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

A Fault Tolerance Method for Distributed Stream Processing System in Multiple Application Scenarios

A stream processing system and distributed technology, applied in the fault-tolerant field of distributed stream processing systems, can solve the problems of low utilization rate of standby nodes and long recovery time, so as to improve resource utilization and reliability, shorten recovery delay, reduce The effect of fault tolerance overhead

Active Publication Date: 2020-06-02
HUAZHONG UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the defects of the prior art, the purpose of the present invention is to solve the technical problems of the fault-tolerant method of the prior art distributed stream processing system in the case of multi-application scenarios and multi-stream applications, which takes a long time to recover and the utilization rate of backup nodes is low

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
  • A Fault Tolerance Method for Distributed Stream Processing System in Multiple Application Scenarios
  • A Fault Tolerance Method for Distributed Stream Processing System in Multiple Application Scenarios
  • A Fault Tolerance Method for Distributed Stream Processing System in Multiple Application Scenarios

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0048] In a distributed stream processing system, multiple different stream applications are often deployed and running at the same time. Due to the uniqueness of each stream application and the volatility of data flow, there will be workload differences between applications at the same time, resulting in There are significantly different load differences between different nodes at the same time and between different tasks on the same node. Aiming at the volatility of stream processing application data flow, the present invention proposes to use idle resources on idle nodes to do hot backup for tas...

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 fault-tolerant method of a distributed stream processing system in a multi-application scene, and belongs to the field of distributed stream processing. According to the invention, historical valid data analysis of all nodes and real-time load data monitoring are carried out; an active backup mechanism or a check point mechanism is effectively adopted according to different load states of the nodes, so that the problem of high fault recovery delay of the computing nodes in a flow processing system is effectively solved, the fault-tolerant overhead is reduced, the recovery delay is greatly shortened, and the reliability of the system is improved. Hot standby task selection and standby node selection are carried out through load sensing in a multi-application scene;the backup node is reasonably selected for running replica tasks of part of tasks, idle resources on the idle nodes are used for hot standby for the tasks on the busy nodes, and therefore the recovery time delay of the busy nodes when faults happen is remarkably shortened, and meanwhile the resource utilization rate and reliability of a fault-tolerant mechanism of the distributed flow processingsystem are improved.

Description

technical field [0001] The invention belongs to the field of distributed stream processing, and more specifically relates to a fault-tolerant method for a distributed stream processing system in multiple application scenarios. Background technique [0002] With the continuous expansion of distributed computing technology in various application fields, distributed stream processing systems are widely used in many fields, such as financial management, network monitoring, communication data management, WEB applications, sensor network data processing, etc. A distributed stream processing system refers to an Internet software system that uses a distributed system to process data stream services. Through distributed technology, stream data is no longer centrally placed on a single server (node) for processing, but all application logic is distributed on each sub-node in the network, and the sub-nodes are used for independent processing, and then the result Summarize to the downs...

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 Patents(China)
IPC IPC(8): H04L12/24H04L29/08
CPCH04L41/0663H04L41/0668H04L41/5051H04L67/1008H04L67/1012H04L67/1034
Inventor 陈汉华金海詹晶晶张凡
Owner HUAZHONG UNIV OF SCI & TECH
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