Commit | Line | Data |
---|---|---|
eb6d42ea SR |
1 | ftrace - Function Tracer |
2 | ======================== | |
3 | ||
4 | Copyright 2008 Red Hat Inc. | |
a41eebab SR |
5 | Author: Steven Rostedt <srostedt@redhat.com> |
6 | License: The GNU Free Documentation License, Version 1.2 | |
a97762a7 | 7 | (dual licensed under the GPL v2) |
f2d9c740 SR |
8 | Reviewers: Elias Oltmanns, Randy Dunlap, Andrew Morton, |
9 | John Kacur, and David Teigland. | |
eb6d42ea | 10 | |
42ec632e | 11 | Written for: 2.6.28-rc2 |
eb6d42ea SR |
12 | |
13 | Introduction | |
14 | ------------ | |
15 | ||
16 | Ftrace is an internal tracer designed to help out developers and | |
17 | designers of systems to find what is going on inside the kernel. | |
18 | It can be used for debugging or analyzing latencies and performance | |
19 | issues that take place outside of user-space. | |
20 | ||
21 | Although ftrace is the function tracer, it also includes an | |
22 | infrastructure that allows for other types of tracing. Some of the | |
f2d9c740 | 23 | tracers that are currently in ftrace include a tracer to trace |
eb6d42ea SR |
24 | context switches, the time it takes for a high priority task to |
25 | run after it was woken up, the time interrupts are disabled, and | |
f2d9c740 SR |
26 | more (ftrace allows for tracer plugins, which means that the list of |
27 | tracers can always grow). | |
eb6d42ea SR |
28 | |
29 | ||
30 | The File System | |
31 | --------------- | |
32 | ||
33 | Ftrace uses the debugfs file system to hold the control files as well | |
34 | as the files to display output. | |
35 | ||
36 | To mount the debugfs system: | |
37 | ||
38 | # mkdir /debug | |
39 | # mount -t debugfs nodev /debug | |
40 | ||
f2d9c740 SR |
41 | (Note: it is more common to mount at /sys/kernel/debug, but for simplicity |
42 | this document will use /debug) | |
eb6d42ea SR |
43 | |
44 | That's it! (assuming that you have ftrace configured into your kernel) | |
45 | ||
46 | After mounting the debugfs, you can see a directory called | |
47 | "tracing". This directory contains the control and output files | |
48 | of ftrace. Here is a list of some of the key files: | |
49 | ||
50 | ||
51 | Note: all time values are in microseconds. | |
52 | ||
9b803c0f | 53 | current_tracer: This is used to set or display the current tracer |
eb6d42ea SR |
54 | that is configured. |
55 | ||
9b803c0f | 56 | available_tracers: This holds the different types of tracers that |
a41eebab | 57 | have been compiled into the kernel. The tracers |
f2d9c740 SR |
58 | listed here can be configured by echoing their name |
59 | into current_tracer. | |
eb6d42ea | 60 | |
9b803c0f | 61 | tracing_enabled: This sets or displays whether the current_tracer |
eb6d42ea | 62 | is activated and tracing or not. Echo 0 into this |
f2d9c740 | 63 | file to disable the tracer or 1 to enable it. |
eb6d42ea | 64 | |
9b803c0f | 65 | trace: This file holds the output of the trace in a human readable |
f2d9c740 | 66 | format (described below). |
eb6d42ea | 67 | |
9b803c0f | 68 | latency_trace: This file shows the same trace but the information |
eb6d42ea | 69 | is organized more to display possible latencies |
f2d9c740 | 70 | in the system (described below). |
eb6d42ea | 71 | |
9b803c0f | 72 | trace_pipe: The output is the same as the "trace" file but this |
eb6d42ea SR |
73 | file is meant to be streamed with live tracing. |
74 | Reads from this file will block until new data | |
75 | is retrieved. Unlike the "trace" and "latency_trace" | |
76 | files, this file is a consumer. This means reading | |
77 | from this file causes sequential reads to display | |
78 | more current data. Once data is read from this | |
79 | file, it is consumed, and will not be read | |
80 | again with a sequential read. The "trace" and | |
81 | "latency_trace" files are static, and if the | |
f2d9c740 | 82 | tracer is not adding more data, they will display |
eb6d42ea SR |
83 | the same information every time they are read. |
84 | ||
ee6bce52 | 85 | trace_options: This file lets the user control the amount of data |
eb6d42ea SR |
86 | that is displayed in one of the above output |
87 | files. | |
88 | ||
9b803c0f | 89 | trace_max_latency: Some of the tracers record the max latency. |
eb6d42ea SR |
90 | For example, the time interrupts are disabled. |
91 | This time is saved in this file. The max trace | |
92 | will also be stored, and displayed by either | |
93 | "trace" or "latency_trace". A new max trace will | |
94 | only be recorded if the latency is greater than | |
95 | the value in this file. (in microseconds) | |
96 | ||
1696b2b0 | 97 | buffer_size_kb: This sets or displays the number of kilobytes each CPU |
9b803c0f SR |
98 | buffer can hold. The tracer buffers are the same size |
99 | for each CPU. The displayed number is the size of the | |
1696b2b0 | 100 | CPU buffer and not total size of all buffers. The |
f2d9c740 SR |
101 | trace buffers are allocated in pages (blocks of memory |
102 | that the kernel uses for allocation, usually 4 KB in size). | |
9b803c0f SR |
103 | If the last page allocated has room for more bytes |
104 | than requested, the rest of the page will be used, | |
105 | making the actual allocation bigger than requested. | |
106 | (Note, the size may not be a multiple of the page size due | |
107 | to buffer managment overhead.) | |
eb6d42ea SR |
108 | |
109 | This can only be updated when the current_tracer | |
9b803c0f | 110 | is set to "nop". |
eb6d42ea | 111 | |
9b803c0f | 112 | tracing_cpumask: This is a mask that lets the user only trace |
eb6d42ea SR |
113 | on specified CPUS. The format is a hex string |
114 | representing the CPUS. | |
115 | ||
9b803c0f | 116 | set_ftrace_filter: When dynamic ftrace is configured in (see the |
f2d9c740 SR |
117 | section below "dynamic ftrace"), the code is dynamically |
118 | modified (code text rewrite) to disable calling of the | |
119 | function profiler (mcount). This lets tracing be configured | |
120 | in with practically no overhead in performance. This also | |
121 | has a side effect of enabling or disabling specific functions | |
122 | to be traced. Echoing names of functions into this file | |
123 | will limit the trace to only those functions. | |
124 | ||
125 | set_ftrace_notrace: This has an effect opposite to that of | |
126 | set_ftrace_filter. Any function that is added here will not | |
127 | be traced. If a function exists in both set_ftrace_filter | |
128 | and set_ftrace_notrace, the function will _not_ be traced. | |
eb6d42ea | 129 | |
df4fc315 SR |
130 | set_ftrace_pid: Have the function tracer only trace a single thread. |
131 | ||
985ec20a FW |
132 | set_graph_function: Select the function where the trace have to start |
133 | with the function graph tracer (See the section | |
134 | "dynamic ftrace" for more details). | |
135 | ||
9b803c0f SR |
136 | available_filter_functions: This lists the functions that ftrace |
137 | has processed and can trace. These are the function | |
138 | names that you can pass to "set_ftrace_filter" or | |
139 | "set_ftrace_notrace". (See the section "dynamic ftrace" | |
140 | below for more details.) | |
eb6d42ea SR |
141 | |
142 | ||
143 | The Tracers | |
144 | ----------- | |
145 | ||
f2d9c740 | 146 | Here is the list of current tracers that may be configured. |
eb6d42ea | 147 | |
9b803c0f | 148 | function - function tracer that uses mcount to trace all functions. |
eb6d42ea | 149 | |
985ec20a FW |
150 | function_graph_tracer - similar to the function tracer except that the |
151 | function tracer probes the functions on their entry whereas the | |
152 | function graph tracer traces on both entry and exit of the | |
153 | functions. It then provides the ability to draw a graph of | |
154 | function calls like a primitive C code source. | |
155 | ||
eb6d42ea SR |
156 | sched_switch - traces the context switches between tasks. |
157 | ||
f2d9c740 | 158 | irqsoff - traces the areas that disable interrupts and saves |
eb6d42ea SR |
159 | the trace with the longest max latency. |
160 | See tracing_max_latency. When a new max is recorded, | |
161 | it replaces the old trace. It is best to view this | |
f2d9c740 | 162 | trace via the latency_trace file. |
eb6d42ea | 163 | |
f2d9c740 SR |
164 | preemptoff - Similar to irqsoff but traces and records the amount of |
165 | time for which preemption is disabled. | |
eb6d42ea SR |
166 | |
167 | preemptirqsoff - Similar to irqsoff and preemptoff, but traces and | |
f2d9c740 SR |
168 | records the largest time for which irqs and/or preemption |
169 | is disabled. | |
eb6d42ea SR |
170 | |
171 | wakeup - Traces and records the max latency that it takes for | |
172 | the highest priority task to get scheduled after | |
173 | it has been woken up. | |
174 | ||
9b803c0f SR |
175 | nop - This is not a tracer. To remove all tracers from tracing |
176 | simply echo "nop" into current_tracer. | |
eb6d42ea | 177 | |
e2ea5399 MM |
178 | hw-branch-tracer - traces branches on all cpu's in a circular buffer. |
179 | ||
eb6d42ea SR |
180 | |
181 | Examples of using the tracer | |
182 | ---------------------------- | |
183 | ||
f2d9c740 SR |
184 | Here are typical examples of using the tracers when controlling them only |
185 | with the debugfs interface (without using any user-land utilities). | |
eb6d42ea SR |
186 | |
187 | Output format: | |
188 | -------------- | |
189 | ||
f2d9c740 | 190 | Here is an example of the output format of the file "trace" |
eb6d42ea SR |
191 | |
192 | -------- | |
9b803c0f | 193 | # tracer: function |
eb6d42ea SR |
194 | # |
195 | # TASK-PID CPU# TIMESTAMP FUNCTION | |
196 | # | | | | | | |
197 | bash-4251 [01] 10152.583854: path_put <-path_walk | |
198 | bash-4251 [01] 10152.583855: dput <-path_put | |
199 | bash-4251 [01] 10152.583855: _atomic_dec_and_lock <-dput | |
200 | -------- | |
201 | ||
f2d9c740 | 202 | A header is printed with the tracer name that is represented by the trace. |
9b803c0f | 203 | In this case the tracer is "function". Then a header showing the format. Task |
f2d9c740 | 204 | name "bash", the task PID "4251", the CPU that it was running on |
