CN102158513A - Service cluster and energy-saving method and device thereof - Google Patents
Service cluster and energy-saving method and device thereof Download PDFInfo
- Publication number
- CN102158513A CN102158513A CN2010101119768A CN201010111976A CN102158513A CN 102158513 A CN102158513 A CN 102158513A CN 2010101119768 A CN2010101119768 A CN 2010101119768A CN 201010111976 A CN201010111976 A CN 201010111976A CN 102158513 A CN102158513 A CN 102158513A
- Authority
- CN
- China
- Prior art keywords
- node
- load
- migration
- section point
- nodes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
The invention provides a service cluster and an energy-saving method and device thereof. The method comprises the following steps of: acquiring loads corresponding to preset quantity of nodes in the server cluster; and in the preset quantity of nodes, if the load of the first node is less than or equal to the resource surplus of the second node, migrating a process corresponding to the operation on the first node to the second node for operating. By applying the technical scheme provided by the invention, the loads of the nodes and the load surplus resources are acquired; when the load surplus resources of other nodes can satisfy the load requirement on one node, the operation on one node can be migrated to other nodes, and the node subjected to operation migration is in an idle state and even can be closed; and therefore, the electricity consumption of the whole server cluster is reduced, and the operation cost is saved.
Description
Technical field
The present invention relates to server technology, be meant a kind of server cluster method for saving energy, device and server cluster especially.
Background technology
Along with the demand to high-performance server is more and more, server cluster is because its high cost performance has obtained extensive application, at present the scale of server cluster is also increasing, and the server node in the server cluster (abbreviation node) quantity increases substantially and brought the quick growth of power consumption.Server node quantity in the server cluster is in quick growth, but its service efficiency is before ranging in low level not, to use the most general X86 server cluster is example, generally believe that its utilance is lower than 30%, Intel server average utilization has only 10% usually, thereby causes a large amount of waste of power resources.
In the prior art, can pass through the automatic frequency reducing of processor for the separate unit server, close peripheral hardware, means such as server dormancy realize energy-conservation; But for server cluster, whether in the energy-conservation way of existing server cluster, normally checking passively has operation in operation on the node, if not then this node is closed.Adopt prior art, if the cluster of 100 nodes is arranged in actual applications, each node all has operation, but each has only 10% utilance, and 100 nodes need standard-sized sheet so, and this can waste electric power resource.
The inventor is in realizing process of the present invention, and find that there are the following problems at least in the prior art: the utilance of the server node in the server cluster is low, thereby causes the waste of server cluster electric power resource.
Summary of the invention
The purpose of this invention is to provide a kind of server cluster method for saving energy, device and server cluster, be used to realize the energy-conservation of server cluster.
A kind of server cluster method for saving energy comprises: obtain the pairing load of a predetermined number node in the server group of planes; In a described predetermined number node, if the load of first node is less than or equal to the resource residual amount of Section Point; The pairing process migration of operation on the described first node is moved to Section Point.
In the method, the pairing process migration of operation on the described first node is moved to Section Point, be specially: with the address space of the process of the operation correspondence on the described first node, described process to the executing state of the access parameter of other process, process code, described process and will be to the all-access of the described process before the migration, the described process after the migration that the counterpoise new url moves to the described Section Point.
In the method, obtain before the load of a predetermined number node in the server group of planes, also comprise: all nodes in the described server group of planes are divided into groups according to described predetermined number, form at least one groups of nodes; The step of obtaining the load of a predetermined number node in the server group of planes is specially: in each described groups of nodes, obtain the pairing load of a predetermined number node in the groups of nodes, and inquire about described first node and the described Section Point that is fit to carry out job migration.
In the method, described inquiry is fit to carry out the described first node and the described Section Point of job migration, comprising: inquire about the node of the numbering maximum of moving in the described groups of nodes, obtain the operation situation moved on this node as described load; Obtain the described load resource surplus of the node of the numbering minimum of moving in the described groups of nodes; When described load during smaller or equal to described load resource surplus, the node of described numbering maximum is as described first node, and the node of described numbering minimum is as described Section Point.
