Memory partition deployment method and device

A technology for memory partitioning and deploying devices, which is applied in the field of data processing and can solve the problems of high system delay and overhead and inability to meet practical applications.

Active Publication Date: 2015-04-15
HUAWEI CLOUD COMPUTING TECH CO LTD
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, in the application scenario with many write operations, since the distributed system does not have a reasonable deployment of memory partitions, the memory partitions of the system can only be randomly deployed, so the distributed system still needs to perform a large number of cross-network write operations. The delay overhead is large and cannot meet the requirements of practical applications

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Memory partition deployment method and device
  • Memory partition deployment method and device
  • Memory partition deployment method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] An embodiment of the present invention provides a method for deploying memory partitions, which is used for rationally deploying memory partitions of a distributed system and reducing the delay overhead of the distributed system. The embodiment of the present invention also provides a related device for deploying memory partitions, which will be described separately below.

[0051] For the basic flow of the memory partition deployment method provided by the embodiment of the present invention, please refer to figure 1 ,mainly include:

[0052] 101. Determine the hotspot partition in the distributed system within the preset time period;

[0053] A distributed system includes multiple nodes, and memory partitions are deployed on the nodes. Among them, the hotspot partition is the memory partition with the highest number of visits in the distributed system;

[0054] Wherein, the preset time period may be an artificially set time period, or may be a default time period of ...

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

No PUM Login to view more

Abstract

The invention discloses a memory partition deployment method. The memory partition deployment method is used for rationally deploying the memory partition of a distributed system, and reducing the time delay overhead of the distributed system. The memory partition deployment method comprises the steps: determining the hot spot partition in the distributed system within the preset time slot, wherein the distributed system comprises multiple nodes, the memory partition is deployed on the nodes, and the hot spot partition is the memory partition in the distributed system of which the frequency of the visits is arranged in the front rank; determining the frequency of the hot spot partition which is visited by each node; according to the frequency of the hot spot partition which is visited by each node, determining the optimal deployment node of the hot spot partition; informing the optimal deployment node of the hot spot partition to the node currently located by the hot spot partition. The invention further provides a relevant memory partition deployment device.

Description

technical field [0001] The present invention relates to the field of data processing, in particular to a memory partition deployment method and device. Background technique [0002] Distributed memory data grid (IMDG, In-memory Data Grid) is a new type of grid system for memory resource sharing on wide area network. Its main goal is to improve the system performance of memory-intensive applications or IO-intensive applications when physical memory is insufficient. [0003] The distributed memory grid technology uses a consistent hash algorithm to divide the data into blocks and distribute them as much as possible to the memory partitions of all nodes in the distributed system to ensure data balance, but this makes the memory partitions of the distributed system Deployment is relatively random, resulting in distributed systems often requiring cross-network data access. For example, when the processes App1 and App2 on node A access the memory partition Data1 of node B, they ...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30
CPCG06F16/2471
Inventor 张森彭信民
Owner HUAWEI CLOUD COMPUTING TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap