"Free," "buffer,""swap," "dirty." What does it all mean? If you said,"something to do with the Summer of '68", you may need a primer on'meminfo'.
The entries in the /proc/meminfo can helpexplain what's going on with your memory usage, if you know how to read it.
Example of "cat /proc/meminfo":
root: total: used: free: shared: buffers: cached:
Mem: 1055760384 1041887232 13873152 0 100417536 711233536
Swap: 1077501952 8540160 1068961792
MemTotal: 1031016 kB
MemFree: 13548 kB
MemShared: 0 kB
Buffers: 98064 kB
Cached: 692320 kB
SwapCached: 2244 kB
Active: 563112 kB
Inact_dirty: 309584 kB
Inact_clean: 79508 kB
Inact_target: 190440 kB
HighTotal: 130992 kB (物理内存大于896M 才是高端内存)
HighFree: 1876 kB
LowTotal: 900024 kB
LowFree: 11672 kB
SwapTotal: 1052248 kB
SwapFree: 1043908 kB
Committed_AS: 332340 kB
The information comes in the form of bothhigh-level and low-level statistics. At the top you see a quick summary of themost common values people would like to look at. Below you find the individualvalues we will discuss. First we will discuss the high-level statistics.
High-Level Statistics
MemTotal:Total usable ram (i.e. physical ram minus a few reserved bits and the kernelbinary code)
MemFree:Is sum of LowFree+HighFree (overall stat)
MemShared:0; is here for compat reasons but always zero.
Buffers:Memory in buffer cache. mostly useless as metric nowadays
Cached:Memory in the pagecache (diskcache) minus SwapCache
SwapCache:Memory that once was swapped out, is swapped back in but still also is in theswapfile (if memory is needed it doesn't need to be swapped out AGAIN becauseit is already in the swapfile. This saves I/O)
Detailed Level Statistics
VM Statistics
VM splits the cache pages into"active" and "inactive" memory. The idea is that if youneed memory and some cache needs to be sacrificed for that, you take it frominactive since that's expected to be not used. The vm checks what is used on aregular basis and moves stuff around.
When you use memory, the CPU sets a bit inthe pagetable and the VM checks that bit occasionally, and based on that, itcan move pages back to active. And within active there's an order of"longest ago not used" (roughly, it's a little more complex inreality). The longest-ago used ones can get moved to inactive. Inactive issplit into two in the above kernel (2.4.18-24.8.0). Some have it three.
Active:Memory that has been used more recently and usually not reclaimed unlessabsolutely necessary.
Inact_dirty:Dirty means "might need writing to disk or swap." Takes morework to free. Examples might be files that have not been written to yet. Theyaren't written to memory too soon in order to keep the I/O down. For instance,if you're writing logs, it might be better to wait until you have a completelog ready before sending it to disk.
Inact_clean:Assumed to be easily freeable. The kernel will try to keep some clean stuffaround always to have a bit of breathing room.
Inact_target:Just a goal metric the kernel uses for making sure there are enough inactivepages around. When exceeded, the kernel will not do work to move pages fromactive to inactive. A page can also get inactive in a few other ways, e.g. ifyou do a long sequential I/O, the kernel assumes you're not going to use thatmemory and makes it inactive preventively. So you can get more inactive pagesthan the target because the kernel marks some cache as "more likely to benever used" and lets it cheat in the "last used" order.
Memory Statistics
HighTotal:is the total amount of memory in the high region.Highmem is all memoryabove (approx) 860MB of physical RAM. Kernel uses indirect tricks to accessthe high memory region. Data cache can go in this memory region.
LowTotal:The total amount of non-highmem memory.
LowFree: The amount of free memory of the low memory region. This is thememory the kernel can address directly. All kernel datastructures need to gointo low memory.
SwapTotal:Total amount of physical swap memory.
SwapFree:Total amount of swap memory free.
Committed_AS:An estimate of how much RAM you would need to make a 99.99% guarantee thatthere never is OOM (out of memory) for this workload. Normally the kernel willovercommit memory. That means, say you do a 1GB malloc, nothing happens,really. Only when you start USING that malloc memory you will get real memoryon demand, and just as much as you use. So you sort of take a mortgage and hopethe bank doesn't go bust. Other cases might include when you mmap a file that'sshared only when you write to it and you get a private copy of that data. Whileit normally is shared between processes. The Committed_AS is a guesstimate ofhow much RAM/swap you would need worst-case.