In the method, also comprise after the process migration of the operation correspondence on the described first node moved to Section Point: to described first node sending controling instruction, described control command is in order to reduce the power consumption of described first node.
In the method, described load comprises: cpu busy percentage or idleness, memory usage or idleness, and/or network interface card flow.
The device that a kind of server cluster is energy-conservation comprises: operation unit, the load that is used for obtaining a server group of planes predetermined number node; The management and monitoring unit is used at a described predetermined number node, selects first node, and the load of this first node is smaller or equal to the load resource surplus; And the selection Section Point, the load resource surplus of this Section Point is more than or equal to described load; The process migration unit is used for the process migration of the operation correspondence on the described first node is moved to Section Point.
In the device, described process migration unit comprises: first acquiring unit is used to the address space of the process of obtaining; Second acquisition unit is used to obtain the access parameter of described process to other process; The 3rd acquiring unit is used to obtain the process code; The 4th acquiring unit is used to obtain the executing state of described process; The 5th acquiring unit is used to obtain the all-access counterpoise new url to the described process before the migration is arrived migration described process afterwards.
In the device, described management and monitoring unit specifically comprises: first query unit, be used to inquire about the node of the numbering maximum of moving in the described groups of nodes, and obtain the operation situation moved on this node as described load; First query unit is used to obtain the described load resource surplus of the node of the numbering minimum of moving in the described groups of nodes; The contrast unit is used for when described load during smaller or equal to described load resource surplus, and the node of described numbering maximum is as described first node, and the node of described numbering minimum is as described Section Point.
A kind of server cluster comprises: node is used to finish various calculation tasks; Also comprise: the device that server cluster is energy-conservation comprises in the energy-conservation device of this server cluster: operation unit, the load that is used for obtaining a server group of planes predetermined number node; The management and monitoring unit is used at a described predetermined number node, selects first node, and the load of this first node is smaller or equal to the load resource surplus; And the selection Section Point, the load resource surplus of this Section Point is more than or equal to load; The process migration unit is used for the pairing process migration of the operation on the described first node is moved to Section Point.
The technical scheme that is provided is provided, obtain the load and the load surplus resources of node, when the load surplus resources of other nodes can satisfy the load needs of a node, can be to other nodes with the job migration on the described node, the node that carries out after the job migration is in idle condition, even can be closed, like this then reduced the power consumption of whole server cluster, saved operating cost.
Description of drawings
Fig. 1 is an embodiment of the invention server cluster method for saving energy schematic flow sheet;
Fig. 2 is an embodiment of the invention server cluster structure chart;
Fig. 3 is an embodiment of the invention server cluster energy-saving process schematic diagram;
Fig. 4 is the energy-conservation structure drawing of device of embodiment of the invention server cluster.
Embodiment
For making purpose of the present invention, technical characterictic and implementation result clearer, below in conjunction with the accompanying drawings and the specific embodiments technical scheme of the present invention is described in detail.Among the embodiment provided by the invention, between each server node (abbreviation node) of server cluster, realize job migration.
Among the present invention, provide a kind of server cluster method for saving energy, as shown in Figure 1, comprising:
The technical scheme that is provided is provided, obtain the load and the load surplus resources of node, when the load surplus resources of other nodes can satisfy the load needs of a node, can be to other nodes with the job migration on the described node, the node that carries out after the job migration is in idle condition, even can be closed, like this then reduced the power consumption of whole server cluster, saved operating cost.
In the technical scheme of the foregoing description, the pairing process migration of the operation on the described first node is moved to Section Point, specifically comprise and obtaining: the address space of process; Described process is to the access parameter of other process; The process code; The executing state of described process; And will arrive migration described process afterwards to the all-access counterpoise new url of the described process before the migration.
Obtain the load of a predetermined number node in the server group of planes, specifically comprise: all node grouping in the described server group of planes are formed groups of nodes, with all nodes in each described groups of nodes as a described predetermined number node.
In each described groups of nodes, the node that inquiry is fit to carry out job migration comprises: inquire about the node of the numbering maximum of moving in the described groups of nodes, obtain the operation situation moved on this node as described load; Obtain the described load resource surplus of the node of the numbering minimum of moving in the described groups of nodes, as described first threshold; When described load smaller or equal to described first threshold, and described load resource surplus is during more than or equal to described first threshold, the node of described numbering maximum is as described first node, the node of described numbering minimum is as described Section Point.
