selftests/bpf: Add benchmark runner infrastructure

While working on BPF ringbuf implementation, testing, and benchmarking, I've developed a pretty generic and modular benchmark runner, which seems to be generically useful, as I've already used it for one more purpose (testing fastest way to trigger BPF program, to minimize overhead of in-kernel code). This patch adds generic part of benchmark runner and sets up Makefile for extending it with more sets of benchmarks. Benchmarker itself operates by spinning up specified number of producer and consumer threads, setting up interval timer sending SIGALARM signal to application once a second. Every second, current snapshot with hits/drops counters are collected and stored in an array. Drops are useful for producer/consumer benchmarks in which producer might overwhelm consumers. Once test finishes after given amount of warm-up and testing seconds, mean and stddev are calculated (ignoring warm-up results) and is printed out to stdout. This setup seems to give consistent and accurate results. To validate behavior, I added two atomic counting tests: global and local. For global one, all the producer threads are atomically incrementing same counter as fast as possible. This, of course, leads to huge drop of performance once there is more than one producer thread due to CPUs fighting for the same memory location. Local counting, on the other hand, maintains one counter per each producer thread, incremented independently. Once per second, all counters are read and added together to form final "counting throughput" measurement. As expected, such setup demonstrates linear scalability with number of producers (as long as there are enough physical CPU cores, of course). See example output below. Also, this setup can nicely demonstrate disastrous effects of false sharing, if care is not taken to take those per-producer counters apart into independent cache lines. Demo output shows global counter first with 1 producer, then with 4. Both total and per-producer performance significantly drop. The last run is local counter with 4 producers, demonstrating near-perfect scalability. $ ./bench -a -w1 -d2 -p1 count-global Setting up benchmark 'count-global'... Benchmark 'count-global' started. Iter 0 ( 24.822us): hits 148.179M/s (148.179M/prod), drops 0.000M/s Iter 1 ( 37.939us): hits 149.308M/s (149.308M/prod), drops 0.000M/s Iter 2 (-10.774us): hits 150.717M/s (150.717M/prod), drops 0.000M/s Iter 3 ( 3.807us): hits 151.435M/s (151.435M/prod), drops 0.000M/s Summary: hits 150.488 ± 1.079M/s (150.488M/prod), drops 0.000 ± 0.000M/s $ ./bench -a -w1 -d2 -p4 count-global Setting up benchmark 'count-global'... Benchmark 'count-global' started. Iter 0 ( 60.659us): hits 53.910M/s ( 13.477M/prod), drops 0.000M/s Iter 1 (-17.658us): hits 53.722M/s ( 13.431M/prod), drops 0.000M/s Iter 2 ( 5.865us): hits 53.495M/s ( 13.374M/prod), drops 0.000M/s Iter 3 ( 0.104us): hits 53.606M/s ( 13.402M/prod), drops 0.000M/s Summary: hits 53.608 ± 0.113M/s ( 13.402M/prod), drops 0.000 ± 0.000M/s $ ./bench -a -w1 -d2 -p4 count-local Setting up benchmark 'count-local'... Benchmark 'count-local' started. Iter 0 ( 23.388us): hits 640.450M/s (160.113M/prod), drops 0.000M/s Iter 1 ( 2.291us): hits 605.661M/s (151.415M/prod), drops 0.000M/s Iter 2 ( -6.415us): hits 607.092M/s (151.773M/prod), drops 0.000M/s Iter 3 ( -1.361us): hits 601.796M/s (150.449M/prod), drops 0.000M/s Summary: hits 604.849 ± 2.739M/s (151.212M/prod), drops 0.000 ± 0.000M/s Benchmark runner supports setting thread affinity for producer and consumer threads. You can use -a flag for default CPU selection scheme, where first consumer gets CPU #0, next one gets CPU #1, and so on. Then producer threads pick up next CPU and increment one-by-one as well. But user can also specify a set of CPUs independently for producers and consumers with --prod-affinity 1,2-10,15 and --cons-affinity <set-of-cpus>. The latter allows to force producers and consumers to share same set of CPUs, if necessary. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200512192445.2351848-3-andriin@fb.com
