Re: [PATCH V9 4/6] perf,tools: Dump per-sample freq/CPU%/CORE_BUSY% in report -D

From: Arnaldo Carvalho de Melo
Date: Thu Sep 10 2015 - 10:21:36 EST

Next message: Marc MarÃ: "Re: [PATCH v2] QEMU fw_cfg DMA interface documentation"
Previous message: Muthoot: "my subject"
In reply to: kan . liang: "[PATCH V9 4/6] perf,tools: Dump per-sample freq/CPU%/CORE_BUSY% in report -D"
Next in thread: kan . liang: "[PATCH V9 6/6] perf,tools: Show freq/CPU%/CORE_BUSY% in perf report by --freq-perf"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Em Tue, Sep 08, 2015 at 03:32:47PM -0400, kan.liang@xxxxxxxxx escreveu:
> From: Kan Liang <kan.liang@xxxxxxxxx>
>
> The group read results from cycles/ref-cycles/TSC/ASTATE/MSTATE event
> can be used to calculate the frequency, CPU Utilization and percent
> performance during each sampling period.
> This patch shows them in report -D.
>
> Here is an example:
>
> $ perf record --freq-perf ~/tchain_edit
>
> Here is one sample from perf report -D
>
> 1972044565107 0x3498 [0x88]: PERF_RECORD_SAMPLE(IP, 0x2): 10608/10608:
> 0x4005fd period: 564686 addr: 0
> ... sample_read:
> .... group nr 5
> ..... id 0000000000000012, value 0000000002143901
> ..... id 0000000000000052, value 0000000002143896
> ..... id 0000000000000094, value 00000000021e443d
> ..... id 00000000000000d4, value 00000000021db984
> ..... id 0000000000000114, value 00000000021db964
> ..... Freq 2301 MHz
> ..... CPU% 98%
> ..... CORE_BUSY% 99%
>
> Signed-off-by: Kan Liang <kan.liang@xxxxxxxxx>
> Acked-by: Jiri Olsa <jolsa@xxxxxxxxxx>
> ---
> tools/perf/util/session.c | 28 +++++++++++++++++++++---
> tools/perf/util/session.h | 54 +++++++++++++++++++++++++++++++++++++++++++++++
> 2 files changed, 79 insertions(+), 3 deletions(-)
>
> diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
> index 23fed17..ba763f7 100644
> --- a/tools/perf/util/session.c
> +++ b/tools/perf/util/session.c
> @@ -7,7 +7,6 @@
> #include <sys/mman.h>
>
> #include "evlist.h"
> -#include "evsel.h"
> #include "session.h"
> #include "tool.h"
> #include "sort.h"
> @@ -878,8 +877,15 @@ static void perf_evlist__print_tstamp(struct perf_evlist *evlist,
> printf("%" PRIu64 " ", sample->time);
> }
>
> -static void sample_read__printf(struct perf_sample *sample, u64 read_format)
> +static void sample_read__printf(struct perf_sample *sample,
> + struct perf_evsel *evsel)

Hey, this is a _printf_ function, i.e. one thinks about functions with
such name it doing just that, printing whatever is _already_ in the data
structures, at maximum messing with _output_ related internal state.

This probably needs setting up at some other place, so that when it
comes here it is already all worked out.

