Skip to contentSkip to conversation

perf report: Change sort order by a specified event in group

PATCH Superseded Jin Yao 2 participants 7 messages Dec 11, 2019 perf events

v2 of 7 Superseded Latest is v7 →

lore
Share & tools
lore

Jin Yao

author
#0 lore raw

PATCH v2 1/3 perf report: Change sort order by a specified event in group

When performing "perf report --group", it shows the event group information together. By default, the output is sorted by the first event in group.

It would be nice for user to select any event for sorting. This patch introduces a new option "--group-sort-idx" to sort the output by the event at the index n in event group.

For example,

Before:

  # perf report --group --stdio

# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 12K of events 'cpu/instructions,period=2000003/, cpu/cpu-cycles,period=200003/, BR_MISP_RETIRED.ALL_BRANCHES:pp, cpu/event=0xc0,umask=1,cmask=1, # Event count (approx.): 6451235635
#

  #                         Overhead  Command    Shared Object            Symbol
  # ................................  .........  .......................  ...................................
  #
      92.19%  98.68%   0.00%  93.30%  mgen       mgen                     [.] LOOP1
       3.12%   0.29%   0.00%   0.16%  gsd-color  libglib-2.0.so.0.5600.4  [.] 0x0000000000049515
       1.56%   0.03%   0.00%   0.04%  gsd-color  libglib-2.0.so.0.5600.4  [.] 0x00000000000494b7
       1.56%   0.01%   0.00%   0.00%  gsd-color  libglib-2.0.so.0.5600.4  [.] 0x00000000000494ce
       1.56%   0.00%   0.00%   0.00%  mgen       [kernel.kallsyms]        [k] task_tick_fair
       0.00%   0.15%   0.00%   0.04%  perf       [kernel.kallsyms]        [k] smp_call_function_single
       0.00%   0.13%   0.00%   6.08%  swapper    [kernel.kallsyms]        [k] intel_idle
       0.00%   0.03%   0.00%   0.00%  gsd-color  libglib-2.0.so.0.5600.4  [.] g_main_context_check
       0.00%   0.03%   0.00%   0.00%  swapper    [kernel.kallsyms]        [k] apic_timer_interrupt
       ...

After:

  # perf report --group --stdio --group-sort-idx 3

# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 12K of events 'cpu/instructions,period=2000003/, cpu/cpu-cycles,period=200003/, BR_MISP_RETIRED.ALL_BRANCHES:pp, cpu/event=0xc0,umask=1,cmask=1, # Event count (approx.): 6451235635
#

  #                         Overhead  Command    Shared Object            Symbol
  # ................................  .........  .......................  ...................................
  #
      92.19%  98.68%   0.00%  93.30%  mgen       mgen                     [.] LOOP1
       0.00%   0.13%   0.00%   6.08%  swapper    [kernel.kallsyms]        [k] intel_idle
       3.12%   0.29%   0.00%   0.16%  gsd-color  libglib-2.0.so.0.5600.4  [.] 0x0000000000049515
       0.00%   0.00%   0.00%   0.06%  swapper    [kernel.kallsyms]        [k] hrtimer_start_range_ns
       1.56%   0.03%   0.00%   0.04%  gsd-color  libglib-2.0.so.0.5600.4  [.] 0x00000000000494b7
       0.00%   0.15%   0.00%   0.04%  perf       [kernel.kallsyms]        [k] smp_call_function_single
       0.00%   0.00%   0.00%   0.02%  mgen       [kernel.kallsyms]        [k] update_curr
       0.00%   0.00%   0.00%   0.02%  mgen       [kernel.kallsyms]        [k] apic_timer_interrupt
       0.00%   0.00%   0.00%   0.02%  mgen       [kernel.kallsyms]        [k] native_apic_msr_eoi_write
       0.00%   0.00%   0.00%   0.02%  mgen       [kernel.kallsyms]        [k] __update_load_avg_se
       0.00%   0.00%   0.00%   0.02%  mgen       [kernel.kallsyms]        [k] scheduler_tick

Now the output is sorted by the fourth event in group.

v2:
---
No change

---
 tools/perf/Documentation/perf-report.txt |   4 +
 tools/perf/builtin-report.c              |  10 +++
 tools/perf/ui/hist.c                     | 110 +++++++++++++++++++----
 tools/perf/util/symbol_conf.h            |   1 +
 4 files changed, 110 insertions(+), 15 deletions(-)
tools/perf/Documentation/perf-report.txt +4 -0
index 8dbe2119686a..9ade613ef020 100644
@@ -371,6 +371,10 @@ OPTIONS
 	Show event group information together. It forces group output also
 	if there are no groups defined in data file.
 