2024-11-24 03:20:53 +07:00 · 2020-05-12 12:24:43 -07:00 · 2020-05-12 12:24:43 -07:00 · 8e7c2a023a
commit 8e7c2a023a
parent cd49291ce1
5 changed files with 608 additions and 1 deletions
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@ -38,3 +38,4 @@ test_cpp
 /bpf_gcc
 /tools
 /runqslower
+/bench
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@ -77,7 +77,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
 	flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
-	test_lirc_mode2_user xdping test_cpp runqslower
+	test_lirc_mode2_user xdping test_cpp runqslower bench

 TEST_CUSTOM_PROGS = urandom_read

@ -407,6 +407,17 @@ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
 	$(call msg,CXX,,$@)
 	$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@

+# Benchmark runner
+$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h
+	$(call msg,CC,,$@)
+	$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@
+$(OUTPUT)/bench.o: bench.h testing_helpers.h
+$(OUTPUT)/bench: LDLIBS += -lm
+$(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \
+		 $(OUTPUT)/bench_count.o
+	$(call msg,BINARY,,$@)
+	$(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS)
+
 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR)			\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
 	feature								\
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@ -0,0 +1,423 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define _GNU_SOURCE
+#include <argp.h>
+#include <linux/compiler.h>
+#include <sys/time.h>
+#include <sched.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <sys/sysinfo.h>
+#include <sys/resource.h>
+#include <signal.h>
+#include "bench.h"
+#include "testing_helpers.h"
+
+struct env env = {
+	.warmup_sec = 1,
+	.duration_sec = 5,
+	.affinity = false,
+	.consumer_cnt = 1,
+	.producer_cnt = 1,
+};
+
+static int libbpf_print_fn(enum libbpf_print_level level,
+		    const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !env.verbose)
+		return 0;
+	return vfprintf(stderr, format, args);
+}
+
+static int bump_memlock_rlimit(void)
+{
+	struct rlimit rlim_new = {
+		.rlim_cur	= RLIM_INFINITY,
+		.rlim_max	= RLIM_INFINITY,
+	};
+
+	return setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+}
+
+void setup_libbpf()
+{
+	int err;
+
+	libbpf_set_print(libbpf_print_fn);
+
+	err = bump_memlock_rlimit();
+	if (err)
+		fprintf(stderr, "failed to increase RLIMIT_MEMLOCK: %d", err);
+}
+
+void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+	double hits_per_sec, drops_per_sec;
+	double hits_per_prod;
+
+	hits_per_sec = res->hits / 1000000.0 / (delta_ns / 1000000000.0);
+	hits_per_prod = hits_per_sec / env.producer_cnt;
+	drops_per_sec = res->drops / 1000000.0 / (delta_ns / 1000000000.0);
+
+	printf("Iter %3d (%7.3lfus): ",
+	       iter, (delta_ns - 1000000000) / 1000.0);
+
+	printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s\n",
+	       hits_per_sec, hits_per_prod, drops_per_sec);
+}
+
+void hits_drops_report_final(struct bench_res res[], int res_cnt)
+{
+	int i;
+	double hits_mean = 0.0, drops_mean = 0.0;
+	double hits_stddev = 0.0, drops_stddev = 0.0;
+
+	for (i = 0; i < res_cnt; i++) {
+		hits_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt);
+		drops_mean += res[i].drops / 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);
+			drops_stddev += (drops_mean - res[i].drops / 1000000.0) *
+					(drops_mean - res[i].drops / 1000000.0) /
+					(res_cnt - 1.0);
+		}
+		hits_stddev = sqrt(hits_stddev);
+		drops_stddev = sqrt(drops_stddev);
+	}
+	printf("Summary: hits %8.3lf \u00B1 %5.3lfM/s (%7.3lfM/prod), ",
+	       hits_mean, hits_stddev, hits_mean / env.producer_cnt);
+	printf("drops %8.3lf \u00B1 %5.3lfM/s\n",
+	       drops_mean, drops_stddev);
+}
+
+const char *argp_program_version = "benchmark";
+const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
