CN105354091A - Spatial position based elastic load balance method and system - Google Patents
Spatial position based elastic load balance method and system Download PDFInfo
- Publication number
- CN105354091A CN105354091A CN201510680052.2A CN201510680052A CN105354091A CN 105354091 A CN105354091 A CN 105354091A CN 201510680052 A CN201510680052 A CN 201510680052A CN 105354091 A CN105354091 A CN 105354091A
- Authority
- CN
- China
- Prior art keywords
- server
- spatial data
- graticule mesh
- data
- load
- 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
-
- 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]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to a spatial position based elastic load balance method. The method comprises the following steps: constructing mapping relationships between spatial data and server nodes with a spatial Hash algorithm; making statistics on hotspot access regions in which the spatial data accessed by a user within a set time range are located; and obtaining the server nodes in which the hotspot access regions are located according to the mapping relationships, performing copy on data in one server node, storing the data into another server node, and bearing a load by an original server node and a later-stored server node in turn. The method has the beneficial effects that the spatial hotspot access regions perform redundancy on the corresponding server nodes according to dynamic feedback of a system, so that a server can achieve accurate load balance control based on spatial positions. When the geospatial data server is managed with the method, the data throughput of the whole system can be increased and the spatial data load balance can be closely combined with the spatial positions.
Description
Technical field
The present invention relates to a kind of elastic load equalization methods based on locus and system.
Background technology
Load balancing is exactly the server set be jointly made up of in the mode of data access symmetry multiple servers, wherein every station server all has the ability and assisting without the need to other servers that externally provide alone service, by certain load-balancing algorithm or technology, in certain station server being assigned in symmetrical structure of the request equilibrium that outside can be sent.Load balancing can average customer request to server array, solve a large amount of Concurrency Access server problem by distributed server response message, reach the object improving server acknowledge efficiency.
Elastic load equilibrium can realize the Appropriate application of resource automatically, generally be applied to two aspects, by load balancing, a large amount of Concurrency Access or data traffic are on average shared multiple network server node equipment on the one hand, thus reduce server response time, certain more heavy duty computing can be shared dynamically the lower multiple stage node device of present load on the other hand, finally gather the result of each node compute, thus strengthening system bulk treatment ability.Current load-balancing technique includes static load balancing and dynamic load leveling, static load balancing is just according to the distribution of certain dispatching method determination task before task access services device, therefore this method does not rely on any load condition in server system, dynamic load leveling is then carry out periodic load monitoring to each server node, and distributes task according to dynamic load dispatching algorithm according to the load information of feedback.Common static load balancing algorithm has robin scheduling etc., and common dynamic load algorithm has Smallest connection number balanced.
Spatial data accessing often has the aggregation on position, for hot spot region, certain visit capacity often much larger than the visit capacity in other regions, so cause the congenital unbalanced of when analysis space data server load, time by existing various elastic load equilibrium for the treatment of spatial data, owing to not considering the influence factor of locus, be only by management on data scatter to different node to reach the object of each node visit pressure reduction, this way inherits the thinking of conventional load equilibrium, although effective, but during access for data on spacial hot spots position, the feature of geographical spatial data can not be given full play to, still have greatly improved on accuracy and efficiency when processing spatial data load balancing space.
Summary of the invention
For the weak point existed in the problems referred to above, the invention provides a kind of elastic load equalization methods based on locus and system.
For achieving the above object, the invention provides a kind of elastic load equalization methods based on locus, the method comprises the following steps:
Step 101: by space hash algorithm, builds the mapping relations between spatial data and server node;
Step 102: the focus access region at the spatial data place of user's access within the scope of statistics setting-up time;
Step 103: the server node obtaining described focus access region place according to mapping relations, copies the data on server node and is stored in another server node, turns carry load by the server node wheel of former server node and rear storage.
