Chinaunix首页 | 论坛 | 博客
  • 博客访问: 1281980
  • 博文数量: 168
  • 博客积分: 3483
  • 博客等级: 中校
  • 技术积分: 1696
  • 用 户 组: 普通用户
  • 注册时间: 2006-02-06 13:17
文章分类

全部博文(168)

文章存档

2015年(6)

2014年(9)

2013年(47)

2012年(11)

2011年(13)

2010年(18)

2009年(11)

2008年(42)

2007年(11)

分类: LINUX

2013-06-02 09:06:34

[NFS] /proc/net/rpc/nfsd file explained

This file is populated writen by /proc/net/rpc/nfsd file by kernel code linux/fs/nfsd/stats.c and linux/net/sunrpc/stats.c: 

cat /proc/net/rpc/nfsd
rc 14 277482605 1519481075
fh 5208 0 0 0 0
io 3197575487 677537481
th 128 1196 48 11 677 54 66 31 288 27 26 118
ra 256 1089064507 0 0 0 0 0 0 0 0 0 1410044
net 471073134 0 471089819 60766
rpc 1796938178 0 0 0 0
proc2 18 0 152 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
proc3 22 1 219996357 556065 24059461 43520164 606473 150260668 28056897 545340 198181 3708 0 412742 104649 177365 10 4940 255357 152 3
 0 1809695
proc4 2 0 0
proc4ops 40 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0

Line by line explaination

rc 14 277482605 1519481075
    rc Statistsics for the reply cache [3]
    - hits: client it's retransmiting (a bad thing! o hits is good)  [1]
     - misses: a operation that requires caching
     - nocache: a operation that no requires caching

fh 5208 0 0 0 0
    fh (filehandle): [1]
       
     - stale: *supose* to be file handle errors (like when you resize the
              underlying filesystem)
     - total-lookups, anonlookups, dir-not-in-cache, nodir-not-in-cache: do
       not appear (and I always seen it as zeros). So I supose they are unused.

io 3197575487 677537481
    io (input/output):
     - bytes-read: bytes read directly from disk
     - bytes-written: bytes written to disk           

th 128 1196 48 11 677 54 66 31 288 27 26 118
    th (threads): ...
     - threads: number of nfsd threads
     - fullcnt: number of times that the last 10% of threads  (so all threads) are busy.
     - 10%-20% (1196), 20%-30% ... 90%-100%: histogram (in the unit of seconds) of the percentage of threads is used
       1196 means there is 1196 seconds in which more than 10% threads (and less than 20% threads) are 
       used.

ra 256 1089064507 0 0 0 0 0 0 0 0 0 1410044
    ra (read-ahead): ...
     - cache-size: always the double of number threads
     - 10%, 20% ... 100%: how deep it found what was looking for. I *suppose*
       this means how far the cached block is from the original block that was
       first requested.
     - not-found: not found in the read-ahead cache

net 1797032444 15813112 1781194739 52706
   net:
    - netcnt: counts every read
    - netudpcnt: counts every UDP packet it receives
    - nettcpcnt: counts every time it receives data from a TCP connection
    - nettcpconn: count every TCP connection it receives

rpc 1796938178 0 0 0 0
   rpc:
    - rpccnt: counts all rpc operations
    - rpcbadfmt: counts if while processing a RPC it encounters the
                 following errors: err_bad_dir, err_bad_rpc, err_bad_prog, err_bad_vers,
                 err_bad_proc, err_bad
    - rpcbadauth: bad authentication. It does not count if you try to mount
                  from a machine that it's not in your exports file
    - rpcbadclnt: unused

proc3 22 1 219996357 556065 24059461 43520164 606473 150260668 28056897 545340 198181 3708 0 412742 104649 177365 10 4940 255357 152 3
 0 1809695
   This should be the nfsv3 statistic, comparing with the output of nfsstat, we should be able to figure out what are those number for

Server nfs v3:
null         getattr      setattr      lookup       access       readlink   
1         0% 219996357 46% 556065    0% 24059461  5% 43520164  9% 606473    0%
read         write        create       mkdir        symlink      mknod       
150260668 31% 28056899  5% 545340    0% 198181    0% 3708      0% 0         0%
remove       rmdir        rename       link         readdir      readdirplus 
412742    0% 104649    0% 177365    0% 10        0% 4940      0% 255357    0%
fsstat       fsinfo       pathconf     commit     
152       0% 3         0% 0         0% 1809696   0%

Looks like field 9 and filed 10 is the read and write count. But I still can not tell the difference between
and this nfs read count.

reference:
[1]
[2] http://blog.peacon.co.uk/wiki/Monitoring_NFS_Performance
[3] ftp://82.96.64.7/pub/linux/kernel/people/marcelo/linux-2.4/fs/nfsd/stats.c
Posted 27th January 2012 by Deep Dive
阅读(4073) | 评论(0) | 转发(0) |
给主人留下些什么吧!~~