[RFC,v6,4/6] test/ring: add perf tests for configurable element size ring

diff --git a/app/test/Makefile b/app/test/Makefile
index 483865b4a..6f168881c 100644
--- a/app/test/Makefile
+++ b/app/test/Makefile
@@ -79,6 +79,7 @@  SRCS-y += test_rand_perf.c
 SRCS-y += test_ring.c
 SRCS-y += test_ring_elem.c
 SRCS-y += test_ring_perf.c
+SRCS-y += test_ring_perf_elem.c
 SRCS-y += test_pmd_perf.c
 
 ifeq ($(CONFIG_RTE_LIBRTE_TABLE),y)
diff --git a/app/test/meson.build b/app/test/meson.build
index 1ca25c00a..634cbbf26 100644
--- a/app/test/meson.build
+++ b/app/test/meson.build
@@ -102,6 +102,7 @@  test_sources = files('commands.c',
 	'test_ring.c',
 	'test_ring_elem.c',
 	'test_ring_perf.c',
+	'test_ring_perf_elem.c',
 	'test_rwlock.c',
 	'test_sched.c',
 	'test_service_cores.c',
diff --git a/app/test/test_ring_perf_elem.c b/app/test/test_ring_perf_elem.c
new file mode 100644
index 000000000..402b7877a
--- /dev/null
+++ b/app/test/test_ring_perf_elem.c
@@ -0,0 +1,419 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2014 Intel Corporation
+ */
+
+
+#include <stdio.h>
+#include <inttypes.h>
+#include <rte_ring.h>
+#include <rte_ring_elem.h>
+#include <rte_cycles.h>
+#include <rte_launch.h>
+#include <rte_pause.h>
+
+#include "test.h"
+
+/*
+ * Ring
+ * ====
+ *
+ * Measures performance of various operations using rdtsc
+ *  * Empty ring dequeue
+ *  * Enqueue/dequeue of bursts in 1 threads
+ *  * Enqueue/dequeue of bursts in 2 threads
+ */
+
+#define RING_NAME "RING_PERF"
+#define RING_SIZE 4096
+#define MAX_BURST 64
+
+/*
+ * the sizes to enqueue and dequeue in testing
+ * (marked volatile so they won't be seen as compile-time constants)
+ */
+static const volatile unsigned bulk_sizes[] = { 8, 32 };
+
+struct lcore_pair {
+	unsigned c1, c2;
+};
+
+static volatile unsigned lcore_count;
+
+/**** Functions to analyse our core mask to get cores for different tests ***/
+
+static int
+get_two_hyperthreads(struct lcore_pair *lcp)
+{
+	unsigned id1, id2;
+	unsigned c1, c2, s1, s2;
+	RTE_LCORE_FOREACH(id1) {
+		/* inner loop just re-reads all id's. We could skip the
+		 * first few elements, but since number of cores is small
+		 * there is little point
+		 */
+		RTE_LCORE_FOREACH(id2) {
+			if (id1 == id2)
+				continue;
+
+			c1 = rte_lcore_to_cpu_id(id1);
+			c2 = rte_lcore_to_cpu_id(id2);
+			s1 = rte_lcore_to_socket_id(id1);
+			s2 = rte_lcore_to_socket_id(id2);
+			if ((c1 == c2) && (s1 == s2)) {
+				lcp->c1 = id1;
+				lcp->c2 = id2;
+				return 0;
+			}
+		}
+	}
+	return 1;
+}
+
+static int
+get_two_cores(struct lcore_pair *lcp)
+{
+	unsigned id1, id2;
+	unsigned c1, c2, s1, s2;
+	RTE_LCORE_FOREACH(id1) {
+		RTE_LCORE_FOREACH(id2) {
+			if (id1 == id2)
+				continue;
+
+			c1 = rte_lcore_to_cpu_id(id1);
+			c2 = rte_lcore_to_cpu_id(id2);
+			s1 = rte_lcore_to_socket_id(id1);
+			s2 = rte_lcore_to_socket_id(id2);
+			if ((c1 != c2) && (s1 == s2)) {
+				lcp->c1 = id1;
+				lcp->c2 = id2;
+				return 0;
+			}
+		}
+	}
+	return 1;
+}
+
+static int
+get_two_sockets(struct lcore_pair *lcp)
+{
+	unsigned id1, id2;
+	unsigned s1, s2;
+	RTE_LCORE_FOREACH(id1) {
+		RTE_LCORE_FOREACH(id2) {
+			if (id1 == id2)
+				continue;
+			s1 = rte_lcore_to_socket_id(id1);
+			s2 = rte_lcore_to_socket_id(id2);
+			if (s1 != s2) {
+				lcp->c1 = id1;
+				lcp->c2 = id2;
+				return 0;
+			}
+		}
+	}
+	return 1;
+}
+
+/* Get cycle counts for dequeuing from an empty ring. Should be 2 or 3 cycles */
+static void
+test_empty_dequeue(struct rte_ring *r)
