1nfsiostat(8)                System Manager's Manual               nfsiostat(8)
2
3
4

NAME

6       nfsiostat    -    Emulate   iostat   for   NFS   mount   points   using
7       /proc/self/mountstats
8

SYNOPSIS

10       nfsiostat [[<interval>] [<count>]] [<options>][<mount_point>]
11

DESCRIPTION

13       The nfsiostat command displays NFS client per-mount statisitics.
14
15       <interval>
16              specifies the amount of time in  seconds  between  each  report.
17              The  first  report  contains  statistics for the time since each
18              file system was mounted.  Each subsequent report  contains  sta‐
19              tistics collected during the interval since the previous report.
20
21       <count>
22              If  the  <count>  parameter  is  specified, the value of <count>
23              determines the number of reports generated at <interval> seconds
24              apart.  if  the  interval  parameter  is  specified  without the
25              <count> parameter, the command generates reports continuously.
26
27       <options>
28              Define below
29
30       <mount_point>
31              If one or more <mount point> names are specified, statistics for
32              only  these  mount points will be displayed.  Otherwise, all NFS
33              mount points on the client are listed.
34
35       The meaning of each column of nfsiostat's output is the following:
36               - op/s
37                      This is the number of operations per second.
38               - rpc bklog
39                      This is the length of the backlog queue.
40               - kB/s
41                      This is the number of kB written/read per second.
42               - kB/op
43                      This is the number of kB written/read  per  each  opera‐
44                      tion.
45               - retrans
46                      This is the number of retransmissions.
47               - avg RTT (ms)
48                      This  is the duration from the time that client's kernel
49                      sends the RPC request until the  time  it  receives  the
50                      reply.
51               - avg exe (ms)
52                      This  is the duration from the time that NFS client does
53                      the RPC request to its kernel until the RPC  request  is
54                      completed, this includes the RTT time above.
55               - avg queue (ms)
56                      This  is  the duration from the time the NFS client cre‐
57                      ated the RPC request task to the  time  the  request  is
58                      transmitted.
59               - errors
60                      This  is the number of operations that completed with an
61                      error status (status < 0).  This count is only available
62                      on kernels with RPC iostats version 1.1 or above.
63
64       Note  that  if  an  interval is used as argument to nfsiostat, then the
65       diffrence from previous  interval  will  be  displayed,  otherwise  the
66       results will be from the time that the share was mounted.
67
68

OPTIONS

70       -a  or  --attr
71              displays statistics related to the attribute cache
72
73       -d  or  --dir
74              displays statistics related to directory operations
75
76       -h  or  --help
77              shows help message and exit
78
79       -l LIST or  --list=LIST
80              only print stats for first LIST mount points
81
82       -p  or  --page
83              displays statistics related to the page cache
84
85       -s  or  --sort
86              Sort NFS mount points by ops/second
87
88       --version
89              show program's version number and exit
90

FILES

92       /proc/self/mountstats
93

SEE ALSO

95       iostat(8), mountstats(8), nfsstat(8)
96

AUTHOR

98       Chuck Lever <chuck.lever@oracle.com>
99
100
101
102                                  15 Apr 2010                     nfsiostat(8)