202 can be by servers
Central processing unit (Central Processing Unit, CPU), microprocessor (Micro Processor Unit,
MPU), digital signal processor (Digital Signal Processor, DSP) or field programmable gate
Array (Field Programmable Gate Array, FPGA) etc. is realized.
A kind of structure for cloud computing resource pool energy saving of system system specific embodiment that Fig. 5 provides for the present invention is shown
It is intended to, as shown in figure 5, the cloud computing resource pool energy saving of system system includes：Virtual network controls node
301 and at least two virtual network nodes 302；Wherein,
The virtual network controls node 301, for always being used in the resource of all virtual network nodes
When rate is less than the first predetermined threshold value, virtual network node to be integrated is determined；By the virtual network to be integrated
Virtual network service on node, is migrated to destination virtual network node.
The virtual network node 302 acts on behalf of Agent3021 including resource statistics；The resource statistics agency
Agent3021, for reporting the resource of this node to use to virtual network controls node every prefixed time interval
Rate；Virtual network controls node 301, receives the resource utilization of each virtual network node, according to each
The resource utilization of virtual network node calculates the resource overall availability of all virtual network nodes.
In actual applications, the virtual network controls node 301 and virtual network node 302 can be by taking
Business device is realized.
In actual applications, the resource statistics act on behalf of Agent3021 can be by the centre in server
Manage device (Central Processing Unit, CPU), microprocessor (Micro Processor Unit, MPU),
Digital signal processor (Digital Signal Processor, DSP) or field programmable gate array (Field
Programmable Gate Array, FPGA) etc. realize.
A kind of flow for cloud computing resource pool energy saving of system method specific embodiment that Fig. 6 provides for the present invention is shown
It is intended to, as shown in fig. 6, specific steps include：
Step 601：Judge whether the resource overall availability of all virtual network nodes is less than the first predetermined threshold value.
Specifically, this step can be that virtual network controls node judges the resource of all virtual network nodes
Whether overall availability is less than the first predetermined threshold value.
It should be noted that, in actual applications, the virtual network controls node can be realized by server.
Wherein, the virtual network node can be the server or SDN equipment of carrying virtual network service.
Specifically, this step can include, and virtual network controls node judges the band of all virtual network nodes
Whether wide overall availability is less than predetermined threshold value one；Virtual network controls node judges all virtual network nodes
Whether CPU overall availabilities are less than predetermined threshold value two；Virtual network controls node judges all virtual network nodes
Internal memory overall availability whether be less than predetermined threshold value three；It is less than predetermined threshold value one, CPU in bandwidth overall availability
When overall availability is less than predetermined threshold value two, and internal memory overall availability less than predetermined threshold value three, virtual network controls
Node confirms that the resource overall availability of all virtual network nodes is less than the first predetermined threshold value, otherwise, virtual net
Network control node confirms that the resource overall availability of all virtual network nodes is not less than the first predetermined threshold value.
Wherein, the predetermined threshold value one, predetermined threshold value two and predetermined threshold value three can be entered according to the actual requirements
Row is set.Such as it is that the bandwidth of all virtual network nodes is total in cloud computing resources cell system in actual demand
Utilization rate is less than m%, when CPU overall availabilities are less than n%, and internal memory overall availability less than k%, that is, needs whole
The scale of virtual network node in cloud computing resources cell system is closed, the energy consumption of cloud computing resources cell system is reduced
In the case of, the predetermined threshold value one may be configured as m%, and predetermined threshold value two may be configured as n%, predetermined threshold value
Three may be configured as k%.It should be noted that, predetermined threshold value one, predetermined threshold value two and predetermined threshold value three can phases
Together, it can also differ.Wherein, virtual network node A, virtual net are included in all virtual network nodes
Network node B and virtual network node C, virtual network node A bandwidth utilization rate are A%, virtual network
Node B bandwidth utilization rate is B%, in the case that virtual network node C bandwidth utilization rate is C%,
The bandwidth overall availability of all virtual network nodes is A%+B%+C%, i.e., all virtual network nodes
Bandwidth overall availability be A%, B% and C% sum.
