Skip to contentSkip to conversation

perf top: Support --group-sort-idx to change the sort order

PATCH Applied Jin Yao 3 participants 6 messages Mar 25, 2020 – Apr 4, 2020 perf events

lore
Share & tools
lore

Jin Yao

author
#0 lore raw

PATCH v2 1/2 perf top: Support --group-sort-idx to change the sort order

perf report has supported the option --group-sort-idx, which sorts the output by the event at the index n in event group.

For example,
perf record -e cycles,instructions,cache-misses
perf report --group --group-sort-idx 2 --stdio

The perf-report output is sorted by cache-misses.

This patch supports --group-sort-idx in perf-top.

For example,
perf top --group -e cycles,instructions,cache-misses --group-sort-idx 2

The perf-top output is sorted by cache-misses.

---
 tools/perf/Documentation/perf-top.txt | 5 +++++
 tools/perf/builtin-top.c              | 4 ++++
 2 files changed, 9 insertions(+)
tools/perf/Documentation/perf-top.txt +5 -0
index 324b6b53c86b..0e97dcef794d 100644
@@ -53,6 +53,11 @@ Default is to monitor all CPUS.
 --group::
         Put the counters into a counter group.
 
+--group-sort-idx::
+	Sort the output by the event at the index n in group. If n is invalid,
+	sort by the first event. It can support multiple groups with different
+	amount of events. WARNING: This should be used on grouped events.
+
 -F <freq>::
 --freq=<freq>::
 	Profile at this frequency. Use 'max' to use the currently maximum
tools/perf/builtin-top.c +4 -0
index d2539b793f9d..494c7b9a1022 100644
@@ -1545,6 +1545,10 @@ int cmd_top(int argc, const char **argv)
 			"number of thread to run event synthesize"),
 	OPT_BOOLEAN(0, "namespaces", &opts->record_namespaces,
 		    "Record namespaces events"),
+	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: should be used on grouped events."),
 	OPTS_EVSWITCH(&top.evswitch),
 	OPT_END()
 	};
Signature · 1 line
2.17.1
author
#1 lore raw

PATCH v2 2/2 perf top: support hotkey to change sort order

It would be nice if we can use a hotkey in perf top browser to select a event for sorting.

For example,
perf top --group -e cycles,instructions,cache-misses

Samples

                Overhead  Shared Object             Symbol
  40.03%  45.71%   0.03%  div                       [.] main
  20.46%  14.67%   0.21%  libc-2.27.so              [.] __random_r
  20.01%  19.54%   0.02%  libc-2.27.so              [.] __random
   9.68%  10.68%   0.00%  div                       [.] compute_flag
   4.32%   4.70%   0.00%  libc-2.27.so              [.] rand
   3.84%   3.43%   0.00%  div                       [.] rand@plt
   0.05%   0.05%   2.33%  libc-2.27.so              [.] __strcmp_sse2_unaligned
   0.04%   0.08%   2.43%  perf                      [.] perf_hpp__is_dynamic_en
   0.04%   0.02%   6.64%  perf                      [.] rb_next
   0.04%   0.01%   3.87%  perf                      [.] dso__find_symbol
   0.04%   0.04%   1.77%  perf                      [.] sort__dso_cmp

When user press hotkey '2' (event index, starting from 0), it indicates to sort output by the third event in group (cache-misses).

Samples

                Overhead  Shared Object               Symbol
   4.07%   1.28%   6.68%  perf                        [.] rb_next
   3.57%   3.98%   4.11%  perf                        [.] __hists__insert_output
   3.67%  11.24%   3.60%  perf                        [.] perf_hpp__is_dynamic_e
   3.67%   3.20%   3.20%  perf                        [.] hpp__sort_overhead
   0.81%   0.06%   3.01%  perf                        [.] dso__find_symbol
   1.62%   5.47%   2.51%  perf                        [.] hists__match
   2.70%   1.86%   2.47%  libc-2.27.so                [.] _int_malloc
   0.19%   0.00%   2.29%  [kernel]                    [k] copy_page
   0.41%   0.32%   1.98%  perf                        [.] hists__decay_entries
   1.84%   3.67%   1.68%  perf                        [.] sort__dso_cmp
   0.16%   0.00%   1.63%  [kernel]                    [k] clear_page_erms

Now the output is sorted by cache-misses.

v2:
---
Zero the history if hotkey is pressed.

