DPDK patches and discussions
 help / color / mirror / Atom feed
From: Anatoly Burakov <anatoly.burakov@intel.com>
To: dev@dpdk.org
Cc: David Hunt <david.hunt@intel.com>,
	liang.j.ma@intel.com, reshma.pattan@intel.com
Subject: [dpdk-dev] [PATCH 3/3] l3fwd-power: add interrupt-only mode
Date: Thu, 28 May 2020 10:13:51 +0100
Message-ID: <ceb97619dcaa91188757e6cf330870a6dfe97de6.1590656906.git.anatoly.burakov@intel.com> (raw)
In-Reply-To: <cover.1590656906.git.anatoly.burakov@intel.com>
In-Reply-To: <cover.1590656906.git.anatoly.burakov@intel.com>

In addition to existing modes, add a mode which is very similar to
legacy mode, but does not do frequency scaling, and thus does not
depend on the power library.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
---
 examples/l3fwd-power/main.c | 215 +++++++++++++++++++++++++++++++++---
 1 file changed, 202 insertions(+), 13 deletions(-)

diff --git a/examples/l3fwd-power/main.c b/examples/l3fwd-power/main.c
index 5cee9d5387..4161e01974 100644
--- a/examples/l3fwd-power/main.c
+++ b/examples/l3fwd-power/main.c
@@ -195,9 +195,11 @@ static int parse_ptype; /**< Parse packet type using rx callback, and */
 			/**< disabled by default */
 
 enum appmode {
-	APP_MODE_LEGACY = 0,
+	APP_MODE_DEFAULT = 0,
+	APP_MODE_LEGACY,
 	APP_MODE_EMPTY_POLL,
-	APP_MODE_TELEMETRY
+	APP_MODE_TELEMETRY,
+	APP_MODE_INTERRUPT
 };
 
 enum appmode app_mode;
@@ -900,6 +902,170 @@ static int event_register(struct lcore_conf *qconf)
 