+{
+	const unsigned iter_shift = 26;
+	const unsigned iterations = 1<<iter_shift;
+	unsigned i = 0;
+	uint32_t burst[MAX_BURST];
+
+	const uint64_t sc_start = rte_rdtsc();
+	for (i = 0; i < iterations; i++)
+		rte_ring_sc_dequeue_bulk_elem(r, burst, 8, bulk_sizes[0], NULL);
+	const uint64_t sc_end = rte_rdtsc();
+
+	const uint64_t mc_start = rte_rdtsc();
+	for (i = 0; i < iterations; i++)
+		rte_ring_mc_dequeue_bulk_elem(r, burst, 8, bulk_sizes[0], NULL);
+	const uint64_t mc_end = rte_rdtsc();
+
+	printf("SC empty dequeue: %.2F\n",
+			(double)(sc_end-sc_start) / iterations);
+	printf("MC empty dequeue: %.2F\n",
+			(double)(mc_end-mc_start) / iterations);
+}
+
+/*
+ * for the separate enqueue and dequeue threads they take in one param
+ * and return two. Input = burst size, output = cycle average for sp/sc & mp/mc
+ */
+struct thread_params {
+	struct rte_ring *r;
+	unsigned size;        /* input value, the burst size */
+	double spsc, mpmc;    /* output value, the single or multi timings */
+};
+
+/*
+ * Function that uses rdtsc to measure timing for ring enqueue. Needs pair
+ * thread running dequeue_bulk function
+ */
+static int
+enqueue_bulk(void *p)
+{
+	const unsigned iter_shift = 23;
+	const unsigned iterations = 1<<iter_shift;
+	struct thread_params *params = p;
+	struct rte_ring *r = params->r;
+	const unsigned size = params->size;
+	unsigned i;
+	uint32_t burst[MAX_BURST] = {0};
+
+#ifdef RTE_USE_C11_MEM_MODEL
+	if (__atomic_add_fetch(&lcore_count, 1, __ATOMIC_RELAXED) != 2)
+#else
+	if (__sync_add_and_fetch(&lcore_count, 1) != 2)
+#endif
+		while (lcore_count != 2)
+			rte_pause();
+
+	const uint64_t sp_start = rte_rdtsc();
+	for (i = 0; i < iterations; i++)
+		while (rte_ring_sp_enqueue_bulk_elem(r, burst, 8, size, NULL)
+				== 0)
+			rte_pause();
+	const uint64_t sp_end = rte_rdtsc();
+
+	const uint64_t mp_start = rte_rdtsc();
+	for (i = 0; i < iterations; i++)
+		while (rte_ring_mp_enqueue_bulk_elem(r, burst, 8, size, NULL)
+				== 0)
+			rte_pause();
+	const uint64_t mp_end = rte_rdtsc();
+
+	params->spsc = ((double)(sp_end - sp_start))/(iterations*size);
+	params->mpmc = ((double)(mp_end - mp_start))/(iterations*size);
+	return 0;
+}
+
+/*
+ * Function that uses rdtsc to measure timing for ring dequeue. Needs pair
+ * thread running enqueue_bulk function
+ */
+static int
+dequeue_bulk(void *p)
+{
+	const unsigned iter_shift = 23;
+	const unsigned iterations = 1<<iter_shift;
+	struct thread_params *params = p;
+	struct rte_ring *r = params->r;
+	const unsigned size = params->size;
+	unsigned i;
+	uint32_t burst[MAX_BURST] = {0};
+
+#ifdef RTE_USE_C11_MEM_MODEL
+	if (__atomic_add_fetch(&lcore_count, 1, __ATOMIC_RELAXED) != 2)
+#else
+	if (__sync_add_and_fetch(&lcore_count, 1) != 2)
+#endif
+		while (lcore_count != 2)
+			rte_pause();
+
+	const uint64_t sc_start = rte_rdtsc();
+	for (i = 0; i < iterations; i++)
+		while (rte_ring_sc_dequeue_bulk_elem(r, burst, 8, size, NULL)
+				== 0)
+			rte_pause();
+	const uint64_t sc_end = rte_rdtsc();
+
+	const uint64_t mc_start = rte_rdtsc();
+	for (i = 0; i < iterations; i++)
+		while (rte_ring_mc_dequeue_bulk_elem(r, burst, 8, size, NULL)
+				== 0)
+			rte_pause();
+	const uint64_t mc_end = rte_rdtsc();
+
+	params->spsc = ((double)(sc_end - sc_start))/(iterations*size);
+	params->mpmc = ((double)(mc_end - mc_start))/(iterations*size);
+	return 0;
+}
+
+/*
+ * Function that calls the enqueue and dequeue bulk functions on pairs of cores.