+--group-sort-idx::
+	Sort the output by the event at the index n in group. If n is invalid,
+	sort by the first event. WARNING: This should be used with --group.
+
 --demangle::
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.
tools/perf/builtin-report.c +10 -0
index 387311c67264..729cf7611d8a 100644
@@ -1210,6 +1210,10 @@ int cmd_report(int argc, const char **argv)
 		    "Show a column with the sum of periods"),
 	OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, &report.group_set,
 		    "Show event group information together"),
+	OPT_INTEGER(0, "group-sort-idx", &symbol_conf.group_sort_idx,
+		    "Sort the output by the event at the index n in group. "
+		    "If n is invalid, sort by the first event. "
+		    "WARNING: use only with --group."),
 	OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
 		    "use branch records for per branch histogram filling",
 		    parse_branch_mode),
@@ -1302,6 +1306,12 @@ int cmd_report(int argc, const char **argv)
 		return -EINVAL;
 	}
 
+	if (symbol_conf.group_sort_idx &&
+	    (!symbol_conf.event_group || !report.group_set)) {
+		parse_options_usage(NULL, options, "group-sort-idx", 0);
+		return -EINVAL;
+	}
+
 	if (report.inverted_callchain)
 		callchain_param.order = ORDER_CALLER;
 	if (symbol_conf.cumulate_callchain && !callchain_param.order_set)
tools/perf/ui/hist.c +95 -15

132 lines not on this page · raw message

tools/perf/util/symbol_conf.h +1 -0
index 10f1ec3e0349..b916afb95ec5 100644
@@ -73,6 +73,7 @@ struct symbol_conf {
 	const char	*symfs;
 	int		res_sample;
 	int		pad_output_len_dso;
+	int		group_sort_idx;
 };
 
 extern struct symbol_conf symbol_conf;
Signature · 1 line
2.17.1
author
#1 lore raw

PATCH v2 2/3 perf report: Support a new key to reload the browser

Sometimes we may need to reload the browser to update the output since some options are changed.

This patch creates a new key K_RELOAD. Once the __cmd_report() returns K_RELOAD, it would repeat the whole process, such as, read samples from data file, sort the data and display in the browser.

v2:
---
This is a new patch created in v2.

---
 tools/perf/builtin-report.c | 4 ++--
 tools/perf/ui/keysyms.h     | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)
tools/perf/builtin-report.c +2 -2
index 729cf7611d8a..02178fc54d67 100644
@@ -635,7 +635,7 @@ static int report__browse_hists(struct report *rep)
 		 * Usually "ret" is the last pressed key, and we only
 		 * care if the key notifies us to switch data file.
 		 */
-		if (ret != K_SWITCH_INPUT_DATA)
+		if (ret != K_SWITCH_INPUT_DATA && ret != K_RELOAD)
 			ret = 0;
 		break;
 	case 2:
@@ -1538,7 +1538,7 @@ int cmd_report(int argc, const char **argv)
 	sort__setup_elide(stdout);
 
 	ret = __cmd_report(&report);
-	if (ret == K_SWITCH_INPUT_DATA) {
+	if (ret == K_SWITCH_INPUT_DATA || ret == K_RELOAD) {
 		perf_session__delete(session);
 		goto repeat;
 	} else
tools/perf/ui/keysyms.h +1 -0
index fbfac29077f2..04cc4e5c031f 100644
@@ -25,5 +25,6 @@
 #define K_ERROR	 -2
 #define K_RESIZE -3
 #define K_SWITCH_INPUT_DATA -4
+#define K_RELOAD -5
 
 #endif /* _PERF_KEYSYMS_H_ */
Signature · 1 line
2.17.1
author
#2 lore raw

PATCH v2 3/3 perf report: support hotkey to let user select any event for sorting

In reply to Jin Yao

When performing "perf report --group", it shows the event group information together. In previous patch, we have supported a new option "--group-sort-idx" to sort the output by the event at the index n in event group.

