论坛徽章:: 0

电梯直达

1楼 [收藏(0)] [报告]

发表于 2012-03-05 17:23 |只看该作者 |倒序浏览

vmstat命令参数详解

vmstat 命令参数详解：

vmstat  n m  :每隔n秒钟刷新，抓取m次数后退出。

FIELD DESCRIPTION FOR VM MODE
Procs
      r: The number of processes waiting for run time.       处于运行队列中的内核线程数目（进程数）。
      b: The number of processes in uninterruptible sleep.  置于等待队列（等待资源、等待输入／输出）的内核线程数目。处于block队列中不可中断的进程数

Memory
      swpd: the amount of virtual memory used.                   可用的虚拟交换内存
      free: the amount of idle memory.                                     空闲内存
      buff: the amount of memory used as buffers.             已用缓冲数目
      cache: the amount of memory used as cache.          已用缓存数目
      inact: the amount of inactive memory. (-a option)       不活动的内存数
      active: the amount of active memory. (-a option)       活动内存数

Swap
      si: Amount of memory swapped in from disk (/s).       从磁盘到内存的交换页数目（单位/S)
      so: Amount of memory swapped to disk (/s).                从交换内存到磁盘的交换页数目（单位/S）

IO
      bi: Blocks received from a block device (blocks/s).    接收到块设备的块数（块/秒）
      bo: Blocks sent to a block device (blocks/s).                发送到块设备的块数（块/秒）

System
      in: The number of interrupts per second, including the clock.       每秒中断数，包括时钟中断
      cs: The number of context switches per second.                            每秒上下文切换数

CPU
      These are percentages of total CPU time.
      us: Time spent running non-kernel code. (user time, including nice time) 用户时间                处于用户模式的时间百分比
      sy: Time spent running kernel code. (system time)                                        系统时间                处于内核模式的时间百分比
      id: Time spent idle. Prior to Linux 2.5.41, this includes IO-wait time.             CPU空闲时间       空闲时间百分比
      wa: Time spent waiting for IO. Prior to Linux 2.5.41, included in idle.          CPU 空闲时间，在此期间系统有未完成的磁盘/NFS I/O 请求
      st: Time stolen from a virtual machine. Prior to Linux 2.6.11, unknown.       来自于虚拟机偷取的CPU所占的百分比（这个不会翻译...）

FIELD DESCRIPTION FOR DISK MODE
Reads
      total: Total reads completed successfully
      merged: grouped reads (resulting in one I/O)
      sectors: Sectors read successfully
      ms: milliseconds spent reading

Writes
      total: Total writes completed successfully
      merged: grouped writes (resulting in one I/O)
      sectors: Sectors written successfully
      ms: milliseconds spent writing

IO
      cur: I/O in progress

   s: seconds spent for I/O

----------------------------------------------------------------------------------------------------------

NOTICE:

　　procs r: 运行的进程比较多，系统很繁忙

　　bi/bo: 磁盘写的数据量稍大，如果是大文件的写，10M以内基本不用担心，如果是小文件写2M以内基本正常

　　cpu us: 持续大于50%，服务高峰期可以接受，如果长期大于50 ，可以考虑优化

   cpu sy: 现实内核进程所占的百分比，这里us + sy的参考值为80%，如果us+sy 大于 80%说明可能存在CPU不足。

　　cpu wa: 列显示了IO等待所占用的CPU时间的百分比。这里wa的参考值为30%，如果wa超过30%，说明IO等待严重，这可能是磁盘大量随机访问造成的，
也可能磁盘或者磁盘访问控制器的带宽瓶颈造成的(主要是块操作)。
　　cpu id:  CPU 空闲时所占百分比  平常持续小于50，服务高峰期可以接受