| Age | Commit message (Collapse) | Author |
|---|
|
Shell tests run perf, that maps ring buffers, so they take a turn using
the per user budget in kernel.perf_event_mlock_kb by default; the ones
that don't map them, like the ones running just 'perf stat', say
" (no_mlock)" in their description line and thus keep running in parallel
with the ones taking turns.
The 'perf sched stats' tests are among them, they synthesize the samples
from /proc/schedstat without mapping a ring buffer, and the tests already
marked " (exclusive)" don't need it, exclusive implies every other
requisite and keeps them running alone.
Reviewed-by: Ian Rogers <irogers@google.com>
Tested-by: Ian Rogers <irogers@google.com>
Assisted-by: LLM
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
In test_stat_cpi_python.sh, 'perf test -w noploop &' defaults to a
1-second duration and can exit under heavy parallel load before
'perf stat -p' and 'perf script stat-cpi' finish starting up. In
addition, the fixed 'sleep 0.5' before sending SIGINT can fire before
Python finishes importing the perf module, opening the live evlist, and
flushing the first interval.
In stat-cpi.py, register SIGINT and SIGTERM handlers before calling
_open_live_evlist() and pass flush=True when printing live output so
redirected stdout is flushed immediately after each interval.
In test_stat_cpi_python.sh, run 'perf test -w noploop 60 &' so the
target workload stays alive until killed, and poll the output file for
'cpi' (up to 5 seconds) before sending SIGINT.
Fixes: 4425182d426b ("perf python: Port stat-cpi to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Refactor 'perf script' to launch standalone scripts directly via fork()
and execvp() and remove the legacy embedded Perl and Python scripting
engines:
- Remove the embedded Perl scripting engine
(util/scripting-engines/trace-event-perl.c), Perl scripts, bin
wrappers, and Trace-Util library
(scripts/perl/Perf-Trace-Util/), and script_perl.sh test.
- Remove libperl feature checks from Makefile.config, Makefile.perf,
builtin-check.c, and Documentation/perf-check.txt.
- Remove -g / --gen-script option and scripting_ops dispatch table from
builtin-script.c and trace-event-scripting.c.
- Hide the legacy -s / --script option and update script discovery in
find_script() and list_available_scripts() to prioritize the system
'python' directory over bare filenames in the current directory.
- Update the Python script shell tests (test_arm_coresight_disasm.sh,
test_task_analyzer.sh, and test_*_python.sh) to invoke scripts via
'perf script <script>' rather than running the Python interpreter
directly on the script file path.
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
Port stat-cpi.py from the legacy embedded scripting framework to a
standalone Python script in tools/perf/python/ to calculate Cycles Per
Instruction (CPI) per interval per CPU or thread.
Improvements compared to the legacy script:
- Support both perf.data file mode (via perf.session stat callbacks)
and live counter collection mode (using perf.parse_events,
evlist.open, and evsel.read across intervals), with automatic fallback
to user-space (:u) and self-process monitoring when perf_event_paranoid
restricts system-wide events (EACCES).
- Compute per-interval counter deltas (val, ena, run) keyed by raw event
name so cumulative PERF_RECORD_STAT snapshots and hybrid PMU events
(e.g. cpu_core/cycles/, cpu_atom/cycles/) are accumulated accurately,
and scale counts by time_enabled / time_running when multiplexed.
- Replace hard-coded CPU ([0, 1]) and thread ([0]) arrays with dynamic
CPU and thread discovery so arbitrary system topologies work
automatically.
- Add CLI option handling (-i, -I, -p) via argparse and type annotations
passing mypy and pylint.
Add a shell test (test_stat_cpi_python.sh) to verify the standalone
script.
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
