1prstat(1M) System Administration Commands prstat(1M)
2
6 prstat - report active process statistics
7
9 prstat [-acHJLmRrtTv] [-d u | d] [-C psrsetlist] [-h lgrplist]
10 [-j projlist] [-k tasklist] [-n ntop[,nbottom]]
11 [-p pidlist] [-P cpulist] [-s key | -S key ]
12 [-u euidlist] [-U uidlist] [-z zoneidlist] [-Z]
13 [interval [count]]
14
17 The prstat utility iteratively examines all active processes on the
18 system and reports statistics based on the selected output mode and
19 sort order. prstat provides options to examine only processes matching
20 specified PIDs, UIDs, zone IDs, CPU IDs, and processor set IDs.
21 The -j, -k, -C, -p, -P, -u, -U, and -z options accept lists as argu‐
24 ments. Items in a list can be either separated by commas or enclosed in
25 quotes and separated by commas or spaces.
26 If you do not specify an option, prstat examines all processes and
29 reports statistics sorted by CPU usage.
30
32 The following options are supported:
33 -a
35 Report information about processes and users. In this mode prstat
37 displays separate reports about processes and users at the same
38 time.
39 -c
42 Print new reports below previous reports instead of overprinting
44 them.
45 -C psrsetlist
48 Report only processes or lwps that are bound to processor sets in
50 the given list. Each processor set is identified by an integer as
51 reported by psrset(1M). The load averages displayed are the sum of
52 the load averages of the specified processor sets (see pset_getloa‐
53 davg(3C)). Processes with one or more LWPs bound to processor sets
54 in the given list are reported even when the -L option is not used.
55 -d u | d
58 Specify u for a printed representation of the internal representa‐
60 tion of time. See time(2). Specify d for standard date format. See
61 date(1).
62 -h lgrplist
65 Report only processes or lwps whose home lgroup is in the given
67 list of lgroups. No processes or lwps will be listed for invalid
68 lgroups.
69 -H
72 Report information about home lgroup. In this mode, prstat adds an
74 extra column showing process or lwps home lgroup with the header
75 LGRP.
76 -j projlist
79 Report only processes or lwps whose project ID is in the given
81 list. Each project ID can be specified as either a project name or
82 a numerical project ID. See project(4).
83 -J
86 Report information about processes and projects. In this mode
88 prstat displays separate reports about processes and projects at
89 the same time.
90 -k tasklist
93 Report only processes or lwps whose task ID is in tasklist.
95 -L
98 Report statistics for each light-weight process (LWP). By default,
100 prstat reports only the number of LWPs for each process.
101 -m
104 Report microstate process accounting information. In addition to
106 all fields listed in -v mode, this mode also includes the percent‐
107 age of time the process has spent processing system traps, text
108 page faults, data page faults, waiting for user locks and waiting
109 for CPU (latency time).
110 -n ntop[,nbottom]
113 Restrict number of output lines. The ntop argument determines how
115 many lines of process or lwp statistics are reported, and the nbot‐
116 tom argument determines how many lines of user, task, or projects
117 statistics are reported if the -a, -t, -T, or -J options are speci‐
118 fied. By default, prstat displays as many lines of output that fit
119 in a window or terminal. When you specify the -c option or direct
120 the output to a file, the default values for ntop and nbottom are
121 15 and 5.
122 -p pidlist
125 Report only processes whose process ID is in the given list.
127 -P cpulist
130 Report only processes or lwps which have most recently executed on
132 a CPU in the given list. Each CPU is identified by an integer as
133 reported by psrinfo(1M).
134 -R
137 Put prstat in the real time scheduling class. When this option is
139 used, prstat is given priority over time-sharing and interactive
140 processes. This option is available only for superuser.
141 -r
144 Disable lookups for user names and project names. (Note that this
146 does not apply to lookups for the -j, -u, or -U options.)
147 -s key
150 Sort output lines (that is, processes, lwps, or users) by key in
152 descending order. Only one key can be used as an argument.
