https://support.huawei.com/enterprise/en/doc/EDOC1000181485/ddbc0e8b/optimizing-block-device-parameter-settings-of-linux#:~:text=The%20queue%20depth%20determines%20the%20maximum%20number%20of,block%20device%2C%20run%20cat.%20linux-ob3a%3A~%20%23%20cat%20%2Fsys%2Fblock%2Fsdc%2Fqueue%2Fnr_requests

Operating block devices will greatly affect host performance. Correct configuration of the queue depth scheduling algorithm, prefetch volume, and I/O alignment for block devices helps improve the system performance.

Queue Depth

The queue depth determines the maximum number of concurrent I/Os written to the block device. In Linux, the default value is 128. Do not change the value unless absolutely necessary. To query the queue depth of the block device, run cat.

linux-ob3a:~ # cat /sys/block/sdc/queue/nr_requests 
128

In the event of testing the highest system performance, you can set the queue depth to a larger value to increase the I/O write pressure and the probability of combining I/Os in the queue. To temporarily change the queue depth of a block device, use the following method:

echo 256 > /sys/block/sdc/queue/nr_requests

You can tune the performance by temporarily changing the queue depth of a block device. After the application server is restarted, the queue depth is restored to the default value.

Scheduling Algorithm

Linux 2.6 kernel supports four types of block device scheduling algorithms: noop, anticipatory, deadline, and cfq. The default scheduling algorithm is cfq. To query the block device scheduling algorithm in use, run cat.

linux-ob3a:~ # cat /sys/block/sdc/queue/scheduler 
noop deadline [cfq] 

Inappropriate configuration of the scheduling algorithm affects system performance, such as I/O concurrency. You can use the following method to temporarily change the scheduling algorithm of the block device:

echo noop > /sys/block/sdc/queue/scheduler

You can tune the performance by temporarily changing the scheduling algorithm. After the application server is restarted, the scheduling algorithm is restored to the default value.

Prefetch Volume

Similar to the prefetch algorithm of a storage array, the prefetch function of Linux is only available for sequential read, sequential streams identification, and reading of data in the read_ahead_kb length (in units of sectors) in advance. For example, the default prefetch volume in SUSE 11 is 512 sectors, namely, 256 KB. To query the prefetch volume of the block device, run cat.

linux-ob3a:~ # cat /sys/block/sdc/queue/read_ahead_kb 
512

If an application needs to read a large number of large-sized files, you can raise the system performance by setting the prefetch volume to a larger value. To do this, use the following method:

echo 1024 > /sys/block/sdc/queue/read_ahead_kb

I/O Alignment

If MBR partitions are created in Linux or Windows (pre Windows Server 2003 versions), the first 63 sectors of a disk are reserved for the master boot record and partition table. The first partition starts from the 64th sector by default. As a result, misalignment occurs between data blocks (database or file system) delivered by hosts and data blocks stored in the storage array, causing poor I/O processing efficiency.

In Linux, you can resolve I/O misalignment in either of the following ways:

  • Method 1: Change the start location of a partition.

    When creating MBR partitions in Linux, it is recommended that you enter the expert mode of the fdisk command and set the start location of the first partition to that of the second extent on a LUN. The default extent size is 4 MB. The following is a quick command used to create an MBR partition in /dev/sdb. The partition uses all space of /dev/sdb. The start sector is set to 8192, namely, 4 MB.

    printf "n\np\n1\n\n\nx\nb\n1\n 8192\nw\n" | fdisk /dev/sdb
  • Method 2: Create GPT partitions.

    The following is a quick command used to create a GPT partition in /dev/sdb. The partition uses all space of /dev/sdb. The start sector is set to 8192, namely, 4 MB.

    parted -s -- /dev/sdb "mklabel gpt" "unit s" "mkpart primary 8192 -1" "print"

To create MBR partitions in Windows (pre Windows Server 2003 versions), it is recommended that you run diskpart to set partition alignment.

diskpart> select disk 1 
diskpart> create partition primary align=4096

[转帖]Optimizing Block Device Parameter Settings of Linux的更多相关文章

  1. 部署samba服务之后,在客户端用挂载访问的方式,错误信息:mount: block device //192.168.1.108/mysqldata is write-protected, mounting read-only mount: cannot mount block device //192.168.1.108/mysqldata read-only

    部署samba服务之后,在客户端用挂载访问的方式,错误信息:mount: block device //192.168.1.108/mysqldata is write-protected, moun ...

  2. Is an MTD device a block device or a char device?

    转:http://www.linux-mtd.infradead.org/faq/general.html#L_mtd_what Note, you can find Ukranian transla ...

