[PATCH 1/2] perf map: synthesize maps only for thread group leader

[Konstantin Khlebnikov]

Threads share map_groups, all map events are merged into it.

Thus we could send mmaps only for thread group leader.
Otherwise it took ages to attach and record something from
processes with many vmas and threads.

Thread group leader could be already dead,
but it seems perf cannot handle this case anyway.

Testing dummy:

#include <stdio.h>
#include <stdlib.h>
#include <sys/mman.h>
#include <pthread.h>
#include <unistd.h>

void *thread(void *arg) {
        pause();
}

int main(int argc, char **argv) {
        int threads = 10000;
        int vmas = 50000;
        pthread_t th;
        for (int i = 0; i < threads; i++)
                pthread_create(&th, NULL, thread, NULL);
        for (int i = 0; i < vmas; i++)
                mmap(NULL, 4096, (i & 1) ? PROT_READ : PROT_WRITE,
                     MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
        sleep(60);
        return 0;
}

Signed-off-by: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxxxxxx>
---
 tools/perf/util/event.c |   13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 0c8ecf0c78a4..0cd42150f712 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -541,10 +541,17 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 						      tgid, process, machine) < 0)
 			return -1;
 
+		/*
+		 * send mmap only for thread group leader
+		 * see thread__init_map_groups
+		 */
+		if (pid == tgid &&
+		    perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+						       process, machine, mmap_data,
+						       proc_map_timeout))
+			return -1;
 
-		return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-							  process, machine, mmap_data,
-							  proc_map_timeout);
+		return 0;
 	}
 
 	if (machine__is_default_guest(machine))