1 ======================== 1 ========================
2 ftrace - Function Tracer 2 ftrace - Function Tracer
3 ======================== 3 ========================
4 4
5 Copyright 2008 Red Hat Inc. 5 Copyright 2008 Red Hat Inc.
6 6
7 :Author: Steven Rostedt <srostedt@redhat.com> 7 :Author: Steven Rostedt <srostedt@redhat.com>
8 :License: The GNU Free Documentation License, 8 :License: The GNU Free Documentation License, Version 1.2
9 (dual licensed under the GPL v2) 9 (dual licensed under the GPL v2)
10 :Original Reviewers: Elias Oltmanns, Randy Du 10 :Original Reviewers: Elias Oltmanns, Randy Dunlap, Andrew Morton,
11 John Kacur, and David Te 11 John Kacur, and David Teigland.
12 12
13 - Written for: 2.6.28-rc2 13 - Written for: 2.6.28-rc2
14 - Updated for: 3.10 14 - Updated for: 3.10
15 - Updated for: 4.13 - Copyright 2017 VMware In 15 - Updated for: 4.13 - Copyright 2017 VMware Inc. Steven Rostedt
16 - Converted to rst format - Changbin Du <changb 16 - Converted to rst format - Changbin Du <changbin.du@intel.com>
17 17
18 Introduction 18 Introduction
19 ------------ 19 ------------
20 20
21 Ftrace is an internal tracer designed to help 21 Ftrace is an internal tracer designed to help out developers and
22 designers of systems to find what is going on 22 designers of systems to find what is going on inside the kernel.
23 It can be used for debugging or analyzing late 23 It can be used for debugging or analyzing latencies and
24 performance issues that take place outside of 24 performance issues that take place outside of user-space.
25 25
26 Although ftrace is typically considered the fu 26 Although ftrace is typically considered the function tracer, it
27 is really a framework of several assorted trac 27 is really a framework of several assorted tracing utilities.
28 There's latency tracing to examine what occurs 28 There's latency tracing to examine what occurs between interrupts
29 disabled and enabled, as well as for preemptio 29 disabled and enabled, as well as for preemption and from a time
30 a task is woken to the task is actually schedu 30 a task is woken to the task is actually scheduled in.
31 31
32 One of the most common uses of ftrace is the e 32 One of the most common uses of ftrace is the event tracing.
33 Throughout the kernel is hundreds of static ev 33 Throughout the kernel is hundreds of static event points that
34 can be enabled via the tracefs file system to 34 can be enabled via the tracefs file system to see what is
35 going on in certain parts of the kernel. 35 going on in certain parts of the kernel.
36 36
37 See events.rst for more information. 37 See events.rst for more information.
38 38
39 39
40 Implementation Details 40 Implementation Details
41 ---------------------- 41 ----------------------
42 42
43 See Documentation/trace/ftrace-design.rst for 43 See Documentation/trace/ftrace-design.rst for details for arch porters and such.
44 44
45 45
46 The File System 46 The File System
47 --------------- 47 ---------------
48 48
49 Ftrace uses the tracefs file system to hold th 49 Ftrace uses the tracefs file system to hold the control files as
50 well as the files to display output. 50 well as the files to display output.
51 51
52 When tracefs is configured into the kernel (wh 52 When tracefs is configured into the kernel (which selecting any ftrace
53 option will do) the directory /sys/kernel/trac 53 option will do) the directory /sys/kernel/tracing will be created. To mount
54 this directory, you can add to your /etc/fstab 54 this directory, you can add to your /etc/fstab file::
55 55
56 tracefs /sys/kernel/tracing trace 56 tracefs /sys/kernel/tracing tracefs defaults 0 0
57 57
58 Or you can mount it at run time with:: 58 Or you can mount it at run time with::
59 59
60 mount -t tracefs nodev /sys/kernel/tracing 60 mount -t tracefs nodev /sys/kernel/tracing
61 61
62 For quicker access to that directory you may w 62 For quicker access to that directory you may want to make a soft link to
63 it:: 63 it::
64 64
65 ln -s /sys/kernel/tracing /tracing 65 ln -s /sys/kernel/tracing /tracing
66 66
67 .. attention:: 67 .. attention::
68 68
69 Before 4.1, all ftrace tracing control files 69 Before 4.1, all ftrace tracing control files were within the debugfs
70 file system, which is typically located at / 70 file system, which is typically located at /sys/kernel/debug/tracing.
71 For backward compatibility, when mounting th 71 For backward compatibility, when mounting the debugfs file system,
72 the tracefs file system will be automaticall 72 the tracefs file system will be automatically mounted at:
73 73
74 /sys/kernel/debug/tracing 74 /sys/kernel/debug/tracing
75 75
76 All files located in the tracefs file system 76 All files located in the tracefs file system will be located in that
77 debugfs file system directory as well. 77 debugfs file system directory as well.
78 78
79 .. attention:: 79 .. attention::
80 80
81 Any selected ftrace option will also create 81 Any selected ftrace option will also create the tracefs file system.
82 The rest of the document will assume that yo 82 The rest of the document will assume that you are in the ftrace directory
83 (cd /sys/kernel/tracing) and will only conce 83 (cd /sys/kernel/tracing) and will only concentrate on the files within that
84 directory and not distract from the content 84 directory and not distract from the content with the extended
85 "/sys/kernel/tracing" path name. 85 "/sys/kernel/tracing" path name.
86 86
87 That's it! (assuming that you have ftrace conf 87 That's it! (assuming that you have ftrace configured into your kernel)
88 88
89 After mounting tracefs you will have access to 89 After mounting tracefs you will have access to the control and output files
90 of ftrace. Here is a list of some of the key f 90 of ftrace. Here is a list of some of the key files:
91 91
92 92
93 Note: all time values are in microseconds. 93 Note: all time values are in microseconds.
94 94
95 current_tracer: 95 current_tracer:
96 96
97 This is used to set or display the cur 97 This is used to set or display the current tracer
98 that is configured. Changing the curre 98 that is configured. Changing the current tracer clears
99 the ring buffer content as well as the 99 the ring buffer content as well as the "snapshot" buffer.
100 100
101 available_tracers: 101 available_tracers:
102 102
103 This holds the different types of trac 103 This holds the different types of tracers that
104 have been compiled into the kernel. Th 104 have been compiled into the kernel. The
105 tracers listed here can be configured 105 tracers listed here can be configured by
106 echoing their name into current_tracer 106 echoing their name into current_tracer.
107 107
108 tracing_on: 108 tracing_on:
109 109
110 This sets or displays whether writing 110 This sets or displays whether writing to the trace
111 ring buffer is enabled. Echo 0 into th 111 ring buffer is enabled. Echo 0 into this file to disable
112 the tracer or 1 to enable it. Note, th 112 the tracer or 1 to enable it. Note, this only disables
113 writing to the ring buffer, the tracin 113 writing to the ring buffer, the tracing overhead may
114 still be occurring. 114 still be occurring.
115 115
116 The kernel function tracing_off() can 116 The kernel function tracing_off() can be used within the
117 kernel to disable writing to the ring 117 kernel to disable writing to the ring buffer, which will
118 set this file to "0". User space can r 118 set this file to "0". User space can re-enable tracing by
119 echoing "1" into the file. 119 echoing "1" into the file.
120 120
121 Note, the function and event trigger " 121 Note, the function and event trigger "traceoff" will also
122 set this file to zero and stop tracing 122 set this file to zero and stop tracing. Which can also
123 be re-enabled by user space using this 123 be re-enabled by user space using this file.
124 124
125 trace: 125 trace:
126 126
127 This file holds the output of the trac 127 This file holds the output of the trace in a human
128 readable format (described below). Ope 128 readable format (described below). Opening this file for
129 writing with the O_TRUNC flag clears t 129 writing with the O_TRUNC flag clears the ring buffer content.
130 Note, this file is not a consumer. If 130 Note, this file is not a consumer. If tracing is off
131 (no tracer running, or tracing_on is z 131 (no tracer running, or tracing_on is zero), it will produce
132 the same output each time it is read. 132 the same output each time it is read. When tracing is on,
133 it may produce inconsistent results as 133 it may produce inconsistent results as it tries to read
134 the entire buffer without consuming it 134 the entire buffer without consuming it.
135 135
136 trace_pipe: 136 trace_pipe:
137 137
138 The output is the same as the "trace" 138 The output is the same as the "trace" file but this
139 file is meant to be streamed with live 139 file is meant to be streamed with live tracing.
140 Reads from this file will block until 140 Reads from this file will block until new data is
141 retrieved. Unlike the "trace" file, t 141 retrieved. Unlike the "trace" file, this file is a
142 consumer. This means reading from this 142 consumer. This means reading from this file causes
143 sequential reads to display more curre 143 sequential reads to display more current data. Once
144 data is read from this file, it is con 144 data is read from this file, it is consumed, and
145 will not be read again with a sequenti 145 will not be read again with a sequential read. The
146 "trace" file is static, and if the tra 146 "trace" file is static, and if the tracer is not
147 adding more data, it will display the 147 adding more data, it will display the same
148 information every time it is read. 148 information every time it is read.
149 149
150 trace_options: 150 trace_options:
151 151
152 This file lets the user control the am 152 This file lets the user control the amount of data
153 that is displayed in one of the above 153 that is displayed in one of the above output
154 files. Options also exist to modify ho 154 files. Options also exist to modify how a tracer
155 or events work (stack traces, timestam 155 or events work (stack traces, timestamps, etc).
156 156
157 options: 157 options:
158 158
159 This is a directory that has a file fo 159 This is a directory that has a file for every available
160 trace option (also in trace_options). 160 trace option (also in trace_options). Options may also be set
161 or cleared by writing a "1" or "0" res 161 or cleared by writing a "1" or "0" respectively into the
162 corresponding file with the option nam 162 corresponding file with the option name.
163 163
164 tracing_max_latency: 164 tracing_max_latency:
165 165
166 Some of the tracers record the max lat 166 Some of the tracers record the max latency.
167 For example, the maximum time that int 167 For example, the maximum time that interrupts are disabled.
168 The maximum time is saved in this file 168 The maximum time is saved in this file. The max trace will also be
169 stored, and displayed by "trace". A ne 169 stored, and displayed by "trace". A new max trace will only be
170 recorded if the latency is greater tha 170 recorded if the latency is greater than the value in this file
171 (in microseconds). 171 (in microseconds).
172 172
173 By echoing in a time into this file, n 173 By echoing in a time into this file, no latency will be recorded
174 unless it is greater than the time in 174 unless it is greater than the time in this file.
175 175
176 tracing_thresh: 176 tracing_thresh:
177 177
178 Some latency tracers will record a tra 178 Some latency tracers will record a trace whenever the
179 latency is greater than the number in 179 latency is greater than the number in this file.
180 Only active when the file contains a n 180 Only active when the file contains a number greater than 0.
181 (in microseconds) 181 (in microseconds)
182 182
183 buffer_percent: <<
184 <<
185 This is the watermark for how much the <<
186 before a waiter is woken up. That is, <<
187 blocking read syscall on one of the pe <<
188 will block until the given amount of d <<
189 is in the ring buffer before it wakes <<
190 controls how the splice system calls a <<
191 <<
192 0 - means to wake up as soon as th <<
193 50 - means to wake up when roughly <<
194 are full. <<
195 100 - means to block until the ring <<
196 about to start overwriting the <<
197 <<
198 buffer_size_kb: 183 buffer_size_kb:
199 184
200 This sets or displays the number of ki 185 This sets or displays the number of kilobytes each CPU
201 buffer holds. By default, the trace bu 186 buffer holds. By default, the trace buffers are the same size
202 for each CPU. The displayed number is 187 for each CPU. The displayed number is the size of the
203 CPU buffer and not total size of all b 188 CPU buffer and not total size of all buffers. The
204 trace buffers are allocated in pages ( 189 trace buffers are allocated in pages (blocks of memory
205 that the kernel uses for allocation, u 190 that the kernel uses for allocation, usually 4 KB in size).
206 A few extra pages may be allocated to 191 A few extra pages may be allocated to accommodate buffer management
207 meta-data. If the last page allocated 192 meta-data. If the last page allocated has room for more bytes
208 than requested, the rest of the page w 193 than requested, the rest of the page will be used,
209 making the actual allocation bigger th 194 making the actual allocation bigger than requested or shown.
210 ( Note, the size may not be a multiple 195 ( Note, the size may not be a multiple of the page size
211 due to buffer management meta-data. ) 196 due to buffer management meta-data. )
212 197
213 Buffer sizes for individual CPUs may v 198 Buffer sizes for individual CPUs may vary
214 (see "per_cpu/cpu0/buffer_size_kb" bel 199 (see "per_cpu/cpu0/buffer_size_kb" below), and if they do
215 this file will show "X". 200 this file will show "X".
216 201
217 buffer_total_size_kb: 202 buffer_total_size_kb:
218 203
219 This displays the total combined size 204 This displays the total combined size of all the trace buffers.
220 205
221 buffer_subbuf_size_kb: <<
222 <<
223 This sets or displays the sub buffer s <<
224 into several same size "sub buffers". <<
225 the size of the sub buffer. Normally, <<
226 architecture's page (4K on x86). The s <<
227 at the start which also limits the siz <<
228 the sub buffer is a page size, no even <<
229 size minus the sub buffer meta data. <<
230 <<
231 Note, the buffer_subbuf_size_kb is a w <<
232 minimum size of the subbuffer. The ker <<
233 implementation details, or simply fail <<
234 not handle the request. <<
235 <<
236 Changing the sub buffer size allows fo <<
237 page size. <<
238 <<
239 Note: When changing the sub-buffer siz <<
240 data in the ring buffer and the snapsh <<
241 <<
242 free_buffer: 206 free_buffer:
243 207
244 If a process is performing tracing, an 208 If a process is performing tracing, and the ring buffer should be
245 shrunk "freed" when the process is fin 209 shrunk "freed" when the process is finished, even if it were to be
246 killed by a signal, this file can be u 210 killed by a signal, this file can be used for that purpose. On close
247 of this file, the ring buffer will be 211 of this file, the ring buffer will be resized to its minimum size.
248 Having a process that is tracing also 212 Having a process that is tracing also open this file, when the process
249 exits its file descriptor for this fil 213 exits its file descriptor for this file will be closed, and in doing so,
250 the ring buffer will be "freed". 214 the ring buffer will be "freed".
251 215
252 It may also stop tracing if disable_on 216 It may also stop tracing if disable_on_free option is set.
253 217
254 tracing_cpumask: 218 tracing_cpumask:
255 219
256 This is a mask that lets the user only 220 This is a mask that lets the user only trace on specified CPUs.
257 The format is a hex string representin 221 The format is a hex string representing the CPUs.
258 222
259 set_ftrace_filter: 223 set_ftrace_filter:
260 224
261 When dynamic ftrace is configured in ( 225 When dynamic ftrace is configured in (see the
262 section below "dynamic ftrace"), the c 226 section below "dynamic ftrace"), the code is dynamically
263 modified (code text rewrite) to disabl 227 modified (code text rewrite) to disable calling of the
264 function profiler (mcount). This lets 228 function profiler (mcount). This lets tracing be configured
265 in with practically no overhead in per 229 in with practically no overhead in performance. This also
266 has a side effect of enabling or disab 230 has a side effect of enabling or disabling specific functions
267 to be traced. Echoing names of functio 231 to be traced. Echoing names of functions into this file
268 will limit the trace to only those fun 232 will limit the trace to only those functions.
269 This influences the tracers "function" 233 This influences the tracers "function" and "function_graph"
270 and thus also function profiling (see 234 and thus also function profiling (see "function_profile_enabled").
271 235
272 The functions listed in "available_fil 236 The functions listed in "available_filter_functions" are what
273 can be written into this file. 237 can be written into this file.
274 238
275 This interface also allows for command 239 This interface also allows for commands to be used. See the
276 "Filter commands" section for more det 240 "Filter commands" section for more details.
277 241
278 As a speed up, since processing string 242 As a speed up, since processing strings can be quite expensive
279 and requires a check of all functions 243 and requires a check of all functions registered to tracing, instead
280 an index can be written into this file 244 an index can be written into this file. A number (starting with "1")
281 written will instead select the same c 245 written will instead select the same corresponding at the line position
282 of the "available_filter_functions" fi 246 of the "available_filter_functions" file.
283 247
284 set_ftrace_notrace: 248 set_ftrace_notrace:
285 249
286 This has an effect opposite to that of 250 This has an effect opposite to that of
287 set_ftrace_filter. Any function that i 251 set_ftrace_filter. Any function that is added here will not
288 be traced. If a function exists in bot 252 be traced. If a function exists in both set_ftrace_filter
289 and set_ftrace_notrace, the function w 253 and set_ftrace_notrace, the function will _not_ be traced.
290 254
291 set_ftrace_pid: 255 set_ftrace_pid:
292 256
293 Have the function tracer only trace th 257 Have the function tracer only trace the threads whose PID are
294 listed in this file. 258 listed in this file.
295 259
296 If the "function-fork" option is set, 260 If the "function-fork" option is set, then when a task whose
297 PID is listed in this file forks, the 261 PID is listed in this file forks, the child's PID will
298 automatically be added to this file, a 262 automatically be added to this file, and the child will be
299 traced by the function tracer as well. 263 traced by the function tracer as well. This option will also
300 cause PIDs of tasks that exit to be re 264 cause PIDs of tasks that exit to be removed from the file.
301 265
302 set_ftrace_notrace_pid: 266 set_ftrace_notrace_pid:
303 267
304 Have the function tracer ignore thread 268 Have the function tracer ignore threads whose PID are listed in
305 this file. 269 this file.
306 270
307 If the "function-fork" option is set, 271 If the "function-fork" option is set, then when a task whose
308 PID is listed in this file forks, the 272 PID is listed in this file forks, the child's PID will
309 automatically be added to this file, a 273 automatically be added to this file, and the child will not be
310 traced by the function tracer as well. 274 traced by the function tracer as well. This option will also
311 cause PIDs of tasks that exit to be re 275 cause PIDs of tasks that exit to be removed from the file.
312 276
313 If a PID is in both this file and "set 277 If a PID is in both this file and "set_ftrace_pid", then this
314 file takes precedence, and the thread 278 file takes precedence, and the thread will not be traced.
315 279
316 set_event_pid: 280 set_event_pid:
317 281
318 Have the events only trace a task with 282 Have the events only trace a task with a PID listed in this file.
319 Note, sched_switch and sched_wake_up w 283 Note, sched_switch and sched_wake_up will also trace events
320 listed in this file. 284 listed in this file.
321 285
322 To have the PIDs of children of tasks 286 To have the PIDs of children of tasks with their PID in this file
323 added on fork, enable the "event-fork" 287 added on fork, enable the "event-fork" option. That option will also
324 cause the PIDs of tasks to be removed 288 cause the PIDs of tasks to be removed from this file when the task
325 exits. 289 exits.
326 290
327 set_event_notrace_pid: 291 set_event_notrace_pid:
328 292
329 Have the events not trace a task with 293 Have the events not trace a task with a PID listed in this file.
330 Note, sched_switch and sched_wakeup wi 294 Note, sched_switch and sched_wakeup will trace threads not listed
331 in this file, even if a thread's PID i 295 in this file, even if a thread's PID is in the file if the
332 sched_switch or sched_wakeup events al 296 sched_switch or sched_wakeup events also trace a thread that should
333 be traced. 297 be traced.
334 298
335 To have the PIDs of children of tasks 299 To have the PIDs of children of tasks with their PID in this file
336 added on fork, enable the "event-fork" 300 added on fork, enable the "event-fork" option. That option will also
337 cause the PIDs of tasks to be removed 301 cause the PIDs of tasks to be removed from this file when the task
338 exits. 302 exits.
339 303
340 set_graph_function: 304 set_graph_function:
341 305
342 Functions listed in this file will cau 306 Functions listed in this file will cause the function graph
343 tracer to only trace these functions a 307 tracer to only trace these functions and the functions that
344 they call. (See the section "dynamic f 308 they call. (See the section "dynamic ftrace" for more details).
345 Note, set_ftrace_filter and set_ftrace 309 Note, set_ftrace_filter and set_ftrace_notrace still affects
346 what functions are being traced. 310 what functions are being traced.
347 311
348 set_graph_notrace: 312 set_graph_notrace:
349 313
350 Similar to set_graph_function, but wil 314 Similar to set_graph_function, but will disable function graph
351 tracing when the function is hit until 315 tracing when the function is hit until it exits the function.
352 This makes it possible to ignore traci 316 This makes it possible to ignore tracing functions that are called
353 by a specific function. 317 by a specific function.
354 318
355 available_filter_functions: 319 available_filter_functions:
356 320
357 This lists the functions that ftrace h 321 This lists the functions that ftrace has processed and can trace.
358 These are the function names that you 322 These are the function names that you can pass to
359 "set_ftrace_filter", "set_ftrace_notra 323 "set_ftrace_filter", "set_ftrace_notrace",
360 "set_graph_function", or "set_graph_no 324 "set_graph_function", or "set_graph_notrace".
361 (See the section "dynamic ftrace" belo 325 (See the section "dynamic ftrace" below for more details.)
362 326
363 available_filter_functions_addrs: <<
364 <<
365 Similar to available_filter_functions, <<
366 for each function. The displayed addre <<
367 and can differ from /proc/kallsyms add <<
368 <<
369 dyn_ftrace_total_info: 327 dyn_ftrace_total_info:
370 328
371 This file is for debugging purposes. T 329 This file is for debugging purposes. The number of functions that
372 have been converted to nops and are av 330 have been converted to nops and are available to be traced.
373 331
374 enabled_functions: 332 enabled_functions:
375 333
376 This file is more for debugging ftrace 334 This file is more for debugging ftrace, but can also be useful
377 in seeing if any function has a callba 335 in seeing if any function has a callback attached to it.
378 Not only does the trace infrastructure 336 Not only does the trace infrastructure use ftrace function
379 trace utility, but other subsystems mi 337 trace utility, but other subsystems might too. This file
380 displays all functions that have a cal 338 displays all functions that have a callback attached to them
381 as well as the number of callbacks tha 339 as well as the number of callbacks that have been attached.
382 Note, a callback may also call multipl 340 Note, a callback may also call multiple functions which will
383 not be listed in this count. 341 not be listed in this count.
384 342
385 If the callback registered to be trace 343 If the callback registered to be traced by a function with
386 the "save regs" attribute (thus even m 344 the "save regs" attribute (thus even more overhead), a 'R'
387 will be displayed on the same line as 345 will be displayed on the same line as the function that
388 is returning registers. 346 is returning registers.
389 347
390 If the callback registered to be trace 348 If the callback registered to be traced by a function with
391 the "ip modify" attribute (thus the re 349 the "ip modify" attribute (thus the regs->ip can be changed),
392 an 'I' will be displayed on the same l 350 an 'I' will be displayed on the same line as the function that
393 can be overridden. 351 can be overridden.
394 352
395 If a non ftrace trampoline is attached <<
396 Note, normal ftrace trampolines can al <<
397 "direct" trampoline can be attached to <<
398 <<
399 Some architectures can not call direct <<
400 the ftrace ops function located above <<
401 such cases an 'O' will be displayed. <<
402 <<
403 If a function had either the "ip modif <<
404 it in the past, a 'M' will be shown. T <<
405 used to know if a function was every m <<
406 and can be used for debugging. <<
407 <<
408 If the architecture supports it, it wi 353 If the architecture supports it, it will also show what callback
409 is being directly called by the functi 354 is being directly called by the function. If the count is greater
410 than 1 it most likely will be ftrace_o 355 than 1 it most likely will be ftrace_ops_list_func().
411 356
412 If the callback of a function jumps to 357 If the callback of a function jumps to a trampoline that is
413 specific to the callback and which is 358 specific to the callback and which is not the standard trampoline,
414 its address will be printed as well as 359 its address will be printed as well as the function that the
415 trampoline calls. 360 trampoline calls.
416 361
417 touched_functions: <<
418 <<
419 This file contains all the functions t <<
420 to it via the ftrace infrastructure. I <<
421 enabled_functions but shows all functi <<
422 traced. <<
423 <<
424 To see any function that has every bee <<
425 direct trampoline, one can perform the <<
426 <<
427 grep ' M ' /sys/kernel/tracing/touched <<
428 <<
429 function_profile_enabled: 362 function_profile_enabled:
430 363
431 When set it will enable all functions 364 When set it will enable all functions with either the function
432 tracer, or if configured, the function 365 tracer, or if configured, the function graph tracer. It will
433 keep a histogram of the number of func 366 keep a histogram of the number of functions that were called
434 and if the function graph tracer was c 367 and if the function graph tracer was configured, it will also keep
435 track of the time spent in those funct 368 track of the time spent in those functions. The histogram
436 content can be displayed in the files: 369 content can be displayed in the files:
437 370
438 trace_stat/function<cpu> ( function0, 371 trace_stat/function<cpu> ( function0, function1, etc).
439 372
440 trace_stat: 373 trace_stat:
441 374
442 A directory that holds different traci 375 A directory that holds different tracing stats.
443 376
444 kprobe_events: 377 kprobe_events:
445 378
446 Enable dynamic trace points. See kprob 379 Enable dynamic trace points. See kprobetrace.rst.
447 380
448 kprobe_profile: 381 kprobe_profile:
449 382
450 Dynamic trace points stats. See kprobe 383 Dynamic trace points stats. See kprobetrace.rst.
451 384
452 max_graph_depth: 385 max_graph_depth:
453 386
454 Used with the function graph tracer. T 387 Used with the function graph tracer. This is the max depth
455 it will trace into a function. Setting 388 it will trace into a function. Setting this to a value of
456 one will show only the first kernel fu 389 one will show only the first kernel function that is called
457 from user space. 390 from user space.
458 391
459 printk_formats: 392 printk_formats:
460 393
461 This is for tools that read the raw fo 394 This is for tools that read the raw format files. If an event in
462 the ring buffer references a string, o 395 the ring buffer references a string, only a pointer to the string
463 is recorded into the buffer and not th 396 is recorded into the buffer and not the string itself. This prevents
464 tools from knowing what that string wa 397 tools from knowing what that string was. This file displays the string
465 and address for the string allowing to 398 and address for the string allowing tools to map the pointers to what
466 the strings were. 399 the strings were.
467 400
468 saved_cmdlines: 401 saved_cmdlines:
469 402
470 Only the pid of the task is recorded i 403 Only the pid of the task is recorded in a trace event unless
471 the event specifically saves the task 404 the event specifically saves the task comm as well. Ftrace
472 makes a cache of pid mappings to comms 405 makes a cache of pid mappings to comms to try to display
473 comms for events. If a pid for a comm 406 comms for events. If a pid for a comm is not listed, then
474 "<...>" is displayed in the output. 407 "<...>" is displayed in the output.
475 408
476 If the option "record-cmd" is set to " 409 If the option "record-cmd" is set to "0", then comms of tasks
477 will not be saved during recording. By 410 will not be saved during recording. By default, it is enabled.
478 411
479 saved_cmdlines_size: 412 saved_cmdlines_size:
480 413
481 By default, 128 comms are saved (see " 414 By default, 128 comms are saved (see "saved_cmdlines" above). To
482 increase or decrease the amount of com 415 increase or decrease the amount of comms that are cached, echo
483 the number of comms to cache into this 416 the number of comms to cache into this file.
484 417
485 saved_tgids: 418 saved_tgids:
486 419
487 If the option "record-tgid" is set, on 420 If the option "record-tgid" is set, on each scheduling context switch
488 the Task Group ID of a task is saved i 421 the Task Group ID of a task is saved in a table mapping the PID of
489 the thread to its TGID. By default, th 422 the thread to its TGID. By default, the "record-tgid" option is
490 disabled. 423 disabled.
491 424
492 snapshot: 425 snapshot:
493 426
494 This displays the "snapshot" buffer an 427 This displays the "snapshot" buffer and also lets the user
495 take a snapshot of the current running 428 take a snapshot of the current running trace.
496 See the "Snapshot" section below for m 429 See the "Snapshot" section below for more details.
497 430
498 stack_max_size: 431 stack_max_size:
499 432
500 When the stack tracer is activated, th 433 When the stack tracer is activated, this will display the
501 maximum stack size it has encountered. 434 maximum stack size it has encountered.
502 See the "Stack Trace" section below. 435 See the "Stack Trace" section below.
503 436
504 stack_trace: 437 stack_trace:
505 438
506 This displays the stack back trace of 439 This displays the stack back trace of the largest stack
507 that was encountered when the stack tr 440 that was encountered when the stack tracer is activated.
508 See the "Stack Trace" section below. 441 See the "Stack Trace" section below.
509 442
510 stack_trace_filter: 443 stack_trace_filter:
511 444
512 This is similar to "set_ftrace_filter" 445 This is similar to "set_ftrace_filter" but it limits what
513 functions the stack tracer will check. 446 functions the stack tracer will check.
514 447
515 trace_clock: 448 trace_clock:
516 449
517 Whenever an event is recorded into the 450 Whenever an event is recorded into the ring buffer, a
518 "timestamp" is added. This stamp comes 451 "timestamp" is added. This stamp comes from a specified
519 clock. By default, ftrace uses the "lo 452 clock. By default, ftrace uses the "local" clock. This
520 clock is very fast and strictly per cp 453 clock is very fast and strictly per cpu, but on some
521 systems it may not be monotonic with r 454 systems it may not be monotonic with respect to other
522 CPUs. In other words, the local clocks 455 CPUs. In other words, the local clocks may not be in sync
523 with local clocks on other CPUs. 456 with local clocks on other CPUs.
524 457
525 Usual clocks for tracing:: 458 Usual clocks for tracing::
526 459
527 # cat trace_clock 460 # cat trace_clock
528 [local] global counter x86-tsc 461 [local] global counter x86-tsc
529 462
530 The clock with the square brackets aro 463 The clock with the square brackets around it is the one in effect.
531 464
532 local: 465 local:
533 Default clock, but may not be 466 Default clock, but may not be in sync across CPUs
534 467
535 global: 468 global:
536 This clock is in sync with all 469 This clock is in sync with all CPUs but may
537 be a bit slower than the local 470 be a bit slower than the local clock.
538 471
539 counter: 472 counter:
540 This is not a clock at all, bu 473 This is not a clock at all, but literally an atomic
541 counter. It counts up one by o 474 counter. It counts up one by one, but is in sync
542 with all CPUs. This is useful 475 with all CPUs. This is useful when you need to
543 know exactly the order events 476 know exactly the order events occurred with respect to
544 each other on different CPUs. 477 each other on different CPUs.
545 478
546 uptime: 479 uptime:
547 This uses the jiffies counter 480 This uses the jiffies counter and the time stamp
548 is relative to the time since 481 is relative to the time since boot up.
549 482
550 perf: 483 perf:
551 This makes ftrace use the same 484 This makes ftrace use the same clock that perf uses.
552 Eventually perf will be able t 485 Eventually perf will be able to read ftrace buffers
553 and this will help out in inte 486 and this will help out in interleaving the data.
554 487
555 x86-tsc: 488 x86-tsc:
556 Architectures may define their 489 Architectures may define their own clocks. For
557 example, x86 uses its own TSC 490 example, x86 uses its own TSC cycle clock here.
558 491
559 ppc-tb: 492 ppc-tb:
560 This uses the powerpc timebase 493 This uses the powerpc timebase register value.
561 This is in sync across CPUs an 494 This is in sync across CPUs and can also be used
562 to correlate events across hyp 495 to correlate events across hypervisor/guest if
563 tb_offset is known. 496 tb_offset is known.
564 497
565 mono: 498 mono:
566 This uses the fast monotonic c 499 This uses the fast monotonic clock (CLOCK_MONOTONIC)
567 which is monotonic and is subj 500 which is monotonic and is subject to NTP rate adjustments.
568 501
569 mono_raw: 502 mono_raw:
570 This is the raw monotonic cloc 503 This is the raw monotonic clock (CLOCK_MONOTONIC_RAW)
571 which is monotonic but is not 504 which is monotonic but is not subject to any rate adjustments
572 and ticks at the same rate as 505 and ticks at the same rate as the hardware clocksource.
573 506
574 boot: 507 boot:
575 This is the boot clock (CLOCK_ 508 This is the boot clock (CLOCK_BOOTTIME) and is based on the
576 fast monotonic clock, but also 509 fast monotonic clock, but also accounts for time spent in
577 suspend. Since the clock acces 510 suspend. Since the clock access is designed for use in
578 tracing in the suspend path, s 511 tracing in the suspend path, some side effects are possible
579 if clock is accessed after the 512 if clock is accessed after the suspend time is accounted before
580 the fast mono clock is updated 513 the fast mono clock is updated. In this case, the clock update
581 appears to happen slightly soo 514 appears to happen slightly sooner than it normally would have.
582 Also on 32-bit systems, it's p 515 Also on 32-bit systems, it's possible that the 64-bit boot offset
583 sees a partial update. These e 516 sees a partial update. These effects are rare and post
584 processing should be able to h 517 processing should be able to handle them. See comments in the
585 ktime_get_boot_fast_ns() funct 518 ktime_get_boot_fast_ns() function for more information.
586 519
587 tai: 520 tai:
588 This is the tai clock (CLOCK_T 521 This is the tai clock (CLOCK_TAI) and is derived from the wall-
589 clock time. However, this cloc 522 clock time. However, this clock does not experience
590 discontinuities and backwards 523 discontinuities and backwards jumps caused by NTP inserting leap
591 seconds. Since the clock acces 524 seconds. Since the clock access is designed for use in tracing,
592 side effects are possible. The 525 side effects are possible. The clock access may yield wrong
593 readouts in case the internal 526 readouts in case the internal TAI offset is updated e.g., caused
594 by setting the system time or 527 by setting the system time or using adjtimex() with an offset.
