Lines Matching refs:trace
89 This sets or displays whether writing to the trace
95 trace:
97 This file holds the output of the trace in a human
102 The output is the same as the "trace" file but this
105 retrieved. Unlike the "trace" file, this file is a
110 "trace" file is static, and if the tracer is not
124 trace option (also in trace_options). Options may also be set
132 This time is saved in this file. The max trace
133 will also be stored, and displayed by "trace".
134 A new max trace will only be recorded if the
140 Some latency tracers will record a trace whenever the
148 buffer holds. By default, the trace buffers are the same size
151 trace buffers are allocated in pages (blocks of memory
161 This displays the total combined size of all the trace buffers.
178 This is a mask that lets the user only trace
191 will limit the trace to only those functions.
205 Have the function tracer only trace a single thread.
216 has processed and can trace. These are the function
225 Not only does the trace infrastructure use ftrace function
226 trace utility, but other subsystems might too. This file
259 Enable dynamic trace points. See kprobetrace.txt.
263 Dynamic trace points stats. See kprobetrace.txt.
268 it will trace into a function. Setting this to a value of
284 Only the pid of the task is recorded in a trace event unless
293 take a snapshot of the current running trace.
304 This displays the stack back trace of the largest stack
394 This is a way to make multiple trace buffers where different
400 This is the trace event directory. It holds event tracepoints
411 This is a directory that contains the trace per_cpu information.
422 per_cpu/cpu0/trace:
424 This is similar to the "trace" file, but it will only display
489 Function call tracer to trace all kernel functions.
503 the trace with the longest max latency.
505 it replaces the old trace. It is best to view this
506 trace with the latency-format option enabled.
534 This is the "trace nothing" tracer. To remove all
549 Here is an example of the output format of the file "trace"
576 the trace. In this case the tracer is "function". Then it shows the
589 Latency trace format
593 tracers is set, the trace file gives somewhat more information to see
594 why a latency happened. Here is a typical trace.
598 # irqsoff latency trace v1.1.5 on 3.8.0-test+
619 ps-6143 2d..1 306us : <stack trace>
633 for which interrupts were disabled. It gives the trace version (which
636 of trace entries displayed and the total number (both are four: #4/4).
649 The next lines after the header are the trace itself. The header
652 cmd: The name of the process in the trace.
679 time: When the latency-format option is enabled, the trace file
681 trace. This differs from the output when latency-format
687 current trace and the next trace.
694 The rest is the same as the 'trace' file.
696 Note, the latency tracers will usually end with a back trace
703 what gets printed in the trace output, or manipulate the tracers.
732 function-trace
769 verbose - This deals with the trace file when the
786 stacktrace - This is one of the options that changes the trace
787 itself. When a trace is recorded, so is the stack
789 trace sites.
799 the trace is reported, it shows the oldest events first,
812 userstacktrace - This option changes the trace. It records a
823 trace,trace_pipe. Example:
836 latency-format - This option changes the trace. When
837 it is enabled, the trace displays
840 trace format".
854 in the sched_switch trace point to fill comm cache
860 overwrite - This controls what happens when the trace buffer is
870 When disabled, the trace looks like:
888 function-trace - The latency tracers will enable function tracing
890 it is disabled, the latency tracers do not trace
910 the trace leading up to that latency point so that every time a
911 new maximum is reached, the old saved trace is discarded and the
912 new trace is saved.
917 # echo 0 > options/function-trace
924 # cat trace
927 # irqsoff latency trace v1.1.5 on 3.8.0-test+
948 <idle>-0 0dNs3 25us : <stack trace>
971 Note the above example had function-trace not set. If we set
972 function-trace, we get a much larger output:
974 with echo 1 > options/function-trace
978 # irqsoff latency trace v1.1.5 on 3.8.0-test+
1015 bash-2042 3d..1 120us : <stack trace>
1047 trace has provided some very helpful debugging information.
1063 # echo 0 > options/function-trace
1070 # cat trace
1073 # preemptoff latency trace v1.1.5 on 3.8.0-test+
1094 sshd-1991 1d..1 52us : <stack trace>
1110 # preemptoff latency trace v1.1.5 on 3.8.0-test+
1162 bash-1994 1.N.1 104us : <stack trace>
1172 The above is an example of the preemptoff trace with
1173 function-trace set. Here we see that interrupts were not disabled
1205 But neither will trace the time that interrupts and/or
1210 Again, using this trace is much like the irqsoff and preemptoff
1213 # echo 0 > options/function-trace
1220 # cat trace
1223 # preemptirqsoff latency trace v1.1.5 on 3.8.0-test+
1244 ls-2230 3...1 111us : <stack trace>
1272 Here is a trace with function-trace set:
1276 # preemptirqsoff latency trace v1.1.5 on 3.8.0-test+
1355 ls-2269 3d... 186us : <stack trace>
1365 This is an interesting trace. It started with kworker running and
1383 # echo 0 > options/function-trace
1389 # cat trace
1392 # wakeup latency trace v1.1.5 on 3.8.0-test+
1419 trace is to concentrate only on Real-Time tasks.
1449 # echo 0 > options/function-trace
1455 # cat trace
1460 # wakeup_rt latency trace v1.1.5 on 3.8.0-test+
1482 to perform the task switch. Note, since the trace point in the schedule
1492 Note, that the trace data shows the internal priority (99 - rtprio).
1501 Doing the same with chrt -r 5 and function-trace set.
1503 echo 1 > options/function-trace
1507 # wakeup_rt latency trace v1.1.5 on 3.8.0-test+
1608 This isn't that big of a trace, even with function tracing enabled,
1609 so I included the entire trace.
1622 # echo 0 > options/function-trace
1629 # cat trace
1632 # wakeup_rt latency trace v1.1.5 on 3.8.0-test+
1674 # cat trace
1699 Sometimes using echo to stop the trace is not sufficient because
1723 By writing into set_ftrace_pid you can trace a
1732 # cat trace | head
1744 # cat trace |head
1756 If you want to trace a function when executing, you could use
1918 enabled. It is sometimes better to only trace one cpu (see
2017 trace buffer.
2020 enabled for functions whose start is in the trace buffer,
2113 wish to trace and which ones we want the mcount calls to remain
2146 # cat trace
2309 If you want to trace only one function and all of its children,
2314 will produce the following "expanded" trace of the __do_fault()
2357 Now if you want to go back to trace all functions you can clear
2449 These commands can enable or disable a trace event. Note, because
2451 are registered, the trace point is activated, but disabled in
2475 something, and want to dump the trace when a certain function
2488 The trace_pipe outputs the same content as the trace file, but
2491 different. The trace is live.
2494 # cat trace_pipe > /tmp/trace.out &
2499 # cat trace
2513 # cat /tmp/trace.out
2528 trace entries
2533 used to modify the size of the internal trace buffers. The
2587 Snapshot preserves a current trace buffer at a particular point
2601 "trace" (described above in the section "The File
2636 # cat trace
2674 set_event snapshot trace trace_clock trace_marker trace_options
2749 # cat instances/zoot/trace
2773 You can see that the trace of the top most trace buffer shows only
2783 Note, if a process has a trace file open in one of the instance
2787 Stack trace
2806 You can also enable it from the kernel command line to trace
2846 kernel/trace/*.c files.