-/*-
- * BSD LICENSE
- *
- * Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2018 Intel Corporation
*/
#include <stdio.h>
#include <getopt.h>
#include <unistd.h>
#include <signal.h>
+#include <math.h>
#include <rte_common.h>
#include <rte_byteorder.h>
#include <rte_malloc.h>
#include <rte_memory.h>
#include <rte_memcpy.h>
-#include <rte_memzone.h>
#include <rte_eal.h>
-#include <rte_per_lcore.h>
#include <rte_launch.h>
-#include <rte_atomic.h>
#include <rte_cycles.h>
#include <rte_prefetch.h>
#include <rte_lcore.h>
#include <rte_per_lcore.h>
#include <rte_branch_prediction.h>
#include <rte_interrupts.h>
-#include <rte_pci.h>
#include <rte_random.h>
#include <rte_debug.h>
#include <rte_ether.h>
#include <rte_ethdev.h>
-#include <rte_ring.h>
#include <rte_mempool.h>
#include <rte_mbuf.h>
#include <rte_ip.h>
#include <rte_string_fns.h>
#include <rte_timer.h>
#include <rte_power.h>
-#include <rte_eal.h>
#include <rte_spinlock.h>
+#include <rte_power_empty_poll.h>
+#include <rte_metrics.h>
+#include <rte_telemetry.h>
+#include <rte_power_pmd_mgmt.h>
+
+#include "perf_core.h"
+#include "main.h"
#define RTE_LOGTYPE_L3FWD_POWER RTE_LOGTYPE_USER1
#define MIN_ZERO_POLL_COUNT 10
-/* around 100ms at 2 Ghz */
-#define TIMER_RESOLUTION_CYCLES 200000000ULL
/* 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
*/
#define NB_MBUF RTE_MAX ( \
- (nb_ports*nb_rx_queue*RTE_TEST_RX_DESC_DEFAULT + \
+ (nb_ports*nb_rx_queue*nb_rxd + \
nb_ports*nb_lcores*MAX_PKT_BURST + \
- nb_ports*n_tx_queue*RTE_TEST_TX_DESC_DEFAULT + \
+ nb_ports*n_tx_queue*nb_txd + \
nb_lcores*MEMPOOL_CACHE_SIZE), \
(unsigned)8192)
/*
* Configurable number of RX/TX ring descriptors
*/
-#define RTE_TEST_RX_DESC_DEFAULT 128
-#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
+
+#define NUM_TELSTATS RTE_DIM(telstats_strings)
+
static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT;
static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT;
/* ethernet addresses of ports */
-static struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS];
+static struct rte_ether_addr ports_eth_addr[RTE_MAX_ETHPORTS];
/* ethernet addresses of ports */
static rte_spinlock_t locks[RTE_MAX_ETHPORTS];
static int promiscuous_on = 0;
/* NUMA is enabled by default. */
static int numa_on = 1;
+static bool empty_poll_stop;
+static bool empty_poll_train;
+volatile bool quit_signal;
+static struct ep_params *ep_params;
+static struct ep_policy policy;
+static long ep_med_edpi, ep_hgh_edpi;
+/* timer to update telemetry every 500ms */
+static struct rte_timer telemetry_timer;
+
+/* stats index returned by metrics lib */
+int telstats_index;
+
+struct telstats_name {
+ char name[RTE_ETH_XSTATS_NAME_SIZE];
+};
+
+/* telemetry stats to be reported */
+const struct telstats_name telstats_strings[] = {
+ {"empty_poll"},
+ {"full_poll"},
+ {"busy_percent"}
+};
+
+/* core busyness in percentage */
+enum busy_rate {
+ ZERO = 0,
+ PARTIAL = 50,
+ FULL = 100
+};
+
+/* reference poll count to measure core busyness */
+#define DEFAULT_COUNT 10000
+/*
+ * reference CYCLES to be used to
+ * measure core busyness based on poll count
+ */
+#define MIN_CYCLES 1500000ULL
+#define MAX_CYCLES 22000000ULL
+
+/* (500ms) */
+#define TELEMETRY_INTERVALS_PER_SEC 2
+
+static int parse_ptype; /**< Parse packet type using rx callback, and */
+ /**< disabled by default */
+
+enum appmode {
+ APP_MODE_DEFAULT = 0,
+ APP_MODE_LEGACY,
+ APP_MODE_EMPTY_POLL,
+ APP_MODE_TELEMETRY,
+ APP_MODE_INTERRUPT,
+ APP_MODE_PMD_MGMT
+};
+
+enum appmode app_mode;
+
+static enum rte_power_pmd_mgmt_type pmgmt_type;
+bool baseline_enabled;
enum freq_scale_hint_t
{
};
struct lcore_rx_queue {
- uint8_t port_id;
+ uint16_t port_id;
uint8_t queue_id;
enum freq_scale_hint_t freq_up_hint;
uint32_t zero_rx_packet_count;
#define MAX_RX_QUEUE_INTERRUPT_PER_PORT 16
-#define MAX_LCORE_PARAMS 1024
-struct lcore_params {
- uint8_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) /
- sizeof(lcore_params_array_default[0]);
+struct lcore_params *lcore_params = lcore_params_array_default;
+uint16_t nb_lcore_params = RTE_DIM(lcore_params_array_default);
static struct rte_eth_conf port_conf = {
.rxmode = {
- .mq_mode = ETH_MQ_RX_RSS,
- .max_rx_pkt_len = ETHER_MAX_LEN,
+ .mq_mode = RTE_ETH_MQ_RX_RSS,
.split_hdr_size = 0,
- .header_split = 0, /**< Header Split disabled */
- .hw_ip_checksum = 1, /**< IP checksum offload enabled */
- .hw_vlan_filter = 0, /**< VLAN filtering disabled */
- .jumbo_frame = 0, /**< Jumbo Frame Support disabled */
- .hw_strip_crc = 0, /**< CRC stripped by hardware */
+ .offloads = RTE_ETH_RX_OFFLOAD_CHECKSUM,
},
.rx_adv_conf = {
.rss_conf = {
.rss_key = NULL,
- .rss_hf = ETH_RSS_UDP,
+ .rss_hf = RTE_ETH_RSS_UDP,
},
},
.txmode = {
- .mq_mode = ETH_MQ_TX_NONE,
- },
- .intr_conf = {
- .lsc = 1,
- .rxq = 1,
- },
+ .mq_mode = RTE_ETH_MQ_TX_NONE,
+ }
};
+static uint32_t max_pkt_len;
+
static struct rte_mempool * pktmbuf_pool[NB_SOCKETS];
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
-#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
+#ifdef RTE_ARCH_X86
#include <rte_hash_crc.h>
#define DEFAULT_HASH_FUNC rte_hash_crc
#else
uint16_t port_dst;
uint16_t port_src;
uint8_t proto;
-} __attribute__((__packed__));
+} __rte_packed;
struct ipv6_5tuple {
uint8_t ip_dst[IPV6_ADDR_LEN];
uint16_t port_dst;
uint16_t port_src;
uint8_t proto;
-} __attribute__((__packed__));
+} __rte_packed;
struct ipv4_l3fwd_route {
struct ipv4_5tuple key;
};
static struct ipv4_l3fwd_route ipv4_l3fwd_route_array[] = {
- {{IPv4(100,10,0,1), IPv4(200,10,0,1), 101, 11, IPPROTO_TCP}, 0},
- {{IPv4(100,20,0,2), IPv4(200,20,0,2), 102, 12, IPPROTO_TCP}, 1},
- {{IPv4(100,30,0,3), IPv4(200,30,0,3), 103, 13, IPPROTO_TCP}, 2},
- {{IPv4(100,40,0,4), IPv4(200,40,0,4), 104, 14, IPPROTO_TCP}, 3},
+ {{RTE_IPV4(100,10,0,1), RTE_IPV4(200,10,0,1), 101, 11, IPPROTO_TCP}, 0},
+ {{RTE_IPV4(100,20,0,2), RTE_IPV4(200,20,0,2), 102, 12, IPPROTO_TCP}, 1},
+ {{RTE_IPV4(100,30,0,3), RTE_IPV4(200,30,0,3), 103, 13, IPPROTO_TCP}, 2},
+ {{RTE_IPV4(100,40,0,4), RTE_IPV4(200,40,0,4), 104, 14, IPPROTO_TCP}, 3},
};
static struct ipv6_l3fwd_route ipv6_l3fwd_route_array[] = {
#define L3FWD_HASH_ENTRIES 1024
-#define IPV4_L3FWD_NUM_ROUTES \
- (sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0]))
-
-#define IPV6_L3FWD_NUM_ROUTES \
- (sizeof(ipv6_l3fwd_route_array) / sizeof(ipv6_l3fwd_route_array[0]))
-
-static uint8_t ipv4_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;
-static uint8_t ipv6_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;
+static uint16_t ipv4_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;
+static uint16_t ipv6_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;
#endif
#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
};
static struct ipv4_l3fwd_route ipv4_l3fwd_route_array[] = {
- {IPv4(1,1,1,0), 24, 0},
- {IPv4(2,1,1,0), 24, 1},
- {IPv4(3,1,1,0), 24, 2},
- {IPv4(4,1,1,0), 24, 3},
- {IPv4(5,1,1,0), 24, 4},
- {IPv4(6,1,1,0), 24, 5},
- {IPv4(7,1,1,0), 24, 6},
- {IPv4(8,1,1,0), 24, 7},
+ {RTE_IPV4(1,1,1,0), 24, 0},
+ {RTE_IPV4(2,1,1,0), 24, 1},
+ {RTE_IPV4(3,1,1,0), 24, 2},
+ {RTE_IPV4(4,1,1,0), 24, 3},
+ {RTE_IPV4(5,1,1,0), 24, 4},
+ {RTE_IPV4(6,1,1,0), 24, 5},
+ {RTE_IPV4(7,1,1,0), 24, 6},
+ {RTE_IPV4(8,1,1,0), 24, 7},
};
-#define IPV4_L3FWD_NUM_ROUTES \
- (sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0]))
-
#define IPV4_L3FWD_LPM_MAX_RULES 1024
typedef struct rte_lpm lookup_struct_t;
uint64_t nb_rx_processed;
/* total iterations looped recently */
uint64_t nb_iteration_looped;
- uint32_t padding[9];
+ /*
+ * Represents empty and non empty polls
+ * of rte_eth_rx_burst();
+ * ep_nep[0] holds non empty polls
+ * i.e. 0 < nb_rx <= MAX_BURST
+ * ep_nep[1] holds empty polls.
