DPDK  21.02.0
examples/rxtx_callbacks/main.c
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright(c) 2010-2015 Intel Corporation
*/
#include <stdint.h>
#include <inttypes.h>
#include <getopt.h>
#include <rte_eal.h>
#include <rte_ethdev.h>
#include <rte_cycles.h>
#include <rte_lcore.h>
#include <rte_mbuf.h>
#include <rte_mbuf_dyn.h>
#define RX_RING_SIZE 1024
#define TX_RING_SIZE 1024
#define NUM_MBUFS 8191
#define MBUF_CACHE_SIZE 250
#define BURST_SIZE 32
static int hwts_dynfield_offset = -1;
static inline rte_mbuf_timestamp_t *
hwts_field(struct rte_mbuf *mbuf)
{
return RTE_MBUF_DYNFIELD(mbuf,
hwts_dynfield_offset, rte_mbuf_timestamp_t *);
}
typedef uint64_t tsc_t;
static int tsc_dynfield_offset = -1;
static inline tsc_t *
tsc_field(struct rte_mbuf *mbuf)
{
return RTE_MBUF_DYNFIELD(mbuf, tsc_dynfield_offset, tsc_t *);
}
static const char usage[] =
"%s EAL_ARGS -- [-t]\n";
static const struct rte_eth_conf port_conf_default = {
.rxmode = {
},
};
static struct {
uint64_t total_cycles;
uint64_t total_queue_cycles;
uint64_t total_pkts;
} latency_numbers;
int hw_timestamping;
#define TICKS_PER_CYCLE_SHIFT 16
static uint64_t ticks_per_cycle_mult;
static uint16_t
add_timestamps(uint16_t port __rte_unused, uint16_t qidx __rte_unused,
struct rte_mbuf **pkts, uint16_t nb_pkts,
uint16_t max_pkts __rte_unused, void *_ __rte_unused)
{
unsigned i;
uint64_t now = rte_rdtsc();
for (i = 0; i < nb_pkts; i++)
*tsc_field(pkts[i]) = now;
return nb_pkts;
}
static uint16_t
calc_latency(uint16_t port, uint16_t qidx __rte_unused,
struct rte_mbuf **pkts, uint16_t nb_pkts, void *_ __rte_unused)
{
uint64_t cycles = 0;
uint64_t queue_ticks = 0;
uint64_t now = rte_rdtsc();
uint64_t ticks;
unsigned i;
if (hw_timestamping)
rte_eth_read_clock(port, &ticks);
for (i = 0; i < nb_pkts; i++) {
cycles += now - *tsc_field(pkts[i]);
if (hw_timestamping)
queue_ticks += ticks - *hwts_field(pkts[i]);
}
latency_numbers.total_cycles += cycles;
if (hw_timestamping)
latency_numbers.total_queue_cycles += (queue_ticks
* ticks_per_cycle_mult) >> TICKS_PER_CYCLE_SHIFT;
latency_numbers.total_pkts += nb_pkts;
if (latency_numbers.total_pkts > (100 * 1000 * 1000ULL)) {
printf("Latency = %"PRIu64" cycles\n",
latency_numbers.total_cycles / latency_numbers.total_pkts);
if (hw_timestamping) {
printf("Latency from HW = %"PRIu64" cycles\n",
latency_numbers.total_queue_cycles
/ latency_numbers.total_pkts);
}
latency_numbers.total_cycles = 0;
latency_numbers.total_queue_cycles = 0;
latency_numbers.total_pkts = 0;
}
return nb_pkts;
}
/*
* Initialises a given port using global settings and with the rx buffers
* coming from the mbuf_pool passed as parameter
*/
static inline int
port_init(uint16_t port, struct rte_mempool *mbuf_pool)
{
struct rte_eth_conf port_conf = port_conf_default;
const uint16_t rx_rings = 1, tx_rings = 1;
uint16_t nb_rxd = RX_RING_SIZE;
uint16_t nb_txd = TX_RING_SIZE;
int retval;
uint16_t q;
struct rte_eth_dev_info dev_info;
struct rte_eth_rxconf rxconf;
struct rte_eth_txconf txconf;
return -1;
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 |=
if (hw_timestamping) {
if (!(dev_info.rx_offload_capa & DEV_RX_OFFLOAD_TIMESTAMP)) {
printf("\nERROR: Port %u does not support hardware timestamping\n"
, port);
return -1;
}
rte_mbuf_dyn_rx_timestamp_register(&hwts_dynfield_offset, NULL);
if (hwts_dynfield_offset < 0) {
printf("ERROR: Failed to register timestamp field\n");
return -rte_errno;
}
}
retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf);
if (retval != 0)
return retval;
retval = rte_eth_dev_adjust_nb_rx_tx_desc(port, &nb_rxd, &nb_txd);
if (retval != 0)
return retval;
rxconf = dev_info.default_rxconf;
for (q = 0; q < rx_rings; q++) {
retval = rte_eth_rx_queue_setup(port, q, nb_rxd,
rte_eth_dev_socket_id(port), &rxconf, mbuf_pool);
