[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20201130115925.GA20959@kernel.org>
Date: Mon, 30 Nov 2020 08:59:25 -0300
From: Arnaldo Carvalho de Melo <acme@...nel.org>
To: Namhyung Kim <namhyung@...nel.org>
Cc: Jiri Olsa <jolsa@...hat.com>, Ingo Molnar <mingo@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
LKML <linux-kernel@...r.kernel.org>,
Stephane Eranian <eranian@...gle.com>,
Ian Rogers <irogers@...gle.com>
Subject: Re: [PATCH v2 2/2] perf test: Add shadow stat test
Em Fri, Nov 27, 2020 at 01:14:04PM +0900, Namhyung Kim escreveu:
> It calculates IPC from the cycles and instruction counts and compares
> it with the shadow stat for both global aggregation (default) and no
> aggregation mode.
>
> $ perf stat -a -A -e cycles,instructions sleep 1
>
> Performance counter stats for 'system wide':
>
> CPU0 39,580,880 cycles
> CPU1 45,426,945 cycles
> CPU2 31,151,685 cycles
> CPU3 55,167,421 cycles
> CPU0 17,073,564 instructions # 0.43 insn per cycle
> CPU1 34,955,764 instructions # 0.77 insn per cycle
> CPU2 15,688,459 instructions # 0.50 insn per cycle
> CPU3 34,699,217 instructions # 0.63 insn per cycle
>
> 1.003275495 seconds time elapsed
>
> In this example, the 'insn per cycle' should be matched to the number
> for each cpu. For CPU2, 0.50 = 15,688,459 / 31,151,685 .
Merged torvalds/master into perf/core and applied this patch,
Thanks,
- Arnaldo
> Signed-off-by: Namhyung Kim <namhyung@...nel.org>
> ---
> tools/perf/tests/shell/stat+shadow_stat.sh | 80 ++++++++++++++++++++++
> 1 file changed, 80 insertions(+)
> create mode 100755 tools/perf/tests/shell/stat+shadow_stat.sh
>
> diff --git a/tools/perf/tests/shell/stat+shadow_stat.sh b/tools/perf/tests/shell/stat+shadow_stat.sh
> new file mode 100755
> index 000000000000..249dfe48cf6a
> --- /dev/null
> +++ b/tools/perf/tests/shell/stat+shadow_stat.sh
> @@ -0,0 +1,80 @@
> +#!/bin/sh
> +# perf stat metrics (shadow stat) test
> +# SPDX-License-Identifier: GPL-2.0
> +
> +set -e
> +
> +# skip if system-wide mode is forbidden
> +perf stat -a true > /dev/null 2>&1 || exit 2
> +
> +test_global_aggr()
> +{
> + local cyc
> +
> + perf stat -a --no-big-num -e cycles,instructions sleep 1 2>&1 | \
> + grep -e cycles -e instructions | \
> + while read num evt hash ipc rest
> + do
> + # skip not counted events
> + if [[ $num == "<not" ]]; then
> + continue
> + fi
> +
> + # save cycles count
> + if [[ $evt == "cycles" ]]; then
> + cyc=$num
> + continue
> + fi
> +
> + # skip if no cycles
> + if [[ -z $cyc ]]; then
> + continue
> + fi
> +
> + # use printf for rounding and a leading zero
> + local res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
> + if [[ $ipc != $res ]]; then
> + echo "IPC is different: $res != $ipc ($num / $cyc)"
> + exit 1
> + fi
> + done
> +}
> +
> +test_no_aggr()
> +{
> + declare -A results
> +
> + perf stat -a -A --no-big-num -e cycles,instructions sleep 1 2>&1 | \
> + grep ^CPU | \
> + while read cpu num evt hash ipc rest
> + do
> + # skip not counted events
> + if [[ $num == "<not" ]]; then
> + continue
> + fi
> +
> + # save cycles count
> + if [[ $evt == "cycles" ]]; then
> + results[$cpu]=$num
> + continue
> + fi
> +
> + # skip if no cycles
> + local cyc=${results[$cpu]}
> + if [[ -z $cyc ]]; then
> + continue
> + fi
> +
> + # use printf for rounding and a leading zero
> + local res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
> + if [[ $ipc != $res ]]; then
> + echo "IPC is different for $cpu: $res != $ipc ($num / $cyc)"
> + exit 1
> + fi
> + done
> +}
> +
> +test_global_aggr
> +test_no_aggr
> +
> +exit 0
> --
> 2.29.2.454.gaff20da3a2-goog
>
--
- Arnaldo
Powered by blists - more mailing lists