---
 tools/perf/builtin-top.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)
tools/perf/builtin-top.c +9 -2
index 494c7b9a1022..29ddae7e1805 100644
@@ -616,6 +616,7 @@ static void *display_thread_tui(void *arg)
 		.arg		= top,
 		.refresh	= top->delay_secs,
 	};
+	int ret;
 
 	/* In order to read symbols from other namespaces perf to  needs to call
 	 * setns(2).  This isn't permitted if the struct_fs has multiple users.
@@ -626,6 +627,7 @@ static void *display_thread_tui(void *arg)
 
 	prctl(PR_SET_NAME, "perf-top-UI", 0, 0, 0);
 
+repeat:
 	perf_top__sort_new_samples(top);
 
 	/*
@@ -638,13 +640,18 @@ static void *display_thread_tui(void *arg)
 		hists->uid_filter_str = top->record_opts.target.uid_str;
 	}
 
-	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+	ret = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
 				      top->min_percent,
 				      &top->session->header.env,
 				      !top->record_opts.overwrite,
 				      &top->annotation_opts);
 
-	stop_top();
+	if (ret == K_RELOAD) {
+		top->zero = true;
+		goto repeat;
+	} else
+		stop_top();
+
 	return NULL;
 }
 
Signature · 1 line
2.17.1
author
#2 lore raw

Re: [PATCH v2 2/2] perf top: support hotkey to change sort order

Hi Arnaldo,

The v2 patch zeros the history when pressing the hotkey. Is it OK?

Thanks
Jin Yao

Quoted 90 lines · Jin Yao

It would be nice if we can use a hotkey in perf top browser to select a event for sorting.

For example,
perf top --group -e cycles,instructions,cache-misses

Samples

                 Overhead  Shared Object             Symbol
   40.03%  45.71%   0.03%  div                       [.] main
   20.46%  14.67%   0.21%  libc-2.27.so              [.] __random_r
   20.01%  19.54%   0.02%  libc-2.27.so              [.] __random
    9.68%  10.68%   0.00%  div                       [.] compute_flag
    4.32%   4.70%   0.00%  libc-2.27.so              [.] rand
    3.84%   3.43%   0.00%  div                       [.] rand@plt
    0.05%   0.05%   2.33%  libc-2.27.so              [.] __strcmp_sse2_unaligned
    0.04%   0.08%   2.43%  perf                      [.] perf_hpp__is_dynamic_en
    0.04%   0.02%   6.64%  perf                      [.] rb_next
    0.04%   0.01%   3.87%  perf                      [.] dso__find_symbol
    0.04%   0.04%   1.77%  perf                      [.] sort__dso_cmp

When user press hotkey '2' (event index, starting from 0), it indicates to sort output by the third event in group (cache-misses).

Samples

                 Overhead  Shared Object               Symbol
    4.07%   1.28%   6.68%  perf                        [.] rb_next
    3.57%   3.98%   4.11%  perf                        [.] __hists__insert_output
    3.67%  11.24%   3.60%  perf                        [.] perf_hpp__is_dynamic_e
    3.67%   3.20%   3.20%  perf                        [.] hpp__sort_overhead
    0.81%   0.06%   3.01%  perf                        [.] dso__find_symbol
    1.62%   5.47%   2.51%  perf                        [.] hists__match
    2.70%   1.86%   2.47%  libc-2.27.so                [.] _int_malloc
    0.19%   0.00%   2.29%  [kernel]                    [k] copy_page
    0.41%   0.32%   1.98%  perf                        [.] hists__decay_entries
    1.84%   3.67%   1.68%  perf                        [.] sort__dso_cmp
    0.16%   0.00%   1.63%  [kernel]                    [k] clear_page_erms

Now the output is sorted by cache-misses.

v2:
---
Zero the history if hotkey is pressed.