if (retval < 0)
return retval;
}
txconf = dev_info.default_txconf;
txconf.offloads = port_conf.txmode.offloads;
for (q = 0; q < tx_rings; q++) {
retval = rte_eth_tx_queue_setup(port, q, nb_txd,
rte_eth_dev_socket_id(port), &txconf);
if (retval < 0)
return retval;
}
retval = rte_eth_dev_start(port);
if (retval < 0)
return retval;
if (hw_timestamping && ticks_per_cycle_mult == 0) {
uint64_t cycles_base = rte_rdtsc();
uint64_t ticks_base;
retval = rte_eth_read_clock(port, &ticks_base);
if (retval != 0)
return retval;
uint64_t cycles = rte_rdtsc();
uint64_t ticks;
rte_eth_read_clock(port, &ticks);
uint64_t c_freq = cycles - cycles_base;
uint64_t t_freq = ticks - ticks_base;
double freq_mult = (double)c_freq / t_freq;
printf("TSC Freq ~= %" PRIu64
"\nHW Freq ~= %" PRIu64
"\nRatio : %f\n",
c_freq * 10, t_freq * 10, freq_mult);
/* TSC will be faster than internal ticks so freq_mult is > 0
* We convert the multiplication to an integer shift & mult
*/
ticks_per_cycle_mult = (1 << TICKS_PER_CYCLE_SHIFT) / freq_mult;
}
struct rte_ether_addr addr;
retval = rte_eth_macaddr_get(port, &addr);
if (retval < 0) {
printf("Failed to get MAC address on 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",
(unsigned)port,
addr.addr_bytes[0], addr.addr_bytes[1],
addr.addr_bytes[2], addr.addr_bytes[3],
addr.addr_bytes[4], addr.addr_bytes[5]);
if (retval != 0)
return retval;
rte_eth_add_rx_callback(port, 0, add_timestamps, NULL);
rte_eth_add_tx_callback(port, 0, calc_latency, NULL);
return 0;
}
/*
* Main thread that does the work, reading from INPUT_PORT
* and writing to OUTPUT_PORT
*/
static __rte_noreturn void
lcore_main(void)
{
uint16_t port;
if (rte_eth_dev_socket_id(port) > 0 &&
(int)rte_socket_id())
printf("WARNING, port %u is on remote NUMA node to "
"polling thread.\n\tPerformance will "
"not be optimal.\n", port);
printf("\nCore %u forwarding packets. [Ctrl+C to quit]\n",
for (;;) {
struct rte_mbuf *bufs[BURST_SIZE];
const uint16_t nb_rx = rte_eth_rx_burst(port, 0,
bufs, BURST_SIZE);
if (unlikely(nb_rx == 0))
continue;
const uint16_t nb_tx = rte_eth_tx_burst(port ^ 1, 0,
bufs, nb_rx);
if (unlikely(nb_tx < nb_rx)) {
uint16_t buf;
for (buf = nb_tx; buf < nb_rx; buf++)
rte_pktmbuf_free(bufs[buf]);
}
}
}
}
/* Main function, does initialisation and calls the per-lcore functions */
int
main(int argc, char *argv[])
{
struct rte_mempool *mbuf_pool;
uint16_t nb_ports;
uint16_t portid;
struct option lgopts[] = {
{ NULL, 0, 0, 0 }
};
int opt, option_index;
static const struct rte_mbuf_dynfield tsc_dynfield_desc = {
.name = "example_bbdev_dynfield_tsc",
.size = sizeof(tsc_t),
.align = __alignof__(tsc_t),
};
/* init EAL */
int ret = rte_eal_init(argc, argv);
if (ret < 0)
rte_exit(EXIT_FAILURE, "Error with EAL initialization\n");
argc -= ret;
argv += ret;
while ((opt = getopt_long(argc, argv, "t", lgopts, &option_index))
!= EOF)
switch (opt) {
case 't':
hw_timestamping = 1;
break;
default:
printf(usage, argv[0]);
return -1;
}
optind = 1; /* reset getopt lib */
if (nb_ports < 2 || (nb_ports & 1))
rte_exit(EXIT_FAILURE, "Error: number of ports must be even\n");
mbuf_pool = rte_pktmbuf_pool_create("MBUF_POOL",
NUM_MBUFS * nb_ports, MBUF_CACHE_SIZE, 0,
RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id());
if (mbuf_pool == NULL)
rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n");
tsc_dynfield_offset =
rte_mbuf_dynfield_register(&tsc_dynfield_desc);
if (tsc_dynfield_offset < 0)
rte_exit(EXIT_FAILURE, "Cannot register mbuf field\n");
/* initialize all ports */
if (port_init(portid, mbuf_pool) != 0)
rte_exit(EXIT_FAILURE, "Cannot init port %"PRIu8"\n",
portid);
if (rte_lcore_count() > 1)
printf("\nWARNING: Too much enabled lcores - "
"App uses only 1 lcore\n");
/* call lcore_main on main core only */
lcore_main();
return 0;
}