[dpdk-dev] [PATCH v3 5/7] l3fwd-power: add interrupt-only mode

[Anatoly Burakov <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>
Tested-by: Yinan Wang <yinan.wang@intel.com>
---
 examples/l3fwd-power/main.c | 188 +++++++++++++++++++++++++++++++++++-
 1 file changed, 185 insertions(+), 3 deletions(-)

diff --git a/examples/l3fwd-power/main.c b/examples/l3fwd-power/main.c
index c02b0a3574..51acbfd87d 100644
--- a/examples/l3fwd-power/main.c
+++ b/examples/l3fwd-power/main.c
@@ -198,7 +198,8 @@ enum appmode {
 	APP_MODE_DEFAULT = 0,
 	APP_MODE_LEGACY,
 	APP_MODE_EMPTY_POLL,
-	APP_MODE_TELEMETRY
+	APP_MODE_TELEMETRY,
+	APP_MODE_INTERRUPT
 };
 
 enum appmode app_mode;
@@ -901,6 +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)
@@ -1440,7 +1605,8 @@ 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);
 }
 
@@ -1585,6 +1751,7 @@ parse_ep_config(const char *q_arg)
 #define CMD_LINE_OPT_PARSE_PTYPE "parse-ptype"
 #define CMD_LINE_OPT_LEGACY "legacy"
 #define CMD_LINE_OPT_EMPTY_POLL "empty-poll"
+#define CMD_LINE_OPT_INTERRUPT_ONLY "interrupt-only"
 #define CMD_LINE_OPT_TELEMETRY "telemetry"
 
 /* Parse the argument given in the command line of the application */
@@ -1606,6 +1773,7 @@ parse_args(int argc, char **argv)
 		{CMD_LINE_OPT_PARSE_PTYPE, 0, 0, 0},
 		{CMD_LINE_OPT_LEGACY, 0, 0, 0},
 		{CMD_LINE_OPT_TELEMETRY, 0, 0, 0},
+		{CMD_LINE_OPT_INTERRUPT_ONLY, 0, 0, 0},
 		{NULL, 0, 0, 0}
 	};
 
@@ -1716,6 +1884,17 @@ parse_args(int argc, char **argv)
 				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 =
@@ -2298,7 +2477,8 @@ 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) {
@@ -2576,6 +2756,8 @@ 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)
-- 
2.17.1