+ * i.e. nb_rx == 0
+ */
+ uint64_t ep_nep[2];
+ /*
+ * Represents full and empty+partial
+ * polls of rte_eth_rx_burst();
+ * ep_nep[0] holds empty+partial polls.
+ * i.e. 0 <= nb_rx < MAX_BURST
+ * ep_nep[1] holds full polls
+ * i.e. nb_rx == MAX_BURST
+ */
+ uint64_t fp_nfp[2];
+ enum busy_rate br;
+ rte_spinlock_t telemetry_lock;
} __rte_cache_aligned;
static struct lcore_conf lcore_conf[RTE_MAX_LCORE] __rte_cache_aligned;
static inline uint32_t power_idle_heuristic(uint32_t zero_rx_packet_count);
static inline enum freq_scale_hint_t power_freq_scaleup_heuristic( \
- unsigned lcore_id, uint8_t port_id, uint16_t queue_id);
+ 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 quit_signal;
+}
/* exit signal handler */
static void
signal_exit_now(int sigtype)
{
- unsigned lcore_id;
- int ret;
-
- if (sigtype == SIGINT) {
- for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
- if (rte_lcore_is_enabled(lcore_id) == 0)
- continue;
- /* init power management library */
- ret = rte_power_exit(lcore_id);
- if (ret)
- rte_exit(EXIT_FAILURE, "Power management "
- "library de-initialization failed on "
- "core%u\n", lcore_id);
- }
- }
+ if (sigtype == SIGINT)
+ quit_signal = true;
- rte_exit(EXIT_SUCCESS, "User forced exit\n");
}
/* Freqency scale down timer callback */
static void
-power_timer_cb(__attribute__((unused)) struct rte_timer *tim,
- __attribute__((unused)) void *arg)
+power_timer_cb(__rte_unused struct rte_timer *tim,
+ __rte_unused void *arg)
{
uint64_t hz;
float sleep_time_ratio;
/* Enqueue a single packet, and send burst if queue is filled */
static inline int
-send_single_packet(struct rte_mbuf *m, uint8_t port)
+send_single_packet(struct rte_mbuf *m, uint16_t port)
{
uint32_t lcore_id;
struct lcore_conf *qconf;
#ifdef DO_RFC_1812_CHECKS
static inline int
-is_valid_ipv4_pkt(struct ipv4_hdr *pkt, uint32_t link_len)
+is_valid_ipv4_pkt(struct rte_ipv4_hdr *pkt, uint32_t link_len)
{
/* From http://www.rfc-editor.org/rfc/rfc1812.txt section 5.2.2 */
/*
* 1. The packet length reported by the Link Layer must be large
* enough to hold the minimum length legal IP datagram (20 bytes).
*/
- if (link_len < sizeof(struct ipv4_hdr))
+ if (link_len < sizeof(struct rte_ipv4_hdr))
return -1;
/* 2. The IP checksum must be correct. */
* datagram header, whose length is specified in the IP header length
* field.
*/
- if (rte_cpu_to_be_16(pkt->total_length) < sizeof(struct ipv4_hdr))
+ if (rte_cpu_to_be_16(pkt->total_length) < sizeof(struct rte_ipv4_hdr))
return -5;
return 0;
key.port_dst, key.port_src, key.proto);
}
-static inline uint8_t
-get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint8_t portid,
+static inline uint16_t
+get_ipv4_dst_port(struct rte_ipv4_hdr *ipv4_hdr, uint16_t portid,
lookup_struct_t * ipv4_l3fwd_lookup_struct)
{
struct ipv4_5tuple key;
- struct tcp_hdr *tcp;
- struct udp_hdr *udp;
+ struct rte_tcp_hdr *tcp;
+ struct rte_udp_hdr *udp;
int ret = 0;
key.ip_dst = rte_be_to_cpu_32(ipv4_hdr->dst_addr);
switch (ipv4_hdr->next_proto_id) {
case IPPROTO_TCP:
- tcp = (struct tcp_hdr *)((unsigned char *)ipv4_hdr +
- sizeof(struct ipv4_hdr));
+ tcp = (struct rte_tcp_hdr *)((unsigned char *)ipv4_hdr +
+ sizeof(struct rte_ipv4_hdr));
key.port_dst = rte_be_to_cpu_16(tcp->dst_port);
key.port_src = rte_be_to_cpu_16(tcp->src_port);
break;
case IPPROTO_UDP:
- udp = (struct udp_hdr *)((unsigned char *)ipv4_hdr +
- sizeof(struct ipv4_hdr));
+ udp = (struct rte_udp_hdr *)((unsigned char *)ipv4_hdr +
+ sizeof(struct rte_ipv4_hdr));
key.port_dst = rte_be_to_cpu_16(udp->dst_port);
key.port_src = rte_be_to_cpu_16(udp->src_port);
break;
/* Find destination port */
ret = rte_hash_lookup(ipv4_l3fwd_lookup_struct, (const void *)&key);
- return (uint8_t)((ret < 0)? portid : ipv4_l3fwd_out_if[ret]);
+ return ((ret < 0) ? portid : ipv4_l3fwd_out_if[ret]);
}
-static inline uint8_t
-get_ipv6_dst_port(struct ipv6_hdr *ipv6_hdr, uint8_t portid,
+static inline uint16_t
+get_ipv6_dst_port(struct rte_ipv6_hdr *ipv6_hdr, uint16_t portid,
lookup_struct_t *ipv6_l3fwd_lookup_struct)
{
struct ipv6_5tuple key;
- struct tcp_hdr *tcp;
- struct udp_hdr *udp;
+ struct rte_tcp_hdr *tcp;
+ struct rte_udp_hdr *udp;
int ret = 0;
memcpy(key.ip_dst, ipv6_hdr->dst_addr, IPV6_ADDR_LEN);
switch (ipv6_hdr->proto) {
case IPPROTO_TCP:
- tcp = (struct tcp_hdr *)((unsigned char *) ipv6_hdr +
- sizeof(struct ipv6_hdr));
+ tcp = (struct rte_tcp_hdr *)((unsigned char *) ipv6_hdr +
+ sizeof(struct rte_ipv6_hdr));
key.port_dst = rte_be_to_cpu_16(tcp->dst_port);
key.port_src = rte_be_to_cpu_16(tcp->src_port);
break;
case IPPROTO_UDP:
- udp = (struct udp_hdr *)((unsigned char *) ipv6_hdr +
- sizeof(struct ipv6_hdr));
+ udp = (struct rte_udp_hdr *)((unsigned char *) ipv6_hdr +
+ sizeof(struct rte_ipv6_hdr));
key.port_dst = rte_be_to_cpu_16(udp->dst_port);
key.port_src = rte_be_to_cpu_16(udp->src_port);
break;
/* Find destination port */
ret = rte_hash_lookup(ipv6_l3fwd_lookup_struct, (const void *)&key);
- return (uint8_t)((ret < 0)? portid : ipv6_l3fwd_out_if[ret]);
+ return ((ret < 0) ? portid : ipv6_l3fwd_out_if[ret]);
}
#endif
#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
-static inline uint8_t
-get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint8_t portid,
+static inline uint16_t
+get_ipv4_dst_port(struct rte_ipv4_hdr *ipv4_hdr, uint16_t portid,
lookup_struct_t *ipv4_l3fwd_lookup_struct)
{
uint32_t next_hop;
- return (uint8_t) ((rte_lpm_lookup(ipv4_l3fwd_lookup_struct,
+ return ((rte_lpm_lookup(ipv4_l3fwd_lookup_struct,
rte_be_to_cpu_32(ipv4_hdr->dst_addr), &next_hop) == 0)?