---
  tools/perf/builtin-top.c | 11 +++++++++--
  1 file changed, 9 insertions(+), 2 deletions(-)
tools/perf/builtin-top.c +9 -2
index 494c7b9a1022..29ddae7e1805 100644
@@ -616,6 +616,7 @@ static void *display_thread_tui(void *arg)
  		.arg		= top,
  		.refresh	= top->delay_secs,
  	};
+	int ret;
 
  	/* In order to read symbols from other namespaces perf to  needs to call
  	 * setns(2).  This isn't permitted if the struct_fs has multiple users.
@@ -626,6 +627,7 @@ static void *display_thread_tui(void *arg)
 
  	prctl(PR_SET_NAME, "perf-top-UI", 0, 0, 0);
 
+repeat:
  	perf_top__sort_new_samples(top);
 
  	/*
@@ -638,13 +640,18 @@ static void *display_thread_tui(void *arg)
  		hists->uid_filter_str = top->record_opts.target.uid_str;
  	}
 
-	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+	ret = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
  				      top->min_percent,
  				      &top->session->header.env,
  				      !top->record_opts.overwrite,
  				      &top->annotation_opts);
 
-	stop_top();
+	if (ret == K_RELOAD) {
+		top->zero = true;
+		goto repeat;
+	} else
+		stop_top();
+
  	return NULL;
  }
 
#3 lore raw

Re: [PATCH v2 2/2] perf top: support hotkey to change sort order

Em Mon, Mar 30, 2020 at 08:43:47AM +0800, Jin, Yao escreveu:

Quoted 3 lines

Hi Arnaldo,

The v2 patch zeros the history when pressing the hotkey. Is it OK?

Yeah, I've applied it to my perf/core branch.

Thanks,

- Arnaldo

Quoted 87 lines

Thanks
Jin Yao

Quoted 83 lines · Jin Yao

It would be nice if we can use a hotkey in perf top browser to select a event for sorting.

For example,
perf top --group -e cycles,instructions,cache-misses

Samples

                 Overhead  Shared Object             Symbol
   40.03%  45.71%   0.03%  div                       [.] main
   20.46%  14.67%   0.21%  libc-2.27.so              [.] __random_r
   20.01%  19.54%   0.02%  libc-2.27.so              [.] __random
    9.68%  10.68%   0.00%  div                       [.] compute_flag
    4.32%   4.70%   0.00%  libc-2.27.so              [.] rand
    3.84%   3.43%   0.00%  div                       [.] rand@plt
    0.05%   0.05%   2.33%  libc-2.27.so              [.] __strcmp_sse2_unaligned
    0.04%   0.08%   2.43%  perf                      [.] perf_hpp__is_dynamic_en
    0.04%   0.02%   6.64%  perf                      [.] rb_next
    0.04%   0.01%   3.87%  perf                      [.] dso__find_symbol
    0.04%   0.04%   1.77%  perf                      [.] sort__dso_cmp

When user press hotkey '2' (event index, starting from 0), it indicates to sort output by the third event in group (cache-misses).

Samples

                 Overhead  Shared Object               Symbol
    4.07%   1.28%   6.68%  perf                        [.] rb_next
    3.57%   3.98%   4.11%  perf                        [.] __hists__insert_output
    3.67%  11.24%   3.60%  perf                        [.] perf_hpp__is_dynamic_e
    3.67%   3.20%   3.20%  perf                        [.] hpp__sort_overhead
    0.81%   0.06%   3.01%  perf                        [.] dso__find_symbol
    1.62%   5.47%   2.51%  perf                        [.] hists__match
    2.70%   1.86%   2.47%  libc-2.27.so                [.] _int_malloc
    0.19%   0.00%   2.29%  [kernel]                    [k] copy_page
    0.41%   0.32%   1.98%  perf                        [.] hists__decay_entries
    1.84%   3.67%   1.68%  perf                        [.] sort__dso_cmp
    0.16%   0.00%   1.63%  [kernel]                    [k] clear_page_erms

Now the output is sorted by cache-misses.

v2:
---
Zero the history if hotkey is pressed.

