iostats.txt 8.12 KB
Newer Older
1
=====================
Linus Torvalds's avatar
Linus Torvalds committed
2
I/O statistics fields
3
=====================
Linus Torvalds's avatar
Linus Torvalds committed
4 5 6

Since 2.4.20 (and some versions before, with patches), and 2.5.45,
more extensive disk statistics have been introduced to help measure disk
7
activity. Tools such as ``sar`` and ``iostat`` typically interpret these and do
Linus Torvalds's avatar
Linus Torvalds committed
8 9 10 11
the work for you, but in case you are interested in creating your own
tools, the fields are explained here.

In 2.4 now, the information is found as additional fields in
12 13
``/proc/partitions``.  In 2.6 and upper, the same information is found in two
places: one is in the file ``/proc/diskstats``, and the other is within
Linus Torvalds's avatar
Linus Torvalds committed
14 15
the sysfs file system, which must be mounted in order to obtain
the information. Throughout this document we'll assume that sysfs
16 17
is mounted on ``/sys``, although of course it may be mounted anywhere.
Both ``/proc/diskstats`` and sysfs use the same source for the information
Linus Torvalds's avatar
Linus Torvalds committed
18 19
and so should not differ.

20
Here are examples of these different formats::
Linus Torvalds's avatar
Linus Torvalds committed
21

22 23 24
   2.4:
      3     0   39082680 hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
      3     1    9221278 hda1 35486 0 35496 38030 0 0 0 0 0 38030 38030
Linus Torvalds's avatar
Linus Torvalds committed
25

26
   2.6+ sysfs:
27 28
      446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
      35486    38030    38030    38030
Linus Torvalds's avatar
Linus Torvalds committed
29

30
   2.6+ diskstats:
31 32
      3    0   hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
      3    1   hda1 35486 38030 38030 38030
Linus Torvalds's avatar
Linus Torvalds committed
33

34 35 36
On 2.4 you might execute ``grep 'hda ' /proc/partitions``. On 2.6+, you have
a choice of ``cat /sys/block/hda/stat`` or ``grep 'hda ' /proc/diskstats``.

Linus Torvalds's avatar
Linus Torvalds committed
37
The advantage of one over the other is that the sysfs choice works well
38
if you are watching a known, small set of disks.  ``/proc/diskstats`` may
Linus Torvalds's avatar
Linus Torvalds committed
39 40 41 42 43 44
be a better choice if you are watching a large number of disks because
you'll avoid the overhead of 50, 100, or 500 or more opens/closes with
each snapshot of your disk statistics.

In 2.4, the statistics fields are those after the device name. In
the above example, the first field of statistics would be 446216.
45
By contrast, in 2.6+ if you look at ``/sys/block/hda/stat``, you'll
Linus Torvalds's avatar
Linus Torvalds committed
46
find just the eleven fields, beginning with 446216.  If you look at
47
``/proc/diskstats``, the eleven fields will be preceded by the major and
48
minor device numbers, and device name.  Each of these formats provides
Linus Torvalds's avatar
Linus Torvalds committed
49 50
eleven fields of statistics, each meaning exactly the same things.
All fields except field 9 are cumulative since boot.  Field 9 should
51 52 53
go to zero as I/Os complete; all others only increase (unless they
overflow and wrap).  Yes, these are (32-bit or 64-bit) unsigned long
(native word size) numbers, and on a very busy or long-lived system they
Linus Torvalds's avatar
Linus Torvalds committed
54 55 56 57 58 59 60
may wrap. Applications should be prepared to deal with that; unless
your observations are measured in large numbers of minutes or hours,
they should not wrap twice before you notice them.

Each set of stats only applies to the indicated device; if you want
system-wide stats you'll have to find all the devices and sum them all up.

61
Field  1 -- # of reads completed
Linus Torvalds's avatar
Linus Torvalds committed
62
    This is the total number of reads completed successfully.
63

Linus Torvalds's avatar
Linus Torvalds committed
64 65 66 67 68
Field  2 -- # of reads merged, field 6 -- # of writes merged
    Reads and writes which are adjacent to each other may be merged for
    efficiency.  Thus two 4K reads may become one 8K read before it is
    ultimately handed to the disk, and so it will be counted (and queued)
    as only one I/O.  This field lets you know how often this was done.
69

Linus Torvalds's avatar
Linus Torvalds committed
70 71
Field  3 -- # of sectors read
    This is the total number of sectors read successfully.
72

Linus Torvalds's avatar
Linus Torvalds committed
73 74 75
Field  4 -- # of milliseconds spent reading
    This is the total number of milliseconds spent by all reads (as
    measured from __make_request() to end_that_request_last()).
76

Linus Torvalds's avatar
Linus Torvalds committed
77 78
Field  5 -- # of writes completed
    This is the total number of writes completed successfully.
79

80 81
Field  6 -- # of writes merged
    See the description of field 2.
82

Linus Torvalds's avatar
Linus Torvalds committed
83 84
Field  7 -- # of sectors written
    This is the total number of sectors written successfully.
85