eb6d42ea SR |
205 | "01", the timestamp in <secs>.<usecs> format, the function name that was |
206 | traced "path_put" and the parent function that called this function | |
f2d9c740 SR |
207 | "path_walk". The timestamp is the time at which the function was |
208 | entered. | |
eb6d42ea | 209 | |
f2d9c740 | 210 | The sched_switch tracer also includes tracing of task wakeups and |
eb6d42ea SR |
211 | context switches. |
212 | ||
213 | ksoftirqd/1-7 [01] 1453.070013: 7:115:R + 2916:115:S | |
214 | ksoftirqd/1-7 [01] 1453.070013: 7:115:R + 10:115:S | |
215 | ksoftirqd/1-7 [01] 1453.070013: 7:115:R ==> 10:115:R | |
216 | events/1-10 [01] 1453.070013: 10:115:S ==> 2916:115:R | |
217 | kondemand/1-2916 [01] 1453.070013: 2916:115:S ==> 7:115:R | |
218 | ksoftirqd/1-7 [01] 1453.070013: 7:115:S ==> 0:140:R | |
219 | ||
f2d9c740 | 220 | Wake ups are represented by a "+" and the context switches are shown as |
eb6d42ea SR |
221 | "==>". The format is: |
222 | ||
223 | Context switches: | |
224 | ||
225 | Previous task Next Task | |
226 | ||
227 | <pid>:<prio>:<state> ==> <pid>:<prio>:<state> | |
228 | ||
229 | Wake ups: | |
230 | ||
231 | Current task Task waking up | |
232 | ||
233 | <pid>:<prio>:<state> + <pid>:<prio>:<state> | |
234 | ||
f2d9c740 | 235 | The prio is the internal kernel priority, which is the inverse of the |
eb6d42ea SR |
236 | priority that is usually displayed by user-space tools. Zero represents |
237 | the highest priority (99). Prio 100 starts the "nice" priorities with | |
238 | 100 being equal to nice -20 and 139 being nice 19. The prio "140" is | |
239 | reserved for the idle task which is the lowest priority thread (pid 0). | |
240 | ||
241 | ||
242 | Latency trace format | |
243 | -------------------- | |
244 | ||
245 | For traces that display latency times, the latency_trace file gives | |
f2d9c740 | 246 | somewhat more information to see why a latency happened. Here is a typical |
eb6d42ea SR |
247 | trace. |
248 | ||
249 | # tracer: irqsoff | |
250 | # | |
251 | irqsoff latency trace v1.1.5 on 2.6.26-rc8 | |
252 | -------------------------------------------------------------------- | |
253 | latency: 97 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) | |
254 | ----------------- | |
255 | | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) | |
256 | ----------------- | |
257 | => started at: apic_timer_interrupt | |
258 | => ended at: do_softirq | |
259 | ||
260 | # _------=> CPU# | |
261 | # / _-----=> irqs-off | |
262 | # | / _----=> need-resched | |
263 | # || / _---=> hardirq/softirq | |
264 | # ||| / _--=> preempt-depth | |
265 | # |||| / | |
266 | # ||||| delay | |
267 | # cmd pid ||||| time | caller | |
268 | # \ / ||||| \ | / | |
269 | <idle>-0 0d..1 0us+: trace_hardirqs_off_thunk (apic_timer_interrupt) | |
270 | <idle>-0 0d.s. 97us : __do_softirq (do_softirq) | |
271 | <idle>-0 0d.s1 98us : trace_hardirqs_on (do_softirq) | |
272 | ||
273 | ||
eb6d42ea | 274 | |
f2d9c740 SR |
275 | This shows that the current tracer is "irqsoff" tracing the time for which |
276 | interrupts were disabled. It gives the trace version and the version | |
277 | of the kernel upon which this was executed on (2.6.26-rc8). Then it displays | |
278 | the max latency in microsecs (97 us). The number of trace entries displayed | |
279 | and the total number recorded (both are three: #3/3). The type of | |
eb6d42ea | 280 | preemption that was used (PREEMPT). VP, KP, SP, and HP are always zero |
f2d9c740 | 281 | and are reserved for later use. #P is the number of online CPUS (#P:2). |
eb6d42ea | 282 | |
f2d9c740 | 283 | The task is the process that was running when the latency occurred. |
eb6d42ea SR |
284 | (swapper pid: 0). |
285 | ||
f2d9c740 SR |
286 | The start and stop (the functions in which the interrupts were disabled and |
287 | enabled respectively) that caused the latencies: | |
eb6d42ea SR |
288 | |
289 | apic_timer_interrupt is where the interrupts were disabled. | |
290 | do_softirq is where they were enabled again. | |
291 | ||
292 | The next lines after the header are the trace itself. The header | |
293 | explains which is which. | |
294 | ||
295 | cmd: The name of the process in the trace. | |
296 | ||
297 | pid: The PID of that process. | |
298 | ||
f2d9c740 | 299 | CPU#: The CPU which the process was running on. |
eb6d42ea SR |
300 | |
301 | irqs-off: 'd' interrupts are disabled. '.' otherwise. | |
9244489a SR |
302 | Note: If the architecture does not support a way to |
303 | read the irq flags variable, an 'X' will always | |
304 | be printed here. | |
eb6d42ea SR |
305 | |
306 | need-resched: 'N' task need_resched is set, '.' otherwise. | |
307 | ||
308 | hardirq/softirq: | |
f2d9c740 | 309 | 'H' - hard irq occurred inside a softirq. |
eb6d42ea SR |
310 | 'h' - hard irq is running |
311 | 's' - soft irq is running | |
312 | '.' - normal context. | |
313 | ||
314 | preempt-depth: The level of preempt_disabled | |
315 | ||
316 | The above is mostly meaningful for kernel developers. | |
317 | ||
a41eebab | 318 | time: This differs from the trace file output. The trace file output |
f2d9c740 | 319 | includes an absolute timestamp. The timestamp used by the |
a41eebab | 320 | latency_trace file is relative to the start of the trace. |
eb6d42ea SR |
321 | |
322 | delay: This is just to help catch your eye a bit better. And | |
323 | needs to be fixed to be only relative to the same CPU. | |
a41eebab | 324 | The marks are determined by the difference between this |
eb6d42ea SR |
325 | current trace and the next trace. |
326 | '!' - greater than preempt_mark_thresh (default 100) | |
327 | '+' - greater than 1 microsecond | |
328 | ' ' - less than or equal to 1 microsecond. | |
329 | ||
330 | The rest is the same as the 'trace' file. | |
331 | ||
332 | ||
ee6bce52 SR |
333 | trace_options |
334 | ------------- | |
eb6d42ea | 335 | |
ee6bce52 | 336 | The trace_options file is used to control what gets printed in the trace |
eb6d42ea SR |
337 | output. To see what is available, simply cat the file: |
338 | ||
ee6bce52 | 339 | cat /debug/tracing/trace_options |
eb6d42ea | 340 | print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \ |
b54d3de9 | 341 | noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj |
eb6d42ea | 342 | |
a41eebab | 343 | To disable one of the options, echo in the option prepended with "no". |
eb6d42ea | 344 | |
ee6bce52 | 345 | echo noprint-parent > /debug/tracing/trace_options |
eb6d42ea SR |
346 | |
347 | To enable an option, leave off the "no". | |
348 | ||
ee6bce52 | 349 | echo sym-offset > /debug/tracing/trace_options |
eb6d42ea SR |
350 | |
351 | Here are the available options: | |
352 | ||
353 | print-parent - On function traces, display the calling function | |
354 | as well as the function being traced. | |
355 | ||
356 | print-parent: | |
357 | bash-4000 [01] 1477.606694: simple_strtoul <-strict_strtoul | |
358 | ||
359 | noprint-parent: | |
360 | bash-4000 [01] 1477.606694: simple_strtoul | |
361 | ||
362 | ||
363 | sym-offset - Display not only the function name, but also the offset | |
364 | in the function. For example, instead of seeing just | |
a41eebab | 365 | "ktime_get", you will see "ktime_get+0xb/0x20". |
eb6d42ea SR |
366 | |
367 | sym-offset: | |
368 | bash-4000 [01] 1477.606694: simple_strtoul+0x6/0xa0 | |
369 | ||
370 | sym-addr - this will also display the function address as well as | |
371 | the function name. | |
372 | ||
373 | sym-addr: | |
374 | bash-4000 [01] 1477.606694: simple_strtoul <c0339346> | |
375 | ||
376 | verbose - This deals with the latency_trace file. | |
377 | ||
378 | bash 4000 1 0 00000000 00010a95 [58127d26] 1720.415ms \ | |
379 | (+0.000ms): simple_strtoul (strict_strtoul) | |
380 | ||
381 | raw - This will display raw numbers. This option is best for use with | |
382 | user applications that can translate the raw numbers better than | |
383 | having it done in the kernel. | |
384 | ||
a41eebab | 385 | hex - Similar to raw, but the numbers will be in a hexadecimal format. |
eb6d42ea SR |
386 | |
387 | bin - This will print out the formats in raw binary. | |
388 | ||
389 | block - TBD (needs update) | |
390 | ||
391 | stacktrace - This is one of the options that changes the trace itself. | |
392 | When a trace is recorded, so is the stack of functions. | |
393 | This allows for back traces of trace sites. | |
394 | ||
02b67518 TE |
395 | userstacktrace - This option changes the trace. |
396 | It records a stacktrace of the current userspace thread. | |
397 | ||
b54d3de9 TE |
398 | sym-userobj - when user stacktrace are enabled, look up which object the |
399 | address belongs to, and print a relative address | |
400 | This is especially useful when ASLR is on, otherwise you don't | |
401 | get a chance to resolve the address to object/file/line after the app is no | |
402 | longer running | |
403 | ||
404 | The lookup is performed when you read trace,trace_pipe,latency_trace. Example: | |
405 | ||
406 | a.out-1623 [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0 | |
407 | x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6] | |
408 | ||
eb6d42ea SR |
409 | sched-tree - TBD (any users??) |
410 | ||
411 | ||
412 | sched_switch | |
413 | ------------ | |
414 | ||
f2d9c740 | 415 | This tracer simply records schedule switches. Here is an example |
a41eebab | 416 | of how to use it. |
eb6d42ea SR |
417 | |
418 | # echo sched_switch > /debug/tracing/current_tracer | |
419 | # echo 1 > /debug/tracing/tracing_enabled | |
420 | # sleep 1 | |
421 | # echo 0 > /debug/tracing/tracing_enabled | |
422 | # cat /debug/tracing/trace | |
423 | ||
424 | # tracer: sched_switch | |
425 | # | |
426 | # TASK-PID CPU# TIMESTAMP FUNCTION | |
427 | # | | | | | | |
428 | bash-3997 [01] 240.132281: 3997:120:R + 4055:120:R | |
429 | bash-3997 [01] 240.132284: 3997:120:R ==> 4055:120:R | |
430 | sleep-4055 [01] 240.132371: 4055:120:S ==> 3997:120:R | |
431 | bash-3997 [01] 240.132454: 3997:120:R + 4055:120:S | |
432 | bash-3997 [01] 240.132457: 3997:120:R ==> 4055:120:R | |