next_hop : portid);
}
#endif
static inline void
-l3fwd_simple_forward(struct rte_mbuf *m, uint8_t portid,
+parse_ptype_one(struct rte_mbuf *m)
+{
+ struct rte_ether_hdr *eth_hdr;
+ uint32_t packet_type = RTE_PTYPE_UNKNOWN;
+ uint16_t ether_type;
+
+ eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
+ ether_type = eth_hdr->ether_type;
+ if (ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4))
+ packet_type |= RTE_PTYPE_L3_IPV4_EXT_UNKNOWN;
+ else if (ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6))
+ packet_type |= RTE_PTYPE_L3_IPV6_EXT_UNKNOWN;
+
+ m->packet_type = packet_type;
+}
+
+static uint16_t
+cb_parse_ptype(uint16_t port __rte_unused, uint16_t queue __rte_unused,
+ struct rte_mbuf *pkts[], uint16_t nb_pkts,
+ uint16_t max_pkts __rte_unused,
+ void *user_param __rte_unused)
+{
+ unsigned int i;
+
+ for (i = 0; i < nb_pkts; ++i)
+ parse_ptype_one(pkts[i]);
+
+ return nb_pkts;
+}
+
+static int
+add_cb_parse_ptype(uint16_t portid, uint16_t queueid)
+{
+ printf("Port %d: softly parse packet type info\n", portid);
+ if (rte_eth_add_rx_callback(portid, queueid, cb_parse_ptype, NULL))
+ return 0;
+
+ printf("Failed to add rx callback: port=%d\n", portid);
+ return -1;
+}
+
+static inline void
+l3fwd_simple_forward(struct rte_mbuf *m, uint16_t portid,
struct lcore_conf *qconf)
{
- struct ether_hdr *eth_hdr;
- struct ipv4_hdr *ipv4_hdr;
+ struct rte_ether_hdr *eth_hdr;
+ struct rte_ipv4_hdr *ipv4_hdr;
void *d_addr_bytes;
- uint8_t dst_port;
+ uint16_t dst_port;
- eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
+ eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
if (RTE_ETH_IS_IPV4_HDR(m->packet_type)) {
/* Handle IPv4 headers.*/
ipv4_hdr =
- rte_pktmbuf_mtod_offset(m, struct ipv4_hdr *,
- sizeof(struct ether_hdr));
+ rte_pktmbuf_mtod_offset(m, struct rte_ipv4_hdr *,
+ sizeof(struct rte_ether_hdr));
#ifdef DO_RFC_1812_CHECKS
/* Check to make sure the packet is valid (RFC1812) */
dst_port = portid;
/* 02:00:00:00:00:xx */
- d_addr_bytes = ð_hdr->d_addr.addr_bytes[0];
+ d_addr_bytes = ð_hdr->dst_addr.addr_bytes[0];
*((uint64_t *)d_addr_bytes) =
0x000000000002 + ((uint64_t)dst_port << 40);
#endif
/* src addr */
- ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr);
+ rte_ether_addr_copy(&ports_eth_addr[dst_port],
+ ð_hdr->src_addr);
send_single_packet(m, dst_port);
} else if (RTE_ETH_IS_IPV6_HDR(m->packet_type)) {
/* Handle IPv6 headers.*/
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
- struct ipv6_hdr *ipv6_hdr;
+ struct rte_ipv6_hdr *ipv6_hdr;
ipv6_hdr =
- rte_pktmbuf_mtod_offset(m, struct ipv6_hdr *,
- sizeof(struct ether_hdr));
+ rte_pktmbuf_mtod_offset(m, struct rte_ipv6_hdr *,
+ sizeof(struct rte_ether_hdr));
dst_port = get_ipv6_dst_port(ipv6_hdr, portid,
qconf->ipv6_lookup_struct);
dst_port = portid;
/* 02:00:00:00:00:xx */
- d_addr_bytes = ð_hdr->d_addr.addr_bytes[0];
+ d_addr_bytes = ð_hdr->dst_addr.addr_bytes[0];
*((uint64_t *)d_addr_bytes) =
0x000000000002 + ((uint64_t)dst_port << 40);
/* src addr */
- ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr);
+ rte_ether_addr_copy(&ports_eth_addr[dst_port],
+ ð_hdr->src_addr);
send_single_packet(m, dst_port);
#else
*/
else
return SUSPEND_THRESHOLD;
-
- return 0;
}
static inline enum freq_scale_hint_t
power_freq_scaleup_heuristic(unsigned lcore_id,
- uint8_t port_id,
+ uint16_t port_id,
uint16_t queue_id)
{
+ uint32_t rxq_count = rte_eth_rx_queue_count(port_id, queue_id);
/**
* HW Rx queue size is 128 by default, Rx burst read at maximum 32 entries
* per iteration
#define FREQ_UP_TREND2_ACC 100
#define FREQ_UP_THRESHOLD 10000
- if (likely(rte_eth_rx_descriptor_done(port_id, queue_id,
- FREQ_GEAR3_RX_PACKET_THRESHOLD) > 0)) {
+ if (likely(rxq_count > FREQ_GEAR3_RX_PACKET_THRESHOLD)) {
stats[lcore_id].trend = 0;
return FREQ_HIGHEST;
- } else if (likely(rte_eth_rx_descriptor_done(port_id, queue_id,
- FREQ_GEAR2_RX_PACKET_THRESHOLD) > 0))
+ } else if (likely(rxq_count > FREQ_GEAR2_RX_PACKET_THRESHOLD))
stats[lcore_id].trend += FREQ_UP_TREND2_ACC;
- else if (likely(rte_eth_rx_descriptor_done(port_id, queue_id,
- FREQ_GEAR1_RX_PACKET_THRESHOLD) > 0))
+ else if (likely(rxq_count > FREQ_GEAR1_RX_PACKET_THRESHOLD))
stats[lcore_id].trend += FREQ_UP_TREND1_ACC;
if (likely(stats[lcore_id].trend > FREQ_UP_THRESHOLD)) {
* 0 on success
*/
static int
-sleep_until_rx_interrupt(int num)
+sleep_until_rx_interrupt(int num, int lcore)
{
+ /*
+ * we want to track when we are woken up by traffic so that we can go
+ * back to sleep again without log spamming. Avoid cache line sharing
+ * to prevent threads stepping on each others' toes.