It would be nice if we can use a hotkey in browser to select a event to sort.

For example,

  # perf report --group

Samples: 12K of events 'cpu/instructions,period=2000003/, cpu/cpu-cycles,period=200003/, ...

                        Overhead  Command    Shared Object            Symbol
  92.19%  98.68%   0.00%  93.30%  mgen       mgen                     [.] LOOP1
   3.12%   0.29%   0.00%   0.16%  gsd-color  libglib-2.0.so.0.5600.4  [.] 0x0000000000049515
   1.56%   0.03%   0.00%   0.04%  gsd-color  libglib-2.0.so.0.5600.4  [.] 0x00000000000494b7
   1.56%   0.01%   0.00%   0.00%  gsd-color  libglib-2.0.so.0.5600.4  [.] 0x00000000000494ce
   1.56%   0.00%   0.00%   0.00%  mgen       [kernel.kallsyms]        [k] task_tick_fair
   0.00%   0.15%   0.00%   0.04%  perf       [kernel.kallsyms]        [k] smp_call_function_single
   0.00%   0.13%   0.00%   6.08%  swapper    [kernel.kallsyms]        [k] intel_idle
   0.00%   0.03%   0.00%   0.00%  gsd-color  libglib-2.0.so.0.5600.4  [.] g_main_context_check
   0.00%   0.03%   0.00%   0.00%  swapper    [kernel.kallsyms]        [k] apic_timer_interrupt
   0.00%   0.03%   0.00%   0.00%  swapper    [kernel.kallsyms]        [k] check_preempt_curr

When user press hotkey '3' (event index, starting from 0), it indicates to sort output by the forth event in group.

Samples: 12K of events 'cpu/instructions,period=2000003/, cpu/cpu-cycles,period=200003/, ...

                        Overhead  Command    Shared Object            Symbol
  92.19%  98.68%   0.00%  93.30%  mgen       mgen                     [.] LOOP1
   0.00%   0.13%   0.00%   6.08%  swapper    [kernel.kallsyms]        [k] intel_idle
   3.12%   0.29%   0.00%   0.16%  gsd-color  libglib-2.0.so.0.5600.4  [.] 0x0000000000049515
   0.00%   0.00%   0.00%   0.06%  swapper    [kernel.kallsyms]        [k] hrtimer_start_range_ns
   1.56%   0.03%   0.00%   0.04%  gsd-color  libglib-2.0.so.0.5600.4  [.] 0x00000000000494b7
   0.00%   0.15%   0.00%   0.04%  perf       [kernel.kallsyms]        [k] smp_call_function_single
   0.00%   0.00%   0.00%   0.02%  mgen       [kernel.kallsyms]        [k] update_curr
   0.00%   0.00%   0.00%   0.02%  mgen       [kernel.kallsyms]        [k] apic_timer_interrupt
   0.00%   0.00%   0.00%   0.02%  mgen       [kernel.kallsyms]        [k] native_apic_msr_eoi_write
   0.00%   0.00%   0.00%   0.02%  mgen       [kernel.kallsyms]        [k] __update_load_avg_se

v2:
---
1. Report warning at helpline when index is invalid.
2. Report warning at helpline when it's not group event.
3. Use "case '0' ... '9'" to refine the code
4. Split K_RELOAD implementation to another patch.