- Arnaldo

> {
> + u64 read_format = evsel->attr.read_format;
> + struct perf_evlist *evlist = evsel->evlist;
> + struct perf_sample_id *sid;
> + perf_freq_t data = { 0 };
> + u64 cpu_max_freq = evlist->env->cpuattr.max_freq;
> +
> printf("... sample_read:\n");
>
> if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
> @@ -902,10 +908,26 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format)
> printf("..... id %016" PRIx64
> ", value %016" PRIx64 "\n",
> value->id, value->value);
> +
> + sid = perf_evlist__id2sid(evlist, value->id);
> + evsel = sid->evsel;
> + if (evsel != NULL)
> + perf_freq__init(evlist->env->msr_pmu_type,
> + evsel, data, value->value);
> }
> } else
> printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n",
> sample->read.one.id, sample->read.one.value);
> +
> + if (perf_freq__has_freq(data))
> + printf("..... Freq %lu MHz\n",
> + perf_freq__get_freq(data, cpu_max_freq/1000));
> + if (perf_freq__has_cpu_util(data))
> + printf("..... CPU%% %lu%%\n",
> + perf_freq__get_cpu_util(data));
> + if (perf_freq__has_core_busy(data))
> + printf("..... CORE_BUSY%% %lu%%\n",
> + perf_freq__get_core_busy(data));
> }
>
> static void dump_event(struct perf_evlist *evlist, union perf_event *event,
> @@ -965,7 +987,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
> printf("... transaction: %" PRIx64 "\n", sample->transaction);
>
> if (sample_type & PERF_SAMPLE_READ)
> - sample_read__printf(sample, evsel->attr.read_format);
> + sample_read__printf(sample, evsel);
> }
>
> static struct machine *machines__find_for_cpumode(struct machines *machines,
> diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
> index 3915be7..83bf4a9 100644
> --- a/tools/perf/util/session.h
> +++ b/tools/perf/util/session.h
> @@ -11,6 +11,7 @@
> #include "ordered-events.h"
> #include <linux/rbtree.h>
> #include <linux/perf_event.h>
> +#include "evsel.h"
>
> struct ip_callchain;
> struct thread;
> @@ -42,6 +43,10 @@ struct perf_session {
> #define PRINT_IP_OPT_ONELINE (1<<4)
> #define PRINT_IP_OPT_SRCLINE (1<<5)
>
> +#define PERF_MSR_TSC 0
> +#define PERF_MSR_APERF 1
> +#define PERF_MSR_MPERF 2
> +
> enum perf_freq_perf_index {
> FREQ_PERF_TSC = 0,
> FREQ_PERF_APERF = 1,
> @@ -52,6 +57,55 @@ enum perf_freq_perf_index {
> FREQ_PERF_MAX
> };
>
> +typedef u64 perf_freq_t[FREQ_PERF_MAX];
> +
> +static inline void perf_freq__init(unsigned int msr_pmu_type,
> + struct perf_evsel *evsel,
> + perf_freq_t array,
> + u64 value)
> +{
> + if (evsel->attr.type == msr_pmu_type) {
> + if (evsel->attr.config == PERF_MSR_TSC)
> + array[FREQ_PERF_TSC] = value;
> + if (evsel->attr.config == PERF_MSR_APERF)
> + array[FREQ_PERF_APERF] = value;
> + if (evsel->attr.config == PERF_MSR_MPERF)
> + array[FREQ_PERF_MPERF] = value;
> + }
> + if (evsel->attr.type == PERF_TYPE_HARDWARE) {
> + if (evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES)
> + array[FREQ_PERF_CYCLES] = value;
> + if (evsel->attr.config == PERF_COUNT_HW_REF_CPU_CYCLES)
> + array[FREQ_PERF_REF_CYCLES] = value;
> + }
> +}
> +
> +static inline bool perf_freq__has_freq(perf_freq_t array)
> +{
> + return ((array[FREQ_PERF_CYCLES] > 0) && (array[FREQ_PERF_REF_CYCLES] > 0));
> +}
> +static inline u64 perf_freq__get_freq(perf_freq_t array, u64 cpu_max_freq)
> +{
> + return ((array[FREQ_PERF_CYCLES] * cpu_max_freq) / array[FREQ_PERF_REF_CYCLES]);
> +}
> +static inline bool perf_freq__has_cpu_util(perf_freq_t array)
> +{
> + return ((array[FREQ_PERF_TSC] > 0) && (array[FREQ_PERF_REF_CYCLES] > 0));
> +}
> +static inline u64 perf_freq__get_cpu_util(perf_freq_t array)
> +{
> + return ((100 * array[FREQ_PERF_REF_CYCLES]) / array[FREQ_PERF_TSC]);
> +}
> +
> +static inline bool perf_freq__has_core_busy(perf_freq_t array)
> +{
> + return ((array[FREQ_PERF_APERF] > 0) && (array[FREQ_PERF_MPERF] > 0));
> +}
> +static inline u64 perf_freq__get_core_busy(perf_freq_t array)
> +{
> + return ((100 * array[FREQ_PERF_APERF]) / array[FREQ_PERF_MPERF]);
> +}
> +
> struct perf_tool;
>
> struct perf_session *perf_session__new(struct perf_data_file *file,
> --
> 1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Marc MarÃ: "Re: [PATCH v2] QEMU fw_cfg DMA interface documentation"
Previous message: Muthoot: "my subject"
In reply to: kan . liang: "[PATCH V9 4/6] perf,tools: Dump per-sample freq/CPU%/CORE_BUSY% in report -D"
Next in thread: kan . liang: "[PATCH V9 6/6] perf,tools: Show freq/CPU%/CORE_BUSY% in perf report by --freq-perf"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]