/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2010-2016 Intel Corporation
+ * Copyright(c) 2010-2018 Intel Corporation
*/
#include <stdio.h>
#include <rte_timer.h>
#include <rte_power.h>
#include <rte_spinlock.h>
+#include <rte_power_empty_poll.h>
+
+#include "perf_core.h"
+#include "main.h"
#define RTE_LOGTYPE_L3FWD_POWER RTE_LOGTYPE_USER1
/* 100 ms interval */
#define TIMER_NUMBER_PER_SECOND 10
+/* (10ms) */
+#define INTERVALS_PER_SECOND 100
/* 100000 us */
#define SCALING_PERIOD (1000000/TIMER_NUMBER_PER_SECOND)
#define SCALING_DOWN_TIME_RATIO_THRESHOLD 0.25
/*
* Configurable number of RX/TX ring descriptors
*/
-#define RTE_TEST_RX_DESC_DEFAULT 512
-#define RTE_TEST_TX_DESC_DEFAULT 512
+#define RTE_TEST_RX_DESC_DEFAULT 1024
+#define RTE_TEST_TX_DESC_DEFAULT 1024
+
+/*
+ * These two thresholds were decided on by running the training algorithm on
+ * a 2.5GHz Xeon. These defaults can be overridden by supplying non-zero values
+ * for the med_threshold and high_threshold parameters on the command line.
+ */
+#define EMPTY_POLL_MED_THRESHOLD 350000UL
+#define EMPTY_POLL_HGH_THRESHOLD 580000UL
+
+
+
static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT;
static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT;
static int promiscuous_on = 0;
/* NUMA is enabled by default. */
static int numa_on = 1;
+/* emptypoll is disabled by default. */
+static bool empty_poll_on;
+static bool empty_poll_train;
+volatile bool empty_poll_stop;
+static struct ep_params *ep_params;
+static struct ep_policy policy;
+static long ep_med_edpi, ep_hgh_edpi;
+
static int parse_ptype; /**< Parse packet type using rx callback, and */
/**< disabled by default */
#define MAX_RX_QUEUE_INTERRUPT_PER_PORT 16
-#define MAX_LCORE_PARAMS 1024
-struct lcore_params {
- uint16_t port_id;
- uint8_t queue_id;
- uint8_t lcore_id;
-} __rte_cache_aligned;
-
-static struct lcore_params lcore_params_array[MAX_LCORE_PARAMS];
+struct lcore_params lcore_params_array[MAX_LCORE_PARAMS];
static struct lcore_params lcore_params_array_default[] = {
{0, 0, 2},
{0, 1, 2},
{3, 1, 3},
};
-static struct lcore_params * lcore_params = lcore_params_array_default;
-static uint16_t nb_lcore_params = sizeof(lcore_params_array_default) /
+struct lcore_params *lcore_params = lcore_params_array_default;
+uint16_t nb_lcore_params = sizeof(lcore_params_array_default) /
sizeof(lcore_params_array_default[0]);
static struct rte_eth_conf port_conf = {
.mq_mode = ETH_MQ_RX_RSS,
.max_rx_pkt_len = ETHER_MAX_LEN,
.split_hdr_size = 0,
- .ignore_offload_bitfield = 1,
- .offloads = (DEV_RX_OFFLOAD_CRC_STRIP |
- DEV_RX_OFFLOAD_CHECKSUM),
+ .offloads = DEV_RX_OFFLOAD_CHECKSUM,
},
.rx_adv_conf = {
.rss_conf = {
static inline enum freq_scale_hint_t power_freq_scaleup_heuristic( \
unsigned int lcore_id, uint16_t port_id, uint16_t queue_id);
+
+/*
+ * These defaults are using the max frequency index (1), a medium index (9)
+ * and a typical low frequency index (14). These can be adjusted to use
+ * different indexes using the relevant command line parameters.
