CN104331326A - Scheduling method and system for cloud computing - Google Patents
Scheduling method and system for cloud computing Download PDFInfo
- Publication number
- CN104331326A CN104331326A CN201410684658.9A CN201410684658A CN104331326A CN 104331326 A CN104331326 A CN 104331326A CN 201410684658 A CN201410684658 A CN 201410684658A CN 104331326 A CN104331326 A CN 104331326A
- Authority
- CN
- China
- Prior art keywords
- cloud computing
- task
- node
- energy consumption
- run
- 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
Classifications
-
- 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
Abstract
The invention relates to the field of cloud computing, in particular to a scheduling method and a scheduling system for cloud computing. The method comprises the following steps that a cloud computing node refers to a cloud computing task load list to determine a task which can be finished by the cloud computing node, forms an operating request aiming at the task and sends the operating request to a cloud computing system management node; the cloud computing system management node receives the operating request and acquires energy consumption increased by finishing the task by the cloud computing node corresponding to the operating request; the cloud computing system management node schedules the task into a cloud computing node with the minimum energy consumption increase for operating. The cloud computing system management node schedules the task according to the request of the cloud computing node, and schedules the task into the cloud computing node with the minimum energy consumption increase for operating according to energy consumption, the load that the cloud computing system management node traverses all cloud computing nodes is eliminated, task scheduling is more reasonable, fair and quick, the energy consumption of a cloud computing system can be effectively reduced, and the operating efficiency of the cloud computing system can be improved.
Description
Technical field
The present invention relates to field of cloud calculation, more specifically, relate to a kind of cloud computing dispatching method and system.
Background technology
Cloud computing system, refers to the parallel computing machine carrying out large-scale calculations or data processing of energy that multiple cloud computing node combines, also referred to as parallel computer.The effect of parallel computation is split by large-scale calculation task, and each node that each parallel section obtained after fractionation distributes in cloud again carries out distributed parallel computation, finally again by process unified after collection.Cloud computing system operationally can consume a large amount of electric energy, usually, be integrated with thousands of cloud computer nodes in cloud computing system, cloud computing system can add up the state of all cloud computing nodes by cloud computing system management node, according to the node state scheduling task of cloud computing node.But because cloud computing system is huge, cloud computing node substantial amounts, only undertaken adding up, screen and dispatching by cloud computing system management node, be difficult to travel through all cloud computing nodes, and easily cause congested, thus consume a large amount of energy when cloud computing system is run, also reduce the operational efficiency of cloud computing system simultaneously.
Summary of the invention
The present invention, for overcoming at least one defect (deficiency) described in above-mentioned prior art, provides a kind of cloud computing dispatching method that effectively can reduce cloud computing system energy consumption.
The present invention also provides a kind of cloud computing dispatching system that effectively can reduce cloud computing system energy consumption.
For solving the problems of the technologies described above, technical scheme of the present invention is as follows:
A kind of cloud computing dispatching method, comprising:
Cloud computing node consults its task that can complete of cloud computing task load list deciding, and sends to cloud computing system management node for this task formation operation request;
Cloud computing system management node receives the request of operation, obtains cloud computing node corresponding to the request of operation and completes the energy consumption that this task increases;
This task scheduling is run to increasing in the minimum cloud computing node of energy consumption by cloud computing system management node.
Cloud computing system management node is dispatched task according to the request of cloud computing node in the method for the invention, and according to energy consumption, task scheduling is run in the minimum cloud computing node of energy consumption, eliminate the load that cloud computing system management node travels through all cloud computing nodes, make task scheduling more reasonable, fair and quick, effectively can reduce the energy consumption of cloud computing system, also can improve the operational efficiency of cloud computing system.
Further, described cloud computing task load table is stored on any one cloud computing node.The position that cloud computing task load table stores can be selected arbitrarily, consults, improve the dirigibility of cloud computing system layout for cloud computing system management node and each cloud computing node.
