1 perf-sched(1) 1 perf-sched(1)
2 ============= !! 2 ==============
3 3
4 NAME 4 NAME
5 ---- 5 ----
6 perf-sched - Tool to trace/measure scheduler p 6 perf-sched - Tool to trace/measure scheduler properties (latencies)
7 7
8 SYNOPSIS 8 SYNOPSIS
9 -------- 9 --------
10 [verse] 10 [verse]
11 'perf sched' {record|latency|map|replay|script 11 'perf sched' {record|latency|map|replay|script|timehist}
12 12
13 DESCRIPTION 13 DESCRIPTION
14 ----------- 14 -----------
15 There are several variants of 'perf sched': 15 There are several variants of 'perf sched':
16 16
17 'perf sched record <command>' to record the 17 'perf sched record <command>' to record the scheduling events
18 of an arbitrary workload. 18 of an arbitrary workload.
19 19
20 'perf sched latency' to report the per task 20 'perf sched latency' to report the per task scheduling latencies
21 and other scheduling properties of the workl 21 and other scheduling properties of the workload.
22 22
23 Example usage: <<
24 perf sched record -- sleep 1 <<
25 perf sched latency <<
26 <<
27 -------------------------------------------- <<
28 Task | Runtime ms | Cou <<
29 -------------------------------------------- <<
30 perf:(2) | 2.804 ms | <<
31 NetworkManager:1343 | 0.372 ms | <<
32 kworker/1:2-xfs:4649 | 0.012 ms | <<
33 kworker/3:1-xfs:388 | 0.011 ms | <<
34 sleep:147736 | 0.938 ms | <<
35 <<
36 It shows Runtime(time that a task spent actu <<
37 Count(number of times a delay was calculated <<
38 task was ready to run but was kept waiting). <<
39 <<
40 Tasks with the same command name are merged <<
41 given within (), However if -p option is use <<
42 <<
43 'perf sched script' to see a detailed trace 23 'perf sched script' to see a detailed trace of the workload that
44 was recorded (aliased to 'perf script' for 24 was recorded (aliased to 'perf script' for now).
45 25
46 'perf sched replay' to simulate the workload 26 'perf sched replay' to simulate the workload that was recorded
47 via perf sched record. (this is done by star 27 via perf sched record. (this is done by starting up mockup threads
48 that mimic the workload based on the events 28 that mimic the workload based on the events in the trace. These
49 threads can then replay the timings (CPU run 29 threads can then replay the timings (CPU runtime and sleep patterns)
50 of the workload as it occurred when it was r 30 of the workload as it occurred when it was recorded - and can repeat
51 it a number of times, measuring its performa 31 it a number of times, measuring its performance.)
52 32
53 'perf sched map' to print a textual context- 33 'perf sched map' to print a textual context-switching outline of
54 workload captured via perf sched record. Co 34 workload captured via perf sched record. Columns stand for
55 individual CPUs, and the two-letter shortcut 35 individual CPUs, and the two-letter shortcuts stand for tasks that
56 are running on a CPU. A '*' denotes the CPU 36 are running on a CPU. A '*' denotes the CPU that had the event, and
57 a dot signals an idle CPU. 37 a dot signals an idle CPU.
58 38
59 'perf sched timehist' provides an analysis o 39 'perf sched timehist' provides an analysis of scheduling events.
60 40
61 Example usage: 41 Example usage:
62 perf sched record -- sleep 1 42 perf sched record -- sleep 1
63 perf sched timehist 43 perf sched timehist
64 44
65 By default it shows the individual schedule 45 By default it shows the individual schedule events, including the wait
66 time (time between sched-out and next sched 46 time (time between sched-out and next sched-in events for the task), the
67 task scheduling delay (time between runnabl !! 47 task scheduling delay (time between wakeup and actually running) and run
68 run time for the task: !! 48 time for the task:
69 49
70 time cpu task name 50 time cpu task name wait time sch delay run time
71 [tid/pid] 51 [tid/pid] (msec) (msec) (msec)
72 -------------- ------ ----------------- 52 -------------- ------ -------------------- --------- --------- ---------
73 79371.874569 [0011] gcc[31949] 53 79371.874569 [0011] gcc[31949] 0.014 0.000 1.148
74 79371.874591 [0010] gcc[31951] 54 79371.874591 [0010] gcc[31951] 0.000 0.000 0.024
75 79371.874603 [0010] migration/10[59] 55 79371.874603 [0010] migration/10[59] 3.350 0.004 0.011
76 79371.874604 [0011] <idle> 56 79371.874604 [0011] <idle> 1.148 0.000 0.035
77 79371.874723 [0005] <idle> 57 79371.874723 [0005] <idle> 0.016 0.000 1.383
78 79371.874746 [0005] gcc[31949] 58 79371.874746 [0005] gcc[31949] 0.153 0.078 0.022
79 ... 59 ...