在Linux下查看内存我们一般用free命令:
[root@scs-2 tmp]# free
total used free shared buffers cached
Mem: 3266180 3250004 16176 0 110652 2668236
-/+ buffers/cache: 471116 2795064
Swap: 2048276 80160 1968116
下面是对这些数值的解释:
total:总计物理内存的大小。
used:已使用多大。
free:可用有多少。
Shared:多个进程共享的内存总额。
Buffers/cached:磁盘缓存的大小。
第三行(-/+buffers/cached):
used:已使用多大。
free:可用有多少。
第四行就不多解释了。
区别:第二行(mem)的used/free与第三行(-/+ buffers/cache) used/free的区别。这两个的区别在于使用的角度来看,第一行是从OS的角度来看,因为对于OS,buffers/cached 都是属于被使用,所以他的可用内存是16176KB,已用内存是3250004KB,其中包括,内核(OS)使用+Application(X, oracle,etc)使用的+buffers+cached.
第三行所指的是从应用程序角度来看,对于应用程序来说,buffers/cached 是等于可用的,因为buffer/cached是为了提高文件读取的性能,当应用程序需在用到内存的时候,buffer/cached会很快地被回收。
所以从应用程序的角度来说,可用内存=系统freememory+buffers+cached。
如上例:
2795064=16176+110652+2668236
接下来解释什么时候内存会被交换,以及按什么方交换。 当可用内存少于额定值的时候,就会开会进行交换。
如何看额定值:
cat /proc/meminfo
[root@scs-2 tmp]# cat /proc/meminfo
MemTotal: 3266180 kB
MemFree: 17456 kB
Buffers: 111328 kB
Cached: 2664024 kB
SwapCached: 0 kB
Active: 467236 kB
Inactive: 2644928 kB
HighTotal: 0 kB
HighFree: 0 kB
LowTotal: 3266180 kB
LowFree: 17456 kB
SwapTotal: 2048276 kB
SwapFree: 1968116 kB
Dirty: 8 kB
Writeback: 0 kB
Mapped: 345360 kB
Slab: 112344 kB
Committed_AS: 535292 kB
PageTables: 2340 kB
VmallocTotal: 536870911 kB
VmallocUsed: 272696 kB
VmallocChunk: 536598175 kB
HugePages_Total: 0
HugePages_Free: 0
Hugepagesize: 2048 kB
用free -m查看的结果:
[root@scs-2 tmp]# free -m
total used free shared buffers cached
Mem: 3189 3173 16 0 107 2605
-/+ buffers/cache: 460 2729
Swap: 2000 78 1921
查看/proc/kcore文件的大小(内存镜像):
[root@scs-2 tmp]# ll -h /proc/kcore
-r-------- 1 root root 4.1G Jun 12 12:04/proc/kcore
备注:
占用内存的测量
测量一个进程占用了多少内存,linux为我们提供了一个很方便的方法,/proc目录为我们提供了所有的信息,实际上top等工具也通过这里来获取相应的信息。
/proc/meminfo 机器的内存使用信息
/proc/pid/maps pid为进程号,显示当前进程所占用的虚拟地址。
/proc/pid/statm 进程所占用的内存
[root@localhost ~]# cat /proc/self/statm
654 57 44 0 0 334 0
输出解释
CPU 以及CPU0。。。的每行的每个参数意思(以第一行为例)为:
参数 解释 /proc//status
Size (pages) 任务虚拟地址空间的大小 VmSize/4
Resident(pages) 应用程序正在使用的物理内存的大小 VmRSS/4
Shared(pages) 共享页数 0
Trs(pages) 程序所拥有的可执行虚拟内存的大小 VmExe/4
Lrs(pages) 被映像到任务的虚拟内存空间的库的大小 VmLib/4
Drs(pages) 程序数据段和用户态的栈的大小(VmData+ VmStk )4
dt(pages) 04
查看机器可用内存
/proc/28248/>free
total used free shared buffers cached
Mem: 1023788 926400 97388 0 134668 503688
-/+ buffers/cache: 288044 735744
Swap: 1959920 89608 1870312
我们通过free命令查看机器空闲内存时,会发现free的值很小。这主要是因为,在linux中有这么一种思想,内存不用白不用,因此它尽可能的cache和buffer一些数据,以方便下次使用。但实际上这些内存也是可以立刻拿来使用的。
所以 空闲内存=free+buffers+cached=total-used