  3. RMAN备份失败之:mount: block device /dev/emcpowerc1 is write-protected, mounting read-only

    今天再做巡检的时候发现有一台服务器的RMAN备份不正常,有一段时间没能正常备份了.检查了一下脚本,正常,定时任务列表也正常,再检查一下/var/log/cron的内容,也没有问题.尝试在该挂载点上创建 ...

  4. centos6.4 ceph安装部署之ceph block device

    1,prelight/preface ceph storage clusterceph block deviceceph filesystemceph object storage 此篇记录ceph ...

  5. Openstack: aborted: Block Device Mapping is Invalid

    Issue: When you create an instance, you may encounter following exception: aborted: Block Device Map ...

  6. QEMU KVM Libvirt手册(6) – Network Block Device

    网络块设备是通过NBD Server将虚拟块设备通过TCP/IP export出来,可以远程访问. NBD Server通常是qemu-nbd 可以提供unix socket qemu-nbd -t ...

  7. Mount 挂载错误mount:block device /dev/sr0 is write – protected , mounting read-only

    Mount 挂载错误mount:block device /dev/sr0 is write – protected , mounting read-only 安装虚拟机出现以下提示: mount:b ...

  8. mount: block device /dev/cdrom is write-protected, mounting read-only 解决方法

    [root@localhost ~]# mount /dev/cdrom /mnt/cdrom/ mount: block device /dev/sr0 is write-protected, mo ...

  9. DRBD(Distributed Replicated Block Device) 分布式块设备复制 进行集群高可用方案

    DRBD是一个用软件实现的.无共享的.服务器之间镜像块设备内容的存储复制解决方案. 外文名 DRBD drbdadm 高级管理工具 drbdsetup 置装载进kernel的DRBD模块 drbdme ...

  10. Nova: 虚机的块设备总结 [Nova Instance Block Device]

    和物理机一样,虚拟机包括几个重要的部分:CPU.内存.磁盘设备.网络设备等.本文将简要总结虚机磁盘设备有关知识. 1. Nova boot CLI 中有关虚机块设备的几个参数 nova boot CL ...

随机推荐

  1. [Python急救站]含义GUI的学生管理系统

    这个管理系统是含有GUI界面的学生管理系统,比较方便. import tkinter as tk class Student: def __init__(self, name, student_id, ...

  2. PyTorch项目源码学习(1)

    PyTorch PyTorch是一个开源的深度学习框架,项目地址 https://github.com/pytorch/pytorch 在学术工作中的使用频率较高.其主体由C++开发,PyTorch是 ...

  3. 6、Flutter 列表组件 滑动

    列表有以下分类: 1.垂直列表 class MyApp extends StatelessWidget { const MyApp({super.key}); @override Widget bui ...

  4. 神经网络优化篇:理解指数加权平均数(Understanding exponentially weighted averages)

    理解指数加权平均数 回忆一下这个计算指数加权平均数的关键方程. \({{v}_{t}}=\beta {{v}_{t-1}}+(1-\beta ){{\theta }_{t}}\) \(\beta=0. ...

  5. ROMA集成关键技术:增量数据集成

    摘要:本文将详解ROMA集成关键技术-增量数据集成技术. 本文分享自华为云社区<ROMA集成关键技术(2)-增量数据集成技术>,作者:华为云PaaS服务小智 . 1.概述 ROMA平台的核 ...

  6. 如何做好分支管理,保证高效CI/CD?

    摘要:一文讲述git分支管理策略. 本文分享自华为云社区<如何做好分支管理,保证高效CICD?>,作者:华为云PaaS服务小智. 引言 CI/CD是DevOps 的基础核心,做好CI/CD ...

  7. Mac 播放 swf Flash文件

    Flash已不再支持,swf 文件彻底打不开了(一些教程),通过PD虚拟,安装 windows 操作系统在里在装了 flash 播放器使用了一段时间,始终不方便.于是找到了如下方法 首先安装:Adob ...

  8. go对mongodb的聚合查询

    mongodb的环境搭建参考前面一篇通过mongo-driver使用说明 GO 包管理机制 BSON 介绍 在Go中使用BSON对象构建操作命令 在我们发送查询给数据库之前, 很重要的一点是,理解Go ...

  9. 路由分发 路由别名的名称空间 虚拟环境 HTTPresponse JsonResponse request对象获取文件 CBV源码剖析 模板语法传值特性 模板语法过滤器

    目录 路由分发 路由别名冲突 反向解析失败 方式一:名称空间 include 方式二:别名不冲突即可 虚拟环境 python -m venv venv_name 视图层之必会三板斧 HTTPrespo ...

  10. 在 HTML 页面中使用 React

    该方案使用场景:在html页面中使用react,主js文件index.js和其它非react功能使用js模块化的方式开发,适合轻量级中小型应用 index.html代码: 引入react.react- ...