Client-based distributed storage load balancing method and device

A distributed storage and load balancing technology, applied in multi-program devices, resource allocation, program control design, etc., can solve problems such as high delay and unbalanced performance, achieve simple structure, reduce access delay, and QoS quality. Guaranteed effect

Inactive Publication Date: 2020-07-31
INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In terms of intelligent data analysis, in the face of a large number of clients accessing distributed storage, the high concurrency and low latency requirements required by it can no longer be met by the current storage-side load balancing based on distributed storage, mainly due to high latency. , the problem of unbalanced performance

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
  • Client-based distributed storage load balancing method and device
  • Client-based distributed storage load balancing method and device
  • Client-based distributed storage load balancing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Such as figure 1 As shown, the present invention provides a client-based distributed storage load balancing method, comprising the following steps:

[0058] S1. Deploy service scripts on each distributed storage node, and deploy proxy scripts on each client node;

[0059] S2. Configure each distributed storage node to automatically count the resource load information of the node; the resource load information includes system resource utilization, the number of client node connections, data service queue depth, and data service average delay; system resource utilization Rate includes CPU, memory, network and hard disk IO usage;

[0060] S3. Configure the service script of distributed storage nodes to globally synchronize the resource load information of each distributed storage node, generate a list of global node resource loads, and set the resource load information for each distributed storage node according to the distributed storage node resource load information s...

Embodiment 2

[0064] Such as figure 2 As shown, the present invention provides a client-based distributed storage load balancing method, comprising the following steps:

[0065] S1. Deploy service scripts on each distributed storage node, and deploy proxy scripts on each client node;

[0066] S2. Configure each distributed storage node to automatically count the resource load information of the node; the resource load information includes system resource utilization and the number of client node connections;

[0067] S3. Configure the service script of distributed storage nodes to globally synchronize the resource load information of each distributed storage node, generate a list of global node resource loads, and set the resource load information for each distributed storage node according to the distributed storage node resource load information Service weight value; the specific steps are as follows:

[0068] S31. Configuring the service script of the distributed storage nodes to inte...

Embodiment 3

[0084] Such as image 3 As shown, the present invention provides a client-based distributed storage load balancing device, including:

[0085] Script deployment module 1, for deploying service scripts on each distributed storage node, and deploying agent scripts on each client node;

[0086] The resource load information statistics module 2 is used to configure each distributed storage node to automatically count the resource load information of the node; the resource load information includes system resource utilization and the number of client node connections;

[0087] The global resource load list generation module 3 is used to configure the service script of the distributed storage nodes to globally synchronize the resource load information of each distributed storage node, generate a global node resource load list, and based on the resource load information of each distributed storage node Set the service weight value for each distributed storage node; the global resour...

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 client-based distributed storage load balancing method and device, and the method comprises the following steps: deploying a service script at each distributed storage node, and deploying an agent script at each client node; configuring each distributed storage node to automatically count resource load information of the node; configuring a service script of each distributed storage node to globally synchronize the resource load information of each distributed storage node to generate a global node resource load list, and setting a service weight value for each distributed storage node according to the resource load information of each distributed storage node; configuring a service script of the distributed storage node to synchronize the global node resource loadlist and the service weight value of each distributed storage node to an agent script of each client node; and configuring the proxy script of the client node, and automatically selecting the distributed storage node of the service to perform load balancing according to the global node resource load table and the service weight value of each distributed storage node.

Description

technical field [0001] The invention belongs to the technical field of load balancing, and in particular relates to a client-based distributed storage load balancing method and device. Background technique [0002] OpenCL is the abbreviation of Open Computing Language, an open computing language. [0003] FPGA is the abbreviation of Field-Programmable Gate Array, Field Programmable Gate Array. [0004] AOCL is the abbreviation of Altera SDK for OpenCL. [0005] OpenCL, short for Open Computing Language, is an open computing language. [0006] In the era of the Internet of Things, big data, and 5G data explosion, the scale of data is getting bigger and bigger. Based on this large-scale data volume, using AI intelligence to further mine its data value has been put into practice by leaders in various fields. in actual engineering technology. In terms of intelligent data analysis, in the face of a large number of clients accessing distributed storage, the high concurrency an...

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): G06F9/50
CPCG06F9/5083
Inventor 王勇
Owner INSPUR SUZHOU INTELLIGENT 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