Is this normal - I've never seen buffers so high?

$ cat /proc/meminfo 
MemTotal: 16332808 kB
MemFree: 1112264 kB
Buffers: 10630124 kB
Cached: 699400 kB
SwapCached: 0 kB
Active: 3262924 kB
Inactive: 8132004 kB
Active(anon): 27464 kB
Inactive(anon): 38888 kB
Active(file): 3235460 kB
Inactive(file): 8093116 kB
Unevictable: 0 kB
Mlocked: 0 kB
SwapTotal: 525308 kB
SwapFree: 525308 kB
Dirty: 40 kB
Writeback: 0 kB
AnonPages: 65412 kB
Mapped: 11300 kB
Shmem: 940 kB
Slab: 3674368 kB
SReclaimable: 3652612 kB
SUnreclaim: 21756 kB
KernelStack: 1496 kB
PageTables: 3340 kB
NFS_Unstable: 0 kB
Bounce: 0 kB
WritebackTmp: 0 kB
CommitLimit: 8691712 kB
Committed_AS: 594304 kB
VmallocTotal: 34359738367 kB
VmallocUsed: 102232 kB
VmallocChunk: 34359634044 kB
HardwareCorrupted: 0 kB
DirectMap4k: 2048 kB
DirectMap2M: 16691200 kB

closed as unclear what you're asking by slm, Anthon, jasonwryan, Renan, Tim Kennedy Aug 15 '13 at 5:22

Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • What's that machine doing? Is everything working as usual? – Mat Aug 13 '13 at 14:56
  • Use 'top' command and see %MEM for each process. It is impossible to to known the problem on total memory usage. As a general rule, system will try using more memory as you have for caching (in your case it is 16GB RAM) – damphat Aug 13 '13 at 15:02
  • It's idle, the usage is buffer - which i believe is file meta data. Nothing in top is using the memory - which is to be expected. Working fine, just I have never seen this on any of my other machines and wondered if it was Ubuntu 13.04 (bug?) which is the only difference. – smremde Aug 13 '13 at 15:08
  • what file systems are you using? (cat /etc/mounts) do you have a lot of inodes? (df -i) – Matt Aug 13 '13 at 21:07

It's not normal, but it can happen depending upon what you are or were doing. According to the kernel documentation for the proc filesystem, "buffers" is the amount of memory used by cached raw disk data as opposed to "cached" which is the memory used by cached file data.

Buffers should normally be much smaller than Cached, but you can make buffers shoot up if you perform a lot of direct disk IO. I was able to make mine increase significantly by running sudo dd if=/dev/sda of=/dev/null bs=1M count=16384. Here are my results.

$ cat /proc/meminfo 
MemTotal:       16435344 kB
MemFree:          187388 kB
Buffers:         5655192 kB
Cached:          8473748 kB
SwapCached:            0 kB
Active:          7141492 kB
Inactive:        8228596 kB
Active(anon):    1073180 kB
Inactive(anon):   169312 kB
Active(file):    6068312 kB
Inactive(file):  8059284 kB
Unevictable:           0 kB
Mlocked:               0 kB
SwapTotal:       4192928 kB
SwapFree:        4192928 kB
Dirty:                36 kB
Writeback:             0 kB
AnonPages:       1241160 kB
Mapped:           437492 kB
Shmem:              1336 kB
Slab:             256696 kB
SReclaimable:     206660 kB
SUnreclaim:        50036 kB
KernelStack:        3160 kB
PageTables:        12224 kB
NFS_Unstable:          0 kB
Bounce:                0 kB
WritebackTmp:          0 kB
CommitLimit:    12410600 kB
Committed_AS:    3064896 kB
VmallocTotal:   34359738367 kB
VmallocUsed:      306540 kB
VmallocChunk:   34359429104 kB
HardwareCorrupted:     0 kB
AnonHugePages:         0 kB
HugePages_Total:       0
HugePages_Free:        0
HugePages_Rsvd:        0
HugePages_Surp:        0
Hugepagesize:       2048 kB
DirectMap4k:       58816 kB
DirectMap2M:    16717824 kB

Do you have any programs performing a lot of block IO?

Not the answer you're looking for? Browse other questions tagged or ask your own question.