#include <rte_string_fns.h>
#include <rte_timer.h>
#include <rte_power.h>
+#include <rte_eal.h>
+#include <rte_spinlock.h>
#define RTE_LOGTYPE_L3FWD_POWER RTE_LOGTYPE_USER1
#define MAX_PKT_BURST 32
-#define MIN_ZERO_POLL_COUNT 5
+#define MIN_ZERO_POLL_COUNT 10
/* around 100ms at 2 Ghz */
#define TIMER_RESOLUTION_CYCLES 200000000ULL
/* ethernet addresses of ports */
static struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS];
+/* ethernet addresses of ports */
+static rte_spinlock_t locks[RTE_MAX_ETHPORTS];
+
/* mask of enabled ports */
static uint32_t enabled_port_mask = 0;
/* Ports set in promiscuous mode off by default. */
#define MAX_TX_QUEUE_PER_PORT RTE_MAX_ETHPORTS
#define MAX_RX_QUEUE_PER_PORT 128
+#define MAX_RX_QUEUE_INTERRUPT_PER_PORT 16
+
+
#define MAX_LCORE_PARAMS 1024
struct lcore_params {
uint8_t port_id;
static struct rte_eth_conf port_conf = {
.rxmode = {
- .mq_mode = ETH_MQ_RX_RSS,
+ .mq_mode = ETH_MQ_RX_RSS,
.max_rx_pkt_len = ETHER_MAX_LEN,
.split_hdr_size = 0,
.header_split = 0, /**< Header Split disabled */
.rx_adv_conf = {
.rss_conf = {
.rss_key = NULL,
- .rss_hf = ETH_RSS_IP,
+ .rss_hf = ETH_RSS_UDP,
},
},
.txmode = {
- .mq_mode = ETH_DCB_NONE,
+ .mq_mode = ETH_MQ_TX_NONE,
+ },
+ .intr_conf = {
+ .lsc = 1,
+#ifdef RTE_NEXT_ABI
+ .rxq = 1,
+#endif
},
};
/* accumulate total execution time in us when callback is invoked */
sleep_time_ratio = (float)(stats[lcore_id].sleep_time) /
(float)SCALING_PERIOD;
-
/**
* check whether need to scale down frequency a step if it sleep a lot.
*/
- if (sleep_time_ratio >= SCALING_DOWN_TIME_RATIO_THRESHOLD)
- rte_power_freq_down(lcore_id);
+ if (sleep_time_ratio >= SCALING_DOWN_TIME_RATIO_THRESHOLD) {
+ if (rte_power_freq_down)
+ rte_power_freq_down(lcore_id);
+ }
else if ( (unsigned)(stats[lcore_id].nb_rx_processed /
- stats[lcore_id].nb_iteration_looped) < MAX_PKT_BURST)
+ stats[lcore_id].nb_iteration_looped) < MAX_PKT_BURST) {
/**
* scale down a step if average packet per iteration less
* than expectation.
*/
- rte_power_freq_down(lcore_id);
+ if (rte_power_freq_down)
+ rte_power_freq_down(lcore_id);
+ }
/**
* initialize another timer according to current frequency to ensure
}
-#define SLEEP_GEAR1_THRESHOLD 100
-#define SLEEP_GEAR2_THRESHOLD 1000
+#define MINIMUM_SLEEP_TIME 1
+#define SUSPEND_THRESHOLD 300
static inline uint32_t
power_idle_heuristic(uint32_t zero_rx_packet_count)
{
- /* If zero count is less than 100, use it as the sleep time in us */
- if (zero_rx_packet_count < SLEEP_GEAR1_THRESHOLD)
- return zero_rx_packet_count;
- /* If zero count is less than 1000, sleep time should be 100 us */
- else if ((zero_rx_packet_count >= SLEEP_GEAR1_THRESHOLD) &&
- (zero_rx_packet_count < SLEEP_GEAR2_THRESHOLD))
- return SLEEP_GEAR1_THRESHOLD;
- /* If zero count is greater than 1000, sleep time should be 1000 us */
- else if (zero_rx_packet_count >= SLEEP_GEAR2_THRESHOLD)
- return SLEEP_GEAR2_THRESHOLD;
+ /* If zero count is less than 100, sleep 1us */
+ if (zero_rx_packet_count < SUSPEND_THRESHOLD)
+ return MINIMUM_SLEEP_TIME;
+ /* If zero count is less than 1000, sleep 100 us which is the
+ minimum latency switching from C3/C6 to C0
+ */
+ else
+ return SUSPEND_THRESHOLD;
return 0;
}
return FREQ_CURRENT;
}
+/**
+ * force polling thread sleep until one-shot rx interrupt triggers
+ * @param port_id
+ * Port id.