433 | sleep-4055 [01] 240.132460: 4055:120:D ==> 3997:120:R | |
434 | bash-3997 [01] 240.132463: 3997:120:R + 4055:120:D | |
435 | bash-3997 [01] 240.132465: 3997:120:R ==> 4055:120:R | |
436 | <idle>-0 [00] 240.132589: 0:140:R + 4:115:S | |
437 | <idle>-0 [00] 240.132591: 0:140:R ==> 4:115:R | |
438 | ksoftirqd/0-4 [00] 240.132595: 4:115:S ==> 0:140:R | |
439 | <idle>-0 [00] 240.132598: 0:140:R + 4:115:S | |
440 | <idle>-0 [00] 240.132599: 0:140:R ==> 4:115:R | |
441 | ksoftirqd/0-4 [00] 240.132603: 4:115:S ==> 0:140:R | |
442 | sleep-4055 [01] 240.133058: 4055:120:S ==> 3997:120:R | |
443 | [...] | |
444 | ||
445 | ||
446 | As we have discussed previously about this format, the header shows | |
447 | the name of the trace and points to the options. The "FUNCTION" | |
448 | is a misnomer since here it represents the wake ups and context | |
449 | switches. | |
450 | ||
f2d9c740 SR |
451 | The sched_switch file only lists the wake ups (represented with '+') |
452 | and context switches ('==>') with the previous task or current task | |
eb6d42ea SR |
453 | first followed by the next task or task waking up. The format for both |
454 | of these is PID:KERNEL-PRIO:TASK-STATE. Remember that the KERNEL-PRIO | |
455 | is the inverse of the actual priority with zero (0) being the highest | |
456 | priority and the nice values starting at 100 (nice -20). Below is | |
457 | a quick chart to map the kernel priority to user land priorities. | |
458 | ||
459 | Kernel priority: 0 to 99 ==> user RT priority 99 to 0 | |
460 | Kernel priority: 100 to 139 ==> user nice -20 to 19 | |
461 | Kernel priority: 140 ==> idle task priority | |
462 | ||
463 | The task states are: | |
464 | ||
465 | R - running : wants to run, may not actually be running | |
466 | S - sleep : process is waiting to be woken up (handles signals) | |
f2d9c740 SR |
467 | D - disk sleep (uninterruptible sleep) : process must be woken up |
468 | (ignores signals) | |
eb6d42ea SR |
469 | T - stopped : process suspended |
470 | t - traced : process is being traced (with something like gdb) | |
471 | Z - zombie : process waiting to be cleaned up | |
472 | X - unknown | |
473 | ||
474 | ||
475 | ftrace_enabled | |
476 | -------------- | |
477 | ||
f2d9c740 SR |
478 | The following tracers (listed below) give different output depending |
479 | on whether or not the sysctl ftrace_enabled is set. To set ftrace_enabled, | |
eb6d42ea SR |
480 | one can either use the sysctl function or set it via the proc |
481 | file system interface. | |
482 | ||
483 | sysctl kernel.ftrace_enabled=1 | |
484 | ||
485 | or | |
486 | ||
487 | echo 1 > /proc/sys/kernel/ftrace_enabled | |
488 | ||
489 | To disable ftrace_enabled simply replace the '1' with '0' in | |
490 | the above commands. | |
491 | ||
492 | When ftrace_enabled is set the tracers will also record the functions | |
493 | that are within the trace. The descriptions of the tracers | |
494 | will also show an example with ftrace enabled. | |
495 | ||
496 | ||
497 | irqsoff | |
498 | ------- | |
499 | ||
500 | When interrupts are disabled, the CPU can not react to any other | |
501 | external event (besides NMIs and SMIs). This prevents the timer | |
502 | interrupt from triggering or the mouse interrupt from letting the | |
503 | kernel know of a new mouse event. The result is a latency with the | |
504 | reaction time. | |
505 | ||
f2d9c740 SR |
506 | The irqsoff tracer tracks the time for which interrupts are disabled. |
507 | When a new maximum latency is hit, the tracer saves the trace leading up | |
508 | to that latency point so that every time a new maximum is reached, the old | |
509 | saved trace is discarded and the new trace is saved. | |
eb6d42ea | 510 | |
f2d9c740 | 511 | To reset the maximum, echo 0 into tracing_max_latency. Here is an |
eb6d42ea SR |
512 | example: |
513 | ||
514 | # echo irqsoff > /debug/tracing/current_tracer | |
515 | # echo 0 > /debug/tracing/tracing_max_latency | |
516 | # echo 1 > /debug/tracing/tracing_enabled | |
517 | # ls -ltr | |
518 | [...] | |
519 | # echo 0 > /debug/tracing/tracing_enabled | |
520 | # cat /debug/tracing/latency_trace | |
521 | # tracer: irqsoff | |
522 | # | |
f2d9c740 | 523 | irqsoff latency trace v1.1.5 on 2.6.26 |
eb6d42ea | 524 | -------------------------------------------------------------------- |
f2d9c740 | 525 | latency: 12 us, #3/3, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) |
eb6d42ea | 526 | ----------------- |
f2d9c740 | 527 | | task: bash-3730 (uid:0 nice:0 policy:0 rt_prio:0) |
eb6d42ea | 528 | ----------------- |
f2d9c740 SR |
529 | => started at: sys_setpgid |
530 | => ended at: sys_setpgid | |
eb6d42ea SR |
531 | |
532 | # _------=> CPU# | |
533 | # / _-----=> irqs-off | |
534 | # | / _----=> need-resched | |
535 | # || / _---=> hardirq/softirq | |
536 | # ||| / _--=> preempt-depth | |
537 | # |||| / | |
538 | # ||||| delay | |
539 | # cmd pid ||||| time | caller | |
540 | # \ / ||||| \ | / | |
f2d9c740 SR |
541 | bash-3730 1d... 0us : _write_lock_irq (sys_setpgid) |
542 | bash-3730 1d..1 1us+: _write_unlock_irq (sys_setpgid) | |
543 | bash-3730 1d..2 14us : trace_hardirqs_on (sys_setpgid) | |
eb6d42ea | 544 | |
eb6d42ea | 545 | |
f2d9c740 SR |
546 | Here we see that that we had a latency of 12 microsecs (which is |
547 | very good). The _write_lock_irq in sys_setpgid disabled interrupts. | |
548 | The difference between the 12 and the displayed timestamp 14us occurred | |
549 | because the clock was incremented between the time of recording the max | |
550 | latency and the time of recording the function that had that latency. | |
eb6d42ea | 551 | |
f2d9c740 SR |
552 | Note the above example had ftrace_enabled not set. If we set the |
553 | ftrace_enabled, we get a much larger output: | |
eb6d42ea SR |
554 | |
555 | # tracer: irqsoff | |
556 | # | |
557 | irqsoff latency trace v1.1.5 on 2.6.26-rc8 | |
558 | -------------------------------------------------------------------- | |
559 | latency: 50 us, #101/101, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) | |
560 | ----------------- | |
561 | | task: ls-4339 (uid:0 nice:0 policy:0 rt_prio:0) | |
562 | ----------------- | |
563 | => started at: __alloc_pages_internal | |
564 | => ended at: __alloc_pages_internal | |
565 | ||
566 | # _------=> CPU# | |
567 | # / _-----=> irqs-off | |
568 | # | / _----=> need-resched | |
569 | # || / _---=> hardirq/softirq | |
570 | # ||| / _--=> preempt-depth | |
571 | # |||| / | |
572 | # ||||| delay | |
573 | # cmd pid ||||| time | caller | |
574 | # \ / ||||| \ | / | |
575 | ls-4339 0...1 0us+: get_page_from_freelist (__alloc_pages_internal) | |
576 | ls-4339 0d..1 3us : rmqueue_bulk (get_page_from_freelist) | |
577 | ls-4339 0d..1 3us : _spin_lock (rmqueue_bulk) | |
578 | ls-4339 0d..1 4us : add_preempt_count (_spin_lock) | |
579 | ls-4339 0d..2 4us : __rmqueue (rmqueue_bulk) | |
580 | ls-4339 0d..2 5us : __rmqueue_smallest (__rmqueue) | |
581 | ls-4339 0d..2 5us : __mod_zone_page_state (__rmqueue_smallest) | |
582 | ls-4339 0d..2 6us : __rmqueue (rmqueue_bulk) | |
583 | ls-4339 0d..2 6us : __rmqueue_smallest (__rmqueue) | |
584 | ls-4339 0d..2 7us : __mod_zone_page_state (__rmqueue_smallest) | |
585 | ls-4339 0d..2 7us : __rmqueue (rmqueue_bulk) | |
586 | ls-4339 0d..2 8us : __rmqueue_smallest (__rmqueue) | |
587 | [...] | |
588 | ls-4339 0d..2 46us : __rmqueue_smallest (__rmqueue) | |
589 | ls-4339 0d..2 47us : __mod_zone_page_state (__rmqueue_smallest) | |
590 | ls-4339 0d..2 47us : __rmqueue (rmqueue_bulk) | |
591 | ls-4339 0d..2 48us : __rmqueue_smallest (__rmqueue) | |
592 | ls-4339 0d..2 48us : __mod_zone_page_state (__rmqueue_smallest) | |
593 | ls-4339 0d..2 49us : _spin_unlock (rmqueue_bulk) | |
594 | ls-4339 0d..2 49us : sub_preempt_count (_spin_unlock) | |
595 | ls-4339 0d..1 50us : get_page_from_freelist (__alloc_pages_internal) | |
596 | ls-4339 0d..2 51us : trace_hardirqs_on (__alloc_pages_internal) | |
597 | ||
598 | ||
eb6d42ea SR |
599 | |
600 | Here we traced a 50 microsecond latency. But we also see all the | |
a41eebab | 601 | functions that were called during that time. Note that by enabling |
f2d9c740 | 602 | function tracing, we incur an added overhead. This overhead may |
a41eebab SR |
603 | extend the latency times. But nevertheless, this trace has provided |
604 | some very helpful debugging information. | |
eb6d42ea SR |
605 | |
606 | ||
607 | preemptoff | |
608 | ---------- | |
609 | ||
a41eebab SR |
610 | When preemption is disabled, we may be able to receive interrupts but |
611 | the task cannot be preempted and a higher priority task must wait | |
eb6d42ea SR |
612 | for preemption to be enabled again before it can preempt a lower |
613 | priority task. | |
614 | ||
a41eebab | 615 | The preemptoff tracer traces the places that disable preemption. |
f2d9c740 SR |
616 | Like the irqsoff tracer, it records the maximum latency for which preemption |
617 | was disabled. The control of preemptoff tracer is much like the irqsoff | |
618 | tracer. | |
eb6d42ea SR |
619 | |
620 | # echo preemptoff > /debug/tracing/current_tracer | |
621 | # echo 0 > /debug/tracing/tracing_max_latency | |
622 | # echo 1 > /debug/tracing/tracing_enabled | |
623 | # ls -ltr | |
624 | [...] | |
625 | # echo 0 > /debug/tracing/tracing_enabled | |
626 | # cat /debug/tracing/latency_trace | |
627 | # tracer: preemptoff | |
628 | # | |
629 | preemptoff latency trace v1.1.5 on 2.6.26-rc8 | |
630 | -------------------------------------------------------------------- | |
631 | latency: 29 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) | |
632 | ----------------- | |
633 | | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0) | |
634 | ----------------- | |
635 | => started at: do_IRQ | |
636 | => ended at: __do_softirq | |
637 | ||
638 | # _------=> CPU# | |
639 | # / _-----=> irqs-off | |
640 | # | / _----=> need-resched | |
641 | # || / _---=> hardirq/softirq | |
642 | # ||| / _--=> preempt-depth | |
643 | # |||| / | |
644 | # ||||| delay | |
645 | # cmd pid ||||| time | caller | |
646 | # \ / ||||| \ | / | |
647 | sshd-4261 0d.h. 0us+: irq_enter (do_IRQ) | |