Improve further as the present invention, described step 101 comprises:
According to warp and parallel, graticule mesh is divided into spatial data scope;
Set up hash function MD5, be mapped on the node of server, build described mapping relations by each graticule mesh obtained, wherein the coordinate of its lower-left angle point and upper right angle point is taked in the expression of graticule mesh locus;
Again by described mapping relations to by the GML data storage in different mesh regions on corresponding server node.
Improve further as the present invention, described step 102 comprises:
The request of access amount of statistics each graticule mesh GML data storage server node within the scope of setting-up time;
Determine the spatial data that request of access amount is more;
The more hot spot region of request access data is obtained based on the spatial data that request of access amount is more.
Improve further as the present invention, described step 103 comprises:
Described mapping relations obtain the server A at place, hot spot region;
Obtain the spatial data that in server A, hot spot region is corresponding again, this spatial data of part is copied on redundant server A1; Described redundant server A1 is the server for backing up, or the server that in system, load is little;
In spatial data copy, part server node provides the request of spatial data;
After spatial data copy, server A and redundant server A1 take turns vicarious load elastic load.
Improve further as the present invention, described in described step 103, this spatial data of part copied on redundant server A1 and comprise:
Spatial data in server A is copied on redundant server A1;
Described hot spot region corresponding to described server A is the graticule mesh divided in step 1, divides equally formation two halves, obtain the coordinate of equal timesharing two intermediate points to this graticule mesh;
Delete all data of one of them little graticule mesh in two little graticule mesh in server A, delete all data of another graticule mesh in two little graticule mesh in server A 1 simultaneously;
Delete the mapping value of the graticule mesh set up according to hash algorithm again, again according to lower left corner point coordinate and the upper right corner point coordinate generation mapping value of two little graticule mesh, newly-generated graticule mesh is stored in server A or A1 by the situation according to deleting little graticule mesh;
When user accesses described spatial data again, in server A or A1, wheel robin is utilized to carry out load balancing.
The invention provides a kind of device of the elastic load equalization methods based on locus, this system comprises:
Build module, it, for by space hash algorithm, builds the mapping relations between spatial data and server node;
Statistical module, it is for adding up the focus access region at the spatial data place of user's access within the scope of setting-up time;
Load balancing module, it is for obtaining the server node at described focus access region place according to mapping relations, data on server node copied and is stored in another server node, turning carry load by the server node wheel of former server node and rear storage.
Improve further as the present invention, build module and comprise:
Division unit, it is for being divided into graticule mesh according to warp and parallel to spatial data scope;
Construction unit, each graticule mesh obtained is mapped on the node of server for setting up hash function MD5, builds described mapping relations by it, and wherein the coordinate of its lower-left angle point and upper right angle point is taked in the expression of graticule mesh locus;
Storage unit, its for by described mapping relations to by the GML data storage in different mesh regions to corresponding server node.
Improve further as the present invention, described load balancing module comprises:
Acquiring unit, it is for obtaining the server A at place, hot spot region according to mapping relations;
Copy cell, it is for obtaining spatial data corresponding to hot spot region in server A, copies on redundant server A1 by this spatial data of part; Described redundant server A1 is the server for backing up, or the server that in system, load is little;
Load Balance Unit, it is in spatial data copy, and part server node provides the request of spatial data; After spatial data copy, server A and redundant server A1 take turns vicarious load elastic load.
Improve further as the present invention, described Load Balance Unit comprises:
Copy subelement, it is for copying the spatial data in server A to redundant server A1;
Obtain subelement, it is the graticule mesh divided in step 1 for the described hot spot region corresponding according to described server A, divides equally formation two halves, obtain the coordinate of equal timesharing two intermediate points to this graticule mesh;
Delete subelement, it is for deleting all data of one of them little graticule mesh in two little graticule mesh in server A, deletes all data of another graticule mesh in two little graticule mesh in server A 1 simultaneously;
Generate subelement, it is for deleting the mapping value of the graticule mesh set up according to hash algorithm again, again according to lower left corner point coordinate and the upper right corner point coordinate generation mapping value of two little graticule mesh, newly-generated graticule mesh is stored in server A or A1 by the situation according to deleting little graticule mesh;
Load balancing subelement, when it accesses described spatial data again for user, utilizes wheel robin to carry out load balancing in server A or A1.
