[v3] examples/distributor: detect high frequency cores

Message ID 20190329131520.10653-1-david.hunt@intel.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers
Series [v3] examples/distributor: detect high frequency cores |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/mellanox-Performance-Testing fail Performance Testing issues
ci/intel-Performance-Testing success Performance Testing PASS
ci/Intel-compilation success Compilation OK

Commit Message

Hunt, David March 29, 2019, 1:15 p.m. UTC
  The distributor application is bottlenecked by the distributor core,
so if we can give more frequency to this core, then the overall
performance of the application may increase.

This patch uses the rte_power_get_capabilities() API to query the
cores provided in the core mask, and if any high frequency cores are
found (e.g. Turbo Boost is enabled), we will pin the distributor
workload to that core.

Signed-off-by: Liang Ma <liang.j.ma@intel.com>
Signed-off-by: David Hunt <david.hunt@intel.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
---
 examples/distributor/main.c      | 200 ++++++++++++++++++++++++-------
 examples/distributor/meson.build |   2 +-
 2 files changed, 155 insertions(+), 47 deletions(-)
  

Comments

Hunt, David April 1, 2019, 9:07 a.m. UTC | #1
Hi Thomas

On 29/3/2019 1:15 PM, David Hunt wrote:
> The distributor application is bottlenecked by the distributor core,
> so if we can give more frequency to this core, then the overall
> performance of the application may increase.
>
> This patch uses the rte_power_get_capabilities() API to query the
> cores provided in the core mask, and if any high frequency cores are
> found (e.g. Turbo Boost is enabled), we will pin the distributor
> workload to that core.
>
> Signed-off-by: Liang Ma <liang.j.ma@intel.com>
> Signed-off-by: David Hunt <david.hunt@intel.com>
> Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
> ---


Please wait for v4, I'm working on a change for later today.

Thanks,
Dave.
  

Patch

diff --git a/examples/distributor/main.c b/examples/distributor/main.c
index 03a05e3d9..3ade4e461 100644
--- a/examples/distributor/main.c
+++ b/examples/distributor/main.c
@@ -16,6 +16,7 @@ 
 #include <rte_prefetch.h>
 #include <rte_distributor.h>
 #include <rte_pause.h>
+#include <rte_power.h>
 
 #define RX_RING_SIZE 1024
 #define TX_RING_SIZE 1024
@@ -37,6 +38,7 @@  volatile uint8_t quit_signal;
 volatile uint8_t quit_signal_rx;
 volatile uint8_t quit_signal_dist;
 volatile uint8_t quit_signal_work;
+unsigned int power_lib_initialised;
 
 static volatile struct app_stats {
 	struct {
@@ -281,6 +283,8 @@  lcore_rx(struct lcore_params *p)
 		if (++port == nb_ports)
 			port = 0;
 	}
+	if (power_lib_initialised)
+		rte_power_exit(rte_lcore_id());
 	/* set worker & tx threads quit flag */
 	printf("\nCore %u exiting rx task.\n", rte_lcore_id());
 	quit_signal = 1;
@@ -363,7 +367,8 @@  lcore_distributor(struct lcore_params *p)
 	}
 	printf("\nCore %u exiting distributor task.\n", rte_lcore_id());
 	quit_signal_work = 1;
-
+	if (power_lib_initialised)
+		rte_power_exit(rte_lcore_id());
 	rte_distributor_flush(d);
 	/* Unblock any returns so workers can exit */
 	rte_distributor_clear_returns(d);
@@ -435,6 +440,8 @@  lcore_tx(struct rte_ring *in_r)
 			}
 		}
 	}
+	if (power_lib_initialised)
+		rte_power_exit(rte_lcore_id());
 	printf("\nCore %u exiting tx task.\n", rte_lcore_id());
 	return 0;
 }
@@ -575,9 +582,33 @@  lcore_worker(struct lcore_params *p)
 		if (num > 0)
 			app_stats.worker_bursts[p->worker_id][num-1]++;
 	}
+	if (power_lib_initialised)
+		rte_power_exit(rte_lcore_id());
+	rte_free(p);
 	return 0;
 }
 
