Abnormal instance detection method and device for distributed system, equipment and medium

A distributed system and abnormal technology, applied in the computer field, can solve problems such as difficulty in achieving the accuracy of abnormal instances, and achieve the effect of improving pertinence and repairing efficiency, solving the problem of low determination efficiency, efficient and accurate positioning

Active Publication Date: 2020-01-03
BAIDU COM TIMES TECH (BEIJING) CO LTD
View PDF12 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method can be fast, the abnormal instances found may not deteriorate the overall processing time of the request, so it will not affect the degradation of system capacity. Therefore, it is difficult to determine the abnormal instances by this method the accuracy of

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
  • Abnormal instance detection method and device for distributed system, equipment and medium
  • Abnormal instance detection method and device for distributed system, equipment and medium
  • Abnormal instance detection method and device for distributed system, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Figure 1a It is a flow chart of the abnormal instance detection method for distributed systems provided by Embodiment 1 of the present invention. This embodiment is applicable to abnormal instances in distributed systems (or distributed clusters), and requests the system as a whole according to the abnormal instances. In the case of screening due to the impact of processing time, the method can be implemented by an abnormal instance detection device for distributed systems, which can be implemented in software and / or hardware, and can be integrated in any device with computing power , including but not limited to servers, etc. The distributed system in the embodiment of the present invention includes multiple services (that is, multiple business modules), each service includes at least one instance, and different instances can process different data fragments.

[0031] like Figure 1a As shown, the abnormal instance detection method for distributed systems provided in ...

Embodiment 2

[0051] figure 2 It is a flow chart of the abnormal instance detection method for distributed systems provided by Embodiment 2 of the present invention. This embodiment further optimizes and expands on the basis of the above embodiments. Such as figure 2 As shown, the method includes:

[0052] S210. Collect timing index data of each instance, and call chain data of calls made by each request to each instance.

[0053] Among them, the call chain data includes a call chain representing the call relationship between the request and the instance and the instance and the instance. Each call chain includes at least the start timestamp and the end timestamp of the call chain. The complete call chain of each request constitutes a call graph. .

[0054] S220. According to the timing index data, determine a set of candidate abnormal instances at the time of system abnormality.

[0055] S230. Taking any candidate exception instance as the current candidate exception instance, and ac...

Embodiment 3

[0070] Figure 3a It is a flow chart of the abnormal instance detection method for distributed systems provided by Embodiment 3 of the present invention. This embodiment further optimizes and expands on the basis of the foregoing embodiments. Such as Figure 3a As shown, the method includes:

[0071] S310. Collect timing index data of each instance, and call chain data of calls made by each request to each instance.

[0072] Among them, the call chain data includes a call chain representing the call relationship between the request and the instance and the instance and the instance. Each call chain includes at least the start timestamp and the end timestamp of the call chain. The complete call chain of each request constitutes a call graph. .

[0073] S320. According to the timing index data, determine a set of candidate abnormal instances at the time of system abnormality.

[0074] S330. Using any candidate exception instance as the current candidate exception instance, d...

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 embodiment of the invention discloses an abnormal instance detection method and device for a distributed system, equipment and a medium, the distributed system comprises a plurality of services, each service comprises at least one instance, and the method comprises the following steps: collecting time sequence index data of each instance and call chain data for requesting to call each instance; determining a candidate abnormal instance set of a system abnormal moment according to the time sequence index data; and according to the call chain data, screening out at least one key abnormal instance from the candidate abnormal instance set, the key abnormal instance being an abnormal instance whose call has a positive contribution to the overall processing time of the request set. Accordingto the embodiment of the invention, the key exception instance in the distributed system can be efficiently and accurately positioned.

Description

technical field [0001] Embodiments of the present invention relate to the field of computer technology, and in particular to a method, device, device and medium for detecting abnormal instances in a distributed system. Background technique [0002] Large-scale distributed systems contain a large number of nodes, and requests often go through a multi-level large-scale "fan-out" process, that is, one request will be diverged into multiple requests to request downstream services in parallel, and the service call chain experienced by the request is very complicated . [0003] In large-scale distributed systems, especially in mixed deployment scenarios, service instance exceptions are normal. In order to avoid system capacity degradation caused by service instance exceptions, existing technologies usually use the following two methods to detect instance exceptions: [0004] 1) Manual method. The manual method requires technicians to obtain all performance indicators of each ins...

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): G06F11/34
CPCG06F11/3452
Inventor 甄真侯进超陈佳捷齐志宏
Owner BAIDU COM TIMES TECH (BEIJING) 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