内存数据库专题之数据库性能瓶颈分析之IO

1. 概述

　　常言道：有数据，有真相。数据库的性能瓶颈分析也是需要拿出具体的数据来的，否则单纯的说谁比谁性能强弱，都是没有说服力和根据的。关于内存数据库和磁盘数据库的性能对比也是如此。内存数据库通过读取内存中的数据来实现读写加速，磁盘数据库通过硬盘IO实现数据读写。Linux平台提供了专门的工具来时先磁盘IO性能的获取，该工具为hdparm，本文就该工具的使用做一个详细的介绍。

2.命令格式

Usage:  hdparm  [options] [device] ..

3.示例结果

[root@localhost zhangzl]# hdparm -Tt /dev/sda

/dev/sda:

 Timing cached reads:   3820 MB in  2.00 seconds = 1910.72 MB/sec

 Timing buffered disk reads:   42 MB in  3.05 seconds =  13.78 MB/sec

在这里我们就能看到差距来了，1910.72/13.78=138.66,一百多倍的读取差距，还是相当可观的。以上数据是我在虚拟机环境下测试的结果，具体的性能指标因机器配置、性能不同，会有不同，需要自行测试。

4.参数详解

Options:

 -a   get/set fs readahead

 -A   set drive read-lookahead flag (0/1)

 -b   get/set bus state (0 == off, 1 == on, 2 == tristate)

 -B   set Advanced Power Management setting (1-255)

 -c   get/set IDE 32-bit IO setting

 -C   check IDE power mode status

 -d   get/set using_dma flag

 --direct  use O_DIRECT to bypass page cache for timings

 -D   enable/disable drive defect management

 -E   set cd-rom drive speed

 -f   flush buffer cache for device on exit

 -g   display drive geometry

 -h   display terse usage information

 -i   display drive identification

 -I   detailed/current information directly from drive

 --Istdin  read identify data from stdin as ASCII hex

 --Istdout write identify data to stdout as ASCII hex

 -k   get/set keep_settings_over_reset flag (0/1)

 -K   set drive keep_features_over_reset flag (0/1)

 -L   set drive doorlock (0/1) (removable harddisks only)

 -M   get/set acoustic management (0-254, 128: quiet, 254: fast) (EXPERIMENTAL)

 -m   get/set multiple sector count

 -n   get/set ignore-write-errors flag (0/1)

 -p   set PIO mode on IDE interface chipset (0,1,2,3,4,...)

 -P   set drive prefetch count

 -q   change next setting quietly

 -Q   get/set DMA tagged-queuing depth (if supported)

 -r   get/set device  readonly flag (DANGEROUS to set)

 -R   register an IDE interface (DANGEROUS)

 -S   set standby (spindown) timeout

 -t   perform device read timings

 -T   perform cache read timings

 -u   get/set unmaskirq flag (0/1)

 -U   un-register an IDE interface (DANGEROUS)

 -v   defaults; same as -mcudkrag for IDE drives

 -V   display program version and exit immediately

 -w   perform device reset (DANGEROUS)

 -W   set drive write-caching flag (0/1) (DANGEROUS)

 -x   tristate device for hotswap (0/1) (DANGEROUS)

 -X   set IDE xfer mode (DANGEROUS)

 -y   put IDE drive in standby mode

 -Y   put IDE drive to sleep

 -Z   disable Seagate auto-powersaving mode

 -z   re-read partition table

 --security-help  display help for ATA security commands

转载于:https://www.cnblogs.com/hadoopdev/archive/2013/04/25/3041843.html