MySQL 的 InnoDB 存储引擎不仅可以缓存索引,而且还可以缓存数据,如果将其表和索引存储在裸设备(Raw Device)上,从而绕过了文件
MySQL 的 InnoDB 存储引擎不仅可以缓存索引,而且还可以缓存数据,如果将其表和索引存储在裸设备(Raw Device)上,从而绕过了文件系统的高速缓存和缓冲器而直接访问磁盘,,那么将大大降低Linux文件系统的负担,使系统性能获得显著改善。
另外,从裸设备在数据库应用的优化原理中,我们也可以看到优化数据库的一个基本方向,就是如何设法降低因数据库特有的 I/O 密集型访问所导致的文件系统的繁重负担。因此,即使在现有的基于文件系统的数据库存储引擎上,也可考虑使用特殊的文件系统挂载方式。
例如为存储数据库文件的分区使用 noatime 作为挂载参数,由于访问次数(access times)不再被记录 可以带来系统性能的一定程度的提升。
──────────────────────────────────────────────────────────────────────────────
本笔记最新配置之系统环境:
──────────────────────────────────────────────────────────────────────────────
OS: CentOS6
HDD: /dev/sdc /dev/sdd
RAW: /dev/raw/raw1 /dev/raw/raw2
MySQL: 5.1.61
USER: mysql:mysql
参考官方网站的配置指引:
──────────────────────────────────────────────────────────────────────────────
(1) 设置裸设备(Prepare the raw device)
──────────────────────────────────────────────────────────────────────────────
在使用裸设备之前,必须先将磁盘设备绑定到裸设备上:
# /bin/raw /dev/raw/raw1 /dev/sdc;
--------------------------------------------------------------------------------
/dev/raw/raw1: bound to major 8, minor 32
--------------------------------------------------------------------------------
再绑定另一个裸设备,然后还要让您的MySQL数据库的运行用户有权读写裸设备:
# /bin/raw /dev/raw/raw2 /dev/sdd;
# chown root:mysql /dev/raw/raw1 /dev/raw/raw2;
# chmod 0660 /dev/raw/raw1 /dev/raw/raw2;
# /bin/raw -qa;
# /bin/raw -q /dev/raw/raw1;
# /bin/ls -l /dev/raw/raw1;
# blockdev --report /dev/raw/raw1;
# blockdev --report /dev/sdc;
vi /etc/udev/rules.d/60-raw.rules;
--------------------------------------------------------------------------------
ACTION=="add", KERNEL=="sdc", GROUP=="mysql", MODE=="0660", RUN+="/bin/raw /dev/raw/raw1 %N"
ACTION=="add", KERNEL=="sdd", GROUP=="mysql", MODE=="0660", RUN+="/bin/raw /dev/raw/raw2 %N"
--------------------------------------------------------------------------------
Note: this make sure device /dev/sdc and /dev/sdd will bind automatically when server reboot.
# vi /etc/udev/rules.d/41-local-permissions-rules;
──────────────────────────────────────────────────────────────────────────────
(2) 如有需要,先备份旧有的InnoDB数据表
──────────────────────────────────────────────────────────────────────────────
如果您的数据库已经运行,并且现有数据存储于旧的InnoDB引擎之中,如果您需要迁移的话,
请在关闭数据库之前预先用mysqldump命令导出您的数据, 等新引擎配置好之后再导入即可。
可参考如下SQL命令查看和导出您的InnoDB数据表:
mysql> SELECT table_schema,table_name,engine FROM INFORMATION_SCHEMA.TABLES;
mysql> SELECT table_schema, table_name FROM INFORMATION_SCHEMA.TABLES WHERE engine='InnoDB';
如有需要,可用mysqldump导出数据,请参考如下格式(请用相应的数据库和表名称):
mysqldump -u root -p -h localhost [database].[table] > database.table.sql
注意:您必须逐个表导出旧的数据。
──────────────────────────────────────────────────────────────────────────────
(3) 初始化阶段MySQL的配置
──────────────────────────────────────────────────────────────────────────────
When you create a new data file, put the keyword newraw
immediately after the data file size in innodb_data_file_path:
# vi /etc/my.cnf;
--------------------------------------------------------------------------------
[mysqld]
innodb_buffer_pool_size=128M
innodb_data_home_dir=
innodb_data_file_path=/dev/raw/raw1:64Mnewraw;/dev/raw/raw2:64Mnewraw
--------------------------------------------------------------------------------