Describedly also comprise after the pairing process migration of operation on the described first node is moved to Section Point: to described first node sending controling instruction, described control command is in order to reduce the power consumption of described first node.In this area, normally described first node is turned off by IPMI (IPMI, Integrated DellRemote Access Controller).
Described load comprises: cpu busy percentage/idleness, memory usage/idleness, and network interface card flow.
Use the technical scheme that above-mentioned each embodiment provides, in a server cluster as shown in Figure 2, comprised a plurality of groups of nodes, each groups of nodes has comprised a plurality of nodes.Owing to comprised more node in the whole server cluster, and the number of its node is dynamic change, can increase also and can reduce, and therefore, the present invention is directed to different situations multiple technical scheme is provided.
Wherein, comprising:
In on the same group, each node is numbered, in first group, numbering is from node11 to node1N, wherein, the numbering of each node node back, the numbering of the group at first expression place, second numbering that is illustrated in the group, if there is more group, then adopt multidigit to represent the numbering of organizing, if there are a plurality of nodes in same group, then adopt multidigit to represent to organize interior numbering, its representation also can change.
Specific implementation comprises various ways, below is a kind of preferred scheme:
Node by the numbering maximum moved in the operating system inquiry group obtains the operation situation of moving on this node, as cpu busy percentage/idleness, and memory usage/idleness;
Obtain the load resource surplus of the node of the numbering minimum of moving in the group.
If the load of this node increases, illustrate that not having other node has resource can supply migration, and have new operation to submit to.
Can on the basis of the technical scheme that step 301～step 307 provided, further optimize, in the step 303, obtain the load of all nodes in the groups of nodes, load is sorted, be followed successively by according to load order from small to large: Load
1, Load
2, Load
3... Load
N/2, Load
N/2+1... Load
nIn step 304 with Load
1Load and Load
nThe load resource surplus, Load
2Load and Load
N-1The load resource surplus ... .., and Load
N/2Load and Load
N/2+1The load resource surplus compare successively, and carry out follow-up step.Wherein, the load resource surplus deducts load by load capacity and obtains.
In step 305, by process migration, will just operate in the job migration of numbering on the maximum node to the minimum node of numbering, specifically comprise:
Process migration is moved to a process of carrying out on another node that connects by network from a node.Finish the process status that process migration need obtain process to be migrated, comprise: the address space of (1) process, (2) to the visit of other process, as socket, pipeline etc., (3) code, this code can be formed the part of address space, (4) executing state, currency as register, storehouse etc., and (5) all are linked to those all-access to the process before the migration on the new process copy again, realize real seamless migration, this is because non-seamless migration can lead to errors.
The operation of whole process migration must be an atomic operation, so just can avoid losing or two copies being arranged of process; The process migration system of the isomorphism that can realize comprises: V Charllote, DEMOS/MP, Sprite, Condor and Accent.Wherein:
DEMOS/MP can move by implementation process, a process in DEMOS/MP can be in its execution phase migration, continuation obtains the required resource of operation process at another new processor, and rapid updating message path, receives at the new processor place to transmit the message of coming.The DEMOS/MP system can effectively carry out process migration and not influence system service.
Condor is the resource management system of computation-intensive operation, and this system is made up of job management and resource management two parts.User job partly is in charge of in job management, and the user can understand job queue by its, submit new operation to, perhaps inquiry job situation about finishing etc.The available situation of resource management part monitoring resources is carried out the distribution of resource and scheduling etc.; In the resource management part, the Resource Owner has the highest priority that this resource is used in the Condor system, can formulate the resource usage policy according to the actual conditions of oneself, the operation that other users submit to the execution of Condor system can not hinder the use of Resource Owner to its resource.In other words, the Condor system is by adopting chance to calculate (OpportunisticComputing), effectively utilize the microcomputer resource that ownership distributes, having created the computation-intensive operating environment.In addition, Condor also possesses as supporting and realizes interconnection between kinds of platform, checkpoint and process migration, remote system call, the Condor pond, and characteristics such as can dynamically be expanded in the Condor pond.