 	return 0;
 }
+
+/* main processing loop */
+static int main_intr_loop(__rte_unused void *dummy)
+{
+	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
+	unsigned int lcore_id;
+	uint64_t prev_tsc, diff_tsc, cur_tsc;
+	int i, j, nb_rx;
+	uint8_t queueid;
+	uint16_t portid;
+	struct lcore_conf *qconf;
+	struct lcore_rx_queue *rx_queue;
+	uint32_t lcore_rx_idle_count = 0;
+	uint32_t lcore_idle_hint = 0;
+	int intr_en = 0;
+
+	const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) /
+				   US_PER_S * BURST_TX_DRAIN_US;
+
+	prev_tsc = 0;
+
+	lcore_id = rte_lcore_id();
+	qconf = &lcore_conf[lcore_id];
+
+	if (qconf->n_rx_queue == 0) {
+		RTE_LOG(INFO, L3FWD_POWER, "lcore %u has nothing to do\n",
+				lcore_id);
+		return 0;
+	}
+
+	RTE_LOG(INFO, L3FWD_POWER, "entering main interrupt loop on lcore %u\n",
+			lcore_id);
+
+	for (i = 0; i < qconf->n_rx_queue; i++) {
+		portid = qconf->rx_queue_list[i].port_id;
+		queueid = qconf->rx_queue_list[i].queue_id;
+		RTE_LOG(INFO, L3FWD_POWER,
+				" -- lcoreid=%u portid=%u rxqueueid=%hhu\n",
+				lcore_id, portid, queueid);
+	}
+
+	/* add into event wait list */
+	if (event_register(qconf) == 0)
+		intr_en = 1;
+	else
+		RTE_LOG(INFO, L3FWD_POWER, "RX interrupt won't enable.\n");
+
+	while (!is_done()) {
+		stats[lcore_id].nb_iteration_looped++;
+
+		cur_tsc = rte_rdtsc();
+
+		/*
+		 * TX burst queue drain
+		 */
+		diff_tsc = cur_tsc - prev_tsc;
+		if (unlikely(diff_tsc > drain_tsc)) {
+			for (i = 0; i < qconf->n_tx_port; ++i) {
+				portid = qconf->tx_port_id[i];
+				rte_eth_tx_buffer_flush(portid,
+						qconf->tx_queue_id[portid],
+						qconf->tx_buffer[portid]);
+			}
+			prev_tsc = cur_tsc;
+		}
+
+start_rx:
+		/*
+		 * Read packet from RX queues
+		 */
+		lcore_rx_idle_count = 0;
+		for (i = 0; i < qconf->n_rx_queue; ++i) {
+			rx_queue = &(qconf->rx_queue_list[i]);
+			rx_queue->idle_hint = 0;
+			portid = rx_queue->port_id;
+			queueid = rx_queue->queue_id;
+
+			nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst,
+					MAX_PKT_BURST);
+
+			stats[lcore_id].nb_rx_processed += nb_rx;
+			if (unlikely(nb_rx == 0)) {
+				/**
+				 * no packet received from rx queue, try to
+				 * sleep for a while forcing CPU enter deeper
+				 * C states.
+				 */
+				rx_queue->zero_rx_packet_count++;
+
+				if (rx_queue->zero_rx_packet_count <=
+						MIN_ZERO_POLL_COUNT)
+					continue;
+
+				rx_queue->idle_hint = power_idle_heuristic(
+						rx_queue->zero_rx_packet_count);
+				lcore_rx_idle_count++;
+			} else {
+				rx_queue->zero_rx_packet_count = 0;
+			}
+
+			/* Prefetch first packets */
+			for (j = 0; j < PREFETCH_OFFSET && j < nb_rx; j++) {
+				rte_prefetch0(rte_pktmbuf_mtod(
+						pkts_burst[j], void *));
+			}
+
+			/* Prefetch and forward already prefetched packets */
+			for (j = 0; j < (nb_rx - PREFETCH_OFFSET); j++) {
+				rte_prefetch0(rte_pktmbuf_mtod(
+						pkts_burst[j + PREFETCH_OFFSET],
+						void *));
+				l3fwd_simple_forward(
+						pkts_burst[j], portid, qconf);
+			}
+
+			/* Forward remaining prefetched packets */
+			for (; j < nb_rx; j++) {
+				l3fwd_simple_forward(
+						pkts_burst[j], portid, qconf);
+			}
+		}
+
+		if (unlikely(lcore_rx_idle_count == qconf->n_rx_queue)) {
+			/**
+			 * All Rx queues empty in recent consecutive polls,
+			 * sleep in a conservative manner, meaning sleep as
+			 * less as possible.
+			 */
+			for (i = 1,
+			    lcore_idle_hint = qconf->rx_queue_list[0].idle_hint;
+					i < qconf->n_rx_queue; ++i) {
+				rx_queue = &(qconf->rx_queue_list[i]);
+				if (rx_queue->idle_hint < lcore_idle_hint)
+					lcore_idle_hint = rx_queue->idle_hint;
+			}
+
+			if (lcore_idle_hint < SUSPEND_THRESHOLD)
+				/**
+				 * execute "pause" instruction to avoid context
+				 * switch which generally take hundred of
+				 * microseconds for short sleep.
+				 */
+				rte_delay_us(lcore_idle_hint);
+			else {
+				/* suspend until rx interrupt triggers */
+				if (intr_en) {
+					turn_on_off_intr(qconf, 1);
+					sleep_until_rx_interrupt(
+							qconf->n_rx_queue);
+					turn_on_off_intr(qconf, 0);
+					/**
+					 * start receiving packets immediately
+					 */
+					if (likely(!is_done()))
+						goto start_rx;
+				}
+			}
+			stats[lcore_id].sleep_time += lcore_idle_hint;
+		}
+	}
+
+	return 0;
+}
+
 /* main processing loop */
 static int
 main_telemetry_loop(__rte_unused void *dummy)
@@ -1126,7 +1292,7 @@ main_empty_poll_loop(__rte_unused void *dummy)
 }
 /* main processing loop */
 static int
-main_loop(__rte_unused void *dummy)
+main_legacy_loop(__rte_unused void *dummy)
 {
 	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
 	unsigned lcore_id;
@@ -1438,7 +1604,8 @@ print_usage(const char *prgname)
 		"  --empty-poll: enable empty poll detection"
 		" follow (training_flag, high_threshold, med_threshold)\n"
 		" --telemetry: enable telemetry mode, to update"
-		" empty polls, full polls, and core busyness to telemetry\n",
+		" empty polls, full polls, and core busyness to telemetry\n"
+		" --interrupt-only: enable interrupt-only mode\n",
 		prgname);
 }
 
@@ -1582,6 +1749,7 @@ parse_ep_config(const char *q_arg)
 }
 #define CMD_LINE_OPT_PARSE_PTYPE "parse-ptype"
 #define CMD_LINE_OPT_TELEMETRY "telemetry"
+#define CMD_LINE_OPT_INTERRUPT_ONLY "interrupt-only"
 
 /* Parse the argument given in the command line of the application */
 static int
@@ -1601,6 +1769,7 @@ parse_args(int argc, char **argv)
 		{"empty-poll", 1, 0, 0},
 		{CMD_LINE_OPT_PARSE_PTYPE, 0, 0, 0},
 		{CMD_LINE_OPT_TELEMETRY, 0, 0, 0},
+		{CMD_LINE_OPT_INTERRUPT_ONLY, 0, 0, 0},
 		{NULL, 0, 0, 0}
 	};
 
