svcadm(8)을 검색하려면 섹션에서 8 을 선택하고, 맨 페이지 이름에 svcadm을 입력하고 검색을 누른다.
mpstat(8)
mpstat(8) System Administration Commands mpstat(8)
NAME
mpstat - report per-processor or per-processor-set statistics
SYNOPSIS
/usr/bin/mpstat [-amq] [-A core|soc|bins] [-f filter_str]
[-k keys] [-o num] [-p | -P set] [-T d | u] [-I statfile]
[-O statfile] [interval [count]]
DESCRIPTION
The mpstat command reports processor statistics in tabular form. Each
row of the table represents the activity of one processor. The first
table summarizes all activity since boot. Each subsequent table summa‐
rizes activity for the preceding interval. All values are rates listed
as events per second unless otherwise noted.
During execution of the kernel status command, the state of the kernel
can change. If relevant, a state change message is included in the mp‐
stat output, in one of the following forms:
<<processor 3 moved from pset: -1 to: 1>>
<<pset destroyed: 1>>
<<pset created: 1>>
<<processors added: 1, 3>>
<<processors removed: 1, 3>>
The mpstat command reports the following information:
CPU|SET|COR|SOC|BIN
CPU
Processor ID for which statistics are shown, when the -a and -A
options are omitted.
SET
Processor set ID for which statistics are aggregated, for the
-a option.
COR
Core ID for which statistics are aggregated, for the -A core
option.
SOC
Socket ID for which statistics are aggregated, for the -A soc
option.
BIN
Bin ordinal for which statistics are aggregated, for the -A
bins option.
minf
minor faults
mjf
major faults
xcal
inter-processor cross-calls
intr
interrupts
ithr
interrupts as threads (not counting clock interrupt)
csw
context switches
icsw
involuntary context switches
migr
thread migrations (to another processor)
smtx
spins on mutexes (lock not acquired on first try)
srw
spins on readers/writer locks (lock not acquired on first try)
syscl
system calls
usr
percent user time
sys
percent system time
st
percent of CPU time which was taken off by the hypervisor. Always
zero when running on physical hardware.
idl
percent idle time
sze
number of processors in the requested processor set
set
processor set membership of each CPU
OPTIONS
The following options are supported:
-a
Aggregate output by processor set. Sort the output by set. The de‐
fault output is sorted by CPU number.
-A core
Aggregate CPU output by core ID. Data rows having the same core ID
are aggregated into one row. The columns are replaced with subto‐
tals, by default. The -m option prints column averages, instead.
The -A option is incompatible with the -a option for aggregating by
processor set.
-A soc
Aggregate CPU output by socket ID. Data rows having the same socket
ID are aggregated into one row. The columns are replaced with
subtotals, by default. The -m option prints column averages, in‐
stead.
The -A option is incompatible with the -a option for aggregating by
processor set.
-A bins
Aggregate the rows into bins within each sampling period, grouping
them in the order in which they appear, and aggregate over rows for
each bin. The -k option may be used to change the row order prior
to the binning step. The sze column prints the number of CPUs in
each bin. The BIN column replaces the CPU column and prints the or‐
dinal of each bin.
Aggregation by ID (-A core|soc) is processed before sorting (-k).
Grouping by bins (-A bins) is done next. Finally, the number of
output lines printed per interval may be limited by -o.
The -A option is incompatible with the -a option for aggregating by
processor set.
See the NOTES section for the order in which the -A, -m, -f, -k,
and -o operations are performed.
-f filter_str
Print only those rows matching the filter string. The filter string
consists of a symbolic left operand, an operator, and a numeric
right operand. The non-case-sensitive left operand must be one of
the following (includes all column headers):
soc core cpu minf mjf xcal intr ithr csw
icsw migr smtx srw syscl usr sys st idl
The operator may be >=, >, <=, <, ==, or !=. The right operand must
be a non-negative integer. Whitespace is ignored.
More than one filter may be given by passing multiple -f options.
The filter conditions are always ANDed together to produce the fi‐
nal output.
See the NOTES section for the order in which the -A, -m, -f, -k,
and -o operations are performed.
-I statfile
Replay data previously saved in statfile. Create data files for re‐
play by specifying -O. This option is especially useful for analyz‐
ing statistics on machines with large numbers of CPUs. The file may
be reprocessed multiple times using different sorting and aggrega‐
tion options.
The -I option is incompatible with an interval and count specifica‐
tion.
Read from the standard input if the file name is — (hyphen).
-k key1,...
Sort rows within each sampling period from highest to lowest by
key1, then key2, and so on. Each key may be any of the column head‐
ers such as xcal, intr, sys, and so forth.
See the NOTES section for the order in which the -A, -m, -f, -k,
and -o operations are performed.
-m
Print the arithmetic mean value rather than the sum when the -a or
-A options are used to aggregate data over multiple CPUs.
See the NOTES section for the order in which the -A, -m, -f, -k,
and -o operations are performed.
-o num
Print only the first num rows within each sampling period, after
applying sorting and aggregation options.
See the NOTES section for the order in which the -A, -m, -f, -k,
and -o operations are performed.
-O statfile
Save all data to statfile. This data may be replayed at a later
time using -I.
Write to the standard output if the file name is — (hyphen).
The purpose of -O is to capture all available data. It is incompat‐
ible with the data reduction options: -a, -A, -f, -k, -m, -o, -p,
and -P.
-p
Report processor set membership of each CPU. Sort the output by
set. The default output is sorted by CPU number.
-P set
Display only those processors in the specified set.
-q
Suppress messages related to state changes.
