Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method of setting independent weight factors and speed factors for data copies

A data copy and weight factor technology, applied in the input/output process of data processing, electrical digital data processing, instruments, etc., can solve the problems of read and write delay, poor read and write performance, performance bottleneck, etc., to reduce delay, improve The effect of writing efficiency

Active Publication Date: 2016-11-09
北京银信长远科技股份有限公司
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above read and write operations do not consider performance overhead. Assuming that one of the nodes is a machine with low configuration and poor read and write performance, there will be a performance bottleneck, resulting in read and write delays.
In a large server group, the performance and configuration of the servers are quite different, so according to the existing technology, the performance of the entire system is dragged down by the slow updating servers

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
  • Method of setting independent weight factors and speed factors for data copies

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] see figure 1 , to realize the embodiment of the method of setting independent weight factors and speed factors for data copy of the present invention as follows:

[0024] Assuming that there is 100M of data to be stored, it is stored on 10 storage nodes according to 3 copies, and is stored according to a unit of 10M. The traditional data distribution table is as follows:

[0025] data

[0026] X indicates the distribution of data copies on the nodes, and each storage node has 3 data copies. The present invention designs a weight factor on the basis of traditional data distribution. The setting principle is that only one copy has a high weight. In this example, the high weight factor is 3-1=2, and the other copies have equal low weights, all of which are 1. . In this way, the above data distribution table changes to:

[0027] data

[0028] X means there is a data distribution, 2 means the weight factor is 2, and 1 means the weight factor is 1.

...

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 provides a method of setting independent weight factors and speed factors for data copies and relates to the technical field of computer. The method mainly includes: adding a weight for each data copy; reading and writing the data copies sequentially according to weight size during data reading and writing, wherein the higher the weights are, the higher the priority of reading and writing is. Return conditions of data writing success can be set, preset uniformity principles can be met according to the weights of the data copies, so that writing efficiency of a system is improved and delay is reduced; different speed factors are set according to respective performance of storage nodes, and the nodes with good performance are read and written preferentially.

Description

technical field [0001] The invention relates to the field of computer technology, especially the field of computer data storage. Background technique [0002] In software-defined storage, distributed computing, and big data applications, data copies are used to store data. A data copy means that a piece of data generally has 2 or 3 copies, which are stored in different storage nodes to ensure data consistency and integrity. [0003] The following takes three data copies as an example to describe in detail. Suppose there are 100M data to be stored, and there are 3 copies, then the same 100M data are stored on 3 storage nodes respectively. In this way, even if one or two storage nodes fail, the data is still intact and no data loss will occur. How the 100M data is stored in the storage node is defined through the metadata table. [0004] Metadata tables are not actual data, but descriptions of where the actual data is stored. Assuming that 100M is stored in units of 4M, t...

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
IPC IPC(8): G06F3/06
CPCG06F3/0611G06F3/0638G06F3/067
Inventor 关宁风
Owner 北京银信长远科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com