selftests/bpf/benchs: Add overwrite mode benchmark for BPF ring buffer

Add --rb-overwrite option to benchmark BPF ring buffer in overwrite mode.
Since overwrite mode is not yet supported by libbpf for consumer, also add
--rb-bench-producer option to benchmark producer directly without a consumer.

Benchmarks on an x86_64 and an arm64 CPU are shown below for reference.

- AMD EPYC 9654 (x86_64)

Ringbuf, multi-producer contention in overwrite mode, no consumer
=================================================================
rb-prod nr_prod 1    32.180 ± 0.033M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 2    9.617 ± 0.003M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 3    8.810 ± 0.002M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 4    9.272 ± 0.001M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 8    9.173 ± 0.001M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 12   3.086 ± 0.032M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 16   2.945 ± 0.021M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 20   2.519 ± 0.021M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 24   2.545 ± 0.021M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 28   2.363 ± 0.024M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 32   2.357 ± 0.021M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 36   2.267 ± 0.011M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 40   2.284 ± 0.020M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 44   2.215 ± 0.025M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 48   2.193 ± 0.023M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 52   2.208 ± 0.024M/s (drops 0.000 ± 0.000M/s)

- HiSilicon Kunpeng 920 (arm64)

Ringbuf, multi-producer contention in overwrite mode, no consumer
=================================================================
rb-prod nr_prod 1    14.478 ± 0.006M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 2    21.787 ± 0.010M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 3    6.045 ± 0.001M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 4    5.352 ± 0.003M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 8    4.850 ± 0.002M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 12   3.542 ± 0.016M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 16   3.509 ± 0.021M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 20   3.171 ± 0.010M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 24   3.154 ± 0.014M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 28   2.974 ± 0.015M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 32   3.167 ± 0.014M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 36   2.903 ± 0.010M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 40   2.866 ± 0.010M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 44   2.914 ± 0.010M/s (drops 0.000 ± 0.000M/s)
rb-prod nr_prod 48   2.806 ± 0.012M/s (drops 0.000 ± 0.000M/s)
Rb-prod nr_prod 52   2.840 ± 0.012M/s (drops 0.000 ± 0.000M/s)

Signed-off-by: Xu Kuohai <[email protected]>
Signed-off-by: Andrii Nakryiko <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: Xu Kuohai

tools/testing/selftests/bpf/benchs/bench_ringbufs.c

@@ -19,6 +19,8 @@ static struct {
 	int ringbuf_sz; /* per-ringbuf, in bytes */
 	bool ringbuf_use_output; /* use slower output API */
 	int perfbuf_sz; /* per-CPU size, in pages */
+	bool overwrite;
+	bool bench_producer;
 } args = {
 	.back2back = false,
 	.batch_cnt = 500,
@@ -27,6 +29,8 @@ static struct {
 	.ringbuf_sz = 512 * 1024,
 	.ringbuf_use_output = false,
 	.perfbuf_sz = 128,
+	.overwrite = false,
+	.bench_producer = false,
 };
 
 enum {
@@ -35,6 +39,8 @@ enum {
 	ARG_RB_BATCH_CNT = 2002,
 	ARG_RB_SAMPLED = 2003,
 	ARG_RB_SAMPLE_RATE = 2004,
+	ARG_RB_OVERWRITE = 2005,
+	ARG_RB_BENCH_PRODUCER = 2006,
 };
 
 static const struct argp_option opts[] = {
@@ -43,6 +49,8 @@ static const struct argp_option opts[] = {
 	{ "rb-batch-cnt", ARG_RB_BATCH_CNT, "CNT", 0, "Set BPF-side record batch count"},
 	{ "rb-sampled", ARG_RB_SAMPLED, NULL, 0, "Notification sampling"},
 	{ "rb-sample-rate", ARG_RB_SAMPLE_RATE, "RATE", 0, "Notification sample rate"},
+	{ "rb-overwrite", ARG_RB_OVERWRITE, NULL, 0, "Overwrite mode"},
+	{ "rb-bench-producer", ARG_RB_BENCH_PRODUCER, NULL, 0, "Benchmark producer"},
 	{},
 };
 
@@ -72,6 +80,12 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 			argp_usage(state);
 		}
 		break;
+	case ARG_RB_OVERWRITE:
+		args.overwrite = true;
+		break;
+	case ARG_RB_BENCH_PRODUCER:
+		args.bench_producer = true;
+		break;
 	default:
 		return ARGP_ERR_UNKNOWN;
 	}
@@ -95,8 +109,33 @@ static inline void bufs_trigger_batch(void)
 
 static void bufs_validate(void)
 {
-	if (env.consumer_cnt != 1) {
-		fprintf(stderr, "rb-libbpf benchmark needs one consumer!\n");
+	if (args.bench_producer && strcmp(env.bench_name, "rb-libbpf")) {
+		fprintf(stderr, "--rb-bench-producer only works with rb-libbpf!\n");
+		exit(1);
+	}
+
+	if (args.overwrite && !args.bench_producer) {
+		fprintf(stderr, "overwrite mode only works with --rb-bench-producer for now!\n");
+		exit(1);
+	}
+
+	if (args.bench_producer && env.consumer_cnt != 0) {
+		fprintf(stderr, "no consumer is needed for --rb-bench-producer!\n");
+		exit(1);
+	}
+
+	if (args.bench_producer && args.back2back) {
+		fprintf(stderr, "back-to-back mode makes no sense for --rb-bench-producer!\n");
+		exit(1);
+	}
+
+	if (args.bench_producer && args.sampled) {
+		fprintf(stderr, "sampling mode makes no sense for --rb-bench-producer!\n");
+		exit(1);
+	}
+
+	if (!args.bench_producer && env.consumer_cnt != 1) {
+		fprintf(stderr, "benchmarks without --rb-bench-producer require exactly one consumer!\n");
 		exit(1);
 	}
 