-T u | d
Specify u for a printed representation of the internal representa‐
tion of time. See time(2). Specify d for standard date format. See
date(1).
interval
Report once each interval seconds.
count
Only print count reports.
EXAMPLES
On displays of 80-character width, example output below wraps by one to
seven characters. By making a window wider, you can eliminate this
wrap.
Example 1 Using mpstat to Generate User and System Operation Statistics
The following command generates processor statistics over a five-second
interval in two reports. The command shows the processor set membership
of each CPU. The default output is sorted by CPU number, aggregated by
processor set, for user (usr) and system (sys) operations.
example% mpstat -ap 5 2
SET minf mjf xcal intr ithr csw icsw migr smtx srw syscl usr sys st idl sze
0 6 0 355 291 190 22 0 0 0 0 43 0 2 0 43 1
1 24 17 534 207 200 70 1 0 2 0 600 4 1 1 83 2
2 19 7 353 325 318 44 0 0 5 0 345 1 1 0 94 3
3 36 2 149 237 236 14 0 0 4 0 97 0 0 0 98 2
SET minf mjf xcal intr ithr csw icsw migr smtx srw syscl usr sys st idl sze
0 1 0 720 405 304 55 0 0 18 0 12 0 15 0 81 1
1 0 69 1955 230 200 313 33 4 41 9 7086 34 10 0 19 2
2 0 46 685 314 300 203 11 0 54 1 5287 36 6 2 26 3
3 0 0 14 386 384 0 0 0 0 0 0 0 0 0 100 2
Example 2 Displaying CPUs That Meet Filter Requirement
The following command displays the three CPUs with the highest intr
rates.
example% mpstat -k intr -o 3
CPU minf mjf xcal intr ithr csw icsw migr smtx srw syscl usr sys st idl
56 1143 5 975 4238 82 465 74 53 124 0 198163 42 17 1 40
123 1189 6 1315 1030 890 461 65 53 122 0 24383 27 12 0 62
4 1184 5 1040 149 70 502 73 55 113 0 82039 31 13 0 56
Example 3 Aggregating Multiple CPUs into Quartiles
The following command aggregates 256 CPUs into quartiles by sys time.
example% mpstat -A 4 -k sys
BIN minf mjf xcal intr ithr csw icsw migr smtx srw syscl usr sys st idl sze
0 18 0 5811 7105 1 22154 17 9529 1176 0 72 1 79 1 18 64
1 0 0 4624 1006 12 1321 42 418 175 0 3591 36 37 0 27 64
2 1195 5 1056 92 10 526 74 56 104 0 45876 27 12 0 61 64
3 0 0 2 18 8 10 0 0 0 0 1 0 0 0 100 64
Example 4 Saving Statistics for Later Reprocessing
The following command saves statistics for later reprocessing and ag‐
gregates by core ID on a machine with eight CPUs per core.
example% mpstat -O /tmp/t1; mpstat -I /tmp/t1 -A core
COR minf mjf xcal intr ithr csw icsw migr smtx srw syscl usr sys st idl sze
514 0 0 124 45 0 21 0 3 1 0 0 0 3 0 97 8
521 0 0 16 5 0 1 0 0 0 0 0 0 0 1 99 8
528 0 0 11 5 0 3 0 0 0 0 0 0 0 0 100 8
535 0 0 7 4 0 1 0 0 0 0 0 0 0 0 100 8
542 0 0 7 4 0 1 0 0 0 0 0 0 0 0 100 8
549 0 0 10 4 0 1 0 0 0 0 0 0 0 0 100 8
556 0 0 10 5 0 1 0 0 0 0 0 0 0 0 100 8
563 0 0 8 4 0 1 0 0 0 0 0 0 0 0 100 8
Example 5 Showing Chips With High System Call Activity
The following command displays only those chips with over 10000 system
calls on record.
example% mpstat -A soc -f 'syscl > 10000'
SOC minf mjf xcal intr ithr csw icsw migr smtx srw syscl usr sys st idl sze
0 308 0 4089 2236 247 3415 36 550 3723 0 10113 312 46 0 1242 16
2 1849 0 5304 2723 40 4536 100 601 5916 0 39795 1194 144 0 4262 56
ATTRIBUTES
See attributes(7) for descriptions of the following attributes:
tab() box; cw(2.75i) |cw(2.75i) lw(2.75i) |lw(2.75i) ATTRIBUTE TYPEAT‐
TRIBUTE VALUE _ Availabilitysystem/core-os _ Interface StabilitySee be‐
low.
Invocation is evolving. Human readable output is unstable.
SEE ALSO
date(1), sar(1), time(2), attributes(7), iostat(8), sar(8), vmstat(8)
NOTES
The order in which the options -A, -m, -f, -k, and -o are applied is as
follows: Aggregation by ID (-A core|soc), mean (-m), filtering (-f),
sorting (-k), aggregation by bins (-A bins), and finally limiting the
number of output lines per interval (-o).
The sum of CPU utilization might vary slightly from 100 due to rounding
errors in the production of a percentage figure.
The total time used for CPU processing is the sum of usr and sys output
values, reported for user and system operations. The idl value reports
the time that the CPU is idle for any reason other than pending disk
I/O operations.
Run the iostat command with the -x option to report I/O service times
in svc_t output. The iostat utility also reports the same st, user
(us), and system (sy) statistics. See iostat(8) for more information.
When executing in a zone and if the pools facility is active, mpstat(8)
will only provide information for those processors which are a member
of the processor set of the pool to which the zone is bound.
Oracle Solaris 11.4 25 Jan 2016 mpstat(8)