]> www.infradead.org Git - users/jedix/linux-maple.git/commit
selftests/resctrl: Keep results from first test run
authorReinette Chatre <reinette.chatre@intel.com>
Thu, 24 Oct 2024 21:18:51 +0000 (14:18 -0700)
committerShuah Khan <skhan@linuxfoundation.org>
Tue, 5 Nov 2024 00:02:03 +0000 (17:02 -0700)
commit295b898426d8fb5b79672d1dae358ca8070f2196
tree18920a04a8f77a3c9ed2032962351678fff4043a
parent501cfdba0a400e70ea220a4b02f1805e0e9de6a1
selftests/resctrl: Keep results from first test run

The resctrl selftests drop the results from every first test run
to avoid (per comment) "inaccurate due to monitoring setup transition
phase" data. Previously inaccurate data resulted from workloads needing
some time to "settle" and also the measurements themselves to
account for earlier measurements to measure across needed timeframe.

commit da50de0a92f3 ("selftests/resctrl: Calculate resctrl FS derived mem
bw over sleep(1) only")

ensured that measurements accurately measure just the time frame of
interest. The default "fill_buf" benchmark since separated the buffer
prepare phase from the benchmark run phase reducing the need for the
tests themselves to accommodate the benchmark's "settle" time.

With these enhancements there are no remaining portions needing
to "settle" and the first test run can contribute to measurements.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
tools/testing/selftests/resctrl/cmt_test.c
tools/testing/selftests/resctrl/mba_test.c
tools/testing/selftests/resctrl/mbm_test.c