Linus Torvalds's avatar
Linus Torvalds committed
86 87 88
Field  8 -- # of milliseconds spent writing
    This is the total number of milliseconds spent by all writes (as
    measured from __make_request() to end_that_request_last()).
89

Linus Torvalds's avatar
Linus Torvalds committed
90 91
Field  9 -- # of I/Os currently in progress
    The only field that should go to zero. Incremented as requests are
92
    given to appropriate struct request_queue and decremented as they finish.
93

Linus Torvalds's avatar
Linus Torvalds committed
94
Field 10 -- # of milliseconds spent doing I/Os
95
    This field increases so long as field 9 is nonzero.
96

Linus Torvalds's avatar
Linus Torvalds committed
97 98 99 100 101 102 103 104 105 106 107 108 109 110
Field 11 -- weighted # of milliseconds spent doing I/Os
    This field is incremented at each I/O start, I/O completion, I/O
    merge, or read of these stats by the number of I/Os in progress
    (field 9) times the number of milliseconds spent doing I/O since the
    last update of this field.  This can provide an easy measure of both
    I/O completion time and the backlog that may be accumulating.


To avoid introducing performance bottlenecks, no locks are held while
modifying these counters.  This implies that minor inaccuracies may be
introduced when changes collide, so (for instance) adding up all the
read I/Os issued per partition should equal those made to the disks ...
but due to the lack of locking it may only be very close.

111
In 2.6+, there are counters for each CPU, which make the lack of locking
112 113
almost a non-issue.  When the statistics are read, the per-CPU counters
are summed (possibly overflowing the unsigned long variable they are
Linus Torvalds's avatar
Linus Torvalds committed
114
summed to) and the result given to the user.  There is no convenient
115
user interface for accessing the per-CPU counters themselves.
Linus Torvalds's avatar
Linus Torvalds committed
116 117 118 119

Disks vs Partitions
-------------------

120
There were significant changes between 2.4 and 2.6+ in the I/O subsystem.
Linus Torvalds's avatar
Linus Torvalds committed
121 122 123 124
As a result, some statistic information disappeared. The translation from
a disk address relative to a partition to the disk address relative to
the host disk happens much earlier.  All merges and timings now happen
at the disk level rather than at both the disk and partition level as
125
in 2.4.  Consequently, you'll see a different statistics output on 2.6+ for
Linus Torvalds's avatar
Linus Torvalds committed
126
partitions from that for disks.  There are only *four* fields available
127
for partitions on 2.6+ machines.  This is reflected in the examples above.
Linus Torvalds's avatar
Linus Torvalds committed
128 129 130

Field  1 -- # of reads issued
    This is the total number of reads issued to this partition.
131

Linus Torvalds's avatar
Linus Torvalds committed
132 133 134
Field  2 -- # of sectors read
    This is the total number of sectors requested to be read from this
    partition.
135

Linus Torvalds's avatar
Linus Torvalds committed
136 137
Field  3 -- # of writes issued
    This is the total number of writes issued to this partition.
138

Linus Torvalds's avatar
Linus Torvalds committed
139 140 141 142 143 144 145 146 147 148 149
Field  4 -- # of sectors written
    This is the total number of sectors requested to be written to
    this partition.

Note that since the address is translated to a disk-relative one, and no
record of the partition-relative address is kept, the subsequent success
or failure of the read cannot be attributed to the partition.  In other
words, the number of reads for partitions is counted slightly before time
of queuing for partitions, and at completion for whole disks.  This is
a subtle distinction that is probably uninteresting for most cases.

150 151 152 153 154 155 156 157 158 159 160
More significant is the error induced by counting the numbers of
reads/writes before merges for partitions and after for disks. Since a
typical workload usually contains a lot of successive and adjacent requests,
the number of reads/writes issued can be several times higher than the
number of reads/writes completed.

In 2.6.25, the full statistic set is again available for partitions and
disk and partition statistics are consistent again. Since we still don't
keep record of the partition-relative address, an operation is attributed to
the partition which contains the first sector of the request after the
eventual merges. As requests can be merged across partition, this could lead
161
to some (probably insignificant) inaccuracy.
162

Linus Torvalds's avatar
Linus Torvalds committed
163 164 165
Additional notes
----------------

166
In 2.6+, sysfs is not mounted by default.  If your distribution of
Linus Torvalds's avatar
Linus Torvalds committed
167
Linux hasn't added it already, here's the line you'll want to add to
168
your ``/etc/fstab``::
Linus Torvalds's avatar
Linus Torvalds committed
169

170
	none /sys sysfs defaults 0 0
Linus Torvalds's avatar
Linus Torvalds committed
171 172


173 174 175
In 2.6+, all disk statistics were removed from ``/proc/stat``.  In 2.4, they
appear in both ``/proc/partitions`` and ``/proc/stat``, although the ones in
``/proc/stat`` take a very different format from those in ``/proc/partitions``
Linus Torvalds's avatar
Linus Torvalds committed
176 177 178
(see proc(5), if your system has it.)

-- ricklind@us.ibm.com