153 There are five possible key values:
155 cpu
157 Sort by process CPU usage. This is the default.
159 pri
162 Sort by process priority.
164 rss
167 Sort by resident set size.
169 size
172 Sort by size of process image.
174 time
177 Sort by process execution time.
179 -S key
183 Sort output lines by key in ascending order. Possible key values
185 are the same as for the -s option. See -s.
186 -t
189 Report total usage summary for each user. The summary includes the
191 total number of processes or LWPs owned by the user, total size of
192 process images, total resident set size, total cpu time, and per‐
193 centages of recent cpu time and system memory.
194 -T
197 Report information about processes and tasks. In this mode prstat
199 displays separate reports about processes and tasks at the same
200 time.
201 -u euidlist
204 Report only processes whose effective user ID is in the given list.
206 Each user ID may be specified as either a login name or a numerical
207 user ID.
208 -U uidlist
211 Report only processes whose real user ID is in the given list. Each
213 user ID may be specified as either a login name or a numerical user
214 ID.
215 -v
218 Report verbose process usage. This output format includes the per‐
220 centage of time the process has spent in user mode, in system mode,
221 and sleeping. It also includes the number of voluntary and involun‐
222 tary context switches, system calls and the number of signals
223 received. Statistics that are not reported are marked with the -
224 sign.
225 -z zoneidlist
228 Report only processes or LWPs whose zone ID is in the given list.
230 Each zone ID can be specified as either a zone name or a numerical
231 zone ID. See zones(5).
232 -Z
235 Report information about processes and zones. In this mode, prstat
237 displays separate reports about processes and zones at the same
238 time.
239
242 The following list defines the column headings and the meanings of a
243 prstat report:
244 PID
246 The process ID of the process.
248 USERNAME
251 The real user (login) name or real user ID.
253 SWAP
256 The total virtual memory size of the process, including all mapped
258 files and devices, in kilobytes (K), megabytes (M), or gigabytes
259 (G).
260 RSS
263 The resident set size of the process (RSS), in kilobytes (K),
265 megabytes (M), or gigabytes (G). The RSS value is an estimate pro‐
266 vided by proc(4) that might underestimate the actual resident set
267 size. Users who want to get more accurate usage information for
268 capacity planning should use the -x option to pmap(1) instead.
269 STATE
272 The state of the process:
274 cpuN
276 Process is running on CPU N.
278 sleep
281 Sleeping: process is waiting for an event to complete.
283 wait
286 Waiting: process is waiting for CPU usage to drop to the CPU-
288 caps enforced limits. See the description of CPU-caps in
289 resource_controls(5).
290 run
293 Runnable: process in on run queue.
295 zombie
298 Zombie state: process terminated and parent not waiting.
300 stop
303 Process is stopped.
305 PRI
309 The priority of the process. Larger numbers mean higher priority.
311 NICE
314 Nice value used in priority computation. Only processes in certain
316 scheduling classes have a nice value.
317 TIME
320 The cumulative execution time for the process.
322 CPU
325 The percentage of recent CPU time used by the process. If executing
327 in a non-global zone and the pools facility is active, the percent‐
328 age will be that of the processors in the processor set in use by
329 the pool to which the zone is bound.
330 PROCESS
333 The name of the process (name of executed file).
335 LWPID
338 The lwp ID of the lwp being reported.
340 NLWP
343 The number of lwps in the process.
345 With the some options, in addition to a number of the column headings
349 shown above, there are:
350 NPROC
352 Number of processes in a specified collection.
354 MEMORY
357 Percentage of memory used by a specified collection of processes.
359 The following columns are displayed when the -v or -m option is speci‐
363 fied
364 USR
366 The percentage of time the process has spent in user mode.
368 SYS
371 The percentage of time the process has spent in system mode.
373 TRP
376 The percentage of time the process has spent in processing system
378 traps.
379 TFL
382 The percentage of time the process has spent processing text page
384 faults.
