[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20181126095341.GB18780@krava>
Date: Mon, 26 Nov 2018 10:53:41 +0100
From: Jiri Olsa <jolsa@...hat.com>
To: Jin Yao <yao.jin@...ux.intel.com>
Cc: acme@...nel.org, jolsa@...nel.org, peterz@...radead.org,
mingo@...hat.com, alexander.shishkin@...ux.intel.com,
Linux-kernel@...r.kernel.org, ak@...ux.intel.com,
kan.liang@...el.com, yao.jin@...el.com
Subject: Re: [PATCH 2/2] perf report: Display average IPC and IPC coverage
per symbol
On Mon, Nov 26, 2018 at 05:40:54PM +0800, Jin Yao wrote:
SNIP
> diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
> index f96c005..94f62c8 100644
> --- a/tools/perf/util/sort.c
> +++ b/tools/perf/util/sort.c
> @@ -13,6 +13,7 @@
> #include "strlist.h"
> #include <traceevent/event-parse.h>
> #include "mem-events.h"
> +#include "annotate.h"
> #include <linux/kernel.h>
>
> regex_t parent_regex;
> @@ -422,6 +423,47 @@ struct sort_entry sort_srcline_to = {
> .se_width_idx = HISTC_SRCLINE_TO,
> };
>
> +static int hist_entry__sym_ipc_snprintf(struct hist_entry *he, char *bf,
> + size_t size, unsigned int width)
> +{
> +
> + struct symbol *sym = he->ms.sym;
> + struct map *map = he->ms.map;
> + struct perf_evsel *evsel = hists_to_evsel(he->hists);
> + struct annotation *notes;
> + double ipc = 0.0, coverage = 0.0;
> + char tmp[64];
> +
> + if (!sym)
> + return repsep_snprintf(bf, size, "%-*s", width, "-");
> +
> + if (!sym->annotated &&
> + symbol__annotate2(sym, map, evsel, &annotation__default_options,
> + NULL) < 0) {
> + return 0;
> + }
> +
> + sym->annotated = true;
I don't like this being set in here.. please move it to
symbol__annotate2 or symbol__annotate, not sure which
one of these is the best fit
> + notes = symbol__annotation(sym);
> +
> + if (notes->hit_cycles)
> + ipc = notes->hit_insn / ((double)notes->hit_cycles);
> +
> + if (notes->total_insn)
> + coverage = notes->cover_insn * 100.0 /
> + ((double)notes->total_insn);
missing { } for multiline code in 'if' condition
thanks,
jirka
Powered by blists - more mailing lists