---
  tools/perf/builtin-top.c | 11 +++++++++--
  1 file changed, 9 insertions(+), 2 deletions(-)
tools/perf/builtin-top.c +9 -2
index 494c7b9a1022..29ddae7e1805 100644
@@ -616,6 +616,7 @@ static void *display_thread_tui(void *arg)
  		.arg		= top,
  		.refresh	= top->delay_secs,
  	};
+	int ret;
  	/* In order to read symbols from other namespaces perf to  needs to call
  	 * setns(2).  This isn't permitted if the struct_fs has multiple users.
@@ -626,6 +627,7 @@ static void *display_thread_tui(void *arg)
  	prctl(PR_SET_NAME, "perf-top-UI", 0, 0, 0);
+repeat:
  	perf_top__sort_new_samples(top);
  	/*
@@ -638,13 +640,18 @@ static void *display_thread_tui(void *arg)
  		hists->uid_filter_str = top->record_opts.target.uid_str;
  	}
-	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+	ret = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
  				      top->min_percent,
  				      &top->session->header.env,
  				      !top->record_opts.overwrite,
  				      &top->annotation_opts);
-	stop_top();
+	if (ret == K_RELOAD) {
+		top->zero = true;
+		goto repeat;
+	} else
+		stop_top();
+
  	return NULL;
  }
 
Signature · 1 line
- Arnaldo
merge bot Applied
#4 lore raw

[tip: perf/urgent] perf top: Support hotkey to change sort order

In reply to Jin Yao
The following commit has been merged into the perf/urgent branch of tip:

The following commit has been merged into the perf/urgent branch of tip:

Commit-ID:     2605af0f32d1bf434dd6819732c7851a97f5cbc0
Gitweb:        https://git.kernel.org/tip/2605af0f32d1bf434dd6819732c7851a97f5cbc0
Author:        Jin Yao <[email protected]>
AuthorDate:    Wed, 25 Mar 2020 06:07:11 +08:00
Committer:     Arnaldo Carvalho de Melo <[email protected]>
CommitterDate: Fri, 03 Apr 2020 09:37:55 -03:00

perf top: Support hotkey to change sort order

It would be nice if we can use a hotkey in perf top browser to select a event for sorting.

For example:

  perf top --group -e cycles,instructions,cache-misses

Samples

                  Overhead  Shared Object             Symbol
    40.03%  45.71%   0.03%  div                       [.] main
    20.46%  14.67%   0.21%  libc-2.27.so              [.] __random_r
    20.01%  19.54%   0.02%  libc-2.27.so              [.] __random
     9.68%  10.68%   0.00%  div                       [.] compute_flag
     4.32%   4.70%   0.00%  libc-2.27.so              [.] rand
     3.84%   3.43%   0.00%  div                       [.] rand@plt
     0.05%   0.05%   2.33%  libc-2.27.so              [.] __strcmp_sse2_unaligned
     0.04%   0.08%   2.43%  perf                      [.] perf_hpp__is_dynamic_en
     0.04%   0.02%   6.64%  perf                      [.] rb_next
     0.04%   0.01%   3.87%  perf                      [.] dso__find_symbol
     0.04%   0.04%   1.77%  perf                      [.] sort__dso_cmp

When user press hotkey '2' (event index, starting from 0), it indicates to sort output by the third event in group (cache-misses).

Samples

                  Overhead  Shared Object               Symbol
     4.07%   1.28%   6.68%  perf                        [.] rb_next
     3.57%   3.98%   4.11%  perf                        [.] __hists__insert_output
     3.67%  11.24%   3.60%  perf                        [.] perf_hpp__is_dynamic_e
     3.67%   3.20%   3.20%  perf                        [.] hpp__sort_overhead
     0.81%   0.06%   3.01%  perf                        [.] dso__find_symbol
     1.62%   5.47%   2.51%  perf                        [.] hists__match
     2.70%   1.86%   2.47%  libc-2.27.so                [.] _int_malloc
     0.19%   0.00%   2.29%  [kernel]                    [k] copy_page
     0.41%   0.32%   1.98%  perf                        [.] hists__decay_entries
     1.84%   3.67%   1.68%  perf                        [.] sort__dso_cmp
     0.16%   0.00%   1.63%  [kernel]                    [k] clear_page_erms

Now the output is sorted by cache-misses.

v2:
---
Zero the history if hotkey is pressed.