Other system, though its characteristics are respectively arranged, equally can the implementation process migration.
Corresponding, if the scale of server cluster is not very big, and its scale can control, and can save step 302 so, and so, all computing nodes in the then whole server cluster are all handled as the node in the same groups of nodes.
In a scene that is applied to server cluster, this cluster has 100 nodes (server), if adopt the energy-conservation way of existing server cluster, checks passively then whether node has operation in operation, if this node does not have operation in operation, this node is closed.If each node all has operation, but each has only 10% utilance, 100 nodes need standard-sized sheet so, if and adopt technical scheme of the present invention, realize the process migration of operation between different nodes, if All Jobs is moved on 25 nodes, then average every utilance is about 40%, close other 75 nodes, power consumption can approximately be reduced to 1/4 of former power consumption.
Corresponding, the invention provides the energy-conservation device of a kind of server cluster, as shown in Figure 4, comprising:
Management and monitoring unit 402 is used at a described predetermined number node, selects first node, and the load of this first node is smaller or equal to first threshold; And the selection Section Point, the load resource surplus of this Section Point is more than or equal to first threshold;
The technical scheme provided is provided, because can be with the job migration on the node to another node, previous node like this be owing to be in idle condition, even can close, and then the power consumption of whole server cluster reduces, and has saved operating cost.
Wherein, comprise in the process migration unit 403:
First acquiring unit is used to the address space of the process of obtaining;
Second acquisition unit is used to obtain the access parameter of described process to other process;
The 3rd acquiring unit is used to obtain the process code;
The 4th acquiring unit is used to obtain the executing state of described process;
The 5th acquiring unit is used to obtain the all-access counterpoise new url to the described process before the migration is arrived migration described process afterwards.
Management and monitoring unit 402 specifically comprises:
First query unit is used to inquire about the node of the numbering maximum of moving in the described groups of nodes, obtains the operation situation moved on this node as described load;
First query unit is used to obtain the described load resource surplus of the node of the numbering minimum of moving in the described groups of nodes, as described first threshold;
The contrast unit, be used for when described load smaller or equal to described first threshold, and described load resource surplus is during more than or equal to described first threshold, the node of described numbering maximum is as described first node, the node of described numbering minimum is as described Section Point.
Corresponding, the invention provides a kind of server cluster, comprising: node is used to finish various calculation tasks; Also comprise:
The device that server cluster is energy-conservation comprises in the energy-conservation device of this server cluster:
Operation unit, the load that is used for obtaining a server group of planes predetermined number node;
The management and monitoring unit is used at a described predetermined number node, selects first node, and the load of this first node is smaller or equal to first threshold; And the selection Section Point, the load resource surplus of this Section Point is more than or equal to first threshold;
The process migration unit is used for the pairing process migration of the operation on the described first node is moved to Section Point.
Embodiments of the invention have following beneficial effect, because can be with the job migration on the node to another node, previous node like this be owing to be in idle condition, even can close, then the power consumption of whole server cluster reduces, and has saved operating cost.
Should be noted that above embodiment is only unrestricted in order to technical scheme of the present invention to be described, all parameter values can be according to the actual conditions adjustment, and in this rights protection scope.Those of ordinary skill in the art should be appreciated that and can make amendment or be equal to replacement technical scheme of the present invention, and do not break away from the spiritual scope of technical solution of the present invention, and it all should be encompassed in the middle of the claim scope of the present invention.
Claims (10)
1. a server cluster method for saving energy is characterized in that, comprising:
Obtain the pairing load of a predetermined number node in the server group of planes;
In a described predetermined number node, if the load of first node is less than or equal to the resource residual amount of Section Point;
The pairing process migration of operation on the described first node is moved to Section Point.
2. method according to claim 1 is characterized in that, the pairing process migration of the operation on the described first node is moved to Section Point, is specially:
With the address space of the process of the operation correspondence on the described first node, described process to the executing state of the access parameter of other process, process code, described process and will be to the all-access of the described process before the migration, the described process after the migration that the counterpoise new url moves to the described Section Point.