+ * @param queue_id
+ * Rx queue id.
+ * @return
+ * 0 on success
+ */
+static int
+sleep_until_rx_interrupt(int num)
+{
+ struct rte_epoll_event event[num];
+ int n, i;
+ uint8_t port_id, queue_id;
+ void *data;
+
+ RTE_LOG(INFO, L3FWD_POWER,
+ "lcore %u sleeps until interrupt triggers\n",
+ rte_lcore_id());
+
+ n = rte_epoll_wait(RTE_EPOLL_PER_THREAD, event, num, -1);
+ for (i = 0; i < n; i++) {
+ data = event[i].epdata.data;
+ port_id = ((uintptr_t)data) >> CHAR_BIT;
+ queue_id = ((uintptr_t)data) &
+ RTE_LEN2MASK(CHAR_BIT, uint8_t);
+ RTE_LOG(INFO, L3FWD_POWER,
+ "lcore %u is waked up from rx interrupt on"
+ " port %d queue %d\n",
+ rte_lcore_id(), port_id, queue_id);
+ }
+
+ return 0;
+}
+
+static void turn_on_intr(struct lcore_conf *qconf)
+{
+ int i;
+ struct lcore_rx_queue *rx_queue;
+ uint8_t port_id, queue_id;
+
+ for (i = 0; i < qconf->n_rx_queue; ++i) {
+ rx_queue = &(qconf->rx_queue_list[i]);
+ port_id = rx_queue->port_id;
+ queue_id = rx_queue->queue_id;
+
+ rte_spinlock_lock(&(locks[port_id]));
+ rte_eth_dev_rx_intr_enable(port_id, queue_id);
+ rte_spinlock_unlock(&(locks[port_id]));
+ }
+}
+
+static int event_register(struct lcore_conf *qconf)
+{
+ struct lcore_rx_queue *rx_queue;
+ uint8_t portid, queueid;
+ uint32_t data;
+ int ret;
+ int i;
+
+ for (i = 0; i < qconf->n_rx_queue; ++i) {
+ rx_queue = &(qconf->rx_queue_list[i]);
+ portid = rx_queue->port_id;
+ queueid = rx_queue->queue_id;
+ data = portid << CHAR_BIT | queueid;
+
+ ret = rte_eth_dev_rx_intr_ctl_q(portid, queueid,
+ RTE_EPOLL_PER_THREAD,
+ RTE_INTR_EVENT_ADD,
+ (void *)((uintptr_t)data));
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
/* main processing loop */
static int
main_loop(__attribute__((unused)) void *dummy)
struct lcore_conf *qconf;
struct lcore_rx_queue *rx_queue;
enum freq_scale_hint_t lcore_scaleup_hint;
-
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;
RTE_LOG(INFO, L3FWD_POWER, "entering main 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=%hhu "
"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 (1) {
stats[lcore_id].nb_iteration_looped++;
prev_tsc_power = cur_tsc_power;
}
+start_rx:
/*
* Read packet from RX queues
*/
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)) {
/**
rx_queue->freq_up_hint;
}
- if (lcore_scaleup_hint == FREQ_HIGHEST)
- rte_power_freq_max(lcore_id);
- else if (lcore_scaleup_hint == FREQ_HIGHER)
- rte_power_freq_up(lcore_id);
+ if (lcore_scaleup_hint == FREQ_HIGHEST) {
+ if (rte_power_freq_max)
+ rte_power_freq_max(lcore_id);
+ } else if (lcore_scaleup_hint == FREQ_HIGHER) {
+ if (rte_power_freq_up)
+ rte_power_freq_up(lcore_id);
+ }
} else {
/**
* All Rx queues empty in recent consecutive polls,
lcore_idle_hint = rx_queue->idle_hint;
}
- if ( lcore_idle_hint < SLEEP_GEAR1_THRESHOLD)
+ if (lcore_idle_hint < SUSPEND_THRESHOLD)
/**
* execute "pause" instruction to avoid context
- * switch for short sleep.