595 These effects are rare and pos 528 These effects are rare and post processing should be able to
596 handle them. See comments in t 529 handle them. See comments in the ktime_get_tai_fast_ns()
597 function for more information. 530 function for more information.
598 531
599 To set a clock, simply echo the clock 532 To set a clock, simply echo the clock name into this file::
600 533
601 # echo global > trace_clock 534 # echo global > trace_clock
602 535
603 Setting a clock clears the ring buffer 536 Setting a clock clears the ring buffer content as well as the
604 "snapshot" buffer. 537 "snapshot" buffer.
605 538
606 trace_marker: 539 trace_marker:
607 540
608 This is a very useful file for synchro 541 This is a very useful file for synchronizing user space
609 with events happening in the kernel. W 542 with events happening in the kernel. Writing strings into
610 this file will be written into the ftr 543 this file will be written into the ftrace buffer.
611 544
612 It is useful in applications to open t 545 It is useful in applications to open this file at the start
613 of the application and just reference 546 of the application and just reference the file descriptor
614 for the file:: 547 for the file::
615 548
616 void trace_write(const char *f 549 void trace_write(const char *fmt, ...)
617 { 550 {
618 va_list ap; 551 va_list ap;
619 char buf[256]; 552 char buf[256];
620 int n; 553 int n;
621 554
622 if (trace_fd < 0) 555 if (trace_fd < 0)
623 return; 556 return;
624 557
625 va_start(ap, fmt); 558 va_start(ap, fmt);
626 n = vsnprintf(buf, 256 559 n = vsnprintf(buf, 256, fmt, ap);
627 va_end(ap); 560 va_end(ap);
628 561
629 write(trace_fd, buf, n 562 write(trace_fd, buf, n);
630 } 563 }
631 564
632 start:: 565 start::
633 566
634 trace_fd = open("trace_marker" !! 567 trace_fd = open("trace_marker", WR_ONLY);
635 568
636 Note: Writing into the trace_marker fi 569 Note: Writing into the trace_marker file can also initiate triggers
637 that are written into /sys/kerne 570 that are written into /sys/kernel/tracing/events/ftrace/print/trigger
638 See "Event triggers" in Document 571 See "Event triggers" in Documentation/trace/events.rst and an
639 example in Documentation/trace/h 572 example in Documentation/trace/histogram.rst (Section 3.)
640 573
641 trace_marker_raw: 574 trace_marker_raw:
642 575
643 This is similar to trace_marker above, 576 This is similar to trace_marker above, but is meant for binary data
644 to be written to it, where a tool can 577 to be written to it, where a tool can be used to parse the data
645 from trace_pipe_raw. 578 from trace_pipe_raw.
646 579
647 uprobe_events: 580 uprobe_events:
648 581
649 Add dynamic tracepoints in programs. 582 Add dynamic tracepoints in programs.
650 See uprobetracer.rst 583 See uprobetracer.rst
651 584
652 uprobe_profile: 585 uprobe_profile:
653 586
654 Uprobe statistics. See uprobetrace.txt 587 Uprobe statistics. See uprobetrace.txt
655 588
656 instances: 589 instances:
657 590
658 This is a way to make multiple trace b 591 This is a way to make multiple trace buffers where different
659 events can be recorded in different bu 592 events can be recorded in different buffers.
660 See "Instances" section below. 593 See "Instances" section below.
661 594
662 events: 595 events:
663 596
664 This is the trace event directory. It 597 This is the trace event directory. It holds event tracepoints
665 (also known as static tracepoints) tha 598 (also known as static tracepoints) that have been compiled
666 into the kernel. It shows what event t 599 into the kernel. It shows what event tracepoints exist
667 and how they are grouped by system. Th 600 and how they are grouped by system. There are "enable"
668 files at various levels that can enabl 601 files at various levels that can enable the tracepoints
669 when a "1" is written to them. 602 when a "1" is written to them.
670 603
671 See events.rst for more information. 604 See events.rst for more information.
672 605
673 set_event: 606 set_event:
674 607
675 By echoing in the event into this file 608 By echoing in the event into this file, will enable that event.
676 609
677 See events.rst for more information. 610 See events.rst for more information.
678 611
679 available_events: 612 available_events:
680 613
681 A list of events that can be enabled i 614 A list of events that can be enabled in tracing.
682 615
683 See events.rst for more information. 616 See events.rst for more information.
684 617
685 timestamp_mode: 618 timestamp_mode:
686 619
687 Certain tracers may change the timesta 620 Certain tracers may change the timestamp mode used when
688 logging trace events into the event bu 621 logging trace events into the event buffer. Events with
689 different modes can coexist within a b 622 different modes can coexist within a buffer but the mode in
690 effect when an event is logged determi 623 effect when an event is logged determines which timestamp mode
691 is used for that event. The default t 624 is used for that event. The default timestamp mode is
692 'delta'. 625 'delta'.
693 626
694 Usual timestamp modes for tracing: 627 Usual timestamp modes for tracing:
695 628
696 # cat timestamp_mode 629 # cat timestamp_mode
697 [delta] absolute 630 [delta] absolute
698 631
699 The timestamp mode with the square b 632 The timestamp mode with the square brackets around it is the
700 one in effect. 633 one in effect.
701 634
702 delta: Default timestamp mode - time 635 delta: Default timestamp mode - timestamp is a delta against
703 a per-buffer timestamp. 636 a per-buffer timestamp.
704 637
705 absolute: The timestamp is a full ti 638 absolute: The timestamp is a full timestamp, not a delta
706 against some other value. As 639 against some other value. As such it takes up more
707 space and is less efficient. 640 space and is less efficient.
708 641
709 hwlat_detector: 642 hwlat_detector:
710 643
711 Directory for the Hardware Latency Det 644 Directory for the Hardware Latency Detector.
712 See "Hardware Latency Detector" sectio 645 See "Hardware Latency Detector" section below.
713 646
714 per_cpu: 647 per_cpu:
715 648
716 This is a directory that contains the 649 This is a directory that contains the trace per_cpu information.
717 650
718 per_cpu/cpu0/buffer_size_kb: 651 per_cpu/cpu0/buffer_size_kb:
719 652
720 The ftrace buffer is defined per_cpu. 653 The ftrace buffer is defined per_cpu. That is, there's a separate
721 buffer for each CPU to allow writes to 654 buffer for each CPU to allow writes to be done atomically,
722 and free from cache bouncing. These bu 655 and free from cache bouncing. These buffers may have different
723 size buffers. This file is similar to 656 size buffers. This file is similar to the buffer_size_kb
724 file, but it only displays or sets the 657 file, but it only displays or sets the buffer size for the
725 specific CPU. (here cpu0). 658 specific CPU. (here cpu0).
726 659
727 per_cpu/cpu0/trace: 660 per_cpu/cpu0/trace:
728 661
729 This is similar to the "trace" file, b 662 This is similar to the "trace" file, but it will only display
730 the data specific for the CPU. If writ 663 the data specific for the CPU. If written to, it only clears
731 the specific CPU buffer. 664 the specific CPU buffer.
732 665
733 per_cpu/cpu0/trace_pipe 666 per_cpu/cpu0/trace_pipe
734 667
735 This is similar to the "trace_pipe" fi 668 This is similar to the "trace_pipe" file, and is a consuming
736 read, but it will only display (and co 669 read, but it will only display (and consume) the data specific
737 for the CPU. 670 for the CPU.
738 671
739 per_cpu/cpu0/trace_pipe_raw 672 per_cpu/cpu0/trace_pipe_raw
740 673
741 For tools that can parse the ftrace ri 674 For tools that can parse the ftrace ring buffer binary format,
742 the trace_pipe_raw file can be used to 675 the trace_pipe_raw file can be used to extract the data
743 from the ring buffer directly. With th 676 from the ring buffer directly. With the use of the splice()
744 system call, the buffer data can be qu 677 system call, the buffer data can be quickly transferred to
745 a file or to the network where a serve 678 a file or to the network where a server is collecting the
746 data. 679 data.
747 680
748 Like trace_pipe, this is a consuming r 681 Like trace_pipe, this is a consuming reader, where multiple
749 reads will always produce different da 682 reads will always produce different data.
750 683
751 per_cpu/cpu0/snapshot: 684 per_cpu/cpu0/snapshot:
752 685
753 This is similar to the main "snapshot" 686 This is similar to the main "snapshot" file, but will only
754 snapshot the current CPU (if supported 687 snapshot the current CPU (if supported). It only displays
755 the content of the snapshot for a give 688 the content of the snapshot for a given CPU, and if
756 written to, only clears this CPU buffe 689 written to, only clears this CPU buffer.
757 690
758 per_cpu/cpu0/snapshot_raw: 691 per_cpu/cpu0/snapshot_raw:
759 692
760 Similar to the trace_pipe_raw, but wil 693 Similar to the trace_pipe_raw, but will read the binary format
761 from the snapshot buffer for the given 694 from the snapshot buffer for the given CPU.
762 695
763 per_cpu/cpu0/stats: 696 per_cpu/cpu0/stats:
764 697
765 This displays certain stats about the 698 This displays certain stats about the ring buffer:
766 699
767 entries: 700 entries:
768 The number of events that are 701 The number of events that are still in the buffer.
769 702
770 overrun: 703 overrun:
771 The number of lost events due 704 The number of lost events due to overwriting when
772 the buffer was full. 705 the buffer was full.
773 706
774 commit overrun: 707 commit overrun:
775 Should always be zero. 708 Should always be zero.
776 This gets set if so many event 709 This gets set if so many events happened within a nested
777 event (ring buffer is re-entra 710 event (ring buffer is re-entrant), that it fills the
778 buffer and starts dropping eve 711 buffer and starts dropping events.
779 712
780 bytes: 713 bytes:
781 Bytes actually read (not overw 714 Bytes actually read (not overwritten).
782 715
783 oldest event ts: 716 oldest event ts:
784 The oldest timestamp in the bu 717 The oldest timestamp in the buffer
785 718
786 now ts: 719 now ts:
787 The current timestamp 720 The current timestamp
788 721
789 dropped events: 722 dropped events:
790 Events lost due to overwrite o 723 Events lost due to overwrite option being off.
791 724
792 read events: 725 read events:
793 The number of events read. 726 The number of events read.
794 727
795 The Tracers 728 The Tracers
796 ----------- 729 -----------
797 730
798 Here is the list of current tracers that may b 731 Here is the list of current tracers that may be configured.
799 732
800 "function" 733 "function"
801 734
802 Function call tracer to trace all kern 735 Function call tracer to trace all kernel functions.
803 736
804 "function_graph" 737 "function_graph"
805 738
806 Similar to the function tracer except 739 Similar to the function tracer except that the
807 function tracer probes the functions o 740 function tracer probes the functions on their entry
808 whereas the function graph tracer trac 741 whereas the function graph tracer traces on both entry
809 and exit of the functions. It then pro 742 and exit of the functions. It then provides the ability
810 to draw a graph of function calls simi 743 to draw a graph of function calls similar to C code
811 source. 744 source.
812 745
813 "blk" 746 "blk"
814 747
815 The block tracer. The tracer used by t 748 The block tracer. The tracer used by the blktrace user
816 application. 749 application.
817 750
818 "hwlat" 751 "hwlat"
819 752
820 The Hardware Latency tracer is used to 753 The Hardware Latency tracer is used to detect if the hardware
821 produces any latency. See "Hardware La 754 produces any latency. See "Hardware Latency Detector" section
822 below. 755 below.
823 756
824 "irqsoff" 757 "irqsoff"
825 758
826 Traces the areas that disable interrup 759 Traces the areas that disable interrupts and saves
827 the trace with the longest max latency 760 the trace with the longest max latency.
828 See tracing_max_latency. When a new ma 761 See tracing_max_latency. When a new max is recorded,
829 it replaces the old trace. It is best 762 it replaces the old trace. It is best to view this
830 trace with the latency-format option e 763 trace with the latency-format option enabled, which
831 happens automatically when the tracer 764 happens automatically when the tracer is selected.
832 765
833 "preemptoff" 766 "preemptoff"
834 767
835 Similar to irqsoff but traces and reco 768 Similar to irqsoff but traces and records the amount of
836 time for which preemption is disabled. 769 time for which preemption is disabled.
837 770
838 "preemptirqsoff" 771 "preemptirqsoff"
839 772
840 Similar to irqsoff and preemptoff, but 773 Similar to irqsoff and preemptoff, but traces and
841 records the largest time for which irq 774 records the largest time for which irqs and/or preemption
842 is disabled. 775 is disabled.
843 776
844 "wakeup" 777 "wakeup"
845 778
846 Traces and records the max latency tha 779 Traces and records the max latency that it takes for
847 the highest priority task to get sched 780 the highest priority task to get scheduled after
848 it has been woken up. 781 it has been woken up.
849 Traces all tasks as an average develop 782 Traces all tasks as an average developer would expect.
850 783
851 "wakeup_rt" 784 "wakeup_rt"
852 785
853 Traces and records the max latency tha 786 Traces and records the max latency that it takes for just
854 RT tasks (as the current "wakeup" does 787 RT tasks (as the current "wakeup" does). This is useful
855 for those interested in wake up timing 788 for those interested in wake up timings of RT tasks.
856 789
857 "wakeup_dl" 790 "wakeup_dl"
858 791
859 Traces and records the max latency tha 792 Traces and records the max latency that it takes for
860 a SCHED_DEADLINE task to be woken (as 793 a SCHED_DEADLINE task to be woken (as the "wakeup" and
861 "wakeup_rt" does). 794 "wakeup_rt" does).
862 795
863 "mmiotrace" 796 "mmiotrace"
864 797
865 A special tracer that is used to trace 798 A special tracer that is used to trace binary module.
866 It will trace all the calls that a mod 799 It will trace all the calls that a module makes to the
867 hardware. Everything it writes and rea 800 hardware. Everything it writes and reads from the I/O
868 as well. 801 as well.
869 802
870 "branch" 803 "branch"
871 804
872 This tracer can be configured when tra 805 This tracer can be configured when tracing likely/unlikely
873 calls within the kernel. It will trace 806 calls within the kernel. It will trace when a likely and
874 unlikely branch is hit and if it was c 807 unlikely branch is hit and if it was correct in its prediction
875 of being correct. 808 of being correct.
876 809
877 "nop" 810 "nop"
878 811
879 This is the "trace nothing" tracer. To 812 This is the "trace nothing" tracer. To remove all
880 tracers from tracing simply echo "nop" 813 tracers from tracing simply echo "nop" into
881 current_tracer. 814 current_tracer.
882 815
883 Error conditions 816 Error conditions
884 ---------------- 817 ----------------
885 818
886 For most ftrace commands, failure modes are 819 For most ftrace commands, failure modes are obvious and communicated
887 using standard return codes. 820 using standard return codes.
888 821
889 For other more involved commands, extended e 822 For other more involved commands, extended error information may be
890 available via the tracing/error_log file. F 823 available via the tracing/error_log file. For the commands that
891 support it, reading the tracing/error_log fi 824 support it, reading the tracing/error_log file after an error will
892 display more detailed information about what 825 display more detailed information about what went wrong, if
893 information is available. The tracing/error 826 information is available. The tracing/error_log file is a circular
894 error log displaying a small number (current 827 error log displaying a small number (currently, 8) of ftrace errors
895 for the last (8) failed commands. 828 for the last (8) failed commands.
896 829
897 The extended error information and usage tak 830 The extended error information and usage takes the form shown in
898 this example:: 831 this example::
899 832
900 # echo xxx > /sys/kernel/tracing/events/sc !! 833 # echo xxx > /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger
901 echo: write error: Invalid argument 834 echo: write error: Invalid argument
902 835
903 # cat /sys/kernel/tracing/error_log !! 836 # cat /sys/kernel/debug/tracing/error_log
904 [ 5348.887237] location: error: Couldn't y 837 [ 5348.887237] location: error: Couldn't yyy: zzz
905 Command: xxx 838 Command: xxx
906 ^ 839 ^
907 [ 7517.023364] location: error: Bad rrr: s 840 [ 7517.023364] location: error: Bad rrr: sss
908 Command: ppp qqq 841 Command: ppp qqq
909 ^ 842 ^
910 843
911 To clear the error log, echo the empty strin 844 To clear the error log, echo the empty string into it::
912 845
913 # echo > /sys/kernel/tracing/error_log !! 846 # echo > /sys/kernel/debug/tracing/error_log
914 847
915 Examples of using the tracer 848 Examples of using the tracer
916 ---------------------------- 849 ----------------------------
917 850
918 Here are typical examples of using the tracers 851 Here are typical examples of using the tracers when controlling
919 them only with the tracefs interface (without 852 them only with the tracefs interface (without using any
920 user-land utilities). 853 user-land utilities).
921 854
922 Output format: 855 Output format:
923 -------------- 856 --------------
924 857
925 Here is an example of the output format of the 858 Here is an example of the output format of the file "trace"::
926 859
927 # tracer: function 860 # tracer: function
928 # 861 #
929 # entries-in-buffer/entries-written: 140080/ 862 # entries-in-buffer/entries-written: 140080/250280 #P:4
930 # 863 #
931 # _-----=> irqs 864 # _-----=> irqs-off
932 # / _----=> need 865 # / _----=> need-resched
933 # | / _---=> hard 866 # | / _---=> hardirq/softirq
934 # || / _--=> pree 867 # || / _--=> preempt-depth
935 # ||| / delay 868 # ||| / delay
936 # TASK-PID CPU# |||| TIMESTA 869 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
937 # | | | |||| | 870 # | | | |||| | |
938 bash-1977 [000] .... 17284.9936 871 bash-1977 [000] .... 17284.993652: sys_close <-system_call_fastpath
939 bash-1977 [000] .... 17284.9936 872 bash-1977 [000] .... 17284.993653: __close_fd <-sys_close
940 bash-1977 [000] .... 17284.9936 873 bash-1977 [000] .... 17284.993653: _raw_spin_lock <-__close_fd
941 sshd-1974 [003] .... 17284.9936 874 sshd-1974 [003] .... 17284.993653: __srcu_read_unlock <-fsnotify
942 bash-1977 [000] .... 17284.9936 875 bash-1977 [000] .... 17284.993654: add_preempt_count <-_raw_spin_lock
943 bash-1977 [000] ...1 17284.9936 876 bash-1977 [000] ...1 17284.993655: _raw_spin_unlock <-__close_fd
944 bash-1977 [000] ...1 17284.9936 877 bash-1977 [000] ...1 17284.993656: sub_preempt_count <-_raw_spin_unlock
945 bash-1977 [000] .... 17284.9936 878 bash-1977 [000] .... 17284.993657: filp_close <-__close_fd
946 bash-1977 [000] .... 17284.9936 879 bash-1977 [000] .... 17284.993657: dnotify_flush <-filp_close
947 sshd-1974 [003] .... 17284.9936 880 sshd-1974 [003] .... 17284.993658: sys_select <-system_call_fastpath
948 .... 881 ....
949 882
950 A header is printed with the tracer name that 883 A header is printed with the tracer name that is represented by
951 the trace. In this case the tracer is "functio 884 the trace. In this case the tracer is "function". Then it shows the
952 number of events in the buffer as well as the 885 number of events in the buffer as well as the total number of entries
953 that were written. The difference is the numbe 886 that were written. The difference is the number of entries that were
954 lost due to the buffer filling up (250280 - 14 887 lost due to the buffer filling up (250280 - 140080 = 110200 events
955 lost). 888 lost).
956 889
957 The header explains the content of the events. 890 The header explains the content of the events. Task name "bash", the task
958 PID "1977", the CPU that it was running on "00 891 PID "1977", the CPU that it was running on "000", the latency format
959 (explained below), the timestamp in <secs>.<us 892 (explained below), the timestamp in <secs>.<usecs> format, the
960 function name that was traced "sys_close" and 893 function name that was traced "sys_close" and the parent function that
961 called this function "system_call_fastpath". T 894 called this function "system_call_fastpath". The timestamp is the time
962 at which the function was entered. 895 at which the function was entered.
963 896
964 Latency trace format 897 Latency trace format
965 -------------------- 898 --------------------
966 899
967 When the latency-format option is enabled or w 900 When the latency-format option is enabled or when one of the latency
968 tracers is set, the trace file gives somewhat 901 tracers is set, the trace file gives somewhat more information to see
969 why a latency happened. Here is a typical trac 902 why a latency happened. Here is a typical trace::
970 903
971 # tracer: irqsoff 904 # tracer: irqsoff
972 # 905 #
973 # irqsoff latency trace v1.1.5 on 3.8.0-test 906 # irqsoff latency trace v1.1.5 on 3.8.0-test+
974 # ------------------------------------------ 907 # --------------------------------------------------------------------
975 # latency: 259 us, #4/4, CPU#2 | (M:preempt 908 # latency: 259 us, #4/4, CPU#2 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
976 # ----------------- 909 # -----------------
977 # | task: ps-6143 (uid:0 nice:0 policy:0 910 # | task: ps-6143 (uid:0 nice:0 policy:0 rt_prio:0)
978 # ----------------- 911 # -----------------
979 # => started at: __lock_task_sighand 912 # => started at: __lock_task_sighand
980 # => ended at: _raw_spin_unlock_irqrestor 913 # => ended at: _raw_spin_unlock_irqrestore
981 # 914 #
982 # 915 #
983 # _------=> CPU# 916 # _------=> CPU#
984 # / _-----=> irqs-off 917 # / _-----=> irqs-off
985 # | / _----=> need-resched 918 # | / _----=> need-resched
986 # || / _---=> hardirq/softirq 919 # || / _---=> hardirq/softirq
987 # ||| / _--=> preempt-depth 920 # ||| / _--=> preempt-depth
988 # |||| / delay 921 # |||| / delay
989 # cmd pid ||||| time | caller 922 # cmd pid ||||| time | caller
990 # \ / ||||| \ | / 923 # \ / ||||| \ | /
991 ps-6143 2d... 0us!: trace_hardir 924 ps-6143 2d... 0us!: trace_hardirqs_off <-__lock_task_sighand
992 ps-6143 2d..1 259us+: trace_hardir 925 ps-6143 2d..1 259us+: trace_hardirqs_on <-_raw_spin_unlock_irqrestore
993 ps-6143 2d..1 263us+: time_hardirq 926 ps-6143 2d..1 263us+: time_hardirqs_on <-_raw_spin_unlock_irqrestore
994 ps-6143 2d..1 306us : <stack trace 927 ps-6143 2d..1 306us : <stack trace>
995 => trace_hardirqs_on_caller 928 => trace_hardirqs_on_caller
996 => trace_hardirqs_on 929 => trace_hardirqs_on
997 => _raw_spin_unlock_irqrestore 930 => _raw_spin_unlock_irqrestore
998 => do_task_stat 931 => do_task_stat
999 => proc_tgid_stat 932 => proc_tgid_stat
1000 => proc_single_show 933 => proc_single_show
1001 => seq_read 934 => seq_read
1002 => vfs_read 935 => vfs_read
1003 => sys_read 936 => sys_read
1004 => system_call_fastpath 937 => system_call_fastpath
1005 938
1006 939
1007 This shows that the current tracer is "irqsof 940 This shows that the current tracer is "irqsoff" tracing the time
1008 for which interrupts were disabled. It gives 941 for which interrupts were disabled. It gives the trace version (which
1009 never changes) and the version of the kernel 942 never changes) and the version of the kernel upon which this was executed on
1010 (3.8). Then it displays the max latency in mi 943 (3.8). Then it displays the max latency in microseconds (259 us). The number
1011 of trace entries displayed and the total numb 944 of trace entries displayed and the total number (both are four: #4/4).
1012 VP, KP, SP, and HP are always zero and are re 945 VP, KP, SP, and HP are always zero and are reserved for later use.
1013 #P is the number of online CPUs (#P:4). 946 #P is the number of online CPUs (#P:4).
1014 947
1015 The task is the process that was running when 948 The task is the process that was running when the latency
1016 occurred. (ps pid: 6143). 949 occurred. (ps pid: 6143).
1017 950
1018 The start and stop (the functions in which th 951 The start and stop (the functions in which the interrupts were
1019 disabled and enabled respectively) that cause 952 disabled and enabled respectively) that caused the latencies:
1020 953
1021 - __lock_task_sighand is where the interrup 954 - __lock_task_sighand is where the interrupts were disabled.
1022 - _raw_spin_unlock_irqrestore is where they 955 - _raw_spin_unlock_irqrestore is where they were enabled again.
1023 956
1024 The next lines after the header are the trace 957 The next lines after the header are the trace itself. The header
1025 explains which is which. 958 explains which is which.
1026 959
1027 cmd: The name of the process in the trace. 960 cmd: The name of the process in the trace.
1028 961
1029 pid: The PID of that process. 962 pid: The PID of that process.
1030 963
1031 CPU#: The CPU which the process was running 964 CPU#: The CPU which the process was running on.
1032 965
1033 irqs-off: 'd' interrupts are disabled. '.' 966 irqs-off: 'd' interrupts are disabled. '.' otherwise.
1034 .. caution:: If the architecture does 967 .. caution:: If the architecture does not support a way to
1035 read the irq flags variable, 968 read the irq flags variable, an 'X' will always
1036 be printed here. 969 be printed here.
1037 970
1038 need-resched: 971 need-resched:
1039 - 'N' both TIF_NEED_RESCHED and PREEM 972 - 'N' both TIF_NEED_RESCHED and PREEMPT_NEED_RESCHED is set,
1040 - 'n' only TIF_NEED_RESCHED is set, 973 - 'n' only TIF_NEED_RESCHED is set,
1041 - 'p' only PREEMPT_NEED_RESCHED is se 974 - 'p' only PREEMPT_NEED_RESCHED is set,
1042 - '.' otherwise. 975 - '.' otherwise.
1043 976
1044 hardirq/softirq: 977 hardirq/softirq:
1045 - 'Z' - NMI occurred inside a hardirq 978 - 'Z' - NMI occurred inside a hardirq
1046 - 'z' - NMI is running 979 - 'z' - NMI is running
1047 - 'H' - hard irq occurred inside a so 980 - 'H' - hard irq occurred inside a softirq.
1048 - 'h' - hard irq is running 981 - 'h' - hard irq is running
1049 - 's' - soft irq is running 982 - 's' - soft irq is running
1050 - '.' - normal context. 983 - '.' - normal context.
1051 984
1052 preempt-depth: The level of preempt_disable 985 preempt-depth: The level of preempt_disabled
1053 986
1054 The above is mostly meaningful for kernel dev 987 The above is mostly meaningful for kernel developers.
1055 988
1056 time: 989 time:
1057 When the latency-format option is ena 990 When the latency-format option is enabled, the trace file
1058 output includes a timestamp relative 991 output includes a timestamp relative to the start of the
1059 trace. This differs from the output w 992 trace. This differs from the output when latency-format
1060 is disabled, which includes an absolu 993 is disabled, which includes an absolute timestamp.
1061 994
1062 delay: 995 delay:
1063 This is just to help catch your eye a 996 This is just to help catch your eye a bit better. And
1064 needs to be fixed to be only relative 997 needs to be fixed to be only relative to the same CPU.
1065 The marks are determined by the diffe 998 The marks are determined by the difference between this
1066 current trace and the next trace. 999 current trace and the next trace.
1067 1000
1068 - '$' - greater than 1 second 1001 - '$' - greater than 1 second
1069 - '@' - greater than 100 millisecon 1002 - '@' - greater than 100 millisecond
1070 - '*' - greater than 10 millisecond 1003 - '*' - greater than 10 millisecond
1071 - '#' - greater than 1000 microseco 1004 - '#' - greater than 1000 microsecond
1072 - '!' - greater than 100 microsecon 1005 - '!' - greater than 100 microsecond
1073 - '+' - greater than 10 microsecond 1006 - '+' - greater than 10 microsecond
1074 - ' ' - less than or equal to 10 mi 1007 - ' ' - less than or equal to 10 microsecond.
1075 1008
1076 The rest is the same as the 'trace' file. 1009 The rest is the same as the 'trace' file.
1077 1010
1078 Note, the latency tracers will usually end 1011 Note, the latency tracers will usually end with a back trace
1079 to easily find where the latency occurred. 1012 to easily find where the latency occurred.
1080 1013
1081 trace_options 1014 trace_options
1082 ------------- 1015 -------------
1083 1016
1084 The trace_options file (or the options direct 1017 The trace_options file (or the options directory) is used to control
1085 what gets printed in the trace output, or man 1018 what gets printed in the trace output, or manipulate the tracers.
1086 To see what is available, simply cat the file 1019 To see what is available, simply cat the file::
1087 1020
1088 cat trace_options 1021 cat trace_options
1089 print-parent 1022 print-parent
1090 nosym-offset 1023 nosym-offset
1091 nosym-addr 1024 nosym-addr
1092 noverbose 1025 noverbose
1093 noraw 1026 noraw
1094 nohex 1027 nohex
1095 nobin 1028 nobin
1096 noblock 1029 noblock
1097 nofields <<
1098 trace_printk 1030 trace_printk
1099 annotate 1031 annotate
1100 nouserstacktrace 1032 nouserstacktrace
1101 nosym-userobj 1033 nosym-userobj
1102 noprintk-msg-only 1034 noprintk-msg-only
1103 context-info 1035 context-info
1104 nolatency-format 1036 nolatency-format
1105 record-cmd 1037 record-cmd
1106 norecord-tgid 1038 norecord-tgid
1107 overwrite 1039 overwrite
1108 nodisable_on_free 1040 nodisable_on_free
1109 irq-info 1041 irq-info
1110 markers 1042 markers
1111 noevent-fork 1043 noevent-fork
1112 function-trace 1044 function-trace
1113 nofunction-fork 1045 nofunction-fork
1114 nodisplay-graph 1046 nodisplay-graph
1115 nostacktrace 1047 nostacktrace
1116 nobranch 1048 nobranch
1117 1049
1118 To disable one of the options, echo in the op 1050 To disable one of the options, echo in the option prepended with
1119 "no":: 1051 "no"::
1120 1052
1121 echo noprint-parent > trace_options 1053 echo noprint-parent > trace_options
1122 1054
1123 To enable an option, leave off the "no":: 1055 To enable an option, leave off the "no"::
1124 1056
1125 echo sym-offset > trace_options 1057 echo sym-offset > trace_options
1126 1058
1127 Here are the available options: 1059 Here are the available options:
1128 1060
1129 print-parent 1061 print-parent
1130 On function traces, display the calli 1062 On function traces, display the calling (parent)
1131 function as well as the function bein 1063 function as well as the function being traced.
1132 :: 1064 ::
1133 1065
1134 print-parent: 1066 print-parent:
1135 bash-4000 [01] 1477.606694: simp 1067 bash-4000 [01] 1477.606694: simple_strtoul <-kstrtoul
1136 1068
1137 noprint-parent: 1069 noprint-parent:
1138 bash-4000 [01] 1477.606694: simp 1070 bash-4000 [01] 1477.606694: simple_strtoul
1139 1071
1140 1072
1141 sym-offset 1073 sym-offset
1142 Display not only the function name, b 1074 Display not only the function name, but also the
1143 offset in the function. For example, 1075 offset in the function. For example, instead of
1144 seeing just "ktime_get", you will see 1076 seeing just "ktime_get", you will see
1145 "ktime_get+0xb/0x20". 1077 "ktime_get+0xb/0x20".
1146 :: 1078 ::
1147 1079
1148 sym-offset: 1080 sym-offset:
1149 bash-4000 [01] 1477.606694: simp 1081 bash-4000 [01] 1477.606694: simple_strtoul+0x6/0xa0
1150 1082
1151 sym-addr 1083 sym-addr
1152 This will also display the function a 1084 This will also display the function address as well
1153 as the function name. 1085 as the function name.
1154 :: 1086 ::
1155 1087
1156 sym-addr: 1088 sym-addr:
1157 bash-4000 [01] 1477.606694: simp 1089 bash-4000 [01] 1477.606694: simple_strtoul <c0339346>
1158 1090
1159 verbose 1091 verbose
1160 This deals with the trace file when t 1092 This deals with the trace file when the
1161 latency-format option is enabled. 1093 latency-format option is enabled.
1162 :: 1094 ::
1163 1095
1164 bash 4000 1 0 00000000 00010a95 1096 bash 4000 1 0 00000000 00010a95 [58127d26] 1720.415ms \
1165 (+0.000ms): simple_strtoul (kstrt 1097 (+0.000ms): simple_strtoul (kstrtoul)
1166 1098
1167 raw 1099 raw
1168 This will display raw numbers. This o 1100 This will display raw numbers. This option is best for
1169 use with user applications that can t 1101 use with user applications that can translate the raw
1170 numbers better than having it done in 1102 numbers better than having it done in the kernel.