+ */
+ static struct {
+ bool wakeup;
+ } __rte_cache_aligned status[RTE_MAX_LCORE];
struct rte_epoll_event event[num];
int n, i;
- uint8_t port_id, queue_id;
+ uint16_t port_id;
+ uint8_t queue_id;
void *data;
- RTE_LOG(INFO, L3FWD_POWER,
- "lcore %u sleeps until interrupt triggers\n",
- rte_lcore_id());
+ if (status[lcore].wakeup) {
+ 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);
+ n = rte_epoll_wait(RTE_EPOLL_PER_THREAD, event, num, 10);
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_eth_dev_rx_intr_disable(port_id, queue_id);
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);
}
+ status[lcore].wakeup = n != 0;
return 0;
}
-static void turn_on_intr(struct lcore_conf *qconf)
+static void turn_on_off_intr(struct lcore_conf *qconf, bool on)
{
int i;
struct lcore_rx_queue *rx_queue;
- uint8_t port_id, queue_id;
+ uint8_t queue_id;
+ uint16_t port_id;
for (i = 0; i < qconf->n_rx_queue; ++i) {
rx_queue = &(qconf->rx_queue_list[i]);
queue_id = rx_queue->queue_id;
rte_spinlock_lock(&(locks[port_id]));
- rte_eth_dev_rx_intr_enable(port_id, queue_id);
+ if (on)
+ rte_eth_dev_rx_intr_enable(port_id, queue_id);
+ else
+ rte_eth_dev_rx_intr_disable(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;
+ uint8_t queueid;
+ uint16_t portid;
uint32_t data;
int ret;
int i;
return 0;
}
-/* main processing loop */
-static int
-main_loop(__attribute__((unused)) void *dummy)
+/* Main processing loop. 8< */
+static int main_intr_loop(__rte_unused void *dummy)
{
struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
- unsigned lcore_id;
+ unsigned int lcore_id;
uint64_t prev_tsc, diff_tsc, cur_tsc;
- uint64_t prev_tsc_power = 0, cur_tsc_power, diff_tsc_power;
int i, j, nb_rx;
- uint8_t portid, queueid;
+ uint8_t queueid;
+ uint16_t portid;
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;
+ const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) /
+ US_PER_S * BURST_TX_DRAIN_US;
prev_tsc = 0;
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);
+ RTE_LOG(INFO, L3FWD_POWER, "lcore %u has nothing to do\n",
+ lcore_id);
return 0;
}
- RTE_LOG(INFO, L3FWD_POWER, "entering main loop on lcore %u\n", lcore_id);
+ 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=%hhu "
- "rxqueueid=%hhu\n", lcore_id, portid, queueid);
+ RTE_LOG(INFO, L3FWD_POWER,
+ " -- lcoreid=%u portid=%u rxqueueid=%hhu\n",
+ lcore_id, portid, queueid);
}
/* add into event wait list */
else
RTE_LOG(INFO, L3FWD_POWER, "RX interrupt won't enable.\n");
- while (1) {
+ while (!is_done()) {
stats[lcore_id].nb_iteration_looped++;
cur_tsc = rte_rdtsc();
- cur_tsc_power = cur_tsc;
/*
* TX burst queue drain
prev_tsc = cur_tsc;
}
- diff_tsc_power = cur_tsc_power - prev_tsc_power;
- if (diff_tsc_power > TIMER_RESOLUTION_CYCLES) {
- rte_timer_manage();
- prev_tsc_power = cur_tsc_power;
- }
-
start_rx:
/*
* Read packet from RX queues
*/
- lcore_scaleup_hint = FREQ_CURRENT;
lcore_rx_idle_count = 0;
for (i = 0; i < qconf->n_rx_queue; ++i) {
rx_queue = &(qconf->rx_queue_list[i]);
queueid = rx_queue->queue_id;
nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst,
- MAX_PKT_BURST);
+ MAX_PKT_BURST);
stats[lcore_id].nb_rx_processed += nb_rx;
if (unlikely(nb_rx == 0)) {
rx_queue->zero_rx_packet_count++;
if (rx_queue->zero_rx_packet_count <=
- MIN_ZERO_POLL_COUNT)
+ MIN_ZERO_POLL_COUNT)
continue;
- rx_queue->idle_hint = power_idle_heuristic(\
- rx_queue->zero_rx_packet_count);
+ 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;
-
- /**
- * do not scale up frequency immediately as
- * user to kernel space communication is costly
- * which might impact packet I/O for received
- * packets.
- */
- rx_queue->freq_up_hint =
- power_freq_scaleup_heuristic(lcore_id,
- portid, queueid);
}
/* Prefetch first packets */
/* 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);
+ 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);
+ l3fwd_simple_forward(
+ pkts_burst[j], portid, qconf);
}
}
- if (likely(lcore_rx_idle_count != qconf->n_rx_queue)) {
- for (i = 1, lcore_scaleup_hint =
- qconf->rx_queue_list[0].freq_up_hint;
- i < qconf->n_rx_queue; ++i) {
- rx_queue = &(qconf->rx_queue_list[i]);
- if (rx_queue->freq_up_hint >
- lcore_scaleup_hint)
- lcore_scaleup_hint =
- rx_queue->freq_up_hint;
- }
-
- 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 {
+ 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;
+ 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)
*/
rte_delay_us(lcore_idle_hint);
else {
- /* suspend until rx interrupt trigges */
+ /* suspend until rx interrupt triggers */
if (intr_en) {
- turn_on_intr(qconf);
+ turn_on_off_intr(qconf, 1);
sleep_until_rx_interrupt(
- qconf->n_rx_queue);
+ qconf->n_rx_queue,
+ lcore_id);
+ turn_on_off_intr(qconf, 0);
+ /**
+ * start receiving packets immediately
+ */
+ if (likely(!is_done()))
+ goto start_rx;
}
- /* start receiving packets immediately */
- goto start_rx;
}
stats[lcore_id].sleep_time += lcore_idle_hint;
}
}
-}
-
-static int
-check_lcore_params(void)
-{
- uint8_t queue, lcore;
- uint16_t i;
- int socketid;
- for (i = 0; i < nb_lcore_params; ++i) {
- queue = lcore_params[i].queue_id;
- if (queue >= MAX_RX_QUEUE_PER_PORT) {
- printf("invalid queue number: %hhu\n", queue);
- return -1;
- }
- lcore = lcore_params[i].lcore_id;
- if (!rte_lcore_is_enabled(lcore)) {
- printf("error: lcore %hhu is not enabled in lcore "
- "mask\n", lcore);
- return -1;
- }
- if ((socketid = rte_lcore_to_socket_id(lcore) != 0) &&
- (numa_on == 0)) {
- printf("warning: lcore %hhu is on socket %d with numa "
- "off\n", lcore, socketid);
- }
- }
return 0;
}
+/* >8 End of main processing loop. */
+/* main processing loop */
static int
-check_port_config(const unsigned nb_ports)
+main_telemetry_loop(__rte_unused void *dummy)
{
- unsigned portid;
- uint16_t i;
-
- for (i = 0; i < nb_lcore_params; ++i) {
- portid = lcore_params[i].port_id;
- if ((enabled_port_mask & (1 << portid)) == 0) {
- printf("port %u is not enabled in port mask\n",
- portid);
- return -1;
- }
- if (portid >= nb_ports) {
- printf("port %u is not present on the board\n",
- portid);
- return -1;
- }
- }
- return 0;
-}
+ struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
+ unsigned int lcore_id;
+ uint64_t prev_tsc, diff_tsc, cur_tsc, prev_tel_tsc;
+ int i, j, nb_rx;
+ uint8_t queueid;
+ uint16_t portid;
+ struct lcore_conf *qconf;
+ struct lcore_rx_queue *rx_queue;
+ uint64_t ep_nep[2] = {0}, fp_nfp[2] = {0};
+ uint64_t poll_count;
+ enum busy_rate br;
-static uint8_t
-get_port_n_rx_queues(const uint8_t port)
-{
- int queue = -1;
- uint16_t i;
+ const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) /