The invention provides a kind of system of the elastic load equalization methods based on locus, comprising: client layer, lexical analysis layer, data server layer;
Described client layer, for sending and receive the services request of spatial data;
Described lexical analysis layer, for setting up the mapping relations between locus and server, adds up hot spot region also realizes server system load balancing according to dispatching algorithm simultaneously; The focus access region at the spatial data place of user's access within certain a period of time of statistics.
Described data server layer, for outwards providing spatial data; Obtained the server at focus access region place again by hash function, the data on server copied and is stored in another server, reaching load balancing.
Beneficial effect of the present invention is: by hash algorithm, spatial data is distributed to different server nodes according to its locus, thus reaches the load balancing effect relevant to locus.According to system dynamic feedback space focus access region, redundancy is being carried out to the server node of its correspondence, making server can reach accurate load balancing based on locus and control.When adopting the present invention to manage geographical spatial data services device, the data throughput of whole system can be improved, spatial data load balancing and locus can be combined closely.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of elastic load equalization methods based on locus of the present invention.
Fig. 2 is that load-balancing algorithm realizes schematic diagram.
Embodiment
Embodiment 1, as depicted in figs. 1 and 2, a kind of elastic load equalization methods based on locus of the present invention, the method comprises the following steps: by space hash algorithm, builds the mapping relations between spatial data and server node; According to warp and parallel, graticule mesh is divided into spatial data scope; Set up hash function MD5, be mapped on the node of server, build described mapping relations by each graticule mesh obtained, wherein the coordinate of its lower-left angle point and upper right angle point is taked in the expression of graticule mesh locus; Again by described mapping relations to by the GML data storage in different mesh regions on corresponding server node.
The focus access region at the spatial data place of user's access within the scope of statistics setting-up time; The request of access amount of statistics each graticule mesh GML data storage server node within the scope of setting-up time; Determine the spatial data that request of access amount is more; The more hot spot region of request access data is obtained based on the spatial data that request of access amount is more.
Obtain the server node at described focus access region place according to mapping relations, the data on server node are copied and is stored in another server node, turn carry load by the server node wheel of former server node and rear storage; Described mapping relations obtain the server A at place, hot spot region; Obtain the spatial data that in server A, hot spot region is corresponding again, this spatial data of part is copied on redundant server A1; Described redundant server A1 is the server for backing up, or the server that in system, load is little; In spatial data copy, part server node provides the request of spatial data; After spatial data copy, server A and redundant server A1 take turns vicarious load elastic load.Described being copied on redundant server A1 by this spatial data of part comprises: copied to by the spatial data in server A on redundant server A1; Described hot spot region corresponding to described server A is the graticule mesh divided in step 1, divides equally formation two halves, obtain the coordinate of equal timesharing two intermediate points to this graticule mesh; Delete all data of one of them little graticule mesh in two little graticule mesh in server A, delete all data of another graticule mesh in two little graticule mesh in server A 1 simultaneously; Delete the mapping value of the graticule mesh set up according to hash algorithm again, again according to lower left corner point coordinate and the upper right corner point coordinate generation mapping value of two little graticule mesh, newly-generated graticule mesh is stored in server A or A1 by the situation according to deleting little graticule mesh; When user accesses described spatial data again, in server A or A1, wheel robin is utilized to carry out load balancing.
Embodiment 2, a kind of device of the elastic load equalization methods based on locus, this system comprises: build module, and it, for by space hash algorithm, builds the mapping relations between spatial data and server node; Structure module comprises: division unit, and it is for being divided into graticule mesh according to warp and parallel to spatial data scope; Construction unit, each graticule mesh obtained is mapped on the node of server for setting up hash function MD5, builds described mapping relations by it, and wherein the coordinate of its lower-left angle point and upper right angle point is taked in the expression of graticule mesh locus; Storage unit, its for by described mapping relations to by the GML data storage in different mesh regions to corresponding server node.