+ */
+static uint8_t freq_tlb[] = {14, 9, 1};
+
+static int is_done(void)
+{
+ return empty_poll_stop;
+}
+
/* exit signal handler */
static void
signal_exit_now(int sigtype)
{
unsigned lcore_id;
- unsigned int portid, nb_ports;
+ unsigned int portid;
int ret;
+ RTE_SET_USED(lcore_id);
+ RTE_SET_USED(portid);
+ RTE_SET_USED(ret);
+
if (sigtype == SIGINT) {
+ if (empty_poll_on)
+ empty_poll_stop = true;
+
+
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
if (rte_lcore_is_enabled(lcore_id) == 0)
continue;
"core%u\n", lcore_id);
}
- nb_ports = rte_eth_dev_count();
- for (portid = 0; portid < nb_ports; portid++) {
- if ((enabled_port_mask & (1 << portid)) == 0)
- continue;
+ if (!empty_poll_on) {
+ RTE_ETH_FOREACH_DEV(portid) {
+ if ((enabled_port_mask & (1 << portid)) == 0)
+ continue;
- rte_eth_dev_stop(portid);
- rte_eth_dev_close(portid);
+ rte_eth_dev_stop(portid);
+ rte_eth_dev_close(portid);
+ }
}
}
- rte_exit(EXIT_SUCCESS, "User forced exit\n");
+ if (!empty_poll_on)
+ rte_exit(EXIT_SUCCESS, "User forced exit\n");
}
/* Freqency scale down timer callback */
return 0;
}
+/* main processing loop */
+static int
+main_empty_poll_loop(__attribute__((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;
+
+ 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;
+ }
+
+ 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);
+ }
+
+ 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;
+ }
+
+ /*
+ * Read packet from RX queues
+ */
+ 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 (nb_rx == 0) {
+
+ rte_power_empty_poll_stat_update(lcore_id);
+
+ continue;
+ } else {
+ rte_power_poll_stat_update(lcore_id, nb_rx);
+ }
+
+
+ /* 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);
+ }
+
+ }
+
+ }
+
+ return 0;
+}
/* main processing loop */
static int
main_loop(__attribute__((unused)) void *dummy)
}
static int
-check_port_config(const unsigned nb_ports)
+check_port_config(void)
{
unsigned portid;
uint16_t i;
portid);
return -1;
}
- if (portid >= nb_ports) {
+ if (!rte_eth_dev_is_valid_port(portid)) {
printf("port %u is not present on the board\n",
portid);
return -1;
{
printf ("%s [EAL options] -- -p PORTMASK -P"
" [--config (port,queue,lcore)[,(port,queue,lcore]]"
+ " [--high-perf-cores CORELIST"
+ " [--perf-config (port,queue,hi_perf,lcore_index)[,(port,queue,hi_perf,lcore_index]]"
" [--enable-jumbo [--max-pkt-len PKTLEN]]\n"
" -p PORTMASK: hexadecimal bitmask of ports to configure\n"
" -P : enable promiscuous mode\n"
" --config (port,queue,lcore): rx queues configuration\n"
+ " --high-perf-cores CORELIST: list of high performance cores\n"
+ " --perf-config: similar as config, cores specified as indices"
+ " for bins containing high or regular performance cores\n"
" --no-numa: optional, disable numa awareness\n"
" --enable-jumbo: enable jumbo frame"
" which max packet len is PKTLEN in decimal (64-9600)\n"
- " --parse-ptype: parse packet type by software\n",
+ " --parse-ptype: parse packet type by software\n"
+ " --empty-poll: enable empty poll detection"
+ " follow (training_flag, high_threshold, med_threshold)\n",
prgname);
}
return 0;
}
+static int
+parse_ep_config(const char *q_arg)
+{
+ char s[256];
+ const char *p = q_arg;
+ char *end;
+ int num_arg;
+
+ char *str_fld[3];
+
+ int training_flag;
+ int med_edpi;
+ int hgh_edpi;
+
+ ep_med_edpi = EMPTY_POLL_MED_THRESHOLD;
+ ep_hgh_edpi = EMPTY_POLL_MED_THRESHOLD;
+
+ snprintf(s, sizeof(s), "%s", p);
+
+ num_arg = rte_strsplit(s, sizeof(s), str_fld, 3, ',');
+
+ empty_poll_train = false;
+
+ if (num_arg == 0)
+ return 0;
+
+ if (num_arg == 3) {
+
+ training_flag = strtoul(str_fld[0], &end, 0);
+ med_edpi = strtoul(str_fld[1], &end, 0);
+ hgh_edpi = strtoul(str_fld[2], &end, 0);
+
+ if (training_flag == 1)
+ empty_poll_train = true;