---
 tools/perf/ui/browsers/hists.c | 25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)
tools/perf/ui/browsers/hists.c +24 -1
index d4d3558fdef4..b9288a1385dd 100644
@@ -2876,7 +2876,8 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
 	"s             Switch to another data file in PWD\n"
 	"t             Zoom into current Thread\n"
 	"V             Verbose (DSO names in callchains, etc)\n"
-	"/             Filter symbol by name";
+	"/             Filter symbol by name\n"
+	"0-9           Sort by event n in group";
 	static const char top_help[] = HIST_BROWSER_HELP_COMMON
 	"P             Print histograms to perf.hist.N\n"
 	"t             Zoom into current Thread\n"
@@ -2937,6 +2938,28 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
 			 * go to the next or previous
 			 */
 			goto out_free_stack;
+		case '0' ... '9':
+			if (!symbol_conf.event_group ||
+			    evsel->core.nr_members < 2) {
+				snprintf(buf, sizeof(buf),
+					 "Sort by index only available with group events!");
+				helpline = buf;
+				continue;
+			}
+
+			symbol_conf.group_sort_idx = key - '0';
+
+			if (symbol_conf.group_sort_idx >= evsel->core.nr_members) {
+				snprintf(buf, sizeof(buf),
+					 "Max event group index to sort is %d (index from 0 to %d)",
+					 evsel->core.nr_members - 1,
+					 evsel->core.nr_members - 1);
+				helpline = buf;
+				continue;
+			}
+
+			key = K_RELOAD;
+			goto out_free_stack;
 		case 'a':
 			if (!hists__has(hists, sym)) {
 				ui_browser__warning(&browser->b, delay_secs * 2,
Signature · 1 line
2.17.1
#3 lore raw
In reply to Jin Yao

On Wed, Dec 11, 2019 at 03:30:34PM +0800, Jin Yao wrote:

SNIP

Quoted 29 lines
tools/perf/ui/hist.c +29 -0
+
+static int __hpp__group_sort_idx(struct hist_entry *a, struct hist_entry *b,
+				 hpp_field_fn get_field, int idx)
+{
+	struct evsel *evsel = hists_to_evsel(a->hists);
+	u64 *fields_a, *fields_b;
+	int cmp, nr_members, ret, i;
+
+	cmp = field_cmp(get_field(a), get_field(b));
+	if (!perf_evsel__is_group_event(evsel))
+		return cmp;
+
+	nr_members = evsel->core.nr_members;
+	ret = pair_fields_alloc(a, b, get_field, nr_members,
+			      &fields_a, &fields_b);
+	if (ret) {
+		ret = cmp;
+		goto out;
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		if (i == idx) {
+			ret = field_cmp(fields_a[i], fields_b[i]);
+			if (ret)
+				goto out;
+		}
+	}
+
+	if (cmp) {

tools/perf/ui/hist.c static int field_cmp(u64 field_a, u64 field_b) · line 231

Quoted 10 lines
tools/perf/ui/hist.c +10 -0
+		ret = cmp;
+		goto out;
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		if (i != idx) {
+			ret = field_cmp(fields_a[i], fields_b[i]);
+			if (ret)
+				goto out;
+		}

hi,
I'm missing why we compare the fields for 2nd time in here

thanks,
jirka

author
#4 lore raw
Quoted 47 lines · Jiri Olsa

On Wed, Dec 11, 2019 at 03:30:34PM +0800, Jin Yao wrote:

SNIP

Quoted 29 lines
tools/perf/ui/hist.c +29 -0
+
+static int __hpp__group_sort_idx(struct hist_entry *a, struct hist_entry *b,
+				 hpp_field_fn get_field, int idx)
+{
+	struct evsel *evsel = hists_to_evsel(a->hists);
+	u64 *fields_a, *fields_b;
+	int cmp, nr_members, ret, i;
+
+	cmp = field_cmp(get_field(a), get_field(b));
+	if (!perf_evsel__is_group_event(evsel))
+		return cmp;
+
+	nr_members = evsel->core.nr_members;
+	ret = pair_fields_alloc(a, b, get_field, nr_members,
+			      &fields_a, &fields_b);
+	if (ret) {
+		ret = cmp;
+		goto out;
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		if (i == idx) {
+			ret = field_cmp(fields_a[i], fields_b[i]);
+			if (ret)
+				goto out;
+		}
+	}
+
+	if (cmp) {

tools/perf/ui/hist.c static int field_cmp(u64 field_a, u64 field_b) · line 231

Quoted 10 lines
tools/perf/ui/hist.c +10 -0
+		ret = cmp;
+		goto out;
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		if (i != idx) {
+			ret = field_cmp(fields_a[i], fields_b[i]);
+			if (ret)
+				goto out;
+		}

hi,
I'm missing why we compare the fields for 2nd time in here

Quoted 3 lines

thanks,
jirka

Hi,

I think we may continue comparing the remaining of fields if the index field is equal. :)