@@ -128,12 +167,17 @@ static void ringbuf_libbpf_measure(struct bench_res *res)
 {
 	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
 
-	res->hits = atomic_swap(&buf_hits.value, 0);
+	if (args.bench_producer)
+		res->hits = atomic_swap(&ctx->skel->bss->hits, 0);
+	else
+		res->hits = atomic_swap(&buf_hits.value, 0);
 	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
 }
 
 static struct ringbuf_bench *ringbuf_setup_skeleton(void)
 {
+	__u32 flags;
+	struct bpf_map *ringbuf;
 	struct ringbuf_bench *skel;
 
 	setup_libbpf();
@@ -146,12 +190,19 @@ static struct ringbuf_bench *ringbuf_setup_skeleton(void)
 
 	skel->rodata->batch_cnt = args.batch_cnt;
 	skel->rodata->use_output = args.ringbuf_use_output ? 1 : 0;
+	skel->rodata->bench_producer = args.bench_producer;
 
 	if (args.sampled)
 		/* record data + header take 16 bytes */
 		skel->rodata->wakeup_data_size = args.sample_rate * 16;
 
-	bpf_map__set_max_entries(skel->maps.ringbuf, args.ringbuf_sz);
+	ringbuf = skel->maps.ringbuf;
+	if (args.overwrite) {
+		flags = bpf_map__map_flags(ringbuf) | BPF_F_RB_OVERWRITE;
+		bpf_map__set_map_flags(ringbuf, flags);
+	}
+
+	bpf_map__set_max_entries(ringbuf, args.ringbuf_sz);
 
 	if (ringbuf_bench__load(skel)) {
 		fprintf(stderr, "failed to load skeleton\n");
@@ -171,10 +222,12 @@ static void ringbuf_libbpf_setup(void)
 {
 	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
 	struct bpf_link *link;
+	int map_fd;
 
 	ctx->skel = ringbuf_setup_skeleton();
-	ctx->ringbuf = ring_buffer__new(bpf_map__fd(ctx->skel->maps.ringbuf),
-					buf_process_sample, NULL, NULL);
+
+	map_fd = bpf_map__fd(ctx->skel->maps.ringbuf);
+	ctx->ringbuf = ring_buffer__new(map_fd, buf_process_sample, NULL, NULL);
 	if (!ctx->ringbuf) {
 		fprintf(stderr, "failed to create ringbuf\n");
 		exit(1);

tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh

@@ -49,3 +49,7 @@ for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do
 	summarize "rb-libbpf nr_prod $b" "$($RUN_RB_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)"
 done
 
+header "Ringbuf, multi-producer contention in overwrite mode, no consumer"
+for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do
+	summarize "rb-prod nr_prod $b" "$($RUN_BENCH -p$b --rb-batch-cnt 50 --rb-overwrite --rb-bench-producer rb-libbpf)"
+done

tools/testing/selftests/bpf/progs/ringbuf_bench.c

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2020 Facebook
 
+#include <stdbool.h>
 #include <linux/bpf.h>
 #include <stdint.h>
 #include <bpf/bpf_helpers.h>
@@ -14,16 +15,21 @@ struct {
 
 const volatile int batch_cnt = 0;
 const volatile long use_output = 0;
+const volatile bool bench_producer = false;
 
 long sample_val = 42;
 long dropped __attribute__((aligned(128))) = 0;
+long hits __attribute__((aligned(128))) = 0;
 
 const volatile long wakeup_data_size = 0;
 
 static __always_inline long get_flags()
 {
 	long sz;
 
+	if (bench_producer)
+		return BPF_RB_NO_WAKEUP;
+
 	if (!wakeup_data_size)
 		return 0;
 
@@ -47,6 +53,8 @@ int bench_ringbuf(void *ctx)
 				*sample = sample_val;
 				flags = get_flags();
 				bpf_ringbuf_submit(sample, flags);
+				if (bench_producer)
+					__sync_add_and_fetch(&hits, 1);
 			}
 		}
 	} else {
@@ -55,6 +63,9 @@ int bench_ringbuf(void *ctx)
 			if (bpf_ringbuf_output(&ringbuf, &sample_val,
 					       sizeof(sample_val), flags))
 				__sync_add_and_fetch(&dropped, 1);
+			else if (bench_producer)
+				__sync_add_and_fetch(&hits, 1);
+
 		}
 	}
 	return 0;