perf stat: Add per processor socket count aggregation

This patch adds per-processor socket count aggregation for system-wide
mode measurements. This is a useful mode to detect imbalance between
sockets.

To enable this mode, use --aggr-socket in addition
to -a. (system-wide).

The output includes the socket number and the number of online
processors on that socket. This is useful to gauge the amount of
aggregation.

 # ./perf stat -I 1000 -a --aggr-socket -e cycles sleep 2
 #           time socket cpus             counts events
      1.000097680 S0        4          5,788,785 cycles
      2.000379943 S0        4         27,361,546 cycles
      2.001167808 S0        4            818,275 cycles

Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1360161962-9675-3-git-send-email-eranian@google.com
[ committer note: Added missing man page entry based on above comments ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

2 files changed, 123 insertions, 12 deletions

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 5289da3344e9..faf4f4feebcc 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -116,9 +116,16 @@ perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- m
 
 -I msecs::
 --interval-print msecs::
-        print count deltas every N milliseconds (minimum: 100ms)
+        Print count deltas every N milliseconds (minimum: 100ms)
         example: perf stat -I 1000 -e cycles -a sleep 5
 
+--aggr-socket::
+Aggregate counts per processor socket for system-wide mode measurements.  This
+is a useful mode to detect imbalance between sockets.  To enable this mode,
+use --aggr-socket in addition to -a. (system-wide).  The output includes the
+socket number and the number of online processors on that socket. This is
+useful to gauge the amount of aggregation.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0368a1036ad6..99848761f573 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -68,6 +68,7 @@
 static void print_stat(int argc, const char **argv);
 static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
 static void print_counter(struct perf_evsel *counter, char *prefix);
+static void print_aggr_socket(char *prefix);
 
 static struct perf_evlist       *evsel_list;
 
@@ -79,6 +80,7 @@ static int			run_count			=  1;
 static bool                     no_inherit                      = false;
 static bool                     scale                           =  true;
 static bool                     no_aggr                         = false;
+static bool                     aggr_socket                     = false;
 static pid_t                    child_pid                       = -1;
 static bool                     null_run                        =  false;
 static int                      detailed_run                    =  0;
@@ -93,6 +95,7 @@ static const char		*post_cmd			= NULL;
 static bool                     sync_run                        = false;
 static unsigned int             interval                        = 0;
 static struct timespec          ref_time;
+static struct cpu_map           *sock_map;
 
 static volatile int done = 0;
 
@@ -312,7 +315,9 @@ static void print_interval(void)
         sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
 
         if (num_print_interval == 0 && !csv_output) {
-                if (no_aggr)
+                if (aggr_socket)
+                        fprintf(output, "#           time socket cpus             counts events\n");
+                else if (no_aggr)
                         fprintf(output, "#           time CPU                 counts events\n");
                 else
                         fprintf(output, "#           time             counts events\n");
@@ -321,7 +326,9 @@ static void print_interval(void)
         if (++num_print_interval == 25)
                 num_print_interval = 0;
 
-        if (no_aggr) {
+        if (aggr_socket)
+                print_aggr_socket(prefix);
+        else if (no_aggr) {
                 list_for_each_entry(counter, &evsel_list->entries, node)
                         print_counter(counter, prefix);
         } else {
@@ -349,6 +356,12 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv)
                 ts.tv_nsec = 0;
         }
 
+        if (aggr_socket
+            && cpu_map__build_socket_map(evsel_list->cpus, &sock_map)) {
+                perror("cannot build socket map");
+                return -1;
+        }
+
         if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
                 perror("failed to create pipes");
                 return -1;
@@ -529,13 +542,21 @@ static void print_noise(struct perf_evsel *evsel, double avg)
         print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
 }
 
-static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
+static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
         double msecs = avg / 1e6;
         char cpustr[16] = { '\0', };
         const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s";
 
-        if (no_aggr)
+        if (aggr_socket)
+                sprintf(cpustr, "S%*d%s%*d%s",
+                        csv_output ? 0 : -5,
+                        cpu,
+                        csv_sep,
+                        csv_output ? 0 : 4,
+                        nr,
+                        csv_sep);
+        else if (no_aggr)
                 sprintf(cpustr, "CPU%*d%s",
                         csv_output ? 0 : -4,
                         perf_evsel__cpus(evsel)->map[cpu], csv_sep);
@@ -734,7 +755,7 @@ static void print_ll_cache_misses(int cpu,
         fprintf(output, " of all LL-cache hits   ");
 }
 
-static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
+static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
         double total, ratio = 0.0;
         char cpustr[16] = { '\0', };
@@ -747,7 +768,15 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
         else
                 fmt = "%s%18.0f%s%-25s";
 
-        if (no_aggr)
+        if (aggr_socket)
+                sprintf(cpustr, "S%*d%s%*d%s",
+                        csv_output ? 0 : -5,
+                        cpu,
+                        csv_sep,
+                        csv_output ? 0 : 4,
+                        nr,
+                        csv_sep);
+        else if (no_aggr)
                 sprintf(cpustr, "CPU%*d%s",
                         csv_output ? 0 : -4,
                         perf_evsel__cpus(evsel)->map[cpu], csv_sep);
@@ -853,6 +882,70 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
         }
 }
 
+static void print_aggr_socket(char *prefix)
+{
+        struct perf_evsel *counter;
+        u64 ena, run, val;
+        int cpu, s, s2, sock, nr;
+
+        if (!sock_map)
+                return;
+
+        for (s = 0; s < sock_map->nr; s++) {
+                sock = cpu_map__socket(sock_map, s);
+                list_for_each_entry(counter, &evsel_list->entries, node) {
+                        val = ena = run = 0;
+                        nr = 0;
+                        for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+                                s2 = cpu_map__get_socket(evsel_list->cpus, cpu);
+                                if (s2 != sock)
+                                        continue;
+                                val += counter->counts->cpu[cpu].val;
+                                ena += counter->counts->cpu[cpu].ena;
+                                run += counter->counts->cpu[cpu].run;
+                                nr++;