@@ -1674,8 +1843,8 @@ parse_args(int argc, char **argv)
 
 			if (!strncmp(lgopts[option_index].name,
 						"empty-poll", 10)) {
-				if (app_mode == APP_MODE_TELEMETRY) {
-					printf(" empty-poll cannot be enabled as telemetry mode is enabled\n");
+				if (app_mode != APP_MODE_DEFAULT) {
+					printf(" empty-poll mode is mutually exclusive with other modes\n");
 					return -1;
 				}
 				app_mode = APP_MODE_EMPTY_POLL;
@@ -1692,14 +1861,25 @@ parse_args(int argc, char **argv)
 			if (!strncmp(lgopts[option_index].name,
 					CMD_LINE_OPT_TELEMETRY,
 					sizeof(CMD_LINE_OPT_TELEMETRY))) {
-				if (app_mode == APP_MODE_EMPTY_POLL) {
-					printf("telemetry mode cannot be enabled as empty poll mode is enabled\n");
+				if (app_mode != APP_MODE_DEFAULT) {
+					printf(" telemetry mode is mutually exclusive with other modes\n");
 					return -1;
 				}
 				app_mode = APP_MODE_TELEMETRY;
 				printf("telemetry mode is enabled\n");
 			}
 
+			if (!strncmp(lgopts[option_index].name,
+					CMD_LINE_OPT_INTERRUPT_ONLY,
+					sizeof(CMD_LINE_OPT_INTERRUPT_ONLY))) {
+				if (app_mode != APP_MODE_DEFAULT) {
+					printf(" interrupt-only mode is mutually exclusive with other modes\n");
+					return -1;
+				}
+				app_mode = APP_MODE_INTERRUPT;
+				printf("interrupt-only mode is enabled\n");
+			}
+
 			if (!strncmp(lgopts[option_index].name,
 					"enable-jumbo", 12)) {
 				struct option lenopts =
@@ -2253,7 +2433,12 @@ main(int argc, char **argv)
 	if (ret < 0)
 		rte_exit(EXIT_FAILURE, "Invalid L3FWD parameters\n");
 
-	if (app_mode != APP_MODE_TELEMETRY && init_power_library())
+	if (app_mode == APP_MODE_DEFAULT)
+		app_mode = APP_MODE_LEGACY;
+
+	/* only legacy and empty poll mode rely on power library */
+	if ((app_mode == APP_MODE_LEGACY || app_mode == APP_MODE_EMPTY_POLL) &&
+			init_power_library())
 		rte_exit(EXIT_FAILURE, "init_power_library failed\n");
 
 	if (update_lcore_params() < 0)
@@ -2277,7 +2462,8 @@ main(int argc, char **argv)
 	RTE_ETH_FOREACH_DEV(portid) {
 		struct rte_eth_conf local_port_conf = port_conf;
 		/* not all app modes need interrupts */
-		bool need_intr = app_mode == APP_MODE_LEGACY;
+		bool need_intr = app_mode == APP_MODE_LEGACY ||
+				app_mode == APP_MODE_INTERRUPT;
 
 		/* skip ports that are not enabled */
 		if ((enabled_port_mask & (1 << portid)) == 0) {
@@ -2526,12 +2712,12 @@ main(int argc, char **argv)
 
 	/* launch per-lcore init on every lcore */
 	if (app_mode == APP_MODE_LEGACY) {
-		rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER);
+		rte_eal_mp_remote_launch(main_legacy_loop, NULL, CALL_MASTER);
 	} else if (app_mode == APP_MODE_EMPTY_POLL) {
 		empty_poll_stop = false;
 		rte_eal_mp_remote_launch(main_empty_poll_loop, NULL,
 				SKIP_MASTER);
-	} else {
+	} else if (app_mode == APP_MODE_TELEMETRY) {
 		unsigned int i;
 
 		/* Init metrics library */
@@ -2555,6 +2741,8 @@ main(int argc, char **argv)
 				"Returns global power stats. Parameters: None");
 		rte_eal_mp_remote_launch(main_telemetry_loop, NULL,
 						SKIP_MASTER);
+	} else if (app_mode == APP_MODE_INTERRUPT) {
+		rte_eal_mp_remote_launch(main_intr_loop, NULL, CALL_MASTER);
 	}
 
 	if (app_mode == APP_MODE_EMPTY_POLL || app_mode == APP_MODE_TELEMETRY)
@@ -2577,7 +2765,8 @@ main(int argc, char **argv)
 	if (app_mode == APP_MODE_EMPTY_POLL)
 		rte_power_empty_poll_stat_free();
 