1171 1103
1172 hex 1104 hex
1173 Similar to raw, but the numbers will 1105 Similar to raw, but the numbers will be in a hexadecimal format.
1174 1106
1175 bin 1107 bin
1176 This will print out the formats in ra 1108 This will print out the formats in raw binary.
1177 1109
1178 block 1110 block
1179 When set, reading trace_pipe will not 1111 When set, reading trace_pipe will not block when polled.
1180 1112
1181 fields <<
1182 Print the fields as described by thei <<
1183 option than using hex, bin or raw, as <<
1184 of the content of the event. <<
1185 <<
1186 trace_printk 1113 trace_printk
1187 Can disable trace_printk() from writi 1114 Can disable trace_printk() from writing into the buffer.
1188 1115
1189 trace_printk_dest <<
1190 Set to have trace_printk() and simila <<
1191 write into this instance. Note, only <<
1192 this set. By setting this flag, it cl <<
1193 of the instance that had it set previ <<
1194 level trace has this set, and will ge <<
1195 instance has it set then clears it. <<
1196 <<
1197 This flag cannot be cleared by the to <<
1198 default instance. The only way the to <<
1199 cleared, is by it being set in anothe <<
1200 <<
1201 annotate 1116 annotate
1202 It is sometimes confusing when the CP 1117 It is sometimes confusing when the CPU buffers are full
1203 and one CPU buffer had a lot of event 1118 and one CPU buffer had a lot of events recently, thus
1204 a shorter time frame, were another CP 1119 a shorter time frame, were another CPU may have only had
1205 a few events, which lets it have olde 1120 a few events, which lets it have older events. When
1206 the trace is reported, it shows the o 1121 the trace is reported, it shows the oldest events first,
1207 and it may look like only one CPU ran 1122 and it may look like only one CPU ran (the one with the
1208 oldest events). When the annotate opt 1123 oldest events). When the annotate option is set, it will
1209 display when a new CPU buffer started 1124 display when a new CPU buffer started::
1210 1125
1211 <idle>-0 [001] 1126 <idle>-0 [001] dNs4 21169.031481: wake_up_idle_cpu <-add_timer_on
1212 <idle>-0 [001] 1127 <idle>-0 [001] dNs4 21169.031482: _raw_spin_unlock_irqrestore <-add_timer_on
1213 <idle>-0 [001] 1128 <idle>-0 [001] .Ns4 21169.031484: sub_preempt_count <-_raw_spin_unlock_irqrestore
1214 ##### CPU 2 buffer started ## 1129 ##### CPU 2 buffer started ####
1215 <idle>-0 [002] 1130 <idle>-0 [002] .N.1 21169.031484: rcu_idle_exit <-cpu_idle
1216 <idle>-0 [001] 1131 <idle>-0 [001] .Ns3 21169.031484: _raw_spin_unlock <-clocksource_watchdog
1217 <idle>-0 [001] 1132 <idle>-0 [001] .Ns3 21169.031485: sub_preempt_count <-_raw_spin_unlock
1218 1133
1219 userstacktrace 1134 userstacktrace
1220 This option changes the trace. It rec 1135 This option changes the trace. It records a
1221 stacktrace of the current user space 1136 stacktrace of the current user space thread after
1222 each trace event. 1137 each trace event.
1223 1138
1224 sym-userobj 1139 sym-userobj
1225 when user stacktrace are enabled, loo 1140 when user stacktrace are enabled, look up which
1226 object the address belongs to, and pr 1141 object the address belongs to, and print a
1227 relative address. This is especially 1142 relative address. This is especially useful when
1228 ASLR is on, otherwise you don't get a 1143 ASLR is on, otherwise you don't get a chance to
1229 resolve the address to object/file/li 1144 resolve the address to object/file/line after
1230 the app is no longer running 1145 the app is no longer running
1231 1146
1232 The lookup is performed when you read 1147 The lookup is performed when you read
1233 trace,trace_pipe. Example:: 1148 trace,trace_pipe. Example::
1234 1149
1235 a.out-1623 [000] 40874.465 1150 a.out-1623 [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0
1236 x494] <- /root/a.out[+0x4a8 1151 x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
1237 1152
1238 1153
1239 printk-msg-only 1154 printk-msg-only
1240 When set, trace_printk()s will only s 1155 When set, trace_printk()s will only show the format
1241 and not their parameters (if trace_bp 1156 and not their parameters (if trace_bprintk() or
1242 trace_bputs() was used to save the tr 1157 trace_bputs() was used to save the trace_printk()).
1243 1158
1244 context-info 1159 context-info
1245 Show only the event data. Hides the c 1160 Show only the event data. Hides the comm, PID,
1246 timestamp, CPU, and other useful data 1161 timestamp, CPU, and other useful data.
1247 1162
1248 latency-format 1163 latency-format
1249 This option changes the trace output. 1164 This option changes the trace output. When it is enabled,
1250 the trace displays additional informa 1165 the trace displays additional information about the
1251 latency, as described in "Latency tra 1166 latency, as described in "Latency trace format".
1252 1167
1253 pause-on-trace 1168 pause-on-trace
1254 When set, opening the trace file for 1169 When set, opening the trace file for read, will pause
1255 writing to the ring buffer (as if tra 1170 writing to the ring buffer (as if tracing_on was set to zero).
1256 This simulates the original behavior 1171 This simulates the original behavior of the trace file.
1257 When the file is closed, tracing will 1172 When the file is closed, tracing will be enabled again.
1258 1173
1259 hash-ptr 1174 hash-ptr
1260 When set, "%p" in the event printk fo 1175 When set, "%p" in the event printk format displays the
1261 hashed pointer value instead of real 1176 hashed pointer value instead of real address.
1262 This will be useful if you want to fi 1177 This will be useful if you want to find out which hashed
1263 value is corresponding to the real va 1178 value is corresponding to the real value in trace log.
1264 1179
1265 record-cmd 1180 record-cmd
1266 When any event or tracer is enabled, 1181 When any event or tracer is enabled, a hook is enabled
1267 in the sched_switch trace point to fi 1182 in the sched_switch trace point to fill comm cache
1268 with mapped pids and comms. But this 1183 with mapped pids and comms. But this may cause some
1269 overhead, and if you only care about 1184 overhead, and if you only care about pids, and not the
1270 name of the task, disabling this opti 1185 name of the task, disabling this option can lower the
1271 impact of tracing. See "saved_cmdline 1186 impact of tracing. See "saved_cmdlines".
1272 1187
1273 record-tgid 1188 record-tgid
1274 When any event or tracer is enabled, 1189 When any event or tracer is enabled, a hook is enabled
1275 in the sched_switch trace point to fi 1190 in the sched_switch trace point to fill the cache of
1276 mapped Thread Group IDs (TGID) mappin 1191 mapped Thread Group IDs (TGID) mapping to pids. See
1277 "saved_tgids". 1192 "saved_tgids".
1278 1193
1279 overwrite 1194 overwrite
1280 This controls what happens when the t 1195 This controls what happens when the trace buffer is
1281 full. If "1" (default), the oldest ev 1196 full. If "1" (default), the oldest events are
1282 discarded and overwritten. If "0", th 1197 discarded and overwritten. If "0", then the newest
1283 events are discarded. 1198 events are discarded.
1284 (see per_cpu/cpu0/stats for overrun a 1199 (see per_cpu/cpu0/stats for overrun and dropped)
1285 1200
1286 disable_on_free 1201 disable_on_free
1287 When the free_buffer is closed, traci 1202 When the free_buffer is closed, tracing will
1288 stop (tracing_on set to 0). 1203 stop (tracing_on set to 0).
1289 1204
1290 irq-info 1205 irq-info
1291 Shows the interrupt, preempt count, n 1206 Shows the interrupt, preempt count, need resched data.
1292 When disabled, the trace looks like:: 1207 When disabled, the trace looks like::
1293 1208
1294 # tracer: function 1209 # tracer: function
1295 # 1210 #
1296 # entries-in-buffer/entries-w 1211 # entries-in-buffer/entries-written: 144405/9452052 #P:4
1297 # 1212 #
1298 # TASK-PID CPU# 1213 # TASK-PID CPU# TIMESTAMP FUNCTION
1299 # | | | 1214 # | | | | |
1300 <idle>-0 [002] 1215 <idle>-0 [002] 23636.756054: ttwu_do_activate.constprop.89 <-try_to_wake_up
1301 <idle>-0 [002] 1216 <idle>-0 [002] 23636.756054: activate_task <-ttwu_do_activate.constprop.89
1302 <idle>-0 [002] 1217 <idle>-0 [002] 23636.756055: enqueue_task <-activate_task
1303 1218
1304 1219
1305 markers 1220 markers
1306 When set, the trace_marker is writabl 1221 When set, the trace_marker is writable (only by root).
1307 When disabled, the trace_marker will 1222 When disabled, the trace_marker will error with EINVAL
1308 on write. 1223 on write.
1309 1224
1310 event-fork 1225 event-fork
1311 When set, tasks with PIDs listed in s 1226 When set, tasks with PIDs listed in set_event_pid will have
1312 the PIDs of their children added to s 1227 the PIDs of their children added to set_event_pid when those
1313 tasks fork. Also, when tasks with PID 1228 tasks fork. Also, when tasks with PIDs in set_event_pid exit,
1314 their PIDs will be removed from the f 1229 their PIDs will be removed from the file.
1315 1230
1316 This affects PIDs listed in set_event 1231 This affects PIDs listed in set_event_notrace_pid as well.
1317 1232
1318 function-trace 1233 function-trace
1319 The latency tracers will enable funct 1234 The latency tracers will enable function tracing
1320 if this option is enabled (default it 1235 if this option is enabled (default it is). When
1321 it is disabled, the latency tracers d 1236 it is disabled, the latency tracers do not trace
1322 functions. This keeps the overhead of 1237 functions. This keeps the overhead of the tracer down
1323 when performing latency tests. 1238 when performing latency tests.
1324 1239
1325 function-fork 1240 function-fork
1326 When set, tasks with PIDs listed in s 1241 When set, tasks with PIDs listed in set_ftrace_pid will
1327 have the PIDs of their children added 1242 have the PIDs of their children added to set_ftrace_pid
1328 when those tasks fork. Also, when tas 1243 when those tasks fork. Also, when tasks with PIDs in
1329 set_ftrace_pid exit, their PIDs will 1244 set_ftrace_pid exit, their PIDs will be removed from the
1330 file. 1245 file.
1331 1246
1332 This affects PIDs in set_ftrace_notra 1247 This affects PIDs in set_ftrace_notrace_pid as well.
1333 1248
1334 display-graph 1249 display-graph
1335 When set, the latency tracers (irqsof 1250 When set, the latency tracers (irqsoff, wakeup, etc) will
1336 use function graph tracing instead of 1251 use function graph tracing instead of function tracing.
1337 1252
1338 stacktrace 1253 stacktrace
1339 When set, a stack trace is recorded a 1254 When set, a stack trace is recorded after any trace event
1340 is recorded. 1255 is recorded.
1341 1256
1342 branch 1257 branch
1343 Enable branch tracing with the tracer 1258 Enable branch tracing with the tracer. This enables branch
1344 tracer along with the currently set t 1259 tracer along with the currently set tracer. Enabling this
1345 with the "nop" tracer is the same as 1260 with the "nop" tracer is the same as just enabling the
1346 "branch" tracer. 1261 "branch" tracer.
1347 1262
1348 .. tip:: Some tracers have their own options. 1263 .. tip:: Some tracers have their own options. They only appear in this
1349 file when the tracer is active. They a 1264 file when the tracer is active. They always appear in the
1350 options directory. 1265 options directory.
1351 1266
1352 1267
1353 Here are the per tracer options: 1268 Here are the per tracer options:
1354 1269
1355 Options for function tracer: 1270 Options for function tracer:
1356 1271
1357 func_stack_trace 1272 func_stack_trace
1358 When set, a stack trace is recorded a 1273 When set, a stack trace is recorded after every
1359 function that is recorded. NOTE! Limi 1274 function that is recorded. NOTE! Limit the functions
1360 that are recorded before enabling thi 1275 that are recorded before enabling this, with
1361 "set_ftrace_filter" otherwise the sys 1276 "set_ftrace_filter" otherwise the system performance
1362 will be critically degraded. Remember 1277 will be critically degraded. Remember to disable
1363 this option before clearing the funct 1278 this option before clearing the function filter.
1364 1279
1365 Options for function_graph tracer: 1280 Options for function_graph tracer:
1366 1281
1367 Since the function_graph tracer has a slight 1282 Since the function_graph tracer has a slightly different output
1368 it has its own options to control what is di 1283 it has its own options to control what is displayed.
1369 1284
1370 funcgraph-overrun 1285 funcgraph-overrun
1371 When set, the "overrun" of the graph 1286 When set, the "overrun" of the graph stack is
1372 displayed after each function traced. 1287 displayed after each function traced. The
1373 overrun, is when the stack depth of t 1288 overrun, is when the stack depth of the calls
1374 is greater than what is reserved for 1289 is greater than what is reserved for each task.
1375 Each task has a fixed array of functi 1290 Each task has a fixed array of functions to
1376 trace in the call graph. If the depth 1291 trace in the call graph. If the depth of the
1377 calls exceeds that, the function is n 1292 calls exceeds that, the function is not traced.
1378 The overrun is the number of function 1293 The overrun is the number of functions missed
1379 due to exceeding this array. 1294 due to exceeding this array.
1380 1295
1381 funcgraph-cpu 1296 funcgraph-cpu
1382 When set, the CPU number of the CPU w 1297 When set, the CPU number of the CPU where the trace
1383 occurred is displayed. 1298 occurred is displayed.
1384 1299
1385 funcgraph-overhead 1300 funcgraph-overhead
1386 When set, if the function takes longe 1301 When set, if the function takes longer than
1387 A certain amount, then a delay marker 1302 A certain amount, then a delay marker is
1388 displayed. See "delay" above, under t 1303 displayed. See "delay" above, under the
1389 header description. 1304 header description.
1390 1305
1391 funcgraph-proc 1306 funcgraph-proc
1392 Unlike other tracers, the process' co 1307 Unlike other tracers, the process' command line
1393 is not displayed by default, but inst 1308 is not displayed by default, but instead only
1394 when a task is traced in and out duri 1309 when a task is traced in and out during a context
1395 switch. Enabling this options has the 1310 switch. Enabling this options has the command
1396 of each process displayed at every li 1311 of each process displayed at every line.
1397 1312
1398 funcgraph-duration 1313 funcgraph-duration
1399 At the end of each function (the retu 1314 At the end of each function (the return)
1400 the duration of the amount of time in 1315 the duration of the amount of time in the
1401 function is displayed in microseconds 1316 function is displayed in microseconds.
1402 1317
1403 funcgraph-abstime 1318 funcgraph-abstime
1404 When set, the timestamp is displayed 1319 When set, the timestamp is displayed at each line.
1405 1320
1406 funcgraph-irqs 1321 funcgraph-irqs
1407 When disabled, functions that happen 1322 When disabled, functions that happen inside an
1408 interrupt will not be traced. 1323 interrupt will not be traced.
1409 1324
1410 funcgraph-tail 1325 funcgraph-tail
1411 When set, the return event will inclu 1326 When set, the return event will include the function
1412 that it represents. By default this i 1327 that it represents. By default this is off, and
1413 only a closing curly bracket "}" is d 1328 only a closing curly bracket "}" is displayed for
1414 the return of a function. 1329 the return of a function.
1415 1330
1416 funcgraph-retval <<
1417 When set, the return value of each tr <<
1418 will be printed after an equal sign " <<
1419 this is off. <<
1420 <<
1421 funcgraph-retval-hex <<
1422 When set, the return value will alway <<
1423 in hexadecimal format. If the option <<
1424 the return value is an error code, it <<
1425 in signed decimal format; otherwise i <<
1426 printed in hexadecimal format. By def <<
1427 is off. <<
1428 <<
1429 sleep-time 1331 sleep-time
1430 When running function graph tracer, t 1332 When running function graph tracer, to include
1431 the time a task schedules out in its 1333 the time a task schedules out in its function.
1432 When enabled, it will account time th 1334 When enabled, it will account time the task has been
1433 scheduled out as part of the function 1335 scheduled out as part of the function call.
1434 1336
1435 graph-time 1337 graph-time
1436 When running function profiler with f 1338 When running function profiler with function graph tracer,
1437 to include the time to call nested fu 1339 to include the time to call nested functions. When this is
1438 not set, the time reported for the fu 1340 not set, the time reported for the function will only
1439 include the time the function itself 1341 include the time the function itself executed for, not the
1440 time for functions that it called. 1342 time for functions that it called.
1441 1343
1442 Options for blk tracer: 1344 Options for blk tracer:
1443 1345
1444 blk_classic 1346 blk_classic
1445 Shows a more minimalistic output. 1347 Shows a more minimalistic output.
1446 1348
1447 1349
1448 irqsoff 1350 irqsoff
1449 ------- 1351 -------
1450 1352
1451 When interrupts are disabled, the CPU can not 1353 When interrupts are disabled, the CPU can not react to any other
1452 external event (besides NMIs and SMIs). This 1354 external event (besides NMIs and SMIs). This prevents the timer
1453 interrupt from triggering or the mouse interr 1355 interrupt from triggering or the mouse interrupt from letting
1454 the kernel know of a new mouse event. The res 1356 the kernel know of a new mouse event. The result is a latency
1455 with the reaction time. 1357 with the reaction time.
1456 1358
1457 The irqsoff tracer tracks the time for which 1359 The irqsoff tracer tracks the time for which interrupts are
1458 disabled. When a new maximum latency is hit, 1360 disabled. When a new maximum latency is hit, the tracer saves
1459 the trace leading up to that latency point so 1361 the trace leading up to that latency point so that every time a
1460 new maximum is reached, the old saved trace i 1362 new maximum is reached, the old saved trace is discarded and the
1461 new trace is saved. 1363 new trace is saved.
1462 1364
1463 To reset the maximum, echo 0 into tracing_max 1365 To reset the maximum, echo 0 into tracing_max_latency. Here is
1464 an example:: 1366 an example::
1465 1367
1466 # echo 0 > options/function-trace 1368 # echo 0 > options/function-trace
1467 # echo irqsoff > current_tracer 1369 # echo irqsoff > current_tracer
1468 # echo 1 > tracing_on 1370 # echo 1 > tracing_on
1469 # echo 0 > tracing_max_latency 1371 # echo 0 > tracing_max_latency
1470 # ls -ltr 1372 # ls -ltr
1471 [...] 1373 [...]
1472 # echo 0 > tracing_on 1374 # echo 0 > tracing_on
1473 # cat trace 1375 # cat trace
1474 # tracer: irqsoff 1376 # tracer: irqsoff
1475 # 1377 #
1476 # irqsoff latency trace v1.1.5 on 3.8.0-tes 1378 # irqsoff latency trace v1.1.5 on 3.8.0-test+
1477 # ----------------------------------------- 1379 # --------------------------------------------------------------------
1478 # latency: 16 us, #4/4, CPU#0 | (M:preempt 1380 # latency: 16 us, #4/4, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
1479 # ----------------- 1381 # -----------------
1480 # | task: swapper/0-0 (uid:0 nice:0 poli 1382 # | task: swapper/0-0 (uid:0 nice:0 policy:0 rt_prio:0)
1481 # ----------------- 1383 # -----------------
1482 # => started at: run_timer_softirq 1384 # => started at: run_timer_softirq
1483 # => ended at: run_timer_softirq 1385 # => ended at: run_timer_softirq
1484 # 1386 #
1485 # 1387 #
1486 # _------=> CPU# 1388 # _------=> CPU#
1487 # / _-----=> irqs-off 1389 # / _-----=> irqs-off
1488 # | / _----=> need-resched 1390 # | / _----=> need-resched
1489 # || / _---=> hardirq/softir 1391 # || / _---=> hardirq/softirq
1490 # ||| / _--=> preempt-depth 1392 # ||| / _--=> preempt-depth
1491 # |||| / delay 1393 # |||| / delay
1492 # cmd pid ||||| time | caller 1394 # cmd pid ||||| time | caller
1493 # \ / ||||| \ | / 1395 # \ / ||||| \ | /
1494 <idle>-0 0d.s2 0us+: _raw_spin_l 1396 <idle>-0 0d.s2 0us+: _raw_spin_lock_irq <-run_timer_softirq
1495 <idle>-0 0dNs3 17us : _raw_spin_u 1397 <idle>-0 0dNs3 17us : _raw_spin_unlock_irq <-run_timer_softirq
1496 <idle>-0 0dNs3 17us+: trace_hardi 1398 <idle>-0 0dNs3 17us+: trace_hardirqs_on <-run_timer_softirq
1497 <idle>-0 0dNs3 25us : <stack trac 1399 <idle>-0 0dNs3 25us : <stack trace>
1498 => _raw_spin_unlock_irq 1400 => _raw_spin_unlock_irq
1499 => run_timer_softirq 1401 => run_timer_softirq
1500 => __do_softirq 1402 => __do_softirq
1501 => call_softirq 1403 => call_softirq
1502 => do_softirq 1404 => do_softirq
1503 => irq_exit 1405 => irq_exit
1504 => smp_apic_timer_interrupt 1406 => smp_apic_timer_interrupt
1505 => apic_timer_interrupt 1407 => apic_timer_interrupt
1506 => rcu_idle_exit 1408 => rcu_idle_exit
1507 => cpu_idle 1409 => cpu_idle
1508 => rest_init 1410 => rest_init
1509 => start_kernel 1411 => start_kernel
1510 => x86_64_start_reservations 1412 => x86_64_start_reservations
1511 => x86_64_start_kernel 1413 => x86_64_start_kernel
1512 1414
1513 Here we see that we had a latency of 16 micro 1415 Here we see that we had a latency of 16 microseconds (which is
1514 very good). The _raw_spin_lock_irq in run_tim 1416 very good). The _raw_spin_lock_irq in run_timer_softirq disabled
1515 interrupts. The difference between the 16 and 1417 interrupts. The difference between the 16 and the displayed
1516 timestamp 25us occurred because the clock was 1418 timestamp 25us occurred because the clock was incremented
1517 between the time of recording the max latency 1419 between the time of recording the max latency and the time of
1518 recording the function that had that latency. 1420 recording the function that had that latency.
1519 1421
1520 Note the above example had function-trace not 1422 Note the above example had function-trace not set. If we set
1521 function-trace, we get a much larger output:: 1423 function-trace, we get a much larger output::
1522 1424
1523 with echo 1 > options/function-trace 1425 with echo 1 > options/function-trace
1524 1426
1525 # tracer: irqsoff 1427 # tracer: irqsoff
1526 # 1428 #
1527 # irqsoff latency trace v1.1.5 on 3.8.0-tes 1429 # irqsoff latency trace v1.1.5 on 3.8.0-test+
1528 # ----------------------------------------- 1430 # --------------------------------------------------------------------
1529 # latency: 71 us, #168/168, CPU#3 | (M:pree 1431 # latency: 71 us, #168/168, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
1530 # ----------------- 1432 # -----------------
1531 # | task: bash-2042 (uid:0 nice:0 policy 1433 # | task: bash-2042 (uid:0 nice:0 policy:0 rt_prio:0)
1532 # ----------------- 1434 # -----------------
1533 # => started at: ata_scsi_queuecmd 1435 # => started at: ata_scsi_queuecmd
1534 # => ended at: ata_scsi_queuecmd 1436 # => ended at: ata_scsi_queuecmd
1535 # 1437 #
1536 # 1438 #
1537 # _------=> CPU# 1439 # _------=> CPU#
1538 # / _-----=> irqs-off 1440 # / _-----=> irqs-off
1539 # | / _----=> need-resched 1441 # | / _----=> need-resched
1540 # || / _---=> hardirq/softir 1442 # || / _---=> hardirq/softirq
1541 # ||| / _--=> preempt-depth 1443 # ||| / _--=> preempt-depth
1542 # |||| / delay 1444 # |||| / delay
1543 # cmd pid ||||| time | caller 1445 # cmd pid ||||| time | caller
1544 # \ / ||||| \ | / 1446 # \ / ||||| \ | /
1545 bash-2042 3d... 0us : _raw_spin_l 1447 bash-2042 3d... 0us : _raw_spin_lock_irqsave <-ata_scsi_queuecmd
1546 bash-2042 3d... 0us : add_preempt 1448 bash-2042 3d... 0us : add_preempt_count <-_raw_spin_lock_irqsave
1547 bash-2042 3d..1 1us : ata_scsi_fi 1449 bash-2042 3d..1 1us : ata_scsi_find_dev <-ata_scsi_queuecmd
1548 bash-2042 3d..1 1us : __ata_scsi_ 1450 bash-2042 3d..1 1us : __ata_scsi_find_dev <-ata_scsi_find_dev
1549 bash-2042 3d..1 2us : ata_find_de 1451 bash-2042 3d..1 2us : ata_find_dev.part.14 <-__ata_scsi_find_dev
1550 bash-2042 3d..1 2us : ata_qc_new_ 1452 bash-2042 3d..1 2us : ata_qc_new_init <-__ata_scsi_queuecmd
1551 bash-2042 3d..1 3us : ata_sg_init 1453 bash-2042 3d..1 3us : ata_sg_init <-__ata_scsi_queuecmd
1552 bash-2042 3d..1 4us : ata_scsi_rw 1454 bash-2042 3d..1 4us : ata_scsi_rw_xlat <-__ata_scsi_queuecmd
1553 bash-2042 3d..1 4us : ata_build_r 1455 bash-2042 3d..1 4us : ata_build_rw_tf <-ata_scsi_rw_xlat
1554 [...] 1456 [...]
1555 bash-2042 3d..1 67us : delay_tsc < 1457 bash-2042 3d..1 67us : delay_tsc <-__delay
1556 bash-2042 3d..1 67us : add_preempt 1458 bash-2042 3d..1 67us : add_preempt_count <-delay_tsc
1557 bash-2042 3d..2 67us : sub_preempt 1459 bash-2042 3d..2 67us : sub_preempt_count <-delay_tsc
1558 bash-2042 3d..1 67us : add_preempt 1460 bash-2042 3d..1 67us : add_preempt_count <-delay_tsc
1559 bash-2042 3d..2 68us : sub_preempt 1461 bash-2042 3d..2 68us : sub_preempt_count <-delay_tsc
1560 bash-2042 3d..1 68us+: ata_bmdma_s 1462 bash-2042 3d..1 68us+: ata_bmdma_start <-ata_bmdma_qc_issue
1561 bash-2042 3d..1 71us : _raw_spin_u 1463 bash-2042 3d..1 71us : _raw_spin_unlock_irqrestore <-ata_scsi_queuecmd
1562 bash-2042 3d..1 71us : _raw_spin_u 1464 bash-2042 3d..1 71us : _raw_spin_unlock_irqrestore <-ata_scsi_queuecmd
1563 bash-2042 3d..1 72us+: trace_hardi 1465 bash-2042 3d..1 72us+: trace_hardirqs_on <-ata_scsi_queuecmd
1564 bash-2042 3d..1 120us : <stack trac 1466 bash-2042 3d..1 120us : <stack trace>
1565 => _raw_spin_unlock_irqrestore 1467 => _raw_spin_unlock_irqrestore
1566 => ata_scsi_queuecmd 1468 => ata_scsi_queuecmd
1567 => scsi_dispatch_cmd 1469 => scsi_dispatch_cmd
1568 => scsi_request_fn 1470 => scsi_request_fn
1569 => __blk_run_queue_uncond 1471 => __blk_run_queue_uncond
1570 => __blk_run_queue 1472 => __blk_run_queue
1571 => blk_queue_bio 1473 => blk_queue_bio
1572 => submit_bio_noacct 1474 => submit_bio_noacct
1573 => submit_bio 1475 => submit_bio
1574 => submit_bh 1476 => submit_bh
1575 => __ext3_get_inode_loc 1477 => __ext3_get_inode_loc
1576 => ext3_iget 1478 => ext3_iget
1577 => ext3_lookup 1479 => ext3_lookup
1578 => lookup_real 1480 => lookup_real
1579 => __lookup_hash 1481 => __lookup_hash
1580 => walk_component 1482 => walk_component
1581 => lookup_last 1483 => lookup_last
1582 => path_lookupat 1484 => path_lookupat
1583 => filename_lookup 1485 => filename_lookup
1584 => user_path_at_empty 1486 => user_path_at_empty
1585 => user_path_at 1487 => user_path_at
1586 => vfs_fstatat 1488 => vfs_fstatat
1587 => vfs_stat 1489 => vfs_stat
1588 => sys_newstat 1490 => sys_newstat
1589 => system_call_fastpath 1491 => system_call_fastpath
1590 1492
1591 1493
1592 Here we traced a 71 microsecond latency. But 1494 Here we traced a 71 microsecond latency. But we also see all the
1593 functions that were called during that time. 1495 functions that were called during that time. Note that by
1594 enabling function tracing, we incur an added 1496 enabling function tracing, we incur an added overhead. This
1595 overhead may extend the latency times. But ne 1497 overhead may extend the latency times. But nevertheless, this
1596 trace has provided some very helpful debuggin 1498 trace has provided some very helpful debugging information.
1597 1499
1598 If we prefer function graph output instead of 1500 If we prefer function graph output instead of function, we can set
1599 display-graph option:: 1501 display-graph option::
1600 1502
1601 with echo 1 > options/display-graph 1503 with echo 1 > options/display-graph
1602 1504
1603 # tracer: irqsoff 1505 # tracer: irqsoff
1604 # 1506 #
1605 # irqsoff latency trace v1.1.5 on 4.20.0-rc 1507 # irqsoff latency trace v1.1.5 on 4.20.0-rc6+
1606 # ----------------------------------------- 1508 # --------------------------------------------------------------------
1607 # latency: 3751 us, #274/274, CPU#0 | (M:de 1509 # latency: 3751 us, #274/274, CPU#0 | (M:desktop VP:0, KP:0, SP:0 HP:0 #P:4)
1608 # ----------------- 1510 # -----------------
1609 # | task: bash-1507 (uid:0 nice:0 policy 1511 # | task: bash-1507 (uid:0 nice:0 policy:0 rt_prio:0)
1610 # ----------------- 1512 # -----------------
1611 # => started at: free_debug_processing 1513 # => started at: free_debug_processing
1612 # => ended at: return_to_handler 1514 # => ended at: return_to_handler
1613 # 1515 #
1614 # 1516 #
1615 # _-- 1517 # _-----=> irqs-off
1616 # / _- 1518 # / _----=> need-resched
1617 # | / _ 1519 # | / _---=> hardirq/softirq
1618 # || / 1520 # || / _--=> preempt-depth
1619 # ||| / 1521 # ||| /
1620 # REL TIME CPU TASK/PID |||| 1522 # REL TIME CPU TASK/PID |||| DURATION FUNCTION CALLS
1621 # | | | | |||| 1523 # | | | | |||| | | | | | |
1622 0 us | 0) bash-1507 | d... 1524 0 us | 0) bash-1507 | d... | 0.000 us | _raw_spin_lock_irqsave();
1623 0 us | 0) bash-1507 | d..1 1525 0 us | 0) bash-1507 | d..1 | 0.378 us | do_raw_spin_trylock();
1624 1 us | 0) bash-1507 | d..2 1526 1 us | 0) bash-1507 | d..2 | | set_track() {
1625 2 us | 0) bash-1507 | d..2 1527 2 us | 0) bash-1507 | d..2 | | save_stack_trace() {
1626 2 us | 0) bash-1507 | d..2 1528 2 us | 0) bash-1507 | d..2 | | __save_stack_trace() {
1627 3 us | 0) bash-1507 | d..2 1529 3 us | 0) bash-1507 | d..2 | | __unwind_start() {
1628 3 us | 0) bash-1507 | d..2 1530 3 us | 0) bash-1507 | d..2 | | get_stack_info() {
1629 3 us | 0) bash-1507 | d..2 1531 3 us | 0) bash-1507 | d..2 | 0.351 us | in_task_stack();
1630 4 us | 0) bash-1507 | d..2 1532 4 us | 0) bash-1507 | d..2 | 1.107 us | }
1631 [...] 1533 [...]
1632 3750 us | 0) bash-1507 | d..1 1534 3750 us | 0) bash-1507 | d..1 | 0.516 us | do_raw_spin_unlock();
1633 3750 us | 0) bash-1507 | d..1 1535 3750 us | 0) bash-1507 | d..1 | 0.000 us | _raw_spin_unlock_irqrestore();
1634 3764 us | 0) bash-1507 | d..1 1536 3764 us | 0) bash-1507 | d..1 | 0.000 us | tracer_hardirqs_on();
1635 bash-1507 0d..1 3792us : <stack trac 1537 bash-1507 0d..1 3792us : <stack trace>
1636 => free_debug_processing 1538 => free_debug_processing
1637 => __slab_free 1539 => __slab_free
1638 => kmem_cache_free 1540 => kmem_cache_free
1639 => vm_area_free 1541 => vm_area_free
1640 => remove_vma 1542 => remove_vma
1641 => exit_mmap 1543 => exit_mmap
1642 => mmput 1544 => mmput
1643 => begin_new_exec 1545 => begin_new_exec
1644 => load_elf_binary 1546 => load_elf_binary
1645 => search_binary_handler 1547 => search_binary_handler
1646 => __do_execve_file.isra.32 1548 => __do_execve_file.isra.32
1647 => __x64_sys_execve 1549 => __x64_sys_execve
1648 => do_syscall_64 1550 => do_syscall_64
1649 => entry_SYSCALL_64_after_hwframe 1551 => entry_SYSCALL_64_after_hwframe
1650 1552
1651 preemptoff 1553 preemptoff
1652 ---------- 1554 ----------
1653 1555
1654 When preemption is disabled, we may be able t 1556 When preemption is disabled, we may be able to receive
1655 interrupts but the task cannot be preempted a 1557 interrupts but the task cannot be preempted and a higher
1656 priority task must wait for preemption to be 1558 priority task must wait for preemption to be enabled again
1657 before it can preempt a lower priority task. 1559 before it can preempt a lower priority task.