Specifically, when resource overall availability is not less than the first predetermined threshold value, step 602 is performed；In resource
When overall availability is less than the first predetermined threshold value, step 603 is performed.
Step 602：Wait preset time.
Specifically, in order to avoid excessively continually judge all virtual network nodes resource overall availability whether
It less than the first predetermined threshold value, can wait after preset time, return again to execution step 601.
Wherein, the preset time can be configured according to practical situations.Such as in actual applications,
If after stand-by period T, then judging whether the resource overall availability of all virtual network nodes is preset less than first
Threshold value, the control of the energy consumption to cloud computing resources cell system is not interfered with generally, and the preset time is that can be set
For T.
Step 603：It is right according to the order of the current resource utilization of each virtual network node from big to small
Each virtual network node is ranked up.
Specifically, this step can be, virtual network controls node is according to each virtual network node current
The order of resource utilization from big to small, is ranked up to each virtual network node.
Step 604：By in all virtual network nodes, the minimum virtual network section of current resource utilization
Point confirms as virtual network node to be integrated.
Specifically, this step can be, virtual network controls node is by all virtual network nodes, currently
The minimum virtual network node of resource utilization confirm as virtual network node to be integrated.
Step 605：Calculate the resource total surplus value of all virtual network nodes.
Specifically, this step can be that virtual network controls node calculates all in cloud computing resources cell system
The resource total surplus value of virtual network node.
Specifically, this step can include, and virtual network controls node calculates institute in cloud computing resources cell system
There is the broadband total surplus value of virtual network node；Virtual network controls node calculates cloud computing resources cell system
In all virtual network nodes CPU total surplus values；Virtual network controls node calculates cloud computing resource pool
The internal memory total surplus value of all virtual network nodes in system.
Such as, the broadband total surplus value can be represented with W ', the broadband value of each virtual network node
It can be represented with W, the total number of the virtual network node of cloud computing resources cell system can be represented with n, n
For natural number n, the broadband of each virtual network node, which takes value, can use WnRepresent, then broadband total surplus
Value W '=W*n- (W1+W2+W3+……+Wn)；The CPU total surpluses value can be used
CPU ' represents that the CPU values of each virtual network node can be represented with CPU, each virtual network section
The CPU of point, which takes value, can use CPUnRepresent, then CPU total surpluses value CPU '=CPU*n- (CPU1
+CPU2+CPU3+……+CPUn)；The internal memory total surplus value can use MEM ' expressions, often
The internal memory value of individual virtual network node can represent with MEM, the EMS memory occupation of each virtual network node
Value can use MEMnRepresent, then internal memory total surplus value MEM '=MEM*n- (MEM1+MEM2
+MEM3+……+MEMn)。
Step 606：Judge whether the resource total surplus value of all virtual network nodes is more than or equal to and treat whole
Close the resource occupation value of virtual network node.
Specifically, this step can be that virtual network controls node judges the resource of all virtual network nodes
Whether total surplus value is more than or equal to the resource occupation value of virtual network node to be integrated.
Specifically, when resource total surplus value is more than or equal to resource occupation value, step 607 is performed,
Otherwise, return to step 602.
Step 607：According to the resource occupation value order from big to small of virtual network service, integration is treated
Each virtual network service is ranked up on virtual network node.
Specifically, this step can be, virtual network controls node according to virtual network service resource occupation
The order of value from big to small, treats each virtual network service on integration virtual network node and is ranked up.
Step 608：Judge on virtual network node to be integrated with the presence or absence of the virtual network service not migrated.
Specifically, this step can be, virtual network controls node judge be on virtual network node to be integrated
It is no to there is the virtual network service not migrated.
Specifically, when there is the virtual network service not migrated, step 609 is performed, otherwise, step is performed
Rapid 613.
Step 609：According to the ranking results of virtual network service, selected in the virtual network service never migrated
Make the maximum virtual network service of resource occupation value.
Specifically, this step can be, virtual network controls node according to the ranking results of virtual network service,
Never the maximum virtual network service of resource occupancy value is selected out in the virtual network service migrated.
