On Fri, 4 Jul 2025, Ahmed S. Darwish wrote: > The number and breadth of cyclictest's options is huge, and just > exploring them in sequence can get the manpage reader lost. > > Put the cyclictest's sleep-mechanism related options: > > -c, --clock=CLOCK > -x, --posix_timers > -s, --system > -r, --relative > -R, --resolution > > into their own group. Adjust the Synopsis accordingly as well. > > Further groupings will be added next. > > Signed-off-by: Ahmed S. Darwish <darwi@xxxxxxxxxxxxx> > --- > src/cyclictest/cyclictest.8 | 66 +++++++++++++++++++------------------ > 1 file changed, 34 insertions(+), 32 deletions(-) > > diff --git a/src/cyclictest/cyclictest.8 b/src/cyclictest/cyclictest.8 > index 0bc2fc1..eb7d713 100644 > --- a/src/cyclictest/cyclictest.8 > +++ b/src/cyclictest/cyclictest.8 > @@ -14,14 +14,14 @@ cyclictest \- High resolution test program > .IR pm\-c\-state ] > .RB [ \-\-deepest\-idle\-state\~\c > .IR idle-state-num ] > +.RB [ \-c\~\c > +.IR clock\-type ] > .RB [ \-a\~\c > .IR proc\-set ] > .RB [ \-A\~\c > .IR alignment\-usec ] > .RB [ \-b\~\c > .IR break\-usec ] > -.RB [ \-c\~\c > -.IR clock\-type ] > .RB [ \-d\~\c > .IR distance\-usec ] > .RB [ \-D\~\c > @@ -95,6 +95,38 @@ cpus. > Save battery when running cyclictest. This will give you poorer realtime > results, but will not drain your battery so quickly. > . > +.SS "Sleep-mechanism clock options" > +. > +.TP > +.B \-c, \-\-clock=CLOCK > +select clock > +.br > +0 = CLOCK_MONOTONIC (default) > +.br > +1 = CLOCK_REALTIME > +. > +.TP > +.B \-x, \-\-posix_timers > +Use POSIX timers instead of clock_nanosleep. > +. > +.TP > +.B \-s, \-\-system > +Use sys_nanosleep and sys_setitimer instead of posix timers. Note, that \-s > +can only be used with one thread because itimers are per process and not > +per thread. \-s uses the nanosleep syscall and is not restricted to one > +thread. > +. > +.TP > +.B \-r, \-\-relative > +Use relative timers instead of absolute. The default behaviour of the tests > +is to use absolute timers. This option is there for completeness and should > +not be used for reproducible tests. > +. > +.TP > +.B \-R, \-\-resolution > +Check clock resolution, calling clock_gettime() many times. List of > +lock_gettime() values will be reported with -X > +. > .SS "Other options" > . > .TP > @@ -121,14 +153,6 @@ Align thread wakeups to a specific offset in microseconds > Send break trace command when latency > USEC > . > .TP > -.B \-c, \-\-clock=CLOCK > -select clock > -.br > -0 = CLOCK_MONOTONIC (default) > -.br > -1 = CLOCK_REALTIME > -. > -.TP > .B \-d, \-\-distance=DIST > Distance of thread intervals in us, default = 500 > . > @@ -217,28 +241,10 @@ Print a summary only on exit. Useful for automated tests, where only the > summary output needs to be captured. > . > .TP > -.B \-r, \-\-relative > -Use relative timers instead of absolute. The default behaviour of the tests > -is to use absolute timers. This option is there for completeness and should > -not be used for reproducible tests. > -. > -.TP > -.B \-R, \-\-resolution > -Check clock resolution, calling clock_gettime() many times. List of > -lock_gettime() values will be reported with -X > -. > -.TP > .B \-\-secaligned [USEC] > align thread wakeups to the next full second and apply the optional offset. > . > .TP > -.B \-s, \-\-system > -Use sys_nanosleep and sys_setitimer instead of posix timers. Note, that \-s > -can only be used with one thread because itimers are per process and not > -per thread. \-s uses the nanosleep syscall and is not restricted to one > -thread. > -. > -.TP > .B \\-S, \-\-smp > Set options for standard testing on SMP systems. Equivalent to using the > options: "\-t \-a" as well keeping any specified priority equal across all > @@ -283,10 +289,6 @@ the count, and v is the latency value in microseconds. > .B \-\-dbg_cyclictest > Print info userful for debugging cyclictest > . > -.TP > -.B \-x, \-\-posix_timers > -Use POSIX timers instead of clock_nanosleep. > -. > .SH "See also" > .BR numa (3), > .BR numactl (8), > -- > 2.49.0 > > > Signed-off-by: John Kacur <jkacur@xxxxxxxxxx>