+const char argp_program_doc[] =
+"benchmark    Generic benchmarking framework.\n"
+"\n"
+"This tool runs benchmarks.\n"
+"\n"
+"USAGE: benchmark <bench-name>\n"
+"\n"
+"EXAMPLES:\n"
+"    # run 'count-local' benchmark with 1 producer and 1 consumer\n"
+"    benchmark count-local\n"
+"    # run 'count-local' with 16 producer and 8 consumer thread, pinned to CPUs\n"
+"    benchmark -p16 -c8 -a count-local\n";
+
+enum {
+	ARG_PROD_AFFINITY_SET = 1000,
+	ARG_CONS_AFFINITY_SET = 1001,
+};
+
+static const struct argp_option opts[] = {
+	{ "list", 'l', NULL, 0, "List available benchmarks"},
+	{ "duration", 'd', "SEC", 0, "Duration of benchmark, seconds"},
+	{ "warmup", 'w', "SEC", 0, "Warm-up period, seconds"},
+	{ "producers", 'p', "NUM", 0, "Number of producer threads"},
+	{ "consumers", 'c', "NUM", 0, "Number of consumer threads"},
+	{ "verbose", 'v', NULL, 0, "Verbose debug output"},
+	{ "affinity", 'a', NULL, 0, "Set consumer/producer thread affinity"},
+	{ "prod-affinity", ARG_PROD_AFFINITY_SET, "CPUSET", 0,
+	  "Set of CPUs for producer threads; implies --affinity"},
+	{ "cons-affinity", ARG_CONS_AFFINITY_SET, "CPUSET", 0,
+	  "Set of CPUs for consumer threads; implies --affinity"},
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	static int pos_args;
+
+	switch (key) {
+	case 'v':
+		env.verbose = true;
+		break;
+	case 'l':
+		env.list = true;
+		break;
+	case 'd':
+		env.duration_sec = strtol(arg, NULL, 10);
+		if (env.duration_sec <= 0) {
+			fprintf(stderr, "Invalid duration: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
+	case 'w':
+		env.warmup_sec = strtol(arg, NULL, 10);
+		if (env.warmup_sec <= 0) {
+			fprintf(stderr, "Invalid warm-up duration: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
+	case 'p':
+		env.producer_cnt = strtol(arg, NULL, 10);
+		if (env.producer_cnt <= 0) {
+			fprintf(stderr, "Invalid producer count: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
+	case 'c':
+		env.consumer_cnt = strtol(arg, NULL, 10);
+		if (env.consumer_cnt <= 0) {
+			fprintf(stderr, "Invalid consumer count: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
+	case 'a':
+		env.affinity = true;
+		break;
+	case ARG_PROD_AFFINITY_SET:
+		env.affinity = true;
+		if (parse_num_list(arg, &env.prod_cpus.cpus,
+				   &env.prod_cpus.cpus_len)) {
+			fprintf(stderr, "Invalid format of CPU set for producers.");
+			argp_usage(state);
+		}
+		break;
+	case ARG_CONS_AFFINITY_SET:
+		env.affinity = true;
+		if (parse_num_list(arg, &env.cons_cpus.cpus,
+				   &env.cons_cpus.cpus_len)) {
+			fprintf(stderr, "Invalid format of CPU set for consumers.");
+			argp_usage(state);
+		}
+		break;
+	case ARGP_KEY_ARG:
+		if (pos_args++) {
+			fprintf(stderr,
+				"Unrecognized positional argument: %s\n", arg);
+			argp_usage(state);
+		}
+		env.bench_name = strdup(arg);
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+	return 0;
+}
+
+static void parse_cmdline_args(int argc, char **argv)
+{
+	static const struct argp argp = {
+		.options = opts,
+		.parser = parse_arg,
+		.doc = argp_program_doc,
+	};
+	if (argp_parse(&argp, argc, argv, 0, NULL, NULL))
+		exit(1);
+	if (!env.list && !env.bench_name) {
+		argp_help(&argp, stderr, ARGP_HELP_DOC, "bench");
+		exit(1);
+	}
+}
+
+static void collect_measurements(long delta_ns);
+
+static __u64 last_time_ns;
+static void sigalarm_handler(int signo)
+{
+	long new_time_ns = get_time_ns();
+	long delta_ns = new_time_ns - last_time_ns;
+
+	collect_measurements(delta_ns);
+
+	last_time_ns = new_time_ns;
+}
+
+/* set up periodic 1-second timer */
+static void setup_timer()
+{
+	static struct sigaction sigalarm_action = {
+		.sa_handler = sigalarm_handler,
+	};
+	struct itimerval timer_settings = {};
+	int err;
+
+	last_time_ns = get_time_ns();
+	err = sigaction(SIGALRM, &sigalarm_action, NULL);
+	if (err < 0) {
+		fprintf(stderr, "failed to install SIGALARM handler: %d\n", -errno);
+		exit(1);
+	}
+	timer_settings.it_interval.tv_sec = 1;