1658 1560
1659 The preemptoff tracer traces the places that 1561 The preemptoff tracer traces the places that disable preemption.
1660 Like the irqsoff tracer, it records the maxim 1562 Like the irqsoff tracer, it records the maximum latency for
1661 which preemption was disabled. The control of 1563 which preemption was disabled. The control of preemptoff tracer
1662 is much like the irqsoff tracer. 1564 is much like the irqsoff tracer.
1663 :: 1565 ::
1664 1566
1665 # echo 0 > options/function-trace 1567 # echo 0 > options/function-trace
1666 # echo preemptoff > current_tracer 1568 # echo preemptoff > current_tracer
1667 # echo 1 > tracing_on 1569 # echo 1 > tracing_on
1668 # echo 0 > tracing_max_latency 1570 # echo 0 > tracing_max_latency
1669 # ls -ltr 1571 # ls -ltr
1670 [...] 1572 [...]
1671 # echo 0 > tracing_on 1573 # echo 0 > tracing_on
1672 # cat trace 1574 # cat trace
1673 # tracer: preemptoff 1575 # tracer: preemptoff
1674 # 1576 #
1675 # preemptoff latency trace v1.1.5 on 3.8.0- 1577 # preemptoff latency trace v1.1.5 on 3.8.0-test+
1676 # ----------------------------------------- 1578 # --------------------------------------------------------------------
1677 # latency: 46 us, #4/4, CPU#1 | (M:preempt 1579 # latency: 46 us, #4/4, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
1678 # ----------------- 1580 # -----------------
1679 # | task: sshd-1991 (uid:0 nice:0 policy 1581 # | task: sshd-1991 (uid:0 nice:0 policy:0 rt_prio:0)
1680 # ----------------- 1582 # -----------------
1681 # => started at: do_IRQ 1583 # => started at: do_IRQ
1682 # => ended at: do_IRQ 1584 # => ended at: do_IRQ
1683 # 1585 #
1684 # 1586 #
1685 # _------=> CPU# 1587 # _------=> CPU#
1686 # / _-----=> irqs-off 1588 # / _-----=> irqs-off
1687 # | / _----=> need-resched 1589 # | / _----=> need-resched
1688 # || / _---=> hardirq/softir 1590 # || / _---=> hardirq/softirq
1689 # ||| / _--=> preempt-depth 1591 # ||| / _--=> preempt-depth
1690 # |||| / delay 1592 # |||| / delay
1691 # cmd pid ||||| time | caller 1593 # cmd pid ||||| time | caller
1692 # \ / ||||| \ | / 1594 # \ / ||||| \ | /
1693 sshd-1991 1d.h. 0us+: irq_enter < 1595 sshd-1991 1d.h. 0us+: irq_enter <-do_IRQ
1694 sshd-1991 1d..1 46us : irq_exit <- 1596 sshd-1991 1d..1 46us : irq_exit <-do_IRQ
1695 sshd-1991 1d..1 47us+: trace_preem 1597 sshd-1991 1d..1 47us+: trace_preempt_on <-do_IRQ
1696 sshd-1991 1d..1 52us : <stack trac 1598 sshd-1991 1d..1 52us : <stack trace>
1697 => sub_preempt_count 1599 => sub_preempt_count
1698 => irq_exit 1600 => irq_exit
1699 => do_IRQ 1601 => do_IRQ
1700 => ret_from_intr 1602 => ret_from_intr
1701 1603
1702 1604
1703 This has some more changes. Preemption was di 1605 This has some more changes. Preemption was disabled when an
1704 interrupt came in (notice the 'h'), and was e 1606 interrupt came in (notice the 'h'), and was enabled on exit.
1705 But we also see that interrupts have been dis 1607 But we also see that interrupts have been disabled when entering
1706 the preempt off section and leaving it (the ' 1608 the preempt off section and leaving it (the 'd'). We do not know if
1707 interrupts were enabled in the mean time or s 1609 interrupts were enabled in the mean time or shortly after this
1708 was over. 1610 was over.
1709 :: 1611 ::
1710 1612
1711 # tracer: preemptoff 1613 # tracer: preemptoff
1712 # 1614 #
1713 # preemptoff latency trace v1.1.5 on 3.8.0- 1615 # preemptoff latency trace v1.1.5 on 3.8.0-test+
1714 # ----------------------------------------- 1616 # --------------------------------------------------------------------
1715 # latency: 83 us, #241/241, CPU#1 | (M:pree 1617 # latency: 83 us, #241/241, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
1716 # ----------------- 1618 # -----------------
1717 # | task: bash-1994 (uid:0 nice:0 policy 1619 # | task: bash-1994 (uid:0 nice:0 policy:0 rt_prio:0)
1718 # ----------------- 1620 # -----------------
1719 # => started at: wake_up_new_task 1621 # => started at: wake_up_new_task
1720 # => ended at: task_rq_unlock 1622 # => ended at: task_rq_unlock
1721 # 1623 #
1722 # 1624 #
1723 # _------=> CPU# 1625 # _------=> CPU#
1724 # / _-----=> irqs-off 1626 # / _-----=> irqs-off
1725 # | / _----=> need-resched 1627 # | / _----=> need-resched
1726 # || / _---=> hardirq/softir 1628 # || / _---=> hardirq/softirq
1727 # ||| / _--=> preempt-depth 1629 # ||| / _--=> preempt-depth
1728 # |||| / delay 1630 # |||| / delay
1729 # cmd pid ||||| time | caller 1631 # cmd pid ||||| time | caller
1730 # \ / ||||| \ | / 1632 # \ / ||||| \ | /
1731 bash-1994 1d..1 0us : _raw_spin_l 1633 bash-1994 1d..1 0us : _raw_spin_lock_irqsave <-wake_up_new_task
1732 bash-1994 1d..1 0us : select_task 1634 bash-1994 1d..1 0us : select_task_rq_fair <-select_task_rq
1733 bash-1994 1d..1 1us : __rcu_read_ 1635 bash-1994 1d..1 1us : __rcu_read_lock <-select_task_rq_fair
1734 bash-1994 1d..1 1us : source_load 1636 bash-1994 1d..1 1us : source_load <-select_task_rq_fair
1735 bash-1994 1d..1 1us : source_load 1637 bash-1994 1d..1 1us : source_load <-select_task_rq_fair
1736 [...] 1638 [...]
1737 bash-1994 1d..1 12us : irq_enter < 1639 bash-1994 1d..1 12us : irq_enter <-smp_apic_timer_interrupt
1738 bash-1994 1d..1 12us : rcu_irq_ent 1640 bash-1994 1d..1 12us : rcu_irq_enter <-irq_enter
1739 bash-1994 1d..1 13us : add_preempt 1641 bash-1994 1d..1 13us : add_preempt_count <-irq_enter
1740 bash-1994 1d.h1 13us : exit_idle < 1642 bash-1994 1d.h1 13us : exit_idle <-smp_apic_timer_interrupt
1741 bash-1994 1d.h1 13us : hrtimer_int 1643 bash-1994 1d.h1 13us : hrtimer_interrupt <-smp_apic_timer_interrupt
1742 bash-1994 1d.h1 13us : _raw_spin_l 1644 bash-1994 1d.h1 13us : _raw_spin_lock <-hrtimer_interrupt
1743 bash-1994 1d.h1 14us : add_preempt 1645 bash-1994 1d.h1 14us : add_preempt_count <-_raw_spin_lock
1744 bash-1994 1d.h2 14us : ktime_get_u 1646 bash-1994 1d.h2 14us : ktime_get_update_offsets <-hrtimer_interrupt
1745 [...] 1647 [...]
1746 bash-1994 1d.h1 35us : lapic_next_ 1648 bash-1994 1d.h1 35us : lapic_next_event <-clockevents_program_event
1747 bash-1994 1d.h1 35us : irq_exit <- 1649 bash-1994 1d.h1 35us : irq_exit <-smp_apic_timer_interrupt
1748 bash-1994 1d.h1 36us : sub_preempt 1650 bash-1994 1d.h1 36us : sub_preempt_count <-irq_exit
1749 bash-1994 1d..2 36us : do_softirq 1651 bash-1994 1d..2 36us : do_softirq <-irq_exit
1750 bash-1994 1d..2 36us : __do_softir 1652 bash-1994 1d..2 36us : __do_softirq <-call_softirq
1751 bash-1994 1d..2 36us : __local_bh_ 1653 bash-1994 1d..2 36us : __local_bh_disable <-__do_softirq
1752 bash-1994 1d.s2 37us : add_preempt 1654 bash-1994 1d.s2 37us : add_preempt_count <-_raw_spin_lock_irq
1753 bash-1994 1d.s3 38us : _raw_spin_u 1655 bash-1994 1d.s3 38us : _raw_spin_unlock <-run_timer_softirq
1754 bash-1994 1d.s3 39us : sub_preempt 1656 bash-1994 1d.s3 39us : sub_preempt_count <-_raw_spin_unlock
1755 bash-1994 1d.s2 39us : call_timer_ 1657 bash-1994 1d.s2 39us : call_timer_fn <-run_timer_softirq
1756 [...] 1658 [...]
1757 bash-1994 1dNs2 81us : cpu_needs_a 1659 bash-1994 1dNs2 81us : cpu_needs_another_gp <-rcu_process_callbacks
1758 bash-1994 1dNs2 82us : __local_bh_ 1660 bash-1994 1dNs2 82us : __local_bh_enable <-__do_softirq
1759 bash-1994 1dNs2 82us : sub_preempt 1661 bash-1994 1dNs2 82us : sub_preempt_count <-__local_bh_enable
1760 bash-1994 1dN.2 82us : idle_cpu <- 1662 bash-1994 1dN.2 82us : idle_cpu <-irq_exit
1761 bash-1994 1dN.2 83us : rcu_irq_exi 1663 bash-1994 1dN.2 83us : rcu_irq_exit <-irq_exit
1762 bash-1994 1dN.2 83us : sub_preempt 1664 bash-1994 1dN.2 83us : sub_preempt_count <-irq_exit
1763 bash-1994 1.N.1 84us : _raw_spin_u 1665 bash-1994 1.N.1 84us : _raw_spin_unlock_irqrestore <-task_rq_unlock
1764 bash-1994 1.N.1 84us+: trace_preem 1666 bash-1994 1.N.1 84us+: trace_preempt_on <-task_rq_unlock
1765 bash-1994 1.N.1 104us : <stack trac 1667 bash-1994 1.N.1 104us : <stack trace>
1766 => sub_preempt_count 1668 => sub_preempt_count
1767 => _raw_spin_unlock_irqrestore 1669 => _raw_spin_unlock_irqrestore
1768 => task_rq_unlock 1670 => task_rq_unlock
1769 => wake_up_new_task 1671 => wake_up_new_task
1770 => do_fork 1672 => do_fork
1771 => sys_clone 1673 => sys_clone
1772 => stub_clone 1674 => stub_clone
1773 1675
1774 1676
1775 The above is an example of the preemptoff tra 1677 The above is an example of the preemptoff trace with
1776 function-trace set. Here we see that interrup 1678 function-trace set. Here we see that interrupts were not disabled
1777 the entire time. The irq_enter code lets us k 1679 the entire time. The irq_enter code lets us know that we entered
1778 an interrupt 'h'. Before that, the functions 1680 an interrupt 'h'. Before that, the functions being traced still
1779 show that it is not in an interrupt, but we c 1681 show that it is not in an interrupt, but we can see from the
1780 functions themselves that this is not the cas 1682 functions themselves that this is not the case.
1781 1683
1782 preemptirqsoff 1684 preemptirqsoff
1783 -------------- 1685 --------------
1784 1686
1785 Knowing the locations that have interrupts di 1687 Knowing the locations that have interrupts disabled or
1786 preemption disabled for the longest times is 1688 preemption disabled for the longest times is helpful. But
1787 sometimes we would like to know when either p 1689 sometimes we would like to know when either preemption and/or
1788 interrupts are disabled. 1690 interrupts are disabled.
1789 1691
1790 Consider the following code:: 1692 Consider the following code::
1791 1693
1792 local_irq_disable(); 1694 local_irq_disable();
1793 call_function_with_irqs_off(); 1695 call_function_with_irqs_off();
1794 preempt_disable(); 1696 preempt_disable();
1795 call_function_with_irqs_and_preemption_of 1697 call_function_with_irqs_and_preemption_off();
1796 local_irq_enable(); 1698 local_irq_enable();
1797 call_function_with_preemption_off(); 1699 call_function_with_preemption_off();
1798 preempt_enable(); 1700 preempt_enable();
1799 1701
1800 The irqsoff tracer will record the total leng 1702 The irqsoff tracer will record the total length of
1801 call_function_with_irqs_off() and 1703 call_function_with_irqs_off() and
1802 call_function_with_irqs_and_preemption_off(). 1704 call_function_with_irqs_and_preemption_off().
1803 1705
1804 The preemptoff tracer will record the total l 1706 The preemptoff tracer will record the total length of
1805 call_function_with_irqs_and_preemption_off() 1707 call_function_with_irqs_and_preemption_off() and
1806 call_function_with_preemption_off(). 1708 call_function_with_preemption_off().
1807 1709
1808 But neither will trace the time that interrup 1710 But neither will trace the time that interrupts and/or
1809 preemption is disabled. This total time is th 1711 preemption is disabled. This total time is the time that we can
1810 not schedule. To record this time, use the pr 1712 not schedule. To record this time, use the preemptirqsoff
1811 tracer. 1713 tracer.
1812 1714
1813 Again, using this trace is much like the irqs 1715 Again, using this trace is much like the irqsoff and preemptoff
1814 tracers. 1716 tracers.
1815 :: 1717 ::
1816 1718
1817 # echo 0 > options/function-trace 1719 # echo 0 > options/function-trace
1818 # echo preemptirqsoff > current_tracer 1720 # echo preemptirqsoff > current_tracer
1819 # echo 1 > tracing_on 1721 # echo 1 > tracing_on
1820 # echo 0 > tracing_max_latency 1722 # echo 0 > tracing_max_latency
1821 # ls -ltr 1723 # ls -ltr
1822 [...] 1724 [...]
1823 # echo 0 > tracing_on 1725 # echo 0 > tracing_on
1824 # cat trace 1726 # cat trace
1825 # tracer: preemptirqsoff 1727 # tracer: preemptirqsoff
1826 # 1728 #
1827 # preemptirqsoff latency trace v1.1.5 on 3. 1729 # preemptirqsoff latency trace v1.1.5 on 3.8.0-test+
1828 # ----------------------------------------- 1730 # --------------------------------------------------------------------
1829 # latency: 100 us, #4/4, CPU#3 | (M:preempt 1731 # latency: 100 us, #4/4, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
1830 # ----------------- 1732 # -----------------
1831 # | task: ls-2230 (uid:0 nice:0 policy:0 1733 # | task: ls-2230 (uid:0 nice:0 policy:0 rt_prio:0)
1832 # ----------------- 1734 # -----------------
1833 # => started at: ata_scsi_queuecmd 1735 # => started at: ata_scsi_queuecmd
1834 # => ended at: ata_scsi_queuecmd 1736 # => ended at: ata_scsi_queuecmd
1835 # 1737 #
1836 # 1738 #
1837 # _------=> CPU# 1739 # _------=> CPU#
1838 # / _-----=> irqs-off 1740 # / _-----=> irqs-off
1839 # | / _----=> need-resched 1741 # | / _----=> need-resched
1840 # || / _---=> hardirq/softir 1742 # || / _---=> hardirq/softirq
1841 # ||| / _--=> preempt-depth 1743 # ||| / _--=> preempt-depth
1842 # |||| / delay 1744 # |||| / delay
1843 # cmd pid ||||| time | caller 1745 # cmd pid ||||| time | caller
1844 # \ / ||||| \ | / 1746 # \ / ||||| \ | /
1845 ls-2230 3d... 0us+: _raw_spin_l 1747 ls-2230 3d... 0us+: _raw_spin_lock_irqsave <-ata_scsi_queuecmd
1846 ls-2230 3...1 100us : _raw_spin_u 1748 ls-2230 3...1 100us : _raw_spin_unlock_irqrestore <-ata_scsi_queuecmd
1847 ls-2230 3...1 101us+: trace_preem 1749 ls-2230 3...1 101us+: trace_preempt_on <-ata_scsi_queuecmd
1848 ls-2230 3...1 111us : <stack trac 1750 ls-2230 3...1 111us : <stack trace>
1849 => sub_preempt_count 1751 => sub_preempt_count
1850 => _raw_spin_unlock_irqrestore 1752 => _raw_spin_unlock_irqrestore
1851 => ata_scsi_queuecmd 1753 => ata_scsi_queuecmd
1852 => scsi_dispatch_cmd 1754 => scsi_dispatch_cmd
1853 => scsi_request_fn 1755 => scsi_request_fn
1854 => __blk_run_queue_uncond 1756 => __blk_run_queue_uncond
1855 => __blk_run_queue 1757 => __blk_run_queue
1856 => blk_queue_bio 1758 => blk_queue_bio
1857 => submit_bio_noacct 1759 => submit_bio_noacct
1858 => submit_bio 1760 => submit_bio
1859 => submit_bh 1761 => submit_bh
1860 => ext3_bread 1762 => ext3_bread
1861 => ext3_dir_bread 1763 => ext3_dir_bread
1862 => htree_dirblock_to_tree 1764 => htree_dirblock_to_tree
1863 => ext3_htree_fill_tree 1765 => ext3_htree_fill_tree
1864 => ext3_readdir 1766 => ext3_readdir
1865 => vfs_readdir 1767 => vfs_readdir
1866 => sys_getdents 1768 => sys_getdents
1867 => system_call_fastpath 1769 => system_call_fastpath
1868 1770
1869 1771
1870 The trace_hardirqs_off_thunk is called from a 1772 The trace_hardirqs_off_thunk is called from assembly on x86 when
1871 interrupts are disabled in the assembly code. 1773 interrupts are disabled in the assembly code. Without the
1872 function tracing, we do not know if interrupt 1774 function tracing, we do not know if interrupts were enabled
1873 within the preemption points. We do see that 1775 within the preemption points. We do see that it started with
1874 preemption enabled. 1776 preemption enabled.
1875 1777
1876 Here is a trace with function-trace set:: 1778 Here is a trace with function-trace set::
1877 1779
1878 # tracer: preemptirqsoff 1780 # tracer: preemptirqsoff
1879 # 1781 #
1880 # preemptirqsoff latency trace v1.1.5 on 3. 1782 # preemptirqsoff latency trace v1.1.5 on 3.8.0-test+
1881 # ----------------------------------------- 1783 # --------------------------------------------------------------------
1882 # latency: 161 us, #339/339, CPU#3 | (M:pre 1784 # latency: 161 us, #339/339, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
1883 # ----------------- 1785 # -----------------
1884 # | task: ls-2269 (uid:0 nice:0 policy:0 1786 # | task: ls-2269 (uid:0 nice:0 policy:0 rt_prio:0)
1885 # ----------------- 1787 # -----------------
1886 # => started at: schedule 1788 # => started at: schedule
1887 # => ended at: mutex_unlock 1789 # => ended at: mutex_unlock
1888 # 1790 #
1889 # 1791 #
1890 # _------=> CPU# 1792 # _------=> CPU#
1891 # / _-----=> irqs-off 1793 # / _-----=> irqs-off
1892 # | / _----=> need-resched 1794 # | / _----=> need-resched
1893 # || / _---=> hardirq/softir 1795 # || / _---=> hardirq/softirq
1894 # ||| / _--=> preempt-depth 1796 # ||| / _--=> preempt-depth
1895 # |||| / delay 1797 # |||| / delay
1896 # cmd pid ||||| time | caller 1798 # cmd pid ||||| time | caller
1897 # \ / ||||| \ | / 1799 # \ / ||||| \ | /
1898 kworker/-59 3...1 0us : __schedule 1800 kworker/-59 3...1 0us : __schedule <-schedule
1899 kworker/-59 3d..1 0us : rcu_preempt 1801 kworker/-59 3d..1 0us : rcu_preempt_qs <-rcu_note_context_switch
1900 kworker/-59 3d..1 1us : add_preempt 1802 kworker/-59 3d..1 1us : add_preempt_count <-_raw_spin_lock_irq
1901 kworker/-59 3d..2 1us : deactivate_ 1803 kworker/-59 3d..2 1us : deactivate_task <-__schedule
1902 kworker/-59 3d..2 1us : dequeue_tas 1804 kworker/-59 3d..2 1us : dequeue_task <-deactivate_task
1903 kworker/-59 3d..2 2us : update_rq_c 1805 kworker/-59 3d..2 2us : update_rq_clock <-dequeue_task
1904 kworker/-59 3d..2 2us : dequeue_tas 1806 kworker/-59 3d..2 2us : dequeue_task_fair <-dequeue_task
1905 kworker/-59 3d..2 2us : update_curr 1807 kworker/-59 3d..2 2us : update_curr <-dequeue_task_fair
1906 kworker/-59 3d..2 2us : update_min_ 1808 kworker/-59 3d..2 2us : update_min_vruntime <-update_curr
1907 kworker/-59 3d..2 3us : cpuacct_cha 1809 kworker/-59 3d..2 3us : cpuacct_charge <-update_curr
1908 kworker/-59 3d..2 3us : __rcu_read_ 1810 kworker/-59 3d..2 3us : __rcu_read_lock <-cpuacct_charge
1909 kworker/-59 3d..2 3us : __rcu_read_ 1811 kworker/-59 3d..2 3us : __rcu_read_unlock <-cpuacct_charge
1910 kworker/-59 3d..2 3us : update_cfs_ 1812 kworker/-59 3d..2 3us : update_cfs_rq_blocked_load <-dequeue_task_fair
1911 kworker/-59 3d..2 4us : clear_buddi 1813 kworker/-59 3d..2 4us : clear_buddies <-dequeue_task_fair
1912 kworker/-59 3d..2 4us : account_ent 1814 kworker/-59 3d..2 4us : account_entity_dequeue <-dequeue_task_fair
1913 kworker/-59 3d..2 4us : update_min_ 1815 kworker/-59 3d..2 4us : update_min_vruntime <-dequeue_task_fair
1914 kworker/-59 3d..2 4us : update_cfs_ 1816 kworker/-59 3d..2 4us : update_cfs_shares <-dequeue_task_fair
1915 kworker/-59 3d..2 5us : hrtick_upda 1817 kworker/-59 3d..2 5us : hrtick_update <-dequeue_task_fair
1916 kworker/-59 3d..2 5us : wq_worker_s 1818 kworker/-59 3d..2 5us : wq_worker_sleeping <-__schedule
1917 kworker/-59 3d..2 5us : kthread_dat 1819 kworker/-59 3d..2 5us : kthread_data <-wq_worker_sleeping
1918 kworker/-59 3d..2 5us : put_prev_ta 1820 kworker/-59 3d..2 5us : put_prev_task_fair <-__schedule
1919 kworker/-59 3d..2 6us : pick_next_t 1821 kworker/-59 3d..2 6us : pick_next_task_fair <-pick_next_task
1920 kworker/-59 3d..2 6us : clear_buddi 1822 kworker/-59 3d..2 6us : clear_buddies <-pick_next_task_fair
1921 kworker/-59 3d..2 6us : set_next_en 1823 kworker/-59 3d..2 6us : set_next_entity <-pick_next_task_fair
1922 kworker/-59 3d..2 6us : update_stat 1824 kworker/-59 3d..2 6us : update_stats_wait_end <-set_next_entity
1923 ls-2269 3d..2 7us : finish_task 1825 ls-2269 3d..2 7us : finish_task_switch <-__schedule
1924 ls-2269 3d..2 7us : _raw_spin_u 1826 ls-2269 3d..2 7us : _raw_spin_unlock_irq <-finish_task_switch
1925 ls-2269 3d..2 8us : do_IRQ <-re 1827 ls-2269 3d..2 8us : do_IRQ <-ret_from_intr
1926 ls-2269 3d..2 8us : irq_enter < 1828 ls-2269 3d..2 8us : irq_enter <-do_IRQ
1927 ls-2269 3d..2 8us : rcu_irq_ent 1829 ls-2269 3d..2 8us : rcu_irq_enter <-irq_enter
1928 ls-2269 3d..2 9us : add_preempt 1830 ls-2269 3d..2 9us : add_preempt_count <-irq_enter
1929 ls-2269 3d.h2 9us : exit_idle < 1831 ls-2269 3d.h2 9us : exit_idle <-do_IRQ
1930 [...] 1832 [...]
1931 ls-2269 3d.h3 20us : sub_preempt 1833 ls-2269 3d.h3 20us : sub_preempt_count <-_raw_spin_unlock
1932 ls-2269 3d.h2 20us : irq_exit <- 1834 ls-2269 3d.h2 20us : irq_exit <-do_IRQ
1933 ls-2269 3d.h2 21us : sub_preempt 1835 ls-2269 3d.h2 21us : sub_preempt_count <-irq_exit
1934 ls-2269 3d..3 21us : do_softirq 1836 ls-2269 3d..3 21us : do_softirq <-irq_exit
1935 ls-2269 3d..3 21us : __do_softir 1837 ls-2269 3d..3 21us : __do_softirq <-call_softirq
1936 ls-2269 3d..3 21us+: __local_bh_ 1838 ls-2269 3d..3 21us+: __local_bh_disable <-__do_softirq
1937 ls-2269 3d.s4 29us : sub_preempt 1839 ls-2269 3d.s4 29us : sub_preempt_count <-_local_bh_enable_ip
1938 ls-2269 3d.s5 29us : sub_preempt 1840 ls-2269 3d.s5 29us : sub_preempt_count <-_local_bh_enable_ip
1939 ls-2269 3d.s5 31us : do_IRQ <-re 1841 ls-2269 3d.s5 31us : do_IRQ <-ret_from_intr
1940 ls-2269 3d.s5 31us : irq_enter < 1842 ls-2269 3d.s5 31us : irq_enter <-do_IRQ
1941 ls-2269 3d.s5 31us : rcu_irq_ent 1843 ls-2269 3d.s5 31us : rcu_irq_enter <-irq_enter
1942 [...] 1844 [...]
1943 ls-2269 3d.s5 31us : rcu_irq_ent 1845 ls-2269 3d.s5 31us : rcu_irq_enter <-irq_enter
1944 ls-2269 3d.s5 32us : add_preempt 1846 ls-2269 3d.s5 32us : add_preempt_count <-irq_enter
1945 ls-2269 3d.H5 32us : exit_idle < 1847 ls-2269 3d.H5 32us : exit_idle <-do_IRQ
1946 ls-2269 3d.H5 32us : handle_irq 1848 ls-2269 3d.H5 32us : handle_irq <-do_IRQ
1947 ls-2269 3d.H5 32us : irq_to_desc 1849 ls-2269 3d.H5 32us : irq_to_desc <-handle_irq
1948 ls-2269 3d.H5 33us : handle_fast 1850 ls-2269 3d.H5 33us : handle_fasteoi_irq <-handle_irq
1949 [...] 1851 [...]
1950 ls-2269 3d.s5 158us : _raw_spin_u 1852 ls-2269 3d.s5 158us : _raw_spin_unlock_irqrestore <-rtl8139_poll
1951 ls-2269 3d.s3 158us : net_rps_act 1853 ls-2269 3d.s3 158us : net_rps_action_and_irq_enable.isra.65 <-net_rx_action
1952 ls-2269 3d.s3 159us : __local_bh_ 1854 ls-2269 3d.s3 159us : __local_bh_enable <-__do_softirq
1953 ls-2269 3d.s3 159us : sub_preempt 1855 ls-2269 3d.s3 159us : sub_preempt_count <-__local_bh_enable
1954 ls-2269 3d..3 159us : idle_cpu <- 1856 ls-2269 3d..3 159us : idle_cpu <-irq_exit
1955 ls-2269 3d..3 159us : rcu_irq_exi 1857 ls-2269 3d..3 159us : rcu_irq_exit <-irq_exit
1956 ls-2269 3d..3 160us : sub_preempt 1858 ls-2269 3d..3 160us : sub_preempt_count <-irq_exit
1957 ls-2269 3d... 161us : __mutex_unl 1859 ls-2269 3d... 161us : __mutex_unlock_slowpath <-mutex_unlock
1958 ls-2269 3d... 162us+: trace_hardi 1860 ls-2269 3d... 162us+: trace_hardirqs_on <-mutex_unlock
1959 ls-2269 3d... 186us : <stack trac 1861 ls-2269 3d... 186us : <stack trace>
1960 => __mutex_unlock_slowpath 1862 => __mutex_unlock_slowpath
1961 => mutex_unlock 1863 => mutex_unlock
1962 => process_output 1864 => process_output
1963 => n_tty_write 1865 => n_tty_write
1964 => tty_write 1866 => tty_write
1965 => vfs_write 1867 => vfs_write
1966 => sys_write 1868 => sys_write
1967 => system_call_fastpath 1869 => system_call_fastpath
1968 1870
1969 This is an interesting trace. It started with 1871 This is an interesting trace. It started with kworker running and
1970 scheduling out and ls taking over. But as soo 1872 scheduling out and ls taking over. But as soon as ls released the
1971 rq lock and enabled interrupts (but not preem 1873 rq lock and enabled interrupts (but not preemption) an interrupt
1972 triggered. When the interrupt finished, it st 1874 triggered. When the interrupt finished, it started running softirqs.
1973 But while the softirq was running, another in 1875 But while the softirq was running, another interrupt triggered.
1974 When an interrupt is running inside a softirq 1876 When an interrupt is running inside a softirq, the annotation is 'H'.
1975 1877
1976 1878
1977 wakeup 1879 wakeup
1978 ------ 1880 ------
1979 1881
1980 One common case that people are interested in 1882 One common case that people are interested in tracing is the
1981 time it takes for a task that is woken to act 1883 time it takes for a task that is woken to actually wake up.
1982 Now for non Real-Time tasks, this can be arbi 1884 Now for non Real-Time tasks, this can be arbitrary. But tracing
1983 it nonetheless can be interesting. !! 1885 it none the less can be interesting.
1984 1886
1985 Without function tracing:: 1887 Without function tracing::
1986 1888
1987 # echo 0 > options/function-trace 1889 # echo 0 > options/function-trace
1988 # echo wakeup > current_tracer 1890 # echo wakeup > current_tracer
1989 # echo 1 > tracing_on 1891 # echo 1 > tracing_on
1990 # echo 0 > tracing_max_latency 1892 # echo 0 > tracing_max_latency
1991 # chrt -f 5 sleep 1 1893 # chrt -f 5 sleep 1
1992 # echo 0 > tracing_on 1894 # echo 0 > tracing_on
1993 # cat trace 1895 # cat trace
1994 # tracer: wakeup 1896 # tracer: wakeup
1995 # 1897 #
1996 # wakeup latency trace v1.1.5 on 3.8.0-test 1898 # wakeup latency trace v1.1.5 on 3.8.0-test+
1997 # ----------------------------------------- 1899 # --------------------------------------------------------------------
1998 # latency: 15 us, #4/4, CPU#3 | (M:preempt 1900 # latency: 15 us, #4/4, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
1999 # ----------------- 1901 # -----------------
2000 # | task: kworker/3:1H-312 (uid:0 nice:- 1902 # | task: kworker/3:1H-312 (uid:0 nice:-20 policy:0 rt_prio:0)
2001 # ----------------- 1903 # -----------------
2002 # 1904 #
2003 # _------=> CPU# 1905 # _------=> CPU#
2004 # / _-----=> irqs-off 1906 # / _-----=> irqs-off
2005 # | / _----=> need-resched 1907 # | / _----=> need-resched
2006 # || / _---=> hardirq/softir 1908 # || / _---=> hardirq/softirq
2007 # ||| / _--=> preempt-depth 1909 # ||| / _--=> preempt-depth
2008 # |||| / delay 1910 # |||| / delay
2009 # cmd pid ||||| time | caller 1911 # cmd pid ||||| time | caller
2010 # \ / ||||| \ | / 1912 # \ / ||||| \ | /
2011 <idle>-0 3dNs7 0us : 0:120: 1913 <idle>-0 3dNs7 0us : 0:120:R + [003] 312:100:R kworker/3:1H
2012 <idle>-0 3dNs7 1us+: ttwu_do_act 1914 <idle>-0 3dNs7 1us+: ttwu_do_activate.constprop.87 <-try_to_wake_up
2013 <idle>-0 3d..3 15us : __schedule 1915 <idle>-0 3d..3 15us : __schedule <-schedule
2014 <idle>-0 3d..3 15us : 0:120: 1916 <idle>-0 3d..3 15us : 0:120:R ==> [003] 312:100:R kworker/3:1H
2015 1917
2016 The tracer only traces the highest priority t 1918 The tracer only traces the highest priority task in the system
2017 to avoid tracing the normal circumstances. He 1919 to avoid tracing the normal circumstances. Here we see that
2018 the kworker with a nice priority of -20 (not 1920 the kworker with a nice priority of -20 (not very nice), took
2019 just 15 microseconds from the time it woke up 1921 just 15 microseconds from the time it woke up, to the time it
2020 ran. 1922 ran.
2021 1923
2022 Non Real-Time tasks are not that interesting. 1924 Non Real-Time tasks are not that interesting. A more interesting
2023 trace is to concentrate only on Real-Time tas 1925 trace is to concentrate only on Real-Time tasks.