+ * switch which generally take hundred of
+ * microseconds for short sleep.
*/
rte_delay_us(lcore_idle_hint);
- else
- /* long sleep force runing thread to suspend */
- usleep(lcore_idle_hint);
-
+ else {
+ /* suspend until rx interrupt trigges */
+ if (intr_en) {
+ turn_on_intr(qconf);
+ sleep_until_rx_interrupt(
+ qconf->n_rx_queue);
+ }
+ /* start receiving packets immediately */
+ goto start_rx;
+ }
stats[lcore_id].sleep_time += lcore_idle_hint;
}
}
char s[64];
/* create ipv4 hash */
- snprintf(s, sizeof(s), "ipv4_l3fwd_hash_%d", socketid);
+ rte_snprintf(s, sizeof(s), "ipv4_l3fwd_hash_%d", socketid);
ipv4_l3fwd_hash_params.name = s;
ipv4_l3fwd_hash_params.socket_id = socketid;
ipv4_l3fwd_lookup_struct[socketid] =
"socket %d\n", socketid);
/* create ipv6 hash */
- snprintf(s, sizeof(s), "ipv6_l3fwd_hash_%d", socketid);
+ rte_snprintf(s, sizeof(s), "ipv6_l3fwd_hash_%d", socketid);
ipv6_l3fwd_hash_params.name = s;
ipv6_l3fwd_hash_params.socket_id = socketid;
ipv6_l3fwd_lookup_struct[socketid] =
unsigned lcore_id;
uint64_t hz;
uint32_t n_tx_queue, nb_lcores;
+ uint32_t dev_rxq_num, dev_txq_num;
uint8_t portid, nb_rx_queue, queue, socketid;
/* catch SIGINT and restore cpufreq governor to ondemand */
printf("Initializing port %d ... ", portid );
fflush(stdout);
+ rte_eth_dev_info_get(portid, &dev_info);
+ dev_rxq_num = dev_info.max_rx_queues;
+ dev_txq_num = dev_info.max_tx_queues;
+
nb_rx_queue = get_port_n_rx_queues(portid);
+ if (nb_rx_queue > dev_rxq_num)
+ rte_exit(EXIT_FAILURE,
+ "Cannot configure not existed rxq: "
+ "port=%d\n", portid);
+
n_tx_queue = nb_lcores;
- if (n_tx_queue > MAX_TX_QUEUE_PER_PORT)
- n_tx_queue = MAX_TX_QUEUE_PER_PORT;
+ if (n_tx_queue > dev_txq_num)
+ n_tx_queue = dev_txq_num;
printf("Creating queues: nb_rxq=%d nb_txq=%u... ",
nb_rx_queue, (unsigned)n_tx_queue );
ret = rte_eth_dev_configure(portid, nb_rx_queue,
if (rte_lcore_is_enabled(lcore_id) == 0)
continue;
+ if (queueid >= dev_txq_num)
+ continue;
+
if (numa_on)
socketid = \
(uint8_t)rte_lcore_to_socket_id(lcore_id);
/* init power management library */
ret = rte_power_init(lcore_id);
if (ret)
- rte_exit(EXIT_FAILURE, "Power management library "
- "initialization failed on core%u\n", lcore_id);
+ rte_log(RTE_LOG_ERR, RTE_LOGTYPE_POWER,
+ "Power management library initialization "
+ "failed on core%u", lcore_id);
/* init timer structures for each enabled lcore */
rte_timer_init(&power_timers[lcore_id]);
if (ret < 0)
rte_exit(EXIT_FAILURE, "rte_eth_dev_start: err=%d, "
"port=%d\n", ret, portid);
-
/*
* If enabled, put device in promiscuous mode.
* This allows IO forwarding mode to forward packets
*/
if (promiscuous_on)
rte_eth_promiscuous_enable(portid);
+ /* initialize spinlock for each port */
+ rte_spinlock_init(&(locks[portid]));
}
check_all_ports_link_status((uint8_t)nb_ports, enabled_port_mask);
git.droids-corp.org / dpdk.git / commitdiff