selftest/bpf/benchs: Add bpf_loop benchmark

Add benchmark to measure the throughput and latency of the bpf_loop
call.

Testing this on my dev machine on 1 thread, the data is as follows:

        nr_loops: 10
bpf_loop - throughput: 198.519 ± 0.155 M ops/s, latency: 5.037 ns/op

        nr_loops: 100
bpf_loop - throughput: 247.448 ± 0.305 M ops/s, latency: 4.041 ns/op

        nr_loops: 500
bpf_loop - throughput: 260.839 ± 0.380 M ops/s, latency: 3.834 ns/op

        nr_loops: 1000
bpf_loop - throughput: 262.806 ± 0.629 M ops/s, latency: 3.805 ns/op

        nr_loops: 5000
bpf_loop - throughput: 264.211 ± 1.508 M ops/s, latency: 3.785 ns/op

        nr_loops: 10000
bpf_loop - throughput: 265.366 ± 3.054 M ops/s, latency: 3.768 ns/op

        nr_loops: 50000
bpf_loop - throughput: 235.986 ± 20.205 M ops/s, latency: 4.238 ns/op

        nr_loops: 100000
bpf_loop - throughput: 264.482 ± 0.279 M ops/s, latency: 3.781 ns/op

        nr_loops: 500000
bpf_loop - throughput: 309.773 ± 87.713 M ops/s, latency: 3.228 ns/op

        nr_loops: 1000000
bpf_loop - throughput: 262.818 ± 4.143 M ops/s, latency: 3.805 ns/op

>From this data, we can see that the latency per loop decreases as the
number of loops increases. On this particular machine, each loop had an
overhead of about ~4 ns, and we were able to run ~250 million loops
per second.

Signed-off-by: Joanne Koong <joannekoong@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211130030622.4131246-5-joannekoong@fb.com

1 files changed, 37 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index c75e7ee28746..3d6082b97a56 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -134,6 +134,39 @@ void hits_drops_report_final(struct bench_res res[], int res_cnt)
 	       total_ops_mean, total_ops_stddev);
 }
 
+void ops_report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+	double hits_per_sec, hits_per_prod;
+
+	hits_per_sec = res->hits / 1000000.0 / (delta_ns / 1000000000.0);
+	hits_per_prod = hits_per_sec / env.producer_cnt;
+
+	printf("Iter %3d (%7.3lfus): ", iter, (delta_ns - 1000000000) / 1000.0);
+
+	printf("hits %8.3lfM/s (%7.3lfM/prod)\n", hits_per_sec, hits_per_prod);
+}
+
+void ops_report_final(struct bench_res res[], int res_cnt)
+{
+	double hits_mean = 0.0, hits_stddev = 0.0;
+	int i;
+
+	for (i = 0; i < res_cnt; i++)
+		hits_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt);
+
+	if (res_cnt > 1)  {
+		for (i = 0; i < res_cnt; i++)
+			hits_stddev += (hits_mean - res[i].hits / 1000000.0) *
+				       (hits_mean - res[i].hits / 1000000.0) /
+				       (res_cnt - 1.0);
+
+		hits_stddev = sqrt(hits_stddev);
+	}
+	printf("Summary: throughput %8.3lf \u00B1 %5.3lf M ops/s (%7.3lfM ops/prod), ",
+	       hits_mean, hits_stddev, hits_mean / env.producer_cnt);
+	printf("latency %8.3lf ns/op\n", 1000.0 / hits_mean * env.producer_cnt);
+}
+
 const char *argp_program_version = "benchmark";
 const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
 const char argp_program_doc[] =
@@ -171,10 +204,12 @@ static const struct argp_option opts[] = {
 
 extern struct argp bench_ringbufs_argp;
 extern struct argp bench_bloom_map_argp;
+extern struct argp bench_bpf_loop_argp;
 
 static const struct argp_child bench_parsers[] = {
 	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
 	{ &bench_bloom_map_argp, 0, "Bloom filter map benchmark", 0 },
+	{ &bench_bpf_loop_argp, 0, "bpf_loop helper benchmark", 0 },
 	{},
 };
 
@@ -373,6 +408,7 @@ extern const struct bench bench_bloom_update;
 extern const struct bench bench_bloom_false_positive;
 extern const struct bench bench_hashmap_without_bloom;
 extern const struct bench bench_hashmap_with_bloom;
+extern const struct bench bench_bpf_loop;
 
 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -404,6 +440,7 @@ static const struct bench *benchs[] = {
 	&bench_bloom_false_positive,
 	&bench_hashmap_without_bloom,
 	&bench_hashmap_with_bloom,
+	&bench_bpf_loop,
 };
 
 static void setup_benchmark()