Step 610：By the resource occupation value of the virtual network service and non-virtual network node to be integrated
Resources left value be compared, and by resources left value be more than or equal to virtual network service resource
The non-virtual network node to be integrated for taking value is used as destination virtual network node to be selected.
Specifically, this step can be, virtual network controls node is by the resource occupation of the virtual network service
The resources left value of value and non-virtual network node to be integrated is compared, and by resources left value
More than or equal to virtual network service resource occupation value non-virtual network node to be integrated as to be selected
Destination virtual network node.
Step 611：A destination virtual network node to be selected is selected as destination virtual network node, and will
The virtual network service is migrated to destination virtual network node from virtual network node to be integrated.
Specifically, this step can be that virtual network controls node selectes a destination virtual network section to be selected
Point as destination virtual network node, and by the virtual network service from virtual network node to be integrated migrate to
Destination virtual network node.
Step 612：Update the resources left value of destination virtual network node.
Specifically, this step can be, the resource of virtual network controls node updates destination virtual network node
Remaining value.
Return and perform step 608.
Step 613：Virtual network node to be integrated is controlled to enter energy saver mode.
Specifically, this step can be that virtual network controls node control virtual network node to be integrated enters
Energy saver mode.
Specifically, as virtual network controls node closes the virtual network node to be integrated；Such as close this and treat whole
Close the power supply of virtual network node so that the virtual network node to be integrated stops service.Or, virtual net
Network control node controls virtual network node no-load run to be integrated.
In this way, the scale for integrating virtual network node in cloud computing resources cell system can be realized, cloud computing is reduced
The energy consumption of resource pool system, improves the effect of cloud computing resource pool energy saving of system emission reduction.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for ability
For the technical staff in domain, the present invention can have various modifications and variations, and protection scope of the present invention is with right
It is required that being defined.
Claims (11)
1. a kind of cloud computing resource pool energy saving of system method, it is characterised in that methods described includes：
When the resource overall availability of all virtual network nodes is less than the first predetermined threshold value, determines and wait to integrate
Virtual network node；
The virtual network service on the virtual network node to be integrated is migrated to destination virtual network node
On.
2. according to the method described in claim 1, it is characterised in that described to determine virtual network to be integrated
Node, be specially：
According to the resource utilization of each virtual network node, from all virtual network nodes really
Make virtual network node to be integrated.
3. according to the method described in claim 1, it is characterised in that described by the virtual network to be integrated
Virtual network service on node, is migrated to destination virtual network node, including：
Judge the resource total surplus value of all virtual network nodes, if treat whole more than or equal to described
Close the resource occupation value of virtual network node；
When confirming that the resource total surplus value is more than or equal to the resource occupation value, void is treated described
The virtual network service on virtual network node is integrated, is migrated to destination virtual network node.
4. method according to claim 3, it is characterised in that described to confirm the resource total surplus
When value is more than or equal to the resource occupation value, void will be virtual on the virtual network node to be integrated
Network service, is migrated to destination virtual network node, including：
When confirming that the resource total surplus value is more than or equal to the resource occupation value, treated according to described
The resource occupation value of the virtual network service on virtual network node is integrated, and it is non-to be integrated described virtual
The resources left value of network node, destination virtual is selected out from the non-virtual network node to be integrated
Network node；
The virtual network service is migrated to the destination virtual network from the virtual network node to be integrated
Node.
5. method according to claim 3, it is characterised in that described by the virtual network to be integrated
Virtual network service on node, is migrated to destination virtual network node, in addition to：
Described when the virtual network service for being not present and not migrating on virtual network node is integrated, control
The virtual network node to be integrated enters energy saver mode.
6. according to the method described in claim 1, it is characterised in that methods described also includes：
When the resource overall availability of all virtual network nodes is more than the second predetermined threshold value, by standby void
Intend network node to be added in cloud computing resources cell system.
7. a kind of cloud computing resource pool energy saving of system device, it is characterised in that described device includes：
Confirm module, during for the resource overall availability in all virtual network nodes less than the first predetermined threshold value,
Determine virtual network node to be integrated；
Transferring module, for migrating the virtual network service on the virtual network node to be integrated to mesh
Mark on virtual network node.