Statistical module, it is for adding up the focus access region at the spatial data place of user's access within the scope of setting-up time;
Load balancing module, it is for obtaining the server node at described focus access region place according to mapping relations, data on server node copied and is stored in another server node, turning carry load by the server node wheel of former server node and rear storage.Described load balancing module comprises: acquiring unit, and it is for obtaining the server A at place, hot spot region according to mapping relations; Copy cell, it is for obtaining spatial data corresponding to hot spot region in server A, copies on redundant server A1 by this spatial data of part; Described redundant server A1 is the server for backing up, or the server that in system, load is little; Load Balance Unit, it is in spatial data copy, and part server node provides the request of spatial data; After spatial data copy, server A and redundant server A1 take turns vicarious load elastic load.Described Load Balance Unit comprises: copy subelement, and it is for copying the spatial data in server A to redundant server A1; Obtain subelement, it is the graticule mesh divided in step 1 for the described hot spot region corresponding according to described server A, divides equally formation two halves, obtain the coordinate of equal timesharing two intermediate points to this graticule mesh; Delete subelement, it is for deleting all data of one of them little graticule mesh in two little graticule mesh in server A, deletes all data of another graticule mesh in two little graticule mesh in server A 1 simultaneously; Generate subelement, it is for deleting the mapping value of the graticule mesh set up according to hash algorithm again, again according to lower left corner point coordinate and the upper right corner point coordinate generation mapping value of two little graticule mesh, newly-generated graticule mesh is stored in server A or A1 by the situation according to deleting little graticule mesh; Load balancing subelement, when it accesses described spatial data again for user, utilizes wheel robin to carry out load balancing in server A or A1.
Embodiment 3, a kind of system of the elastic load equalization methods based on locus, comprising: client layer, lexical analysis layer, data server layer; Described client layer, for sending and receive the services request of spatial data;
Described lexical analysis layer, for setting up the mapping relations between locus and server, adds up hot spot region also realizes server system load balancing according to dispatching algorithm simultaneously; The focus access region at the spatial data place of user's access within certain a period of time of statistics.Described data server layer, for outwards providing spatial data; Obtained the server at focus access region place again by hash function, the data on server copied and is stored in another server, reaching load balancing.
By hash algorithm, spatial data is distributed to different server nodes according to its locus, thus reaches the load balancing effect relevant to locus.According to system dynamic feedback space focus access region, redundancy is being carried out to the server node of its correspondence, making server can reach accurate load balancing based on locus and control.When adopting the present invention to manage geographical spatial data services device, the data throughput of whole system can be improved, spatial data load balancing and locus can be combined closely.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1., based on an elastic load equalization methods for locus, it is characterized in that, the method comprises the following steps:
Step 101: by space hash algorithm, builds the mapping relations between spatial data and server node;
Step 102: the focus access region at the spatial data place of user's access within the scope of statistics setting-up time;
Step 103: the server node obtaining described focus access region place according to mapping relations, copies the data on server node and is stored in another server node, turns carry load by the server node wheel of former server node and rear storage.
2. the elastic load equalization methods based on locus according to claim 1, it is characterized in that, described step 101 comprises:
According to warp and parallel, graticule mesh is divided into spatial data scope;
Set up hash function MD5, be mapped on the node of server, build described mapping relations by each graticule mesh obtained, wherein the coordinate of its lower-left angle point and upper right angle point is taked in the expression of graticule mesh locus;
Again by described mapping relations to by the GML data storage in different mesh regions on corresponding server node.
3. the elastic load equalization methods based on locus according to claim 2, it is characterized in that, described step 102 comprises:
The request of access amount of statistics each graticule mesh GML data storage server node within the scope of setting-up time;
Determine the spatial data that request of access amount is more;
The more hot spot region of request access data is obtained based on the spatial data that request of access amount is more.
