selftests/bpf: Add local-storage-create benchmark

This patch tests how many kmallocs is needed to create and free
a batch of UDP sockets and each socket has a 64bytes bpf storage.
It also measures how fast the UDP sockets can be created.

The result is from my qemu setup.

Before bpf_mem_cache_alloc/free:
./bench -p 1 local-storage-create
Setting up benchmark 'local-storage-create'...
Benchmark 'local-storage-create' started.
Iter   0 ( 73.193us): creates  213.552k/s (213.552k/prod), 3.09 kmallocs/create
Iter   1 (-20.724us): creates  211.908k/s (211.908k/prod), 3.09 kmallocs/create
Iter   2 (  9.280us): creates  212.574k/s (212.574k/prod), 3.12 kmallocs/create
Iter   3 ( 11.039us): creates  213.209k/s (213.209k/prod), 3.12 kmallocs/create
Iter   4 (-11.411us): creates  213.351k/s (213.351k/prod), 3.12 kmallocs/create
Iter   5 ( -7.915us): creates  214.754k/s (214.754k/prod), 3.12 kmallocs/create
Iter   6 ( 11.317us): creates  210.942k/s (210.942k/prod), 3.12 kmallocs/create
Summary: creates  212.789 ± 1.310k/s (212.789k/prod), 3.12 kmallocs/create

After bpf_mem_cache_alloc/free:
./bench -p 1 local-storage-create
Setting up benchmark 'local-storage-create'...
Benchmark 'local-storage-create' started.
Iter   0 ( 68.265us): creates  243.984k/s (243.984k/prod), 1.04 kmallocs/create
Iter   1 ( 30.357us): creates  238.424k/s (238.424k/prod), 1.04 kmallocs/create
Iter   2 (-18.712us): creates  232.963k/s (232.963k/prod), 1.04 kmallocs/create
Iter   3 (-15.885us): creates  238.879k/s (238.879k/prod), 1.04 kmallocs/create
Iter   4 (  5.590us): creates  237.490k/s (237.490k/prod), 1.04 kmallocs/create
Iter   5 (  8.577us): creates  237.521k/s (237.521k/prod), 1.04 kmallocs/create
Iter   6 ( -6.263us): creates  238.508k/s (238.508k/prod), 1.04 kmallocs/create
Summary: creates  237.298 ± 2.198k/s (237.298k/prod), 1.04 kmallocs/create

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20230308065936.1550103-18-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 141 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c
new file mode 100644
index 000000000000..f8b2a640ccbe
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include "bench.h"
+#include "bench_local_storage_create.skel.h"
+
+#define BATCH_SZ 32
+
+struct thread {
+	int fds[BATCH_SZ];
+};
+
+static struct bench_local_storage_create *skel;
+static struct thread *threads;
+static long socket_errs;
+
+static void validate(void)
+{
+	if (env.consumer_cnt > 1) {
+		fprintf(stderr,
+			"local-storage-create benchmark does not need consumer\n");
+		exit(1);
+	}
+}
+
+static void setup(void)
+{
+	skel = bench_local_storage_create__open_and_load();
+	if (!skel) {
+		fprintf(stderr, "error loading skel\n");
+		exit(1);
+	}
+
+	skel->bss->bench_pid = getpid();
+
+	if (!bpf_program__attach(skel->progs.socket_post_create)) {
+		fprintf(stderr, "Error attaching bpf program\n");
+		exit(1);
+	}
+
+	if (!bpf_program__attach(skel->progs.kmalloc)) {
+		fprintf(stderr, "Error attaching bpf program\n");
+		exit(1);
+	}
+
+	threads = calloc(env.producer_cnt, sizeof(*threads));
+
+	if (!threads) {
+		fprintf(stderr, "cannot alloc thread_res\n");
+		exit(1);
+	}
+}
+
+static void measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&skel->bss->create_cnts, 0);
+	res->drops = atomic_swap(&skel->bss->kmalloc_cnts, 0);
+}
+
+static void *consumer(void *input)
+{
+	return NULL;
+}
+
+static void *producer(void *input)
+{
+	struct thread *t = &threads[(long)(input)];
+	int *fds = t->fds;
+	int i;
+
+	while (true) {
+		for (i = 0; i < BATCH_SZ; i++) {
+			fds[i] = socket(AF_INET6, SOCK_DGRAM, 0);
+			if (fds[i] == -1)
+				atomic_inc(&socket_errs);
+		}
+
+		for (i = 0; i < BATCH_SZ; i++) {
+			if (fds[i] != -1)
+				close(fds[i]);
+		}
+	}
+
+	return NULL;
+}
+
+static void report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+	double creates_per_sec, kmallocs_per_create;
+
+	creates_per_sec = res->hits / 1000.0 / (delta_ns / 1000000000.0);
+	kmallocs_per_create = (double)res->drops / res->hits;
+
+	printf("Iter %3d (%7.3lfus): ",
+	       iter, (delta_ns - 1000000000) / 1000.0);
+	printf("creates %8.3lfk/s (%7.3lfk/prod), ",
+	       creates_per_sec, creates_per_sec / env.producer_cnt);
+	printf("%3.2lf kmallocs/create\n", kmallocs_per_create);
+}
+
+static void report_final(struct bench_res res[], int res_cnt)
+{
+	double creates_mean = 0.0, creates_stddev = 0.0;
+	long total_creates = 0, total_kmallocs = 0;
+	int i;
+
+	for (i = 0; i < res_cnt; i++) {
+		creates_mean += res[i].hits / 1000.0 / (0.0 + res_cnt);
+		total_creates += res[i].hits;
+		total_kmallocs += res[i].drops;
+	}
+
+	if (res_cnt > 1)  {
+		for (i = 0; i < res_cnt; i++)
+			creates_stddev += (creates_mean - res[i].hits / 1000.0) *
+				       (creates_mean - res[i].hits / 1000.0) /
+				       (res_cnt - 1.0);
+		creates_stddev = sqrt(creates_stddev);
+	}
+	printf("Summary: creates %8.3lf \u00B1 %5.3lfk/s (%7.3lfk/prod), ",
+	       creates_mean, creates_stddev, creates_mean / env.producer_cnt);
+	printf("%4.2lf kmallocs/create\n", (double)total_kmallocs / total_creates);
+	if (socket_errs || skel->bss->create_errs)
+		printf("socket() errors %ld create_errs %ld\n", socket_errs,
+		       skel->bss->create_errs);
+}
+
+/* Benchmark performance of creating bpf local storage  */
+const struct bench bench_local_storage_create = {
+	.name = "local-storage-create",
+	.validate = validate,
+	.setup = setup,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = report_progress,
+	.report_final = report_final,
+};