Thanks
Jin Yao

#5 lore raw
Quoted 50 lines · Yao
Quoted 47 lines · Jiri Olsa

On Wed, Dec 11, 2019 at 03:30:34PM +0800, Jin Yao wrote:

SNIP

Quoted 29 lines
tools/perf/ui/hist.c +29 -0
+
+static int __hpp__group_sort_idx(struct hist_entry *a, struct hist_entry *b,
+				 hpp_field_fn get_field, int idx)
+{
+	struct evsel *evsel = hists_to_evsel(a->hists);
+	u64 *fields_a, *fields_b;
+	int cmp, nr_members, ret, i;
+
+	cmp = field_cmp(get_field(a), get_field(b));
+	if (!perf_evsel__is_group_event(evsel))
+		return cmp;
+
+	nr_members = evsel->core.nr_members;
+	ret = pair_fields_alloc(a, b, get_field, nr_members,
+			      &fields_a, &fields_b);
+	if (ret) {
+		ret = cmp;
+		goto out;
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		if (i == idx) {
+			ret = field_cmp(fields_a[i], fields_b[i]);
+			if (ret)
+				goto out;
+		}
+	}
+
+	if (cmp) {

tools/perf/ui/hist.c static int field_cmp(u64 field_a, u64 field_b) · line 231

Quoted 10 lines
tools/perf/ui/hist.c +10 -0
+		ret = cmp;
+		goto out;
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		if (i != idx) {
+			ret = field_cmp(fields_a[i], fields_b[i]);
+			if (ret)
+				goto out;
+		}

hi,
I'm missing why we compare the fields for 2nd time in here

Quoted 8 lines
Quoted 3 lines

thanks,
jirka

Hi,

I think we may continue comparing the remaining of fields if the index field is equal. :)

aah, I missed it's actualy == used in the first one ;-)

why don't you just call it directly?

	ret = field_cmp(fields_a[idx], fields_b[idx])
	if (ret)
		goto out;

jirka

author
#6 lore raw
Quoted 62 lines · Jiri Olsa
Quoted 50 lines · Yao
Quoted 47 lines · Jiri Olsa

On Wed, Dec 11, 2019 at 03:30:34PM +0800, Jin Yao wrote:

SNIP

Quoted 29 lines
tools/perf/ui/hist.c +29 -0
+
+static int __hpp__group_sort_idx(struct hist_entry *a, struct hist_entry *b,
+				 hpp_field_fn get_field, int idx)
+{
+	struct evsel *evsel = hists_to_evsel(a->hists);
+	u64 *fields_a, *fields_b;
+	int cmp, nr_members, ret, i;
+
+	cmp = field_cmp(get_field(a), get_field(b));
+	if (!perf_evsel__is_group_event(evsel))
+		return cmp;
+
+	nr_members = evsel->core.nr_members;
+	ret = pair_fields_alloc(a, b, get_field, nr_members,
+			      &fields_a, &fields_b);
+	if (ret) {
+		ret = cmp;
+		goto out;
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		if (i == idx) {
+			ret = field_cmp(fields_a[i], fields_b[i]);
+			if (ret)
+				goto out;
+		}
+	}
+
+	if (cmp) {

tools/perf/ui/hist.c static int field_cmp(u64 field_a, u64 field_b) · line 231

Quoted 10 lines
tools/perf/ui/hist.c +10 -0
+		ret = cmp;
+		goto out;
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		if (i != idx) {
+			ret = field_cmp(fields_a[i], fields_b[i]);
+			if (ret)
+				goto out;
+		}

hi,
I'm missing why we compare the fields for 2nd time in here

Quoted 8 lines
Quoted 3 lines

thanks,
jirka

Hi,

I think we may continue comparing the remaining of fields if the index field is equal. :)

aah, I missed it's actualy == used in the first one ;-)

Quoted 8 lines

why don't you just call it directly?

	ret = field_cmp(fields_a[idx], fields_b[idx])
	if (ret)
		goto out;

jirka

Oh, yes, we can use simpler code. For example,

	if (idx >= 1 && idx < nr_members) {
		ret = field_cmp(fields_a[idx], fields_b[idx]);
		if (ret)
			goto out;
	}

Thanks
Jin Yao