+ * used to measure ring perf between hyperthreads, cores and sockets.
+ */
+static void
+run_on_core_pair(struct lcore_pair *cores, struct rte_ring *r,
+		lcore_function_t f1, lcore_function_t f2)
+{
+	struct thread_params param1 = {0}, param2 = {0};
+	unsigned i;
+	for (i = 0; i < sizeof(bulk_sizes)/sizeof(bulk_sizes[0]); i++) {
+		lcore_count = 0;
+		param1.size = param2.size = bulk_sizes[i];
+		param1.r = param2.r = r;
+		if (cores->c1 == rte_get_master_lcore()) {
+			rte_eal_remote_launch(f2, &param2, cores->c2);
+			f1(&param1);
+			rte_eal_wait_lcore(cores->c2);
+		} else {
+			rte_eal_remote_launch(f1, &param1, cores->c1);
+			rte_eal_remote_launch(f2, &param2, cores->c2);
+			rte_eal_wait_lcore(cores->c1);
+			rte_eal_wait_lcore(cores->c2);
+		}
+		printf("SP/SC bulk enq/dequeue (size: %u): %.2F\n",
+				bulk_sizes[i], param1.spsc + param2.spsc);
+		printf("MP/MC bulk enq/dequeue (size: %u): %.2F\n",
+				bulk_sizes[i], param1.mpmc + param2.mpmc);
+	}
+}
+
+/*
+ * Test function that determines how long an enqueue + dequeue of a single item
+ * takes on a single lcore. Result is for comparison with the bulk enq+deq.
+ */
+static void
+test_single_enqueue_dequeue(struct rte_ring *r)
+{
+	const unsigned iter_shift = 24;
+	const unsigned iterations = 1<<iter_shift;
+	unsigned i = 0;
+	uint32_t burst[2];
+
+	const uint64_t sc_start = rte_rdtsc();
+	for (i = 0; i < iterations; i++) {
+		rte_ring_sp_enqueue_elem(r, burst, 8);
+		rte_ring_sc_dequeue_elem(r, burst, 8);
+	}
+	const uint64_t sc_end = rte_rdtsc();
+
+	const uint64_t mc_start = rte_rdtsc();
+	for (i = 0; i < iterations; i++) {
+		rte_ring_mp_enqueue_elem(r, burst, 8);
+		rte_ring_mc_dequeue_elem(r, burst, 8);
+	}
+	const uint64_t mc_end = rte_rdtsc();
+
+	printf("SP/SC single enq/dequeue: %.2F\n",
+			((double)(sc_end-sc_start)) / iterations);
+	printf("MP/MC single enq/dequeue: %.2F\n",
+			((double)(mc_end-mc_start)) / iterations);
+}
+
+/*
+ * Test that does both enqueue and dequeue on a core using the burst() API calls
+ * instead of the bulk() calls used in other tests. Results should be the same
+ * as for the bulk function called on a single lcore.