Further, the content that cloud computing task load table stores comprises the running status of task, the operation address of task, the computing power needed for operation task and the energy consumption needed for operation task.
Further, described method also comprises: task scheduling is upgraded cloud computing task load table after increasing the minimum cloud computing node of energy consumption.
Further, cloud computing node is consulted the concrete steps of its task that can complete of cloud computing task load list deciding and is:
Cloud computing node consults cloud computing task load table, has obtained the computing power of this required by task;
Judge that when the residue computing power of cloud computing node self is greater than the computing power of described required by task it can complete described task.
Further, described task is all parallel sections/a certain parallel section/multiple parallel section of cloud computing task to be run or all parallel sections of cloud computing task run or a certain parallel section/multiple parallel section.Task of the present invention can be to be run also can running, can be all parallel sections of cloud computing task, also can be the multiple of cloud computing task or certain parallel section, improve the dirigibility of task scheduling, and the task in cloud computing system at any time can both be performed with minimum energy consumption, greatly reduce the energy consumption of cloud computing system.
Further, when task is all parallel sections/a certain parallel section/multiple parallel section wait the cloud computing task run, cloud computing system management node selects all operation to ask the cloud computing node that in corresponding cloud computing node, energy consumption is minimum to run this task;
When task is all parallel sections/a certain parallel section/multiple parallel section of the cloud computing task run, cloud computing system management node judge to run cloud computing node corresponding to request complete energy consumption that this required by task wants and the energy consumption summation that increased to the cloud computing node that this operation request is corresponding by this task immigration is minimum and be less than run this task cloud computing node needed for energy consumption, run in the cloud computing node corresponding to this task immigration is minimum to energy consumption summation.
A kind of cloud computing dispatching system, comprise cloud computing node and cloud computing system management node, cloud computing node comprises:
Request sending module, for consulting its task that can complete of cloud computing task load list deciding, and sends to cloud computing system management node for this task formation operation request;
Cloud computing system management node comprises:
Request receiving module, for receiving the request of operation, obtaining cloud computing node corresponding to the request of operation and completing the energy consumption that this task increases;
Scheduler module, for running this task scheduling to increasing in the minimum cloud computing node of energy consumption.
In the system of the present invention, the scheduler module of cloud computing system management node is dispatched task according to the request of cloud computing node, and according to energy consumption, task scheduling is run in the minimum cloud computing node of energy consumption, eliminate the load that cloud computing system management node travels through all cloud computing nodes, make task scheduling more reasonable, fair and quick, effectively can reduce the energy consumption of cloud computing system, also can improve the operational efficiency of cloud computing system.
Further, request sending module comprises:
Consulting and computing module, for consulting cloud computing task load table, having obtained the computing power of this required by task;
Determination module, for judging that when the residue computing power of cloud computing node self is greater than the computing power of described required by task it can complete described task;
Sending module, sends to cloud computing system management node for forming operation request for this task.
Further, described task is all parallel sections/a certain parallel section/multiple parallel section of cloud computing task to be run or all parallel sections of cloud computing task run or a certain parallel section/multiple parallel section;
When task is all parallel sections/a certain parallel section/multiple parallel section wait the cloud computing task run, scheduler module selects all operation to ask the cloud computing node that in corresponding cloud computing node, energy consumption is minimum to run this task;
When task is all parallel sections/a certain parallel section/multiple parallel section of the cloud computing task run, scheduler module judge to run cloud computing node corresponding to request complete energy consumption that this required by task wants and the energy consumption summation that increased to the cloud computing node that this operation request is corresponding by this task immigration is minimum and be less than run this task cloud computing node needed for energy consumption, run in the cloud computing node corresponding to this task immigration is minimum to energy consumption summation.
Task of the present invention can be to be run also can running, can be all parallel sections of cloud computing task, also can be the multiple of cloud computing task or certain parallel section, improve the dirigibility of task scheduling, and the task in cloud computing system at any time can both be performed with minimum energy consumption, greatly reduce the energy consumption of cloud computing system.