4. the elastic load equalization methods based on locus according to claim 3, it is characterized in that, described step 103 comprises:
Described mapping relations obtain the server A at place, hot spot region;
Obtain the spatial data that in server A, hot spot region is corresponding again, this spatial data of part is copied on redundant server A1; Described redundant server A1 is the server for backing up, or the server that in system, load is little;
In spatial data copy, part server node provides the request of spatial data;
After spatial data copy, server A and redundant server A1 take turns vicarious load elastic load.
5. the elastic load equalization methods based on locus according to claim 4, is characterized in that, is copied on redundant server A1 by this spatial data of part and comprise described in described step 103:
Spatial data in server A is copied on redundant server A1;
Described hot spot region corresponding to described server A is the graticule mesh divided in step 1, divides equally formation two halves, obtain the coordinate of equal timesharing two intermediate points to this graticule mesh;
Delete all data of one of them little graticule mesh in two little graticule mesh in server A, delete all data of another graticule mesh in two little graticule mesh in server A 1 simultaneously;
Delete the mapping value of the graticule mesh set up according to hash algorithm again, again according to lower left corner point coordinate and the upper right corner point coordinate generation mapping value of two little graticule mesh, newly-generated graticule mesh is stored in server A or A1 by the situation according to deleting little graticule mesh;
When user accesses described spatial data again, in server A or A1, wheel robin is utilized to carry out load balancing.
6., as claimed in claim 1 based on a device for the elastic load equalization methods of locus, it is characterized in that, this system comprises:
Build module, it, for by space hash algorithm, builds the mapping relations between spatial data and server node;
Statistical module, it is for adding up the focus access region at the spatial data place of user's access within the scope of setting-up time;
Load balancing module, it is for obtaining the server node at described focus access region place according to mapping relations, data on server node copied and is stored in another server node, turning carry load by the server node wheel of former server node and rear storage.
7. the device of the elastic load equalization methods based on locus according to claim 6, is characterized in that, builds module and comprises:
Division unit, it is for being divided into graticule mesh according to warp and parallel to spatial data scope;
Construction unit, each graticule mesh obtained is mapped on the node of server for setting up hash function MD5, builds described mapping relations by it, and wherein the coordinate of its lower-left angle point and upper right angle point is taked in the expression of graticule mesh locus;
Storage unit, its for by described mapping relations to by the GML data storage in different mesh regions to corresponding server node.
8. the device of the elastic load equalization methods based on locus according to claim 6, it is characterized in that, described load balancing module comprises:
Acquiring unit, it is for obtaining the server A at place, hot spot region according to mapping relations;
Copy cell, it is for obtaining spatial data corresponding to hot spot region in server A, copies on redundant server A1 by this spatial data of part; Described redundant server A1 is the server for backing up, or the server that in system, load is little;
Load Balance Unit, it is in spatial data copy, and part server node provides the request of spatial data; After spatial data copy, server A and redundant server A1 take turns vicarious load elastic load.
9. the device of the elastic load equalization methods based on locus according to claim 8, is characterized in that: described Load Balance Unit comprises:
Copy subelement, it is for copying the spatial data in server A to redundant server A1;
Obtain subelement, it is the graticule mesh divided in step 1 for the described hot spot region corresponding according to described server A, divides equally formation two halves, obtain the coordinate of equal timesharing two intermediate points to this graticule mesh;
Delete subelement, it is for deleting all data of one of them little graticule mesh in two little graticule mesh in server A, deletes all data of another graticule mesh in two little graticule mesh in server A 1 simultaneously;
Generate subelement, it is for deleting the mapping value of the graticule mesh set up according to hash algorithm again, again according to lower left corner point coordinate and the upper right corner point coordinate generation mapping value of two little graticule mesh, newly-generated graticule mesh is stored in server A or A1 by the situation according to deleting little graticule mesh;
Load balancing subelement, when it accesses described spatial data again for user, utilizes wheel robin to carry out load balancing in server A or A1.