+ if (med_edpi > 0)
+ ep_med_edpi = med_edpi;
+
+ if (med_edpi > 0)
+ ep_hgh_edpi = hgh_edpi;
+
+ } else {
+
+ return -1;
+ }
+
+ return 0;
+
+}
#define CMD_LINE_OPT_PARSE_PTYPE "parse-ptype"
/* Parse the argument given in the command line of the application */
int opt, ret;
char **argvopt;
int option_index;
+ uint32_t limit;
char *prgname = argv[0];
static struct option lgopts[] = {
{"config", 1, 0, 0},
+ {"perf-config", 1, 0, 0},
+ {"high-perf-cores", 1, 0, 0},
{"no-numa", 0, 0, 0},
{"enable-jumbo", 0, 0, 0},
+ {"empty-poll", 1, 0, 0},
{CMD_LINE_OPT_PARSE_PTYPE, 0, 0, 0},
{NULL, 0, 0, 0}
};
argvopt = argv;
- while ((opt = getopt_long(argc, argvopt, "p:P",
+ while ((opt = getopt_long(argc, argvopt, "p:l:m:h:P",
lgopts, &option_index)) != EOF) {
switch (opt) {
printf("Promiscuous mode selected\n");
promiscuous_on = 1;
break;
-
+ case 'l':
+ limit = parse_max_pkt_len(optarg);
+ freq_tlb[LOW] = limit;
+ break;
+ case 'm':
+ limit = parse_max_pkt_len(optarg);
+ freq_tlb[MED] = limit;
+ break;
+ case 'h':
+ limit = parse_max_pkt_len(optarg);
+ freq_tlb[HGH] = limit;
+ break;
/* long options */
case 0:
if (!strncmp(lgopts[option_index].name, "config", 6)) {
}
}
+ if (!strncmp(lgopts[option_index].name,
+ "perf-config", 11)) {
+ ret = parse_perf_config(optarg);
+ if (ret) {
+ printf("invalid perf-config\n");
+ print_usage(prgname);
+ return -1;
+ }
+ }
+
+ if (!strncmp(lgopts[option_index].name,
+ "high-perf-cores", 15)) {
+ ret = parse_perf_core_list(optarg);
+ if (ret) {
+ printf("invalid high-perf-cores\n");
+ print_usage(prgname);
+ return -1;
+ }
+ }
+
if (!strncmp(lgopts[option_index].name,
"no-numa", 7)) {
printf("numa is disabled \n");
numa_on = 0;
}
+ if (!strncmp(lgopts[option_index].name,
+ "empty-poll", 10)) {
+ printf("empty-poll is enabled\n");
+ empty_poll_on = true;
+ ret = parse_ep_config(optarg);
+
+ if (ret) {
+ printf("invalid empty poll config\n");
+ print_usage(prgname);
+ return -1;
+ }
+
+ }
+
if (!strncmp(lgopts[option_index].name,
"enable-jumbo", 12)) {
struct option lenopts =
/* Check the link status of all ports in up to 9s, and print them finally */
static void
-check_all_ports_link_status(uint16_t port_num, uint32_t port_mask)
+check_all_ports_link_status(uint32_t port_mask)
{
#define CHECK_INTERVAL 100 /* 100ms */
#define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */
fflush(stdout);
for (count = 0; count <= MAX_CHECK_TIME; count++) {
all_ports_up = 1;
- for (portid = 0; portid < port_num; portid++) {
+ RTE_ETH_FOREACH_DEV(portid) {
if ((port_mask & (1 << portid)) == 0)
continue;
memset(&link, 0, sizeof(link));
}
+static int
+init_power_library(void)
+{
+ int ret = 0, lcore_id;
+ for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+ if (rte_lcore_is_enabled(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 ret;
+}
+static void
+empty_poll_setup_timer(void)
+{
+ int lcore_id = rte_lcore_id();
+ uint64_t hz = rte_get_timer_hz();
+
+ struct ep_params *ep_ptr = ep_params;
+
+ ep_ptr->interval_ticks = hz / INTERVALS_PER_SECOND;
+
+ rte_timer_reset_sync(&ep_ptr->timer0,
+ ep_ptr->interval_ticks,
+ PERIODICAL,
+ lcore_id,
+ rte_empty_poll_detection,
+ (void *)ep_ptr);
+
+}
+static int
+launch_timer(unsigned int lcore_id)
+{
+ int64_t prev_tsc = 0, cur_tsc, diff_tsc, cycles_10ms;
+
+ RTE_SET_USED(lcore_id);
+
+
+ if (rte_get_master_lcore() != lcore_id) {
+ rte_panic("timer on lcore:%d which is not master core:%d\n",
+ lcore_id,
+ rte_get_master_lcore());
+ }
+
+ RTE_LOG(INFO, POWER, "Bring up the Timer\n");
+
+ empty_poll_setup_timer();
+
+ cycles_10ms = rte_get_timer_hz() / 100;
+
+ while (!is_done()) {
+ cur_tsc = rte_rdtsc();
+ diff_tsc = cur_tsc - prev_tsc;
+ if (diff_tsc > cycles_10ms) {
+ rte_timer_manage();
+ prev_tsc = cur_tsc;
+ cycles_10ms = rte_get_timer_hz() / 100;
