雨
分类: LINUX
2011-03-27 16:22:16
vmstat的输出分为以下几种模式:
(1)、VM MODE (普通选项)(2)、DISK MODE(-d选项)(3)、DISK PARTITION MODE(-p选项)(4)、SLAB MODE (-m选项)
(1)、VM MODE
- # vmstat 2 5
- procs -----------memory---------- ---swap-- -----io---- --system-- -----cpu------
- r b swpd free buff cache si so bi bo in cs us sy id wa st
- 0 0 0 15117732 162184 1071304 0 0 0 2 0 1 0 0 100 0 0
- 0 0 0 15117732 162184 1071304 0 0 0 62 1022 114 0 0 100 0 0
- 0 0 0 15117732 162184 1071304 0 0 0 24 1023 115 0 0 100 0 0
- 0 0 0 15117732 162184 1071304 0 0 0 24 1022 118 0 0 100 0 0
- 0 0 0 15117732 162184 1071304 0 0 0 14 1021 112 0 0 100 0 0
Procsr: The number of processes waiting for run time.(等待运行的进程数)
- r 列表示运行和等待cpu时间片的进程数,如果长期大于1,说明cpu不足,需要增加cpu。
b: The number of processes in uninterruptible sleep.(不中断进程数)
- b 列表示在等待资源的进程数,比如正在等待I/O、或者内存交换等。
Memoryswpd: the amount of virtual memory used.(使用的虚拟内存数)
- swpd 切换到内存交换区的内存数量(k表示)。如果swpd的值不为0,或者比较大,比如超过了100m,只要si、so的值长期为0,系统性能还是正常
free: the amount of idle memory.(空闲内存)
- free 当前的空闲页面列表中内存数量(k表示)
buff: the amount of memory used as buffers.(用作buffer的内存数量)
- buff 作为buffer cache的内存数量,一般对块设备的读写才需要缓冲。
cache: the amount of memory used as cache.(用作cache的内存数量)
- cache: 作为page cache的内存数量,一般作为文件系统的cache,如果cache较大,说明用到cache的文件较多,如果此时IO中bi比较小,说明文件系统效率比较好。
inact: the amount of inactive memory. (-a option)(非活动内存)active: the amount of active memory. (-a option)(活动中的内存)Swapsi: Amount of memory swapped in from disk (/s).(从硬盘中导进内存的swap数量,单位:KB/秒)so: Amount of memory swapped to disk (/s).(导入硬盘的swap数量,单位:KB/秒)IObi: Blocks received from a block device (blocks/s).(来自块设备的块数,单位:块/秒)bo: Blocks sent to a block device (blocks/s).(发往块设备的块数,单位:块/秒)Systemin: The number of interrupts per second, including the clock.(每秒中断数)cs: The number of context switches per second.(每秒上下文切换数)
- cs列表示每秒产生的上下文切换次数,如当 cs 比磁盘 I/O 和网络信息包速率高得多,都应进行进一步调查。
CPUThese are percentages of total CPU time.(占总CPU时间的百分比)us: Time spent running non-kernel code. (user time, including nice time)(用户态占用CPU百分比)
- us 列显示了用户方式下所花费 CPU 时间的百分比。us的值比较高时,说明用户进程消耗的cpu时间多,但是如果长期大于50%,需要考虑优化用户的程序。
sy: Time spent running kernel code. (system time)(内核态占用CPU百分比)
- sy 列显示了内核进程所花费的cpu时间的百分比。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。
id: Time spent idle. Prior to Linux 2.5.41, this includes IO-wait time.(空闲CPU百分比)wa: Time spent waiting for IO. Prior to Linux 2.5.41, included in idle.(IO等待占CPU百分比)
- 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)。
st: Time stolen from a virtual machine. Prior to Linux 2.6.11, unknown.(从一个虚拟机被盗的时间)(没明白)(2)、DISK MODE
- # vmstat -d
- disk- ------------reads------------ ------------writes----------- -----IO------
- total merged sectors ms total merged sectors ms cur sec
- ram0 0 0 0 0 0 0 0 0 0 0
- ......
- ram15 0 0 0 0 0 0 0 0 0 0
- sda 86716 11900 2652279 209257 7464061 17760678 201798334 105591331 0 41193
- sr0 0 0 0 0 0 0 0 0 0 0
- md0 0 0 0 0 0 0 0 0 0 0
Readstotal: Total reads completed successfully(成功读取数)merged: grouped reads (resulting in one I/O)(分组读取数)sectors: Sectors read successfully(成功读取扇区数)ms: milliseconds spent reading(读取花费毫秒数)Writestotal: Total writes completed successfully(成功写入数)merged: grouped writes (resulting in one I/O)(分组写入数)sectors: Sectors written successfully(成功写入扇区数)ms: milliseconds spent writing(写入花费毫秒数)IOcur: I/O in progress(I/O进展)(没明白)s: seconds spent for I/O(I/O花费时间)(3)、DISK PARTITION MODE
- # vmstat -p /dev/sda1
- sda1 reads read sectors writes requested writes
- 957 1918 19 38
reads: Total number of reads issued to this partition(对这个分区的read的总数)read sectors: Total read sectors for partition (该分区读取扇区总数)writes : Total number of writes issued to this partition(对这个分区的write的总数)requested writes: Total number of write requests made for partition(对该分区写请求的总数)(4)、SLAB MODE
- # vmstat -m
- Cache Num Total Size Pages
- nfs_direct_cache 0 0 76 50
- nfs_write_data 36 42 512 7
- nfs_read_data 32 36 448 9
- nfs_inode_cache 7 12 668 6
- nfs_page 0 0 64 59
- fscache_cookie_jar 2 84 44 84
- rpc_buffers 8 8 2048 2
.....
Cache: Cache name(Cache 名字)
Num: Number of currently active objects(当前活动对象个数)Total: Total number of available objects(可用对象总数)Size: Size of each object(每个对象的大小)
Pages: Number of pages with at least one active object(至少有一个活动对象的页数)
另外man page值还提到了totpages和pslab,在-m选项的结果中没有体现出来。totpages: Total number of allocated pages( 分配的页面总数)
pslab: Number of pages per slab(每个slab 页面的数量)