648 | sshd-4261 0d.s. 29us : _local_bh_enable (__do_softirq) | |
649 | sshd-4261 0d.s1 30us : trace_preempt_on (__do_softirq) | |
650 | ||
651 | ||
eb6d42ea SR |
652 | This has some more changes. Preemption was disabled when an interrupt |
653 | came in (notice the 'h'), and was enabled while doing a softirq. | |
654 | (notice the 's'). But we also see that interrupts have been disabled | |
655 | when entering the preempt off section and leaving it (the 'd'). | |
656 | We do not know if interrupts were enabled in the mean time. | |
657 | ||
658 | # tracer: preemptoff | |
659 | # | |
660 | preemptoff latency trace v1.1.5 on 2.6.26-rc8 | |
661 | -------------------------------------------------------------------- | |
662 | latency: 63 us, #87/87, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) | |
663 | ----------------- | |
664 | | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0) | |
665 | ----------------- | |
666 | => started at: remove_wait_queue | |
667 | => ended at: __do_softirq | |
668 | ||
669 | # _------=> CPU# | |
670 | # / _-----=> irqs-off | |
671 | # | / _----=> need-resched | |
672 | # || / _---=> hardirq/softirq | |
673 | # ||| / _--=> preempt-depth | |
674 | # |||| / | |
675 | # ||||| delay | |
676 | # cmd pid ||||| time | caller | |
677 | # \ / ||||| \ | / | |
678 | sshd-4261 0d..1 0us : _spin_lock_irqsave (remove_wait_queue) | |
679 | sshd-4261 0d..1 1us : _spin_unlock_irqrestore (remove_wait_queue) | |
680 | sshd-4261 0d..1 2us : do_IRQ (common_interrupt) | |
681 | sshd-4261 0d..1 2us : irq_enter (do_IRQ) | |
682 | sshd-4261 0d..1 2us : idle_cpu (irq_enter) | |
683 | sshd-4261 0d..1 3us : add_preempt_count (irq_enter) | |
684 | sshd-4261 0d.h1 3us : idle_cpu (irq_enter) | |
685 | sshd-4261 0d.h. 4us : handle_fasteoi_irq (do_IRQ) | |
686 | [...] | |
687 | sshd-4261 0d.h. 12us : add_preempt_count (_spin_lock) | |
688 | sshd-4261 0d.h1 12us : ack_ioapic_quirk_irq (handle_fasteoi_irq) | |
689 | sshd-4261 0d.h1 13us : move_native_irq (ack_ioapic_quirk_irq) | |
690 | sshd-4261 0d.h1 13us : _spin_unlock (handle_fasteoi_irq) | |
691 | sshd-4261 0d.h1 14us : sub_preempt_count (_spin_unlock) | |
692 | sshd-4261 0d.h1 14us : irq_exit (do_IRQ) | |
693 | sshd-4261 0d.h1 15us : sub_preempt_count (irq_exit) | |
694 | sshd-4261 0d..2 15us : do_softirq (irq_exit) | |
695 | sshd-4261 0d... 15us : __do_softirq (do_softirq) | |
696 | sshd-4261 0d... 16us : __local_bh_disable (__do_softirq) | |
697 | sshd-4261 0d... 16us+: add_preempt_count (__local_bh_disable) | |
698 | sshd-4261 0d.s4 20us : add_preempt_count (__local_bh_disable) | |
699 | sshd-4261 0d.s4 21us : sub_preempt_count (local_bh_enable) | |
700 | sshd-4261 0d.s5 21us : sub_preempt_count (local_bh_enable) | |
701 | [...] | |
702 | sshd-4261 0d.s6 41us : add_preempt_count (__local_bh_disable) | |
703 | sshd-4261 0d.s6 42us : sub_preempt_count (local_bh_enable) | |
704 | sshd-4261 0d.s7 42us : sub_preempt_count (local_bh_enable) | |
705 | sshd-4261 0d.s5 43us : add_preempt_count (__local_bh_disable) | |
706 | sshd-4261 0d.s5 43us : sub_preempt_count (local_bh_enable_ip) | |
707 | sshd-4261 0d.s6 44us : sub_preempt_count (local_bh_enable_ip) | |
708 | sshd-4261 0d.s5 44us : add_preempt_count (__local_bh_disable) | |
709 | sshd-4261 0d.s5 45us : sub_preempt_count (local_bh_enable) | |
710 | [...] | |
711 | sshd-4261 0d.s. 63us : _local_bh_enable (__do_softirq) | |
712 | sshd-4261 0d.s1 64us : trace_preempt_on (__do_softirq) | |
713 | ||
714 | ||
715 | The above is an example of the preemptoff trace with ftrace_enabled | |
716 | set. Here we see that interrupts were disabled the entire time. | |
717 | The irq_enter code lets us know that we entered an interrupt 'h'. | |
718 | Before that, the functions being traced still show that it is not | |
f2d9c740 | 719 | in an interrupt, but we can see from the functions themselves that |
eb6d42ea SR |
720 | this is not the case. |
721 | ||
f2d9c740 SR |
722 | Notice that __do_softirq when called does not have a preempt_count. |
723 | It may seem that we missed a preempt enabling. What really happened | |
724 | is that the preempt count is held on the thread's stack and we | |
eb6d42ea | 725 | switched to the softirq stack (4K stacks in effect). The code |
a41eebab | 726 | does not copy the preempt count, but because interrupts are disabled, |
f2d9c740 SR |
727 | we do not need to worry about it. Having a tracer like this is good |
728 | for letting people know what really happens inside the kernel. | |
eb6d42ea SR |
729 | |
730 | ||
731 | preemptirqsoff | |
732 | -------------- | |
733 | ||
734 | Knowing the locations that have interrupts disabled or preemption | |
735 | disabled for the longest times is helpful. But sometimes we would | |
736 | like to know when either preemption and/or interrupts are disabled. | |
737 | ||
f2d9c740 | 738 | Consider the following code: |
eb6d42ea SR |
739 | |
740 | local_irq_disable(); | |
741 | call_function_with_irqs_off(); | |
742 | preempt_disable(); | |
743 | call_function_with_irqs_and_preemption_off(); | |
744 | local_irq_enable(); | |
745 | call_function_with_preemption_off(); | |
746 | preempt_enable(); | |
747 | ||
748 | The irqsoff tracer will record the total length of | |
749 | call_function_with_irqs_off() and | |
750 | call_function_with_irqs_and_preemption_off(). | |
751 | ||
752 | The preemptoff tracer will record the total length of | |
753 | call_function_with_irqs_and_preemption_off() and | |
754 | call_function_with_preemption_off(). | |
755 | ||
756 | But neither will trace the time that interrupts and/or preemption | |
757 | is disabled. This total time is the time that we can not schedule. | |
758 | To record this time, use the preemptirqsoff tracer. | |
759 | ||
760 | Again, using this trace is much like the irqsoff and preemptoff tracers. | |
761 | ||
a41eebab | 762 | # echo preemptirqsoff > /debug/tracing/current_tracer |
eb6d42ea SR |
763 | # echo 0 > /debug/tracing/tracing_max_latency |
764 | # echo 1 > /debug/tracing/tracing_enabled | |
765 | # ls -ltr | |
766 | [...] | |
767 | # echo 0 > /debug/tracing/tracing_enabled | |
768 | # cat /debug/tracing/latency_trace | |
769 | # tracer: preemptirqsoff | |
770 | # | |
771 | preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8 | |
772 | -------------------------------------------------------------------- | |
773 | latency: 293 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) | |
774 | ----------------- | |
775 | | task: ls-4860 (uid:0 nice:0 policy:0 rt_prio:0) | |
776 | ----------------- | |
777 | => started at: apic_timer_interrupt | |
778 | => ended at: __do_softirq | |
779 | ||
780 | # _------=> CPU# | |
781 | # / _-----=> irqs-off | |
782 | # | / _----=> need-resched | |
783 | # || / _---=> hardirq/softirq | |
784 | # ||| / _--=> preempt-depth | |
785 | # |||| / | |
786 | # ||||| delay | |
787 | # cmd pid ||||| time | caller | |
788 | # \ / ||||| \ | / | |
789 | ls-4860 0d... 0us!: trace_hardirqs_off_thunk (apic_timer_interrupt) | |
790 | ls-4860 0d.s. 294us : _local_bh_enable (__do_softirq) | |
791 | ls-4860 0d.s1 294us : trace_preempt_on (__do_softirq) | |
792 | ||
793 | ||
eb6d42ea SR |
794 | |
795 | The trace_hardirqs_off_thunk is called from assembly on x86 when | |
796 | interrupts are disabled in the assembly code. Without the function | |
f2d9c740 | 797 | tracing, we do not know if interrupts were enabled within the preemption |
eb6d42ea SR |
798 | points. We do see that it started with preemption enabled. |
799 | ||
800 | Here is a trace with ftrace_enabled set: | |
801 | ||
802 | ||
803 | # tracer: preemptirqsoff | |
804 | # | |
805 | preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8 | |
806 | -------------------------------------------------------------------- | |
807 | latency: 105 us, #183/183, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) | |
808 | ----------------- | |
809 | | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0) | |
810 | ----------------- | |
811 | => started at: write_chan | |
812 | => ended at: __do_softirq | |
813 | ||
814 | # _------=> CPU# | |
815 | # / _-----=> irqs-off | |
816 | # | / _----=> need-resched | |
817 | # || / _---=> hardirq/softirq | |
818 | # ||| / _--=> preempt-depth | |
819 | # |||| / | |
820 | # ||||| delay | |
821 | # cmd pid ||||| time | caller | |
822 | # \ / ||||| \ | / | |
823 | ls-4473 0.N.. 0us : preempt_schedule (write_chan) | |
824 | ls-4473 0dN.1 1us : _spin_lock (schedule) | |
825 | ls-4473 0dN.1 2us : add_preempt_count (_spin_lock) | |
826 | ls-4473 0d..2 2us : put_prev_task_fair (schedule) | |
827 | [...] | |
828 | ls-4473 0d..2 13us : set_normalized_timespec (ktime_get_ts) | |
829 | ls-4473 0d..2 13us : __switch_to (schedule) | |
830 | sshd-4261 0d..2 14us : finish_task_switch (schedule) | |
831 | sshd-4261 0d..2 14us : _spin_unlock_irq (finish_task_switch) | |
832 | sshd-4261 0d..1 15us : add_preempt_count (_spin_lock_irqsave) | |
833 | sshd-4261 0d..2 16us : _spin_unlock_irqrestore (hrtick_set) | |
834 | sshd-4261 0d..2 16us : do_IRQ (common_interrupt) | |
835 | sshd-4261 0d..2 17us : irq_enter (do_IRQ) | |
836 | sshd-4261 0d..2 17us : idle_cpu (irq_enter) | |
837 | sshd-4261 0d..2 18us : add_preempt_count (irq_enter) | |
838 | sshd-4261 0d.h2 18us : idle_cpu (irq_enter) | |
839 | sshd-4261 0d.h. 18us : handle_fasteoi_irq (do_IRQ) | |
840 | sshd-4261 0d.h. 19us : _spin_lock (handle_fasteoi_irq) | |
841 | sshd-4261 0d.h. 19us : add_preempt_count (_spin_lock) | |
842 | sshd-4261 0d.h1 20us : _spin_unlock (handle_fasteoi_irq) | |
843 | sshd-4261 0d.h1 20us : sub_preempt_count (_spin_unlock) | |
844 | [...] | |
845 | sshd-4261 0d.h1 28us : _spin_unlock (handle_fasteoi_irq) | |
846 | sshd-4261 0d.h1 29us : sub_preempt_count (_spin_unlock) | |
847 | sshd-4261 0d.h2 29us : irq_exit (do_IRQ) | |
848 | sshd-4261 0d.h2 29us : sub_preempt_count (irq_exit) | |
849 | sshd-4261 0d..3 30us : do_softirq (irq_exit) | |
850 | sshd-4261 0d... 30us : __do_softirq (do_softirq) | |
851 | sshd-4261 0d... 31us : __local_bh_disable (__do_softirq) | |
852 | sshd-4261 0d... 31us+: add_preempt_count (__local_bh_disable) | |