3. method according to claim 1 is characterized in that, obtains before the load of a predetermined number node in the server group of planes, also comprises:
All nodes in the described server group of planes are divided into groups according to described predetermined number, form at least one groups of nodes;
The step of obtaining the load of a predetermined number node in the server group of planes is specially:
In each described groups of nodes, obtain the pairing load of a predetermined number node in the groups of nodes, and inquire about described first node and the described Section Point that is fit to carry out job migration.
4. method according to claim 3 is characterized in that, described inquiry is fit to carry out the described first node and the described Section Point of job migration, comprising:
Inquire about the node of the numbering maximum of moving in the described groups of nodes, obtain the operation situation moved on this node as described load;
Obtain the described load resource surplus of the node of the numbering minimum of moving in the described groups of nodes;
When described load during smaller or equal to described load resource surplus, the node of described numbering maximum is as described first node, and the node of described numbering minimum is as described Section Point.
5. method according to claim 1 is characterized in that, also comprises after the process migration of the operation correspondence on the described first node is moved to Section Point:
To described first node sending controling instruction, described control command is in order to reduce the power consumption of described first node.
6. method according to claim 1 is characterized in that, described load comprises:
Cpu busy percentage or idleness, memory usage or idleness, and/or network interface card flow.
7. the device that server cluster is energy-conservation is characterized in that, comprising:
Operation unit, the load that is used for obtaining a server group of planes predetermined number node;
The management and monitoring unit is used at a described predetermined number node, selects first node, and the load of this first node is smaller or equal to the load resource surplus; And the selection Section Point, the load resource surplus of this Section Point is more than or equal to described load;
The process migration unit is used for the process migration of the operation correspondence on the described first node is moved to Section Point.
8. device according to claim 7 is characterized in that, described process migration unit comprises:
First acquiring unit is used to the address space of the process of obtaining;
Second acquisition unit is used to obtain the access parameter of described process to other process;
The 3rd acquiring unit is used to obtain the process code;
The 4th acquiring unit is used to obtain the executing state of described process;
The 5th acquiring unit is used to obtain the all-access counterpoise new url to the described process before the migration is arrived migration described process afterwards.
9. device according to claim 7 is characterized in that, described management and monitoring unit specifically comprises:
First query unit is used to inquire about the node of the numbering maximum of moving in the described groups of nodes, obtains the operation situation moved on this node as described load;
First query unit is used to obtain the described load resource surplus of the node of the numbering minimum of moving in the described groups of nodes;
The contrast unit is used for when described load during smaller or equal to described load resource surplus, and the node of described numbering maximum is as described first node, and the node of described numbering minimum is as described Section Point.
10. server cluster, comprising: node is used to finish various calculation tasks; It is characterized in that, also comprise:
The device that server cluster is energy-conservation comprises in the energy-conservation device of this server cluster:
Operation unit, the load that is used for obtaining a server group of planes predetermined number node;