Compared with prior art, the beneficial effect of technical solution of the present invention is:
(1) cloud computing method of the present invention and system are dispatched task according to the request of cloud computing node, and according to energy consumption, task scheduling is run in the minimum cloud computing node of energy consumption, eliminate the load that cloud computing system management node travels through all cloud computing nodes, make task scheduling more reasonable, fair and quick, effectively can reduce the energy consumption of cloud computing system, also can improve the operational efficiency of cloud computing system.
(2) in the present invention, the task that cloud computing node can complete can be to be run also can running, can be all parallel sections of cloud computing task, also can be the multiple of cloud computing task or certain parallel section, improve the dirigibility of task scheduling, and the task in cloud computing system at any time can both be performed with minimum energy consumption, greatly reduce the energy consumption of cloud computing system.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of cloud computing dispatching method of the present invention specific embodiment 1.
Fig. 2 is particular flow sheet when task is the cloud computing task run in the method for the invention.
Fig. 3 is the Organization Chart of a kind of cloud computing dispatching system of the present invention.
Fig. 4 is the Organization Chart of a kind of cloud computing dispatching system of the present invention specific embodiment.
Embodiment
Accompanying drawing, only for exemplary illustration, can not be interpreted as the restriction to this patent;
In order to better the present embodiment is described, some parts of accompanying drawing have omission, zoom in or out, and do not represent the size of actual product;
To those skilled in the art, in accompanying drawing, some known features and explanation thereof may be omitted is understandable.
In describing the invention, it is to be appreciated that term " first ", " second " only for describing object, and can not be interpreted as the quantity of instruction or hint relative importance or implicit indicated technical characteristic.Thus, one or more these features can be expressed or impliedly be comprised to the feature of " first ", " second " of restriction.In describing the invention, except as otherwise noted, the implication of " multiple " is two or more.
In describing the invention, it should be noted that, unless otherwise clearly defined and limited, term " installation ", " connection " should be interpreted broadly, and such as, can be fixedly connected with, also can be removably connect, or connect integratedly; Can be mechanical connection, also can be electrical connection; Can be directly be connected, also can be indirectly connected by intermediary, the connection of two element internals can be said.For the ordinary skill in the art, concrete condition above-mentioned term can be understood at concrete meaning of the present invention.
Below in conjunction with drawings and Examples, technical scheme of the present invention is described further.
Embodiment 1
As shown in Figure 1, be the process flow diagram of a kind of cloud computing dispatching method of the present invention specific embodiment.See Fig. 1, a kind of cloud computing system dispatching method of this specific embodiment specifically comprises the steps:
S101. cloud computing node consults its task that can complete of cloud computing task load list deciding, and sends to cloud computing system management node for this task formation operation request;
S102. cloud computing system management node receives the request of operation, obtains cloud computing node corresponding to the request of operation and completes the energy consumption that this task increases;
S103. this task scheduling is run to increasing in the minimum cloud computing node of energy consumption by cloud computing system management node.
Based on the scheme of this specific embodiment, method of the present invention is first consulted cloud computing task load table by cloud computing node oneself and is consulted task and judge whether to finish the work, if can, cloud computing node forms operation request for this task and sends to cloud computing system management node; After cloud computing system management node receives the request of operation, obtain each energy consumption required for cloud computing node that can complete this task, these energy consumptions are contrasted, then selection institute is increased the minimum cloud computing node of energy consumption, and this task scheduling is run in the minimum cloud computing node of increase energy consumption.Due to the mode by cloud computing node active request, the burden that cloud computing system management node travels through all cloud computing nodes can be removed from, greatly save time and the energy consumption of traversal, and cloud computing system management node the size of energy consumption can also carry out scheduler task, as far as possible the operation energy consumption of task is dropped to minimum, thus effectively reduce the energy consumption of cloud computing system, improve the operational efficiency of cloud computing system.
