perf top: Collapse and resort all evsels in a group

And link them, i.e. find the hist entries in the non-leader events and
link them to the ones in the leader.

This should be the same thing already done for the 'perf report' case,
but now we do it periodically.

With this in place we get percentages in from the second overhead column
on, not just on the first (the leader).

Try it using:

  perf top --stdio -e '{cycles,instructions}'

You should see something like:

   PerfTop:   20776 irqs/sec  kernel:68.7%  exact:  0.0% lost: 0/0 drop: 0/0 [cycles],  (all, 8 CPUs)
  ---------------------------------------------------------------------------------------------------

     4.44%   0.44%  [kernel]                 [k] do_syscall_64
     2.27%   0.17%  [kernel]                 [k] entry_SYSCALL_64
     1.73%   0.27%  [kernel]                 [k] syscall_return_via_sysret
     1.60%   0.91%  [kernel]                 [k] _raw_spin_lock_irqsave
     1.45%   3.53%  libglib-2.0.so.0.6000.4  [.] g_string_insert_unichar
     1.39%   0.21%  [kernel]                 [k] copy_user_enhanced_fast_string
     1.26%   1.15%  [kernel]                 [k] psi_task_change
     1.16%   0.14%  libpixman-1.so.0.38.0    [.] 0x000000000006f403
     1.00%   0.32%  [kernel]                 [k] __sched_text_start
     0.97%   2.11%  [kernel]                 [k] n_tty_write
     0.96%   0.04%  [kernel]                 [k] queued_spin_lock_slowpath
     0.93%   0.88%  [kernel]                 [k] menu_select
     0.87%   0.14%  [kernel]                 [k] try_to_wake_up
     0.77%   0.10%  libpixman-1.so.0.38.0    [.] 0x000000000006f40b
     0.73%   0.09%  libpixman-1.so.0.38.0    [.] 0x000000000006f413
     0.69%   0.48%  libc-2.29.so             [.] __memmove_avx_unaligned_erms
     0.68%   0.29%  [kernel]                 [k] _raw_spin_lock_irq
     0.61%   0.04%  libpixman-1.so.0.38.0    [.] 0x000000000006f423
     0.60%   0.37%  [kernel]                 [k] native_sched_clock
     0.57%   0.23%  [kernel]                 [k] do_idle
     0.57%   0.23%  [kernel]                 [k] __fget
     0.56%   0.30%  [kernel]                 [k] __switch_to_asm
     0.56%   0.00%  libc-2.29.so             [.] __memset_avx2_erms
     0.52%   0.32%  [kernel]                 [k] _raw_spin_lock
     0.49%   0.24%  [kernel]                 [k] n_tty_poll
     0.49%   0.54%  libglib-2.0.so.0.6000.4  [.] g_mutex_lock
     0.48%   0.62%  [kernel]                 [k] _raw_spin_unlock_irqrestore
     0.47%   0.27%  [kernel]                 [k] __switch_to
     0.47%   0.25%  [kernel]                 [k] pick_next_task_fair
     0.45%   0.17%  [kernel]                 [k] filldir64
     0.40%   0.16%  [kernel]                 [k] update_rq_clock
     0.39%   0.19%  [kernel]                 [k] enqueue_task_fair
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-uw8cjeifxvjpkjp6x2iil0ar@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 94e34853a2380a61590b37482a6754ab2be43cf0..78e7efc597a685e4e8a2b93ad23756a1e70b947d 100644 (file)
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -264,6 +264,30 @@ static void perf_top__show_details(struct perf_top *top)
        pthread_mutex_unlock(&notes->lock);
 }
 
+static void evlist__resort_hists(struct evlist *evlist)
+{
+       struct evsel *pos;
+
+       evlist__for_each_entry(evlist, pos) {
+               struct hists *hists = evsel__hists(pos);
+
+               hists__collapse_resort(hists, NULL);
+
+               /* Non-group events are considered as leader */
+               if (symbol_conf.event_group &&
+                   !perf_evsel__is_group_leader(pos)) {
+                       struct hists *leader_hists = evsel__hists(pos->leader);
+
+                       hists__match(leader_hists, hists);
+                       hists__link(leader_hists, hists);
+               }
+       }
+
+       evlist__for_each_entry(evlist, pos) {
+               perf_evsel__output_resort(pos, NULL);
+       }
+}
+
 static void perf_top__print_sym_table(struct perf_top *top)
 {
        char bf[160];
@@ -304,8 +328,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
                }
        }
 
-       hists__collapse_resort(hists, NULL);
-       perf_evsel__output_resort(evsel, NULL);
+       evlist__resort_hists(top->evlist);
 
        hists__output_recalc_col_len(hists, top->print_entries - printed);
        putchar('\n');
@@ -570,8 +593,7 @@ static void perf_top__sort_new_samples(void *arg)
                }
        }
 
-       hists__collapse_resort(hists, NULL);
-       perf_evsel__output_resort(evsel, NULL);
+       evlist__resort_hists(t->evlist);
 
        if (t->lost || t->drop)
                pr_warning("Too slow to read ring buffer (change period (-c/-F) or limit CPUs (-C)\n");