80 60
81 Times are in msec.usec. 61 Times are in msec.usec.
82 62
83 OPTIONS 63 OPTIONS
84 ------- 64 -------
85 -i:: 65 -i::
86 --input=<file>:: 66 --input=<file>::
87 Input file name. (default: perf.data u 67 Input file name. (default: perf.data unless stdin is a fifo)
88 68
89 -v:: 69 -v::
90 --verbose:: 70 --verbose::
91 Be more verbose. (show symbol address, 71 Be more verbose. (show symbol address, etc)
92 72
93 -D:: 73 -D::
94 --dump-raw-trace=:: 74 --dump-raw-trace=::
95 Display verbose dump of the sched data 75 Display verbose dump of the sched data.
96 76
97 -f:: 77 -f::
98 --force:: 78 --force::
99 Don't complain, do it. 79 Don't complain, do it.
100 80
101 OPTIONS for 'perf sched latency' <<
102 ------------------------------- <<
103 <<
104 -C:: <<
105 --CPU <n>:: <<
106 CPU to profile on. <<
107 <<
108 -p:: <<
109 --pids:: <<
110 latency stats per pid instead of per c <<
111 <<
112 -s:: <<
113 --sort <key[,key2...]>:: <<
114 sort by key(s): runtime, switch, avg, <<
115 by default it's sorted by "avg ,max ,s <<
116 <<
117 OPTIONS for 'perf sched map' 81 OPTIONS for 'perf sched map'
118 ---------------------------- 82 ----------------------------
119 83
120 --compact:: 84 --compact::
121 Show only CPUs with activity. Helps vi 85 Show only CPUs with activity. Helps visualizing on high core
122 count systems. 86 count systems.
123 87
124 --cpus:: 88 --cpus::
125 Show just entries with activities for 89 Show just entries with activities for the given CPUs.
126 90
127 --color-cpus:: 91 --color-cpus::
128 Highlight the given cpus. 92 Highlight the given cpus.
129 93
130 --color-pids:: 94 --color-pids::
131 Highlight the given pids. 95 Highlight the given pids.
132 96
133 --task-name <task>:: <<
134 Map output only for the given task nam <<
135 task names with a comma (without white <<
136 time is printed and is represented by <<
137 task name(s). <<
138 ('-' indicates other tasks while '.' i <<
139 <<
140 --fuzzy-name:: <<
141 Given task name(s) can be partially ma <<
142 <<
143 OPTIONS for 'perf sched timehist' 97 OPTIONS for 'perf sched timehist'
144 --------------------------------- 98 ---------------------------------
145 -k:: 99 -k::
146 --vmlinux=<file>:: 100 --vmlinux=<file>::
147 vmlinux pathname 101 vmlinux pathname
148 102
149 --kallsyms=<file>:: 103 --kallsyms=<file>::
150 kallsyms pathname 104 kallsyms pathname
151 105
152 -g:: 106 -g::
153 --call-graph:: !! 107 --no-call-graph::
154 Display call chains if present (defaul !! 108 Do not display call chains if present.
155 109
156 --max-stack:: 110 --max-stack::
157 Maximum number of functions to display 111 Maximum number of functions to display in backtrace, default 5.
158 112
159 -C=:: <<
160 --cpu=:: <<
161 Only show events for the given CPU(s) <<
162 <<
163 -p=:: 113 -p=::
164 --pid=:: 114 --pid=::
165 Only show events for given process ID 115 Only show events for given process ID (comma separated list).
166 116
167 -t=:: 117 -t=::
168 --tid=:: 118 --tid=::
169 Only show events for given thread ID ( 119 Only show events for given thread ID (comma separated list).
170 120
171 -s:: 121 -s::
172 --summary:: 122 --summary::
173 Show only a summary of scheduling by threa 123 Show only a summary of scheduling by thread with min, max, and average
174 run times (in sec) and relative stddev. 124 run times (in sec) and relative stddev.
175 125
176 -S:: 126 -S::
177 --with-summary:: 127 --with-summary::
178 Show all scheduling events followed by a s 128 Show all scheduling events followed by a summary by thread with min,
179 max, and average run times (in sec) and re 129 max, and average run times (in sec) and relative stddev.
180 130
181 --symfs=<directory>:: 131 --symfs=<directory>::
182 Look for files with symbols relative to th 132 Look for files with symbols relative to this directory.
183 133
184 -V:: 134 -V::
185 --cpu-visual:: 135 --cpu-visual::
186 Show visual aid for sched switches by 136 Show visual aid for sched switches by CPU: 'i' marks idle time,
187 's' are scheduler events. 137 's' are scheduler events.
188 138
189 -w:: 139 -w::
190 --wakeups:: 140 --wakeups::
191 Show wakeup events. 141 Show wakeup events.
192 142
193 -M:: 143 -M::
194 --migrations:: 144 --migrations::
195 Show migration events. 145 Show migration events.
196 146
197 -n:: 147 -n::
198 --next:: 148 --next::
199 Show next task. 149 Show next task.
200 150
201 -I:: 151 -I::
202 --idle-hist:: 152 --idle-hist::
203 Show idle-related events only. 153 Show idle-related events only.
204 154
205 --time:: 155 --time::
206 Only analyze samples within given time 156 Only analyze samples within given time window: <start>,<stop>. Times
207 have the format seconds.microseconds. 157 have the format seconds.microseconds. If start is not given (i.e., time
208 string is ',x.y') then analysis starts 158 string is ',x.y') then analysis starts at the beginning of the file. If
209 stop time is not given (i.e, time stri 159 stop time is not given (i.e, time string is 'x.y,') then analysis goes
210 to end of file. 160 to end of file.
211 161
212 --state:: 162 --state::
213 Show task state when it switched out. 163 Show task state when it switched out.
214 <<
215 --show-prio:: <<
216 Show task priority. <<
217 <<
218 --prio:: <<
219 Only show events for given task priori <<
220 provided as a comma-separated list wit <<
221 priorities are specified with -: 120-1 <<
222 provided: 0,120-129. <<
223 <<
224 OPTIONS for 'perf sched replay' <<
225 ------------------------------ <<
226 <<
227 -r:: <<
228 --repeat <n>:: <<
229 repeat the workload n times (0: infini <<
230 164
231 SEE ALSO 165 SEE ALSO
232 -------- 166 --------
233 linkperf:perf-record[1] 167 linkperf:perf-record[1]
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.