8. device according to claim 7, it is characterised in that the confirmation module, specifically for root
According to the resource utilization of each virtual network node, determine and treat from all virtual network nodes
Integrate virtual network node.
9. device according to claim 7, it is characterised in that the transferring module, specifically for sentencing
The resource total surplus value of disconnected all virtual network nodes, if wait to integrate virtually more than or equal to described
The resource occupation value of network node；Accounted in the confirmation resource total surplus value more than or equal to the resource
During volume value, void migrates the virtual network service on the virtual network node to be integrated to destination virtual
On network node.
10. device according to claim 9, it is characterised in that the transferring module, is specifically also used
When confirming that the resource total surplus value is more than or equal to the resource occupation value, treat whole according to described
Close the resource occupation value of the virtual network service on virtual network node, and the non-virtual net to be integrated
The resources left value of network node, destination virtual net is selected out from the non-virtual network node to be integrated
Network node；The virtual network service is migrated to the destination virtual from the virtual network node to be integrated
Network node.
11. a kind of cloud computing resource pool energy saving of system system, it is characterised in that the system includes：Virtually
Network control node and at least two virtual network nodes；Wherein,
The virtual network controls node is low for the resource overall availability in all virtual network nodes
When the first predetermined threshold value, virtual network node to be integrated is determined；By the virtual network node to be integrated
On virtual network service, migrate to destination virtual network node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610236186.XA CN107301092B (en) | 2016-04-15 | 2016-04-15 | Energy-saving method, device and system for cloud computing resource pool system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610236186.XA CN107301092B (en) | 2016-04-15 | 2016-04-15 | Energy-saving method, device and system for cloud computing resource pool system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107301092A true CN107301092A (en) | 2017-10-27 |
| CN107301092B CN107301092B (en) | 2020-11-10 |
Family
ID=60137613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610236186.XA Active CN107301092B (en) | 2016-04-15 | 2016-04-15 | Energy-saving method, device and system for cloud computing resource pool system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107301092B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110769272A (en) * | 2019-11-19 | 2020-02-07 | 深圳市网心科技有限公司 | Node adjusting method and related equipment thereof |
| CN115277308A (en) * | 2022-07-20 | 2022-11-01 | 杭州迪普科技股份有限公司 | Method and device for deploying SSLVPN equipment in cloud resource pool |
| CN117132399A (en) * | 2023-10-25 | 2023-11-28 | 广州捷晨教育科技有限公司 | Resource management system applied to meta universe |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040158777A1 (en) * | 2003-02-12 | 2004-08-12 | International Business Machines Corporation | Scalable method of continuous monitoring the remotely accessible resources against the node failures for very large clusters |
| CN102096461A (en) * | 2011-01-13 | 2011-06-15 | 浙江大学 | Energy-saving method of cloud data center based on virtual machine migration and load perception integration |
| CN102419718A (en) * | 2011-10-28 | 2012-04-18 | 浪潮(北京)电子信息产业有限公司 | Resource scheduling method |
| CN102890554A (en) * | 2011-07-22 | 2013-01-23 | 鸿富锦精密工业（深圳）有限公司 | Power supply management system and method |
| CN102937912A (en) * | 2012-11-28 | 2013-02-20 | 华为技术有限公司 | Method and equipment for scheduling virtual machine |
| CN104991822A (en) * | 2015-06-30 | 2015-10-21 | 浪潮(北京)电子信息产业有限公司 | Memory management method and apparatus |
| CN105208099A (en) * | 2015-08-24 | 2015-12-30 | 浪潮(北京)电子信息产业有限公司 | System framework for intelligently saving electricity by means of SDN technology in cloud server |
| CN105426241A (en) * | 2015-11-16 | 2016-03-23 | 北京航空航天大学 | Cloud computing data center based unified resource scheduling energy-saving method |
-
2016