+ US_PER_S * BURST_TX_DRAIN_US;
- for (i = 0; i < nb_lcore_params; ++i) {
- if (lcore_params[i].port_id == port &&
- lcore_params[i].queue_id > queue)
- queue = lcore_params[i].queue_id;
- }
- return (uint8_t)(++queue);
-}
+ poll_count = 0;
+ prev_tsc = 0;
+ prev_tel_tsc = 0;
-static int
-init_lcore_rx_queues(void)
-{
- uint16_t i, nb_rx_queue;
- uint8_t lcore;
+ lcore_id = rte_lcore_id();
+ qconf = &lcore_conf[lcore_id];
- for (i = 0; i < nb_lcore_params; ++i) {
- lcore = lcore_params[i].lcore_id;
- nb_rx_queue = lcore_conf[lcore].n_rx_queue;
- if (nb_rx_queue >= MAX_RX_QUEUE_PER_LCORE) {
- printf("error: too many queues (%u) for lcore: %u\n",
- (unsigned)nb_rx_queue + 1, (unsigned)lcore);
- return -1;
- } else {
- lcore_conf[lcore].rx_queue_list[nb_rx_queue].port_id =
- lcore_params[i].port_id;
- lcore_conf[lcore].rx_queue_list[nb_rx_queue].queue_id =
- lcore_params[i].queue_id;
- lcore_conf[lcore].n_rx_queue++;
- }
+ if (qconf->n_rx_queue == 0) {
+ RTE_LOG(INFO, L3FWD_POWER, "lcore %u has nothing to do\n",
+ lcore_id);
+ return 0;
}
- return 0;
-}
-/* display usage */
-static void
-print_usage(const char *prgname)
-{
- printf ("%s [EAL options] -- -p PORTMASK -P"
- " [--config (port,queue,lcore)[,(port,queue,lcore]]"
- " [--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"
- " --no-numa: optional, disable numa awareness\n"
- " --enable-jumbo: enable jumbo frame"
- " which max packet len is PKTLEN in decimal (64-9600)\n",
- prgname);
-}
+ RTE_LOG(INFO, L3FWD_POWER, "entering main telemetry loop on lcore %u\n",
+ lcore_id);
-static int parse_max_pkt_len(const char *pktlen)
-{
- char *end = NULL;
- unsigned long len;
+ 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);
+ }
- /* parse decimal string */
- len = strtoul(pktlen, &end, 10);
- if ((pktlen[0] == '\0') || (end == NULL) || (*end != '\0'))
- return -1;
+ while (!is_done()) {
- if (len == 0)
- return -1;
+ 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]);
+ portid = rx_queue->port_id;
+ queueid = rx_queue->queue_id;
+
+ nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst,
+ MAX_PKT_BURST);
+ ep_nep[nb_rx == 0]++;
+ fp_nfp[nb_rx == MAX_PKT_BURST]++;
+ poll_count++;
+ if (unlikely(nb_rx == 0))
+ continue;
+
+ /* 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(poll_count >= DEFAULT_COUNT)) {
+ diff_tsc = cur_tsc - prev_tel_tsc;
+ if (diff_tsc >= MAX_CYCLES) {
+ br = FULL;
+ } else if (diff_tsc > MIN_CYCLES &&
+ diff_tsc < MAX_CYCLES) {
+ br = (diff_tsc * 100) / MAX_CYCLES;
+ } else {
+ br = ZERO;
+ }
+ poll_count = 0;
+ prev_tel_tsc = cur_tsc;
+ /* update stats for telemetry */
+ rte_spinlock_lock(&stats[lcore_id].telemetry_lock);
+ stats[lcore_id].ep_nep[0] = ep_nep[0];
+ stats[lcore_id].ep_nep[1] = ep_nep[1];
+ stats[lcore_id].fp_nfp[0] = fp_nfp[0];
+ stats[lcore_id].fp_nfp[1] = fp_nfp[1];
+ stats[lcore_id].br = br;
+ rte_spinlock_unlock(&stats[lcore_id].telemetry_lock);
+ }
+ }
+
+ return 0;
+}
+/* main processing loop */
+static int
+main_empty_poll_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;
+
+ 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_legacy_loop(__rte_unused void *dummy)
+{
+ struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
+ unsigned lcore_id;
+ uint64_t prev_tsc, diff_tsc, cur_tsc, tim_res_tsc, hz;
+ uint64_t prev_tsc_power = 0, cur_tsc_power, diff_tsc_power;
+ int i, j, nb_rx;
+ uint8_t queueid;
+ uint16_t portid;
+ 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;
+
+ prev_tsc = 0;
+ hz = rte_get_timer_hz();
+ tim_res_tsc = hz/TIMER_NUMBER_PER_SECOND;
+
+ 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 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();
+ cur_tsc_power = cur_tsc;
+
+ /*
+ * 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;
+ }
+
+ diff_tsc_power = cur_tsc_power - prev_tsc_power;
+ if (diff_tsc_power > tim_res_tsc) {
+ rte_timer_manage();
+ prev_tsc_power = cur_tsc_power;
+ }
+
+start_rx:
+ /*
+ * Read packet from RX queues
+ */
+ lcore_scaleup_hint = FREQ_CURRENT;
+ 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;
+
+ /**
+ * do not scale up frequency immediately as
+ * user to kernel space communication is costly
+ * which might impact packet I/O for received
+ * packets.
+ */
+ rx_queue->freq_up_hint =
+ power_freq_scaleup_heuristic(lcore_id,
+ portid, queueid);
+ }
+
+ /* 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 (likely(lcore_rx_idle_count != qconf->n_rx_queue)) {
+ for (i = 1, lcore_scaleup_hint =
+ qconf->rx_queue_list[0].freq_up_hint;
+ i < qconf->n_rx_queue; ++i) {
+ rx_queue = &(qconf->rx_queue_list[i]);
+ if (rx_queue->freq_up_hint >
+ lcore_scaleup_hint)
+ lcore_scaleup_hint =
+ rx_queue->freq_up_hint;
+ }
+
+ 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,
+ * 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,
+ lcore_id);
+ 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;
+}
+
+static int
+check_lcore_params(void)
+{
+ uint8_t queue, lcore;
+ uint16_t i;
+ int socketid;
+
+ for (i = 0; i < nb_lcore_params; ++i) {
+ queue = lcore_params[i].queue_id;
+ if (queue >= MAX_RX_QUEUE_PER_PORT) {
+ printf("invalid queue number: %hhu\n", queue);
+ return -1;
+ }
+ lcore = lcore_params[i].lcore_id;
+ if (!rte_lcore_is_enabled(lcore)) {
+ printf("error: lcore %hhu is not enabled in lcore "
+ "mask\n", lcore);
+ return -1;
+ }
+ if ((socketid = rte_lcore_to_socket_id(lcore) != 0) &&
+ (numa_on == 0)) {
+ printf("warning: lcore %hhu is on socket %d with numa "
+ "off\n", lcore, socketid);
+ }
+ if (app_mode == APP_MODE_TELEMETRY && lcore == rte_lcore_id()) {
+ printf("cannot enable main core %d in config for telemetry mode\n",
+ rte_lcore_id());
+ return -1;
+ }
+ }
+ return 0;
+}
+
+static int
+check_port_config(void)
+{
+ unsigned portid;
+ uint16_t i;
+
+ for (i = 0; i < nb_lcore_params; ++i) {
+ portid = lcore_params[i].port_id;
+ if ((enabled_port_mask & (1 << portid)) == 0) {
+ printf("port %u is not enabled in port mask\n",
+ portid);
+ return -1;
+ }
+ if (!rte_eth_dev_is_valid_port(portid)) {
+ printf("port %u is not present on the board\n",
+ portid);
+ return -1;
+ }
+ }
+ return 0;
+}
+
+static uint8_t
+get_port_n_rx_queues(const uint16_t port)
+{
+ int queue = -1;
+ uint16_t i;
+
+ for (i = 0; i < nb_lcore_params; ++i) {
+ if (lcore_params[i].port_id == port &&
+ lcore_params[i].queue_id > queue)
+ queue = lcore_params[i].queue_id;
+ }
+ return (uint8_t)(++queue);
+}
+
+static int
+init_lcore_rx_queues(void)
+{
+ uint16_t i, nb_rx_queue;
+ uint8_t lcore;
+
+ for (i = 0; i < nb_lcore_params; ++i) {
+ lcore = lcore_params[i].lcore_id;