+ }
+ }
+
+ RTE_LOG(INFO, POWER, "Timer_subsystem is done\n");
+
+ return 0;
+}
+
+
int
main(int argc, char **argv)
{
if (ret < 0)
rte_exit(EXIT_FAILURE, "Invalid L3FWD parameters\n");
+ if (init_power_library())
+ rte_exit(EXIT_FAILURE, "init_power_library failed\n");
+
+ if (update_lcore_params() < 0)
+ rte_exit(EXIT_FAILURE, "update_lcore_params failed\n");
+
if (check_lcore_params() < 0)
rte_exit(EXIT_FAILURE, "check_lcore_params failed\n");
if (ret < 0)
rte_exit(EXIT_FAILURE, "init_lcore_rx_queues failed\n");
- nb_ports = rte_eth_dev_count();
+ nb_ports = rte_eth_dev_count_avail();
- if (check_port_config(nb_ports) < 0)
+ if (check_port_config() < 0)
rte_exit(EXIT_FAILURE, "check_port_config failed\n");
nb_lcores = rte_lcore_count();
/* initialize all ports */
- for (portid = 0; portid < nb_ports; portid++) {
+ RTE_ETH_FOREACH_DEV(portid) {
struct rte_eth_conf local_port_conf = port_conf;
/* skip ports that are not enabled */
if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
local_port_conf.txmode.offloads |=
DEV_TX_OFFLOAD_MBUF_FAST_FREE;
+
+ local_port_conf.rx_adv_conf.rss_conf.rss_hf &=
+ dev_info.flow_type_rss_offloads;
+ if (local_port_conf.rx_adv_conf.rss_conf.rss_hf !=
+ port_conf.rx_adv_conf.rss_conf.rss_hf) {
+ printf("Port %u modified RSS hash function based on hardware support,"
+ "requested:%#"PRIx64" configured:%#"PRIx64"\n",
+ portid,
+ port_conf.rx_adv_conf.rss_conf.rss_hf,
+ local_port_conf.rx_adv_conf.rss_conf.rss_hf);
+ }
+
ret = rte_eth_dev_configure(portid, nb_rx_queue,
(uint16_t)n_tx_queue, &local_port_conf);
if (ret < 0)
fflush(stdout);
txconf = &dev_info.default_txconf;
- txconf->txq_flags = ETH_TXQ_FLAGS_IGNORE;
txconf->offloads = local_port_conf.txmode.offloads;
ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd,
socketid, txconf);
if (rte_lcore_is_enabled(lcore_id) == 0)
continue;
- /* 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);
-
- /* init timer structures for each enabled lcore */
- rte_timer_init(&power_timers[lcore_id]);
- hz = rte_get_timer_hz();
- rte_timer_reset(&power_timers[lcore_id],
- hz/TIMER_NUMBER_PER_SECOND, SINGLE, lcore_id,
- power_timer_cb, NULL);
-
+ if (empty_poll_on == false) {
+ /* init timer structures for each enabled lcore */
+ rte_timer_init(&power_timers[lcore_id]);
+ hz = rte_get_timer_hz();
+ rte_timer_reset(&power_timers[lcore_id],
+ hz/TIMER_NUMBER_PER_SECOND,
+ SINGLE, lcore_id,
+ power_timer_cb, NULL);
+ }
qconf = &lcore_conf[lcore_id];
printf("\nInitializing rx queues on lcore %u ... ", lcore_id );
fflush(stdout);
printf("\n");
/* start ports */
- for (portid = 0; portid < nb_ports; portid++) {
+ RTE_ETH_FOREACH_DEV(portid) {
if ((enabled_port_mask & (1 << portid)) == 0) {
continue;
}
rte_spinlock_init(&(locks[portid]));
}
- check_all_ports_link_status(nb_ports, enabled_port_mask);
+ check_all_ports_link_status(enabled_port_mask);
+
+ if (empty_poll_on == true) {
+
+ if (empty_poll_train) {
+ policy.state = TRAINING;
+ } else {
+ policy.state = MED_NORMAL;
+ policy.med_base_edpi = ep_med_edpi;
+ policy.hgh_base_edpi = ep_hgh_edpi;
+ }
+
+ ret = rte_power_empty_poll_stat_init(&ep_params,
+ freq_tlb,
+ &policy);
+ if (ret < 0)
+ rte_exit(EXIT_FAILURE, "empty poll init failed");
+ }
+
/* launch per-lcore init on every lcore */
- rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER);
+ if (empty_poll_on == false) {
+ rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER);
+ } else {
+ empty_poll_stop = false;
+ rte_eal_mp_remote_launch(main_empty_poll_loop, NULL,
+ SKIP_MASTER);
+ }
+
+ if (empty_poll_on == true)
+ launch_timer(rte_lcore_id());
+
RTE_LCORE_FOREACH_SLAVE(lcore_id) {
if (rte_eal_wait_lcore(lcore_id) < 0)
return -1;
}
+ if (empty_poll_on)
+ rte_power_empty_poll_stat_free();
+
return 0;
}