- 2016-04-15 CN CN201610236186.XA patent/CN107301092B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040158777A1 (en) * | 2003-02-12 | 2004-08-12 | International Business Machines Corporation | Scalable method of continuous monitoring the remotely accessible resources against the node failures for very large clusters |
| CN102096461A (en) * | 2011-01-13 | 2011-06-15 | 浙江大学 | Energy-saving method of cloud data center based on virtual machine migration and load perception integration |
| CN102890554A (en) * | 2011-07-22 | 2013-01-23 | 鸿富锦精密工业（深圳）有限公司 | Power supply management system and method |
| CN102419718A (en) * | 2011-10-28 | 2012-04-18 | 浪潮(北京)电子信息产业有限公司 | Resource scheduling method |
| CN102937912A (en) * | 2012-11-28 | 2013-02-20 | 华为技术有限公司 | Method and equipment for scheduling virtual machine |
| CN104991822A (en) * | 2015-06-30 | 2015-10-21 | 浪潮(北京)电子信息产业有限公司 | Memory management method and apparatus |
| CN105208099A (en) * | 2015-08-24 | 2015-12-30 | 浪潮(北京)电子信息产业有限公司 | System framework for intelligently saving electricity by means of SDN technology in cloud server |
| CN105426241A (en) * | 2015-11-16 | 2016-03-23 | 北京航空航天大学 | Cloud computing data center based unified resource scheduling energy-saving method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110769272A (en) * | 2019-11-19 | 2020-02-07 | 深圳市网心科技有限公司 | Node adjusting method and related equipment thereof |
| CN115277308A (en) * | 2022-07-20 | 2022-11-01 | 杭州迪普科技股份有限公司 | Method and device for deploying SSLVPN equipment in cloud resource pool |
| CN115277308B (en) * | 2022-07-20 | 2023-04-25 | 杭州迪普科技股份有限公司 | Cloud resource pool SSLVPN equipment deployment method and device |
| CN117132399A (en) * | 2023-10-25 | 2023-11-28 | 广州捷晨教育科技有限公司 | Resource management system applied to meta universe |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107301092B (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mann et al. | Remedy: Network-aware steady state VM management for data centers | |
| CN106133693B (en) | Moving method, device and the equipment of virtual machine | |
| CN107026802A (en) | A kind of method for managing resource and equipment | |
| CN103763174B (en) | Virtual network mapping method based on function block | |
| CN108322333A (en) | A kind of laying method of the virtual network function based on genetic algorithm | |
| CN107251486A (en) | A kind of method for extending linkage, apparatus and system | |
| Plakunov et al. | Data center resource mapping algorithm based on the ant colony optimization | |
| Thananjeyan et al. | Mobility-aware energy optimization in hosts selection for computation offloading in multi-access edge computing | |
| CN111538570A (en) | VNF deployment method and device for energy conservation and QoS guarantee | |
| Borylo et al. | Latency and energy-aware provisioning of network slices in cloud networks | |
| CN107135094A (en) | Intelligent network building method based on meta-model in a kind of SDN frameworks | |
| CN107301092A (en) | A kind of cloud computing resource pool energy saving of system method, apparatus and system | |
| Tseng et al. | Service-oriented virtual machine placement optimization for green data center | |
| CN106681839B (en) | Elastic calculation dynamic allocation method | |
| CN107967164A (en) | A kind of method and system of live migration of virtual machine | |
| CN109347657B (en) | Method for constructing virtual data domain of scientific and technological service under SDN mode | |
| Mousicou et al. | Performance evaluation of dynamic cloud resource migration based on temporal and capacity-aware policy for efficient resource sharing | |
| Hsu et al. | Virtual network mapping algorithm in the cloud infrastructure | |
| Shang et al. | Network congestion-aware online service function chain placement and load balancing | |
| CN105704180B (en) | The configuration method and its system of data center network | |
| Zhang et al. | A novel virtual network mapping algorithm for cost minimizing | |
| Anglano et al. | Profit‐aware coalition formation in fog computing providers: A game‐theoretic approach | |
| Chai et al. | A parallel placement approach for service function chain using deep reinforcement learning | |
| CN111064666B (en) | Networking method and device | |
| Laroui et al. | Virtual mobile edge computing based on IoT devices resources in smart cities |
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 |