+ nb_rx_queue = lcore_conf[lcore].n_rx_queue;
+ if (nb_rx_queue >= MAX_RX_QUEUE_PER_LCORE) {
+ printf("error: too many queues (%u) for lcore: %u\n",
+ (unsigned)nb_rx_queue + 1, (unsigned)lcore);
+ return -1;
+ } else {
+ lcore_conf[lcore].rx_queue_list[nb_rx_queue].port_id =
+ lcore_params[i].port_id;
+ lcore_conf[lcore].rx_queue_list[nb_rx_queue].queue_id =
+ lcore_params[i].queue_id;
+ lcore_conf[lcore].n_rx_queue++;
+ }
+ }
+ return 0;
+}
+
+/* display usage */
+static void
+print_usage(const char *prgname)
+{
+ 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]]"
+ " [--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"
+ " --max-pkt-len PKTLEN: maximum packet length in decimal (64-9600)\n"
+ " --parse-ptype: parse packet type by software\n"
+ " --legacy: use legacy interrupt-based scaling\n"
+ " --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"
+ " --interrupt-only: enable interrupt-only mode\n"
+ " --pmd-mgmt MODE: enable PMD power management mode. "
+ "Currently supported modes: baseline, monitor, pause, scale\n",
+ prgname);
+}
+
+static int parse_max_pkt_len(const char *pktlen)
+{
+ char *end = NULL;
+ unsigned long len;
+
+ /* parse decimal string */
+ len = strtoul(pktlen, &end, 10);
+ if ((pktlen[0] == '\0') || (end == NULL) || (*end != '\0'))
+ return -1;
+
+ if (len == 0)
+ return -1;
return len;
}
/* parse hexadecimal string */
pm = strtoul(portmask, &end, 16);
if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0'))
- return -1;
-
- if (pm == 0)
- return -1;
+ return 0;
return pm;
}
return 0;
}
+static int
+parse_pmd_mgmt_config(const char *name)
+{
+#define PMD_MGMT_MONITOR "monitor"
+#define PMD_MGMT_PAUSE "pause"
+#define PMD_MGMT_SCALE "scale"
+#define PMD_MGMT_BASELINE "baseline"
+
+ if (strncmp(PMD_MGMT_MONITOR, name, sizeof(PMD_MGMT_MONITOR)) == 0) {
+ pmgmt_type = RTE_POWER_MGMT_TYPE_MONITOR;
+ return 0;
+ }
+
+ if (strncmp(PMD_MGMT_PAUSE, name, sizeof(PMD_MGMT_PAUSE)) == 0) {
+ pmgmt_type = RTE_POWER_MGMT_TYPE_PAUSE;
+ return 0;
+ }
+
+ if (strncmp(PMD_MGMT_SCALE, name, sizeof(PMD_MGMT_SCALE)) == 0) {
+ pmgmt_type = RTE_POWER_MGMT_TYPE_SCALE;
+ return 0;
+ }
+ if (strncmp(PMD_MGMT_BASELINE, name, sizeof(PMD_MGMT_BASELINE)) == 0) {
+ baseline_enabled = true;
+ return 0;
+ }
+ /* unknown PMD power management mode */
+ return -1;
+}
+
+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_HGH_THRESHOLD;
+
+ strlcpy(s, p, sizeof(s));
+
+ 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 (hgh_edpi > 0)
+ ep_hgh_edpi = hgh_edpi;
+
+ } else {
+
+ return -1;
+ }
+
+ return 0;
+
+}
+#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"
+#define CMD_LINE_OPT_PMD_MGMT "pmd-mgmt"
+#define CMD_LINE_OPT_MAX_PKT_LEN "max-pkt-len"
+
/* Parse the argument given in the command line of the application */
static int
parse_args(int argc, char **argv)
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},
+ {CMD_LINE_OPT_MAX_PKT_LEN, 1, 0, 0},
+ {CMD_LINE_OPT_EMPTY_POLL, 1, 0, 0},
+ {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},
+ {CMD_LINE_OPT_PMD_MGMT, 1, 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)) {
+ ret = parse_config(optarg);
+ if (ret) {
+ printf("invalid config\n");
+ print_usage(prgname);
+ return -1;
+ }
+ }
+
+ 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;
+ }
+ }
- /* long options */
- case 0:
- if (!strncmp(lgopts[option_index].name, "config", 6)) {
- ret = parse_config(optarg);
+ if (!strncmp(lgopts[option_index].name,
+ "high-perf-cores", 15)) {
+ ret = parse_perf_core_list(optarg);
if (ret) {
- printf("invalid config\n");
+ printf("invalid high-perf-cores\n");
print_usage(prgname);
return -1;
}
}
if (!strncmp(lgopts[option_index].name,
- "enable-jumbo", 12)) {
- struct option lenopts =
- {"max-pkt-len", required_argument, \
- 0, 0};
+ CMD_LINE_OPT_LEGACY,
+ sizeof(CMD_LINE_OPT_LEGACY))) {
+ if (app_mode != APP_MODE_DEFAULT) {
+ printf(" legacy mode is mutually exclusive with other modes\n");
+ return -1;
+ }
+ app_mode = APP_MODE_LEGACY;
+ printf("legacy mode is enabled\n");
+ }
- printf("jumbo frame is enabled \n");
- port_conf.rxmode.jumbo_frame = 1;
+ if (!strncmp(lgopts[option_index].name,
+ CMD_LINE_OPT_EMPTY_POLL, 10)) {
+ if (app_mode != APP_MODE_DEFAULT) {
+ printf(" empty-poll mode is mutually exclusive with other modes\n");
+ return -1;
+ }
+ app_mode = APP_MODE_EMPTY_POLL;
+ ret = parse_ep_config(optarg);
- /**
- * if no max-pkt-len set, use the default value
- * ETHER_MAX_LEN
- */
- if (0 == getopt_long(argc, argvopt, "",
- &lenopts, &option_index)) {
- ret = parse_max_pkt_len(optarg);
- if ((ret < 64) ||
- (ret > MAX_JUMBO_PKT_LEN)){
- printf("invalid packet "
- "length\n");
- print_usage(prgname);
- return -1;
- }
- port_conf.rxmode.max_rx_pkt_len = ret;
+ if (ret) {
+ printf("invalid empty poll config\n");
+ print_usage(prgname);
+ return -1;
+ }
+ printf("empty-poll is enabled\n");
+ }
+
+ if (!strncmp(lgopts[option_index].name,
+ CMD_LINE_OPT_TELEMETRY,
+ sizeof(CMD_LINE_OPT_TELEMETRY))) {
+ if (app_mode != APP_MODE_DEFAULT) {
+ printf(" telemetry mode is mutually exclusive with other modes\n");
+ return -1;
+ }
+ app_mode = APP_MODE_TELEMETRY;
+ printf("telemetry mode is enabled\n");
+ }
+
+ if (!strncmp(lgopts[option_index].name,
+ CMD_LINE_OPT_PMD_MGMT,
+ sizeof(CMD_LINE_OPT_PMD_MGMT))) {
+ if (app_mode != APP_MODE_DEFAULT) {
+ printf(" power mgmt mode is mutually exclusive with other modes\n");
+ return -1;
+ }
+ if (parse_pmd_mgmt_config(optarg) < 0) {
+ printf(" Invalid PMD power management mode: %s\n",
+ optarg);
+ return -1;
+ }
+ app_mode = APP_MODE_PMD_MGMT;
+ printf("PMD power mgmt 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;
}
- printf("set jumbo frame "
- "max packet length to %u\n",
- (unsigned int)port_conf.rxmode.max_rx_pkt_len);
+ app_mode = APP_MODE_INTERRUPT;
+ printf("interrupt-only mode is enabled\n");
+ }
+
+ if (!strncmp(lgopts[option_index].name,
+ CMD_LINE_OPT_MAX_PKT_LEN,
+ sizeof(CMD_LINE_OPT_MAX_PKT_LEN))) {
+ printf("Custom frame size is configured\n");
+ max_pkt_len = parse_max_pkt_len(optarg);
+ }
+
+ if (!strncmp(lgopts[option_index].name,
+ CMD_LINE_OPT_PARSE_PTYPE,
+ sizeof(CMD_LINE_OPT_PARSE_PTYPE))) {
+ printf("soft parse-ptype is enabled\n");
+ parse_ptype = 1;
}
break;
argv[optind-1] = prgname;
ret = optind-1;
- optind = 0; /* reset getopt lib */
+ optind = 1; /* reset getopt lib */
return ret;
}
static void
-print_ethaddr(const char *name, const struct ether_addr *eth_addr)
+print_ethaddr(const char *name, const struct rte_ether_addr *eth_addr)
{
- char buf[ETHER_ADDR_FMT_SIZE];
- ether_format_addr(buf, ETHER_ADDR_FMT_SIZE, eth_addr);