2024 1926
2025 wakeup_rt 1927 wakeup_rt
2026 --------- 1928 ---------
2027 1929
2028 In a Real-Time environment it is very importa 1930 In a Real-Time environment it is very important to know the
2029 wakeup time it takes for the highest priority 1931 wakeup time it takes for the highest priority task that is woken
2030 up to the time that it executes. This is also 1932 up to the time that it executes. This is also known as "schedule
2031 latency". I stress the point that this is abo 1933 latency". I stress the point that this is about RT tasks. It is
2032 also important to know the scheduling latency 1934 also important to know the scheduling latency of non-RT tasks,
2033 but the average schedule latency is better fo 1935 but the average schedule latency is better for non-RT tasks.
2034 Tools like LatencyTop are more appropriate fo 1936 Tools like LatencyTop are more appropriate for such
2035 measurements. 1937 measurements.
2036 1938
2037 Real-Time environments are interested in the 1939 Real-Time environments are interested in the worst case latency.
2038 That is the longest latency it takes for some 1940 That is the longest latency it takes for something to happen,
2039 and not the average. We can have a very fast 1941 and not the average. We can have a very fast scheduler that may
2040 only have a large latency once in a while, bu 1942 only have a large latency once in a while, but that would not
2041 work well with Real-Time tasks. The wakeup_r 1943 work well with Real-Time tasks. The wakeup_rt tracer was designed
2042 to record the worst case wakeups of RT tasks. 1944 to record the worst case wakeups of RT tasks. Non-RT tasks are
2043 not recorded because the tracer only records 1945 not recorded because the tracer only records one worst case and
2044 tracing non-RT tasks that are unpredictable w 1946 tracing non-RT tasks that are unpredictable will overwrite the
2045 worst case latency of RT tasks (just run the 1947 worst case latency of RT tasks (just run the normal wakeup
2046 tracer for a while to see that effect). 1948 tracer for a while to see that effect).
2047 1949
2048 Since this tracer only deals with RT tasks, w 1950 Since this tracer only deals with RT tasks, we will run this
2049 slightly differently than we did with the pre 1951 slightly differently than we did with the previous tracers.
2050 Instead of performing an 'ls', we will run 's 1952 Instead of performing an 'ls', we will run 'sleep 1' under
2051 'chrt' which changes the priority of the task 1953 'chrt' which changes the priority of the task.
2052 :: 1954 ::
2053 1955
2054 # echo 0 > options/function-trace 1956 # echo 0 > options/function-trace
2055 # echo wakeup_rt > current_tracer 1957 # echo wakeup_rt > current_tracer
2056 # echo 1 > tracing_on 1958 # echo 1 > tracing_on
2057 # echo 0 > tracing_max_latency 1959 # echo 0 > tracing_max_latency
2058 # chrt -f 5 sleep 1 1960 # chrt -f 5 sleep 1
2059 # echo 0 > tracing_on 1961 # echo 0 > tracing_on
2060 # cat trace 1962 # cat trace
2061 # tracer: wakeup 1963 # tracer: wakeup
2062 # 1964 #
2063 # tracer: wakeup_rt 1965 # tracer: wakeup_rt
2064 # 1966 #
2065 # wakeup_rt latency trace v1.1.5 on 3.8.0-t 1967 # wakeup_rt latency trace v1.1.5 on 3.8.0-test+
2066 # ----------------------------------------- 1968 # --------------------------------------------------------------------
2067 # latency: 5 us, #4/4, CPU#3 | (M:preempt V 1969 # latency: 5 us, #4/4, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
2068 # ----------------- 1970 # -----------------
2069 # | task: sleep-2389 (uid:0 nice:0 polic 1971 # | task: sleep-2389 (uid:0 nice:0 policy:1 rt_prio:5)
2070 # ----------------- 1972 # -----------------
2071 # 1973 #
2072 # _------=> CPU# 1974 # _------=> CPU#
2073 # / _-----=> irqs-off 1975 # / _-----=> irqs-off
2074 # | / _----=> need-resched 1976 # | / _----=> need-resched
2075 # || / _---=> hardirq/softir 1977 # || / _---=> hardirq/softirq
2076 # ||| / _--=> preempt-depth 1978 # ||| / _--=> preempt-depth
2077 # |||| / delay 1979 # |||| / delay
2078 # cmd pid ||||| time | caller 1980 # cmd pid ||||| time | caller
2079 # \ / ||||| \ | / 1981 # \ / ||||| \ | /
2080 <idle>-0 3d.h4 0us : 0:120: 1982 <idle>-0 3d.h4 0us : 0:120:R + [003] 2389: 94:R sleep
2081 <idle>-0 3d.h4 1us+: ttwu_do_act 1983 <idle>-0 3d.h4 1us+: ttwu_do_activate.constprop.87 <-try_to_wake_up
2082 <idle>-0 3d..3 5us : __schedule 1984 <idle>-0 3d..3 5us : __schedule <-schedule
2083 <idle>-0 3d..3 5us : 0:120: 1985 <idle>-0 3d..3 5us : 0:120:R ==> [003] 2389: 94:R sleep
2084 1986
2085 1987
2086 Running this on an idle system, we see that i 1988 Running this on an idle system, we see that it only took 5 microseconds
2087 to perform the task switch. Note, since the 1989 to perform the task switch. Note, since the trace point in the schedule
2088 is before the actual "switch", we stop the tr 1990 is before the actual "switch", we stop the tracing when the recorded task
2089 is about to schedule in. This may change if w 1991 is about to schedule in. This may change if we add a new marker at the
2090 end of the scheduler. 1992 end of the scheduler.
2091 1993
2092 Notice that the recorded task is 'sleep' with 1994 Notice that the recorded task is 'sleep' with the PID of 2389
2093 and it has an rt_prio of 5. This priority is 1995 and it has an rt_prio of 5. This priority is user-space priority
2094 and not the internal kernel priority. The pol 1996 and not the internal kernel priority. The policy is 1 for
2095 SCHED_FIFO and 2 for SCHED_RR. 1997 SCHED_FIFO and 2 for SCHED_RR.
2096 1998
2097 Note, that the trace data shows the internal 1999 Note, that the trace data shows the internal priority (99 - rtprio).
2098 :: 2000 ::
2099 2001
2100 <idle>-0 3d..3 5us : 0:120:R 2002 <idle>-0 3d..3 5us : 0:120:R ==> [003] 2389: 94:R sleep
2101 2003
2102 The 0:120:R means idle was running with a nic 2004 The 0:120:R means idle was running with a nice priority of 0 (120 - 120)
2103 and in the running state 'R'. The sleep task 2005 and in the running state 'R'. The sleep task was scheduled in with
2104 2389: 94:R. That is the priority is the kerne 2006 2389: 94:R. That is the priority is the kernel rtprio (99 - 5 = 94)
2105 and it too is in the running state. 2007 and it too is in the running state.
2106 2008
2107 Doing the same with chrt -r 5 and function-tr 2009 Doing the same with chrt -r 5 and function-trace set.
2108 :: 2010 ::
2109 2011
2110 echo 1 > options/function-trace 2012 echo 1 > options/function-trace
2111 2013
2112 # tracer: wakeup_rt 2014 # tracer: wakeup_rt
2113 # 2015 #
2114 # wakeup_rt latency trace v1.1.5 on 3.8.0-t 2016 # wakeup_rt latency trace v1.1.5 on 3.8.0-test+
2115 # ----------------------------------------- 2017 # --------------------------------------------------------------------
2116 # latency: 29 us, #85/85, CPU#3 | (M:preemp 2018 # latency: 29 us, #85/85, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
2117 # ----------------- 2019 # -----------------
2118 # | task: sleep-2448 (uid:0 nice:0 polic 2020 # | task: sleep-2448 (uid:0 nice:0 policy:1 rt_prio:5)
2119 # ----------------- 2021 # -----------------
2120 # 2022 #
2121 # _------=> CPU# 2023 # _------=> CPU#
2122 # / _-----=> irqs-off 2024 # / _-----=> irqs-off
2123 # | / _----=> need-resched 2025 # | / _----=> need-resched
2124 # || / _---=> hardirq/softir 2026 # || / _---=> hardirq/softirq
2125 # ||| / _--=> preempt-depth 2027 # ||| / _--=> preempt-depth
2126 # |||| / delay 2028 # |||| / delay
2127 # cmd pid ||||| time | caller 2029 # cmd pid ||||| time | caller
2128 # \ / ||||| \ | / 2030 # \ / ||||| \ | /
2129 <idle>-0 3d.h4 1us+: 0:120: 2031 <idle>-0 3d.h4 1us+: 0:120:R + [003] 2448: 94:R sleep
2130 <idle>-0 3d.h4 2us : ttwu_do_act 2032 <idle>-0 3d.h4 2us : ttwu_do_activate.constprop.87 <-try_to_wake_up
2131 <idle>-0 3d.h3 3us : check_preem 2033 <idle>-0 3d.h3 3us : check_preempt_curr <-ttwu_do_wakeup
2132 <idle>-0 3d.h3 3us : resched_cur 2034 <idle>-0 3d.h3 3us : resched_curr <-check_preempt_curr
2133 <idle>-0 3dNh3 4us : task_woken_ 2035 <idle>-0 3dNh3 4us : task_woken_rt <-ttwu_do_wakeup
2134 <idle>-0 3dNh3 4us : _raw_spin_u 2036 <idle>-0 3dNh3 4us : _raw_spin_unlock <-try_to_wake_up
2135 <idle>-0 3dNh3 4us : sub_preempt 2037 <idle>-0 3dNh3 4us : sub_preempt_count <-_raw_spin_unlock
2136 <idle>-0 3dNh2 5us : ttwu_stat < 2038 <idle>-0 3dNh2 5us : ttwu_stat <-try_to_wake_up
2137 <idle>-0 3dNh2 5us : _raw_spin_u 2039 <idle>-0 3dNh2 5us : _raw_spin_unlock_irqrestore <-try_to_wake_up
2138 <idle>-0 3dNh2 6us : sub_preempt 2040 <idle>-0 3dNh2 6us : sub_preempt_count <-_raw_spin_unlock_irqrestore
2139 <idle>-0 3dNh1 6us : _raw_spin_l 2041 <idle>-0 3dNh1 6us : _raw_spin_lock <-__run_hrtimer
2140 <idle>-0 3dNh1 6us : add_preempt 2042 <idle>-0 3dNh1 6us : add_preempt_count <-_raw_spin_lock
2141 <idle>-0 3dNh2 7us : _raw_spin_u 2043 <idle>-0 3dNh2 7us : _raw_spin_unlock <-hrtimer_interrupt
2142 <idle>-0 3dNh2 7us : sub_preempt 2044 <idle>-0 3dNh2 7us : sub_preempt_count <-_raw_spin_unlock
2143 <idle>-0 3dNh1 7us : tick_progra 2045 <idle>-0 3dNh1 7us : tick_program_event <-hrtimer_interrupt
2144 <idle>-0 3dNh1 7us : clockevents 2046 <idle>-0 3dNh1 7us : clockevents_program_event <-tick_program_event
2145 <idle>-0 3dNh1 8us : ktime_get < 2047 <idle>-0 3dNh1 8us : ktime_get <-clockevents_program_event
2146 <idle>-0 3dNh1 8us : lapic_next_ 2048 <idle>-0 3dNh1 8us : lapic_next_event <-clockevents_program_event
2147 <idle>-0 3dNh1 8us : irq_exit <- 2049 <idle>-0 3dNh1 8us : irq_exit <-smp_apic_timer_interrupt
2148 <idle>-0 3dNh1 9us : sub_preempt 2050 <idle>-0 3dNh1 9us : sub_preempt_count <-irq_exit
2149 <idle>-0 3dN.2 9us : idle_cpu <- 2051 <idle>-0 3dN.2 9us : idle_cpu <-irq_exit
2150 <idle>-0 3dN.2 9us : rcu_irq_exi 2052 <idle>-0 3dN.2 9us : rcu_irq_exit <-irq_exit
2151 <idle>-0 3dN.2 10us : rcu_eqs_ent 2053 <idle>-0 3dN.2 10us : rcu_eqs_enter_common.isra.45 <-rcu_irq_exit
2152 <idle>-0 3dN.2 10us : sub_preempt 2054 <idle>-0 3dN.2 10us : sub_preempt_count <-irq_exit
2153 <idle>-0 3.N.1 11us : rcu_idle_ex 2055 <idle>-0 3.N.1 11us : rcu_idle_exit <-cpu_idle
2154 <idle>-0 3dN.1 11us : rcu_eqs_exi 2056 <idle>-0 3dN.1 11us : rcu_eqs_exit_common.isra.43 <-rcu_idle_exit
2155 <idle>-0 3.N.1 11us : tick_nohz_i 2057 <idle>-0 3.N.1 11us : tick_nohz_idle_exit <-cpu_idle
2156 <idle>-0 3dN.1 12us : menu_hrtime 2058 <idle>-0 3dN.1 12us : menu_hrtimer_cancel <-tick_nohz_idle_exit
2157 <idle>-0 3dN.1 12us : ktime_get < 2059 <idle>-0 3dN.1 12us : ktime_get <-tick_nohz_idle_exit
2158 <idle>-0 3dN.1 12us : tick_do_upd 2060 <idle>-0 3dN.1 12us : tick_do_update_jiffies64 <-tick_nohz_idle_exit
2159 <idle>-0 3dN.1 13us : cpu_load_up 2061 <idle>-0 3dN.1 13us : cpu_load_update_nohz <-tick_nohz_idle_exit
2160 <idle>-0 3dN.1 13us : _raw_spin_l 2062 <idle>-0 3dN.1 13us : _raw_spin_lock <-cpu_load_update_nohz
2161 <idle>-0 3dN.1 13us : add_preempt 2063 <idle>-0 3dN.1 13us : add_preempt_count <-_raw_spin_lock
2162 <idle>-0 3dN.2 13us : __cpu_load_ 2064 <idle>-0 3dN.2 13us : __cpu_load_update <-cpu_load_update_nohz
2163 <idle>-0 3dN.2 14us : sched_avg_u 2065 <idle>-0 3dN.2 14us : sched_avg_update <-__cpu_load_update
2164 <idle>-0 3dN.2 14us : _raw_spin_u 2066 <idle>-0 3dN.2 14us : _raw_spin_unlock <-cpu_load_update_nohz
2165 <idle>-0 3dN.2 14us : sub_preempt 2067 <idle>-0 3dN.2 14us : sub_preempt_count <-_raw_spin_unlock
2166 <idle>-0 3dN.1 15us : calc_load_n 2068 <idle>-0 3dN.1 15us : calc_load_nohz_stop <-tick_nohz_idle_exit
2167 <idle>-0 3dN.1 15us : touch_softl 2069 <idle>-0 3dN.1 15us : touch_softlockup_watchdog <-tick_nohz_idle_exit
2168 <idle>-0 3dN.1 15us : hrtimer_can 2070 <idle>-0 3dN.1 15us : hrtimer_cancel <-tick_nohz_idle_exit
2169 <idle>-0 3dN.1 15us : hrtimer_try 2071 <idle>-0 3dN.1 15us : hrtimer_try_to_cancel <-hrtimer_cancel
2170 <idle>-0 3dN.1 16us : lock_hrtime 2072 <idle>-0 3dN.1 16us : lock_hrtimer_base.isra.18 <-hrtimer_try_to_cancel
2171 <idle>-0 3dN.1 16us : _raw_spin_l 2073 <idle>-0 3dN.1 16us : _raw_spin_lock_irqsave <-lock_hrtimer_base.isra.18
2172 <idle>-0 3dN.1 16us : add_preempt 2074 <idle>-0 3dN.1 16us : add_preempt_count <-_raw_spin_lock_irqsave
2173 <idle>-0 3dN.2 17us : __remove_hr 2075 <idle>-0 3dN.2 17us : __remove_hrtimer <-remove_hrtimer.part.16
2174 <idle>-0 3dN.2 17us : hrtimer_for 2076 <idle>-0 3dN.2 17us : hrtimer_force_reprogram <-__remove_hrtimer
2175 <idle>-0 3dN.2 17us : tick_progra 2077 <idle>-0 3dN.2 17us : tick_program_event <-hrtimer_force_reprogram
2176 <idle>-0 3dN.2 18us : clockevents 2078 <idle>-0 3dN.2 18us : clockevents_program_event <-tick_program_event
2177 <idle>-0 3dN.2 18us : ktime_get < 2079 <idle>-0 3dN.2 18us : ktime_get <-clockevents_program_event
2178 <idle>-0 3dN.2 18us : lapic_next_ 2080 <idle>-0 3dN.2 18us : lapic_next_event <-clockevents_program_event
2179 <idle>-0 3dN.2 19us : _raw_spin_u 2081 <idle>-0 3dN.2 19us : _raw_spin_unlock_irqrestore <-hrtimer_try_to_cancel
2180 <idle>-0 3dN.2 19us : sub_preempt 2082 <idle>-0 3dN.2 19us : sub_preempt_count <-_raw_spin_unlock_irqrestore
2181 <idle>-0 3dN.1 19us : hrtimer_for 2083 <idle>-0 3dN.1 19us : hrtimer_forward <-tick_nohz_idle_exit
2182 <idle>-0 3dN.1 20us : ktime_add_s 2084 <idle>-0 3dN.1 20us : ktime_add_safe <-hrtimer_forward
2183 <idle>-0 3dN.1 20us : ktime_add_s 2085 <idle>-0 3dN.1 20us : ktime_add_safe <-hrtimer_forward
2184 <idle>-0 3dN.1 20us : hrtimer_sta 2086 <idle>-0 3dN.1 20us : hrtimer_start_range_ns <-hrtimer_start_expires.constprop.11
2185 <idle>-0 3dN.1 20us : __hrtimer_s 2087 <idle>-0 3dN.1 20us : __hrtimer_start_range_ns <-hrtimer_start_range_ns
2186 <idle>-0 3dN.1 21us : lock_hrtime 2088 <idle>-0 3dN.1 21us : lock_hrtimer_base.isra.18 <-__hrtimer_start_range_ns
2187 <idle>-0 3dN.1 21us : _raw_spin_l 2089 <idle>-0 3dN.1 21us : _raw_spin_lock_irqsave <-lock_hrtimer_base.isra.18
2188 <idle>-0 3dN.1 21us : add_preempt 2090 <idle>-0 3dN.1 21us : add_preempt_count <-_raw_spin_lock_irqsave
2189 <idle>-0 3dN.2 22us : ktime_add_s 2091 <idle>-0 3dN.2 22us : ktime_add_safe <-__hrtimer_start_range_ns
2190 <idle>-0 3dN.2 22us : enqueue_hrt 2092 <idle>-0 3dN.2 22us : enqueue_hrtimer <-__hrtimer_start_range_ns
2191 <idle>-0 3dN.2 22us : tick_progra 2093 <idle>-0 3dN.2 22us : tick_program_event <-__hrtimer_start_range_ns
2192 <idle>-0 3dN.2 23us : clockevents 2094 <idle>-0 3dN.2 23us : clockevents_program_event <-tick_program_event
2193 <idle>-0 3dN.2 23us : ktime_get < 2095 <idle>-0 3dN.2 23us : ktime_get <-clockevents_program_event
2194 <idle>-0 3dN.2 23us : lapic_next_ 2096 <idle>-0 3dN.2 23us : lapic_next_event <-clockevents_program_event
2195 <idle>-0 3dN.2 24us : _raw_spin_u 2097 <idle>-0 3dN.2 24us : _raw_spin_unlock_irqrestore <-__hrtimer_start_range_ns
2196 <idle>-0 3dN.2 24us : sub_preempt 2098 <idle>-0 3dN.2 24us : sub_preempt_count <-_raw_spin_unlock_irqrestore
2197 <idle>-0 3dN.1 24us : account_idl 2099 <idle>-0 3dN.1 24us : account_idle_ticks <-tick_nohz_idle_exit
2198 <idle>-0 3dN.1 24us : account_idl 2100 <idle>-0 3dN.1 24us : account_idle_time <-account_idle_ticks
2199 <idle>-0 3.N.1 25us : sub_preempt 2101 <idle>-0 3.N.1 25us : sub_preempt_count <-cpu_idle
2200 <idle>-0 3.N.. 25us : schedule <- 2102 <idle>-0 3.N.. 25us : schedule <-cpu_idle
2201 <idle>-0 3.N.. 25us : __schedule 2103 <idle>-0 3.N.. 25us : __schedule <-preempt_schedule
2202 <idle>-0 3.N.. 26us : add_preempt 2104 <idle>-0 3.N.. 26us : add_preempt_count <-__schedule
2203 <idle>-0 3.N.1 26us : rcu_note_co 2105 <idle>-0 3.N.1 26us : rcu_note_context_switch <-__schedule
2204 <idle>-0 3.N.1 26us : rcu_sched_q 2106 <idle>-0 3.N.1 26us : rcu_sched_qs <-rcu_note_context_switch
2205 <idle>-0 3dN.1 27us : rcu_preempt 2107 <idle>-0 3dN.1 27us : rcu_preempt_qs <-rcu_note_context_switch
2206 <idle>-0 3.N.1 27us : _raw_spin_l 2108 <idle>-0 3.N.1 27us : _raw_spin_lock_irq <-__schedule
2207 <idle>-0 3dN.1 27us : add_preempt 2109 <idle>-0 3dN.1 27us : add_preempt_count <-_raw_spin_lock_irq
2208 <idle>-0 3dN.2 28us : put_prev_ta 2110 <idle>-0 3dN.2 28us : put_prev_task_idle <-__schedule
2209 <idle>-0 3dN.2 28us : pick_next_t 2111 <idle>-0 3dN.2 28us : pick_next_task_stop <-pick_next_task
2210 <idle>-0 3dN.2 28us : pick_next_t 2112 <idle>-0 3dN.2 28us : pick_next_task_rt <-pick_next_task
2211 <idle>-0 3dN.2 29us : dequeue_pus 2113 <idle>-0 3dN.2 29us : dequeue_pushable_task <-pick_next_task_rt
2212 <idle>-0 3d..3 29us : __schedule 2114 <idle>-0 3d..3 29us : __schedule <-preempt_schedule
2213 <idle>-0 3d..3 30us : 0:120: 2115 <idle>-0 3d..3 30us : 0:120:R ==> [003] 2448: 94:R sleep
2214 2116
2215 This isn't that big of a trace, even with fun 2117 This isn't that big of a trace, even with function tracing enabled,
2216 so I included the entire trace. 2118 so I included the entire trace.
2217 2119
2218 The interrupt went off while when the system 2120 The interrupt went off while when the system was idle. Somewhere
2219 before task_woken_rt() was called, the NEED_R 2121 before task_woken_rt() was called, the NEED_RESCHED flag was set,
2220 this is indicated by the first occurrence of 2122 this is indicated by the first occurrence of the 'N' flag.
2221 2123
2222 Latency tracing and events 2124 Latency tracing and events
2223 -------------------------- 2125 --------------------------
2224 As function tracing can induce a much larger 2126 As function tracing can induce a much larger latency, but without
2225 seeing what happens within the latency it is 2127 seeing what happens within the latency it is hard to know what
2226 caused it. There is a middle ground, and that 2128 caused it. There is a middle ground, and that is with enabling
2227 events. 2129 events.
2228 :: 2130 ::
2229 2131
2230 # echo 0 > options/function-trace 2132 # echo 0 > options/function-trace
2231 # echo wakeup_rt > current_tracer 2133 # echo wakeup_rt > current_tracer
2232 # echo 1 > events/enable 2134 # echo 1 > events/enable
2233 # echo 1 > tracing_on 2135 # echo 1 > tracing_on
2234 # echo 0 > tracing_max_latency 2136 # echo 0 > tracing_max_latency
2235 # chrt -f 5 sleep 1 2137 # chrt -f 5 sleep 1
2236 # echo 0 > tracing_on 2138 # echo 0 > tracing_on
2237 # cat trace 2139 # cat trace
2238 # tracer: wakeup_rt 2140 # tracer: wakeup_rt
2239 # 2141 #
2240 # wakeup_rt latency trace v1.1.5 on 3.8.0-t 2142 # wakeup_rt latency trace v1.1.5 on 3.8.0-test+
2241 # ----------------------------------------- 2143 # --------------------------------------------------------------------
2242 # latency: 6 us, #12/12, CPU#2 | (M:preempt 2144 # latency: 6 us, #12/12, CPU#2 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
2243 # ----------------- 2145 # -----------------
2244 # | task: sleep-5882 (uid:0 nice:0 polic 2146 # | task: sleep-5882 (uid:0 nice:0 policy:1 rt_prio:5)
2245 # ----------------- 2147 # -----------------
2246 # 2148 #
2247 # _------=> CPU# 2149 # _------=> CPU#
2248 # / _-----=> irqs-off 2150 # / _-----=> irqs-off
2249 # | / _----=> need-resched 2151 # | / _----=> need-resched
2250 # || / _---=> hardirq/softir 2152 # || / _---=> hardirq/softirq
2251 # ||| / _--=> preempt-depth 2153 # ||| / _--=> preempt-depth
2252 # |||| / delay 2154 # |||| / delay
2253 # cmd pid ||||| time | caller 2155 # cmd pid ||||| time | caller
2254 # \ / ||||| \ | / 2156 # \ / ||||| \ | /
2255 <idle>-0 2d.h4 0us : 0:120: 2157 <idle>-0 2d.h4 0us : 0:120:R + [002] 5882: 94:R sleep
2256 <idle>-0 2d.h4 0us : ttwu_do_act 2158 <idle>-0 2d.h4 0us : ttwu_do_activate.constprop.87 <-try_to_wake_up
2257 <idle>-0 2d.h4 1us : sched_wakeu 2159 <idle>-0 2d.h4 1us : sched_wakeup: comm=sleep pid=5882 prio=94 success=1 target_cpu=002
2258 <idle>-0 2dNh2 1us : hrtimer_exp 2160 <idle>-0 2dNh2 1us : hrtimer_expire_exit: hrtimer=ffff88007796feb8
2259 <idle>-0 2.N.2 2us : power_end: 2161 <idle>-0 2.N.2 2us : power_end: cpu_id=2
2260 <idle>-0 2.N.2 3us : cpu_idle: s 2162 <idle>-0 2.N.2 3us : cpu_idle: state=4294967295 cpu_id=2
2261 <idle>-0 2dN.3 4us : hrtimer_can 2163 <idle>-0 2dN.3 4us : hrtimer_cancel: hrtimer=ffff88007d50d5e0
2262 <idle>-0 2dN.3 4us : hrtimer_sta 2164 <idle>-0 2dN.3 4us : hrtimer_start: hrtimer=ffff88007d50d5e0 function=tick_sched_timer expires=34311211000000 softexpires=34311211000000
2263 <idle>-0 2.N.2 5us : rcu_utiliza 2165 <idle>-0 2.N.2 5us : rcu_utilization: Start context switch
2264 <idle>-0 2.N.2 5us : rcu_utiliza 2166 <idle>-0 2.N.2 5us : rcu_utilization: End context switch
2265 <idle>-0 2d..3 6us : __schedule 2167 <idle>-0 2d..3 6us : __schedule <-schedule
2266 <idle>-0 2d..3 6us : 0:120: 2168 <idle>-0 2d..3 6us : 0:120:R ==> [002] 5882: 94:R sleep
2267 2169
2268 2170
2269 Hardware Latency Detector 2171 Hardware Latency Detector
2270 ------------------------- 2172 -------------------------
2271 2173
2272 The hardware latency detector is executed by 2174 The hardware latency detector is executed by enabling the "hwlat" tracer.
2273 2175
2274 NOTE, this tracer will affect the performance 2176 NOTE, this tracer will affect the performance of the system as it will
2275 periodically make a CPU constantly busy with 2177 periodically make a CPU constantly busy with interrupts disabled.
2276 :: 2178 ::
2277 2179
2278 # echo hwlat > current_tracer 2180 # echo hwlat > current_tracer
2279 # sleep 100 2181 # sleep 100
2280 # cat trace 2182 # cat trace
2281 # tracer: hwlat 2183 # tracer: hwlat
2282 # 2184 #
2283 # entries-in-buffer/entries-written: 13/13 2185 # entries-in-buffer/entries-written: 13/13 #P:8
2284 # 2186 #
2285 # _-----=> irq 2187 # _-----=> irqs-off
2286 # / _----=> nee 2188 # / _----=> need-resched
2287 # | / _---=> har 2189 # | / _---=> hardirq/softirq
2288 # || / _--=> pre 2190 # || / _--=> preempt-depth
2289 # ||| / dela 2191 # ||| / delay
2290 # TASK-PID CPU# |||| TIMEST 2192 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
2291 # | | | |||| | 2193 # | | | |||| | |
2292 <...>-1729 [001] d... 678.473 2194 <...>-1729 [001] d... 678.473449: #1 inner/outer(us): 11/12 ts:1581527483.343962693 count:6
2293 <...>-1729 [004] d... 689.556 2195 <...>-1729 [004] d... 689.556542: #2 inner/outer(us): 16/9 ts:1581527494.889008092 count:1
2294 <...>-1729 [005] d... 714.756 2196 <...>-1729 [005] d... 714.756290: #3 inner/outer(us): 16/16 ts:1581527519.678961629 count:5
2295 <...>-1729 [001] d... 718.788 2197 <...>-1729 [001] d... 718.788247: #4 inner/outer(us): 9/17 ts:1581527523.889012713 count:1
2296 <...>-1729 [002] d... 719.796 2198 <...>-1729 [002] d... 719.796341: #5 inner/outer(us): 13/9 ts:1581527524.912872606 count:1
2297 <...>-1729 [006] d... 844.787 2199 <...>-1729 [006] d... 844.787091: #6 inner/outer(us): 9/12 ts:1581527649.889048502 count:2
2298 <...>-1729 [003] d... 849.827 2200 <...>-1729 [003] d... 849.827033: #7 inner/outer(us): 18/9 ts:1581527654.889013793 count:1
2299 <...>-1729 [007] d... 853.859 2201 <...>-1729 [007] d... 853.859002: #8 inner/outer(us): 9/12 ts:1581527658.889065736 count:1
2300 <...>-1729 [001] d... 855.874 2202 <...>-1729 [001] d... 855.874978: #9 inner/outer(us): 9/11 ts:1581527660.861991877 count:1
2301 <...>-1729 [001] d... 863.938 2203 <...>-1729 [001] d... 863.938932: #10 inner/outer(us): 9/11 ts:1581527668.970010500 count:1 nmi-total:7 nmi-count:1
2302 <...>-1729 [007] d... 878.050 2204 <...>-1729 [007] d... 878.050780: #11 inner/outer(us): 9/12 ts:1581527683.385002600 count:1 nmi-total:5 nmi-count:1
2303 <...>-1729 [007] d... 886.114 2205 <...>-1729 [007] d... 886.114702: #12 inner/outer(us): 9/12 ts:1581527691.385001600 count:1
2304 2206
2305 2207
2306 The above output is somewhat the same in the 2208 The above output is somewhat the same in the header. All events will have
2307 interrupts disabled 'd'. Under the FUNCTION t 2209 interrupts disabled 'd'. Under the FUNCTION title there is:
2308 2210
2309 #1 2211 #1
2310 This is the count of events recorded 2212 This is the count of events recorded that were greater than the
2311 tracing_threshold (See below). 2213 tracing_threshold (See below).
2312 2214
2313 inner/outer(us): 11/11 2215 inner/outer(us): 11/11
2314 2216
2315 This shows two numbers as "inner latenc 2217 This shows two numbers as "inner latency" and "outer latency". The test
2316 runs in a loop checking a timestamp twi 2218 runs in a loop checking a timestamp twice. The latency detected within
2317 the two timestamps is the "inner latenc 2219 the two timestamps is the "inner latency" and the latency detected
2318 after the previous timestamp and the ne 2220 after the previous timestamp and the next timestamp in the loop is
2319 the "outer latency". 2221 the "outer latency".
2320 2222
2321 ts:1581527483.343962693 2223 ts:1581527483.343962693
2322 2224
2323 The absolute timestamp that the first l 2225 The absolute timestamp that the first latency was recorded in the window.
2324 2226
2325 count:6 2227 count:6
2326 2228
2327 The number of times a latency was detec 2229 The number of times a latency was detected during the window.
2328 2230
2329 nmi-total:7 nmi-count:1 2231 nmi-total:7 nmi-count:1
2330 2232
2331 On architectures that support it, if an 2233 On architectures that support it, if an NMI comes in during the
2332 test, the time spent in NMI is reported 2234 test, the time spent in NMI is reported in "nmi-total" (in
2333 microseconds). 2235 microseconds).
2334 2236
2335 All architectures that have NMIs will s 2237 All architectures that have NMIs will show the "nmi-count" if an
2336 NMI comes in during the test. 2238 NMI comes in during the test.
2337 2239
2338 hwlat files: 2240 hwlat files:
2339 2241
2340 tracing_threshold 2242 tracing_threshold
2341 This gets automatically set to "10" t 2243 This gets automatically set to "10" to represent 10
2342 microseconds. This is the threshold o 2244 microseconds. This is the threshold of latency that
2343 needs to be detected before the trace 2245 needs to be detected before the trace will be recorded.
2344 2246
2345 Note, when hwlat tracer is finished ( 2247 Note, when hwlat tracer is finished (another tracer is
2346 written into "current_tracer"), the o 2248 written into "current_tracer"), the original value for
2347 tracing_threshold is placed back into 2249 tracing_threshold is placed back into this file.