10. based on a system for the elastic load equalization methods of locus, it is characterized in that, comprising: client layer, lexical analysis layer, data server layer;
Described client layer, for sending and receive the services request of spatial data;
Described lexical analysis layer, for setting up the mapping relations between locus and server, adds up hot spot region also realizes server system load balancing according to dispatching algorithm simultaneously; The focus access region at the spatial data place of user's access within certain a period of time of statistics.
Described data server layer, for outwards providing spatial data; Obtained the server at focus access region place again by hash function, the data on server copied and is stored in another server, reaching load balancing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510680052.2A CN105354091A (en) | 2015-10-19 | 2015-10-19 | Spatial position based elastic load balance method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510680052.2A CN105354091A (en) | 2015-10-19 | 2015-10-19 | Spatial position based elastic load balance method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105354091A true CN105354091A (en) | 2016-02-24 |
Family
ID=55330065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510680052.2A Pending CN105354091A (en) | 2015-10-19 | 2015-10-19 | Spatial position based elastic load balance method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105354091A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107644086A (en) * | 2017-09-25 | 2018-01-30 | 咪咕文化科技有限公司 | The location mode of spatial data |
| CN107786586A (en) * | 2016-08-24 | 2018-03-09 | 腾讯科技（深圳）有限公司 | The load dispatching method and device of business |
| CN111078142A (en) * | 2019-11-26 | 2020-04-28 | 北京中电华大电子设计有限责任公司 | Load balancing method for prolonging service life of hot spot area |
| CN111857979A (en) * | 2020-06-28 | 2020-10-30 | 厦门极致互动网络技术股份有限公司 | Information management method, system, storage medium and equipment of distributed system |
| CN116737392A (en) * | 2023-08-11 | 2023-09-12 | 北京智网易联科技有限公司 | Non-vector data processing method and device and computing equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101370025A (en) * | 2007-08-17 | 2009-02-18 | 北京灵图软件技术有限公司 | Storing method, scheduling method and management system for geographic information data |
| CN101504663A (en) * | 2009-03-17 | 2009-08-12 | 北京大学 | Swarm intelligence based spatial data copy self-adapting distribution method |
| CN101557344A (en) * | 2009-05-21 | 2009-10-14 | 南昌航空大学 | Dynamic load balancing method based on spatial geographical locations |
| CN101719148A (en) * | 2009-11-24 | 2010-06-02 | 北京灵图软件技术有限公司 | Three-dimensional spatial information saving method, device, system and dispatching system |
| CN103327072A (en) * | 2013-05-22 | 2013-09-25 | 中国科学院微电子研究所 | Method for cluster load balance and system thereof |
| CN103942253A (en) * | 2014-03-18 | 2014-07-23 | 深圳市房地产评估发展中心 | Space data processing method and system of load balancing |
-
2015
- 2015-10-19 CN CN201510680052.2A patent/CN105354091A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101370025A (en) * | 2007-08-17 | 2009-02-18 | 北京灵图软件技术有限公司 | Storing method, scheduling method and management system for geographic information data |
| CN101504663A (en) * | 2009-03-17 | 2009-08-12 | 北京大学 | Swarm intelligence based spatial data copy self-adapting distribution method |
| CN101557344A (en) * | 2009-05-21 | 2009-10-14 | 南昌航空大学 | Dynamic load balancing method based on spatial geographical locations |
| CN101719148A (en) * | 2009-11-24 | 2010-06-02 | 北京灵图软件技术有限公司 | Three-dimensional spatial information saving method, device, system and dispatching system |
| CN103327072A (en) * | 2013-05-22 | 2013-09-25 | 中国科学院微电子研究所 | Method for cluster load balance and system thereof |