+ char buf[RTE_ETHER_ADDR_FMT_SIZE];
+ rte_ether_format_addr(buf, RTE_ETHER_ADDR_FMT_SIZE, eth_addr);
printf("%s%s", name, buf);
}
/* populate the ipv4 hash */
- for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) {
+ for (i = 0; i < RTE_DIM(ipv4_l3fwd_route_array); i++) {
ret = rte_hash_add_key (ipv4_l3fwd_lookup_struct[socketid],
(void *) &ipv4_l3fwd_route_array[i].key);
if (ret < 0) {
}
/* populate the ipv6 hash */
- for (i = 0; i < IPV6_L3FWD_NUM_ROUTES; i++) {
+ for (i = 0; i < RTE_DIM(ipv6_l3fwd_route_array); i++) {
ret = rte_hash_add_key (ipv6_l3fwd_lookup_struct[socketid],
(void *) &ipv6_l3fwd_route_array[i].key);
if (ret < 0) {
" on socket %d\n", socketid);
/* populate the LPM table */
- for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) {
+ for (i = 0; i < RTE_DIM(ipv4_l3fwd_route_array); i++) {
ret = rte_lpm_add(ipv4_l3fwd_lookup_struct[socketid],
ipv4_l3fwd_route_array[i].ip,
ipv4_l3fwd_route_array[i].depth,
/* Check the link status of all ports in up to 9s, and print them finally */
static void
-check_all_ports_link_status(uint8_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 */
- uint8_t portid, count, all_ports_up, print_flag = 0;
+ uint8_t count, all_ports_up, print_flag = 0;
+ uint16_t portid;
struct rte_eth_link link;
+ int ret;
+ char link_status_text[RTE_ETH_LINK_MAX_STR_LEN];
printf("\nChecking link status");
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));
- rte_eth_link_get_nowait(portid, &link);
+ ret = rte_eth_link_get_nowait(portid, &link);
+ if (ret < 0) {
+ all_ports_up = 0;
+ if (print_flag == 1)
+ printf("Port %u link get failed: %s\n",
+ portid, rte_strerror(-ret));
+ continue;
+ }
/* print link status if flag set */
if (print_flag == 1) {
- if (link.link_status)
- printf("Port %d Link Up - speed %u "
- "Mbps - %s\n", (uint8_t)portid,
- (unsigned)link.link_speed,
- (link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
- else
- printf("Port %d Link Down\n",
- (uint8_t)portid);
+ rte_eth_link_to_str(link_status_text,
+ sizeof(link_status_text), &link);
+ printf("Port %d %s\n", portid,
+ link_status_text);
continue;
}
/* clear all_ports_up flag if any link down */
- if (link.link_status == ETH_LINK_DOWN) {
+ if (link.link_status == RTE_ETH_LINK_DOWN) {
all_ports_up = 0;
break;
}
}
}
+static int check_ptype(uint16_t portid)
+{
+ int i, ret;
+ int ptype_l3_ipv4 = 0;
+#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
+ int ptype_l3_ipv6 = 0;
+#endif
+ uint32_t ptype_mask = RTE_PTYPE_L3_MASK;
+
+ ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, NULL, 0);
+ if (ret <= 0)
+ return 0;
+
+ uint32_t ptypes[ret];
+
+ ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, ptypes, ret);
+ for (i = 0; i < ret; ++i) {
+ if (ptypes[i] & RTE_PTYPE_L3_IPV4)
+ ptype_l3_ipv4 = 1;
+#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
+ if (ptypes[i] & RTE_PTYPE_L3_IPV6)
+ ptype_l3_ipv6 = 1;
+#endif
+ }
+
+ if (ptype_l3_ipv4 == 0)
+ printf("port %d cannot parse RTE_PTYPE_L3_IPV4\n", portid);
+
+#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
+ if (ptype_l3_ipv6 == 0)
+ printf("port %d cannot parse RTE_PTYPE_L3_IPV6\n", portid);
+#endif
+
+#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
+ if (ptype_l3_ipv4)
+#else /* APP_LOOKUP_EXACT_MATCH */
+ if (ptype_l3_ipv4 && ptype_l3_ipv6)
+#endif
+ return 1;
+
+ return 0;
+
+}
+
+static int
+init_power_library(void)
+{
+ enum power_management_env env;
+ unsigned int lcore_id;
+ int ret = 0;
+
+ RTE_LCORE_FOREACH(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;
+ }
+ /* we're not supporting the VM channel mode */
+ env = rte_power_get_env();
+ if (env != PM_ENV_ACPI_CPUFREQ &&
+ env != PM_ENV_PSTATE_CPUFREQ) {
+ RTE_LOG(ERR, POWER,
+ "Only ACPI and PSTATE mode are supported\n");
+ return -1;
+ }
+ }
+ return ret;
+}
+
+static int
+deinit_power_library(void)
+{
+ unsigned int lcore_id;
+ int ret = 0;
+
+ RTE_LCORE_FOREACH(lcore_id) {
+ /* deinit power management library */
+ ret = rte_power_exit(lcore_id);
+ if (ret) {
+ RTE_LOG(ERR, POWER,
+ "Library deinitialization failed on core %u\n",
+ lcore_id);
+ return ret;
+ }
+ }
+ return ret;
+}
+
+static void
+get_current_stat_values(uint64_t *values)
+{
+ unsigned int lcore_id = rte_lcore_id();
+ struct lcore_conf *qconf;
+ uint64_t app_eps = 0, app_fps = 0, app_br = 0;
+ uint64_t count = 0;
+
+ RTE_LCORE_FOREACH_WORKER(lcore_id) {
+ qconf = &lcore_conf[lcore_id];
+ if (qconf->n_rx_queue == 0)
+ continue;
+ count++;
+ rte_spinlock_lock(&stats[lcore_id].telemetry_lock);
+ app_eps += stats[lcore_id].ep_nep[1];
+ app_fps += stats[lcore_id].fp_nfp[1];
+ app_br += stats[lcore_id].br;
+ rte_spinlock_unlock(&stats[lcore_id].telemetry_lock);
+ }
+
+ if (count > 0) {
+ values[0] = app_eps/count;
+ values[1] = app_fps/count;
+ values[2] = app_br/count;
+ } else
+ memset(values, 0, sizeof(uint64_t) * NUM_TELSTATS);
+
+}
+
+static void
+update_telemetry(__rte_unused struct rte_timer *tim,
+ __rte_unused void *arg)
+{
+ int ret;
+ uint64_t values[NUM_TELSTATS] = {0};
+
+ get_current_stat_values(values);
+ ret = rte_metrics_update_values(RTE_METRICS_GLOBAL, telstats_index,
+ values, RTE_DIM(values));
+ if (ret < 0)
+ RTE_LOG(WARNING, POWER, "failed to update metrcis\n");
+}
+
+static int
+handle_app_stats(const char *cmd __rte_unused,
+ const char *params __rte_unused,
+ struct rte_tel_data *d)
+{
+ uint64_t values[NUM_TELSTATS] = {0};
+ uint32_t i;
+
+ rte_tel_data_start_dict(d);
+ get_current_stat_values(values);
+ for (i = 0; i < NUM_TELSTATS; i++)
+ rte_tel_data_add_dict_u64(d, telstats_strings[i].name,
+ values[i]);
+ return 0;
+}
+
+static void
+telemetry_setup_timer(void)
+{
+ int lcore_id = rte_lcore_id();
+ uint64_t hz = rte_get_timer_hz();
+ uint64_t ticks;
+
+ ticks = hz / TELEMETRY_INTERVALS_PER_SEC;
+ rte_timer_reset_sync(&telemetry_timer,
+ ticks,
+ PERIODICAL,
+ lcore_id,
+ update_telemetry,
+ NULL);
+}
+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_main_lcore() != lcore_id) {
+ rte_panic("timer on lcore:%d which is not main core:%d\n",
+ lcore_id,
+ rte_get_main_lcore());
+ }
+
+ RTE_LOG(INFO, POWER, "Bring up the Timer\n");
+
+ if (app_mode == APP_MODE_EMPTY_POLL)
+ empty_poll_setup_timer();
+ else
+ telemetry_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;
+}
+
+static int
+autodetect_mode(void)
+{
+ RTE_LOG(NOTICE, L3FWD_POWER, "Operating mode not specified, probing frequency scaling support...\n");
+
+ /*
+ * Empty poll and telemetry modes have to be specifically requested to
+ * be enabled, but we can auto-detect between interrupt mode with or
+ * without frequency scaling. Both ACPI and pstate can be used.