The management and monitoring unit is used at a described predetermined number node, selects first node, and the load of this first node is smaller or equal to the load resource surplus; And the selection Section Point, the load resource surplus of this Section Point is more than or equal to load;
The process migration unit is used for the pairing process migration of the operation on the described first node is moved to Section Point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101119768A CN102158513A (en) | 2010-02-11 | 2010-02-11 | Service cluster and energy-saving method and device thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101119768A CN102158513A (en) | 2010-02-11 | 2010-02-11 | Service cluster and energy-saving method and device thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102158513A true CN102158513A (en) | 2011-08-17 |
Family
ID=44439694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010101119768A Pending CN102158513A (en) | 2010-02-11 | 2010-02-11 | Service cluster and energy-saving method and device thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102158513A (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102299964A (en) * | 2011-08-30 | 2011-12-28 | 南京邮电大学 | Data redeployment method applied to energy-saving trunking system |
| CN102369511A (en) * | 2011-09-01 | 2012-03-07 | 华为技术有限公司 | Resource removing method, device and system |
| CN102387024A (en) * | 2010-09-06 | 2012-03-21 | 联想(北京)有限公司 | Power consumption control method, management node and data processing center |
| WO2013040739A1 (en) * | 2011-09-19 | 2013-03-28 | Peking University | System and method for communication in a cellular network |
| CN103051686A (en) * | 2012-12-10 | 2013-04-17 | 北京普泽天玑数据技术有限公司 | Method and system for isolating dynamic application of distributed system |
| CN103106047A (en) * | 2013-01-29 | 2013-05-15 | 浪潮(北京)电子信息产业有限公司 | Storage system based on object and storage method thereof |
| CN103106044A (en) * | 2012-12-13 | 2013-05-15 | 深圳先进技术研究院 | Classification storage energy-saving method |
| CN103150263A (en) * | 2012-12-13 | 2013-06-12 | 深圳先进技术研究院 | Hierarchical storage method |
| CN103250139A (en) * | 2012-11-07 | 2013-08-14 | 华为技术有限公司 | A method and an apparatus for migrating computing nodes ` |
| CN104270430A (en) * | 2014-09-19 | 2015-01-07 | 国云科技股份有限公司 | Server remote dispatching method suitable for cloud computing |
| CN104331322A (en) * | 2014-10-24 | 2015-02-04 | 华为技术有限公司 | Process migration method and device |
| CN105740077A (en) * | 2016-01-29 | 2016-07-06 | 中国联合网络通信集团有限公司 | Task assigning method applicable to cloud computing |
| CN106021411A (en) * | 2016-05-13 | 2016-10-12 | 大连理工大学 | Storm task deployment and configuration platform with cluster adaptability |
| CN106331036A (en) * | 2015-06-30 | 2017-01-11 | 联想(北京)有限公司 | Server control method and device |
| CN106452822A (en) * | 2016-04-25 | 2017-02-22 | 汕头大学 | Online energy consumption management method and apparatus of large-scale server cluster |
| CN106445680A (en) * | 2016-08-31 | 2017-02-22 | 成都云麒麟软件有限公司 | Computing element migration method based on aggregate utility |
| CN106776018A (en) * | 2016-12-01 | 2017-05-31 | 三星（中国）半导体有限公司 | Host node for distributed system and method for parallel processing and equipment from node |
| CN107329801A (en) * | 2017-06-29 | 2017-11-07 | 深信服科技股份有限公司 | A kind of node administration method and device, many component servers |
| CN107835130A (en) * | 2017-12-12 | 2018-03-23 | 中国联合网络通信集团有限公司 | A kind of flow allocation method and device |
| CN108153615A (en) * | 2016-12-02 | 2018-06-12 | 航天星图科技（北京）有限公司 | A kind of fault data restoration methods |
| CN108810071A (en) * | 2018-03-30 | 2018-11-13 | 广东睿江云计算股份有限公司 | A method of the Apache Server cluster load balance based on process migration |
| CN108983946A (en) * | 2018-06-13 | 2018-12-11 | 烽火通信科技股份有限公司 | A kind of server energy consumption control method, system and equipment |
| CN110336705A (en) * | 2019-07-23 | 2019-10-15 | 重庆电子工程职业学院 | A kind of edge cloud power-economizing method |
| CN110633140A (en) * | 2018-06-21 | 2019-12-31 | 中兴通讯股份有限公司 | Resource scheduling method, device and computer storage medium |
| CN110795250A (en) * | 2019-10-30 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Load scheduling method, device, equipment and storage medium |