+	timer_settings.it_value.tv_sec = 1;
+	err = setitimer(ITIMER_REAL, &timer_settings, NULL);
+	if (err < 0) {
+		fprintf(stderr, "failed to arm interval timer: %d\n", -errno);
+		exit(1);
+	}
+}
+
+static void set_thread_affinity(pthread_t thread, int cpu)
+{
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpu, &cpuset);
+	if (pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset)) {
+		fprintf(stderr, "setting affinity to CPU #%d failed: %d\n",
+			cpu, errno);
+		exit(1);
+	}
+}
+
+static int next_cpu(struct cpu_set *cpu_set)
+{
+	if (cpu_set->cpus) {
+		int i;
+
+		/* find next available CPU */
+		for (i = cpu_set->next_cpu; i < cpu_set->cpus_len; i++) {
+			if (cpu_set->cpus[i]) {
+				cpu_set->next_cpu = i + 1;
+				return i;
+			}
+		}
+		fprintf(stderr, "Not enough CPUs specified, need CPU #%d or higher.\n", i);
+		exit(1);
+	}
+
+	return cpu_set->next_cpu++;
+}
+
+static struct bench_state {
+	int res_cnt;
+	struct bench_res *results;
+	pthread_t *consumers;
+	pthread_t *producers;
+} state;
+
+const struct bench *bench = NULL;
+
+extern const struct bench bench_count_global;
+extern const struct bench bench_count_local;
+
+static const struct bench *benchs[] = {
+	&bench_count_global,
+	&bench_count_local,
+};
+
+static void setup_benchmark()
+{
+	int i, err;
+
+	if (!env.bench_name) {
+		fprintf(stderr, "benchmark name is not specified\n");
+		exit(1);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(benchs); i++) {
+		if (strcmp(benchs[i]->name, env.bench_name) == 0) {
+			bench = benchs[i];
+			break;
+		}
+	}
+	if (!bench) {
+		fprintf(stderr, "benchmark '%s' not found\n", env.bench_name);
+		exit(1);
+	}
+
+	printf("Setting up benchmark '%s'...\n", bench->name);
+
+	state.producers = calloc(env.producer_cnt, sizeof(*state.producers));
+	state.consumers = calloc(env.consumer_cnt, sizeof(*state.consumers));
+	state.results = calloc(env.duration_sec + env.warmup_sec + 2,
+			       sizeof(*state.results));
+	if (!state.producers || !state.consumers || !state.results)
+		exit(1);
+
+	if (bench->validate)
+		bench->validate();
+	if (bench->setup)
+		bench->setup();
+
+	for (i = 0; i < env.consumer_cnt; i++) {
+		err = pthread_create(&state.consumers[i], NULL,
+				     bench->consumer_thread, (void *)(long)i);
+		if (err) {
+			fprintf(stderr, "failed to create consumer thread #%d: %d\n",
+				i, -errno);
+			exit(1);
+		}
+		if (env.affinity)
+			set_thread_affinity(state.consumers[i],
+					    next_cpu(&env.cons_cpus));
+	}
+
+	/* unless explicit producer CPU list is specified, continue after
+	 * last consumer CPU
+	 */
+	if (!env.prod_cpus.cpus)
+		env.prod_cpus.next_cpu = env.cons_cpus.next_cpu;
+
+	for (i = 0; i < env.producer_cnt; i++) {
+		err = pthread_create(&state.producers[i], NULL,
+				     bench->producer_thread, (void *)(long)i);
+		if (err) {
+			fprintf(stderr, "failed to create producer thread #%d: %d\n",
+				i, -errno);
+			exit(1);
+		}
+		if (env.affinity)
+			set_thread_affinity(state.producers[i],
+					    next_cpu(&env.prod_cpus));
+	}
+
+	printf("Benchmark '%s' started.\n", bench->name);
+}
+
+static pthread_mutex_t bench_done_mtx = PTHREAD_MUTEX_INITIALIZER;
+static pthread_cond_t bench_done = PTHREAD_COND_INITIALIZER;
+
+static void collect_measurements(long delta_ns) {
+	int iter = state.res_cnt++;
+	struct bench_res *res = &state.results[iter];
+
+	bench->measure(res);
+
+	if (bench->report_progress)
+		bench->report_progress(iter, res, delta_ns);
+
+	if (iter == env.duration_sec + env.warmup_sec) {
+		pthread_mutex_lock(&bench_done_mtx);
+		pthread_cond_signal(&bench_done);
+		pthread_mutex_unlock(&bench_done_mtx);
+	}
+}
+
+int main(int argc, char **argv)
+{
+	parse_cmdline_args(argc, argv);
+
+	if (env.list) {
+		int i;
+
+		printf("Available benchmarks:\n");
+		for (i = 0; i < ARRAY_SIZE(benchs); i++) {
+			printf("- %s\n", benchs[i]->name);
+		}
+		return 0;
+	}
+
+	setup_benchmark();
+
+	setup_timer();
+
+	pthread_mutex_lock(&bench_done_mtx);
