[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <Z-4b-sVycH2LM8y6@google.com>
Date: Wed, 2 Apr 2025 22:26:18 -0700
From: Namhyung Kim <namhyung@...nel.org>
To: Chun-Tse Shao <ctshao@...gle.com>
Cc: linux-kernel@...r.kernel.org, Ian Rogers <irogers@...gle.com>,
Thomas Richter <tmricht@...ux.ibm.com>, peterz@...radead.org,
mingo@...hat.com, acme@...nel.org, mark.rutland@....com,
alexander.shishkin@...ux.intel.com, jolsa@...nel.org,
adrian.hunter@...el.com, kan.liang@...ux.intel.com,
james.clark@...aro.org, dapeng1.mi@...ux.intel.com,
vmolnaro@...hat.com, linux-perf-users@...r.kernel.org
Subject: Re: [PATCH v1] perf test: Allow tolerance for leader sampling test
Hello,
On Tue, Apr 01, 2025 at 10:22:39AM -0700, Chun-Tse Shao wrote:
> There is a known issue that the leader sampling is inconsistent, since
> throttle only affect leader, not the slave. The detail is in [1]. To
> maintain test coverage, this patch sets a tolerance rate of 80% to
> accommodate the throttled samples and prevent test failures due to
> throttling.
>
> [1] lore.kernel.org/20250328182752.769662-1-ctshao@...gle.com
>
> Signed-off-by: Chun-Tse Shao <ctshao@...gle.com>
> Suggested-by: Ian Rogers <irogers@...gle.com>
> Suggested-by: Thomas Richter <tmricht@...ux.ibm.com>
> Tested-by: Thomas Richter <tmricht@...ux.ibm.com>
> ---
> tools/perf/tests/shell/record.sh | 25 +++++++++++++++++++------
> 1 file changed, 19 insertions(+), 6 deletions(-)
>
> diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
> index ba8d873d3ca7..1bbe16fb3420 100755
> --- a/tools/perf/tests/shell/record.sh
> +++ b/tools/perf/tests/shell/record.sh
> @@ -238,22 +238,35 @@ test_leader_sampling() {
> err=1
> return
> fi
> + perf script -i "${perfdata}" | grep brstack > $script_output
> + # Check if the two instruction counts are equal in each record.
> + # However, the throttling code doesn't consider event grouping. During throttling, only the
> + # leader is stopped, causing the slave's counts significantly higher. To temporarily solve this,
> + # let's set the tolerance rate to 80%.
> + # TODO: Revert the code for tolerance once the throttling mechanism is fixed.
> index=0
> - perf script -i "${perfdata}" > $script_output
> + valid_counts=0
> + invalid_counts=0
> + tolerance_rate=0.8
> while IFS= read -r line
> do
> - # Check if the two instruction counts are equal in each record
> cycles=$(echo $line | awk '{for(i=1;i<=NF;i++) if($i=="cycles:") print $(i-1)}')
> if [ $(($index%2)) -ne 0 ] && [ ${cycles}x != ${prev_cycles}x ]
> then
> - echo "Leader sampling [Failed inconsistent cycles count]"
> - err=1
> - return
> + invalid_counts=$(($invalid_counts+1))
> + else
> + valid_counts=$(($valid_counts+1))
> fi
> index=$(($index+1))
> prev_cycles=$cycles
> done < $script_output
> - echo "Basic leader sampling test [Success]"
> + if [[ "$(echo "scale=2; $invalid_counts/($invalid_counts+$valid_counts)" | bc)" > 1-$tolerance_rate ]]
Shouldn't it be double parenthesis to use numeric comparisons?
Also I'm not sure if bash supports floating-point arithmetic.
It'd be better to compare the value in bc and use its return value.
Thanks,
Namhyung
> + then
> + echo "Leader sampling [Failed inconsistent cycles count]"
> + err=1
> + else
> + echo "Basic leader sampling test [Success]"
> + fi
> }
>
> test_topdown_leader_sampling() {
> --
> 2.49.0.472.ge94155a9ec-goog
>
Powered by blists - more mailing lists