From: Kan Liang <[email protected]>
Show frequency, CPU Utilization and percent performance for each symbol
in perf report by --stdio --show-freq-perf
In sampling group, only group leader do sampling. So only need to print
group leader's freq in --group.
Here is an example.
$ perf report --stdio --group --show-freq-perf
Overhead FREQ MHz CPU% CORE_BUSY%
Command Shared Object Symbol
........................................ ......... ..... ..........
........... ................ ......................
99.54% 99.54% 99.53% 99.53% 99.53% 2301 96 99
tchain_edit tchain_edit [.] f3
0.20% 0.20% 0.20% 0.20% 0.20% 2301 98 99
tchain_edit tchain_edit [.] f2
0.05% 0.05% 0.05% 0.05% 0.05% 2300 98 99
tchain_edit [kernel.vmlinux] [k] read_tsc
Signed-off-by: Kan Liang <[email protected]>
---
tools/perf/Documentation/perf-report.txt | 12 ++++++
tools/perf/builtin-report.c | 19 +++++++++
tools/perf/perf.h | 1 +
tools/perf/ui/hist.c | 71 +++++++++++++++++++++++++++++---
tools/perf/util/hist.h | 3 ++
tools/perf/util/session.c | 2 +-
tools/perf/util/sort.c | 3 ++
tools/perf/util/symbol.h | 3 +-
tools/perf/util/util.c | 2 +
9 files changed, 109 insertions(+), 7 deletions(-)
diff --git a/tools/perf/Documentation/perf-report.txt
b/tools/perf/Documentation/perf-report.txt
index c33b69f..faa8825 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -303,6 +303,18 @@ OPTIONS
special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See
'perf mem' for simpler access.
+--show-freq-perf::
+ Show CPU frequency and performance result from sample read.
+ To generate the frequency and performance output, the perf.data file
+ must have been obtained by group read and using special events cycles,
+ ref-cycles, msr/tsc/, msr/aperf/ or msr/mperf/
+ Freq MHz: The frequency during the sample interval. Needs cycles and
+ ref-cycles event.
+ CPU%: CPU utilization during the sample interval. Needs ref-cycles and
+ msr/tsc/ events.
+ CORE_BUSY%: actual percent performance (APERF/MPERF%) during the
+ sample interval. Needs msr/aperf/ and msr/mperf/ events.
+
--percent-limit::
Do not show entries which have an overhead under that percent.
(Default: 0).
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 2a32e9a..f52c63d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -164,6 +164,8 @@ static int process_sample_event(struct perf_tool *tool,
iter.ops = &hist_iter_mem;
else if (symbol_conf.cumulate_callchain)
iter.ops = &hist_iter_cumulative;
+ else if (symbol_conf.show_freq_perf)
+ iter.ops = &hist_iter_freq_perf;
else
iter.ops = &hist_iter_normal;
@@ -721,6 +723,8 @@ int cmd_report(int argc, const char **argv, const char
*prefix __maybe_unused)
OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
"Enable kernel symbol demangling"),
OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
+ OPT_BOOLEAN(0, "show-freq-perf", &symbol_conf.show_freq_perf,
+ "show CPU freqency and performance info"),
OPT_CALLBACK(0, "percent-limit", &report, "percent",
"Don't show entries under that percent",
parse_percent_limit),
OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
@@ -733,7 +737,9 @@ int cmd_report(int argc, const char **argv, const char
*prefix __maybe_unused)
struct perf_data_file file = {
.mode = PERF_DATA_MODE_READ,
};
+ struct perf_evsel *pos;
int ret = hists__init();
+ bool freq_perf_info[FREQ_PERF_MAX] = {0};
if (ret < 0)
return ret;
@@ -821,6 +827,19 @@ repeat:
cpu_max_freq = session->header.env.cpu_max_freq;
msr_pmu_type = perf_header_find_pmu_type(session, "msr");
+ if (symbol_conf.show_freq_perf) {
+ perf_freq = perf_cpu_u = perf_core_busy = false;