+ */
+static void
+test_burst_enqueue_dequeue(struct rte_ring *r)
+{
+	const unsigned iter_shift = 23;
+	const unsigned iterations = 1<<iter_shift;
+	unsigned sz, i = 0;
+	uint32_t burst[MAX_BURST] = {0};
+
+	for (sz = 0; sz < sizeof(bulk_sizes)/sizeof(bulk_sizes[0]); sz++) {
+		const uint64_t sc_start = rte_rdtsc();
+		for (i = 0; i < iterations; i++) {
+			rte_ring_sp_enqueue_burst_elem(r, burst, 8,
+					bulk_sizes[sz], NULL);
+			rte_ring_sc_dequeue_burst_elem(r, burst, 8,
+					bulk_sizes[sz], NULL);
+		}
+		const uint64_t sc_end = rte_rdtsc();
+
+		const uint64_t mc_start = rte_rdtsc();
+		for (i = 0; i < iterations; i++) {
+			rte_ring_mp_enqueue_burst_elem(r, burst, 8,
+					bulk_sizes[sz], NULL);
+			rte_ring_mc_dequeue_burst_elem(r, burst, 8,
+					bulk_sizes[sz], NULL);
+		}
+		const uint64_t mc_end = rte_rdtsc();
+
+		double mc_avg = ((double)(mc_end-mc_start) / iterations) /
+					bulk_sizes[sz];
+		double sc_avg = ((double)(sc_end-sc_start) / iterations) /
+					bulk_sizes[sz];
+
+		printf("SP/SC burst enq/dequeue (size: %u): %.2F\n",
+				bulk_sizes[sz], sc_avg);
+		printf("MP/MC burst enq/dequeue (size: %u): %.2F\n",
+				bulk_sizes[sz], mc_avg);
+	}
+}
+
+/* Times enqueue and dequeue on a single lcore */
+static void
+test_bulk_enqueue_dequeue(struct rte_ring *r)
+{
+	const unsigned iter_shift = 23;
+	const unsigned iterations = 1<<iter_shift;
+	unsigned sz, i = 0;
+	uint32_t burst[MAX_BURST] = {0};
+
+	for (sz = 0; sz < sizeof(bulk_sizes)/sizeof(bulk_sizes[0]); sz++) {
+		const uint64_t sc_start = rte_rdtsc();
+		for (i = 0; i < iterations; i++) {
+			rte_ring_sp_enqueue_bulk_elem(r, burst, 8,
+					bulk_sizes[sz], NULL);
+			rte_ring_sc_dequeue_bulk_elem(r, burst, 8,
+					bulk_sizes[sz], NULL);
+		}
+		const uint64_t sc_end = rte_rdtsc();
+
+		const uint64_t mc_start = rte_rdtsc();
+		for (i = 0; i < iterations; i++) {
+			rte_ring_mp_enqueue_bulk_elem(r, burst, 8,
+					bulk_sizes[sz], NULL);
+			rte_ring_mc_dequeue_bulk_elem(r, burst, 8,
+					bulk_sizes[sz], NULL);
+		}
+		const uint64_t mc_end = rte_rdtsc();
+
+		double sc_avg = ((double)(sc_end-sc_start) /
+				(iterations * bulk_sizes[sz]));
+		double mc_avg = ((double)(mc_end-mc_start) /
+				(iterations * bulk_sizes[sz]));
+
+		printf("SP/SC bulk enq/dequeue (size: %u): %.2F\n",
+				bulk_sizes[sz], sc_avg);
+		printf("MP/MC bulk enq/dequeue (size: %u): %.2F\n",
+				bulk_sizes[sz], mc_avg);
+	}
+}
+
+static int
+test_ring_perf_elem(void)
+{
+	struct lcore_pair cores;
+	struct rte_ring *r = NULL;
+
+	r = rte_ring_create_elem(RING_NAME, RING_SIZE, 8, rte_socket_id(), 0);
+	if (r == NULL)
+		return -1;
+
+	printf("### Testing single element and burst enq/deq ###\n");
+	test_single_enqueue_dequeue(r);
+	test_burst_enqueue_dequeue(r);
+
+	printf("\n### Testing empty dequeue ###\n");
+	test_empty_dequeue(r);
+
+	printf("\n### Testing using a single lcore ###\n");
+	test_bulk_enqueue_dequeue(r);
+
+	if (get_two_hyperthreads(&cores) == 0) {
+		printf("\n### Testing using two hyperthreads ###\n");
+		run_on_core_pair(&cores, r, enqueue_bulk, dequeue_bulk);
+	}
+	if (get_two_cores(&cores) == 0) {
+		printf("\n### Testing using two physical cores ###\n");
+		run_on_core_pair(&cores, r, enqueue_bulk, dequeue_bulk);
+	}
+	if (get_two_sockets(&cores) == 0) {
+		printf("\n### Testing using two NUMA nodes ###\n");
+		run_on_core_pair(&cores, r, enqueue_bulk, dequeue_bulk);
+	}
+	rte_ring_free(r);
+	return 0;
+}
+
+REGISTER_TEST_COMMAND(ring_perf_elem_autotest, test_ring_perf_elem);