Wherein, the cloud computing task load table of step S101 can be stored on any one cloud computing node, consults for cloud computing system management node and each cloud computing node, to improve the dirigibility of cloud computing system layout.
The content that cloud computing task load table stores includes but not limited to the energy consumption needed for each parallel section of the running status of task, the operation address of task, computing power needed for each parallel section of operation task and operation task.The running status of task includes but not limited to that wait runs, running and operation completes, and the operation address of task is the cloud computing node address of each parallel section running this task.Computing power specifically refers to Central processing capability, the memory power and network capabilities etc. of cloud computing node, and Central processing capability can be specifically flops, memory power can be specifically memory size, network capabilities can be specifically the network bandwidth etc.
In specific implementation process, what the information corresponding with task will be real-time is upgraded in cloud computing task load table, upgrades cloud computing task load table by task scheduling after increasing the minimum cloud computing node of energy consumption.As the running status of this task is updated to by waiting for running the address that namely the operation address running, upgrade this task upgrades the cloud computing node running this task.
In specific implementation process, in step S101, cloud computing node is consulted the concrete steps of its task that can complete of cloud computing task load list deciding and is:
S1011. cloud computing node is consulted cloud computing task load table and is obtained task, and has obtained the computing power of this required by task;
S1012. judge when the residue computing power of cloud computing node self is greater than the computing power of described required by task that it can complete described task.
In specific implementation process, because cloud computing nodes all in cloud computing system can cross the process of active participate scheduling, therefore, when cloud computing node judges self to complete a certain parallel section in cloud computing task, then active request runs this parallel section, calculate it complete energy consumption that this parallel section increases and be supplied to cloud computing system management node simultaneously, cloud computing system management node then selects the cloud computing node that energy consumption is minimum, make task scheduling more reasonable like this, fair and quick, effectively can reduce the energy consumption of cloud computing system, also the operational efficiency of cloud computing system can be improved.Based on this, the task described in step S101 can be all parallel sections/a certain parallel section/multiple parallel section of cloud computing task to be run or all parallel sections of cloud computing task run or a certain parallel section/multiple parallel section.
When task is all parallel sections/a certain parallel section/multiple parallel section wait the cloud computing task run, cloud computing system management node selects all operation to ask the cloud computing node that in corresponding cloud computing node, energy consumption is minimum to run this task;
When task is all parallel sections/a certain parallel section/multiple parallel section of the cloud computing task run, cloud computing system management node judge to run cloud computing node corresponding to request complete energy consumption that this required by task wants and the energy consumption summation that increased to the cloud computing node that this operation request is corresponding by this task immigration is minimum and be less than run this task cloud computing node needed for energy consumption, run in the cloud computing node corresponding to this task immigration is minimum to energy consumption summation.
As task be the cloud computing task run time, as shown in Figure 2, the concrete steps of described method are:
S301. cloud computing node consults cloud computing task load table, when judging that it can complete the cloud computing task run, then and the cloud computing task run described in request operation.
S302. cloud computing system management node receives the request of cloud computing node, obtains the described cloud computing task immigration run to the energy consumption run the cloud computing task run described in energy consumption that cloud computing node corresponding to request increase and cloud computing node operation corresponding to the request that runs and increase.
S303. cloud computing system management node consults cloud computing task load table, obtain the energy consumption of the cloud computing required by task run described in the operation of recording in cloud computing task load table, this energy consumption be run described in the cloud computing node of cloud computing task that running run the energy consumption of this cloud computing required by task;
S304. cloud computing system management node judges whether the energy consumption increased is less than the energy consumption of the described cloud computing required by task of the operation of recording in cloud computing task load table, if so, then enters step S205, otherwise terminates.
S305. by the cloud computing node corresponding to the described cloud computing task immigration run to operation request.
Also perform step S306. after migration upgrade the operation address of described cloud computing task and upgrade the energy consumption running described cloud computing required by task.
