Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Content-Type: text/plain;
        charset=us-ascii
Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3696.120.41.1.1\))
Subject: Re: [PATCH 19/19] perf stat: Remove unused perf_counts.aggr field
From:   Athira Rajeev <atrajeev@linux.vnet.ibm.com>
In-Reply-To: <20221014061550.463644-20-namhyung@kernel.org>
Date:   Sun, 16 Oct 2022 19:02:44 +0530
Cc:     Arnaldo Carvalho de Melo <acme@kernel.org>,
        Jiri Olsa <jolsa@kernel.org>, Ingo Molnar <mingo@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Ian Rogers <irogers@google.com>,
        Adrian Hunter <adrian.hunter@intel.com>,
        linux-perf-users@vger.kernel.org,
        Kan Liang <kan.liang@linux.intel.com>,
        Leo Yan <leo.yan@linaro.org>, Andi Kleen <ak@linux.intel.com>,
        James Clark <james.clark@arm.com>,
        Xing Zhengjun <zhengjun.xing@linux.intel.com>
Content-Transfer-Encoding: quoted-printable
Message-Id: <B51023CD-214D-4D85-8086-B7AA6B6701D8@linux.vnet.ibm.com>
References: <20221014061550.463644-1-namhyung@kernel.org>
 <20221014061550.463644-20-namhyung@kernel.org>
To:     Namhyung Kim <namhyung@kernel.org>
Precedence: bulk


> On 14-Oct-2022, at 11:45 AM, Namhyung Kim <namhyung@kernel.org> wrote:
>=20
> The aggr field in the struct perf_counts is to keep the aggregated =
value
> in the AGGR_GLOBAL for the old code.  But it's not used anymore.
>=20
> Acked-by: Ian Rogers <irogers@google.com>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
> tools/perf/util/counts.c |  1 -
> tools/perf/util/counts.h |  1 -
> tools/perf/util/stat.c   | 35 ++---------------------------------
> 3 files changed, 2 insertions(+), 35 deletions(-)
>=20
> diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
> index 7a447d918458..11cd85b278a6 100644
> --- a/tools/perf/util/counts.c
> +++ b/tools/perf/util/counts.c
> @@ -48,7 +48,6 @@ void perf_counts__reset(struct perf_counts *counts)
> {
> 	xyarray__reset(counts->loaded);
> 	xyarray__reset(counts->values);
> -	memset(&counts->aggr, 0, sizeof(struct perf_counts_values));
> }
>=20
> void evsel__reset_counts(struct evsel *evsel)
> diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
> index 5de275194f2b..42760242e0df 100644
> --- a/tools/perf/util/counts.h
> +++ b/tools/perf/util/counts.h
> @@ -11,7 +11,6 @@ struct evsel;
>=20
> struct perf_counts {
> 	s8			  scaled;
> -	struct perf_counts_values aggr;
> 	struct xyarray		  *values;
> 	struct xyarray		  *loaded;
> };
> diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
> index 14c45f4cfdd3..6ab9c58beca7 100644
> --- a/tools/perf/util/stat.c
> +++ b/tools/perf/util/stat.c
> @@ -308,8 +308,6 @@ static void evsel__copy_prev_raw_counts(struct =
evsel *evsel)
> 				*perf_counts(evsel->prev_raw_counts, =
idx, thread);
> 		}
> 	}
> -
> -	evsel->counts->aggr =3D evsel->prev_raw_counts->aggr;
> }
>=20
> void evlist__copy_prev_raw_counts(struct evlist *evlist)
> @@ -320,26 +318,6 @@ void evlist__copy_prev_raw_counts(struct evlist =
*evlist)
> 		evsel__copy_prev_raw_counts(evsel);
> }
>=20
> -void evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
> -{
> -	struct evsel *evsel;
> -
> -	/*
> -	 * To collect the overall statistics for interval mode,
> -	 * we copy the counts from evsel->prev_raw_counts to
> -	 * evsel->counts. The perf_stat_process_counter creates
> -	 * aggr values from per cpu values, but the per cpu values
> -	 * are 0 for AGGR_GLOBAL. So we use a trick that saves the
> -	 * previous aggr value to the first member of perf_counts,
> -	 * then aggr calculation in process_counter_values can work
> -	 * correctly.
> -	 */
> -	evlist__for_each_entry(evlist, evsel) {
> -		*perf_counts(evsel->prev_raw_counts, 0, 0) =3D
> -			evsel->prev_raw_counts->aggr;
> -	}
> -}
> -
> static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused)
> {
> 	uint64_t *key =3D (uint64_t *) __key;
> @@ -423,7 +401,6 @@ process_counter_values(struct perf_stat_config =
*config, struct evsel *evsel,
> 		       int cpu_map_idx, int thread,
> 		       struct perf_counts_values *count)
> {
> -	struct perf_counts_values *aggr =3D &evsel->counts->aggr;
> 	struct perf_stat_evsel *ps =3D evsel->stats;
> 	static struct perf_counts_values zero;
> 	bool skip =3D false;
> @@ -493,12 +470,6 @@ process_counter_values(struct perf_stat_config =
*config, struct evsel *evsel,
> 		}
> 	}
>=20
> -	if (config->aggr_mode =3D=3D AGGR_GLOBAL) {
> -		aggr->val +=3D count->val;
> -		aggr->ena +=3D count->ena;
> -		aggr->run +=3D count->run;
> -	}
> -
> 	return 0;
> }
>=20
> @@ -523,13 +494,10 @@ static int process_counter_maps(struct =
perf_stat_config *config,
> int perf_stat_process_counter(struct perf_stat_config *config,
> 			      struct evsel *counter)
> {
> -	struct perf_counts_values *aggr =3D &counter->counts->aggr;
> 	struct perf_stat_evsel *ps =3D counter->stats;
> -	u64 *count =3D counter->counts->aggr.values;
> +	u64 *count;
> 	int ret;
>=20
> -	aggr->val =3D aggr->ena =3D aggr->run =3D 0;
> -
> 	if (counter->per_pkg)
> 		evsel__zero_per_pkg(counter);
>=20
> @@ -540,6 +508,7 @@ int perf_stat_process_counter(struct =
perf_stat_config *config,
> 	if (config->aggr_mode !=3D AGGR_GLOBAL)
> 		return 0;
>=20
> +	count =3D ps->aggr[0].counts.values;

Hi Namhyung,

We are using ps->aggr[0] here always. Can you please clarify on why =
first index is used here always.

Thanks
Athira
> 	update_stats(&ps->res_stats, *count);
>=20
> 	if (verbose > 0) {
> --=20
> 2.38.0.413.g74048e4d9e-goog
>=20