853 | sshd-4261 0d.s4 34us : add_preempt_count (__local_bh_disable) | |
854 | [...] | |
855 | sshd-4261 0d.s3 43us : sub_preempt_count (local_bh_enable_ip) | |
856 | sshd-4261 0d.s4 44us : sub_preempt_count (local_bh_enable_ip) | |
857 | sshd-4261 0d.s3 44us : smp_apic_timer_interrupt (apic_timer_interrupt) | |
858 | sshd-4261 0d.s3 45us : irq_enter (smp_apic_timer_interrupt) | |
859 | sshd-4261 0d.s3 45us : idle_cpu (irq_enter) | |
860 | sshd-4261 0d.s3 46us : add_preempt_count (irq_enter) | |
861 | sshd-4261 0d.H3 46us : idle_cpu (irq_enter) | |
862 | sshd-4261 0d.H3 47us : hrtimer_interrupt (smp_apic_timer_interrupt) | |
863 | sshd-4261 0d.H3 47us : ktime_get (hrtimer_interrupt) | |
864 | [...] | |
865 | sshd-4261 0d.H3 81us : tick_program_event (hrtimer_interrupt) | |
866 | sshd-4261 0d.H3 82us : ktime_get (tick_program_event) | |
867 | sshd-4261 0d.H3 82us : ktime_get_ts (ktime_get) | |
868 | sshd-4261 0d.H3 83us : getnstimeofday (ktime_get_ts) | |
869 | sshd-4261 0d.H3 83us : set_normalized_timespec (ktime_get_ts) | |
870 | sshd-4261 0d.H3 84us : clockevents_program_event (tick_program_event) | |
871 | sshd-4261 0d.H3 84us : lapic_next_event (clockevents_program_event) | |
872 | sshd-4261 0d.H3 85us : irq_exit (smp_apic_timer_interrupt) | |
873 | sshd-4261 0d.H3 85us : sub_preempt_count (irq_exit) | |
874 | sshd-4261 0d.s4 86us : sub_preempt_count (irq_exit) | |
875 | sshd-4261 0d.s3 86us : add_preempt_count (__local_bh_disable) | |
876 | [...] | |
877 | sshd-4261 0d.s1 98us : sub_preempt_count (net_rx_action) | |
878 | sshd-4261 0d.s. 99us : add_preempt_count (_spin_lock_irq) | |
879 | sshd-4261 0d.s1 99us+: _spin_unlock_irq (run_timer_softirq) | |
880 | sshd-4261 0d.s. 104us : _local_bh_enable (__do_softirq) | |
881 | sshd-4261 0d.s. 104us : sub_preempt_count (_local_bh_enable) | |
882 | sshd-4261 0d.s. 105us : _local_bh_enable (__do_softirq) | |
883 | sshd-4261 0d.s1 105us : trace_preempt_on (__do_softirq) | |
884 | ||
885 | ||
886 | This is a very interesting trace. It started with the preemption of | |
887 | the ls task. We see that the task had the "need_resched" bit set | |
f2d9c740 SR |
888 | via the 'N' in the trace. Interrupts were disabled before the spin_lock |
889 | at the beginning of the trace. We see that a schedule took place to run | |
a41eebab SR |
890 | sshd. When the interrupts were enabled, we took an interrupt. |
891 | On return from the interrupt handler, the softirq ran. We took another | |
f2d9c740 | 892 | interrupt while running the softirq as we see from the capital 'H'. |
eb6d42ea SR |
893 | |
894 | ||
895 | wakeup | |
896 | ------ | |
897 | ||
f2d9c740 SR |
898 | In a Real-Time environment it is very important to know the wakeup |
899 | time it takes for the highest priority task that is woken up to the | |
900 | time that it executes. This is also known as "schedule latency". | |
eb6d42ea SR |
901 | I stress the point that this is about RT tasks. It is also important |
902 | to know the scheduling latency of non-RT tasks, but the average | |
903 | schedule latency is better for non-RT tasks. Tools like | |
a41eebab | 904 | LatencyTop are more appropriate for such measurements. |
eb6d42ea | 905 | |
a41eebab | 906 | Real-Time environments are interested in the worst case latency. |
eb6d42ea SR |
907 | That is the longest latency it takes for something to happen, and |
908 | not the average. We can have a very fast scheduler that may only | |
909 | have a large latency once in a while, but that would not work well | |
910 | with Real-Time tasks. The wakeup tracer was designed to record | |
911 | the worst case wakeups of RT tasks. Non-RT tasks are not recorded | |
912 | because the tracer only records one worst case and tracing non-RT | |
913 | tasks that are unpredictable will overwrite the worst case latency | |
914 | of RT tasks. | |
915 | ||
916 | Since this tracer only deals with RT tasks, we will run this slightly | |
a41eebab SR |
917 | differently than we did with the previous tracers. Instead of performing |
918 | an 'ls', we will run 'sleep 1' under 'chrt' which changes the | |
eb6d42ea SR |
919 | priority of the task. |
920 | ||
921 | # echo wakeup > /debug/tracing/current_tracer | |
922 | # echo 0 > /debug/tracing/tracing_max_latency | |
923 | # echo 1 > /debug/tracing/tracing_enabled | |
924 | # chrt -f 5 sleep 1 | |
925 | # echo 0 > /debug/tracing/tracing_enabled | |
926 | # cat /debug/tracing/latency_trace | |
927 | # tracer: wakeup | |
928 | # | |
929 | wakeup latency trace v1.1.5 on 2.6.26-rc8 | |
930 | -------------------------------------------------------------------- | |
931 | latency: 4 us, #2/2, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) | |
932 | ----------------- | |
933 | | task: sleep-4901 (uid:0 nice:0 policy:1 rt_prio:5) | |
934 | ----------------- | |
935 | ||
936 | # _------=> CPU# | |
937 | # / _-----=> irqs-off | |
938 | # | / _----=> need-resched | |
939 | # || / _---=> hardirq/softirq | |
940 | # ||| / _--=> preempt-depth | |
941 | # |||| / | |
942 | # ||||| delay | |
943 | # cmd pid ||||| time | caller | |
944 | # \ / ||||| \ | / | |
945 | <idle>-0 1d.h4 0us+: try_to_wake_up (wake_up_process) | |
946 | <idle>-0 1d..4 4us : schedule (cpu_idle) | |
947 | ||
948 | ||
eb6d42ea | 949 | |
a41eebab | 950 | Running this on an idle system, we see that it only took 4 microseconds |
eb6d42ea | 951 | to perform the task switch. Note, since the trace marker in the |
a41eebab | 952 | schedule is before the actual "switch", we stop the tracing when |
eb6d42ea SR |
953 | the recorded task is about to schedule in. This may change if |
954 | we add a new marker at the end of the scheduler. | |
955 | ||
956 | Notice that the recorded task is 'sleep' with the PID of 4901 and it | |
957 | has an rt_prio of 5. This priority is user-space priority and not | |
958 | the internal kernel priority. The policy is 1 for SCHED_FIFO and 2 | |
959 | for SCHED_RR. | |
960 | ||
961 | Doing the same with chrt -r 5 and ftrace_enabled set. | |
962 | ||
963 | # tracer: wakeup | |
964 | # | |
965 | wakeup latency trace v1.1.5 on 2.6.26-rc8 | |
966 | -------------------------------------------------------------------- | |
967 | latency: 50 us, #60/60, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) | |
968 | ----------------- | |
969 | | task: sleep-4068 (uid:0 nice:0 policy:2 rt_prio:5) | |
970 | ----------------- | |
971 | ||
972 | # _------=> CPU# | |
973 | # / _-----=> irqs-off | |
974 | # | / _----=> need-resched | |
975 | # || / _---=> hardirq/softirq | |
976 | # ||| / _--=> preempt-depth | |
977 | # |||| / | |
978 | # ||||| delay | |
979 | # cmd pid ||||| time | caller | |
980 | # \ / ||||| \ | / | |
981 | ksoftirq-7 1d.H3 0us : try_to_wake_up (wake_up_process) | |
982 | ksoftirq-7 1d.H4 1us : sub_preempt_count (marker_probe_cb) | |
983 | ksoftirq-7 1d.H3 2us : check_preempt_wakeup (try_to_wake_up) | |
984 | ksoftirq-7 1d.H3 3us : update_curr (check_preempt_wakeup) | |
985 | ksoftirq-7 1d.H3 4us : calc_delta_mine (update_curr) | |
986 | ksoftirq-7 1d.H3 5us : __resched_task (check_preempt_wakeup) | |
987 | ksoftirq-7 1d.H3 6us : task_wake_up_rt (try_to_wake_up) | |
988 | ksoftirq-7 1d.H3 7us : _spin_unlock_irqrestore (try_to_wake_up) | |
989 | [...] | |
990 | ksoftirq-7 1d.H2 17us : irq_exit (smp_apic_timer_interrupt) | |
991 | ksoftirq-7 1d.H2 18us : sub_preempt_count (irq_exit) | |
992 | ksoftirq-7 1d.s3 19us : sub_preempt_count (irq_exit) | |
993 | ksoftirq-7 1..s2 20us : rcu_process_callbacks (__do_softirq) | |
994 | [...] | |
995 | ksoftirq-7 1..s2 26us : __rcu_process_callbacks (rcu_process_callbacks) | |
996 | ksoftirq-7 1d.s2 27us : _local_bh_enable (__do_softirq) | |
997 | ksoftirq-7 1d.s2 28us : sub_preempt_count (_local_bh_enable) | |
998 | ksoftirq-7 1.N.3 29us : sub_preempt_count (ksoftirqd) | |
999 | ksoftirq-7 1.N.2 30us : _cond_resched (ksoftirqd) | |
1000 | ksoftirq-7 1.N.2 31us : __cond_resched (_cond_resched) | |
1001 | ksoftirq-7 1.N.2 32us : add_preempt_count (__cond_resched) | |
1002 | ksoftirq-7 1.N.2 33us : schedule (__cond_resched) | |
1003 | ksoftirq-7 1.N.2 33us : add_preempt_count (schedule) | |
1004 | ksoftirq-7 1.N.3 34us : hrtick_clear (schedule) | |
1005 | ksoftirq-7 1dN.3 35us : _spin_lock (schedule) | |
1006 | ksoftirq-7 1dN.3 36us : add_preempt_count (_spin_lock) | |
1007 | ksoftirq-7 1d..4 37us : put_prev_task_fair (schedule) | |
1008 | ksoftirq-7 1d..4 38us : update_curr (put_prev_task_fair) | |
1009 | [...] | |
1010 | ksoftirq-7 1d..5 47us : _spin_trylock (tracing_record_cmdline) | |
1011 | ksoftirq-7 1d..5 48us : add_preempt_count (_spin_trylock) | |
1012 | ksoftirq-7 1d..6 49us : _spin_unlock (tracing_record_cmdline) | |
1013 | ksoftirq-7 1d..6 49us : sub_preempt_count (_spin_unlock) | |
1014 | ksoftirq-7 1d..4 50us : schedule (__cond_resched) | |
1015 | ||
1016 | The interrupt went off while running ksoftirqd. This task runs at | |
f2d9c740 | 1017 | SCHED_OTHER. Why did not we see the 'N' set early? This may be |
a41eebab | 1018 | a harmless bug with x86_32 and 4K stacks. On x86_32 with 4K stacks |
f2d9c740 | 1019 | configured, the interrupt and softirq run with their own stack. |
a41eebab SR |
1020 | Some information is held on the top of the task's stack (need_resched |
1021 | and preempt_count are both stored there). The setting of the NEED_RESCHED | |
1022 | bit is done directly to the task's stack, but the reading of the | |
1023 | NEED_RESCHED is done by looking at the current stack, which in this case | |
1024 | is the stack for the hard interrupt. This hides the fact that NEED_RESCHED | |
f2d9c740 | 1025 | has been set. We do not see the 'N' until we switch back to the task's |
a41eebab | 1026 | assigned stack. |
eb6d42ea | 1027 | |
9b803c0f SR |
1028 | function |
1029 | -------- | |
eb6d42ea | 1030 | |
9b803c0f SR |
1031 | This tracer is the function tracer. Enabling the function tracer |
1032 | can be done from the debug file system. Make sure the ftrace_enabled is | |
1033 | set; otherwise this tracer is a nop. | |
eb6d42ea SR |
1034 | |
1035 | # sysctl kernel.ftrace_enabled=1 | |
