[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAM9d7cjLvS5BUO_AEkfR3LsT8SNB8MCt-DTHCiRDrZyQxhySoQ@mail.gmail.com>
Date: Mon, 19 Aug 2024 19:21:34 -0700
From: Namhyung Kim <namhyung@...nel.org>
To: Arnaldo Carvalho de Melo <arnaldo.melo@...il.com>
Cc: Arnaldo Carvalho de Melo <acme@...nel.org>, Ian Rogers <irogers@...gle.com>,
Kan Liang <kan.liang@...ux.intel.com>, Jiri Olsa <jolsa@...nel.org>,
Adrian Hunter <adrian.hunter@...el.com>, Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>, LKML <linux-kernel@...r.kernel.org>,
linux-perf-users <linux-perf-users@...r.kernel.org>,
Athira Rajeev <atrajeev@...ux.vnet.ibm.com>
Subject: Re: [PATCH 1/2] perf annotate-data: Show offset and size in hex
On Mon, Aug 19, 2024 at 5:12 PM Arnaldo Carvalho de Melo
<arnaldo.melo@...il.com> wrote:
>
>
>
> On Mon, Aug 19, 2024, 8:36 PM Namhyung Kim <namhyung@...nel.org> wrote:
>>
>> It'd be better to have them in hex to check cacheline alignment.
>>
>>
> Why is it better? To compare with the usual output of some other tool?
>
> Spelling out reasons helps reviewers/users.
Cache line sizes are power of 2 so it'd be natural to use hex and
check whether an offset is in the same boundary. Also perf annotate
shows instruction offsets in hex.
>
> Maybe this should be selectable?
I can add an option and/or a config if you want.
Thanks,
Namhyung
>>
>>
>
>> Percent offset size field
>> 100.00 0 0x1c0 struct cfs_rq {
>> 0.00 0 0x10 struct load_weight load {
>> 0.00 0 0x8 long unsigned int weight;
>> 0.00 0x8 0x4 u32 inv_weight;
>> };
>> 0.00 0x10 0x4 unsigned int nr_running;
>> 14.56 0x14 0x4 unsigned int h_nr_running;
>> 0.00 0x18 0x4 unsigned int idle_nr_running;
>> 0.00 0x1c 0x4 unsigned int idle_h_nr_running;
>> ...
>>
>> Signed-off-by: Namhyung Kim <namhyung@...nel.org>
>> ---
>> tools/perf/ui/browsers/annotate-data.c | 4 ++--
>> tools/perf/util/annotate-data.c | 2 +-
>> tools/perf/util/sort.c | 2 +-
>> 3 files changed, 4 insertions(+), 4 deletions(-)
>>
>> diff --git a/tools/perf/ui/browsers/annotate-data.c b/tools/perf/ui/browsers/annotate-data.c
>> index f563a3bb072c..cd562a8822b7 100644
>> --- a/tools/perf/ui/browsers/annotate-data.c
>> +++ b/tools/perf/ui/browsers/annotate-data.c
>> @@ -427,12 +427,12 @@ static void browser__write(struct ui_browser *uib, void *entry, int row)
>>
>> /* print type info */
>> if (be->indent == 0 && !member->var_name) {
>> - ui_browser__printf(uib, " %10d %10d %s%s",
>> + ui_browser__printf(uib, " %#10x %#10x %s%s",
>> member->offset, member->size,
>> member->type_name,
>> list_empty(&member->children) || be->folded? ";" : " {");
>> } else {
>> - ui_browser__printf(uib, " %10d %10d %*s%s\t%s%s",
>> + ui_browser__printf(uib, " %#10x %#10x %*s%s\t%s%s",
>> member->offset, member->size,
>> be->indent * 4, "", member->type_name,
>> member->var_name ?: "",
>> diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
>> index aa330c7d8edd..25105b3b9a13 100644
>> --- a/tools/perf/util/annotate-data.c
>> +++ b/tools/perf/util/annotate-data.c
>> @@ -1660,7 +1660,7 @@ static void print_annotated_data_type(struct annotated_data_type *mem_type,
>> nr_events++;
>> }
>>
>> - printf(" %10d %10d %*s%s\t%s",
>> + printf(" %#10x %#10x %*s%s\t%s",
>> member->offset, member->size, indent, "", member->type_name,
>> member->var_name ?: "");
>>
>> diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
>> index c4046d5d1749..d315308f9170 100644
>> --- a/tools/perf/util/sort.c
>> +++ b/tools/perf/util/sort.c
>> @@ -2312,7 +2312,7 @@ static int hist_entry__typeoff_snprintf(struct hist_entry *he, char *bf,
>> he->mem_type_off, true);
>> buf[4095] = '\0';
>>
>> - return repsep_snprintf(bf, size, "%s %+d (%s)", he_type->self.type_name,
>> + return repsep_snprintf(bf, size, "%s +%#x (%s)", he_type->self.type_name,
>> he->mem_type_off, buf);
>> }
>>
>> --
>> 2.46.0.184.g6999bdac58-goog
>>
>>
Powered by blists - more mailing lists