tools: bpftool: use PERF_SAMPLE_TIME instead of reading the clock

Jakub Kicinski · borkmann · commit e3687510fce2 · 2018-05-11T01:40:51.000+02:00
Ask the kernel to include sample time in each even instead of
reading the clock.  This is also more accurate because our
clock reading was done when user space would dump the buffer,
not when sample was produced.

Suggested-by: Daniel Borkmann &lt;daniel@iogearbox.net&gt;
Signed-off-by: Jakub Kicinski &lt;jakub.kicinski@netronome.com&gt;
Reviewed-by: Quentin Monnet &lt;quentin.monnet@netronome.com&gt;
Signed-off-by: Daniel Borkmann &lt;daniel@iogearbox.net&gt;
diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c
@@ -39,6 +39,7 @@ struct event_ring_info {
 
 struct perf_event_sample {
 	struct perf_event_header header;
+	u64 time;
 	__u32 size;
 	unsigned char data[];
 };
@@ -57,24 +58,18 @@ print_bpf_output(struct event_ring_info *ring, struct perf_event_sample *e)
 		__u64 id;
 		__u64 lost;
 	} *lost = (void *)e;
-	struct timespec ts;
-
-	if (clock_gettime(CLOCK_MONOTONIC, &ts)) {
-		perror("Can't read clock for timestamp");
-		return;
-	}
 
 	if (json_output) {
 		jsonw_start_object(json_wtr);
-		jsonw_name(json_wtr, "timestamp");
-		jsonw_uint(json_wtr, ts.tv_sec * 1000000000ull + ts.tv_nsec);
 		jsonw_name(json_wtr, "type");
 		jsonw_uint(json_wtr, e->header.type);
 		jsonw_name(json_wtr, "cpu");
 		jsonw_uint(json_wtr, ring->cpu);
 		jsonw_name(json_wtr, "index");
 		jsonw_uint(json_wtr, ring->key);
 		if (e->header.type == PERF_RECORD_SAMPLE) {
+			jsonw_name(json_wtr, "timestamp");
+			jsonw_uint(json_wtr, e->time);
 			jsonw_name(json_wtr, "data");
 			print_data_json(e->data, e->size);
 		} else if (e->header.type == PERF_RECORD_LOST) {
@@ -89,8 +84,8 @@ print_bpf_output(struct event_ring_info *ring, struct perf_event_sample *e)
 		jsonw_end_object(json_wtr);
 	} else {
 		if (e->header.type == PERF_RECORD_SAMPLE) {
-			printf("== @%ld.%ld CPU: %d index: %d =====\n",
-			       (long)ts.tv_sec, ts.tv_nsec,
+			printf("== @%lld.%09lld CPU: %d index: %d =====\n",
+			       e->time / 1000000000ULL, e->time % 1000000000ULL,
 			       ring->cpu, ring->key);
 			fprint_hex(stdout, e->data, e->size, " ");
 			printf("\n");
@@ -185,7 +180,7 @@ static void perf_event_unmap(void *mem)
 static int bpf_perf_event_open(int map_fd, int key, int cpu)
 {
 	struct perf_event_attr attr = {
-		.sample_type = PERF_SAMPLE_RAW,
+		.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME,
 		.type = PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_BPF_OUTPUT,
 	};