9b803c0f | 1036 | # echo function > /debug/tracing/current_tracer |
eb6d42ea SR |
1037 | # echo 1 > /debug/tracing/tracing_enabled |
1038 | # usleep 1 | |
1039 | # echo 0 > /debug/tracing/tracing_enabled | |
1040 | # cat /debug/tracing/trace | |
9b803c0f | 1041 | # tracer: function |
eb6d42ea SR |
1042 | # |
1043 | # TASK-PID CPU# TIMESTAMP FUNCTION | |
1044 | # | | | | | | |
1045 | bash-4003 [00] 123.638713: finish_task_switch <-schedule | |
1046 | bash-4003 [00] 123.638714: _spin_unlock_irq <-finish_task_switch | |
1047 | bash-4003 [00] 123.638714: sub_preempt_count <-_spin_unlock_irq | |
1048 | bash-4003 [00] 123.638715: hrtick_set <-schedule | |
1049 | bash-4003 [00] 123.638715: _spin_lock_irqsave <-hrtick_set | |
1050 | bash-4003 [00] 123.638716: add_preempt_count <-_spin_lock_irqsave | |
1051 | bash-4003 [00] 123.638716: _spin_unlock_irqrestore <-hrtick_set | |
1052 | bash-4003 [00] 123.638717: sub_preempt_count <-_spin_unlock_irqrestore | |
1053 | bash-4003 [00] 123.638717: hrtick_clear <-hrtick_set | |
1054 | bash-4003 [00] 123.638718: sub_preempt_count <-schedule | |
1055 | bash-4003 [00] 123.638718: sub_preempt_count <-preempt_schedule | |
1056 | bash-4003 [00] 123.638719: wait_for_completion <-__stop_machine_run | |
1057 | bash-4003 [00] 123.638719: wait_for_common <-wait_for_completion | |
1058 | bash-4003 [00] 123.638720: _spin_lock_irq <-wait_for_common | |
1059 | bash-4003 [00] 123.638720: add_preempt_count <-_spin_lock_irq | |
1060 | [...] | |
1061 | ||
1062 | ||
9b803c0f SR |
1063 | Note: function tracer uses ring buffers to store the above entries. |
1064 | The newest data may overwrite the oldest data. Sometimes using echo to | |
1065 | stop the trace is not sufficient because the tracing could have overwritten | |
1066 | the data that you wanted to record. For this reason, it is sometimes better to | |
f2d9c740 SR |
1067 | disable tracing directly from a program. This allows you to stop the |
1068 | tracing at the point that you hit the part that you are interested in. | |
1069 | To disable the tracing directly from a C program, something like following | |
1070 | code snippet can be used: | |
eb6d42ea SR |
1071 | |
1072 | int trace_fd; | |
1073 | [...] | |
1074 | int main(int argc, char *argv[]) { | |
1075 | [...] | |
1076 | trace_fd = open("/debug/tracing/tracing_enabled", O_WRONLY); | |
1077 | [...] | |
1078 | if (condition_hit()) { | |
f2d9c740 | 1079 | write(trace_fd, "0", 1); |
eb6d42ea SR |
1080 | } |
1081 | [...] | |
1082 | } | |
1083 | ||
f2d9c740 SR |
1084 | Note: Here we hard coded the path name. The debugfs mount is not |
1085 | guaranteed to be at /debug (and is more commonly at /sys/kernel/debug). | |
1086 | For simple one time traces, the above is sufficent. For anything else, | |
1087 | a search through /proc/mounts may be needed to find where the debugfs | |
1088 | file-system is mounted. | |
eb6d42ea | 1089 | |
df4fc315 SR |
1090 | |
1091 | Single thread tracing | |
1092 | --------------------- | |
1093 | ||
1094 | By writing into /debug/tracing/set_ftrace_pid you can trace a | |
1095 | single thread. For example: | |
1096 | ||
1097 | # cat /debug/tracing/set_ftrace_pid | |
1098 | no pid | |
1099 | # echo 3111 > /debug/tracing/set_ftrace_pid | |
1100 | # cat /debug/tracing/set_ftrace_pid | |
1101 | 3111 | |
1102 | # echo function > /debug/tracing/current_tracer | |
1103 | # cat /debug/tracing/trace | head | |
1104 | # tracer: function | |
1105 | # | |
1106 | # TASK-PID CPU# TIMESTAMP FUNCTION | |
1107 | # | | | | | | |
1108 | yum-updatesd-3111 [003] 1637.254676: finish_task_switch <-thread_return | |
1109 | yum-updatesd-3111 [003] 1637.254681: hrtimer_cancel <-schedule_hrtimeout_range | |
1110 | yum-updatesd-3111 [003] 1637.254682: hrtimer_try_to_cancel <-hrtimer_cancel | |
1111 | yum-updatesd-3111 [003] 1637.254683: lock_hrtimer_base <-hrtimer_try_to_cancel | |
1112 | yum-updatesd-3111 [003] 1637.254685: fget_light <-do_sys_poll | |
1113 | yum-updatesd-3111 [003] 1637.254686: pipe_poll <-do_sys_poll | |
1114 | # echo -1 > /debug/tracing/set_ftrace_pid | |
1115 | # cat /debug/tracing/trace |head | |
1116 | # tracer: function | |
1117 | # | |
1118 | # TASK-PID CPU# TIMESTAMP FUNCTION | |
1119 | # | | | | | | |
1120 | ##### CPU 3 buffer started #### | |
1121 | yum-updatesd-3111 [003] 1701.957688: free_poll_entry <-poll_freewait | |
1122 | yum-updatesd-3111 [003] 1701.957689: remove_wait_queue <-free_poll_entry | |
1123 | yum-updatesd-3111 [003] 1701.957691: fput <-free_poll_entry | |
1124 | yum-updatesd-3111 [003] 1701.957692: audit_syscall_exit <-sysret_audit | |
1125 | yum-updatesd-3111 [003] 1701.957693: path_put <-audit_syscall_exit | |
1126 | ||
1127 | If you want to trace a function when executing, you could use | |
1128 | something like this simple program: | |
1129 | ||
1130 | #include <stdio.h> | |
1131 | #include <stdlib.h> | |
1132 | #include <sys/types.h> | |
1133 | #include <sys/stat.h> | |
1134 | #include <fcntl.h> | |
1135 | #include <unistd.h> | |
1136 | ||
1137 | int main (int argc, char **argv) | |
1138 | { | |
1139 | if (argc < 1) | |
1140 | exit(-1); | |
1141 | ||
1142 | if (fork() > 0) { | |
1143 | int fd, ffd; | |
1144 | char line[64]; | |
1145 | int s; | |
1146 | ||
1147 | ffd = open("/debug/tracing/current_tracer", O_WRONLY); | |
1148 | if (ffd < 0) | |
1149 | exit(-1); | |
1150 | write(ffd, "nop", 3); | |
1151 | ||
1152 | fd = open("/debug/tracing/set_ftrace_pid", O_WRONLY); | |
1153 | s = sprintf(line, "%d\n", getpid()); | |
1154 | write(fd, line, s); | |
1155 | ||
1156 | write(ffd, "function", 8); | |
1157 | ||
1158 | close(fd); | |
1159 | close(ffd); | |
1160 | ||
1161 | execvp(argv[1], argv+1); | |
1162 | } | |
1163 | ||
1164 | return 0; | |
1165 | } | |
1166 | ||
e2ea5399 MM |
1167 | |
1168 | hw-branch-tracer (x86 only) | |
1169 | --------------------------- | |
1170 | ||
1171 | This tracer uses the x86 last branch tracing hardware feature to | |
1172 | collect a branch trace on all cpus with relatively low overhead. | |
1173 | ||
1174 | The tracer uses a fixed-size circular buffer per cpu and only | |
1175 | traces ring 0 branches. The trace file dumps that buffer in the | |
1176 | following format: | |
1177 | ||
1178 | # tracer: hw-branch-tracer | |
1179 | # | |
1180 | # CPU# TO <- FROM | |
1181 | 0 scheduler_tick+0xb5/0x1bf <- task_tick_idle+0x5/0x6 | |
1182 | 2 run_posix_cpu_timers+0x2b/0x72a <- run_posix_cpu_timers+0x25/0x72a | |
1183 | 0 scheduler_tick+0x139/0x1bf <- scheduler_tick+0xed/0x1bf | |
1184 | 0 scheduler_tick+0x17c/0x1bf <- scheduler_tick+0x148/0x1bf | |
1185 | 2 run_posix_cpu_timers+0x9e/0x72a <- run_posix_cpu_timers+0x5e/0x72a | |
1186 | 0 scheduler_tick+0x1b6/0x1bf <- scheduler_tick+0x1aa/0x1bf | |
1187 | ||
1188 | ||
1189 | The tracer may be used to dump the trace for the oops'ing cpu on a | |
1190 | kernel oops into the system log. To enable this, ftrace_dump_on_oops | |
1191 | must be set. To set ftrace_dump_on_oops, one can either use the sysctl | |
1192 | function or set it via the proc system interface. | |
1193 | ||
1194 | sysctl kernel.ftrace_dump_on_oops=1 | |
1195 | ||
1196 | or | |
1197 | ||
1198 | echo 1 > /proc/sys/kernel/ftrace_dump_on_oops | |
1199 | ||
1200 | ||
1201 | Here's an example of such a dump after a null pointer dereference in a | |
1202 | kernel module: | |
1203 | ||
1204 | [57848.105921] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 | |
1205 | [57848.106019] IP: [<ffffffffa0000006>] open+0x6/0x14 [oops] | |
1206 | [57848.106019] PGD 2354e9067 PUD 2375e7067 PMD 0 | |
1207 | [57848.106019] Oops: 0002 [#1] SMP | |
1208 | [57848.106019] last sysfs file: /sys/devices/pci0000:00/0000:00:1e.0/0000:20:05.0/local_cpus | |
1209 | [57848.106019] Dumping ftrace buffer: | |
1210 | [57848.106019] --------------------------------- | |
1211 | [...] | |
1212 | [57848.106019] 0 chrdev_open+0xe6/0x165 <- cdev_put+0x23/0x24 | |
1213 | [57848.106019] 0 chrdev_open+0x117/0x165 <- chrdev_open+0xfa/0x165 | |
1214 | [57848.106019] 0 chrdev_open+0x120/0x165 <- chrdev_open+0x11c/0x165 | |
1215 | [57848.106019] 0 chrdev_open+0x134/0x165 <- chrdev_open+0x12b/0x165 | |
1216 | [57848.106019] 0 open+0x0/0x14 [oops] <- chrdev_open+0x144/0x165 | |
1217 | [57848.106019] 0 page_fault+0x0/0x30 <- open+0x6/0x14 [oops] | |
1218 | [57848.106019] 0 error_entry+0x0/0x5b <- page_fault+0x4/0x30 | |
1219 | [57848.106019] 0 error_kernelspace+0x0/0x31 <- error_entry+0x59/0x5b | |
1220 | [57848.106019] 0 error_sti+0x0/0x1 <- error_kernelspace+0x2d/0x31 | |
1221 | [57848.106019] 0 page_fault+0x9/0x30 <- error_sti+0x0/0x1 | |
1222 | [57848.106019] 0 do_page_fault+0x0/0x881 <- page_fault+0x1a/0x30 | |
1223 | [...] | |
1224 | [57848.106019] 0 do_page_fault+0x66b/0x881 <- is_prefetch+0x1ee/0x1f2 | |
1225 | [57848.106019] 0 do_page_fault+0x6e0/0x881 <- do_page_fault+0x67a/0x881 | |
1226 | [57848.106019] 0 oops_begin+0x0/0x96 <- do_page_fault+0x6e0/0x881 | |
1227 | [57848.106019] 0 trace_hw_branch_oops+0x0/0x2d <- oops_begin+0x9/0x96 | |
1228 | [...] | |
1229 | [57848.106019] 0 ds_suspend_bts+0x2a/0xe3 <- ds_suspend_bts+0x1a/0xe3 | |
1230 | [57848.106019] --------------------------------- | |
1231 | [57848.106019] CPU 0 | |
1232 | [57848.106019] Modules linked in: oops | |
1233 | [57848.106019] Pid: 5542, comm: cat Tainted: G W 2.6.28 #23 | |
1234 | [57848.106019] RIP: 0010:[<ffffffffa0000006>] [<ffffffffa0000006>] open+0x6/0x14 [oops] | |
1235 | [57848.106019] RSP: 0018:ffff880235457d48 EFLAGS: 00010246 | |
1236 | [...] | |
1237 | ||
1238 | ||
985ec20a FW |
1239 | function graph tracer |
1240 | --------------------------- | |
1241 | ||
1242 | This tracer is similar to the function tracer except that it probes | |
1243 | a function on its entry and its exit. | |
1244 | This is done by setting a dynamically allocated stack of return addresses on each | |
1245 | task_struct. Then the tracer overwrites the return address of each function traced | |
1246 | to set a custom probe. Thus the original return address is stored on the stack of return | |
1247 | address in the task_struct. | |
1248 | ||
1249 | Probing on both extremities of a function leads to special features such as | |