+static int
+init_power_library(void)
+{
+	int ret = 0, lcore_id;
+	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
+		/* init power management library */
+		ret = rte_power_init(lcore_id);
+		if (ret) {
+			RTE_LOG(ERR, POWER,
+				"Library initialization failed on core %u\n",
+				lcore_id);
+			/*
+			 * Return on first failure, we'll fall back
+			 * to non-power operation
+			 */
+			return ret;
+		}
+	}
+	return ret;
+}
+
 /* display usage */
 static void
 print_usage(const char *prgname)
@@ -657,7 +688,9 @@  main(int argc, char *argv[])
 	struct rte_distributor *d;
 	struct rte_ring *dist_tx_ring;
 	struct rte_ring *rx_dist_ring;
-	unsigned lcore_id, worker_id = 0;
+	struct rte_power_core_capabilities lcore_cap;
+	unsigned int lcore_id, worker_id = 0;
+	int distr_core_id = -1, rx_core_id = -1, tx_core_id = -1;
 	unsigned nb_ports;
 	uint16_t portid;
 	uint16_t nb_ports_available;
@@ -687,6 +720,9 @@  main(int argc, char *argv[])
 				"1 lcore for packet TX\n"
 				"and at least 1 lcore for worker threads\n");
 
+	if (init_power_library() == 0)
+		power_lib_initialised = 1;
+
 	nb_ports = rte_eth_dev_count_avail();
 	if (nb_ports == 0)
 		rte_exit(EXIT_FAILURE, "Error: no ethernet ports detected\n");
@@ -742,54 +778,122 @@  main(int argc, char *argv[])
 	if (rx_dist_ring == NULL)
 		rte_exit(EXIT_FAILURE, "Cannot create output ring\n");
 
+	if (power_lib_initialised) {
+		/*
+		 * Here we'll pre-assign lcore ids to the rx, tx and
+		 * distributor workloads if there's higher frequency
+		 * on those cores e.g. if Turbo Boost is enabled.
+		 * It's also worth mentioning that it will assign cores in a
+		 * specific order, so that if there's less than three
+		 * available, the higher frequency cores will go to the
+		 * distributor first, then rx, then tx.
+		 */
+		RTE_LCORE_FOREACH_SLAVE(lcore_id) {
+
+			rte_power_get_capabilities(lcore_id, &lcore_cap);
+
+			if (lcore_cap.turbo == 1) {
+				if (distr_core_id < 0) {
+					distr_core_id = lcore_id;
+					printf("Distributor on priority core %d\n",
+						lcore_id);
+					continue;
+				}
+				if (rx_core_id < 0) {
+					rx_core_id = lcore_id;
+					printf("Rx on priority core %d\n",
+						lcore_id);
+					continue;
+				}
+				if (tx_core_id < 0) {
+					tx_core_id = lcore_id;
+					printf("Tx on priority core %d\n",
+						lcore_id);
+					continue;
+				}
+			}
+		}
+	}
+
+	/*
+	 * If there's any of the key workloads left without an lcore_id
+	 * after the high performing core assignment above, pre-assign
+	 * them here.
+	 */
 	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
-		if (worker_id == rte_lcore_count() - 3) {
-			printf("Starting distributor on lcore_id %d\n",
-					lcore_id);
-			/* distributor core */
-			struct lcore_params *p =
-					rte_malloc(NULL, sizeof(*p), 0);
-			if (!p)
-				rte_panic("malloc failure\n");
-			*p = (struct lcore_params){worker_id, d,
-				rx_dist_ring, dist_tx_ring, mbuf_pool};
-			rte_eal_remote_launch(
-				(lcore_function_t *)lcore_distributor,
-				p, lcore_id);
-		} else if (worker_id == rte_lcore_count() - 4) {
-			printf("Starting tx  on worker_id %d, lcore_id %d\n",
-					worker_id, lcore_id);
-			/* tx core */
-			rte_eal_remote_launch((lcore_function_t *)lcore_tx,
-					dist_tx_ring, lcore_id);
-		} else if (worker_id == rte_lcore_count() - 2) {
-			printf("Starting rx on worker_id %d, lcore_id %d\n",
-					worker_id, lcore_id);
-			/* rx core */
-			struct lcore_params *p =
-					rte_malloc(NULL, sizeof(*p), 0);
-			if (!p)
-				rte_panic("malloc failure\n");
-			*p = (struct lcore_params){worker_id, d, rx_dist_ring,
-					dist_tx_ring, mbuf_pool};
-			rte_eal_remote_launch((lcore_function_t *)lcore_rx,
-					p, lcore_id);
-		} else {
-			printf("Starting worker on worker_id %d, lcore_id %d\n",
-					worker_id, lcore_id);
-			struct lcore_params *p =
-					rte_malloc(NULL, sizeof(*p), 0);
-			if (!p)
-				rte_panic("malloc failure\n");
-			*p = (struct lcore_params){worker_id, d, rx_dist_ring,
-					dist_tx_ring, mbuf_pool};
-
-			rte_eal_remote_launch((lcore_function_t *)lcore_worker,
-					p, lcore_id);
+		if (lcore_id == (unsigned int)distr_core_id ||
+				lcore_id == (unsigned int)rx_core_id ||
+				lcore_id == (unsigned int)tx_core_id)
+			continue;
+		if (distr_core_id < 0) {
+			distr_core_id = lcore_id;
+			printf("Distributor on core %d\n", lcore_id);
+			continue;
 		}
-		worker_id++;
+		if (rx_core_id < 0) {
+			rx_core_id = lcore_id;
+			printf("Rx on core %d\n", lcore_id);
+			continue;
+		}
+		if (tx_core_id < 0) {
+			tx_core_id = lcore_id;
+			printf("Tx on core %d\n", lcore_id);
+			continue;
+		}
+	}
+
+	printf(" tx id %d, dist id %d, rx id %d\n",
+			tx_core_id,
+			distr_core_id,
+			rx_core_id);
+
+	/*
+	 * Kick off all the worker threads first, avoiding the pre-assigned
+	 * lcore_ids for tx, rx and distributor workloads.
+	 */
+	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
+		if (lcore_id == (unsigned int)distr_core_id ||
+				lcore_id == (unsigned int)rx_core_id ||
+				lcore_id == (unsigned int)tx_core_id)
+			continue;
+		printf("Starting thread %d as worker, lcore_id %d\n",
+				worker_id, lcore_id);
+		struct lcore_params *p =
+			rte_malloc(NULL, sizeof(*p), 0);
+		if (!p)
+			rte_panic("malloc failure\n");
+		*p = (struct lcore_params){worker_id++, d, rx_dist_ring,
+			dist_tx_ring, mbuf_pool};
+
+		rte_eal_remote_launch((lcore_function_t *)lcore_worker,
+				p, lcore_id);
 	}
 
