perf-sched man page

perf-sched — Tool to trace/measure scheduler properties (latencies)


perf sched {record|latency|map|replay|script|timehist}


There are several variants of perf sched:

'perf sched record <command>' to record the scheduling events
of an arbitrary workload.
'perf sched latency' to report the per task scheduling latencies
and other scheduling properties of the workload.
'perf sched script' to see a detailed trace of the workload that
 was recorded (aliased to 'perf script' for now).
'perf sched replay' to simulate the workload that was recorded
via perf sched record. (this is done by starting up mockup threads
that mimic the workload based on the events in the trace. These
threads can then replay the timings (CPU runtime and sleep patterns)
of the workload as it occurred when it was recorded - and can repeat
it a number of times, measuring its performance.)
'perf sched map' to print a textual context-switching outline of
workload captured via perf sched record.  Columns stand for
individual CPUs, and the two-letter shortcuts stand for tasks that
are running on a CPU. A '*' denotes the CPU that had the event, and
a dot signals an idle CPU.
'perf sched timehist' provides an analysis of scheduling events.
Example usage:
    perf sched record -- sleep 1
    perf sched timehist
By default it shows the individual schedule events, including the wait
time (time between sched-out and next sched-in events for the task), the
task scheduling delay (time between wakeup and actually running) and run
time for the task:
            time    cpu  task name             wait time  sch delay   run time
                         [tid/pid]                (msec)     (msec)     (msec)
  -------------- ------  --------------------  ---------  ---------  ---------
    79371.874569 [0011]  gcc[31949]                0.014      0.000      1.148
    79371.874591 [0010]  gcc[31951]                0.000      0.000      0.024
    79371.874603 [0010]  migration/10[59]          3.350      0.004      0.011
    79371.874604 [0011]  <idle>                    1.148      0.000      0.035
    79371.874723 [0005]  <idle>                    0.016      0.000      1.383
    79371.874746 [0005]  gcc[31949]                0.153      0.078      0.022
Times are in msec.usec.


-i, --input=<file>

Input file name. (default: unless stdin is a fifo)

-v, --verbose

Be more verbose. (show symbol address, etc)

-D, --dump-raw-trace=

Display verbose dump of the sched data.

Options for Perf Sched Map


Show only CPUs with activity. Helps visualizing on high core count systems.


Show just entries with activities for the given CPUs.


Highlight the given cpus.


Highlight the given pids.

Options for Perf Sched Timehist

-k, --vmlinux=<file>

vmlinux pathname


kallsyms pathname

-g, --no-call-graph

Do not display call chains if present.


Maximum number of functions to display in backtrace, default 5.

-s, --summary

Show only a summary of scheduling by thread with min, max, and average run times (in sec) and relative stddev.

-S, --with-summary

Show all scheduling events followed by a summary by thread with min, max, and average run times (in sec) and relative stddev.


Look for files with symbols relative to this directory.

-V, --cpu-visual

Show visual aid for sched switches by CPU: i marks idle time, s are scheduler events.

-w, --wakeups

Show wakeup events.

-M, --migrations

Show migration events.

-I, --idle-hist

Show idle-related events only.


Only analyze samples within given time window: <start>,<stop>. Times have the format seconds.microseconds. If start is not given (i.e., time string is ,x.y) then analysis starts at the beginning of the file. If stop time is not given (i.e, time string is x.y,) then analysis goes to end of file.

See Also



02/20/2017 perf Manual