+ evlist__for_each(session->evlist, pos) {
+ SET_FREQ_PERF_VALUE(pos, freq_perf_info, true);
+ }
+ if (HAS_FREQ(freq_perf_info))
+ perf_freq = true;
+ if (HAS_CPU_U(freq_perf_info))
+ perf_cpu_u = true;
+ if (HAS_CORE_BUSY(freq_perf_info))
+ perf_core_busy = true;
+ }
+
if (setup_sorting() < 0) {
if (sort_order)
parse_options_usage(report_usage, options, "s", 1);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 937b16a..87daab8 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -33,6 +33,7 @@ static inline unsigned long long rdclock(void)
extern const char *input_name;
extern bool perf_host, perf_guest;
+extern bool perf_freq, perf_cpu_u, perf_core_busy;
extern const char perf_version_string[];
void pthread__unblock_sigwinch(void);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 25d6083..949bbf2 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -17,7 +17,7 @@
static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
hpp_field_fn get_field, const char *fmt, int len,
- hpp_snprint_fn print_fn, bool fmt_percent)
+ hpp_snprint_fn print_fn, bool fmt_percent, bool single)
{
int ret;
struct hists *hists = he->hists;
@@ -36,7 +36,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry
*he,
} else
ret = hpp__call_print_fn(hpp, print_fn, fmt, len,
get_field(he));
- if (perf_evsel__is_group_event(evsel)) {
+ if (perf_evsel__is_group_event(evsel) && !single) {
int prev_idx, idx_delta;
struct hist_entry *pair;
int nr_members = evsel->nr_members;
@@ -109,10 +109,17 @@ int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp
*hpp,
const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
{
int len = fmt->user_len ?: fmt->len;
+ bool single = false;
+
+ if (symbol_conf.show_freq_perf &&
+ ((fmt == &perf_hpp__format[PERF_HPP__FREQ]) ||
+ (fmt == &perf_hpp__format[PERF_HPP__CPU_U]) ||
+ (fmt == &perf_hpp__format[PERF_HPP__CORE_BUSY])))
+ single = true;
if (symbol_conf.field_sep) {
return __hpp__fmt(hpp, he, get_field, fmtstr, 1,
- print_fn, fmt_percent);
+ print_fn, fmt_percent, single);
}
if (fmt_percent)
@@ -120,7 +127,7 @@ int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
else
len -= 1;
- return __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn,
fmt_percent);
+ return __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn,
fmt_percent, single);
}
int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
@@ -234,6 +241,30 @@ static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct
perf_hpp *hpp,
return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
}
+static int hpp__single_width_fn(struct perf_hpp_fmt *fmt,
+ struct perf_hpp *hpp __maybe_unused,
+ struct perf_evsel *evsel)
+{
+ int len = fmt->user_len ?: fmt->len;
+
+ if (symbol_conf.event_group && !symbol_conf.show_freq_perf)
+ len = max(len, evsel->nr_members * fmt->len);
+
+ if (len < (int)strlen(fmt->name))
+ len = strlen(fmt->name);
+
+ return len;
+}
+
+static int hpp__single_header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp
*hpp,
+ struct perf_evsel *evsel)
+{
+ int len = hpp__single_width_fn(fmt, hpp, evsel);
+
+ return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
+}
+
+
static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
{
va_list args;
@@ -363,6 +394,9 @@ HPP_PERCENT_ACC_FNS(overhead_acc, period)
HPP_RAW_FNS(samples, nr_events)
HPP_RAW_FNS(period, period)
+HPP_RAW_FNS(freq, freq)
+HPP_RAW_FNS(cpu_u, cpu_u)
+HPP_RAW_FNS(core_busy, core_busy)
static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *a __maybe_unused,
@@ -395,6 +429,17 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt
