Method for dynamic spatial computational domain-oriented map data balance storage in cluster environment
A technology of map data and spatial computing, applied in the direction of input/output to record carrier, etc., can solve the problem of underutilization of parallel computing resources, waste of storage resources, inability to parallelly schedule service nodes to respond to the same client map data access request, etc. problems, to achieve the effect of improving resource utilization and concurrent responsiveness, and achieving load
Inactive Publication Date: 2016-01-20
地大(武汉)资产经营有限公司
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At present, there are two main types of map data storage in the cluster environment. The first type is completely redundant storage, that is, each node in the cluster stores a complete copy of the data. This method is the easiest to implement, but due to Completely redundant storage greatly wastes limited storage resources and cannot adapt to massive map data
The second type is divided storage, which divides massive map data according to themes, scales, spatial ranges or administrative regions, and stores them in each service node in the cluster environment. Since the spatial location of the map data accessed by the client is dynamic, if using In this kind of divided storage method, most of the map data access requests from the client can only be allocated to a certain service node, and all service nodes in the cluster cannot be scheduled in parallel to respond to the same client map data access request. The multi-node parallel computing of the cluster resources are underutilized
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0035] In order to illustrate the thought of the present invention more clearly, below in conjunction with appendix figure 2 Taking the third-level tile map data organized in the form of a quadtree as an example for further description, in this embodiment, the network map service cluster uses 4 service nodes, and the third-level tile map data in the cluster environment The specific steps of balancing storage are as follows:
[0036] Step 200), setting the number of service nodes n=4 in the network map service cluster;
[0037] Step 201), calculate the map subspace size s according to the number n of nodes in the cluster, each map subspace is a regular square, where Level 3 tile data contains a total of 2 3 Row*2 3 Column tile image, which can be divided into (2 3 / s) (2 3 / s)=16 map subspaces;
[0038] Step 202), calculate the position of the map data block in the map subspace, set the row number of the map data block as R, the column number as C, the row number of the...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for dynamic spatial computational domain-oriented map data balance storage in a cluster environment. The method comprises the following steps: setting the number of nodes in a map server cluster; calculating the size of a map sub-space; calculating the position of map data in the sub-space; calculating a target storage node index of the map data in the cluster; storing the map data to a target node; and circularly performing the steps for balance storage of all map data into all nodes of the map server cluster. According to the method, the map data in all map sub-spaces are evenly distributed to all service nodes in the cluster, so that map data access requests of any dynamic spatial computational domain are evenly distributed to all nodes in the cluster, loads of network map service nodes in the cluster environment are balanced, and the dynamic spatial computational domain-oriented massive map data balance storage in the cluster environment is realized.
Description
technical field [0001] The invention relates to the field of high-performance geographic computing, in particular to a method for balanced storage of map data oriented to a dynamic spatial computing domain under a cluster environment. Background technique [0002] The balanced storage of massive map data in the cluster environment is one of the problems that need to be solved in WebGIS, especially in the scene of dynamic changes in the spatial computing domain, how to balance the map data access requests of each dynamic spatial computing domain to each structure in the cluster The point is the key to realize the load balancing of the network map service. At present, there are two main types of map data storage in the cluster environment. The first type is completely redundant storage, that is, each node in the cluster stores a complete copy of the data. This method is the easiest to implement, but due to Completely redundant storage greatly wastes limited storage resources ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F3/06
Inventor 郭明强黄颖罗显刚吴亮谢忠
Owner 地大(武汉)资产经营有限公司