1250 | ||
1251 | _ measure of function's time execution | |
1252 | _ having a reliable call stack to draw function calls graph | |
1253 | ||
1254 | This tracer is useful in several situations: | |
1255 | ||
1256 | _ you want to find the reason of a strange kernel behavior and need to see | |
1257 | what happens in detail on any areas (or specific ones). | |
1258 | _ you are experiencing weird latencies but it's difficult to find its origin. | |
1259 | _ you want to find quickly which path is taken by a specific function | |
1260 | _ you just want to see what happens inside your kernel | |
1261 | ||
1262 | # tracer: function_graph | |
1263 | # | |
1264 | # CPU DURATION FUNCTION CALLS | |
1265 | # | | | | | | | | |
1266 | ||
1267 | 0) | sys_open() { | |
1268 | 0) | do_sys_open() { | |
1269 | 0) | getname() { | |
1270 | 0) | kmem_cache_alloc() { | |
1271 | 0) 1.382 us | __might_sleep(); | |
1272 | 0) 2.478 us | } | |
1273 | 0) | strncpy_from_user() { | |
1274 | 0) | might_fault() { | |
1275 | 0) 1.389 us | __might_sleep(); | |
1276 | 0) 2.553 us | } | |
1277 | 0) 3.807 us | } | |
1278 | 0) 7.876 us | } | |
1279 | 0) | alloc_fd() { | |
1280 | 0) 0.668 us | _spin_lock(); | |
1281 | 0) 0.570 us | expand_files(); | |
1282 | 0) 0.586 us | _spin_unlock(); | |
1283 | ||
1284 | ||
1285 | There are several columns that can be dynamically enabled/disabled. | |
1286 | You can use every combination of options you want, depending on your needs. | |
1287 | ||
1288 | _ The cpu number on which the function executed is default enabled. | |
1289 | It is sometimes better to only trace one cpu (see tracing_cpu_mask file) | |
1290 | or you might sometimes see unordered function calls while cpu tracing switch. | |
1291 | ||
1292 | hide: echo nofuncgraph-cpu > /debug/tracing/trace_options | |
1293 | show: echo funcgraph-cpu > /debug/tracing/trace_options | |
1294 | ||
1295 | _ The duration (function's time of execution) is displayed on the closing bracket | |
1296 | line of a function or on the same line than the current function in case of a leaf | |
1297 | one. It is default enabled. | |
1298 | ||
1299 | hide: echo nofuncgraph-duration > /debug/tracing/trace_options | |
1300 | show: echo funcgraph-duration > /debug/tracing/trace_options | |
1301 | ||
1302 | _ The overhead field precedes the duration one in case of reached duration thresholds. | |
1303 | ||
1304 | hide: echo nofuncgraph-overhead > /debug/tracing/trace_options | |
1305 | show: echo funcgraph-overhead > /debug/tracing/trace_options | |
1306 | depends on: funcgraph-duration | |
1307 | ||
1308 | ie: | |
1309 | ||
1310 | 0) | up_write() { | |
1311 | 0) 0.646 us | _spin_lock_irqsave(); | |
1312 | 0) 0.684 us | _spin_unlock_irqrestore(); | |
1313 | 0) 3.123 us | } | |
1314 | 0) 0.548 us | fput(); | |
1315 | 0) + 58.628 us | } | |
1316 | ||
1317 | [...] | |
1318 | ||
1319 | 0) | putname() { | |
1320 | 0) | kmem_cache_free() { | |
1321 | 0) 0.518 us | __phys_addr(); | |
1322 | 0) 1.757 us | } | |
1323 | 0) 2.861 us | } | |
1324 | 0) ! 115.305 us | } | |
1325 | 0) ! 116.402 us | } | |
1326 | ||
1327 | + means that the function exceeded 10 usecs. | |
1328 | ! means that the function exceeded 100 usecs. | |
1329 | ||
1330 | ||
1331 | _ The task/pid field displays the thread cmdline and pid which executed the function. | |
1332 | It is default disabled. | |
1333 | ||
1334 | hide: echo nofuncgraph-proc > /debug/tracing/trace_options | |
1335 | show: echo funcgraph-proc > /debug/tracing/trace_options | |
1336 | ||
1337 | ie: | |
1338 | ||
1339 | # tracer: function_graph | |
1340 | # | |
1341 | # CPU TASK/PID DURATION FUNCTION CALLS | |
1342 | # | | | | | | | | | | |
1343 | 0) sh-4802 | | d_free() { | |
1344 | 0) sh-4802 | | call_rcu() { | |
1345 | 0) sh-4802 | | __call_rcu() { | |
1346 | 0) sh-4802 | 0.616 us | rcu_process_gp_end(); | |
1347 | 0) sh-4802 | 0.586 us | check_for_new_grace_period(); | |
1348 | 0) sh-4802 | 2.899 us | } | |
1349 | 0) sh-4802 | 4.040 us | } | |
1350 | 0) sh-4802 | 5.151 us | } | |
1351 | 0) sh-4802 | + 49.370 us | } | |
1352 | ||
1353 | ||
1354 | _ The absolute time field is an absolute timestamp given by the clock since | |
1355 | it started. A snapshot of this time is given on each entry/exit of functions | |
1356 | ||
1357 | hide: echo nofuncgraph-abstime > /debug/tracing/trace_options | |
1358 | show: echo funcgraph-abstime > /debug/tracing/trace_options | |
1359 | ||
1360 | ie: | |
1361 | ||
1362 | # | |
1363 | # TIME CPU DURATION FUNCTION CALLS | |
1364 | # | | | | | | | | | |
1365 | 360.774522 | 1) 0.541 us | } | |
1366 | 360.774522 | 1) 4.663 us | } | |
1367 | 360.774523 | 1) 0.541 us | __wake_up_bit(); | |
1368 | 360.774524 | 1) 6.796 us | } | |
1369 | 360.774524 | 1) 7.952 us | } | |
1370 | 360.774525 | 1) 9.063 us | } | |
1371 | 360.774525 | 1) 0.615 us | journal_mark_dirty(); | |
1372 | 360.774527 | 1) 0.578 us | __brelse(); | |
1373 | 360.774528 | 1) | reiserfs_prepare_for_journal() { | |
1374 | 360.774528 | 1) | unlock_buffer() { | |
1375 | 360.774529 | 1) | wake_up_bit() { | |
1376 | 360.774529 | 1) | bit_waitqueue() { | |
1377 | 360.774530 | 1) 0.594 us | __phys_addr(); | |
1378 | ||
1379 | ||
1380 | You can put some comments on specific functions by using ftrace_printk() | |
1381 | For example, if you want to put a comment inside the __might_sleep() function, | |
1382 | you just have to include <linux/ftrace.h> and call ftrace_printk() inside __might_sleep() | |
1383 | ||
1384 | ftrace_printk("I'm a comment!\n") | |
1385 | ||
1386 | will produce: | |
1387 | ||
1388 | 1) | __might_sleep() { | |
1389 | 1) | /* I'm a comment! */ | |
1390 | 1) 1.449 us | } | |
1391 | ||
1392 | ||
1393 | You might find other useful features for this tracer on the "dynamic ftrace" | |
1394 | section such as tracing only specific functions or tasks. | |
1395 | ||
eb6d42ea SR |
1396 | dynamic ftrace |
1397 | -------------- | |
1398 | ||
f2d9c740 | 1399 | If CONFIG_DYNAMIC_FTRACE is set, the system will run with |
eb6d42ea SR |
1400 | virtually no overhead when function tracing is disabled. The way |
1401 | this works is the mcount function call (placed at the start of | |
1402 | every kernel function, produced by the -pg switch in gcc), starts | |
f2d9c740 SR |
1403 | of pointing to a simple return. (Enabling FTRACE will include the |
1404 | -pg switch in the compiling of the kernel.) | |
eb6d42ea | 1405 | |
9b803c0f SR |
1406 | At compile time every C file object is run through the |
1407 | recordmcount.pl script (located in the scripts directory). This | |
1408 | script will process the C object using objdump to find all the | |
1409 | locations in the .text section that call mcount. (Note, only | |
1410 | the .text section is processed, since processing other sections | |
1411 | like .init.text may cause races due to those sections being freed). | |
1412 | ||
1413 | A new section called "__mcount_loc" is created that holds references | |
1414 | to all the mcount call sites in the .text section. This section is | |
1415 | compiled back into the original object. The final linker will add | |
1416 | all these references into a single table. | |
1417 | ||
1418 | On boot up, before SMP is initialized, the dynamic ftrace code | |
1419 | scans this table and updates all the locations into nops. It also | |
1420 | records the locations, which are added to the available_filter_functions | |
1421 | list. Modules are processed as they are loaded and before they are | |
1422 | executed. When a module is unloaded, it also removes its functions from | |
1423 | the ftrace function list. This is automatic in the module unload | |
1424 | code, and the module author does not need to worry about it. | |
1425 | ||
1426 | When tracing is enabled, kstop_machine is called to prevent races | |
1427 | with the CPUS executing code being modified (which can cause the | |
1428 | CPU to do undesireable things), and the nops are patched back | |
1429 | to calls. But this time, they do not call mcount (which is just | |
1430 | a function stub). They now call into the ftrace infrastructure. | |
eb6d42ea SR |
1431 | |
1432 | One special side-effect to the recording of the functions being | |
f2d9c740 SR |
1433 | traced is that we can now selectively choose which functions we |
1434 | wish to trace and which ones we want the mcount calls to remain as | |
eb6d42ea SR |
1435 | nops. |
1436 | ||
a41eebab | 1437 | Two files are used, one for enabling and one for disabling the tracing |
f2d9c740 | 1438 | of specified functions. They are: |
eb6d42ea SR |
1439 | |
1440 | set_ftrace_filter | |
1441 | ||
1442 | and | |
1443 | ||
1444 | set_ftrace_notrace | |
1445 | ||
a41eebab | 1446 | A list of available functions that you can add to these files is listed |
eb6d42ea SR |
1447 | in: |
1448 | ||
1449 | available_filter_functions | |
1450 | ||
1451 | # cat /debug/tracing/available_filter_functions | |
1452 | put_prev_task_idle | |
1453 | kmem_cache_create | |
1454 | pick_next_task_rt | |
1455 | get_online_cpus | |
1456 | pick_next_task_fair | |
1457 | mutex_lock | |
1458 | [...] | |
1459 | ||
f2d9c740 | 1460 | If I am only interested in sys_nanosleep and hrtimer_interrupt: |
eb6d42ea SR |
1461 | |
1462 | # echo sys_nanosleep hrtimer_interrupt \ | |
1463 | > /debug/tracing/set_ftrace_filter | |
1464 | # echo ftrace > /debug/tracing/current_tracer | |
1465 | # echo 1 > /debug/tracing/tracing_enabled | |
1466 | # usleep 1 | |
1467 | # echo 0 > /debug/tracing/tracing_enabled | |
1468 | # cat /debug/tracing/trace | |
1469 | # tracer: ftrace | |
1470 | # | |
1471 | # TASK-PID CPU# TIMESTAMP FUNCTION | |
1472 | # | | | | | | |
1473 | usleep-4134 [00] 1317.070017: hrtimer_interrupt <-smp_apic_timer_interrupt | |
1474 | usleep-4134 [00] 1317.070111: sys_nanosleep <-syscall_call | |
1475 | <idle>-0 [00] 1317.070115: hrtimer_interrupt <-smp_apic_timer_interrupt | |
1476 | ||
f2d9c740 | 1477 | To see which functions are being traced, you can cat the file: |
eb6d42ea SR |
1478 | |
1479 | # cat /debug/tracing/set_ftrace_filter | |
1480 | hrtimer_interrupt | |
1481 | sys_nanosleep | |
1482 | ||