| CN103942253A (en) * | 2014-03-18 | 2014-07-23 | 深圳市房地产评估发展中心 | Space data processing method and system of load balancing |
Non-Patent Citations (2)
| Title |
|---|
| 覃灵军: "基于对象存储系统的动态负载均衡算法", 《计算机科学》 * |
| 黄伟: "视频数据的存储调度优化策略", 《电脑与信息技术》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107786586A (en) * | 2016-08-24 | 2018-03-09 | 腾讯科技（深圳）有限公司 | The load dispatching method and device of business |
| CN107786586B (en) * | 2016-08-24 | 2019-11-05 | 腾讯科技（深圳）有限公司 | The load dispatching method and device of business |
| CN107644086A (en) * | 2017-09-25 | 2018-01-30 | 咪咕文化科技有限公司 | The location mode of spatial data |
| CN107644086B (en) * | 2017-09-25 | 2019-05-10 | 咪咕文化科技有限公司 | The location mode of spatial data |
| CN111078142A (en) * | 2019-11-26 | 2020-04-28 | 北京中电华大电子设计有限责任公司 | Load balancing method for prolonging service life of hot spot area |
| CN111857979A (en) * | 2020-06-28 | 2020-10-30 | 厦门极致互动网络技术股份有限公司 | Information management method, system, storage medium and equipment of distributed system |
| CN111857979B (en) * | 2020-06-28 | 2023-08-15 | 厦门极致互动网络技术股份有限公司 | Information management method, system, storage medium and equipment of distributed system |
| CN116737392A (en) * | 2023-08-11 | 2023-09-12 | 北京智网易联科技有限公司 | Non-vector data processing method and device and computing equipment |
| CN116737392B (en) * | 2023-08-11 | 2023-11-10 | 北京智网易联科技有限公司 | Non-vector data processing method and device and computing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105354091A (en) | Spatial position based elastic load balance method and system | |
| US10623481B2 (en) | Balancing resources in distributed computing environments | |
| US9871855B2 (en) | Balancing load across cache servers in a distributed data store | |
| US20190319881A1 (en) | Traffic management based on past traffic arrival patterns | |
| US11068461B1 (en) | Monitoring key access patterns for nonrelational databases | |
| CN107450855B (en) | Model-variable data distribution method and system for distributed storage | |
| US10963353B2 (en) | Systems and methods for cross-regional back up of distributed databases on a cloud service | |
| CN107105013B (en) | File processing method, server, terminal and system | |
| US10742566B2 (en) | Low-redistribution load balancing | |
| CN110569302A (en) | method and device for physical isolation of distributed cluster based on lucene | |
| CN112346871A (en) | Request processing method and micro-service system | |
| US20150019732A1 (en) | Producer system partitioning among leasing agent systems | |
| KR20160097372A (en) | Efficient resource utilization in data centers | |
| CN104901999A (en) | Method for reliability perceptive cross-domain mapping of virtual data center | |
| CN113312339B (en) | Data migration method and device, computer equipment and storage medium | |
| CN112422611B (en) | Virtual bucket storage processing method and system based on distributed object storage | |
| Nivetha et al. | Modeling fuzzy based replication strategy to improve data availabiity in cloud datacenter | |
| US11442632B2 (en) | Rebalancing of user accounts among partitions of a storage service | |
| US11507313B2 (en) | Datafall: a policy-driven algorithm for decentralized placement and reorganization of replicated data | |
| Huang et al. | Optimizing data partition for scaling out NoSQL cluster | |
| CN108228079B (en) | Storage management method and device | |
| Tziritas et al. | A communication-aware energy-efficient graph-coloring algorithm for VM placement in clouds | |
| US10481963B1 (en) | Load-balancing for achieving transaction fault tolerance | |
| US9842148B2 (en) | Method for failure-resilient data placement in a distributed query processing system | |
| Zhang et al. | Speeding up vm startup by cooperative vm image caching |
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: 20160224 |
|
| RJ01 | Rejection of invention patent application after publication |