#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
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 {
static const struct rte_eth_conf port_conf_default = {
.rxmode = {
.mq_mode = ETH_MQ_RX_RSS,
- .max_rx_pkt_len = ETHER_MAX_LEN,
- .ignore_offload_bitfield = 1,
+ .max_rx_pkt_len = RTE_ETHER_MAX_LEN,
},
.txmode = {
.mq_mode = ETH_MQ_TX_NONE,
if (!rte_eth_dev_is_valid_port(port))
return -1;
- rte_eth_dev_info_get(port, &dev_info);
+ retval = rte_eth_dev_info_get(port, &dev_info);
+ if (retval != 0) {
+ printf("Error during getting device (port %u) info: %s\n",
+ port, strerror(-retval));
+ return retval;
+ }
+
if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
port_conf.txmode.offloads |=
DEV_TX_OFFLOAD_MBUF_FAST_FREE;
+ port_conf.rx_adv_conf.rss_conf.rss_hf &=
+ dev_info.flow_type_rss_offloads;
+ if (port_conf.rx_adv_conf.rss_conf.rss_hf !=
+ port_conf_default.rx_adv_conf.rss_conf.rss_hf) {
+ printf("Port %u modified RSS hash function based on hardware support,"
+ "requested:%#"PRIx64" configured:%#"PRIx64"\n",
+ port,
+ port_conf_default.rx_adv_conf.rss_conf.rss_hf,
+ port_conf.rx_adv_conf.rss_conf.rss_hf);
+ }
+
retval = rte_eth_dev_configure(port, rxRings, txRings, &port_conf);
if (retval != 0)
return retval;
}
txconf = dev_info.default_txconf;
- txconf.txq_flags = ETH_TXQ_FLAGS_IGNORE;
txconf.offloads = port_conf.txmode.offloads;
for (q = 0; q < txRings; q++) {
retval = rte_eth_tx_queue_setup(port, q, nb_txd,
return retval;
struct rte_eth_link link;
- rte_eth_link_get_nowait(port, &link);
- while (!link.link_status) {
+ do {
+ retval = rte_eth_link_get_nowait(port, &link);
+ if (retval < 0) {
+ printf("Failed link get (port %u): %s\n",
+ port, rte_strerror(-retval));
+ return retval;
+ } else if (link.link_status)
+ break;
+
printf("Waiting for Link up on port %"PRIu16"\n", port);
sleep(1);
- rte_eth_link_get_nowait(port, &link);
- }
+ } while (!link.link_status);
if (!link.link_status) {
printf("Link down on port %"PRIu16"\n", port);
return 0;
}
- struct ether_addr addr;
- rte_eth_macaddr_get(port, &addr);
+ struct rte_ether_addr addr;
+ retval = rte_eth_macaddr_get(port, &addr);
+ if (retval < 0) {
+ printf("Failed to get MAC address (port %u): %s\n",
+ port, rte_strerror(-retval));
+ return retval;
+ }
+
printf("Port %u MAC: %02"PRIx8" %02"PRIx8" %02"PRIx8
" %02"PRIx8" %02"PRIx8" %02"PRIx8"\n",
port,
addr.addr_bytes[2], addr.addr_bytes[3],
addr.addr_bytes[4], addr.addr_bytes[5]);
- rte_eth_promiscuous_enable(port);
+ retval = rte_eth_promiscuous_enable(port);
+ if (retval != 0)
+ return retval;
return 0;
}
static int
lcore_rx(struct lcore_params *p)
{
- const uint16_t nb_ports = rte_eth_dev_count();
+ const uint16_t nb_ports = rte_eth_dev_count_avail();
const int socket_id = rte_socket_id();
uint16_t port;
struct rte_mbuf *bufs[BURST_SIZE*2];
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;
}
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);
}
}
}
+ if (power_lib_initialised)
+ rte_power_exit(rte_lcore_id());
printf("\nCore %u exiting tx task.\n", rte_lcore_id());
return 0;
}
* for single port, xor_val will be zero so we won't modify the output
* port, otherwise we send traffic from 0 to 1, 2 to 3, and vice versa
*/
- const unsigned xor_val = (rte_eth_dev_count() > 1);
+ const unsigned xor_val = (rte_eth_dev_count_avail() > 1);
struct rte_mbuf *buf[8] __rte_cache_aligned;
for (i = 0; i < 8; i++)
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)
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;
"1 lcore for packet TX\n"
"and at least 1 lcore for worker threads\n");
- nb_ports = rte_eth_dev_count();
+ 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");
if (nb_ports != 1 && (nb_ports & 1))
if (rx_dist_ring == NULL)
rte_exit(EXIT_FAILURE, "Cannot create output ring\n");
- RTE_LCORE_FOREACH_SLAVE(lcore_id) {
- if (worker_id == rte_lcore_count() - 3) {
- printf("Starting distributor on lcore_id %d\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.priority != 1)
+ continue;
+
+ if (distr_core_id < 0) {
+ distr_core_id = lcore_id;
+ printf("Distributor on priority core %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);
+ 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;
+ }
}
- worker_id++;
}
+ /*
+ * 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 (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;
+ }
+ 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) {
}
print_stats();
+
+ rte_free(pd);
+ rte_free(pr);
+
return 0;
}