2348 2250
2349 hwlat_detector/width 2251 hwlat_detector/width
2350 The length of time the test runs with 2252 The length of time the test runs with interrupts disabled.
2351 2253
2352 hwlat_detector/window 2254 hwlat_detector/window
2353 The length of time of the window whic 2255 The length of time of the window which the test
2354 runs. That is, the test will run for 2256 runs. That is, the test will run for "width"
2355 microseconds per "window" microsecond 2257 microseconds per "window" microseconds
2356 2258
2357 tracing_cpumask 2259 tracing_cpumask
2358 When the test is started. A kernel th 2260 When the test is started. A kernel thread is created that
2359 runs the test. This thread will alter 2261 runs the test. This thread will alternate between CPUs
2360 listed in the tracing_cpumask between 2262 listed in the tracing_cpumask between each period
2361 (one "window"). To limit the test to 2263 (one "window"). To limit the test to specific CPUs
2362 set the mask in this file to only the 2264 set the mask in this file to only the CPUs that the test
2363 should run on. 2265 should run on.
2364 2266
2365 function 2267 function
2366 -------- 2268 --------
2367 2269
2368 This tracer is the function tracer. Enabling 2270 This tracer is the function tracer. Enabling the function tracer
2369 can be done from the debug file system. Make 2271 can be done from the debug file system. Make sure the
2370 ftrace_enabled is set; otherwise this tracer 2272 ftrace_enabled is set; otherwise this tracer is a nop.
2371 See the "ftrace_enabled" section below. 2273 See the "ftrace_enabled" section below.
2372 :: 2274 ::
2373 2275
2374 # sysctl kernel.ftrace_enabled=1 2276 # sysctl kernel.ftrace_enabled=1
2375 # echo function > current_tracer 2277 # echo function > current_tracer
2376 # echo 1 > tracing_on 2278 # echo 1 > tracing_on
2377 # usleep 1 2279 # usleep 1
2378 # echo 0 > tracing_on 2280 # echo 0 > tracing_on
2379 # cat trace 2281 # cat trace
2380 # tracer: function 2282 # tracer: function
2381 # 2283 #
2382 # entries-in-buffer/entries-written: 24799/ 2284 # entries-in-buffer/entries-written: 24799/24799 #P:4
2383 # 2285 #
2384 # _-----=> irq 2286 # _-----=> irqs-off
2385 # / _----=> nee 2287 # / _----=> need-resched
2386 # | / _---=> har 2288 # | / _---=> hardirq/softirq
2387 # || / _--=> pre 2289 # || / _--=> preempt-depth
2388 # ||| / dela 2290 # ||| / delay
2389 # TASK-PID CPU# |||| TIMEST 2291 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
2390 # | | | |||| | 2292 # | | | |||| | |
2391 bash-1994 [002] .... 3082.063 2293 bash-1994 [002] .... 3082.063030: mutex_unlock <-rb_simple_write
2392 bash-1994 [002] .... 3082.063 2294 bash-1994 [002] .... 3082.063031: __mutex_unlock_slowpath <-mutex_unlock
2393 bash-1994 [002] .... 3082.063 2295 bash-1994 [002] .... 3082.063031: __fsnotify_parent <-fsnotify_modify
2394 bash-1994 [002] .... 3082.063 2296 bash-1994 [002] .... 3082.063032: fsnotify <-fsnotify_modify
2395 bash-1994 [002] .... 3082.063 2297 bash-1994 [002] .... 3082.063032: __srcu_read_lock <-fsnotify
2396 bash-1994 [002] .... 3082.063 2298 bash-1994 [002] .... 3082.063032: add_preempt_count <-__srcu_read_lock
2397 bash-1994 [002] ...1 3082.063 2299 bash-1994 [002] ...1 3082.063032: sub_preempt_count <-__srcu_read_lock
2398 bash-1994 [002] .... 3082.063 2300 bash-1994 [002] .... 3082.063033: __srcu_read_unlock <-fsnotify
2399 [...] 2301 [...]
2400 2302
2401 2303
2402 Note: function tracer uses ring buffers to st 2304 Note: function tracer uses ring buffers to store the above
2403 entries. The newest data may overwrite the ol 2305 entries. The newest data may overwrite the oldest data.
2404 Sometimes using echo to stop the trace is not 2306 Sometimes using echo to stop the trace is not sufficient because
2405 the tracing could have overwritten the data t 2307 the tracing could have overwritten the data that you wanted to
2406 record. For this reason, it is sometimes bett 2308 record. For this reason, it is sometimes better to disable
2407 tracing directly from a program. This allows 2309 tracing directly from a program. This allows you to stop the
2408 tracing at the point that you hit the part th 2310 tracing at the point that you hit the part that you are
2409 interested in. To disable the tracing directl 2311 interested in. To disable the tracing directly from a C program,
2410 something like following code snippet can be 2312 something like following code snippet can be used::
2411 2313
2412 int trace_fd; 2314 int trace_fd;
2413 [...] 2315 [...]
2414 int main(int argc, char *argv[]) { 2316 int main(int argc, char *argv[]) {
2415 [...] 2317 [...]
2416 trace_fd = open(tracing_file( 2318 trace_fd = open(tracing_file("tracing_on"), O_WRONLY);
2417 [...] 2319 [...]
2418 if (condition_hit()) { 2320 if (condition_hit()) {
2419 write(trace_fd, "0", 2321 write(trace_fd, "0", 1);
2420 } 2322 }
2421 [...] 2323 [...]
2422 } 2324 }
2423 2325
2424 2326
2425 Single thread tracing 2327 Single thread tracing
2426 --------------------- 2328 ---------------------
2427 2329
2428 By writing into set_ftrace_pid you can trace 2330 By writing into set_ftrace_pid you can trace a
2429 single thread. For example:: 2331 single thread. For example::
2430 2332
2431 # cat set_ftrace_pid 2333 # cat set_ftrace_pid
2432 no pid 2334 no pid
2433 # echo 3111 > set_ftrace_pid 2335 # echo 3111 > set_ftrace_pid
2434 # cat set_ftrace_pid 2336 # cat set_ftrace_pid
2435 3111 2337 3111
2436 # echo function > current_tracer 2338 # echo function > current_tracer
2437 # cat trace | head 2339 # cat trace | head
2438 # tracer: function 2340 # tracer: function
2439 # 2341 #
2440 # TASK-PID CPU# TIMESTAMP 2342 # TASK-PID CPU# TIMESTAMP FUNCTION
2441 # | | | | 2343 # | | | | |
2442 yum-updatesd-3111 [003] 1637.254676: 2344 yum-updatesd-3111 [003] 1637.254676: finish_task_switch <-thread_return
2443 yum-updatesd-3111 [003] 1637.254681: 2345 yum-updatesd-3111 [003] 1637.254681: hrtimer_cancel <-schedule_hrtimeout_range
2444 yum-updatesd-3111 [003] 1637.254682: 2346 yum-updatesd-3111 [003] 1637.254682: hrtimer_try_to_cancel <-hrtimer_cancel
2445 yum-updatesd-3111 [003] 1637.254683: 2347 yum-updatesd-3111 [003] 1637.254683: lock_hrtimer_base <-hrtimer_try_to_cancel
2446 yum-updatesd-3111 [003] 1637.254685: 2348 yum-updatesd-3111 [003] 1637.254685: fget_light <-do_sys_poll
2447 yum-updatesd-3111 [003] 1637.254686: 2349 yum-updatesd-3111 [003] 1637.254686: pipe_poll <-do_sys_poll
2448 # echo > set_ftrace_pid 2350 # echo > set_ftrace_pid
2449 # cat trace |head 2351 # cat trace |head
2450 # tracer: function 2352 # tracer: function
2451 # 2353 #
2452 # TASK-PID CPU# TIMESTAMP 2354 # TASK-PID CPU# TIMESTAMP FUNCTION
2453 # | | | | 2355 # | | | | |
2454 ##### CPU 3 buffer started #### 2356 ##### CPU 3 buffer started ####
2455 yum-updatesd-3111 [003] 1701.957688: 2357 yum-updatesd-3111 [003] 1701.957688: free_poll_entry <-poll_freewait
2456 yum-updatesd-3111 [003] 1701.957689: 2358 yum-updatesd-3111 [003] 1701.957689: remove_wait_queue <-free_poll_entry
2457 yum-updatesd-3111 [003] 1701.957691: 2359 yum-updatesd-3111 [003] 1701.957691: fput <-free_poll_entry
2458 yum-updatesd-3111 [003] 1701.957692: 2360 yum-updatesd-3111 [003] 1701.957692: audit_syscall_exit <-sysret_audit
2459 yum-updatesd-3111 [003] 1701.957693: 2361 yum-updatesd-3111 [003] 1701.957693: path_put <-audit_syscall_exit
2460 2362
2461 If you want to trace a function when executin 2363 If you want to trace a function when executing, you could use
2462 something like this simple program. 2364 something like this simple program.
2463 :: 2365 ::
2464 2366
2465 #include <stdio.h> 2367 #include <stdio.h>
2466 #include <stdlib.h> 2368 #include <stdlib.h>
2467 #include <sys/types.h> 2369 #include <sys/types.h>
2468 #include <sys/stat.h> 2370 #include <sys/stat.h>
2469 #include <fcntl.h> 2371 #include <fcntl.h>
2470 #include <unistd.h> 2372 #include <unistd.h>
2471 #include <string.h> 2373 #include <string.h>
2472 2374
2473 #define _STR(x) #x 2375 #define _STR(x) #x
2474 #define STR(x) _STR(x) 2376 #define STR(x) _STR(x)
2475 #define MAX_PATH 256 2377 #define MAX_PATH 256
2476 2378
2477 const char *find_tracefs(void) 2379 const char *find_tracefs(void)
2478 { 2380 {
2479 static char tracefs[MAX_PATH+1 2381 static char tracefs[MAX_PATH+1];
2480 static int tracefs_found; 2382 static int tracefs_found;
2481 char type[100]; 2383 char type[100];
2482 FILE *fp; 2384 FILE *fp;
2483 2385
2484 if (tracefs_found) 2386 if (tracefs_found)
2485 return tracefs; 2387 return tracefs;
2486 2388
2487 if ((fp = fopen("/proc/mounts" 2389 if ((fp = fopen("/proc/mounts","r")) == NULL) {
2488 perror("/proc/mounts") 2390 perror("/proc/mounts");
2489 return NULL; 2391 return NULL;
2490 } 2392 }
2491 2393
2492 while (fscanf(fp, "%*s %" 2394 while (fscanf(fp, "%*s %"
2493 STR(MAX_PATH) 2395 STR(MAX_PATH)
2494 "s %99s %*s %*d 2396 "s %99s %*s %*d %*d\n",
2495 tracefs, type) = 2397 tracefs, type) == 2) {
2496 if (strcmp(type, "trac 2398 if (strcmp(type, "tracefs") == 0)
2497 break; 2399 break;
2498 } 2400 }
2499 fclose(fp); 2401 fclose(fp);
2500 2402
2501 if (strcmp(type, "tracefs") != 2403 if (strcmp(type, "tracefs") != 0) {
2502 fprintf(stderr, "trace 2404 fprintf(stderr, "tracefs not mounted");
2503 return NULL; 2405 return NULL;
2504 } 2406 }
2505 2407
2506 strcat(tracefs, "/tracing/"); 2408 strcat(tracefs, "/tracing/");
2507 tracefs_found = 1; 2409 tracefs_found = 1;
2508 2410
2509 return tracefs; 2411 return tracefs;
2510 } 2412 }
2511 2413
2512 const char *tracing_file(const char * 2414 const char *tracing_file(const char *file_name)
2513 { 2415 {
2514 static char trace_file[MAX_PAT 2416 static char trace_file[MAX_PATH+1];
2515 snprintf(trace_file, MAX_PATH, 2417 snprintf(trace_file, MAX_PATH, "%s/%s", find_tracefs(), file_name);
2516 return trace_file; 2418 return trace_file;
2517 } 2419 }
2518 2420
2519 int main (int argc, char **argv) 2421 int main (int argc, char **argv)
2520 { 2422 {
2521 if (argc < 1) 2423 if (argc < 1)
2522 exit(-1); 2424 exit(-1);
2523 2425
2524 if (fork() > 0) { 2426 if (fork() > 0) {
2525 int fd, ffd; 2427 int fd, ffd;
2526 char line[64]; 2428 char line[64];
2527 int s; 2429 int s;
2528 2430
2529 ffd = open(tracing_fi 2431 ffd = open(tracing_file("current_tracer"), O_WRONLY);
2530 if (ffd < 0) 2432 if (ffd < 0)
2531 exit(-1); 2433 exit(-1);
2532 write(ffd, "nop", 3); 2434 write(ffd, "nop", 3);
2533 2435
2534 fd = open(tracing_fil 2436 fd = open(tracing_file("set_ftrace_pid"), O_WRONLY);
2535 s = sprintf(line, "%d 2437 s = sprintf(line, "%d\n", getpid());
2536 write(fd, line, s); 2438 write(fd, line, s);
2537 2439
2538 write(ffd, "function" 2440 write(ffd, "function", 8);
2539 2441
2540 close(fd); 2442 close(fd);
2541 close(ffd); 2443 close(ffd);
2542 2444
2543 execvp(argv[1], argv+ 2445 execvp(argv[1], argv+1);
2544 } 2446 }
2545 2447
2546 return 0; 2448 return 0;
2547 } 2449 }
2548 2450
2549 Or this simple script! 2451 Or this simple script!
2550 :: 2452 ::
2551 2453
2552 #!/bin/bash 2454 #!/bin/bash
2553 2455
2554 tracefs=`sed -ne 's/^tracefs \(.*\) tracefs 2456 tracefs=`sed -ne 's/^tracefs \(.*\) tracefs.*/\1/p' /proc/mounts`
2555 echo 0 > $tracefs/tracing_on 2457 echo 0 > $tracefs/tracing_on
2556 echo $$ > $tracefs/set_ftrace_pid 2458 echo $$ > $tracefs/set_ftrace_pid
2557 echo function > $tracefs/current_tracer 2459 echo function > $tracefs/current_tracer
2558 echo 1 > $tracefs/tracing_on 2460 echo 1 > $tracefs/tracing_on
2559 exec "$@" 2461 exec "$@"
2560 2462
2561 2463
2562 function graph tracer 2464 function graph tracer
2563 --------------------------- 2465 ---------------------------
2564 2466
2565 This tracer is similar to the function tracer 2467 This tracer is similar to the function tracer except that it
2566 probes a function on its entry and its exit. 2468 probes a function on its entry and its exit. This is done by
2567 using a dynamically allocated stack of return 2469 using a dynamically allocated stack of return addresses in each
2568 task_struct. On function entry the tracer ove 2470 task_struct. On function entry the tracer overwrites the return
2569 address of each function traced to set a cust 2471 address of each function traced to set a custom probe. Thus the
2570 original return address is stored on the stac 2472 original return address is stored on the stack of return address
2571 in the task_struct. 2473 in the task_struct.
2572 2474
2573 Probing on both ends of a function leads to s 2475 Probing on both ends of a function leads to special features
2574 such as: 2476 such as:
2575 2477
2576 - measure of a function's time execution 2478 - measure of a function's time execution
2577 - having a reliable call stack to draw functi 2479 - having a reliable call stack to draw function calls graph
2578 2480
2579 This tracer is useful in several situations: 2481 This tracer is useful in several situations:
2580 2482
2581 - you want to find the reason of a strange ke 2483 - you want to find the reason of a strange kernel behavior and
2582 need to see what happens in detail on any a 2484 need to see what happens in detail on any areas (or specific
2583 ones). 2485 ones).
2584 2486
2585 - you are experiencing weird latencies but it 2487 - you are experiencing weird latencies but it's difficult to
2586 find its origin. 2488 find its origin.
2587 2489
2588 - you want to find quickly which path is take 2490 - you want to find quickly which path is taken by a specific
2589 function 2491 function
2590 2492
2591 - you just want to peek inside a working kern 2493 - you just want to peek inside a working kernel and want to see
2592 what happens there. 2494 what happens there.
2593 2495
2594 :: 2496 ::
2595 2497
2596 # tracer: function_graph 2498 # tracer: function_graph
2597 # 2499 #
2598 # CPU DURATION FUNCTION C 2500 # CPU DURATION FUNCTION CALLS
2599 # | | | | | | 2501 # | | | | | | |
2600 2502
2601 0) | sys_open() { 2503 0) | sys_open() {
2602 0) | do_sys_open() { 2504 0) | do_sys_open() {
2603 0) | getname() { 2505 0) | getname() {
2604 0) | kmem_cache_alloc 2506 0) | kmem_cache_alloc() {
2605 0) 1.382 us | __might_sleep( 2507 0) 1.382 us | __might_sleep();
2606 0) 2.478 us | } 2508 0) 2.478 us | }
2607 0) | strncpy_from_use 2509 0) | strncpy_from_user() {
2608 0) | might_fault() 2510 0) | might_fault() {
2609 0) 1.389 us | __might_slee 2511 0) 1.389 us | __might_sleep();
2610 0) 2.553 us | } 2512 0) 2.553 us | }
2611 0) 3.807 us | } 2513 0) 3.807 us | }
2612 0) 7.876 us | } 2514 0) 7.876 us | }
2613 0) | alloc_fd() { 2515 0) | alloc_fd() {
2614 0) 0.668 us | _spin_lock(); 2516 0) 0.668 us | _spin_lock();
2615 0) 0.570 us | expand_files(); 2517 0) 0.570 us | expand_files();
2616 0) 0.586 us | _spin_unlock(); 2518 0) 0.586 us | _spin_unlock();
2617 2519
2618 2520
2619 There are several columns that can be dynamic 2521 There are several columns that can be dynamically
2620 enabled/disabled. You can use every combinati 2522 enabled/disabled. You can use every combination of options you
2621 want, depending on your needs. 2523 want, depending on your needs.
2622 2524
2623 - The cpu number on which the function execut 2525 - The cpu number on which the function executed is default
2624 enabled. It is sometimes better to only tr 2526 enabled. It is sometimes better to only trace one cpu (see
2625 tracing_cpumask file) or you might sometime !! 2527 tracing_cpu_mask file) or you might sometimes see unordered
2626 function calls while cpu tracing switch. 2528 function calls while cpu tracing switch.
2627 2529
2628 - hide: echo nofuncgraph-cpu > trace_ 2530 - hide: echo nofuncgraph-cpu > trace_options
2629 - show: echo funcgraph-cpu > trace_op 2531 - show: echo funcgraph-cpu > trace_options
2630 2532
2631 - The duration (function's time of execution) 2533 - The duration (function's time of execution) is displayed on
2632 the closing bracket line of a function or o 2534 the closing bracket line of a function or on the same line
2633 than the current function in case of a leaf 2535 than the current function in case of a leaf one. It is default
2634 enabled. 2536 enabled.
2635 2537
2636 - hide: echo nofuncgraph-duration > t 2538 - hide: echo nofuncgraph-duration > trace_options
2637 - show: echo funcgraph-duration > tra 2539 - show: echo funcgraph-duration > trace_options
2638 2540
2639 - The overhead field precedes the duration fi 2541 - The overhead field precedes the duration field in case of
2640 reached duration thresholds. 2542 reached duration thresholds.
2641 2543
2642 - hide: echo nofuncgraph-overhead > t 2544 - hide: echo nofuncgraph-overhead > trace_options
2643 - show: echo funcgraph-overhead > tra 2545 - show: echo funcgraph-overhead > trace_options
2644 - depends on: funcgraph-duration 2546 - depends on: funcgraph-duration
2645 2547
2646 ie:: 2548 ie::
2647 2549
2648 3) # 1837.709 us | } /* __switch 2550 3) # 1837.709 us | } /* __switch_to */
2649 3) | finish_task_s 2551 3) | finish_task_switch() {
2650 3) 0.313 us | _raw_spin_u 2552 3) 0.313 us | _raw_spin_unlock_irq();
2651 3) 3.177 us | } 2553 3) 3.177 us | }
2652 3) # 1889.063 us | } /* __schedule 2554 3) # 1889.063 us | } /* __schedule */
2653 3) ! 140.417 us | } /* __schedule * 2555 3) ! 140.417 us | } /* __schedule */
2654 3) # 2034.948 us | } /* schedule */ 2556 3) # 2034.948 us | } /* schedule */
2655 3) * 33998.59 us | } /* schedule_preempt 2557 3) * 33998.59 us | } /* schedule_preempt_disabled */
2656 2558
2657 [...] 2559 [...]
2658 2560
2659 1) 0.260 us | msecs_to_ 2561 1) 0.260 us | msecs_to_jiffies();
2660 1) 0.313 us | __rcu_rea 2562 1) 0.313 us | __rcu_read_unlock();
2661 1) + 61.770 us | } 2563 1) + 61.770 us | }
2662 1) + 64.479 us | } 2564 1) + 64.479 us | }
2663 1) 0.313 us | rcu_bh_qs(); 2565 1) 0.313 us | rcu_bh_qs();
2664 1) 0.313 us | __local_bh_en 2566 1) 0.313 us | __local_bh_enable();
2665 1) ! 217.240 us | } 2567 1) ! 217.240 us | }
2666 1) 0.365 us | idle_cpu(); 2568 1) 0.365 us | idle_cpu();
2667 1) | rcu_irq_exit() 2569 1) | rcu_irq_exit() {
2668 1) 0.417 us | rcu_eqs_enter 2570 1) 0.417 us | rcu_eqs_enter_common.isra.47();
2669 1) 3.125 us | } 2571 1) 3.125 us | }
2670 1) ! 227.812 us | } 2572 1) ! 227.812 us | }
2671 1) ! 457.395 us | } 2573 1) ! 457.395 us | }
2672 1) @ 119760.2 us | } 2574 1) @ 119760.2 us | }
2673 2575
2674 [...] 2576 [...]
2675 2577
2676 2) | handle_IPI() { 2578 2) | handle_IPI() {
2677 1) 6.979 us | } 2579 1) 6.979 us | }
2678 2) 0.417 us | scheduler_ipi(); 2580 2) 0.417 us | scheduler_ipi();
2679 1) 9.791 us | } 2581 1) 9.791 us | }
2680 1) + 12.917 us | } 2582 1) + 12.917 us | }
2681 2) 3.490 us | } 2583 2) 3.490 us | }
2682 1) + 15.729 us | } 2584 1) + 15.729 us | }
2683 1) + 18.542 us | } 2585 1) + 18.542 us | }
2684 2) $ 3594274 us | } 2586 2) $ 3594274 us | }
2685 2587
2686 Flags:: 2588 Flags::
2687 2589
2688 + means that the function exceeded 10 usecs 2590 + means that the function exceeded 10 usecs.
2689 ! means that the function exceeded 100 usec 2591 ! means that the function exceeded 100 usecs.
2690 # means that the function exceeded 1000 use 2592 # means that the function exceeded 1000 usecs.
2691 * means that the function exceeded 10 msecs 2593 * means that the function exceeded 10 msecs.
2692 @ means that the function exceeded 100 msec 2594 @ means that the function exceeded 100 msecs.
2693 $ means that the function exceeded 1 sec. 2595 $ means that the function exceeded 1 sec.
2694 2596
2695 2597
2696 - The task/pid field displays the thread cmdl 2598 - The task/pid field displays the thread cmdline and pid which
2697 executed the function. It is default disabl 2599 executed the function. It is default disabled.
2698 2600
2699 - hide: echo nofuncgraph-proc > trace 2601 - hide: echo nofuncgraph-proc > trace_options
2700 - show: echo funcgraph-proc > trace_o 2602 - show: echo funcgraph-proc > trace_options
2701 2603
2702 ie:: 2604 ie::
2703 2605
2704 # tracer: function_graph 2606 # tracer: function_graph
2705 # 2607 #
2706 # CPU TASK/PID DURATION 2608 # CPU TASK/PID DURATION FUNCTION CALLS
2707 # | | | | | 2609 # | | | | | | | | |
2708 0) sh-4802 | | 2610 0) sh-4802 | | d_free() {
2709 0) sh-4802 | | 2611 0) sh-4802 | | call_rcu() {
2710 0) sh-4802 | | 2612 0) sh-4802 | | __call_rcu() {
2711 0) sh-4802 | 0.616 us | 2613 0) sh-4802 | 0.616 us | rcu_process_gp_end();
2712 0) sh-4802 | 0.586 us | 2614 0) sh-4802 | 0.586 us | check_for_new_grace_period();
2713 0) sh-4802 | 2.899 us | 2615 0) sh-4802 | 2.899 us | }
2714 0) sh-4802 | 4.040 us | 2616 0) sh-4802 | 4.040 us | }
2715 0) sh-4802 | 5.151 us | 2617 0) sh-4802 | 5.151 us | }
2716 0) sh-4802 | + 49.370 us | 2618 0) sh-4802 | + 49.370 us | }
2717 2619
2718 2620
2719 - The absolute time field is an absolute time 2621 - The absolute time field is an absolute timestamp given by the
2720 system clock since it started. A snapshot o 2622 system clock since it started. A snapshot of this time is
2721 given on each entry/exit of functions 2623 given on each entry/exit of functions
2722 2624
2723 - hide: echo nofuncgraph-abstime > tr 2625 - hide: echo nofuncgraph-abstime > trace_options
2724 - show: echo funcgraph-abstime > trac 2626 - show: echo funcgraph-abstime > trace_options
2725 2627
2726 ie:: 2628 ie::
2727 2629
2728 # 2630 #
2729 # TIME CPU DURATION 2631 # TIME CPU DURATION FUNCTION CALLS
2730 # | | | | 2632 # | | | | | | | |
2731 360.774522 | 1) 0.541 us | 2633 360.774522 | 1) 0.541 us | }
2732 360.774522 | 1) 4.663 us | 2634 360.774522 | 1) 4.663 us | }
2733 360.774523 | 1) 0.541 us | 2635 360.774523 | 1) 0.541 us | __wake_up_bit();
2734 360.774524 | 1) 6.796 us | 2636 360.774524 | 1) 6.796 us | }
2735 360.774524 | 1) 7.952 us | 2637 360.774524 | 1) 7.952 us | }
2736 360.774525 | 1) 9.063 us | 2638 360.774525 | 1) 9.063 us | }
2737 360.774525 | 1) 0.615 us | 2639 360.774525 | 1) 0.615 us | journal_mark_dirty();
2738 360.774527 | 1) 0.578 us | 2640 360.774527 | 1) 0.578 us | __brelse();
2739 360.774528 | 1) | 2641 360.774528 | 1) | reiserfs_prepare_for_journal() {
2740 360.774528 | 1) | 2642 360.774528 | 1) | unlock_buffer() {
2741 360.774529 | 1) | 2643 360.774529 | 1) | wake_up_bit() {
2742 360.774529 | 1) | 2644 360.774529 | 1) | bit_waitqueue() {
2743 360.774530 | 1) 0.594 us | 2645 360.774530 | 1) 0.594 us | __phys_addr();
2744 2646
2745 2647
2746 The function name is always displayed after t 2648 The function name is always displayed after the closing bracket
2747 for a function if the start of that function 2649 for a function if the start of that function is not in the
2748 trace buffer. 2650 trace buffer.
2749 2651
2750 Display of the function name after the closin 2652 Display of the function name after the closing bracket may be
2751 enabled for functions whose start is in the t 2653 enabled for functions whose start is in the trace buffer,
2752 allowing easier searching with grep for funct 2654 allowing easier searching with grep for function durations.
2753 It is default disabled. 2655 It is default disabled.
2754 2656
2755 - hide: echo nofuncgraph-tail > trace 2657 - hide: echo nofuncgraph-tail > trace_options
2756 - show: echo funcgraph-tail > trace_o 2658 - show: echo funcgraph-tail > trace_options
2757 2659
2758 Example with nofuncgraph-tail (default):: 2660 Example with nofuncgraph-tail (default)::
2759 2661
2760 0) | putname() { 2662 0) | putname() {
2761 0) | kmem_cache_free 2663 0) | kmem_cache_free() {
2762 0) 0.518 us | __phys_addr() 2664 0) 0.518 us | __phys_addr();
2763 0) 1.757 us | } 2665 0) 1.757 us | }
2764 0) 2.861 us | } 2666 0) 2.861 us | }
2765 2667
2766 Example with funcgraph-tail:: 2668 Example with funcgraph-tail::
2767 2669
2768 0) | putname() { 2670 0) | putname() {
2769 0) | kmem_cache_free 2671 0) | kmem_cache_free() {
2770 0) 0.518 us | __phys_addr() 2672 0) 0.518 us | __phys_addr();
2771 0) 1.757 us | } /* kmem_cache 2673 0) 1.757 us | } /* kmem_cache_free() */
2772 0) 2.861 us | } /* putname() */ 2674 0) 2.861 us | } /* putname() */
2773 2675
2774 The return value of each traced function can <<
2775 an equal sign "=". When encountering system c <<
2776 can be very helpful to quickly locate the fun <<
2777 returns an error code. <<
2778 <<
2779 - hide: echo nofuncgraph-retval > tra <<
2780 - show: echo funcgraph-retval > trace <<
2781 <<
2782 Example with funcgraph-retval:: <<
2783 <<
2784 1) | cgroup_migrate() { <<
2785 1) 0.651 us | cgroup_migrate_ad <<
2786 1) | cgroup_migrate_ex <<
2787 1) | cpu_cgroup_can_ <<
2788 1) | cgroup_taskse <<
2789 1) 0.732 us | cgroup_task <<
2790 1) 1.232 us | } /* cgroup_t <<
2791 1) 0.380 us | sched_rt_can_ <<
2792 1) 2.335 us | } /* cpu_cgroup <<
2793 1) 4.369 us | } /* cgroup_migra <<
2794 1) 7.143 us | } /* cgroup_migrate <<
2795 <<
2796 The above example shows that the function cpu <<
2797 returned the error code -22 firstly, then we <<
2798 of this function to get the root cause. <<
2799 <<
2800 When the option funcgraph-retval-hex is not s <<
2801 be displayed in a smart way. Specifically, if <<
2802 it will be printed in signed decimal format, <<
2803 printed in hexadecimal format. <<
2804 <<
2805 - smart: echo nofuncgraph-retval-hex <<
2806 - hexadecimal: echo funcgraph-retval- <<
2807 <<
2808 Example with funcgraph-retval-hex:: <<
2809 <<
2810 1) | cgroup_migrate() <<
2811 1) 0.651 us | cgroup_migrate_ <<
2812 1) | cgroup_migrate_ <<
2813 1) | cpu_cgroup_ca <<
2814 1) | cgroup_task <<
2815 1) 0.732 us | cgroup_ta <<
2816 1) 1.232 us | } /* cgroup <<
2817 1) 0.380 us | sched_rt_ca <<
2818 1) 2.335 us | } /* cpu_cgro <<
2819 1) 4.369 us | } /* cgroup_mig <<
2820 1) 7.143 us | } /* cgroup_migra <<
2821 <<
2822 At present, there are some limitations when u <<
2823 option, and these limitations will be elimina <<
2824 <<
2825 - Even if the function return type is void, a <<
2826 be printed, and you can just ignore it. <<
2827 <<
2828 - Even if return values are stored in multipl <<
2829 value contained in the first register will <<
2830 To illustrate, in the x86 architecture, eax <<
2831 a 64-bit return value, with the lower 32 bi <<
2832 upper 32 bits saved in edx. However, only t <<
2833 will be recorded and printed. <<
2834 <<
2835 - In certain procedure call standards, such a <<
2836 type is smaller than a GPR, it is the respo <<
2837 to perform the narrowing, and the upper bit <<
2838 Therefore, it is advisable to check the cod <<
2839 when using a u8 in a 64-bit GPR, bits [63:8 <<
2840 especially when larger types are truncated, <<
2841 Here are some specific cases to illustrate <<
2842 <<
2843 **Case One**: <<
2844 <<
2845 The function narrow_to_u8 is defined as fol <<
2846 <<
2847 u8 narrow_to_u8(u64 val) <<
2848 { <<
2849 // implicitly truncated <<
2850 return val; <<
2851 } <<
2852 <<
2853 It may be compiled to:: <<
2854 <<
2855 narrow_to_u8: <<
2856 < ... ftrace instrumentation <<
2857 RET <<
2858 <<
2859 If you pass 0x123456789abcdef to this funct <<
2860 it may be recorded as 0x123456789abcdef ins <<
2861 <<
2862 **Case Two**: <<
2863 <<
2864 The function error_if_not_4g_aligned is def <<
2865 <<
2866 int error_if_not_4g_aligned(u64 val) <<
2867 { <<
2868 if (val & GENMASK(31, 0)) <<
2869 return -EINVAL; <<
2870 <<
2871 return 0; <<
2872 } <<
2873 <<
2874 It could be compiled to:: <<
2875 <<
2876 error_if_not_4g_aligned: <<
2877 CBNZ w0, .Lnot_aligned <<
2878 RET // bi <<
2879 // [6 <<
2880 .Lnot_aligned: <<
2881 MOV x0, #-EINVAL <<
2882 RET <<
2883 <<
2884 When passing 0x2_0000_0000 to it, the retur <<
2885 0x2_0000_0000 instead of 0. <<
2886 <<
2887 You can put some comments on specific functio 2676 You can put some comments on specific functions by using
2888 trace_printk() For example, if you want to pu 2677 trace_printk() For example, if you want to put a comment inside
2889 the __might_sleep() function, you just have t 2678 the __might_sleep() function, you just have to include
2890 <linux/ftrace.h> and call trace_printk() insi 2679 <linux/ftrace.h> and call trace_printk() inside __might_sleep()::
2891 2680
2892 trace_printk("I'm a comment!\n") 2681 trace_printk("I'm a comment!\n")
2893 2682
2894 will produce:: 2683 will produce::
2895 2684
2896 1) | __might_sle 2685 1) | __might_sleep() {
2897 1) | /* I'm a 2686 1) | /* I'm a comment! */
2898 1) 1.449 us | } 2687 1) 1.449 us | }
2899 2688
2900 2689
2901 You might find other useful features for this 2690 You might find other useful features for this tracer in the
2902 following "dynamic ftrace" section such as tr 2691 following "dynamic ftrace" section such as tracing only specific
2903 functions or tasks. 2692 functions or tasks.