| CN111625344A (en) * | 2019-02-27 | 2020-09-04 | 阿里巴巴集团控股有限公司 | Resource scheduling system, method and device in application system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060069761A1 (en) * | 2004-09-14 | 2006-03-30 | Dell Products L.P. | System and method for load balancing virtual machines in a computer network |
| CN1947096A (en) * | 2004-05-08 | 2007-04-11 | 国际商业机器公司 | Dynamic migration of virtual machine computer programs |
| CN101452406A (en) * | 2008-12-23 | 2009-06-10 | 北京航空航天大学 | Cluster load balance method transparent for operating system |
-
2010
- 2010-02-11 CN CN2010101119768A patent/CN102158513A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1947096A (en) * | 2004-05-08 | 2007-04-11 | 国际商业机器公司 | Dynamic migration of virtual machine computer programs |
| US20060069761A1 (en) * | 2004-09-14 | 2006-03-30 | Dell Products L.P. | System and method for load balancing virtual machines in a computer network |
| CN101452406A (en) * | 2008-12-23 | 2009-06-10 | 北京航空航天大学 | Cluster load balance method transparent for operating system |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102387024A (en) * | 2010-09-06 | 2012-03-21 | 联想(北京)有限公司 | Power consumption control method, management node and data processing center |
| CN102387024B (en) * | 2010-09-06 | 2014-09-03 | 联想(北京)有限公司 | Power consumption control method, management node and data processing center |
| CN102299964B (en) * | 2011-08-30 | 2013-08-07 | 南京邮电大学 | Data redeployment method applied to energy-saving trunking system |
| CN102299964A (en) * | 2011-08-30 | 2011-12-28 | 南京邮电大学 | Data redeployment method applied to energy-saving trunking system |
| CN102369511A (en) * | 2011-09-01 | 2012-03-07 | 华为技术有限公司 | Resource removing method, device and system |
| WO2012119436A1 (en) * | 2011-09-01 | 2012-09-13 | 华为技术有限公司 | Method, device and system for migrating resources |
| CN102369511B (en) * | 2011-09-01 | 2013-08-28 | 华为技术有限公司 | Resource removing method, device and system |
| WO2013040739A1 (en) * | 2011-09-19 | 2013-03-28 | Peking University | System and method for communication in a cellular network |
| WO2014071580A1 (en) * | 2012-11-07 | 2014-05-15 | 华为技术有限公司 | Compute node migration method and device |
| CN103250139A (en) * | 2012-11-07 | 2013-08-14 | 华为技术有限公司 | A method and an apparatus for migrating computing nodes ` |
| CN103250139B (en) * | 2012-11-07 | 2016-08-03 | 华为技术有限公司 | A kind of method and device migrating calculating node |
| CN103051686A (en) * | 2012-12-10 | 2013-04-17 | 北京普泽天玑数据技术有限公司 | Method and system for isolating dynamic application of distributed system |
| CN103150263A (en) * | 2012-12-13 | 2013-06-12 | 深圳先进技术研究院 | Hierarchical storage method |
| CN103106044A (en) * | 2012-12-13 | 2013-05-15 | 深圳先进技术研究院 | Classification storage energy-saving method |
| CN103106044B (en) * | 2012-12-13 | 2016-09-07 | 深圳先进技术研究院 | Classification storage power-economizing method |
| CN103106047A (en) * | 2013-01-29 | 2013-05-15 | 浪潮(北京)电子信息产业有限公司 | Storage system based on object and storage method thereof |
| CN104270430A (en) * | 2014-09-19 | 2015-01-07 | 国云科技股份有限公司 | Server remote dispatching method suitable for cloud computing |
| CN104331322A (en) * | 2014-10-24 | 2015-02-04 | 华为技术有限公司 | Process migration method and device |
| CN104331322B (en) * | 2014-10-24 | 2018-03-13 | 华为技术有限公司 | A kind of process migration method and apparatus |
| CN106331036A (en) * | 2015-06-30 | 2017-01-11 | 联想(北京)有限公司 | Server control method and device |
| CN105740077A (en) * | 2016-01-29 | 2016-07-06 | 中国联合网络通信集团有限公司 | Task assigning method applicable to cloud computing |
| CN106452822A (en) * | 2016-04-25 | 2017-02-22 | 汕头大学 | Online energy consumption management method and apparatus of large-scale server cluster |
| CN106452822B (en) * | 2016-04-25 | 2019-06-18 | 汕头大学 | A kind of online energy consumption management method and device of large-scale server cluster |
| CN106021411B (en) * | 2016-05-13 | 2019-04-16 | 大连理工大学 | A kind of Storm task deployment and configuration platform with cluster adaptivity |
| CN106021411A (en) * | 2016-05-13 | 2016-10-12 | 大连理工大学 | Storm task deployment and configuration platform with cluster adaptability |
| CN106445680A (en) * | 2016-08-31 | 2017-02-22 | 成都云麒麟软件有限公司 | Computing element migration method based on aggregate utility |
