Re: [PATCH] perf stat: Add Topdown metrics events as default events
From: Arnaldo Carvalho de Melo
Date: Thu Jan 21 2021 - 15:01:42 EST
Em Thu, Jan 21, 2021 at 05:37:52AM -0800, kan.liang@xxxxxxxxxxxxxxx escreveu:
> From: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
>
> The Topdown Microarchitecture Analysis (TMA) Method is a structured
> analysis methodology to identify critical performance bottlenecks in
> out-of-order processors. From the Ice Lake and later platforms, the
> Topdown information can be retrieved from the dedicated "metrics"
> register, which isn't impacted by other events. Also, the Topdown
> metrics support both per thread/process and per core measuring.
> Adding Topdown metrics events as default events can enrich the default
> measuring information, and would not cost any extra multiplexing.
>
> Introduce arch_evlist__add_default_attrs() to allow architecture
> specific default events. Add the Topdown metrics events in the X86
> specific arch_evlist__add_default_attrs(). Other architectures can
> add their own default events later separately.
>
> With the patch,
>
> $perf stat sleep 1
>
> Performance counter stats for 'sleep 1':
>
> 0.82 msec task-clock:u # 0.001 CPUs utilized
> 0 context-switches:u # 0.000 K/sec
> 0 cpu-migrations:u # 0.000 K/sec
> 61 page-faults:u # 0.074 M/sec
> 319,941 cycles:u # 0.388 GHz
> 242,802 instructions:u # 0.76 insn per cycle
> 54,380 branches:u # 66.028 M/sec
> 4,043 branch-misses:u # 7.43% of all branches
> 1,585,555 slots:u # 1925.189 M/sec
> 238,941 topdown-retiring:u # 15.0% retiring
> 410,378 topdown-bad-spec:u # 25.8% bad speculation
> 634,222 topdown-fe-bound:u # 39.9% frontend bound
> 304,675 topdown-be-bound:u # 19.2% backend bound
Shouldn't we be adding this to one of the -d levels?
But you say that this is essentially for free, so you check if this
extra register is in place and if it is, hey, its for free, add it, is
that the rationale?
I.e. it doesn't cause any impact to what we were getting before, so we
should default to use free stuff?
- Arnaldo
> 1.001791625 seconds time elapsed
>
> 0.000000000 seconds user
> 0.001572000 seconds sys
>
> Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
> ---
> tools/perf/arch/x86/util/Build | 1 +
> tools/perf/arch/x86/util/evlist.c | 15 +++++++++++++++
> tools/perf/builtin-stat.c | 3 +++
> tools/perf/util/evlist.c | 5 +++++
> tools/perf/util/evlist.h | 2 ++
> 5 files changed, 26 insertions(+)
> create mode 100644 tools/perf/arch/x86/util/evlist.c
>
> diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
> index 347c39b960eb..ce1ec92fecdc 100644
> --- a/tools/perf/arch/x86/util/Build
> +++ b/tools/perf/arch/x86/util/Build
> @@ -6,6 +6,7 @@ perf-y += perf_regs.o
> perf-y += topdown.o
> perf-y += machine.o
> perf-y += event.o
> +perf-y += evlist.o
>
> perf-$(CONFIG_DWARF) += dwarf-regs.o
> perf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
> diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
> new file mode 100644
> index 000000000000..8c6732cc7794
> --- /dev/null
> +++ b/tools/perf/arch/x86/util/evlist.c
> @@ -0,0 +1,15 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#include <stdio.h>
> +#include "util/pmu.h"
> +#include "util/evlist.h"
> +#include "util/parse-events.h"
> +
> +#define TOPDOWN_L1_EVENTS "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}"
> +
> +int arch_evlist__add_default_attrs(struct evlist *evlist)
> +{
> + if (!pmu_have_event("cpu", "slots"))
> + return 0;
> +
> + return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL);
> +}
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index 3c054b8d4677..abcdabaf1701 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -1827,6 +1827,9 @@ static int add_default_attributes(void)
> }
> if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
> return -1;
> +
> + if (arch_evlist__add_default_attrs(evsel_list) < 0)
> + return -1;
> }
>
> /* Detailed events get appended to the event list: */
> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
> index 05363a7247c4..b38589d8c027 100644
> --- a/tools/perf/util/evlist.c
> +++ b/tools/perf/util/evlist.c
> @@ -303,6 +303,11 @@ int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *a
> return evlist__add_attrs(evlist, attrs, nr_attrs);
> }
>
> +__weak int arch_evlist__add_default_attrs(struct evlist *evlist __maybe_unused)
> +{
> + return 0;
> +}
> +
> struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id)
> {
> struct evsel *evsel;
> diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
> index 1aae75895dea..9eba4958a1e9 100644
> --- a/tools/perf/util/evlist.h
> +++ b/tools/perf/util/evlist.h
> @@ -110,6 +110,8 @@ int __evlist__add_default_attrs(struct evlist *evlist,
> #define evlist__add_default_attrs(evlist, array) \
> __evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
>
> +int arch_evlist__add_default_attrs(struct evlist *evlist);
> +
> int evlist__add_dummy(struct evlist *evlist);
>
> int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
> --
> 2.25.1
>
--
- Arnaldo