2904 2693
2905 dynamic ftrace 2694 dynamic ftrace
2906 -------------- 2695 --------------
2907 2696
2908 If CONFIG_DYNAMIC_FTRACE is set, the system w 2697 If CONFIG_DYNAMIC_FTRACE is set, the system will run with
2909 virtually no overhead when function tracing i 2698 virtually no overhead when function tracing is disabled. The way
2910 this works is the mcount function call (place 2699 this works is the mcount function call (placed at the start of
2911 every kernel function, produced by the -pg sw 2700 every kernel function, produced by the -pg switch in gcc),
2912 starts of pointing to a simple return. (Enabl 2701 starts of pointing to a simple return. (Enabling FTRACE will
2913 include the -pg switch in the compiling of th 2702 include the -pg switch in the compiling of the kernel.)
2914 2703
2915 At compile time every C file object is run th 2704 At compile time every C file object is run through the
2916 recordmcount program (located in the scripts 2705 recordmcount program (located in the scripts directory). This
2917 program will parse the ELF headers in the C o 2706 program will parse the ELF headers in the C object to find all
2918 the locations in the .text section that call 2707 the locations in the .text section that call mcount. Starting
2919 with gcc version 4.6, the -mfentry has been a 2708 with gcc version 4.6, the -mfentry has been added for x86, which
2920 calls "__fentry__" instead of "mcount". Which 2709 calls "__fentry__" instead of "mcount". Which is called before
2921 the creation of the stack frame. 2710 the creation of the stack frame.
2922 2711
2923 Note, not all sections are traced. They may b 2712 Note, not all sections are traced. They may be prevented by either
2924 a notrace, or blocked another way and all inl 2713 a notrace, or blocked another way and all inline functions are not
2925 traced. Check the "available_filter_functions 2714 traced. Check the "available_filter_functions" file to see what functions
2926 can be traced. 2715 can be traced.
2927 2716
2928 A section called "__mcount_loc" is created th 2717 A section called "__mcount_loc" is created that holds
2929 references to all the mcount/fentry call site 2718 references to all the mcount/fentry call sites in the .text section.
2930 The recordmcount program re-links this sectio 2719 The recordmcount program re-links this section back into the
2931 original object. The final linking stage of t 2720 original object. The final linking stage of the kernel will add all these
2932 references into a single table. 2721 references into a single table.
2933 2722
2934 On boot up, before SMP is initialized, the dy 2723 On boot up, before SMP is initialized, the dynamic ftrace code
2935 scans this table and updates all the location 2724 scans this table and updates all the locations into nops. It
2936 also records the locations, which are added t 2725 also records the locations, which are added to the
2937 available_filter_functions list. Modules are 2726 available_filter_functions list. Modules are processed as they
2938 are loaded and before they are executed. Whe 2727 are loaded and before they are executed. When a module is
2939 unloaded, it also removes its functions from 2728 unloaded, it also removes its functions from the ftrace function
2940 list. This is automatic in the module unload 2729 list. This is automatic in the module unload code, and the
2941 module author does not need to worry about it 2730 module author does not need to worry about it.
2942 2731
2943 When tracing is enabled, the process of modif 2732 When tracing is enabled, the process of modifying the function
2944 tracepoints is dependent on architecture. The 2733 tracepoints is dependent on architecture. The old method is to use
2945 kstop_machine to prevent races with the CPUs 2734 kstop_machine to prevent races with the CPUs executing code being
2946 modified (which can cause the CPU to do undes 2735 modified (which can cause the CPU to do undesirable things, especially
2947 if the modified code crosses cache (or page) 2736 if the modified code crosses cache (or page) boundaries), and the nops are
2948 patched back to calls. But this time, they do 2737 patched back to calls. But this time, they do not call mcount
2949 (which is just a function stub). They now cal 2738 (which is just a function stub). They now call into the ftrace
2950 infrastructure. 2739 infrastructure.
2951 2740
2952 The new method of modifying the function trac 2741 The new method of modifying the function tracepoints is to place
2953 a breakpoint at the location to be modified, 2742 a breakpoint at the location to be modified, sync all CPUs, modify
2954 the rest of the instruction not covered by th 2743 the rest of the instruction not covered by the breakpoint. Sync
2955 all CPUs again, and then remove the breakpoin 2744 all CPUs again, and then remove the breakpoint with the finished
2956 version to the ftrace call site. 2745 version to the ftrace call site.
2957 2746
2958 Some archs do not even need to monkey around 2747 Some archs do not even need to monkey around with the synchronization,
2959 and can just slap the new code on top of the 2748 and can just slap the new code on top of the old without any
2960 problems with other CPUs executing it at the 2749 problems with other CPUs executing it at the same time.
2961 2750
2962 One special side-effect to the recording of t 2751 One special side-effect to the recording of the functions being
2963 traced is that we can now selectively choose 2752 traced is that we can now selectively choose which functions we
2964 wish to trace and which ones we want the mcou 2753 wish to trace and which ones we want the mcount calls to remain
2965 as nops. 2754 as nops.
2966 2755
2967 Two files are used, one for enabling and one 2756 Two files are used, one for enabling and one for disabling the
2968 tracing of specified functions. They are: 2757 tracing of specified functions. They are:
2969 2758
2970 set_ftrace_filter 2759 set_ftrace_filter
2971 2760
2972 and 2761 and
2973 2762
2974 set_ftrace_notrace 2763 set_ftrace_notrace
2975 2764
2976 A list of available functions that you can ad 2765 A list of available functions that you can add to these files is
2977 listed in: 2766 listed in:
2978 2767
2979 available_filter_functions 2768 available_filter_functions
2980 2769
2981 :: 2770 ::
2982 2771
2983 # cat available_filter_functions 2772 # cat available_filter_functions
2984 put_prev_task_idle 2773 put_prev_task_idle
2985 kmem_cache_create 2774 kmem_cache_create
2986 pick_next_task_rt 2775 pick_next_task_rt
2987 cpus_read_lock 2776 cpus_read_lock
2988 pick_next_task_fair 2777 pick_next_task_fair
2989 mutex_lock 2778 mutex_lock
2990 [...] 2779 [...]
2991 2780
2992 If I am only interested in sys_nanosleep and 2781 If I am only interested in sys_nanosleep and hrtimer_interrupt::
2993 2782
2994 # echo sys_nanosleep hrtimer_interrupt > se 2783 # echo sys_nanosleep hrtimer_interrupt > set_ftrace_filter
2995 # echo function > current_tracer 2784 # echo function > current_tracer
2996 # echo 1 > tracing_on 2785 # echo 1 > tracing_on
2997 # usleep 1 2786 # usleep 1
2998 # echo 0 > tracing_on 2787 # echo 0 > tracing_on
2999 # cat trace 2788 # cat trace
3000 # tracer: function 2789 # tracer: function
3001 # 2790 #
3002 # entries-in-buffer/entries-written: 5/5 2791 # entries-in-buffer/entries-written: 5/5 #P:4
3003 # 2792 #
3004 # _-----=> irq 2793 # _-----=> irqs-off
3005 # / _----=> nee 2794 # / _----=> need-resched
3006 # | / _---=> har 2795 # | / _---=> hardirq/softirq
3007 # || / _--=> pre 2796 # || / _--=> preempt-depth
3008 # ||| / dela 2797 # ||| / delay
3009 # TASK-PID CPU# |||| TIMEST 2798 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
3010 # | | | |||| | 2799 # | | | |||| | |
3011 usleep-2665 [001] .... 4186.475 2800 usleep-2665 [001] .... 4186.475355: sys_nanosleep <-system_call_fastpath
3012 <idle>-0 [001] d.h1 4186.475 2801 <idle>-0 [001] d.h1 4186.475409: hrtimer_interrupt <-smp_apic_timer_interrupt
3013 usleep-2665 [001] d.h1 4186.475 2802 usleep-2665 [001] d.h1 4186.475426: hrtimer_interrupt <-smp_apic_timer_interrupt
3014 <idle>-0 [003] d.h1 4186.475 2803 <idle>-0 [003] d.h1 4186.475426: hrtimer_interrupt <-smp_apic_timer_interrupt
3015 <idle>-0 [002] d.h1 4186.475 2804 <idle>-0 [002] d.h1 4186.475427: hrtimer_interrupt <-smp_apic_timer_interrupt
3016 2805
3017 To see which functions are being traced, you 2806 To see which functions are being traced, you can cat the file:
3018 :: 2807 ::
3019 2808
3020 # cat set_ftrace_filter 2809 # cat set_ftrace_filter
3021 hrtimer_interrupt 2810 hrtimer_interrupt
3022 sys_nanosleep 2811 sys_nanosleep
3023 2812
3024 2813
3025 Perhaps this is not enough. The filters also 2814 Perhaps this is not enough. The filters also allow glob(7) matching.
3026 2815
3027 ``<match>*`` 2816 ``<match>*``
3028 will match functions that begin with 2817 will match functions that begin with <match>
3029 ``*<match>`` 2818 ``*<match>``
3030 will match functions that end with <m 2819 will match functions that end with <match>
3031 ``*<match>*`` 2820 ``*<match>*``
3032 will match functions that have <match 2821 will match functions that have <match> in it
3033 ``<match1>*<match2>`` 2822 ``<match1>*<match2>``
3034 will match functions that begin with 2823 will match functions that begin with <match1> and end with <match2>
3035 2824
3036 .. note:: 2825 .. note::
3037 It is better to use quotes to enclose t 2826 It is better to use quotes to enclose the wild cards,
3038 otherwise the shell may expand the para 2827 otherwise the shell may expand the parameters into names
3039 of files in the local directory. 2828 of files in the local directory.
3040 2829
3041 :: 2830 ::
3042 2831
3043 # echo 'hrtimer_*' > set_ftrace_filter 2832 # echo 'hrtimer_*' > set_ftrace_filter
3044 2833
3045 Produces:: 2834 Produces::
3046 2835
3047 # tracer: function 2836 # tracer: function
3048 # 2837 #
3049 # entries-in-buffer/entries-written: 897/89 2838 # entries-in-buffer/entries-written: 897/897 #P:4
3050 # 2839 #
3051 # _-----=> irq 2840 # _-----=> irqs-off
3052 # / _----=> nee 2841 # / _----=> need-resched
3053 # | / _---=> har 2842 # | / _---=> hardirq/softirq
3054 # || / _--=> pre 2843 # || / _--=> preempt-depth
3055 # ||| / dela 2844 # ||| / delay
3056 # TASK-PID CPU# |||| TIMEST 2845 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
3057 # | | | |||| | 2846 # | | | |||| | |
3058 <idle>-0 [003] dN.1 4228.547 2847 <idle>-0 [003] dN.1 4228.547803: hrtimer_cancel <-tick_nohz_idle_exit
3059 <idle>-0 [003] dN.1 4228.547 2848 <idle>-0 [003] dN.1 4228.547804: hrtimer_try_to_cancel <-hrtimer_cancel
3060 <idle>-0 [003] dN.2 4228.547 2849 <idle>-0 [003] dN.2 4228.547805: hrtimer_force_reprogram <-__remove_hrtimer
3061 <idle>-0 [003] dN.1 4228.547 2850 <idle>-0 [003] dN.1 4228.547805: hrtimer_forward <-tick_nohz_idle_exit
3062 <idle>-0 [003] dN.1 4228.547 2851 <idle>-0 [003] dN.1 4228.547805: hrtimer_start_range_ns <-hrtimer_start_expires.constprop.11
3063 <idle>-0 [003] d..1 4228.547 2852 <idle>-0 [003] d..1 4228.547858: hrtimer_get_next_event <-get_next_timer_interrupt
3064 <idle>-0 [003] d..1 4228.547 2853 <idle>-0 [003] d..1 4228.547859: hrtimer_start <-__tick_nohz_idle_enter
3065 <idle>-0 [003] d..2 4228.547 2854 <idle>-0 [003] d..2 4228.547860: hrtimer_force_reprogram <-__rem
3066 2855
3067 Notice that we lost the sys_nanosleep. 2856 Notice that we lost the sys_nanosleep.
3068 :: 2857 ::
3069 2858
3070 # cat set_ftrace_filter 2859 # cat set_ftrace_filter
3071 hrtimer_run_queues 2860 hrtimer_run_queues
3072 hrtimer_run_pending 2861 hrtimer_run_pending
3073 hrtimer_init 2862 hrtimer_init
3074 hrtimer_cancel 2863 hrtimer_cancel
3075 hrtimer_try_to_cancel 2864 hrtimer_try_to_cancel
3076 hrtimer_forward 2865 hrtimer_forward
3077 hrtimer_start 2866 hrtimer_start
3078 hrtimer_reprogram 2867 hrtimer_reprogram
3079 hrtimer_force_reprogram 2868 hrtimer_force_reprogram
3080 hrtimer_get_next_event 2869 hrtimer_get_next_event
3081 hrtimer_interrupt 2870 hrtimer_interrupt
3082 hrtimer_nanosleep 2871 hrtimer_nanosleep
3083 hrtimer_wakeup 2872 hrtimer_wakeup
3084 hrtimer_get_remaining 2873 hrtimer_get_remaining
3085 hrtimer_get_res 2874 hrtimer_get_res
3086 hrtimer_init_sleeper 2875 hrtimer_init_sleeper
3087 2876
3088 2877
3089 This is because the '>' and '>>' act just lik 2878 This is because the '>' and '>>' act just like they do in bash.
3090 To rewrite the filters, use '>' 2879 To rewrite the filters, use '>'
3091 To append to the filters, use '>>' 2880 To append to the filters, use '>>'
3092 2881
3093 To clear out a filter so that all functions w 2882 To clear out a filter so that all functions will be recorded
3094 again:: 2883 again::
3095 2884
3096 # echo > set_ftrace_filter 2885 # echo > set_ftrace_filter
3097 # cat set_ftrace_filter 2886 # cat set_ftrace_filter
3098 # 2887 #
3099 2888
3100 Again, now we want to append. 2889 Again, now we want to append.
3101 2890
3102 :: 2891 ::
3103 2892
3104 # echo sys_nanosleep > set_ftrace_filter 2893 # echo sys_nanosleep > set_ftrace_filter
3105 # cat set_ftrace_filter 2894 # cat set_ftrace_filter
3106 sys_nanosleep 2895 sys_nanosleep
3107 # echo 'hrtimer_*' >> set_ftrace_filter 2896 # echo 'hrtimer_*' >> set_ftrace_filter
3108 # cat set_ftrace_filter 2897 # cat set_ftrace_filter
3109 hrtimer_run_queues 2898 hrtimer_run_queues
3110 hrtimer_run_pending 2899 hrtimer_run_pending
3111 hrtimer_init 2900 hrtimer_init
3112 hrtimer_cancel 2901 hrtimer_cancel
3113 hrtimer_try_to_cancel 2902 hrtimer_try_to_cancel
3114 hrtimer_forward 2903 hrtimer_forward
3115 hrtimer_start 2904 hrtimer_start
3116 hrtimer_reprogram 2905 hrtimer_reprogram
3117 hrtimer_force_reprogram 2906 hrtimer_force_reprogram
3118 hrtimer_get_next_event 2907 hrtimer_get_next_event
3119 hrtimer_interrupt 2908 hrtimer_interrupt
3120 sys_nanosleep 2909 sys_nanosleep
3121 hrtimer_nanosleep 2910 hrtimer_nanosleep
3122 hrtimer_wakeup 2911 hrtimer_wakeup
3123 hrtimer_get_remaining 2912 hrtimer_get_remaining
3124 hrtimer_get_res 2913 hrtimer_get_res
3125 hrtimer_init_sleeper 2914 hrtimer_init_sleeper
3126 2915
3127 2916
3128 The set_ftrace_notrace prevents those functio 2917 The set_ftrace_notrace prevents those functions from being
3129 traced. 2918 traced.
3130 :: 2919 ::
3131 2920
3132 # echo '*preempt*' '*lock*' > set_ftrace_no 2921 # echo '*preempt*' '*lock*' > set_ftrace_notrace
3133 2922
3134 Produces:: 2923 Produces::
3135 2924
3136 # tracer: function 2925 # tracer: function
3137 # 2926 #
3138 # entries-in-buffer/entries-written: 39608/ 2927 # entries-in-buffer/entries-written: 39608/39608 #P:4
3139 # 2928 #
3140 # _-----=> irq 2929 # _-----=> irqs-off
3141 # / _----=> nee 2930 # / _----=> need-resched
3142 # | / _---=> har 2931 # | / _---=> hardirq/softirq
3143 # || / _--=> pre 2932 # || / _--=> preempt-depth
3144 # ||| / dela 2933 # ||| / delay
3145 # TASK-PID CPU# |||| TIMEST 2934 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
3146 # | | | |||| | 2935 # | | | |||| | |
3147 bash-1994 [000] .... 4342.324 2936 bash-1994 [000] .... 4342.324896: file_ra_state_init <-do_dentry_open
3148 bash-1994 [000] .... 4342.324 2937 bash-1994 [000] .... 4342.324897: open_check_o_direct <-do_last
3149 bash-1994 [000] .... 4342.324 2938 bash-1994 [000] .... 4342.324897: ima_file_check <-do_last
3150 bash-1994 [000] .... 4342.324 2939 bash-1994 [000] .... 4342.324898: process_measurement <-ima_file_check
3151 bash-1994 [000] .... 4342.324 2940 bash-1994 [000] .... 4342.324898: ima_get_action <-process_measurement
3152 bash-1994 [000] .... 4342.324 2941 bash-1994 [000] .... 4342.324898: ima_match_policy <-ima_get_action
3153 bash-1994 [000] .... 4342.324 2942 bash-1994 [000] .... 4342.324899: do_truncate <-do_last
3154 bash-1994 [000] .... 4342.324 !! 2943 bash-1994 [000] .... 4342.324899: should_remove_suid <-do_truncate
3155 bash-1994 [000] .... 4342.324 2944 bash-1994 [000] .... 4342.324899: notify_change <-do_truncate
3156 bash-1994 [000] .... 4342.324 2945 bash-1994 [000] .... 4342.324900: current_fs_time <-notify_change
3157 bash-1994 [000] .... 4342.324 2946 bash-1994 [000] .... 4342.324900: current_kernel_time <-current_fs_time
3158 bash-1994 [000] .... 4342.324 2947 bash-1994 [000] .... 4342.324900: timespec_trunc <-current_fs_time
3159 2948
3160 We can see that there's no more lock or preem 2949 We can see that there's no more lock or preempt tracing.
3161 2950
3162 Selecting function filters via index 2951 Selecting function filters via index
3163 ------------------------------------ 2952 ------------------------------------
3164 2953
3165 Because processing of strings is expensive (t 2954 Because processing of strings is expensive (the address of the function
3166 needs to be looked up before comparing to the 2955 needs to be looked up before comparing to the string being passed in),
3167 an index can be used as well to enable functi 2956 an index can be used as well to enable functions. This is useful in the
3168 case of setting thousands of specific functio 2957 case of setting thousands of specific functions at a time. By passing
3169 in a list of numbers, no string processing wi 2958 in a list of numbers, no string processing will occur. Instead, the function
3170 at the specific location in the internal arra 2959 at the specific location in the internal array (which corresponds to the
3171 functions in the "available_filter_functions" 2960 functions in the "available_filter_functions" file), is selected.
3172 2961
3173 :: 2962 ::
3174 2963
3175 # echo 1 > set_ftrace_filter 2964 # echo 1 > set_ftrace_filter
3176 2965
3177 Will select the first function listed in "ava 2966 Will select the first function listed in "available_filter_functions"
3178 2967
3179 :: 2968 ::
3180 2969
3181 # head -1 available_filter_functions 2970 # head -1 available_filter_functions
3182 trace_initcall_finish_cb 2971 trace_initcall_finish_cb
3183 2972
3184 # cat set_ftrace_filter 2973 # cat set_ftrace_filter
3185 trace_initcall_finish_cb 2974 trace_initcall_finish_cb
3186 2975
3187 # head -50 available_filter_functions | tai 2976 # head -50 available_filter_functions | tail -1
3188 x86_pmu_commit_txn 2977 x86_pmu_commit_txn
3189 2978
3190 # echo 1 50 > set_ftrace_filter 2979 # echo 1 50 > set_ftrace_filter
3191 # cat set_ftrace_filter 2980 # cat set_ftrace_filter
3192 trace_initcall_finish_cb 2981 trace_initcall_finish_cb
3193 x86_pmu_commit_txn 2982 x86_pmu_commit_txn
3194 2983
3195 Dynamic ftrace with the function graph tracer 2984 Dynamic ftrace with the function graph tracer
3196 --------------------------------------------- 2985 ---------------------------------------------
3197 2986
3198 Although what has been explained above concer 2987 Although what has been explained above concerns both the
3199 function tracer and the function-graph-tracer 2988 function tracer and the function-graph-tracer, there are some
3200 special features only available in the functi 2989 special features only available in the function-graph tracer.
3201 2990
3202 If you want to trace only one function and al 2991 If you want to trace only one function and all of its children,
3203 you just have to echo its name into set_graph 2992 you just have to echo its name into set_graph_function::
3204 2993
3205 echo __do_fault > set_graph_function 2994 echo __do_fault > set_graph_function
3206 2995
3207 will produce the following "expanded" trace o 2996 will produce the following "expanded" trace of the __do_fault()
3208 function:: 2997 function::
3209 2998
3210 0) | __do_fault() { 2999 0) | __do_fault() {
3211 0) | filemap_fault() { 3000 0) | filemap_fault() {
3212 0) | find_lock_page() { 3001 0) | find_lock_page() {
3213 0) 0.804 us | find_get_page(); 3002 0) 0.804 us | find_get_page();
3214 0) | __might_sleep() 3003 0) | __might_sleep() {
3215 0) 1.329 us | } 3004 0) 1.329 us | }
3216 0) 3.904 us | } 3005 0) 3.904 us | }
3217 0) 4.979 us | } 3006 0) 4.979 us | }
3218 0) 0.653 us | _spin_lock(); 3007 0) 0.653 us | _spin_lock();
3219 0) 0.578 us | page_add_file_rmap() 3008 0) 0.578 us | page_add_file_rmap();
3220 0) 0.525 us | native_set_pte_at(); 3009 0) 0.525 us | native_set_pte_at();
3221 0) 0.585 us | _spin_unlock(); 3010 0) 0.585 us | _spin_unlock();
3222 0) | unlock_page() { 3011 0) | unlock_page() {
3223 0) 0.541 us | page_waitqueue(); 3012 0) 0.541 us | page_waitqueue();
3224 0) 0.639 us | __wake_up_bit(); 3013 0) 0.639 us | __wake_up_bit();
3225 0) 2.786 us | } 3014 0) 2.786 us | }
3226 0) + 14.237 us | } 3015 0) + 14.237 us | }
3227 0) | __do_fault() { 3016 0) | __do_fault() {
3228 0) | filemap_fault() { 3017 0) | filemap_fault() {
3229 0) | find_lock_page() { 3018 0) | find_lock_page() {
3230 0) 0.698 us | find_get_page(); 3019 0) 0.698 us | find_get_page();
3231 0) | __might_sleep() 3020 0) | __might_sleep() {
3232 0) 1.412 us | } 3021 0) 1.412 us | }
3233 0) 3.950 us | } 3022 0) 3.950 us | }
3234 0) 5.098 us | } 3023 0) 5.098 us | }
3235 0) 0.631 us | _spin_lock(); 3024 0) 0.631 us | _spin_lock();
3236 0) 0.571 us | page_add_file_rmap() 3025 0) 0.571 us | page_add_file_rmap();
3237 0) 0.526 us | native_set_pte_at(); 3026 0) 0.526 us | native_set_pte_at();
3238 0) 0.586 us | _spin_unlock(); 3027 0) 0.586 us | _spin_unlock();
3239 0) | unlock_page() { 3028 0) | unlock_page() {
3240 0) 0.533 us | page_waitqueue(); 3029 0) 0.533 us | page_waitqueue();
3241 0) 0.638 us | __wake_up_bit(); 3030 0) 0.638 us | __wake_up_bit();
3242 0) 2.793 us | } 3031 0) 2.793 us | }
3243 0) + 14.012 us | } 3032 0) + 14.012 us | }
3244 3033
3245 You can also expand several functions at once 3034 You can also expand several functions at once::
3246 3035
3247 echo sys_open > set_graph_function 3036 echo sys_open > set_graph_function
3248 echo sys_close >> set_graph_function 3037 echo sys_close >> set_graph_function
3249 3038
3250 Now if you want to go back to trace all funct 3039 Now if you want to go back to trace all functions you can clear
3251 this special filter via:: 3040 this special filter via::
3252 3041
3253 echo > set_graph_function 3042 echo > set_graph_function
3254 3043
3255 3044
3256 ftrace_enabled 3045 ftrace_enabled
3257 -------------- 3046 --------------
3258 3047
3259 Note, the proc sysctl ftrace_enable is a big 3048 Note, the proc sysctl ftrace_enable is a big on/off switch for the
3260 function tracer. By default it is enabled (wh 3049 function tracer. By default it is enabled (when function tracing is
3261 enabled in the kernel). If it is disabled, al 3050 enabled in the kernel). If it is disabled, all function tracing is
3262 disabled. This includes not only the function 3051 disabled. This includes not only the function tracers for ftrace, but
3263 also for any other uses (perf, kprobes, stack 3052 also for any other uses (perf, kprobes, stack tracing, profiling, etc). It
3264 cannot be disabled if there is a callback wit 3053 cannot be disabled if there is a callback with FTRACE_OPS_FL_PERMANENT set
3265 registered. 3054 registered.
3266 3055
3267 Please disable this with care. 3056 Please disable this with care.
3268 3057
3269 This can be disable (and enabled) with:: 3058 This can be disable (and enabled) with::
3270 3059
3271 sysctl kernel.ftrace_enabled=0 3060 sysctl kernel.ftrace_enabled=0
3272 sysctl kernel.ftrace_enabled=1 3061 sysctl kernel.ftrace_enabled=1
3273 3062
3274 or 3063 or
3275 3064
3276 echo 0 > /proc/sys/kernel/ftrace_enabled 3065 echo 0 > /proc/sys/kernel/ftrace_enabled
3277 echo 1 > /proc/sys/kernel/ftrace_enabled 3066 echo 1 > /proc/sys/kernel/ftrace_enabled
3278 3067
3279 3068
3280 Filter commands 3069 Filter commands
3281 --------------- 3070 ---------------
3282 3071
3283 A few commands are supported by the set_ftrac 3072 A few commands are supported by the set_ftrace_filter interface.
3284 Trace commands have the following format:: 3073 Trace commands have the following format::
3285 3074
3286 <function>:<command>:<parameter> 3075 <function>:<command>:<parameter>
3287 3076
3288 The following commands are supported: 3077 The following commands are supported:
3289 3078
3290 - mod: 3079 - mod:
3291 This command enables function filtering per 3080 This command enables function filtering per module. The
3292 parameter defines the module. For example, 3081 parameter defines the module. For example, if only the write*
3293 functions in the ext3 module are desired, r 3082 functions in the ext3 module are desired, run:
3294 3083
3295 echo 'write*:mod:ext3' > set_ftrace_filter 3084 echo 'write*:mod:ext3' > set_ftrace_filter
3296 3085
3297 This command interacts with the filter in t 3086 This command interacts with the filter in the same way as
3298 filtering based on function names. Thus, ad 3087 filtering based on function names. Thus, adding more functions
3299 in a different module is accomplished by ap 3088 in a different module is accomplished by appending (>>) to the
3300 filter file. Remove specific module functio 3089 filter file. Remove specific module functions by prepending
3301 '!':: 3090 '!'::
3302 3091
3303 echo '!writeback*:mod:ext3' >> set_ftrace_ 3092 echo '!writeback*:mod:ext3' >> set_ftrace_filter
3304 3093
3305 Mod command supports module globbing. Disab 3094 Mod command supports module globbing. Disable tracing for all
3306 functions except a specific module:: 3095 functions except a specific module::
3307 3096
3308 echo '!*:mod:!ext3' >> set_ftrace_filter 3097 echo '!*:mod:!ext3' >> set_ftrace_filter
3309 3098
3310 Disable tracing for all modules, but still 3099 Disable tracing for all modules, but still trace kernel::
3311 3100
3312 echo '!*:mod:*' >> set_ftrace_filter 3101 echo '!*:mod:*' >> set_ftrace_filter
3313 3102
3314 Enable filter only for kernel:: 3103 Enable filter only for kernel::
3315 3104
3316 echo '*write*:mod:!*' >> set_ftrace_filter 3105 echo '*write*:mod:!*' >> set_ftrace_filter
3317 3106
3318 Enable filter for module globbing:: 3107 Enable filter for module globbing::
3319 3108
3320 echo '*write*:mod:*snd*' >> set_ftrace_fil 3109 echo '*write*:mod:*snd*' >> set_ftrace_filter
3321 3110
3322 - traceon/traceoff: 3111 - traceon/traceoff:
3323 These commands turn tracing on and off when 3112 These commands turn tracing on and off when the specified
3324 functions are hit. The parameter determines 3113 functions are hit. The parameter determines how many times the
3325 tracing system is turned on and off. If uns 3114 tracing system is turned on and off. If unspecified, there is
3326 no limit. For example, to disable tracing w 3115 no limit. For example, to disable tracing when a schedule bug
3327 is hit the first 5 times, run:: 3116 is hit the first 5 times, run::
3328 3117
3329 echo '__schedule_bug:traceoff:5' > set_ftr 3118 echo '__schedule_bug:traceoff:5' > set_ftrace_filter
3330 3119
3331 To always disable tracing when __schedule_b 3120 To always disable tracing when __schedule_bug is hit::
3332 3121
3333 echo '__schedule_bug:traceoff' > set_ftrac 3122 echo '__schedule_bug:traceoff' > set_ftrace_filter
3334 3123
3335 These commands are cumulative whether or no 3124 These commands are cumulative whether or not they are appended
3336 to set_ftrace_filter. To remove a command, 3125 to set_ftrace_filter. To remove a command, prepend it by '!'
3337 and drop the parameter:: 3126 and drop the parameter::
3338 3127
3339 echo '!__schedule_bug:traceoff:0' > set_ft 3128 echo '!__schedule_bug:traceoff:0' > set_ftrace_filter
3340 3129
3341 The above removes the traceoff command for 3130 The above removes the traceoff command for __schedule_bug
3342 that have a counter. To remove commands wit 3131 that have a counter. To remove commands without counters::
3343 3132
3344 echo '!__schedule_bug:traceoff' > set_ftra 3133 echo '!__schedule_bug:traceoff' > set_ftrace_filter
3345 3134
3346 - snapshot: 3135 - snapshot:
3347 Will cause a snapshot to be triggered when 3136 Will cause a snapshot to be triggered when the function is hit.
3348 :: 3137 ::
3349 3138
3350 echo 'native_flush_tlb_others:snapshot' > 3139 echo 'native_flush_tlb_others:snapshot' > set_ftrace_filter
3351 3140
3352 To only snapshot once: 3141 To only snapshot once:
3353 :: 3142 ::
3354 3143
3355 echo 'native_flush_tlb_others:snapshot:1' 3144 echo 'native_flush_tlb_others:snapshot:1' > set_ftrace_filter
3356 3145
3357 To remove the above commands:: 3146 To remove the above commands::
3358 3147
3359 echo '!native_flush_tlb_others:snapshot' > 3148 echo '!native_flush_tlb_others:snapshot' > set_ftrace_filter
3360 echo '!native_flush_tlb_others:snapshot:0' 3149 echo '!native_flush_tlb_others:snapshot:0' > set_ftrace_filter
3361 3150
3362 - enable_event/disable_event: 3151 - enable_event/disable_event:
3363 These commands can enable or disable a trac 3152 These commands can enable or disable a trace event. Note, because
3364 function tracing callbacks are very sensiti 3153 function tracing callbacks are very sensitive, when these commands
3365 are registered, the trace point is activate 3154 are registered, the trace point is activated, but disabled in
3366 a "soft" mode. That is, the tracepoint will 3155 a "soft" mode. That is, the tracepoint will be called, but
3367 just will not be traced. The event tracepoi 3156 just will not be traced. The event tracepoint stays in this mode
3368 as long as there's a command that triggers 3157 as long as there's a command that triggers it.
