I/O wait is a per-CPU performance metric showing time spent idle, when there are threads on the CPU dispatcher queue (in sleep state) that are blocked on disk I/O. This divides CPU idle time into time spent with nothing to do, and time spent blocked on disk I/O. A high rate of I/O wait per CPU shows that the disks may be a bottleneck, leaving the CPU idle while it waits on them.
I/O wait can be a very confusing metric. If another CPU-hungry process comes along, the I/O wait value can drop: the CPUs now have something to do, instead of being idle. However, the same disk I/O is still present and blocking threads, despite the drop in the I/O wait metric. The reverse has sometimes happened when system administrators have upgraded application software and the newer version is more efficient and uses fewer CPU cycles, revealing I/O wait. This can make the system administrator think that the upgrade has caused a disk issue and made performance worse, when in fact disk performance is the same, and CPU performance is improved.

There are also some subtle issues with how I/O wait was being calculated on Solaris. For the Solaris 10 release, the I/O wait metric was deprecated and hardwired to zero for tools that still needed to display it (for compatibility).
A more reliable metric may be the time that application threads are blocked on disk I/O. This captures the pain endured by application threads caused by disk I/O, regardless of what other work the CPUs may be doing. This metric can be measured using static or dynamic tracing.

I/O wait is still a popular metric on Linux systems, and despite its confusing nature, it is used successfully to identify a type of disk bottleneck: disks busy, CPUs idle. One way to interpret it is to treat any wait I/O as a sign of a system bottleneck, and then tune the system to minimize it—even if the I/O is still occurring concurrently with CPU utilization. Concurrent I/O is more likely to be non-blocking I/O, and less likely to cause a direct issue. Nonconcurrent I/O, as identified by I/O wait, is more likely to be application blocking I/O, and a bottleneck.

摘录自《Systems Performance: Enterprise and the Cloud》

随机推荐

  1. 6.1 CUDA: pinned memory固定存储

    CPU和GPU内存交互 在CUDA编程中,内存拷贝是非常费时的一个动作. 从上图我们可以看出:1. CPU和GPU之间的总线bus是PCIe,是双向传输的. 2. CPU和GPU之间的数据拷贝使用DM ...

  2. 【原创】lua编译时发现缺少readline库

    编译lualua项目,其中用到了lua-5.1版本的源码,编译时提示缺少readline库,找不到readline/readline.h头文件等 发现系统中其实有安装readline库不过没有做链接和 ...

  3. 在win64位,python64位2.7版本中安装pyHook

    今天看了一篇博文说的是利用pyhook监听键盘鼠标事件(感兴趣的可以看博客园中相关文章),文章中使用的pyHook模块的官方下载地址是:http://sourceforge.net/projects/ ...

  4. 【Hadoop代码笔记】Hadoop作业提交之JobTracker等相关功能模块初始化

    一.概要描述 本文重点描述在JobTracker一端接收作业.调度作业等几个模块的初始化工作.想过模块的介绍会在其他文章中比较详细的描述.受理作业提交在下一篇文章中会进行描述. 为了表达的尽可能清晰一 ...

  5. 大数据架构师基础:hadoop家族,Cloudera产品系列等各种技术

    大数据我们都知道hadoop,可是还会各种各样的技术进入我们的视野:Spark,Storm,impala,让我们都反映不过来.为了能够更好的架构大数据项目,这里整理一下,供技术人员,项目经理,架构师选 ...

  6. HW6.16

    import java.util.Arrays; public class Solution { public static void main(String[] args) { int[] arra ...

  7. Visual C#使用DirectX实现视频播放

    Visual C#使用DirectX实现视频播放 visual|视频播放 - 很多人第一次接触到DirectX大都是通过游戏,至于安装.升级DirectX的原因无非是满足游戏运行的需要.Direct ...

  8. Oracle中的AS和IS

    Oracle中的AS和IS是ORACLE为了方便而设置的同义词基本上没有不同 . 使用规则: 1.在创建存储过程(PROCEDURE)/函数(FUNCTION),以及自定义类型(TPYE)和包(PAC ...

  9. cocos2d-x 网格动画深入分析

    转自:http://www.2cto.com/kf/201212/179828.html 在TestCpp中的EffectsTest示例中展示了一些屏幕特效,它是将屏幕划分为多个格子,并对这些格子进行 ...

  10. 使用 jsPlumb 绘制拓扑图 —— 异步载入与绘制的实现

    本文实现的方法能够边异步载入数据边绘制拓扑图. 有若干点须要说明一下: 1.  一次性获取全部数据并绘制拓扑图. 请參见文章: <使用 JsPlumb 绘制拓扑图的通用方法> ; 本文实现 ...