In like manner, the energy that the energy consumption that a certain parallel section completing the cloud computing task run when cloud computing node increases and the summation this parallel section being moved to the energy consumption that this cloud computing node increases are less than the cloud computing node running this parallel section is consuming time, then this parallel section of task can be moved to this cloud computing node by cloud computing system management node.And the address by primitive nebula computing node is also updated to the address of new cloud computing node by the operation address of this cloud computing task recorded in cloud computing task load table, and the energy consumption by primitive nebula computing node is also changed to the energy consumption that new cloud computing node runs this parallel section by the energy consumption of this cloud computing required by task of operation of record.
Embodiment 2
On the basis of embodiment 1, the present invention also provides a kind of cloud computing dispatching system.See Fig. 3 and 4, a kind of cloud computing dispatching system of this specific embodiment specifically comprises: cloud computing system management node 100 and carry out at least one mutual cloud computing node 200 with it;
Cloud computing node 200 comprises:
Request sending module 201, for consulting its task that can complete of cloud computing task load list deciding, and sends to cloud computing system management node for this task formation operation request;
Cloud computing system management node 100 comprises:
Request receiving module 101, for receiving the request of operation, obtaining cloud computing node corresponding to the request of operation and completing the energy consumption that this task increases;
Scheduler module 102, for running this task scheduling to increasing in the minimum cloud computing node of energy consumption.
Based on the scheme of this specific embodiment, system of the present invention is first consulted cloud computing task load table by the request sending module 201 in cloud computing node 200 and is consulted task and judge whether to finish the work, if can, request sending module 201 forms operation request for this task and sends to cloud computing system management node 100; After request receiving module 101 in cloud computing system management node 100 receives the request of operation, obtain each energy consumption required for cloud computing node that can complete this task, then scheduler module 102 contrasts these energy consumptions, then selection institute is increased the minimum cloud computing node of energy consumption, and this task scheduling is run in the minimum cloud computing node of increase energy consumption.Due to the mode by cloud computing node 200 active request, the burden that cloud computing system management node 100 travels through all cloud computing nodes 200 can be removed from, greatly save time and the energy consumption of traversal, and cloud computing system management node 100 size of energy consumption can also carry out scheduler task, as far as possible the operation energy consumption of task is dropped to minimum, thus effectively reduce the energy consumption of cloud computing system, improve the operational efficiency of cloud computing system.
Wherein, described cloud computing task load table can be stored on any one cloud computing node 200, consults for cloud computing system management node 100 and each cloud computing node 200, to improve the dirigibility of cloud computing system layout.
The content that cloud computing task load table stores includes but not limited to the energy consumption needed for each parallel section of the running status of task, the operation address of task, computing power needed for each parallel section of operation task and operation task.The running status of task includes but not limited to that wait runs, running and operation completes, and the operation address of task is cloud computing node 200 address of each parallel section running this task.Computing power specifically refers to Central processing capability, the memory power and network capabilities etc. of cloud computing node 200, and Central processing capability can be specifically flops, memory power can be specifically memory size, network capabilities can be specifically the network bandwidth etc.
In specific implementation process, what the information corresponding with task will be real-time is upgraded in cloud computing task load table, upgrades cloud computing task load table by task scheduling after increasing the minimum cloud computing node 200 of energy consumption.As the running status of this task is updated to by waiting for running the address that namely the operation address running, upgrade this task upgrades the cloud computing node 200 running this task.
In specific implementation process, request sending module 201 specifically comprises:
Consult and computing module, obtain task for consulting cloud computing task load table, and obtained the computing power of this required by task;
Determination module, for judging that when the residue computing power of cloud computing node self is greater than the computing power of described required by task it can complete described task;
Sending module, sends to cloud computing system management node for forming operation request for this task.
