From: Xu Kuohai xukuohai@huawei.com
Add overwrite mode bench for ring buffer.
For reference, below are bench numbers collected from x86_64 and arm64.
- x86_64 (AMD EPYC 9654)
Ringbuf, multi-producer contention, overwrite mode ================================================== rb-libbpf nr_prod 1 14.970 ± 0.012M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 14.064 ± 0.007M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 7.493 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 6.575 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 3.696 ± 0.011M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 2.612 ± 0.012M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 2.335 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 2.079 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 1.965 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 1.846 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 1.790 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 1.735 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 1.701 ± 0.002M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 1.669 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 1.749 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 1.709 ± 0.001M/s (drops 0.000 ± 0.000M/s)
- arm64 (HiSilicon Kunpeng 920)
Ringbuf, multi-producer contention, overwrite mode ================================================== rb-libbpf nr_prod 1 10.319 ± 0.231M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 9.219 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 6.699 ± 0.013M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 4.608 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 3.905 ± 0.001M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 3.282 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 3.182 ± 0.008M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 20 3.029 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 3.116 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 2.869 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 3.075 ± 0.010M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 2.795 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 2.947 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 2.748 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 2.767 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 52 2.858 ± 0.002M/s (drops 0.000 ± 0.000M/s)
Signed-off-by: Xu Kuohai xukuohai@huawei.com --- .../selftests/bpf/benchs/bench_ringbufs.c | 22 ++++++++++++++++++- .../bpf/benchs/run_bench_ringbufs.sh | 4 ++++ 2 files changed, 25 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index e1ee979e6acc..6fdfc61c721b 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_mode; } args = { .back2back = false, .batch_cnt = 500, @@ -27,6 +28,7 @@ static struct { .ringbuf_sz = 512 * 1024, .ringbuf_use_output = false, .perfbuf_sz = 128, + .overwrite_mode = 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_mode = true; + break; default: return ARGP_ERR_UNKNOWN; } @@ -104,6 +111,11 @@ static void bufs_validate(void) fprintf(stderr, "back-to-back mode makes sense only for single-producer case!\n"); exit(1); } + + if (args.overwrite_mode && strcmp(env.bench_name, "rb-libbpf") != 0) { + fprintf(stderr, "rb-overwrite mode only supports rb-libbpf!\n"); + exit(1); + } }
static void *bufs_sample_producer(void *input) @@ -134,6 +146,8 @@ static void ringbuf_libbpf_measure(struct bench_res *res)
static struct ringbuf_bench *ringbuf_setup_skeleton(void) { + __u32 flags; + struct bpf_map *ringbuf; struct ringbuf_bench *skel;
setup_libbpf(); @@ -151,7 +165,13 @@ static struct ringbuf_bench *ringbuf_setup_skeleton(void) /* 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_mode) { + flags = bpf_map__map_flags(ringbuf) | BPF_F_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"); diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh index 91e3567962ff..4e758bc52b73 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh +++ b/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, overwrite mode" +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-overwrite --rb-batch-cnt 50 rb-libbpf)" +done