1483 | ||
f2d9c740 | 1484 | Perhaps this is not enough. The filters also allow simple wild cards. |
a41eebab | 1485 | Only the following are currently available |
eb6d42ea | 1486 | |
a41eebab | 1487 | <match>* - will match functions that begin with <match> |
eb6d42ea SR |
1488 | *<match> - will match functions that end with <match> |
1489 | *<match>* - will match functions that have <match> in it | |
1490 | ||
f2d9c740 | 1491 | These are the only wild cards which are supported. |
eb6d42ea SR |
1492 | |
1493 | <match>*<match> will not work. | |
1494 | ||
c072c249 | 1495 | Note: It is better to use quotes to enclose the wild cards, otherwise |
1496 | the shell may expand the parameters into names of files in the local | |
1497 | directory. | |
1498 | ||
1499 | # echo 'hrtimer_*' > /debug/tracing/set_ftrace_filter | |
eb6d42ea SR |
1500 | |
1501 | Produces: | |
1502 | ||
1503 | # tracer: ftrace | |
1504 | # | |
1505 | # TASK-PID CPU# TIMESTAMP FUNCTION | |
1506 | # | | | | | | |
1507 | bash-4003 [00] 1480.611794: hrtimer_init <-copy_process | |
1508 | bash-4003 [00] 1480.611941: hrtimer_start <-hrtick_set | |
1509 | bash-4003 [00] 1480.611956: hrtimer_cancel <-hrtick_clear | |
1510 | bash-4003 [00] 1480.611956: hrtimer_try_to_cancel <-hrtimer_cancel | |
1511 | <idle>-0 [00] 1480.612019: hrtimer_get_next_event <-get_next_timer_interrupt | |
1512 | <idle>-0 [00] 1480.612025: hrtimer_get_next_event <-get_next_timer_interrupt | |
1513 | <idle>-0 [00] 1480.612032: hrtimer_get_next_event <-get_next_timer_interrupt | |
1514 | <idle>-0 [00] 1480.612037: hrtimer_get_next_event <-get_next_timer_interrupt | |
1515 | <idle>-0 [00] 1480.612382: hrtimer_get_next_event <-get_next_timer_interrupt | |
1516 | ||
1517 | ||
1518 | Notice that we lost the sys_nanosleep. | |
1519 | ||
1520 | # cat /debug/tracing/set_ftrace_filter | |
1521 | hrtimer_run_queues | |
1522 | hrtimer_run_pending | |
1523 | hrtimer_init | |
1524 | hrtimer_cancel | |
1525 | hrtimer_try_to_cancel | |
1526 | hrtimer_forward | |
1527 | hrtimer_start | |
1528 | hrtimer_reprogram | |
1529 | hrtimer_force_reprogram | |
1530 | hrtimer_get_next_event | |
1531 | hrtimer_interrupt | |
1532 | hrtimer_nanosleep | |
1533 | hrtimer_wakeup | |
1534 | hrtimer_get_remaining | |
1535 | hrtimer_get_res | |
1536 | hrtimer_init_sleeper | |
1537 | ||
1538 | ||
1539 | This is because the '>' and '>>' act just like they do in bash. | |
1540 | To rewrite the filters, use '>' | |
1541 | To append to the filters, use '>>' | |
1542 | ||
a41eebab | 1543 | To clear out a filter so that all functions will be recorded again: |
eb6d42ea SR |
1544 | |
1545 | # echo > /debug/tracing/set_ftrace_filter | |
1546 | # cat /debug/tracing/set_ftrace_filter | |
1547 | # | |
1548 | ||
1549 | Again, now we want to append. | |
1550 | ||
1551 | # echo sys_nanosleep > /debug/tracing/set_ftrace_filter | |
1552 | # cat /debug/tracing/set_ftrace_filter | |
1553 | sys_nanosleep | |
c072c249 | 1554 | # echo 'hrtimer_*' >> /debug/tracing/set_ftrace_filter |
eb6d42ea SR |
1555 | # cat /debug/tracing/set_ftrace_filter |
1556 | hrtimer_run_queues | |
1557 | hrtimer_run_pending | |
1558 | hrtimer_init | |
1559 | hrtimer_cancel | |
1560 | hrtimer_try_to_cancel | |
1561 | hrtimer_forward | |
1562 | hrtimer_start | |
1563 | hrtimer_reprogram | |
1564 | hrtimer_force_reprogram | |
1565 | hrtimer_get_next_event | |
1566 | hrtimer_interrupt | |
1567 | sys_nanosleep | |
1568 | hrtimer_nanosleep | |
1569 | hrtimer_wakeup | |
1570 | hrtimer_get_remaining | |
1571 | hrtimer_get_res | |
1572 | hrtimer_init_sleeper | |
1573 | ||
1574 | ||
1575 | The set_ftrace_notrace prevents those functions from being traced. | |
1576 | ||
1577 | # echo '*preempt*' '*lock*' > /debug/tracing/set_ftrace_notrace | |
1578 | ||
1579 | Produces: | |
1580 | ||
1581 | # tracer: ftrace | |
1582 | # | |
1583 | # TASK-PID CPU# TIMESTAMP FUNCTION | |
1584 | # | | | | | | |
1585 | bash-4043 [01] 115.281644: finish_task_switch <-schedule | |
1586 | bash-4043 [01] 115.281645: hrtick_set <-schedule | |
1587 | bash-4043 [01] 115.281645: hrtick_clear <-hrtick_set | |
1588 | bash-4043 [01] 115.281646: wait_for_completion <-__stop_machine_run | |
1589 | bash-4043 [01] 115.281647: wait_for_common <-wait_for_completion | |
1590 | bash-4043 [01] 115.281647: kthread_stop <-stop_machine_run | |
1591 | bash-4043 [01] 115.281648: init_waitqueue_head <-kthread_stop | |
1592 | bash-4043 [01] 115.281648: wake_up_process <-kthread_stop | |
1593 | bash-4043 [01] 115.281649: try_to_wake_up <-wake_up_process | |
1594 | ||
1595 | We can see that there's no more lock or preempt tracing. | |
1596 | ||
985ec20a FW |
1597 | |
1598 | * Dynamic ftrace with the function graph tracer * | |
1599 | ||
1600 | ||
1601 | Although what has been explained above concerns both the function tracer and | |
1602 | the function_graph_tracer, the following concerns only the latter. | |
1603 | ||
1604 | If you want to trace only one function and all of its childs, you just have | |
1605 | to echo its name on set_graph_function: | |
1606 | ||
1607 | echo __do_fault > set_graph_function | |
1608 | ||
1609 | will produce the following: | |
1610 | ||
1611 | 0) | __do_fault() { | |
1612 | 0) | filemap_fault() { | |
1613 | 0) | find_lock_page() { | |
1614 | 0) 0.804 us | find_get_page(); | |
1615 | 0) | __might_sleep() { | |
1616 | 0) 1.329 us | } | |
1617 | 0) 3.904 us | } | |
1618 | 0) 4.979 us | } | |
1619 | 0) 0.653 us | _spin_lock(); | |
1620 | 0) 0.578 us | page_add_file_rmap(); | |
1621 | 0) 0.525 us | native_set_pte_at(); | |
1622 | 0) 0.585 us | _spin_unlock(); | |
1623 | 0) | unlock_page() { | |
1624 | 0) 0.541 us | page_waitqueue(); | |
1625 | 0) 0.639 us | __wake_up_bit(); | |
1626 | 0) 2.786 us | } | |
1627 | 0) + 14.237 us | } | |
1628 | 0) | __do_fault() { | |
1629 | 0) | filemap_fault() { | |
1630 | 0) | find_lock_page() { | |
1631 | 0) 0.698 us | find_get_page(); | |
1632 | 0) | __might_sleep() { | |
1633 | 0) 1.412 us | } | |
1634 | 0) 3.950 us | } | |
1635 | 0) 5.098 us | } | |
1636 | 0) 0.631 us | _spin_lock(); | |
1637 | 0) 0.571 us | page_add_file_rmap(); | |
1638 | 0) 0.526 us | native_set_pte_at(); | |
1639 | 0) 0.586 us | _spin_unlock(); | |
1640 | 0) | unlock_page() { | |
1641 | 0) 0.533 us | page_waitqueue(); | |
1642 | 0) 0.638 us | __wake_up_bit(); | |
1643 | 0) 2.793 us | } | |
1644 | 0) + 14.012 us | } | |
1645 | ||
1646 | You can also select several functions: | |
1647 | ||
1648 | echo sys_open > set_graph_function | |
1649 | echo sys_close >> set_graph_function | |
1650 | ||
1651 | Now if you want to go back to trace all functions | |
1652 | ||
1653 | echo > set_graph_function | |
1654 | ||
1655 | ||
eb6d42ea SR |
1656 | trace_pipe |
1657 | ---------- | |
1658 | ||
f2d9c740 SR |
1659 | The trace_pipe outputs the same content as the trace file, but the effect |
1660 | on the tracing is different. Every read from trace_pipe is consumed. | |
eb6d42ea SR |
1661 | This means that subsequent reads will be different. The trace |
1662 | is live. | |
1663 | ||
9b803c0f | 1664 | # echo function > /debug/tracing/current_tracer |
eb6d42ea SR |
1665 | # cat /debug/tracing/trace_pipe > /tmp/trace.out & |
1666 | [1] 4153 | |
1667 | # echo 1 > /debug/tracing/tracing_enabled | |
1668 | # usleep 1 | |
1669 | # echo 0 > /debug/tracing/tracing_enabled | |
1670 | # cat /debug/tracing/trace | |
9b803c0f | 1671 | # tracer: function |
eb6d42ea SR |
1672 | # |
1673 | # TASK-PID CPU# TIMESTAMP FUNCTION | |
1674 | # | | | | | | |
1675 | ||
1676 | # | |
1677 | # cat /tmp/trace.out | |
1678 | bash-4043 [00] 41.267106: finish_task_switch <-schedule | |
1679 | bash-4043 [00] 41.267106: hrtick_set <-schedule | |
1680 | bash-4043 [00] 41.267107: hrtick_clear <-hrtick_set | |
1681 | bash-4043 [00] 41.267108: wait_for_completion <-__stop_machine_run | |
1682 | bash-4043 [00] 41.267108: wait_for_common <-wait_for_completion | |
1683 | bash-4043 [00] 41.267109: kthread_stop <-stop_machine_run | |
1684 | bash-4043 [00] 41.267109: init_waitqueue_head <-kthread_stop | |
1685 | bash-4043 [00] 41.267110: wake_up_process <-kthread_stop | |
1686 | bash-4043 [00] 41.267110: try_to_wake_up <-wake_up_process | |
1687 | bash-4043 [00] 41.267111: select_task_rq_rt <-try_to_wake_up | |
1688 | ||
1689 | ||
f2d9c740 | 1690 | Note, reading the trace_pipe file will block until more input is added. |
eb6d42ea | 1691 | By changing the tracer, trace_pipe will issue an EOF. We needed |
9b803c0f | 1692 | to set the function tracer _before_ we "cat" the trace_pipe file. |
eb6d42ea SR |
1693 | |
1694 | ||
1695 | trace entries | |
1696 | ------------- | |
1697 | ||
1698 | Having too much or not enough data can be troublesome in diagnosing | |
a94c80e7 | 1699 | an issue in the kernel. The file buffer_size_kb is used to modify |
a41eebab | 1700 | the size of the internal trace buffers. The number listed |
eb6d42ea SR |
1701 | is the number of entries that can be recorded per CPU. To know |
1702 | the full size, multiply the number of possible CPUS with the | |
1703 | number of entries. | |
1704 | ||
a94c80e7 | 1705 | # cat /debug/tracing/buffer_size_kb |
1696b2b0 | 1706 | 1408 (units kilobytes) |
eb6d42ea | 1707 | |
a41eebab | 1708 | Note, to modify this, you must have tracing completely disabled. To do that, |
9b803c0f SR |
1709 | echo "nop" into the current_tracer. If the current_tracer is not set |
1710 | to "nop", an EINVAL error will be returned. | |
eb6d42ea | 1711 | |
9b803c0f | 1712 | # echo nop > /debug/tracing/current_tracer |
1696b2b0 | 1713 | # echo 10000 > /debug/tracing/buffer_size_kb |
a94c80e7 | 1714 | # cat /debug/tracing/buffer_size_kb |
1696b2b0 | 1715 | 10000 (units kilobytes) |
eb6d42ea | 1716 | |
f2d9c740 SR |
1717 | The number of pages which will be allocated is limited to a percentage |
1718 | of available memory. Allocating too much will produce an error. | |
eb6d42ea | 1719 | |
a94c80e7 | 1720 | # echo 1000000000000 > /debug/tracing/buffer_size_kb |
eb6d42ea | 1721 | -bash: echo: write error: Cannot allocate memory |
a94c80e7 | 1722 | # cat /debug/tracing/buffer_size_kb |
eb6d42ea SR |
1723 | 85 |
1724 |