3369 :: 3158 ::
3370 3159
3371 echo 'try_to_wake_up:enable_event:sched:sc 3160 echo 'try_to_wake_up:enable_event:sched:sched_switch:2' > \
3372 set_ftrace_filter 3161 set_ftrace_filter
3373 3162
3374 The format is:: 3163 The format is::
3375 3164
3376 <function>:enable_event:<system>:<event>[ 3165 <function>:enable_event:<system>:<event>[:count]
3377 <function>:disable_event:<system>:<event> 3166 <function>:disable_event:<system>:<event>[:count]
3378 3167
3379 To remove the events commands:: 3168 To remove the events commands::
3380 3169
3381 echo '!try_to_wake_up:enable_event:sched:s 3170 echo '!try_to_wake_up:enable_event:sched:sched_switch:0' > \
3382 set_ftrace_filter 3171 set_ftrace_filter
3383 echo '!schedule:disable_event:sched:sched_ 3172 echo '!schedule:disable_event:sched:sched_switch' > \
3384 set_ftrace_filter 3173 set_ftrace_filter
3385 3174
3386 - dump: 3175 - dump:
3387 When the function is hit, it will dump the 3176 When the function is hit, it will dump the contents of the ftrace
3388 ring buffer to the console. This is useful 3177 ring buffer to the console. This is useful if you need to debug
3389 something, and want to dump the trace when 3178 something, and want to dump the trace when a certain function
3390 is hit. Perhaps it's a function that is cal 3179 is hit. Perhaps it's a function that is called before a triple
3391 fault happens and does not allow you to get 3180 fault happens and does not allow you to get a regular dump.
3392 3181
3393 - cpudump: 3182 - cpudump:
3394 When the function is hit, it will dump the 3183 When the function is hit, it will dump the contents of the ftrace
3395 ring buffer for the current CPU to the cons 3184 ring buffer for the current CPU to the console. Unlike the "dump"
3396 command, it only prints out the contents of 3185 command, it only prints out the contents of the ring buffer for the
3397 CPU that executed the function that trigger 3186 CPU that executed the function that triggered the dump.
3398 3187
3399 - stacktrace: 3188 - stacktrace:
3400 When the function is hit, a stack trace is 3189 When the function is hit, a stack trace is recorded.
3401 3190
3402 trace_pipe 3191 trace_pipe
3403 ---------- 3192 ----------
3404 3193
3405 The trace_pipe outputs the same content as th 3194 The trace_pipe outputs the same content as the trace file, but
3406 the effect on the tracing is different. Every 3195 the effect on the tracing is different. Every read from
3407 trace_pipe is consumed. This means that subse 3196 trace_pipe is consumed. This means that subsequent reads will be
3408 different. The trace is live. 3197 different. The trace is live.
3409 :: 3198 ::
3410 3199
3411 # echo function > current_tracer 3200 # echo function > current_tracer
3412 # cat trace_pipe > /tmp/trace.out & 3201 # cat trace_pipe > /tmp/trace.out &
3413 [1] 4153 3202 [1] 4153
3414 # echo 1 > tracing_on 3203 # echo 1 > tracing_on
3415 # usleep 1 3204 # usleep 1
3416 # echo 0 > tracing_on 3205 # echo 0 > tracing_on
3417 # cat trace 3206 # cat trace
3418 # tracer: function 3207 # tracer: function
3419 # 3208 #
3420 # entries-in-buffer/entries-written: 0/0 3209 # entries-in-buffer/entries-written: 0/0 #P:4
3421 # 3210 #
3422 # _-----=> irq 3211 # _-----=> irqs-off
3423 # / _----=> nee 3212 # / _----=> need-resched
3424 # | / _---=> har 3213 # | / _---=> hardirq/softirq
3425 # || / _--=> pre 3214 # || / _--=> preempt-depth
3426 # ||| / dela 3215 # ||| / delay
3427 # TASK-PID CPU# |||| TIMEST 3216 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
3428 # | | | |||| | 3217 # | | | |||| | |
3429 3218
3430 # 3219 #
3431 # cat /tmp/trace.out 3220 # cat /tmp/trace.out
3432 bash-1994 [000] .... 5281.5689 3221 bash-1994 [000] .... 5281.568961: mutex_unlock <-rb_simple_write
3433 bash-1994 [000] .... 5281.5689 3222 bash-1994 [000] .... 5281.568963: __mutex_unlock_slowpath <-mutex_unlock
3434 bash-1994 [000] .... 5281.5689 3223 bash-1994 [000] .... 5281.568963: __fsnotify_parent <-fsnotify_modify
3435 bash-1994 [000] .... 5281.5689 3224 bash-1994 [000] .... 5281.568964: fsnotify <-fsnotify_modify
3436 bash-1994 [000] .... 5281.5689 3225 bash-1994 [000] .... 5281.568964: __srcu_read_lock <-fsnotify
3437 bash-1994 [000] .... 5281.5689 3226 bash-1994 [000] .... 5281.568964: add_preempt_count <-__srcu_read_lock
3438 bash-1994 [000] ...1 5281.5689 3227 bash-1994 [000] ...1 5281.568965: sub_preempt_count <-__srcu_read_lock
3439 bash-1994 [000] .... 5281.5689 3228 bash-1994 [000] .... 5281.568965: __srcu_read_unlock <-fsnotify
3440 bash-1994 [000] .... 5281.5689 3229 bash-1994 [000] .... 5281.568967: sys_dup2 <-system_call_fastpath
3441 3230
3442 3231
3443 Note, reading the trace_pipe file will block 3232 Note, reading the trace_pipe file will block until more input is
3444 added. This is contrary to the trace file. If 3233 added. This is contrary to the trace file. If any process opened
3445 the trace file for reading, it will actually 3234 the trace file for reading, it will actually disable tracing and
3446 prevent new entries from being added. The tra 3235 prevent new entries from being added. The trace_pipe file does
3447 not have this limitation. 3236 not have this limitation.
3448 3237
3449 trace entries 3238 trace entries
3450 ------------- 3239 -------------
3451 3240
3452 Having too much or not enough data can be tro 3241 Having too much or not enough data can be troublesome in
3453 diagnosing an issue in the kernel. The file b 3242 diagnosing an issue in the kernel. The file buffer_size_kb is
3454 used to modify the size of the internal trace 3243 used to modify the size of the internal trace buffers. The
3455 number listed is the number of entries that c 3244 number listed is the number of entries that can be recorded per
3456 CPU. To know the full size, multiply the numb 3245 CPU. To know the full size, multiply the number of possible CPUs
3457 with the number of entries. 3246 with the number of entries.
3458 :: 3247 ::
3459 3248
3460 # cat buffer_size_kb 3249 # cat buffer_size_kb
3461 1408 (units kilobytes) 3250 1408 (units kilobytes)
3462 3251
3463 Or simply read buffer_total_size_kb 3252 Or simply read buffer_total_size_kb
3464 :: 3253 ::
3465 3254
3466 # cat buffer_total_size_kb 3255 # cat buffer_total_size_kb
3467 5632 3256 5632
3468 3257
3469 To modify the buffer, simple echo in a number 3258 To modify the buffer, simple echo in a number (in 1024 byte segments).
3470 :: 3259 ::
3471 3260
3472 # echo 10000 > buffer_size_kb 3261 # echo 10000 > buffer_size_kb
3473 # cat buffer_size_kb 3262 # cat buffer_size_kb
3474 10000 (units kilobytes) 3263 10000 (units kilobytes)
3475 3264
3476 It will try to allocate as much as possible. 3265 It will try to allocate as much as possible. If you allocate too
3477 much, it can cause Out-Of-Memory to trigger. 3266 much, it can cause Out-Of-Memory to trigger.
3478 :: 3267 ::
3479 3268
3480 # echo 1000000000000 > buffer_size_kb 3269 # echo 1000000000000 > buffer_size_kb
3481 -bash: echo: write error: Cannot allocate m 3270 -bash: echo: write error: Cannot allocate memory
3482 # cat buffer_size_kb 3271 # cat buffer_size_kb
3483 85 3272 85
3484 3273
3485 The per_cpu buffers can be changed individual 3274 The per_cpu buffers can be changed individually as well:
3486 :: 3275 ::
3487 3276
3488 # echo 10000 > per_cpu/cpu0/buffer_size_kb 3277 # echo 10000 > per_cpu/cpu0/buffer_size_kb
3489 # echo 100 > per_cpu/cpu1/buffer_size_kb 3278 # echo 100 > per_cpu/cpu1/buffer_size_kb
3490 3279
3491 When the per_cpu buffers are not the same, th 3280 When the per_cpu buffers are not the same, the buffer_size_kb
3492 at the top level will just show an X 3281 at the top level will just show an X
3493 :: 3282 ::
3494 3283
3495 # cat buffer_size_kb 3284 # cat buffer_size_kb
3496 X 3285 X
3497 3286
3498 This is where the buffer_total_size_kb is use 3287 This is where the buffer_total_size_kb is useful:
3499 :: 3288 ::
3500 3289
3501 # cat buffer_total_size_kb 3290 # cat buffer_total_size_kb
3502 12916 3291 12916
3503 3292
3504 Writing to the top level buffer_size_kb will 3293 Writing to the top level buffer_size_kb will reset all the buffers
3505 to be the same again. 3294 to be the same again.
3506 3295
3507 Snapshot 3296 Snapshot
3508 -------- 3297 --------
3509 CONFIG_TRACER_SNAPSHOT makes a generic snapsh 3298 CONFIG_TRACER_SNAPSHOT makes a generic snapshot feature
3510 available to all non latency tracers. (Latenc 3299 available to all non latency tracers. (Latency tracers which
3511 record max latency, such as "irqsoff" or "wak 3300 record max latency, such as "irqsoff" or "wakeup", can't use
3512 this feature, since those are already using t 3301 this feature, since those are already using the snapshot
3513 mechanism internally.) 3302 mechanism internally.)
3514 3303
3515 Snapshot preserves a current trace buffer at 3304 Snapshot preserves a current trace buffer at a particular point
3516 in time without stopping tracing. Ftrace swap 3305 in time without stopping tracing. Ftrace swaps the current
3517 buffer with a spare buffer, and tracing conti 3306 buffer with a spare buffer, and tracing continues in the new
3518 current (=previous spare) buffer. 3307 current (=previous spare) buffer.
3519 3308
3520 The following tracefs files in "tracing" are 3309 The following tracefs files in "tracing" are related to this
3521 feature: 3310 feature:
3522 3311
3523 snapshot: 3312 snapshot:
3524 3313
3525 This is used to take a snapshot and t 3314 This is used to take a snapshot and to read the output
3526 of the snapshot. Echo 1 into this fil 3315 of the snapshot. Echo 1 into this file to allocate a
3527 spare buffer and to take a snapshot ( 3316 spare buffer and to take a snapshot (swap), then read
3528 the snapshot from this file in the sa 3317 the snapshot from this file in the same format as
3529 "trace" (described above in the secti 3318 "trace" (described above in the section "The File
3530 System"). Both reads snapshot and tra 3319 System"). Both reads snapshot and tracing are executable
3531 in parallel. When the spare buffer is 3320 in parallel. When the spare buffer is allocated, echoing
3532 0 frees it, and echoing else (positiv 3321 0 frees it, and echoing else (positive) values clear the
3533 snapshot contents. 3322 snapshot contents.
3534 More details are shown in the table b 3323 More details are shown in the table below.
3535 3324
3536 +--------------+------------+-------- 3325 +--------------+------------+------------+------------+
3537 |status\\input | 0 | 1 3326 |status\\input | 0 | 1 | else |
3538 +==============+============+======== 3327 +==============+============+============+============+
3539 |not allocated |(do nothing)| alloc+s 3328 |not allocated |(do nothing)| alloc+swap |(do nothing)|
3540 +--------------+------------+-------- 3329 +--------------+------------+------------+------------+
3541 |allocated | free | swap 3330 |allocated | free | swap | clear |
3542 +--------------+------------+-------- 3331 +--------------+------------+------------+------------+
3543 3332
3544 Here is an example of using the snapshot feat 3333 Here is an example of using the snapshot feature.
3545 :: 3334 ::
3546 3335
3547 # echo 1 > events/sched/enable 3336 # echo 1 > events/sched/enable
3548 # echo 1 > snapshot 3337 # echo 1 > snapshot
3549 # cat snapshot 3338 # cat snapshot
3550 # tracer: nop 3339 # tracer: nop
3551 # 3340 #
3552 # entries-in-buffer/entries-written: 71/71 3341 # entries-in-buffer/entries-written: 71/71 #P:8
3553 # 3342 #
3554 # _-----=> irq 3343 # _-----=> irqs-off
3555 # / _----=> nee 3344 # / _----=> need-resched
3556 # | / _---=> har 3345 # | / _---=> hardirq/softirq
3557 # || / _--=> pre 3346 # || / _--=> preempt-depth
3558 # ||| / dela 3347 # ||| / delay
3559 # TASK-PID CPU# |||| TIMEST 3348 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
3560 # | | | |||| | 3349 # | | | |||| | |
3561 <idle>-0 [005] d... 2440.603 3350 <idle>-0 [005] d... 2440.603828: sched_switch: prev_comm=swapper/5 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2242 next_prio=120
3562 sleep-2242 [005] d... 2440.603 3351 sleep-2242 [005] d... 2440.603846: sched_switch: prev_comm=snapshot-test-2 prev_pid=2242 prev_prio=120 prev_state=R ==> next_comm=kworker/5:1 next_pid=60 next_prio=120
3563 [...] 3352 [...]
3564 <idle>-0 [002] d... 2440.70723 3353 <idle>-0 [002] d... 2440.707230: sched_switch: prev_comm=swapper/2 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2229 next_prio=120
3565 3354
3566 # cat trace 3355 # cat trace
3567 # tracer: nop 3356 # tracer: nop
3568 # 3357 #
3569 # entries-in-buffer/entries-written: 77/77 3358 # entries-in-buffer/entries-written: 77/77 #P:8
3570 # 3359 #
3571 # _-----=> irq 3360 # _-----=> irqs-off
3572 # / _----=> nee 3361 # / _----=> need-resched
3573 # | / _---=> har 3362 # | / _---=> hardirq/softirq
3574 # || / _--=> pre 3363 # || / _--=> preempt-depth
3575 # ||| / dela 3364 # ||| / delay
3576 # TASK-PID CPU# |||| TIMEST 3365 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
3577 # | | | |||| | 3366 # | | | |||| | |
3578 <idle>-0 [007] d... 2440.707 3367 <idle>-0 [007] d... 2440.707395: sched_switch: prev_comm=swapper/7 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2243 next_prio=120
3579 snapshot-test-2-2229 [002] d... 2440.707 3368 snapshot-test-2-2229 [002] d... 2440.707438: sched_switch: prev_comm=snapshot-test-2 prev_pid=2229 prev_prio=120 prev_state=S ==> next_comm=swapper/2 next_pid=0 next_prio=120
3580 [...] 3369 [...]
3581 3370
3582 3371
3583 If you try to use this snapshot feature when 3372 If you try to use this snapshot feature when current tracer is
3584 one of the latency tracers, you will get the 3373 one of the latency tracers, you will get the following results.
3585 :: 3374 ::
3586 3375
3587 # echo wakeup > current_tracer 3376 # echo wakeup > current_tracer
3588 # echo 1 > snapshot 3377 # echo 1 > snapshot
3589 bash: echo: write error: Device or resource 3378 bash: echo: write error: Device or resource busy
3590 # cat snapshot 3379 # cat snapshot
3591 cat: snapshot: Device or resource busy 3380 cat: snapshot: Device or resource busy
3592 3381
3593 3382
3594 Instances 3383 Instances
3595 --------- 3384 ---------
3596 In the tracefs tracing directory, there is a 3385 In the tracefs tracing directory, there is a directory called "instances".
3597 This directory can have new directories creat 3386 This directory can have new directories created inside of it using
3598 mkdir, and removing directories with rmdir. T 3387 mkdir, and removing directories with rmdir. The directory created
3599 with mkdir in this directory will already con 3388 with mkdir in this directory will already contain files and other
3600 directories after it is created. 3389 directories after it is created.
3601 :: 3390 ::
3602 3391
3603 # mkdir instances/foo 3392 # mkdir instances/foo
3604 # ls instances/foo 3393 # ls instances/foo
3605 buffer_size_kb buffer_total_size_kb event 3394 buffer_size_kb buffer_total_size_kb events free_buffer per_cpu
3606 set_event snapshot trace trace_clock tr 3395 set_event snapshot trace trace_clock trace_marker trace_options
3607 trace_pipe tracing_on 3396 trace_pipe tracing_on
3608 3397
3609 As you can see, the new directory looks simil 3398 As you can see, the new directory looks similar to the tracing directory
3610 itself. In fact, it is very similar, except t 3399 itself. In fact, it is very similar, except that the buffer and
3611 events are agnostic from the main directory, 3400 events are agnostic from the main directory, or from any other
3612 instances that are created. 3401 instances that are created.
3613 3402
3614 The files in the new directory work just like 3403 The files in the new directory work just like the files with the
3615 same name in the tracing directory except the 3404 same name in the tracing directory except the buffer that is used
3616 is a separate and new buffer. The files affec 3405 is a separate and new buffer. The files affect that buffer but do not
3617 affect the main buffer with the exception of 3406 affect the main buffer with the exception of trace_options. Currently,
3618 the trace_options affect all instances and th 3407 the trace_options affect all instances and the top level buffer
3619 the same, but this may change in future relea 3408 the same, but this may change in future releases. That is, options
3620 may become specific to the instance they resi 3409 may become specific to the instance they reside in.
3621 3410
3622 Notice that none of the function tracer files 3411 Notice that none of the function tracer files are there, nor is
3623 current_tracer and available_tracers. This is 3412 current_tracer and available_tracers. This is because the buffers
3624 can currently only have events enabled for th 3413 can currently only have events enabled for them.
3625 :: 3414 ::
3626 3415
3627 # mkdir instances/foo 3416 # mkdir instances/foo
3628 # mkdir instances/bar 3417 # mkdir instances/bar
3629 # mkdir instances/zoot 3418 # mkdir instances/zoot
3630 # echo 100000 > buffer_size_kb 3419 # echo 100000 > buffer_size_kb
3631 # echo 1000 > instances/foo/buffer_size_kb 3420 # echo 1000 > instances/foo/buffer_size_kb
3632 # echo 5000 > instances/bar/per_cpu/cpu1/bu 3421 # echo 5000 > instances/bar/per_cpu/cpu1/buffer_size_kb
3633 # echo function > current_trace 3422 # echo function > current_trace
3634 # echo 1 > instances/foo/events/sched/sched 3423 # echo 1 > instances/foo/events/sched/sched_wakeup/enable
3635 # echo 1 > instances/foo/events/sched/sched 3424 # echo 1 > instances/foo/events/sched/sched_wakeup_new/enable
3636 # echo 1 > instances/foo/events/sched/sched 3425 # echo 1 > instances/foo/events/sched/sched_switch/enable
3637 # echo 1 > instances/bar/events/irq/enable 3426 # echo 1 > instances/bar/events/irq/enable
3638 # echo 1 > instances/zoot/events/syscalls/e 3427 # echo 1 > instances/zoot/events/syscalls/enable
3639 # cat trace_pipe 3428 # cat trace_pipe
3640 CPU:2 [LOST 11745 EVENTS] 3429 CPU:2 [LOST 11745 EVENTS]
3641 bash-2044 [002] .... 10594.481 3430 bash-2044 [002] .... 10594.481032: _raw_spin_lock_irqsave <-get_page_from_freelist
3642 bash-2044 [002] d... 10594.481 3431 bash-2044 [002] d... 10594.481032: add_preempt_count <-_raw_spin_lock_irqsave
3643 bash-2044 [002] d..1 10594.481 3432 bash-2044 [002] d..1 10594.481032: __rmqueue <-get_page_from_freelist
3644 bash-2044 [002] d..1 10594.481 3433 bash-2044 [002] d..1 10594.481033: _raw_spin_unlock <-get_page_from_freelist
3645 bash-2044 [002] d..1 10594.481 3434 bash-2044 [002] d..1 10594.481033: sub_preempt_count <-_raw_spin_unlock
3646 bash-2044 [002] d... 10594.481 3435 bash-2044 [002] d... 10594.481033: get_pageblock_flags_group <-get_pageblock_migratetype
3647 bash-2044 [002] d... 10594.481 3436 bash-2044 [002] d... 10594.481034: __mod_zone_page_state <-get_page_from_freelist
3648 bash-2044 [002] d... 10594.481 3437 bash-2044 [002] d... 10594.481034: zone_statistics <-get_page_from_freelist
3649 bash-2044 [002] d... 10594.481 3438 bash-2044 [002] d... 10594.481034: __inc_zone_state <-zone_statistics
3650 bash-2044 [002] d... 10594.481 3439 bash-2044 [002] d... 10594.481034: __inc_zone_state <-zone_statistics
3651 bash-2044 [002] .... 10594.481 3440 bash-2044 [002] .... 10594.481035: arch_dup_task_struct <-copy_process
3652 [...] 3441 [...]
3653 3442
3654 # cat instances/foo/trace_pipe 3443 # cat instances/foo/trace_pipe
3655 bash-1998 [000] d..4 136.676 3444 bash-1998 [000] d..4 136.676759: sched_wakeup: comm=kworker/0:1 pid=59 prio=120 success=1 target_cpu=000
3656 bash-1998 [000] dN.4 136.676 3445 bash-1998 [000] dN.4 136.676760: sched_wakeup: comm=bash pid=1998 prio=120 success=1 target_cpu=000
3657 <idle>-0 [003] d.h3 136.676 3446 <idle>-0 [003] d.h3 136.676906: sched_wakeup: comm=rcu_preempt pid=9 prio=120 success=1 target_cpu=003
3658 <idle>-0 [003] d..3 136.676 3447 <idle>-0 [003] d..3 136.676909: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=rcu_preempt next_pid=9 next_prio=120
3659 rcu_preempt-9 [003] d..3 136.676 3448 rcu_preempt-9 [003] d..3 136.676916: sched_switch: prev_comm=rcu_preempt prev_pid=9 prev_prio=120 prev_state=S ==> next_comm=swapper/3 next_pid=0 next_prio=120
3660 bash-1998 [000] d..4 136.677 3449 bash-1998 [000] d..4 136.677014: sched_wakeup: comm=kworker/0:1 pid=59 prio=120 success=1 target_cpu=000
3661 bash-1998 [000] dN.4 136.677 3450 bash-1998 [000] dN.4 136.677016: sched_wakeup: comm=bash pid=1998 prio=120 success=1 target_cpu=000
3662 bash-1998 [000] d..3 136.677 3451 bash-1998 [000] d..3 136.677018: sched_switch: prev_comm=bash prev_pid=1998 prev_prio=120 prev_state=R+ ==> next_comm=kworker/0:1 next_pid=59 next_prio=120
3663 kworker/0:1-59 [000] d..4 136.677 3452 kworker/0:1-59 [000] d..4 136.677022: sched_wakeup: comm=sshd pid=1995 prio=120 success=1 target_cpu=001
3664 kworker/0:1-59 [000] d..3 136.677 3453 kworker/0:1-59 [000] d..3 136.677025: sched_switch: prev_comm=kworker/0:1 prev_pid=59 prev_prio=120 prev_state=S ==> next_comm=bash next_pid=1998 next_prio=120
3665 [...] 3454 [...]
3666 3455
3667 # cat instances/bar/trace_pipe 3456 # cat instances/bar/trace_pipe
3668 migration/1-14 [001] d.h3 138.732 3457 migration/1-14 [001] d.h3 138.732674: softirq_raise: vec=3 [action=NET_RX]
3669 <idle>-0 [001] dNh3 138.732 3458 <idle>-0 [001] dNh3 138.732725: softirq_raise: vec=3 [action=NET_RX]
3670 bash-1998 [000] d.h1 138.733 3459 bash-1998 [000] d.h1 138.733101: softirq_raise: vec=1 [action=TIMER]
3671 bash-1998 [000] d.h1 138.733 3460 bash-1998 [000] d.h1 138.733102: softirq_raise: vec=9 [action=RCU]
3672 bash-1998 [000] ..s2 138.733 3461 bash-1998 [000] ..s2 138.733105: softirq_entry: vec=1 [action=TIMER]
3673 bash-1998 [000] ..s2 138.733 3462 bash-1998 [000] ..s2 138.733106: softirq_exit: vec=1 [action=TIMER]
3674 bash-1998 [000] ..s2 138.733 3463 bash-1998 [000] ..s2 138.733106: softirq_entry: vec=9 [action=RCU]
3675 bash-1998 [000] ..s2 138.733 3464 bash-1998 [000] ..s2 138.733109: softirq_exit: vec=9 [action=RCU]
3676 sshd-1995 [001] d.h1 138.733 3465 sshd-1995 [001] d.h1 138.733278: irq_handler_entry: irq=21 name=uhci_hcd:usb4
3677 sshd-1995 [001] d.h1 138.733 3466 sshd-1995 [001] d.h1 138.733280: irq_handler_exit: irq=21 ret=unhandled
3678 sshd-1995 [001] d.h1 138.733 3467 sshd-1995 [001] d.h1 138.733281: irq_handler_entry: irq=21 name=eth0
3679 sshd-1995 [001] d.h1 138.733 3468 sshd-1995 [001] d.h1 138.733283: irq_handler_exit: irq=21 ret=handled
3680 [...] 3469 [...]
3681 3470
3682 # cat instances/zoot/trace 3471 # cat instances/zoot/trace
3683 # tracer: nop 3472 # tracer: nop
3684 # 3473 #
3685 # entries-in-buffer/entries-written: 18996/ 3474 # entries-in-buffer/entries-written: 18996/18996 #P:4
3686 # 3475 #
3687 # _-----=> irq 3476 # _-----=> irqs-off
3688 # / _----=> nee 3477 # / _----=> need-resched
3689 # | / _---=> har 3478 # | / _---=> hardirq/softirq
3690 # || / _--=> pre 3479 # || / _--=> preempt-depth
3691 # ||| / dela 3480 # ||| / delay
3692 # TASK-PID CPU# |||| TIMEST 3481 # TASK-PID CPU# |||| TIMESTAMP FUNCTION
3693 # | | | |||| | 3482 # | | | |||| | |
3694 bash-1998 [000] d... 140.733 3483 bash-1998 [000] d... 140.733501: sys_write -> 0x2
3695 bash-1998 [000] d... 140.733 3484 bash-1998 [000] d... 140.733504: sys_dup2(oldfd: a, newfd: 1)
3696 bash-1998 [000] d... 140.733 3485 bash-1998 [000] d... 140.733506: sys_dup2 -> 0x1
3697 bash-1998 [000] d... 140.733 3486 bash-1998 [000] d... 140.733508: sys_fcntl(fd: a, cmd: 1, arg: 0)
3698 bash-1998 [000] d... 140.733 3487 bash-1998 [000] d... 140.733509: sys_fcntl -> 0x1
3699 bash-1998 [000] d... 140.733 3488 bash-1998 [000] d... 140.733510: sys_close(fd: a)
3700 bash-1998 [000] d... 140.733 3489 bash-1998 [000] d... 140.733510: sys_close -> 0x0
3701 bash-1998 [000] d... 140.733 3490 bash-1998 [000] d... 140.733514: sys_rt_sigprocmask(how: 0, nset: 0, oset: 6e2768, sigsetsize: 8)
3702 bash-1998 [000] d... 140.733 3491 bash-1998 [000] d... 140.733515: sys_rt_sigprocmask -> 0x0
3703 bash-1998 [000] d... 140.733 3492 bash-1998 [000] d... 140.733516: sys_rt_sigaction(sig: 2, act: 7fff718846f0, oact: 7fff71884650, sigsetsize: 8)
3704 bash-1998 [000] d... 140.733 3493 bash-1998 [000] d... 140.733516: sys_rt_sigaction -> 0x0
3705 3494
3706 You can see that the trace of the top most tr 3495 You can see that the trace of the top most trace buffer shows only
3707 the function tracing. The foo instance displa 3496 the function tracing. The foo instance displays wakeups and task
3708 switches. 3497 switches.
3709 3498
3710 To remove the instances, simply delete their 3499 To remove the instances, simply delete their directories:
3711 :: 3500 ::
3712 3501
3713 # rmdir instances/foo 3502 # rmdir instances/foo
3714 # rmdir instances/bar 3503 # rmdir instances/bar
3715 # rmdir instances/zoot 3504 # rmdir instances/zoot
3716 3505
3717 Note, if a process has a trace file open in o 3506 Note, if a process has a trace file open in one of the instance
3718 directories, the rmdir will fail with EBUSY. 3507 directories, the rmdir will fail with EBUSY.
3719 3508
3720 3509
3721 Stack trace 3510 Stack trace
3722 ----------- 3511 -----------
3723 Since the kernel has a fixed sized stack, it 3512 Since the kernel has a fixed sized stack, it is important not to
3724 waste it in functions. A kernel developer mus !! 3513 waste it in functions. A kernel developer must be conscience of
3725 what they allocate on the stack. If they add 3514 what they allocate on the stack. If they add too much, the system
3726 can be in danger of a stack overflow, and cor 3515 can be in danger of a stack overflow, and corruption will occur,
3727 usually leading to a system panic. 3516 usually leading to a system panic.
3728 3517
3729 There are some tools that check this, usually 3518 There are some tools that check this, usually with interrupts
3730 periodically checking usage. But if you can p 3519 periodically checking usage. But if you can perform a check
3731 at every function call that will become very 3520 at every function call that will become very useful. As ftrace provides
3732 a function tracer, it makes it convenient to 3521 a function tracer, it makes it convenient to check the stack size
3733 at every function call. This is enabled via t 3522 at every function call. This is enabled via the stack tracer.
3734 3523
3735 CONFIG_STACK_TRACER enables the ftrace stack 3524 CONFIG_STACK_TRACER enables the ftrace stack tracing functionality.
3736 To enable it, write a '1' into /proc/sys/kern 3525 To enable it, write a '1' into /proc/sys/kernel/stack_tracer_enabled.
3737 :: 3526 ::
3738 3527
3739 # echo 1 > /proc/sys/kernel/stack_tracer_ena 3528 # echo 1 > /proc/sys/kernel/stack_tracer_enabled
3740 3529
3741 You can also enable it from the kernel comman 3530 You can also enable it from the kernel command line to trace
3742 the stack size of the kernel during boot up, 3531 the stack size of the kernel during boot up, by adding "stacktrace"
3743 to the kernel command line parameter. 3532 to the kernel command line parameter.
3744 3533
3745 After running it for a few minutes, the outpu 3534 After running it for a few minutes, the output looks like:
3746 :: 3535 ::
3747 3536
3748 # cat stack_max_size 3537 # cat stack_max_size
3749 2928 3538 2928
3750 3539
3751 # cat stack_trace 3540 # cat stack_trace
3752 Depth Size Location (18 ent 3541 Depth Size Location (18 entries)
3753 ----- ---- -------- 3542 ----- ---- --------
3754 0) 2928 224 update_sd_lb_stats+ 3543 0) 2928 224 update_sd_lb_stats+0xbc/0x4ac
3755 1) 2704 160 find_busiest_group+ 3544 1) 2704 160 find_busiest_group+0x31/0x1f1
3756 2) 2544 256 load_balance+0xd9/0 3545 2) 2544 256 load_balance+0xd9/0x662
3757 3) 2288 80 idle_balance+0xbb/0 3546 3) 2288 80 idle_balance+0xbb/0x130
3758 4) 2208 128 __schedule+0x26e/0x 3547 4) 2208 128 __schedule+0x26e/0x5b9
3759 5) 2080 16 schedule+0x64/0x66 3548 5) 2080 16 schedule+0x64/0x66
3760 6) 2064 128 schedule_timeout+0x 3549 6) 2064 128 schedule_timeout+0x34/0xe0
3761 7) 1936 112 wait_for_common+0x9 3550 7) 1936 112 wait_for_common+0x97/0xf1
3762 8) 1824 16 wait_for_completion 3551 8) 1824 16 wait_for_completion+0x1d/0x1f
3763 9) 1808 128 flush_work+0xfe/0x1 3552 9) 1808 128 flush_work+0xfe/0x119
3764 10) 1680 16 tty_flush_to_ldisc+ 3553 10) 1680 16 tty_flush_to_ldisc+0x1e/0x20
3765 11) 1664 48 input_available_p+0 3554 11) 1664 48 input_available_p+0x1d/0x5c
3766 12) 1616 48 n_tty_poll+0x6d/0x1 3555 12) 1616 48 n_tty_poll+0x6d/0x134
3767 13) 1568 64 tty_poll+0x64/0x7f 3556 13) 1568 64 tty_poll+0x64/0x7f
3768 14) 1504 880 do_select+0x31e/0x5 3557 14) 1504 880 do_select+0x31e/0x511
3769 15) 624 400 core_sys_select+0x1 3558 15) 624 400 core_sys_select+0x177/0x216
3770 16) 224 96 sys_select+0x91/0xb 3559 16) 224 96 sys_select+0x91/0xb9
3771 17) 128 128 system_call_fastpat 3560 17) 128 128 system_call_fastpath+0x16/0x1b
3772 3561
3773 Note, if -mfentry is being used by gcc, funct 3562 Note, if -mfentry is being used by gcc, functions get traced before
3774 they set up the stack frame. This means that 3563 they set up the stack frame. This means that leaf level functions
3775 are not tested by the stack tracer when -mfen 3564 are not tested by the stack tracer when -mfentry is used.
3776 3565
3777 Currently, -mfentry is used by gcc 4.6.0 and 3566 Currently, -mfentry is used by gcc 4.6.0 and above on x86 only.
3778 3567
3779 More 3568 More
3780 ---- 3569 ----
3781 More details can be found in the source code, 3570 More details can be found in the source code, in the `kernel/trace/*.c` files.
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.