---
 tools/perf/builtin-top.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)
tools/perf/builtin-top.c +9 -2
index 9ff7943..289cf83 100644
@@ -616,6 +616,7 @@ static void *display_thread_tui(void *arg)
 		.arg		= top,
 		.refresh	= top->delay_secs,
 	};
+	int ret;
 
 	/* In order to read symbols from other namespaces perf to  needs to call
 	 * setns(2).  This isn't permitted if the struct_fs has multiple users.
@@ -626,6 +627,7 @@ static void *display_thread_tui(void *arg)
 
 	prctl(PR_SET_NAME, "perf-top-UI", 0, 0, 0);
 
+repeat:
 	perf_top__sort_new_samples(top);
 
 	/*
@@ -638,13 +640,18 @@ static void *display_thread_tui(void *arg)
 		hists->uid_filter_str = top->record_opts.target.uid_str;
 	}
 
-	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+	ret = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
 				      top->min_percent,
 				      &top->session->header.env,
 				      !top->record_opts.overwrite,
 				      &top->annotation_opts);
 
-	stop_top();
+	if (ret == K_RELOAD) {
+		top->zero = true;
+		goto repeat;
+	} else
+		stop_top();
+
 	return NULL;
 }
 
merge bot Applied
#5 lore raw
In reply to Jin Yao
The following commit has been merged into the perf/urgent branch of tip:

The following commit has been merged into the perf/urgent branch of tip:

Commit-ID:     df7deb2cceef0546ab2115702da3421b7c61a8c0
Gitweb:        https://git.kernel.org/tip/df7deb2cceef0546ab2115702da3421b7c61a8c0
Author:        Jin Yao <[email protected]>
AuthorDate:    Wed, 25 Mar 2020 06:07:10 +08:00
Committer:     Arnaldo Carvalho de Melo <[email protected]>
CommitterDate: Fri, 03 Apr 2020 09:37:55 -03:00

perf top: Support --group-sort-idx to change the sort order

'perf report' supports the option --group-sort-idx, which sorts the output by the event at the index n in event group.

For example:

  perf record -e cycles,instructions,cache-misses
  perf report --group --group-sort-idx 2 --stdio

The perf-report output is sorted by cache-misses.

This patch supports --group-sort-idx in perf-top.

For example:

  perf top --group -e cycles,instructions,cache-misses --group-sort-idx 2

The perf-top output is sorted by cache-misses.

---
 tools/perf/Documentation/perf-top.txt | 5 +++++
 tools/perf/builtin-top.c              | 4 ++++
 2 files changed, 9 insertions(+)
tools/perf/Documentation/perf-top.txt +5 -0
index ddab103..487737a 100644
@@ -53,6 +53,11 @@ Default is to monitor all CPUS.
 --group::
         Put the counters into a counter group.
 
+--group-sort-idx::
+	Sort the output by the event at the index n in group. If n is invalid,
+	sort by the first event. It can support multiple groups with different
+	amount of events. WARNING: This should be used on grouped events.
+
 -F <freq>::
 --freq=<freq>::
 	Profile at this frequency. Use 'max' to use the currently maximum
tools/perf/builtin-top.c +4 -0
index 02ea2cf..9ff7943 100644
@@ -1560,6 +1560,10 @@ int cmd_top(int argc, const char **argv)
 		    "Record namespaces events"),
 	OPT_BOOLEAN(0, "all-cgroups", &opts->record_cgroup,
 		    "Record cgroup events"),
+	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: should be used on grouped events."),
 	OPTS_EVSWITCH(&top.evswitch),
 	OPT_END()
 	};