From: Ian Rogers <irogers@google.com>
To: Namhyung Kim <namhyung@kernel.org>
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>,
Adrian Hunter <adrian.hunter@intel.com>,
linux-perf-users@vger.kernel.org, Andi Kleen <ak@linux.intel.com>,
Kan Liang <kan.liang@linux.intel.com>,
Leo Yan <leo.yan@linaro.org>,
Zhengjun Xing <zhengjun.xing@linux.intel.com>
Subject: Re: [PATCH 4/6] perf stat: Use thread map index for shadow stat
Date: Wed, 28 Sep 2022 19:10:19 -0700 [thread overview]
Message-ID: <CAP-5=fVY2QP6f=8CvZqERCZzH+sB6A-_wK-edukrz4eeGUz5zg@mail.gmail.com> (raw)
In-Reply-To: <20220926200757.1161448-5-namhyung@kernel.org>
On Mon, Sep 26, 2022 at 1:08 PM Namhyung Kim <namhyung@kernel.org> wrote:
>
> When AGGR_THREAD is active, it aggregates the values for each thread.
> Previously it used cpu map index which is invalid for AGGR_THREAD so
> it had to use separate runtime stats with index 0.
>
> But it can just use the rt_stat with thread_map_index. Rename the
> first_shadow_map_idx() and make it return the thread index.
>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
> tools/perf/util/stat-display.c | 20 +++++++++-----------
> tools/perf/util/stat.c | 8 ++------
> 2 files changed, 11 insertions(+), 17 deletions(-)
>
> diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
> index 234491f43c36..570e2c04d47d 100644
> --- a/tools/perf/util/stat-display.c
> +++ b/tools/perf/util/stat-display.c
> @@ -442,7 +442,7 @@ static void print_metric_header(struct perf_stat_config *config,
> fprintf(os->fh, "%*s ", config->metric_only_len, unit);
> }
>
> -static int first_shadow_cpu_map_idx(struct perf_stat_config *config,
> +static int first_shadow_map_idx(struct perf_stat_config *config,
> struct evsel *evsel, const struct aggr_cpu_id *id)
> {
> struct perf_cpu_map *cpus = evsel__cpus(evsel);
> @@ -452,6 +452,9 @@ static int first_shadow_cpu_map_idx(struct perf_stat_config *config,
> if (config->aggr_mode == AGGR_NONE)
> return perf_cpu_map__idx(cpus, id->cpu);
>
> + if (config->aggr_mode == AGGR_THREAD)
> + return id->thread;
The function's name implies returning an index but that isn't clear
here. Can we change the aggr_cpu_id's thread to be called thread_idx?
Thanks,
Ian
> +
> if (!config->aggr_get_id)
> return 0;
>
> @@ -646,7 +649,7 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int
> }
>
> perf_stat__print_shadow_stats(config, counter, uval,
> - first_shadow_cpu_map_idx(config, counter, &id),
> + first_shadow_map_idx(config, counter, &id),
> &out, &config->metric_events, st);
> if (!config->csv_output && !config->metric_only && !config->json_output) {
> print_noise(config, counter, noise);
> @@ -676,7 +679,7 @@ static void aggr_update_shadow(struct perf_stat_config *config,
> val += perf_counts(counter->counts, idx, 0)->val;
> }
> perf_stat__update_shadow_stats(counter, val,
> - first_shadow_cpu_map_idx(config, counter, &id),
> + first_shadow_map_idx(config, counter, &id),
> &rt_stat);
> }
> }
> @@ -979,14 +982,9 @@ static void print_aggr_thread(struct perf_stat_config *config,
> fprintf(output, "%s", prefix);
>
> id = buf[thread].id;
> - if (config->stats)
> - printout(config, id, 0, buf[thread].counter, buf[thread].uval,
> - prefix, buf[thread].run, buf[thread].ena, 1.0,
> - &config->stats[id.thread]);
> - else
> - printout(config, id, 0, buf[thread].counter, buf[thread].uval,
> - prefix, buf[thread].run, buf[thread].ena, 1.0,
> - &rt_stat);
> + printout(config, id, 0, buf[thread].counter, buf[thread].uval,
> + prefix, buf[thread].run, buf[thread].ena, 1.0,
> + &rt_stat);
> fputc('\n', output);
> }
>
> diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
> index e1d3152ce664..21137c9d5259 100644
> --- a/tools/perf/util/stat.c
> +++ b/tools/perf/util/stat.c
> @@ -389,12 +389,8 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
> }
>
> if (config->aggr_mode == AGGR_THREAD) {
> - if (config->stats)
> - perf_stat__update_shadow_stats(evsel,
> - count->val, 0, &config->stats[thread]);
> - else
> - perf_stat__update_shadow_stats(evsel,
> - count->val, 0, &rt_stat);
> + perf_stat__update_shadow_stats(evsel, count->val,
> + thread, &rt_stat);
> }
> break;
> case AGGR_GLOBAL:
> --
> 2.37.3.998.g577e59143f-goog
>
next prev parent reply other threads:[~2022-09-29 2:10 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-26 20:07 [PATCHSET 0/6] perf stat: Small random cleanups (v1) Namhyung Kim
2022-09-26 20:07 ` [PATCH 1/6] perf stat: Convert perf_stat_evsel.res_stats array Namhyung Kim
2022-09-28 10:33 ` James Clark
2022-09-26 20:07 ` [PATCH 2/6] perf stat: Don't call perf_stat_evsel_id_init() repeatedly Namhyung Kim
2022-09-28 10:41 ` James Clark
2022-09-26 20:07 ` [PATCH 3/6] perf stat: Rename saved_value->cpu_map_idx Namhyung Kim
2022-09-28 10:50 ` James Clark
2022-09-28 23:56 ` Namhyung Kim
2022-09-29 1:58 ` Ian Rogers
2022-09-26 20:07 ` [PATCH 4/6] perf stat: Use thread map index for shadow stat Namhyung Kim
2022-09-28 14:49 ` James Clark
2022-09-29 2:10 ` Ian Rogers [this message]
2022-09-29 4:55 ` Namhyung Kim
2022-09-26 20:07 ` [PATCH 5/6] perf stat: Kill unused per-thread runtime stats Namhyung Kim
2022-09-28 14:51 ` James Clark
2022-09-26 20:07 ` [PATCH 6/6] perf stat: Don't compare runtime stat for shadow stats Namhyung Kim
2022-09-28 14:52 ` James Clark
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAP-5=fVY2QP6f=8CvZqERCZzH+sB6A-_wK-edukrz4eeGUz5zg@mail.gmail.com' \
--to=irogers@google.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=leo.yan@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=zhengjun.xing@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).