__maybe_unused,
.sort = hpp__sort_ ## _fn, \
}
+#define HPP__SINGLE_PRINT_FNS(_name, _fn) \
+ { \
+ .name = _name, \
+ .header = hpp__single_header_fn, \
+ .width = hpp__single_width_fn, \
+ .entry = hpp__entry_ ## _fn, \
+ .cmp = hpp__nop_cmp, \
+ .collapse = hpp__nop_cmp, \
+ .sort = hpp__sort_ ## _fn, \
+ }
+
#define HPP__PRINT_FNS(_name, _fn) \
{ \
.name = _name, \
@@ -414,7 +459,10 @@ struct perf_hpp_fmt perf_hpp__format[] = {
HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
HPP__PRINT_FNS("Samples", samples),
- HPP__PRINT_FNS("Period", period)
+ HPP__PRINT_FNS("Period", period),
+ HPP__SINGLE_PRINT_FNS("FREQ MHz", freq),
+ HPP__SINGLE_PRINT_FNS("CPU%", cpu_u),
+ HPP__SINGLE_PRINT_FNS("CORE_BUSY%", core_busy)
};
LIST_HEAD(perf_hpp__list);
@@ -485,6 +533,14 @@ void perf_hpp__init(void)
if (symbol_conf.show_total_period)
perf_hpp__column_enable(PERF_HPP__PERIOD);
+ if (symbol_conf.show_freq_perf) {
+ if (perf_freq)
+ perf_hpp__column_enable(PERF_HPP__FREQ);
+ if (perf_cpu_u)
+ perf_hpp__column_enable(PERF_HPP__CPU_U);
+ if (perf_core_busy)
+ perf_hpp__column_enable(PERF_HPP__CORE_BUSY);
+ }
/* prepend overhead field for backward compatiblity. */
list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list;
if (list_empty(list))
@@ -652,6 +708,9 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct
hists *hists)
return;
switch (idx) {
+ case PERF_HPP__CPU_U:
+ fmt->len = 5;
+ break;
case PERF_HPP__OVERHEAD:
case PERF_HPP__OVERHEAD_SYS:
case PERF_HPP__OVERHEAD_US:
@@ -661,6 +720,8 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct
hists *hists)
case PERF_HPP__OVERHEAD_GUEST_SYS:
case PERF_HPP__OVERHEAD_GUEST_US:
+ case PERF_HPP__FREQ:
+ case PERF_HPP__CORE_BUSY:
fmt->len = 9;
break;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 70bd557..ec64234 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -237,6 +237,9 @@ enum {
PERF_HPP__OVERHEAD_ACC,
PERF_HPP__SAMPLES,
PERF_HPP__PERIOD,
+ PERF_HPP__FREQ,
+ PERF_HPP__CPU_U,
+ PERF_HPP__CORE_BUSY,
PERF_HPP__MAX_INDEX
};
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7da36b1..c5010f5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1012,7 +1012,7 @@ static int deliver_sample_value(struct perf_evlist
*evlist,
return 0;
}
- if (perf_evsel__is_group_leader(sid->evsel)) {
+ if (symbol_conf.show_freq_perf &&
perf_evsel__is_group_leader(sid->evsel)) {
evsel = sid->evsel;
SET_FREQ_PERF_VALUE(evsel, sample->freq_perf_data,
sample->read.group.values[nr].value);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4c65a14..690e173 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1225,6 +1225,9 @@ static struct hpp_dimension hpp_sort_dimensions[] = {
DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"),
DIM(PERF_HPP__SAMPLES, "sample"),
DIM(PERF_HPP__PERIOD, "period"),
+ DIM(PERF_HPP__FREQ, "freq"),
+ DIM(PERF_HPP__CPU_U, "cpu_u"),
+ DIM(PERF_HPP__CORE_BUSY, "core_busy"),
};
#undef DIM
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fa0ccf3..7d70c89 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -106,7 +106,8 @@ struct symbol_conf {
filter_relative,
show_hist_headers,
branch_callstack,
- has_filter;
+ has_filter,
+ show_freq_perf;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index edc2d63..648b307 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -34,6 +34,8 @@ bool test_attr__enabled;
bool perf_host = true;
bool perf_guest = false;
+bool perf_freq, perf_cpu_u, perf_core_busy;
+
char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events";
void event_attr_init(struct perf_event_attr *attr)
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
