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

Partition-based concurrency control method in multi-main cloud database scene

A control method and database technology, applied in database update, electronic digital data processing, structured data retrieval, etc., can solve problems such as network and computing storage resource consumption, global log scale increase, etc., to improve overall throughput and reduce overhead , to solve the effect of expansion

Active Publication Date: 2021-10-22
EAST CHINA NORMAL UNIVERSITY
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with this solution, as the number of write nodes increases, the increase in the number of transactions leads to a sharp increase in the size of the global log. Checking each transaction on each write no

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
  • Partition-based concurrency control method in multi-main cloud database scene
  • Partition-based concurrency control method in multi-main cloud database scene
  • Partition-based concurrency control method in multi-main cloud database scene

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0029] Example 1

[0030] See figure 1 The present invention is based on the multi-master database architecture of the partition to divide the transaction to the N + 1 partition, and there is a separate transaction log within each partition. There are multiple servers in each partition, and the servers within the partition can access the data of this partition and have read and write permissions, and implement data consistency within the partition through partition transaction logs in common maintenance. Sort by the transaction-dependent transaction serial number implementation, so that a partition coordination node is designed in each partition for transaction allocation serial numbers, inter-partition coordination nodes communicate with each other to achieve conflicting transactions. In order to adapt to dynamic load changes, the transaction will be asynchronously to package the read-write set with the request information to the partition coordination node. After the partition c...

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 partition-based concurrency control method in a multi-main cloud database scene. Transaction sequence number distribution and a cross-partition concurrency control algorithm are adopted, transactions can be executed in a partition mode according to the data range accessed by the transactions in the execution stage of the transactions, and independent transaction log records exist in all the partitions. Then, the transaction types are divided into single-partition transactions and cross-partition transactions, a cross-partition concurrency control algorithm is introduced between the two types of transactions, and the consistency of data under the scene of multiple write nodes is maintained in combination with distribution of transaction serial numbers. Compared with the prior art, the method has the advantages that the overall performance of the system and the overall throughput of the system under the multi-main scene are improved, the expansion of the writing performance of the database under the multi-main scene is effectively realized, the consistency of the data among the computing nodes is maintained, the overhead of maintaining global logs is reduced, and the partitioning strategy can be effectively adjusted during dynamic loading.

Description

technical field [0001] The invention relates to the technical field of optimistic concurrency control of cloud databases, in particular to a partition-based concurrency control method in a multi-master cloud database scenario under mixed workloads. Background technique [0002] The computing-storage separation architecture is the solution for most commercial cloud databases. Under this architecture, the database is divided into two parts: the storage layer and the computing layer. Multiple storage nodes together form a shared storage layer to provide reliable persistent storage services for the computing layer. The computing layer consists of multiple computing nodes, and each computing node runs a separate database process. Computing nodes cache part of the data to serve users' read and write requests. When the cache fails to hit, the computing nodes follow the replacement strategy to read the required data from the storage layer into the cache. [0003] Currently, most cl...

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
IPC IPC(8): G06F16/23G06F16/2455
CPCG06F16/2308G06F16/24552
Inventor 刘文欣蔡鹏
Owner EAST CHINA NORMAL UNIVERSITY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com