On Fri, Sep 5, 2025 at 8:13 AM Xu Kuohai xukuohai@huaweicloud.com wrote:

From: Xu Kuohai xukuohai@huawei.com

Add rb-prod test for bpf ring buffer to bench producer performance without counsumer thread. And add --rb-overwrite option to bench ring buffer in overwrite mode.

For reference, below are bench numbers collected from x86_64 and arm64 CPUs.

• AMD EPYC 9654 (x86_64)

  Ringbuf, overwrite mode with multi-producer contention, no consumer

  rb-prod nr_prod 1 32.295 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 2 9.591 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 3 8.895 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 4 9.206 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 8 9.220 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 12 4.595 ± 0.022M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 16 4.348 ± 0.016M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 20 3.957 ± 0.017M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 24 3.787 ± 0.014M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 28 3.603 ± 0.011M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 32 3.707 ± 0.011M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 36 3.562 ± 0.012M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 40 3.616 ± 0.012M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 44 3.598 ± 0.016M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 48 3.555 ± 0.014M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 52 3.463 ± 0.020M/s (drops 0.000 ± 0.000M/s)

• HiSilicon Kunpeng 920 (arm64)

  Ringbuf, overwrite mode with multi-producer contention, no consumer

  rb-prod nr_prod 1 14.687 ± 0.058M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 2 22.263 ± 0.007M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 3 5.736 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 4 4.934 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 8 4.661 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 12 3.753 ± 0.013M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 16 3.706 ± 0.018M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 20 3.660 ± 0.015M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 24 3.610 ± 0.016M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 28 3.238 ± 0.010M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 32 3.270 ± 0.018M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 36 2.892 ± 0.021M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 40 2.995 ± 0.018M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 44 2.830 ± 0.019M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 48 2.877 ± 0.015M/s (drops 0.000 ± 0.000M/s) rb-prod nr_prod 52 2.814 ± 0.015M/s (drops 0.000 ± 0.000M/s)

Signed-off-by: Xu Kuohai xukuohai@huawei.com

tools/testing/selftests/bpf/bench.c | 2 + .../selftests/bpf/benchs/bench_ringbufs.c | 95 +++++++++++++++++-- .../bpf/benchs/run_bench_ringbufs.sh | 4 + .../selftests/bpf/progs/ringbuf_bench.c | 10 ++ 4 files changed, 103 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index bd29bb2e6cb5..a98063f6436a 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -541,6 +541,7 @@ extern const struct bench bench_trig_uretprobe_multi_nop5;

extern const struct bench bench_rb_libbpf; extern const struct bench bench_rb_custom; +extern const struct bench bench_rb_prod; extern const struct bench bench_pb_libbpf; extern const struct bench bench_pb_custom; extern const struct bench bench_bloom_lookup; @@ -617,6 +618,7 @@ static const struct bench *benchs[] = { /* ringbuf/perfbuf benchmarks */ &bench_rb_libbpf, &bench_rb_custom,

•   &bench_rb_prod,
    &bench_pb_libbpf,
    &bench_pb_custom,
    &bench_bloom_lookup,
  

diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index e1ee979e6acc..6d58479fac91 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -19,6 +19,7 @@ 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;
  

} args = { .back2back = false, .batch_cnt = 500, @@ -27,6 +28,7 @@ static struct { .ringbuf_sz = 512 * 1024, .ringbuf_use_output = false, .perfbuf_sz = 128,

•   .overwrite = false,
  

};

enum { @@ -35,6 +37,7 @@ enum { ARG_RB_BATCH_CNT = 2002, ARG_RB_SAMPLED = 2003, ARG_RB_SAMPLE_RATE = 2004,

•   ARG_RB_OVERWRITE = 2005,
  

};

static const struct argp_option opts[] = { @@ -43,6 +46,7 @@ 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"},
    {},
  

};

@@ -72,6 +76,9 @@ 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;
    default:
            return ARGP_ERR_UNKNOWN;
    }
  

@@ -95,8 +102,30 @@ 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");
  

•   bool bench_prod = !strcmp(env.bench_name, "rb-prod");
  

•   if (args.overwrite && !bench_prod) {
  

•           fprintf(stderr, "overwite mode only works with benchmakr rb-prod!\n");
  

•           exit(1);
  

•   }
  

•   if (bench_prod && env.consumer_cnt != 0) {
  

•           fprintf(stderr, "rb-prod benchmark does not need consumer!\n");
  

•           exit(1);
  

•   }
  

•   if (bench_prod && args.back2back) {
  

•           fprintf(stderr, "back-to-back mode makes no sense for rb-prod!\n");
  

•           exit(1);
  

•   }
  

•   if (bench_prod && args.sampled) {
  

•           fprintf(stderr, "sampling mode makes no sense for rb-prod!\n");
  

•           exit(1);
  

•   }
  

•   if (!bench_prod && env.consumer_cnt != 1) {
  

•           fprintf(stderr, "benchmarks excluding rb-prod need one consumer!\n");
            exit(1);
    }
  
  

@@ -132,8 +161,10 @@ static void ringbuf_libbpf_measure(struct bench_res *res) res->drops = atomic_swap(&ctx->skel->bss->dropped, 0); }

-static struct ringbuf_bench *ringbuf_setup_skeleton(void) +static struct ringbuf_bench *ringbuf_setup_skeleton(int bench_prod)

int because C doesn't support bool?...

but really, do we need another benchmark just to set overwritable mode?... can't you adapt existing benchmarks to optionally set overwritable mode?

(and please drop sdf@google.com from CC for the next revision, that email doesn't exist anymore)

[...]