perf top: Reduce display overhead

Iterate over the symbol table once per display interval, and
copy/sort/tally/decay only those symbols which are active.

Before:

 top - 10:14:53 up  4:08, 17 users,  load average: 1.17, 1.53, 1.49
 Tasks: 273 total,   5 running, 268 sleeping,   0 stopped,   0 zombie
 Cpu(s):  6.9%us, 38.2%sy,  0.0%ni, 19.9%id,  0.0%wa,  0.0%hi, 35.0%si,  0.0%st

   PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  P COMMAND
 28504 root      20   0  1044  260  164 S   58  0.0   0:04.19 2 netserver
 28499 root      20   0  1040  412  316 R   51  0.0   0:04.15 0 netperf
 28500 root      20   0  1040  408  316 R   50  0.0   0:04.14 1 netperf
 28503 root      20   0  1044  260  164 S   50  0.0   0:04.01 1 netserver
 28501 root      20   0  1044  260  164 S   49  0.0   0:03.99 0 netserver
 28502 root      20   0  1040  412  316 S   43  0.0   0:03.96 2 netperf
 28468 root      20   0 1892m 325m  972 S   16 10.8   0:10.50 3 perf
 28467 root      20   0 1892m 325m  972 R    2 10.8   0:00.72 3 perf

After:

 top - 10:16:30 up  4:10, 17 users,  load average: 2.27, 1.88, 1.62
 Tasks: 273 total,   6 running, 267 sleeping,   0 stopped,   0 zombie
 Cpu(s):  2.5%us, 39.7%sy,  0.0%ni, 24.6%id,  0.0%wa,  0.0%hi, 33.3%si,  0.0%st

   PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+  P COMMAND
 28590 root      20   0  1040  412  316 S   54  0.0   0:07.85 2 netperf
 28589 root      20   0  1044  260  164 R   54  0.0   0:07.84 0 netserver
 28588 root      20   0  1040  412  316 R   50  0.0   0:07.89 1 netperf
 28591 root      20   0  1044  256  164 S   50  0.0   0:07.82 1 netserver
 28587 root      20   0  1040  408  316 R   47  0.0   0:07.61 0 netperf
 28592 root      20   0  1044  260  164 R   47  0.0   0:07.85 2 netserver
 28378 root      20   0  8732 1300  860 R    2  0.0   0:01.81 3 top
 28577 root      20   0 1892m 165m  972 R    2  5.5   0:00.48 3 perf
 28578 root      20   0 1892m 165m  972 S    2  5.5   0:00.04 3 perf

[ Impact: optimization ]

Signed-off-by: Mike Galbraith <efault@gmx.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/Documentation/perf_counter/builtin-top.c b/Documentation/perf_counter/builtin-top.c
index 74021ac..4bed265 100644
--- a/Documentation/perf_counter/builtin-top.c
+++ b/Documentation/perf_counter/builtin-top.c
@@ -374,18 +374,26 @@
 
 static void print_sym_table(void)
 {
-	int i, printed;
+	int i, j, active_count, printed;
 	int counter;
 	float events_per_sec = events/delay_secs;
 	float kevents_per_sec = (events-userspace_events)/delay_secs;
 	float sum_kevents = 0.0;
 
 	events = userspace_events = 0;
-	memcpy(tmp, sym_table, sizeof(sym_table[0])*sym_table_count);
-	qsort(tmp, sym_table_count, sizeof(tmp[0]), compare);
 
-	for (i = 0; i < sym_table_count && tmp[i].count[0]; i++)
-		sum_kevents += tmp[i].count[0];
+	/* Iterate over symbol table and copy/tally/decay active symbols. */
+	for (i = 0, active_count = 0; i < sym_table_count; i++) {
+		if (sym_table[i].count[0]) {
+			tmp[active_count++] = sym_table[i];
+			sum_kevents += sym_table[i].count[0];
+
+			for (j = 0; j < nr_counters; j++)
+				sym_table[i].count[j] = zero ? 0 : sym_table[i].count[j] * 7 / 8;
+		}
+	}
+
+	qsort(tmp, active_count + 1, sizeof(tmp[0]), compare);
 
 	write(1, CONSOLE_CLEAR, strlen(CONSOLE_CLEAR));
 
@@ -433,29 +441,23 @@
 	       	       "  ______     ______   _____   ________________   _______________\n\n"
 	);
 
-	for (i = 0, printed = 0; i < sym_table_count; i++) {
+	for (i = 0, printed = 0; i < active_count; i++) {
 		float pcnt;
-		int count;
 
-		if (printed <= 18 && tmp[i].count[0] >= count_filter) {
-			pcnt = 100.0 - (100.0*((sum_kevents-tmp[i].count[0])/sum_kevents));
+		if (++printed > 18 || tmp[i].count[0] < count_filter)
+			break;
 
-			if (nr_counters == 1)
-				printf("%19.2f - %4.1f%% - %016llx : %s\n",
-					sym_weight(tmp + i),
-					pcnt, tmp[i].addr, tmp[i].sym);
-			else
-				printf("%8.1f %10ld - %4.1f%% - %016llx : %s\n",
-					sym_weight(tmp + i),
-					tmp[i].count[0],
-					pcnt, tmp[i].addr, tmp[i].sym);
-			printed++;
-		}
-		/*
-		 * Add decay to the counts:
-		 */
-		for (count = 0; count < nr_counters; count++)
-			sym_table[i].count[count] = zero ? 0 : sym_table[i].count[count] * 7 / 8;
+		pcnt = 100.0 - (100.0*((sum_kevents-tmp[i].count[0])/sum_kevents));
+
+		if (nr_counters == 1)
+			printf("%19.2f - %4.1f%% - %016llx : %s\n",
+				sym_weight(tmp + i),
+				pcnt, tmp[i].addr, tmp[i].sym);
+		else
+			printf("%8.1f %10ld - %4.1f%% - %016llx : %s\n",
+				sym_weight(tmp + i),
+				tmp[i].count[0],
+				pcnt, tmp[i].addr, tmp[i].sym);
 	}
 
 	if (sym_filter_entry)