[PATCH v4 3/4] perf report: Display average IPC and IPC coverage per symbol
From: Jin Yao
Date: Thu Nov 29 2018 - 02:48:15 EST
Support displaying the average IPC and IPC coverage per symbol
in perf report TUI and stdio modes.
For example,
$ perf record -b ...
$ perf report -s symbol
Overhead Symbol IPC [IPC Coverage]
39.60% [.] __random 2.30 [ 54.8%]
18.02% [.] main 0.43 [ 54.3%]
14.21% [.] compute_flag 2.29 [100.0%]
14.16% [.] rand 0.36 [100.0%]
7.06% [.] __random_r 2.57 [ 70.5%]
6.85% [.] rand@plt 0.00 [ 0.0%]
Jiri Olsa <jolsa@xxxxxxxxxx> provides the patch to support the
stdio mode. I merge Jiri's code in this patch.
$ perf report -s symbol --stdio
# Overhead Symbol IPC [IPC Coverage]
# ........ ........................... ....................
#
39.60% [.] __random 2.30 [ 54.8%]
18.02% [.] main 0.43 [ 54.3%]
14.21% [.] compute_flag 2.29 [100.0%]
14.16% [.] rand 0.36 [100.0%]
7.06% [.] __random_r 2.57 [ 70.5%]
6.85% [.] rand@plt 0.00 [ 0.0%]
0.02% [k] run_timer_softirq 1.60 [ 57.2%]
The columns "IPC" and "[IPC Coverage]" are automatically enabled
when the sort-key "symbol" is specified. If the perf.data doesn't
contain timed LBR information, columns are filled with "-".
For example,
# Overhead Symbol IPC [IPC Coverage]
# ........ ........................... ....................
#
46.57% [.] main - -
17.60% [.] rand - -
15.84% [.] __random_r - -
11.90% [.] __random - -
6.50% [.] compute_flag - -
1.59% [.] rand@plt - -
0.00% [.] _dl_relocate_object - -
0.00% [k] tlb_flush_mmu - -
0.00% [k] perf_event_mmap - -
0.00% [k] native_sched_clock - -
0.00% [k] intel_pmu_handle_irq_v4 - -
0.00% [k] native_write_msr - -
v3:
---
Removed the sortkey 'ipc' from command-line. The columns "IPC"
and "[IPC Coverage]" are automatically enabled when "symbol"
is specified.
v2:
---
Merge in Jiri's patch to support stdio mode
Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
---
tools/perf/builtin-report.c | 26 ++++++++++++++++---
tools/perf/util/hist.h | 1 +
tools/perf/util/sort.c | 61 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/sort.h | 2 ++
4 files changed, 87 insertions(+), 3 deletions(-)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 257c9c1..4958095 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -85,6 +85,7 @@ struct report {
int socket_filter;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
struct branch_type_stat brtype_stat;
+ bool symbol_ipc;
};
static int report__config(const char *var, const char *value, void *cb)
@@ -129,7 +130,7 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
struct mem_info *mi;
struct branch_info *bi;
- if (!ui__has_annotation())
+ if (!ui__has_annotation() && !rep->symbol_ipc)
return 0;
hist__account_cycles(sample->branch_stack, al, sample,
@@ -174,7 +175,7 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
struct perf_evsel *evsel = iter->evsel;
int err;
- if (!ui__has_annotation())
+ if (!ui__has_annotation() && !rep->symbol_ipc)
return 0;
hist__account_cycles(sample->branch_stack, al, sample,
@@ -1133,6 +1134,7 @@ int cmd_report(int argc, const char **argv)
.mode = PERF_DATA_MODE_READ,
};
int ret = hists__init();
+ char sort_tmp[128];
if (ret < 0)
return ret;
@@ -1284,6 +1286,24 @@ int cmd_report(int argc, const char **argv)
else
use_browser = 0;
+ if (sort_order && strstr(sort_order, "ipc")) {
+ parse_options_usage(report_usage, options, "s", 1);
+ goto error;
+ }
+
+ if (sort_order && strstr(sort_order, "symbol")) {
+ if (sort__mode == SORT_MODE__BRANCH) {
+ snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s",
+ sort_order, "ipc_lbr");
+ report.symbol_ipc = true;
+ } else {
+ snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s",
+ sort_order, "ipc_null");
+ }
+
+ sort_order = sort_tmp;
+ }
+
if (setup_sorting(session->evlist) < 0) {
if (sort_order)
parse_options_usage(report_usage, options, "s", 1);
@@ -1311,7 +1331,7 @@ int cmd_report(int argc, const char **argv)
* so don't allocate extra space that won't be used in the stdio
* implementation.
