Task monitoring method and device in cloud analysis system

A cloud analysis and task technology, applied in multi-programming devices, resource allocation, hardware monitoring, etc., can solve problems such as difficulties, abnormal time-consuming task operation analysis, failure to clearly locate faults, etc., and achieve the effect of improving efficiency

Active Publication Date: 2020-05-15
HANGZHOU HIKVISION DIGITAL TECH
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] (1) When the time-consuming task operation analysis is abnormal and the fault cannot be clearly located, professionals are required to repeatedly test and troubleshoot to locate the fault;
[0007] (2) When it is necessary to analyze and optimize the time-consuming task analysis of the entire system, it is often difficult

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
  • Task monitoring method and device in cloud analysis system
  • Task monitoring method and device in cloud analysis system
  • Task monitoring method and device in cloud analysis system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] see image 3 , image 3 It is a schematic flowchart of monitoring the time-consuming task processing of each node in Embodiment 1 of the present application.

[0075] Step 301, when the user sends a task analysis request to the scheduling node in the cloud analysis system through the virtual IP address, add label information to the current task in the request, and initialize the additional label information.

[0076] The tag information is implemented by extending the fields of the task. The tag information is expanded in the form of a json array, which can be dynamically added or deleted. The tag information includes at least the node name and the actual time-consuming value. In order to further facilitate the data analysis in the background, the tag information It can also include a time-consuming threshold, an alarm flag, and a reserved field. The time-consuming threshold is the test experience value, which is used to monitor whether the time-consuming situation of ...

Embodiment 2

[0093] join Figure 4 as shown, Figure 4 It is a schematic flow chart for monitoring the time-consuming tasks of modules in each node for this application.

[0094] Step 401, when the user sends a task request analysis to the scheduling node in the cloud analysis system through the virtual IP address, add tag information to the current task, and initialize the added tag information.

[0095] The tag information is implemented by extending the fields of the task. The tag information is expanded in the form of a json array, which can be dynamically added or deleted. The tag information includes at least the module name and the actual time-consuming value. In order to further facilitate data analysis in the background, the tag information It can also include node names, time-consuming thresholds, alarm flags, and reserved fields. Among them, the time-consuming threshold is the test experience value, which is used to monitor whether the time-consuming situation of the task in th...

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 task monitoring method in a cloud analysis system. The method comprises the steps: adding label information to a task from a user task request, and the label information at least comprises the name of a processing main body of the task and the actual consumed time; recording the timestamp of the task entering the current processing main body and the timestamp of the taskleaving the current processing main body; according to the entry timestamp and the exit timestamp, calculating the actual time consumption of the current processing main body, and recording the name of the current processing main body and the actual time consumption in the label information; and judging whether all processing of the task is finished or not, if not, entering the next processing main body, and returning to execute the step of recording the timestamp of the task entering the current processing main body and the timestamp of the task leaving the current processing main body untilall processing of the task is finished. According to the method, the time-consuming bottleneck point of the whole system can be found, and the abnormal processing main body in the task processing process can be quickly found, so that maintenance personnel can efficiently and pertinently perform troubleshooting of the cloud analysis system.

Description

technical field [0001] The embodiment of the present application relates to the field of cloud computing cluster analysis, and in particular to a task monitoring method and device in a cloud analysis system. Background technique [0002] In cloud computing technology, the cloud analysis system is responsible for receiving job tasks, such as picture tasks or video tasks, performing target analysis on job tasks to output target attributes of tasks, etc., and managing and scheduling the entire analysis resources. [0003] see figure 1 as shown, figure 1 It is a schematic diagram of the network topology of the cloud analysis system. The current cloud analysis system includes scheduling nodes and computing nodes. The scheduling node provides a virtual IP address for users to establish a network connection with the cloud analysis system. When a user submits a job task to the scheduling node, the scheduling node will, according to a certain scheduling algorithm, The task is sent...

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): G06F9/50G06F11/30G06F11/34
CPCG06F9/5038G06F11/3017G06F11/3051G06F11/3423Y02D10/00
Inventor 姚沛王志杰王鹏
Owner HANGZHOU HIKVISION DIGITAL TECH
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