In specific implementation process, because cloud computing nodes 200 all in cloud computing system can cross the process of active participate scheduling, therefore, when cloud computing node 200 judges self to complete a certain parallel section in cloud computing task, then active request runs this parallel section, calculate it complete energy consumption that this parallel section increases and be supplied to cloud computing system management node 100 simultaneously, cloud computing system management node 100 selects the cloud computing node 200 that energy consumption is minimum, make task scheduling more reasonable like this, fair and quick, effectively can reduce the energy consumption of cloud computing system, also the operational efficiency of cloud computing system can be improved.Based on this, described task can be all parallel sections/a certain parallel section/multiple parallel section of cloud computing task to be run, and also can be all parallel sections or a certain parallel section/multiple parallel section of the cloud computing task run.
When task is all parallel sections/a certain parallel section/multiple parallel section wait the cloud computing task run, scheduler module 102 selects all operation to ask the cloud computing node 200 that in corresponding cloud computing node 200, energy consumption is minimum to run this task;
When task is all parallel sections/a certain parallel section/multiple parallel section of the cloud computing task run, scheduler module 102 judge to run cloud computing node 200 corresponding to request complete energy consumption that this required by task wants and the energy consumption summation that increased to the cloud computing node 200 that this operation request is corresponding by this task immigration is minimum and be less than run this task cloud computing node 200 needed for energy consumption, by operation in this task immigration to the minimum corresponding cloud computing node 200 of energy consumption summation.
Task of the present invention can be to be run also can running, can be all parallel sections of cloud computing task, also can be the multiple of cloud computing task or certain parallel section, improve the dirigibility of task scheduling, and the task in cloud computing system at any time can both be performed with minimum energy consumption, greatly reduce the energy consumption of cloud computing system.
The corresponding same or analogous parts of same or analogous label;
Describe in accompanying drawing position relationship for only for exemplary illustration, the restriction to this patent can not be interpreted as;
Obviously, the above embodiment of the present invention is only for example of the present invention is clearly described, and is not the restriction to embodiments of the present invention.For those of ordinary skill in the field, can also make other changes in different forms on the basis of the above description.Here exhaustive without the need to also giving all embodiments.All any amendments done within the spirit and principles in the present invention, equivalent to replace and improvement etc., within the protection domain that all should be included in the claims in the present invention.
Claims (10)
1. a cloud computing dispatching method, is characterized in that, comprising:
Cloud computing node consults its task that can complete of cloud computing task load list deciding, and sends to cloud computing system management node for this task formation operation request;
Cloud computing system management node receives the request of operation, obtains cloud computing node corresponding to the request of operation and completes the energy consumption that this task increases;
This task scheduling is run to increasing in the minimum cloud computing node of energy consumption by cloud computing system management node.
2. cloud computing dispatching method according to claim 1, is characterized in that, described cloud computing task load table is stored on any one cloud computing node.
3. cloud computing dispatching method according to claim 1, is characterized in that, the content that cloud computing task load table stores comprises the running status of task, the operation address of task, the computing power needed for operation task and the energy consumption needed for operation task.
4. cloud computing dispatching method according to claim 1, is characterized in that, described method also comprises: task scheduling is upgraded cloud computing task load table after increasing the minimum cloud computing node of energy consumption.
5. the cloud computing dispatching method according to any one of Claims 1-4, is characterized in that, the concrete steps that cloud computing node consults its task that can complete of cloud computing task load list deciding are:
Cloud computing node consults cloud computing task load table, has obtained the computing power of this required by task;
Judge that when the residue computing power of cloud computing node self is greater than the computing power of described required by task it can complete described task.
6. cloud computing dispatching method according to claim 5, it is characterized in that, described task is all parallel sections/a certain parallel section/multiple parallel section of cloud computing task to be run or all parallel sections of cloud computing task run or a certain parallel section/multiple parallel section.
7. cloud computing dispatching method according to claim 6, it is characterized in that, when task is all parallel sections/a certain parallel section/multiple parallel section wait the cloud computing task run, cloud computing system management node selects all operation to ask the cloud computing node that in corresponding cloud computing node, energy consumption is minimum to run this task;
When task is all parallel sections/a certain parallel section/multiple parallel section of the cloud computing task run, cloud computing system management node judge to run cloud computing node corresponding to request complete energy consumption that this required by task wants and the energy consumption summation that increased to the cloud computing node that this operation request is corresponding by this task immigration is minimum and be less than run this task cloud computing node needed for energy consumption, run in the cloud computing node corresponding to this task immigration is minimum to energy consumption summation.