-	if (app_mode != APP_MODE_TELEMETRY && deinit_power_library())
+	if ((app_mode == APP_MODE_LEGACY || app_mode == APP_MODE_EMPTY_POLL) &&
+			deinit_power_library())
 		rte_exit(EXIT_FAILURE, "deinit_power_library failed\n");
 
 	if (rte_eal_cleanup() < 0)
-- 
2.17.1

  parent reply	other threads:[~2020-05-28  9:14 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-28  9:13 [dpdk-dev] [PATCH 0/3] Add interrupt-only mode to l3fwd-power Anatoly Burakov
2020-05-28  9:13 ` [dpdk-dev] [PATCH 1/3] l3fwd-power: disable interrupts by default Anatoly Burakov
2020-05-28  9:13 ` [dpdk-dev] [PATCH 2/3] l3fwd-power: only allow supported power library envs Anatoly Burakov
2020-05-28  9:13 ` Anatoly Burakov [this message]
2020-05-29 13:19   ` [dpdk-dev] [PATCH 3/3] l3fwd-power: add interrupt-only mode Harman Kalra
2020-05-29 14:19     ` Burakov, Anatoly
2020-05-30 10:02       ` [dpdk-dev] [EXT] " Harman Kalra
2020-06-01 12:50         ` Burakov, Anatoly
2020-06-02 10:23           ` Harman Kalra
2020-06-02 12:16             ` Harman Kalra
2020-06-15 11:31               ` Burakov, Anatoly
2020-06-15 11:43                 ` Jerin Jacob
2020-06-15 15:05                   ` Burakov, Anatoly
2020-06-15 15:21                     ` Jerin Jacob
2020-06-15 15:45                       ` Burakov, Anatoly
2020-06-15 16:29                         ` Jerin Jacob
2020-06-16  9:31                           ` Burakov, Anatoly
2020-06-16 17:09                             ` Jerin Jacob
2020-06-08  1:24 ` [dpdk-dev] [PATCH 0/3] Add interrupt-only mode to l3fwd-power Wang, Yinan
2020-06-18 17:18 ` [dpdk-dev] [PATCH v2 0/7] " Anatoly Burakov
2020-06-19 10:53   ` [dpdk-dev] [PATCH v3 " Anatoly Burakov
2020-07-11 11:35     ` Thomas Monjalon
2020-06-19 10:53   ` [dpdk-dev] [PATCH v3 1/7] l3fwd-power: disable interrupts by default Anatoly Burakov
2020-06-19 10:53   ` [dpdk-dev] [PATCH v3 2/7] l3fwd-power: only allow supported power library envs Anatoly Burakov
2020-06-19 10:53   ` [dpdk-dev] [PATCH v3 3/7] l3fwd-power: code style and flow fixes Anatoly Burakov
2020-06-19 10:53   ` [dpdk-dev] [PATCH v3 4/7] l3fwd-power: add support for requesting legacy mode Anatoly Burakov
2020-06-19 10:53   ` [dpdk-dev] [PATCH v3 5/7] l3fwd-power: add interrupt-only mode Anatoly Burakov
2020-06-19 10:53   ` [dpdk-dev] [PATCH v3 6/7] power: add API to probe support for a specific env Anatoly Burakov
2020-06-19 10:53   ` [dpdk-dev] [PATCH v3 7/7] l3fwd-power: add auto-selection of default mode Anatoly Burakov
2020-07-11 10:07     ` Thomas Monjalon
2020-06-18 17:18 ` [dpdk-dev] [PATCH v2 1/7] l3fwd-power: disable interrupts by default Anatoly Burakov
2020-06-18 17:18 ` [dpdk-dev] [PATCH v2 2/7] l3fwd-power: only allow supported power library envs Anatoly Burakov
2020-06-18 17:18 ` [dpdk-dev] [PATCH v2 3/7] l3fwd-power: code style and flow fixes Anatoly Burakov
2020-06-18 17:18 ` [dpdk-dev] [PATCH v2 4/7] l3fwd-power: add support for requesting legacy mode Anatoly Burakov
2020-06-18 17:18 ` [dpdk-dev] [PATCH v2 5/7] l3fwd-power: add interrupt-only mode Anatoly Burakov
2020-06-18 17:18 ` [dpdk-dev] [PATCH v2 6/7] power: add API to probe support for a specific env Anatoly Burakov
2020-06-18 17:18 ` [dpdk-dev] [PATCH v2 7/7] l3fwd-power: add auto-selection of default mode Anatoly Burakov
2020-06-19  7:37   ` [dpdk-dev] [EXT] " Harman Kalra
2020-06-19  9:56     ` Burakov, Anatoly

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=ceb97619dcaa91188757e6cf330870a6dfe97de6.1590656906.git.anatoly.burakov@intel.com \
    --to=anatoly.burakov@intel.com \
    --cc=david.hunt@intel.com \
    --cc=dev@dpdk.org \
    --cc=liang.j.ma@intel.com \
    --cc=reshma.pattan@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

DPDK patches and discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ https://inbox.dpdk.org/dev \
		dev@dpdk.org
	public-inbox-index dev

Example config snippet for mirrors.
Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git