Version:  2.0.40 2.2.26 2.4.37 3.13 3.14 3.15 3.16 3.17 3.18 3.19 4.0 4.1 4.2 4.3 4.4 4.5 4.6 4.7 4.8 4.9 4.10

Linux/Documentation/iostats.txt

  1 I/O statistics fields
  2 ---------------
  3 
  4 Since 2.4.20 (and some versions before, with patches), and 2.5.45,
  5 more extensive disk statistics have been introduced to help measure disk
  6 activity. Tools such as sar and iostat typically interpret these and do
  7 the work for you, but in case you are interested in creating your own
  8 tools, the fields are explained here.
  9 
 10 In 2.4 now, the information is found as additional fields in
 11 /proc/partitions.  In 2.6, the same information is found in two
 12 places: one is in the file /proc/diskstats, and the other is within
 13 the sysfs file system, which must be mounted in order to obtain
 14 the information. Throughout this document we'll assume that sysfs
 15 is mounted on /sys, although of course it may be mounted anywhere.
 16 Both /proc/diskstats and sysfs use the same source for the information
 17 and so should not differ.
 18 
 19 Here are examples of these different formats:
 20 
 21 2.4:
 22    3     0   39082680 hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
 23    3     1    9221278 hda1 35486 0 35496 38030 0 0 0 0 0 38030 38030
 24 
 25 
 26 2.6 sysfs:
 27    446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
 28    35486    38030    38030    38030
 29 
 30 2.6 diskstats:
 31    3    0   hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
 32    3    1   hda1 35486 38030 38030 38030
 33 
 34 On 2.4 you might execute "grep 'hda ' /proc/partitions". On 2.6, you have
 35 a choice of "cat /sys/block/hda/stat" or "grep 'hda ' /proc/diskstats".
 36 The advantage of one over the other is that the sysfs choice works well
 37 if you are watching a known, small set of disks.  /proc/diskstats may
 38 be a better choice if you are watching a large number of disks because
 39 you'll avoid the overhead of 50, 100, or 500 or more opens/closes with
 40 each snapshot of your disk statistics.
 41 
 42 In 2.4, the statistics fields are those after the device name. In
 43 the above example, the first field of statistics would be 446216.
 44 By contrast, in 2.6 if you look at /sys/block/hda/stat, you'll
 45 find just the eleven fields, beginning with 446216.  If you look at
 46 /proc/diskstats, the eleven fields will be preceded by the major and
 47 minor device numbers, and device name.  Each of these formats provides
 48 eleven fields of statistics, each meaning exactly the same things.
 49 All fields except field 9 are cumulative since boot.  Field 9 should
 50 go to zero as I/Os complete; all others only increase (unless they
 51 overflow and wrap).  Yes, these are (32-bit or 64-bit) unsigned long
 52 (native word size) numbers, and on a very busy or long-lived system they
 53 may wrap. Applications should be prepared to deal with that; unless
 54 your observations are measured in large numbers of minutes or hours,
 55 they should not wrap twice before you notice them.
 56 
 57 Each set of stats only applies to the indicated device; if you want
 58 system-wide stats you'll have to find all the devices and sum them all up.
 59 
 60 Field  1 -- # of reads completed
 61     This is the total number of reads completed successfully.
 62 Field  2 -- # of reads merged, field 6 -- # of writes merged
 63     Reads and writes which are adjacent to each other may be merged for
 64     efficiency.  Thus two 4K reads may become one 8K read before it is
 65     ultimately handed to the disk, and so it will be counted (and queued)
 66     as only one I/O.  This field lets you know how often this was done.
 67 Field  3 -- # of sectors read
 68     This is the total number of sectors read successfully.
 69 Field  4 -- # of milliseconds spent reading
 70     This is the total number of milliseconds spent by all reads (as
 71     measured from __make_request() to end_that_request_last()).
 72 Field  5 -- # of writes completed
 73     This is the total number of writes completed successfully.
 74 Field  6 -- # of writes merged
 75     See the description of field 2.
 76 Field  7 -- # of sectors written
 77     This is the total number of sectors written successfully.
 78 Field  8 -- # of milliseconds spent writing
 79     This is the total number of milliseconds spent by all writes (as
 80     measured from __make_request() to end_that_request_last()).
 81 Field  9 -- # of I/Os currently in progress