385 DFL
388 The percentage of time the process has spent processing data page
390 faults.
391 LCK
394 The percentage of time the process has spent waiting for user
396 locks.
397 SLP
400 The percentage of time the process has spent sleeping.
402 LAT
405 The percentage of time the process has spent waiting for CPU.
407 VCX
410 The number of voluntary context switches.
412 ICX
415 The number of involuntary context switches.
417 SCL
420 The number of system calls.
422 SIG
425 The number of signals received.
427 Under the -L option, one line is printed for each lwp in the process
431 and some reporting fields show the values for the lwp, not the process.
432 The following column is displayed when the -H option is specified:
435 LGRP
437 The home lgroup of the process or lwp.
439
442 The following operands are supported:
443 count
445 Specifies the number of times that the statistics are repeated. By
447 default, prstat reports statistics until a termination signal is
448 received.
449 interval
452 Specifies the sampling interval in seconds; the default interval is
454 5 seconds.
455
458 Example 1 Reporting the Five Most Active Super-User Processes
459 The following command reports the five most active super-user processes
462 running on CPU1 and CPU2:
463 example% prstat -u root -n 5 -P 1,2 1 1
466 PID USERNAME SWAP RSS STATE PRI NICE TIME CPU PROCESS/LWP
468 306 root 3024K 1448K sleep 58 0 0:00.00 0.3% sendmail/1
469 102 root 1600K 592K sleep 59 0 0:00.00 0.1% in.rdisc/1
470 250 root 1000K 552K sleep 58 0 0:00.00 0.0% utmpd/1
471 288 root 1720K 1032K sleep 58 0 0:00.00 0.0% sac/1
472 1 root 744K 168K sleep 58 0 0:00.00 0.0% init/1
473 TOTAL: 25, load averages: 0.05, 0.08, 0.12
474 Example 2 Displaying Verbose Process Usage Information
478 The following command displays verbose process usage information about
481 processes with lowest resident set sizes owned by users root and john.
482 example% prstat -S rss -n 5 -vc -u root,john
485 PID USERNAME USR SYS TRP TFL DFL LCK SLP LAT VCX ICX SCL SIG PROCESS/LWP
487 1 root 0.0 0.0 - - - - 100 - 0 0 0 0 init/1
488 102 root 0.0 0.0 - - - - 100 - 0 0 3 0 in.rdisc/1
489 250 root 0.0 0.0 - - - - 100 - 0 0 0 0 utmpd/1
490 1185 john 0.0 0.0 - - - - 100 - 0 0 0 0 csh/1
491 240 root 0.0 0.0 - - - - 100 - 0 0 0 0 powerd/4
492 TOTAL: 71, load averages: 0.02, 0.04, 0.08
493
498 The following exit values are returned:
499 0
501 Successful completion.
503 1
506 An error occurred.
508
511 See attributes(5) for descriptions of the following attributes:
512 ┌─────────────────────────────┬─────────────────────────────┐
517 │ ATTRIBUTE TYPE │ ATTRIBUTE VALUE │
518 ├─────────────────────────────┼─────────────────────────────┤
519 │Availability │SUNWcsu │
520 └─────────────────────────────┴─────────────────────────────┘
521
523 date(1), lgrpinfo(1), plgrp(1), proc(1), ps(1), time(2), psrinfo(1M),
524 psrset(1M), sar(1M), pset_getloadavg(3C), proc(4), project(4),
525 attributes(5), resource_controls(5), zones(5)
526
528 The snapshot of system usage displayed by prstat is true only for a
529 split-second, and it may not be accurate by the time it is displayed.
530 When the -m option is specified, prstat tries to turn on microstate
531 accounting for each process; the original state is restored when prstat
532 exits. See proc(4) for additional information about the microstate
533 accounting facility.
534 The total memory size reported in the SWAP and RSS columns for groups
537 of processes can sometimes overestimate the actual amount of memory
538 used by processes with shared memory segments.
539SunOS 5.11 25 Jun 2009 prstat(1M)