Node preheating method based on positive feedback

A positive feedback and node technology, applied in the field of node preheating, can solve the problems that nodes cannot cope with a large number of read operations, increase processing capacity, and fail to respond, so as to avoid node crashes, improve processing capabilities, and avoid suspended animation.

Active Publication Date: 2020-01-03
CHENGDU DBAPP SECURITY
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In a high-concurrency cluster, the node's cache warm-up is indispensable. Otherwise, when the cache is not working properly to reduce the read and write pressure of the storage, the node will fall into a state of suspended animation because the storage cannot cope with a large number of read operations, and can no longer receive and process. For new requests, the final node cannot continue to work, and other nodes in the cluster may also fall into an unresponsive state due to the increased amount of allocated processing

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
  • Node preheating method based on positive feedback
  • Node preheating method based on positive feedback
  • Node preheating method based on positive feedback

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] A node preheating method based on positive feedback in this embodiment includes the following steps:

[0038] Step 1. Collect the resource occupancy status of the node cache;

[0039] Step 2. Assign initial weights to nodes and distribute requests to nodes according to the initial weights;

[0040] Step 3. Collect changes in the resource occupancy state of the node, and calculate the new weight of the node according to the distribution request volume of the node and the change in resource occupancy state;

[0041] Step 4. Adjust the request distribution amount of the node according to the new weight of the node;

[0042] Step 5. Repeat steps 3 and 4 until the node is shut down.

[0043] The scheduling module is responsible for distributing the requests that need to be processed to the nodes. After receiving the requests from the outside, the scheduling module forwards the requests to each node according to the weight ratio of each node. The higher the weight of the no...

Embodiment 2

[0045] This embodiment is further optimized on the basis of embodiment 1, and said step 3 includes the following sub-steps:

[0046] Step 3.1, obtain the initial occupancy state S1 of the resource occupancy state of the node's cache;

[0047] Step 3.2. Calculate the distribution request amount A of the node according to the following formula:

[0048]

[0049] Step 3.3. Obtain the occupancy state S of the node's cache for resources after the node distributes the request 2 , and calculate the amount of change in resource occupancy state △S=S 2 -S 1 ;

[0050] Step 3.4: Obtain the new weight of the node by the ratio of the distribution request amount A to the resource occupation state change amount ΔS.

[0051] The scheduling module obtains the occupancy of resources by the cache module from the node S 1 , and the built-in state collection tool inside the node calls the internal tool of the operating system to collect the information list of the hardware CPU in the node,...

Embodiment 3

[0058] This embodiment is further optimized on the basis of the above-mentioned embodiment 1 or 2, and the sub-steps of assigning initial weights to nodes in the step 2 are as follows:

[0059] Step 2.1, setting the limit value of the node's request increment and load increment;

[0060] Step 2.2, determine the request increment and load increment of the node;

[0061] Step 2.3, if the request increment of the node is greater than the threshold value and the load increment is less than or equal to the threshold value, assign a high weight to the node;

[0062] If the request increment of the node is greater than the threshold value and the load increment is greater than the threshold value, assign a low weight to the node;

[0063] If the request increment of the node is less than or equal to the threshold value and the load increment is less than or equal to the threshold value, the node is assigned a medium weight;

[0064] If the node's request increment is less than or e...

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 node preheating method based on positive feedback. The node preheating method comprises the following steps: step 1, collecting a resource occupation state cached by a nodes;step 2, allocating an initial weight to the nodes and distributing a request to the nodes according to the initial weight; step 3, collecting the resource occupation state change condition of the nodes, and calculating the new weight of the nodes according to the distribution request quantity and the resource occupation state change quantity of the nodes; step 4, adjusting the request distribution quantity of the nodes according to the new weights of the nodes; step 5, repeating the step 3 and the step 4 until the nodes are closed. The method has the advantages that the nodes are effectivelypreheated, the requests are distributed to the nodes on the basis of positive feedback according to the node processing capacity, node collapse is effectively avoided, and the processing capacity of awhole cluster for a large number of concurrent requests is improved.

Description

technical field [0001] The invention belongs to the technical field of node preheating, and in particular relates to a node preheating method based on positive feedback. Background technique [0002] In the context of the information age, more and more information is stored and disseminated in electronic form. While electronicization provides feasibility for more efficient and rapid processing of information, it also brings greater challenges to the information processing system. The computing power, stability, and processing capacity of a single computer can no longer meet the needs of computing centers, and the cluster system was born to meet these demanding requirements. The cluster distributes the computing and processing pressure of information on each node through algorithms and networks, so as to provide the outside world with processing power and stability much higher than that of a single node when the processing capacity of a single node is limited. High concurre...

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
CPCG06F9/5027G06F2209/508G06F2209/5013
Inventor 钟嘉杰范渊吴永越郑学新刘韬
Owner CHENGDU DBAPP SECURITY
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