*/
- if (ui__has_annotation()) {
+ if (ui__has_annotation() || report.symbol_ipc) {
ret = symbol__annotation_init();
if (ret < 0)
goto error;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 3badd7f..664b5ed 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -62,6 +62,7 @@ enum hist_column {
HISTC_TRACE,
HISTC_SYM_SIZE,
HISTC_DSO_SIZE,
+ HISTC_SYMBOL_IPC,
HISTC_NR_COLS, /* Last entry */
};
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index f96c005..0477935 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 +423,64 @@ 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->annotate2 && symbol__annotate2(sym, map, evsel,
+ &annotation__default_options, NULL) < 0) {
+ return 0;
+ }
+
+ 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);
+ }
+
+ snprintf(tmp, sizeof(tmp), "%-5.2f [%5.1f%%]", ipc, coverage);
+ return repsep_snprintf(bf, size, "%-*s", width, tmp);
+}
+
+struct sort_entry sort_sym_ipc = {
+ .se_header = "IPC [IPC Coverage]",
+ .se_cmp = sort__sym_cmp,
+ .se_snprintf = hist_entry__sym_ipc_snprintf,
+ .se_width_idx = HISTC_SYMBOL_IPC,
+};
+
+static int hist_entry__sym_ipc_null_snprintf(struct hist_entry *he
+ __maybe_unused,
+ char *bf, size_t size,
+ unsigned int width)
+{
+ char tmp[64];
+
+ snprintf(tmp, sizeof(tmp), "%-5s %2s", "-", "-");
+ return repsep_snprintf(bf, size, "%-*s", width, tmp);
+}
+
+struct sort_entry sort_sym_ipc_null = {
+ .se_header = "IPC [IPC Coverage]",
+ .se_cmp = sort__sym_cmp,
+ .se_snprintf = hist_entry__sym_ipc_null_snprintf,
+ .se_width_idx = HISTC_SYMBOL_IPC,
+};
+
/* --sort srcfile */
static char no_srcfile[1];
@@ -1574,6 +1633,7 @@ static struct sort_dimension common_sort_dimensions[] = {
DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size),
DIM(SORT_DSO_SIZE, "dso_size", sort_dso_size),
DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
+ DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null),
};
#undef DIM
@@ -1591,6 +1651,7 @@ static struct sort_dimension bstack_sort_dimensions[] = {
DIM(SORT_CYCLES, "cycles", sort_cycles),
DIM(SORT_SRCLINE_FROM, "srcline_from", sort_srcline_from),
DIM(SORT_SRCLINE_TO, "srcline_to", sort_srcline_to),
+ DIM(SORT_SYM_IPC, "ipc_lbr", sort_sym_ipc),
};
#undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index a97cf8e..130fe37 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -229,6 +229,7 @@ enum sort_type {
SORT_SYM_SIZE,
SORT_DSO_SIZE,
SORT_CGROUP_ID,
+ SORT_SYM_IPC_NULL,
/* branch stack specific sort keys */
__SORT_BRANCH_STACK,
@@ -242,6 +243,7 @@ enum sort_type {
SORT_CYCLES,
SORT_SRCLINE_FROM,
SORT_SRCLINE_TO,
+ SORT_SYM_IPC,
/* memory mode specific sort keys */
__SORT_MEMORY_MODE,
--
2.7.4