+	/* Start tx core */
+	rte_eal_remote_launch((lcore_function_t *)lcore_tx,
+			dist_tx_ring, tx_core_id);
+
+	/* Start distributor core */
+	struct lcore_params *pd =
+		rte_malloc(NULL, sizeof(*pd), 0);
+	if (!pd)
+		rte_panic("malloc failure\n");
+	*pd = (struct lcore_params){worker_id++, d,
+		rx_dist_ring, dist_tx_ring, mbuf_pool};
+	rte_eal_remote_launch(
+			(lcore_function_t *)lcore_distributor,
+			pd, distr_core_id);
+
+	/* Start rx core */
+	struct lcore_params *pr =
+		rte_malloc(NULL, sizeof(*pr), 0);
+	if (!pr)
+		rte_panic("malloc failure\n");
+	*pr = (struct lcore_params){worker_id++, d, rx_dist_ring,
+		dist_tx_ring, mbuf_pool};
+	rte_eal_remote_launch((lcore_function_t *)lcore_rx,
+			pr, rx_core_id);
+
 	freq = rte_get_timer_hz();
 	t = rte_rdtsc() + freq;
 	while (!quit_signal_dist) {
@@ -806,5 +910,9 @@  main(int argc, char *argv[])
 	}
 
 	print_stats();
+
+	rte_free(pd);
+	rte_free(pr);
+
 	return 0;
 }
diff --git a/examples/distributor/meson.build b/examples/distributor/meson.build
index 88c001f56..8cf2ca1da 100644
--- a/examples/distributor/meson.build
+++ b/examples/distributor/meson.build
@@ -6,7 +6,7 @@ 
 # To build this example as a standalone application with an already-installed
 # DPDK instance, use 'make'
 
-deps += 'distributor'
+deps += ['distributor', 'power']
 sources = files(
 	'main.c'
 )