+	pthread_cond_wait(&bench_done, &bench_done_mtx);
+	pthread_mutex_unlock(&bench_done_mtx);
+
+	if (bench->report_final)
+		/* skip first sample */
+		bench->report_final(state.results + env.warmup_sec,
+				    state.res_cnt - env.warmup_sec);
+
+	return 0;
+}
+
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#pragma once
+#include <stdlib.h>
+#include <stdbool.h>
+#include <linux/err.h>
+#include <errno.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <math.h>
+#include <time.h>
+#include <sys/syscall.h>
+
+struct cpu_set {
+	bool *cpus;
+	int cpus_len;
+	int next_cpu;
+};
+
+struct env {
+	char *bench_name;
+	int duration_sec;
+	int warmup_sec;
+	bool verbose;
+	bool list;
+	bool affinity;
+	int consumer_cnt;
+	int producer_cnt;
+	struct cpu_set prod_cpus;
+	struct cpu_set cons_cpus;
+};
+
+struct bench_res {
+	long hits;
+	long drops;
+};
+
+struct bench {
+	const char *name;
+	void (*validate)();
+	void (*setup)();
+	void *(*producer_thread)(void *ctx);
+	void *(*consumer_thread)(void *ctx);
+	void (*measure)(struct bench_res* res);
+	void (*report_progress)(int iter, struct bench_res* res, long delta_ns);
+	void (*report_final)(struct bench_res res[], int res_cnt);
+};
+
+struct counter {
+	long value;
+} __attribute__((aligned(128)));
+
+extern struct env env;
+extern const struct bench *bench;
+
+void setup_libbpf();
+void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns);
+void hits_drops_report_final(struct bench_res res[], int res_cnt);
+
+static inline __u64 get_time_ns() {
+	struct timespec t;
+
+	clock_gettime(CLOCK_MONOTONIC, &t);
+
+	return (u64)t.tv_sec * 1000000000 + t.tv_nsec;
+}
+
+static inline void atomic_inc(long *value)
+{
+	(void)__atomic_add_fetch(value, 1, __ATOMIC_RELAXED);
+}
+
+static inline void atomic_add(long *value, long n)
+{
+	(void)__atomic_add_fetch(value, n, __ATOMIC_RELAXED);
+}
+
+static inline long atomic_swap(long *value, long n)
+{
+	return __atomic_exchange_n(value, n, __ATOMIC_RELAXED);
+}
--- a/tools/testing/selftests/bpf/benchs/bench_count.c
+++ b/tools/testing/selftests/bpf/benchs/bench_count.c
@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bench.h"
+
+/* COUNT-GLOBAL benchmark */
+
+static struct count_global_ctx {
+	struct counter hits;
+} count_global_ctx;
+
+static void *count_global_producer(void *input)
+{
+	struct count_global_ctx *ctx = &count_global_ctx;
+
+	while (true) {
+		atomic_inc(&ctx->hits.value);
+	}
+	return NULL;
+}
+
+static void *count_global_consumer(void *input)
+{
+	return NULL;
+}
+
+static void count_global_measure(struct bench_res *res)
+{
+	struct count_global_ctx *ctx = &count_global_ctx;
+
+	res->hits = atomic_swap(&ctx->hits.value, 0);
+}
+
+/* COUNT-local benchmark */
+
+static struct count_local_ctx {
+	struct counter *hits;
+} count_local_ctx;
+
+static void count_local_setup()
+{
+	struct count_local_ctx *ctx = &count_local_ctx;
+
+	ctx->hits = calloc(env.consumer_cnt, sizeof(*ctx->hits));
+	if (!ctx->hits)
+		exit(1);
+}
+
+static void *count_local_producer(void *input)
+{
+	struct count_local_ctx *ctx = &count_local_ctx;
+	int idx = (long)input;
+
+	while (true) {
+		atomic_inc(&ctx->hits[idx].value);
+	}
+	return NULL;
+}
+
+static void *count_local_consumer(void *input)
+{
+	return NULL;
+}
+
+static void count_local_measure(struct bench_res *res)
+{
+	struct count_local_ctx *ctx = &count_local_ctx;
+	int i;
+
+	for (i = 0; i < env.producer_cnt; i++) {
+		res->hits += atomic_swap(&ctx->hits[i].value, 0);
+	}
+}
+
+const struct bench bench_count_global = {
+	.name = "count-global",
+	.producer_thread = count_global_producer,
+	.consumer_thread = count_global_consumer,
+	.measure = count_global_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_count_local = {
+	.name = "count-local",
+	.setup = count_local_setup,
+	.producer_thread = count_local_producer,
+	.consumer_thread = count_local_consumer,
+	.measure = count_local_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};