InnoDBBufferPool reduces disk I/O by caching data and indexing pages, improving database performance. Its working principle includes: 1. Data reading: Read data from BufferPool; 2. Data writing: After modifying the data, write to BufferPool and refresh it to disk regularly; 3. Cache management: Use the LRU algorithm to manage cache pages; 4. Reading mechanism: Load adjacent data pages in advance. By sizing the BufferPool and using multiple instances, database performance can be optimized.

Compared with other programming languages, MySQL is mainly used to store and manage data, while other languages such as Python, Java, and C are used for logical processing and application development. MySQL is known for its high performance, scalability and cross-platform support, suitable for data management needs, while other languages have advantages in their respective fields such as data analytics, enterprise applications, and system programming.

MySQL is worth learning because it is a powerful open source database management system suitable for data storage, management and analysis. 1) MySQL is a relational database that uses SQL to operate data and is suitable for structured data management. 2) The SQL language is the key to interacting with MySQL and supports CRUD operations. 3) The working principle of MySQL includes client/server architecture, storage engine and query optimizer. 4) Basic usage includes creating databases and tables, and advanced usage involves joining tables using JOIN. 5) Common errors include syntax errors and permission issues, and debugging skills include checking syntax and using EXPLAIN commands. 6) Performance optimization involves the use of indexes, optimization of SQL statements and regular maintenance of databases.

MySQL is suitable for beginners to learn database skills. 1. Install MySQL server and client tools. 2. Understand basic SQL queries, such as SELECT. 3. Master data operations: create tables, insert, update, and delete data. 4. Learn advanced skills: subquery and window functions. 5. Debugging and optimization: Check syntax, use indexes, avoid SELECT*, and use LIMIT.

MySQL efficiently manages structured data through table structure and SQL query, and implements inter-table relationships through foreign keys. 1. Define the data format and type when creating a table. 2. Use foreign keys to establish relationships between tables. 3. Improve performance through indexing and query optimization. 4. Regularly backup and monitor databases to ensure data security and performance optimization.

MySQL is an open source relational database management system that is widely used in Web development. Its key features include: 1. Supports multiple storage engines, such as InnoDB and MyISAM, suitable for different scenarios; 2. Provides master-slave replication functions to facilitate load balancing and data backup; 3. Improve query efficiency through query optimization and index use.

SQL is used to interact with MySQL database to realize data addition, deletion, modification, inspection and database design. 1) SQL performs data operations through SELECT, INSERT, UPDATE, DELETE statements; 2) Use CREATE, ALTER, DROP statements for database design and management; 3) Complex queries and data analysis are implemented through SQL to improve business decision-making efficiency.

The basic operations of MySQL include creating databases, tables, and using SQL to perform CRUD operations on data. 1. Create a database: CREATEDATABASEmy_first_db; 2. Create a table: CREATETABLEbooks(idINTAUTO_INCREMENTPRIMARYKEY, titleVARCHAR(100)NOTNULL, authorVARCHAR(100)NOTNULL, published_yearINT); 3. Insert data: INSERTINTObooks(title, author, published_year)VA


Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Article

Hot Tools

Notepad++7.3.1
Easy-to-use and free code editor

Dreamweaver Mac version
Visual web development tools

ZendStudio 13.5.1 Mac
Powerful PHP integrated development environment

SAP NetWeaver Server Adapter for Eclipse
Integrate Eclipse with SAP NetWeaver application server.

DVWA
Damn Vulnerable Web App (DVWA) is a PHP/MySQL web application that is very vulnerable. Its main goals are to be an aid for security professionals to test their skills and tools in a legal environment, to help web developers better understand the process of securing web applications, and to help teachers/students teach/learn in a classroom environment Web application security. The goal of DVWA is to practice some of the most common web vulnerabilities through a simple and straightforward interface, with varying degrees of difficulty. Please note that this software