 82     The only field that should go to zero. Incremented as requests are
 83     given to appropriate struct request_queue and decremented as they finish.
 84 Field 10 -- # of milliseconds spent doing I/Os
 85     This field increases so long as field 9 is nonzero.
 86 Field 11 -- weighted # of milliseconds spent doing I/Os
 87     This field is incremented at each I/O start, I/O completion, I/O
 88     merge, or read of these stats by the number of I/Os in progress
 89     (field 9) times the number of milliseconds spent doing I/O since the
 90     last update of this field.  This can provide an easy measure of both
 91     I/O completion time and the backlog that may be accumulating.
 92 
 93 
 94 To avoid introducing performance bottlenecks, no locks are held while
 95 modifying these counters.  This implies that minor inaccuracies may be
 96 introduced when changes collide, so (for instance) adding up all the
 97 read I/Os issued per partition should equal those made to the disks ...
 98 but due to the lack of locking it may only be very close.
 99 
100 In 2.6, there are counters for each CPU, which make the lack of locking
101 almost a non-issue.  When the statistics are read, the per-CPU counters
102 are summed (possibly overflowing the unsigned long variable they are
103 summed to) and the result given to the user.  There is no convenient
104 user interface for accessing the per-CPU counters themselves.
105 
106 Disks vs Partitions
107 -------------------
108 
109 There were significant changes between 2.4 and 2.6 in the I/O subsystem.
110 As a result, some statistic information disappeared. The translation from
111 a disk address relative to a partition to the disk address relative to
112 the host disk happens much earlier.  All merges and timings now happen
113 at the disk level rather than at both the disk and partition level as
114 in 2.4.  Consequently, you'll see a different statistics output on 2.6 for
115 partitions from that for disks.  There are only *four* fields available
116 for partitions on 2.6 machines.  This is reflected in the examples above.
117 
118 Field  1 -- # of reads issued
119     This is the total number of reads issued to this partition.
120 Field  2 -- # of sectors read
121     This is the total number of sectors requested to be read from this
122     partition.
123 Field  3 -- # of writes issued
124     This is the total number of writes issued to this partition.
125 Field  4 -- # of sectors written
126     This is the total number of sectors requested to be written to
127     this partition.
128 
129 Note that since the address is translated to a disk-relative one, and no
130 record of the partition-relative address is kept, the subsequent success
131 or failure of the read cannot be attributed to the partition.  In other
132 words, the number of reads for partitions is counted slightly before time
133 of queuing for partitions, and at completion for whole disks.  This is
134 a subtle distinction that is probably uninteresting for most cases.
135 
136 More significant is the error induced by counting the numbers of
137 reads/writes before merges for partitions and after for disks. Since a
138 typical workload usually contains a lot of successive and adjacent requests,
139 the number of reads/writes issued can be several times higher than the
140 number of reads/writes completed.
141 
142 In 2.6.25, the full statistic set is again available for partitions and
143 disk and partition statistics are consistent again. Since we still don't
144 keep record of the partition-relative address, an operation is attributed to
145 the partition which contains the first sector of the request after the
146 eventual merges. As requests can be merged across partition, this could lead
147 to some (probably insignificant) inaccuracy.
148 
149 Additional notes
150 ----------------
151 
152 In 2.6, sysfs is not mounted by default.  If your distribution of
153 Linux hasn't added it already, here's the line you'll want to add to
154 your /etc/fstab:
155 
156 none /sys sysfs defaults 0 0
157 
158 
159 In 2.6, all disk statistics were removed from /proc/stat.  In 2.4, they
160 appear in both /proc/partitions and /proc/stat, although the ones in
161 /proc/stat take a very different format from those in /proc/partitions
162 (see proc(5), if your system has it.)
163 
164 -- ricklind@us.ibm.com

This page was automatically generated by LXR 0.3.1 (source).  •  Linux is a registered trademark of Linus Torvalds  •  Contact us