| CN106445680B (en) * | 2016-08-31 | 2020-01-14 | 杭州聚玻科技有限公司 | Computing unit migration method based on comprehensive utility |
| CN106776018A (en) * | 2016-12-01 | 2017-05-31 | 三星（中国）半导体有限公司 | Host node for distributed system and method for parallel processing and equipment from node |
| CN108153615A (en) * | 2016-12-02 | 2018-06-12 | 航天星图科技（北京）有限公司 | A kind of fault data restoration methods |
| CN107329801A (en) * | 2017-06-29 | 2017-11-07 | 深信服科技股份有限公司 | A kind of node administration method and device, many component servers |
| CN107329801B (en) * | 2017-06-29 | 2020-12-15 | 深信服科技股份有限公司 | Node management method and device and multi-subsatellite server |
| CN107835130A (en) * | 2017-12-12 | 2018-03-23 | 中国联合网络通信集团有限公司 | A kind of flow allocation method and device |
| CN108810071A (en) * | 2018-03-30 | 2018-11-13 | 广东睿江云计算股份有限公司 | A method of the Apache Server cluster load balance based on process migration |
| CN108983946A (en) * | 2018-06-13 | 2018-12-11 | 烽火通信科技股份有限公司 | A kind of server energy consumption control method, system and equipment |
| CN108983946B (en) * | 2018-06-13 | 2021-04-27 | 烽火通信科技股份有限公司 | Server power consumption control method, system and equipment |
| CN110633140A (en) * | 2018-06-21 | 2019-12-31 | 中兴通讯股份有限公司 | Resource scheduling method, device and computer storage medium |
| CN111625344A (en) * | 2019-02-27 | 2020-09-04 | 阿里巴巴集团控股有限公司 | Resource scheduling system, method and device in application system |
| CN111625344B (en) * | 2019-02-27 | 2023-07-04 | 阿里巴巴集团控股有限公司 | Resource scheduling system, method and device in application system |
| CN110336705A (en) * | 2019-07-23 | 2019-10-15 | 重庆电子工程职业学院 | A kind of edge cloud power-economizing method |
| CN110795250A (en) * | 2019-10-30 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Load scheduling method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102158513A (en) | Service cluster and energy-saving method and device thereof | |
| US8776066B2 (en) | Managing task execution on accelerators | |
| CA2522467C (en) | Automated power control policies based on application-specific redundancy characteristics | |
| Shi et al. | Empirical evaluation of vector bin packing algorithms for energy efficient data centers | |
| CN102843419B (en) | A kind of service resource allocation method and system | |
| CN102508714A (en) | Green-computer-based virtual machine scheduling method for cloud computing | |
| TWI425422B (en) | Multi-cpu domain mobile electronic device and operation method thereof | |
| CN104679594B (en) | A kind of middleware distributed computing method | |
| CN104834569A (en) | Cluster resource scheduling method and cluster resource scheduling system based on application types | |
| CN103067425A (en) | Creation method of virtual machine, management system of virtual machine and related equipment thereof | |
| CN104252390A (en) | Resource scheduling method, device and system | |
| US20130167152A1 (en) | Multi-core-based computing apparatus having hierarchical scheduler and hierarchical scheduling method | |
| CN103297499A (en) | Scheduling method and system based on cloud platform | |
| CN103365726A (en) | Resource management method and system facing GPU (Graphic Processing Unit) cluster | |
| CN104050137B (en) | The method and device that kernel is run in a kind of OS | |
| US20200042608A1 (en) | Distributed file system load balancing based on available node capacity | |
| Long et al. | A three-phase energy-saving strategy for cloud storage systems | |
| CN104077189A (en) | Method and device for distributing resources | |
| CN104572279B (en) | A kind of virtual machine dynamic dispatching method of supporting node binding | |
| US20140355478A1 (en) | Method of providing a dynamic node service and device using the same | |
| CN102387024B (en) | Power consumption control method, management node and data processing center | |
| Than et al. | Energy-saving resource allocation in cloud data centers | |
| CN102098223B (en) | Method, device and system for scheduling node devices | |
| CN103973784A (en) | Method for effectively utilizing cloud storage server resources | |
| CN104683480A (en) | Distribution type calculation method based on applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20110817 |