8. a cloud computing dispatching system, comprise cloud computing node and cloud computing system management node, it is characterized in that, cloud computing node comprises:
Request sending module, for consulting its task that can complete of cloud computing task load list deciding, and sends to cloud computing system management node for this task formation operation request;
Cloud computing system management node comprises:
Request receiving module, for receiving the request of operation, obtaining cloud computing node corresponding to the request of operation and completing the energy consumption that this task increases;
Scheduler module, for running this task scheduling to increasing in the minimum cloud computing node of energy consumption.
9. cloud computing dispatching system according to claim 8, it is characterized in that, request sending module comprises:
Consulting and computing module, for consulting cloud computing task load table, having obtained the computing power of this required by task;
Determination module, for judging that when the residue computing power of cloud computing node self is greater than the computing power of described required by task it can complete described task;
Sending module, sends to cloud computing system management node for forming operation request for this task.
10. cloud computing dispatching system according to claim 8 or claim 9, it is characterized in that, described task is all parallel sections/a certain parallel section/multiple parallel section of cloud computing task to be run or all parallel sections of cloud computing task run or a certain parallel section/multiple parallel section;
When task is all parallel sections/a certain parallel section/multiple parallel section wait the cloud computing task run, scheduler module selects all operation to ask the cloud computing node that in corresponding cloud computing node, energy consumption is minimum to run this task;
When task is all parallel sections/a certain parallel section/multiple parallel section of the cloud computing task run, scheduler module judge to run cloud computing node corresponding to request complete energy consumption that this required by task wants and the energy consumption summation that increased to the cloud computing node that this operation request is corresponding by this task immigration is minimum and be less than run this task cloud computing node needed for energy consumption, run in the cloud computing node corresponding to this task immigration is minimum to energy consumption summation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410684658.9A CN104331326A (en) | 2014-11-25 | 2014-11-25 | Scheduling method and system for cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410684658.9A CN104331326A (en) | 2014-11-25 | 2014-11-25 | Scheduling method and system for cloud computing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104331326A true CN104331326A (en) | 2015-02-04 |
Family
ID=52406060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410684658.9A Pending CN104331326A (en) | 2014-11-25 | 2014-11-25 | Scheduling method and system for cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104331326A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037993A (en) * | 2017-11-07 | 2018-05-15 | 大国创新智能科技(东莞)有限公司 | Cloud computing dispatching method and system based on big data and deep learning neutral net |
| CN111541781A (en) * | 2020-07-07 | 2020-08-14 | 中国人民解放军国防科技大学 | Distributed cooperative task scheduling method for mobile equipment in dense network |
| CN112003898A (en) * | 2020-07-27 | 2020-11-27 | 珠海许继芝电网自动化有限公司 | Load balancing method and system for multi-node cluster |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604264A (en) * | 2009-07-08 | 2009-12-16 | 深圳先进技术研究院 | The method for scheduling task of supercomputer and system |
| CN102360246A (en) * | 2011-10-14 | 2012-02-22 | 武汉理工大学 | Self-adaptive threshold-based energy-saving scheduling method in heterogeneous distributed system |
| US20120173709A1 (en) * | 2011-01-05 | 2012-07-05 | Li Li | Seamless scaling of enterprise applications |
| WO2012120664A1 (en) * | 2011-03-09 | 2012-09-13 | 株式会社日立製作所 | Virtual machine migration evaluation method and virtual machine system |
| CN102902344A (en) * | 2011-12-23 | 2013-01-30 | 同济大学 | Method for optimizing energy consumption of cloud computing system based on random tasks |
-
2014
- 2014-11-25 CN CN201410684658.9A patent/CN104331326A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604264A (en) * | 2009-07-08 | 2009-12-16 | 深圳先进技术研究院 | The method for scheduling task of supercomputer and system |
| US20120173709A1 (en) * | 2011-01-05 | 2012-07-05 | Li Li | Seamless scaling of enterprise applications |
| WO2012120664A1 (en) * | 2011-03-09 | 2012-09-13 | 株式会社日立製作所 | Virtual machine migration evaluation method and virtual machine system |
| CN102360246A (en) * | 2011-10-14 | 2012-02-22 | 武汉理工大学 | Self-adaptive threshold-based energy-saving scheduling method in heterogeneous distributed system |
| CN102902344A (en) * | 2011-12-23 | 2013-01-30 | 同济大学 | Method for optimizing energy consumption of cloud computing system based on random tasks |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037993A (en) * | 2017-11-07 | 2018-05-15 | 大国创新智能科技(东莞)有限公司 | Cloud computing dispatching method and system based on big data and deep learning neutral net |
| CN108037993B (en) * | 2017-11-07 | 2020-08-04 | 大国创新智能科技(东莞)有限公司 | Cloud computing scheduling method and system based on big data and deep learning neural network |
| CN111541781A (en) * | 2020-07-07 | 2020-08-14 | 中国人民解放军国防科技大学 | Distributed cooperative task scheduling method for mobile equipment in dense network |
| CN111541781B (en) * | 2020-07-07 | 2020-10-16 | 中国人民解放军国防科技大学 | Distributed cooperative task scheduling method for mobile equipment in dense network |
| CN112003898A (en) * | 2020-07-27 | 2020-11-27 | 珠海许继芝电网自动化有限公司 | Load balancing method and system for multi-node cluster |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101604264B (en) | Task scheduling method and system for supercomputer | |
| CN103164279B (en) | Cloud computing resources distribution method and system | |
| CN106933669A (en) | For the apparatus and method of data processing | |
| CN104915407A (en) | Resource scheduling method under Hadoop-based multi-job environment | |
| CN102981893B (en) | A kind of dispatching method of virtual machine and system | |
| JP2011518393A (en) | System and method for managing energy consumption in a computing environment | |
| KR20120072015A (en) | Method and system for providing energy management in smart grid environment, energy provider in smart grid environment | |
| CN103365726A (en) | Resource management method and system facing GPU (Graphic Processing Unit) cluster | |
| CN101652750A (en) | Data processing device, distributed processing system, data processing method, and data processing program | |
| Xue et al. | Q ET QET: a QoS-based energy-aware task scheduling method in cloud environment | |
| CN102394903B (en) | A kind of active reconstruction calculating system constructing system | |
| CN104754008A (en) | Network storage node, network storage system and device and method for network storage node | |
| CN106302628A (en) | ARM architecture network cluster calculates the unified management dispatching method of resource | |
| CN104331326A (en) | Scheduling method and system for cloud computing | |
| Petri et al. | A HPC based cloud model for real-time energy optimisation | |
| JP6081212B2 (en) | Computer system, resource management apparatus, and resource management method | |
| Alfa et al. | The role of 5G and IoT in smart cities | |
| Whaiduzzaman et al. | Pefc: Performance enhancement framework for cloudlet in mobile cloud computing | |
| Li et al. | Load prediction-based automatic scaling cloud computing | |
| CN114138488A (en) | Cloud-native implementation method and system based on elastic high-performance computing | |
| CN103617090A (en) | Energy saving method based on distributed management | |
| CN116402318B (en) | Multi-stage computing power resource distribution method and device for power distribution network and network architecture | |
| TW201023046A (en) | Delegated virtualization across physical partitions of a multi-core processor (MCP) | |
| GB2505412A (en) | Collaborative modified consensus workload distribution between computing nodes | |
| Wang et al. | An efficient energy-aware and service quality improvement strategy applied in cloud computing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150204 |
|
| RJ01 | Rejection of invention patent application after publication |