+ */
+ if (rte_power_check_env_supported(PM_ENV_ACPI_CPUFREQ))
+ return APP_MODE_LEGACY;
+ if (rte_power_check_env_supported(PM_ENV_PSTATE_CPUFREQ))
+ return APP_MODE_LEGACY;
+
+ RTE_LOG(NOTICE, L3FWD_POWER, "Frequency scaling not supported, selecting interrupt-only mode\n");
+
+ return APP_MODE_INTERRUPT;
+}
+
+static const char *
+mode_to_str(enum appmode mode)
+{
+ switch (mode) {
+ case APP_MODE_LEGACY:
+ return "legacy";
+ case APP_MODE_EMPTY_POLL:
+ return "empty poll";
+ case APP_MODE_TELEMETRY:
+ return "telemetry";
+ case APP_MODE_INTERRUPT:
+ return "interrupt-only";
+ case APP_MODE_PMD_MGMT:
+ return "pmd mgmt";
+ default:
+ return "invalid";
+ }
+}
+
+static uint32_t
+eth_dev_get_overhead_len(uint32_t max_rx_pktlen, uint16_t max_mtu)
+{
+ uint32_t overhead_len;
+
+ if (max_mtu != UINT16_MAX && max_rx_pktlen > max_mtu)
+ overhead_len = max_rx_pktlen - max_mtu;
+ else
+ overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
+ return overhead_len;
+}
+
+static int
+config_port_max_pkt_len(struct rte_eth_conf *conf,
+ struct rte_eth_dev_info *dev_info)
+{
+ uint32_t overhead_len;
+
+ if (max_pkt_len == 0)
+ return 0;
+
+ if (max_pkt_len < RTE_ETHER_MIN_LEN || max_pkt_len > MAX_JUMBO_PKT_LEN)
+ return -1;
+
+ overhead_len = eth_dev_get_overhead_len(dev_info->max_rx_pktlen,
+ dev_info->max_mtu);
+ conf->rxmode.mtu = max_pkt_len - overhead_len;
+
+ if (conf->rxmode.mtu > RTE_ETHER_MTU)
+ conf->txmode.offloads |= RTE_ETH_TX_OFFLOAD_MULTI_SEGS;
+
+ return 0;
+}
+
+/* Power library initialized in the main routine. 8< */
int
main(int argc, char **argv)
{
struct rte_eth_dev_info dev_info;
struct rte_eth_txconf *txconf;
int ret;
- unsigned nb_ports;
+ uint16_t nb_ports;
uint16_t queueid;
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;
- uint8_t nb_tx_port;
+ uint8_t nb_rx_queue, queue, socketid;
+ uint16_t portid;
+ const char *ptr_strings[NUM_TELSTATS];
/* catch SIGINT and restore cpufreq governor to ondemand */
signal(SIGINT, signal_exit_now);
/* init RTE timer library to be used late */
rte_timer_subsystem_init();
+ /* if we're running pmd-mgmt mode, don't default to baseline mode */
+ baseline_enabled = false;
+
/* parse application arguments (after the EAL ones) */
ret = parse_args(argc, argv);
if (ret < 0)
rte_exit(EXIT_FAILURE, "Invalid L3FWD parameters\n");
+ if (app_mode == APP_MODE_DEFAULT)
+ app_mode = autodetect_mode();
+
+ RTE_LOG(INFO, L3FWD_POWER, "Selected operation mode: %s\n",
+ mode_to_str(app_mode));
+
+ /* only legacy and empty poll mode rely on power library */
+ if ((app_mode == APP_MODE_LEGACY || app_mode == APP_MODE_EMPTY_POLL) &&
+ 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_avail();
- nb_ports = rte_eth_dev_count();
- if (nb_ports > RTE_MAX_ETHPORTS)
- nb_ports = RTE_MAX_ETHPORTS;
-
- 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();
- nb_tx_port = 0;
/* initialize all ports */
- for (portid = 0; portid < nb_ports; portid++) {
+ 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 ||
+ app_mode == APP_MODE_INTERRUPT;
+
/* skip ports that are not enabled */
if ((enabled_port_mask & (1 << portid)) == 0) {
printf("\nSkipping disabled port %d\n", portid);
printf("Initializing port %d ... ", portid );
fflush(stdout);
- rte_eth_dev_info_get(portid, &dev_info);
+ ret = rte_eth_dev_info_get(portid, &dev_info);
+ if (ret != 0)
+ rte_exit(EXIT_FAILURE,
+ "Error during getting device (port %u) info: %s\n",
+ portid, strerror(-ret));
+
dev_rxq_num = dev_info.max_rx_queues;
dev_txq_num = dev_info.max_tx_queues;
n_tx_queue = dev_txq_num;
printf("Creating queues: nb_rxq=%d nb_txq=%u... ",
nb_rx_queue, (unsigned)n_tx_queue );
+ /* If number of Rx queue is 0, no need to enable Rx interrupt */
+ if (nb_rx_queue == 0)
+ need_intr = false;
+
+ if (need_intr)
+ local_port_conf.intr_conf.rxq = 1;
+
+ ret = rte_eth_dev_info_get(portid, &dev_info);
+ if (ret != 0)
+ rte_exit(EXIT_FAILURE,
+ "Error during getting device (port %u) info: %s\n",
+ portid, strerror(-ret));
+
+ ret = config_port_max_pkt_len(&local_port_conf, &dev_info);
+ if (ret != 0)
+ rte_exit(EXIT_FAILURE,
+ "Invalid max packet length: %u (port %u)\n",
+ max_pkt_len, portid);
+
+ if (dev_info.tx_offload_capa & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE)
+ local_port_conf.txmode.offloads |=
+ RTE_ETH_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, &port_conf);
+ (uint16_t)n_tx_queue, &local_port_conf);
if (ret < 0)
rte_exit(EXIT_FAILURE, "Cannot configure device: "
"err=%d, port=%d\n", ret, portid);
- rte_eth_macaddr_get(portid, &ports_eth_addr[portid]);
+ ret = rte_eth_dev_adjust_nb_rx_tx_desc(portid, &nb_rxd,
+ &nb_txd);
+ if (ret < 0)
+ rte_exit(EXIT_FAILURE,
+ "Cannot adjust number of descriptors: err=%d, port=%d\n",
+ ret, portid);
+
+ ret = rte_eth_macaddr_get(portid, &ports_eth_addr[portid]);
+ if (ret < 0)
+ rte_exit(EXIT_FAILURE,
+ "Cannot get MAC address: err=%d, port=%d\n",
+ ret, portid);
+
print_ethaddr(" Address:", &ports_eth_addr[portid]);
printf(", ");
rte_eth_dev_socket_id(portid));
if (qconf->tx_buffer[portid] == NULL)
rte_exit(EXIT_FAILURE, "Can't allocate tx buffer for port %u\n",
- (unsigned) portid);
+ portid);
rte_eth_tx_buffer_init(qconf->tx_buffer[portid], MAX_PKT_BURST);
}
printf("txq=%u,%d,%d ", lcore_id, queueid, socketid);
fflush(stdout);
- rte_eth_dev_info_get(portid, &dev_info);
txconf = &dev_info.default_txconf;
- if (port_conf.rxmode.jumbo_frame)
- txconf->txq_flags = 0;
+ txconf->offloads = local_port_conf.txmode.offloads;
ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd,
socketid, txconf);
if (ret < 0)
qconf->tx_queue_id[portid] = queueid;
queueid++;
- qconf->n_tx_port = nb_tx_port;
qconf->tx_port_id[qconf->n_tx_port] = portid;
+ qconf->n_tx_port++;
}
printf("\n");
-
- nb_tx_port++;
}
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
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 (app_mode == APP_MODE_LEGACY) {
+ /* 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);
+
/* init RX queues */
for(queue = 0; queue < qconf->n_rx_queue; ++queue) {
+ struct rte_eth_rxconf rxq_conf;
+
portid = qconf->rx_queue_list[queue].port_id;
queueid = qconf->rx_queue_list[queue].queue_id;
printf("rxq=%d,%d,%d ", portid, queueid, socketid);
fflush(stdout);
+ ret = rte_eth_dev_info_get(portid, &dev_info);
+ if (ret != 0)
+ rte_exit(EXIT_FAILURE,
+ "Error during getting device (port %u) info: %s\n",
+ portid, strerror(-ret));
+
+ rxq_conf = dev_info.default_rxconf;
+ rxq_conf.offloads = port_conf.rxmode.offloads;
ret = rte_eth_rx_queue_setup(portid, queueid, nb_rxd,
- socketid, NULL,
+ socketid, &rxq_conf,
pktmbuf_pool[socketid]);
if (ret < 0)
rte_exit(EXIT_FAILURE,
"rte_eth_rx_queue_setup: err=%d, "
"port=%d\n", ret, portid);
+
+ if (parse_ptype) {
+ if (add_cb_parse_ptype(portid, queueid) < 0)
+ rte_exit(EXIT_FAILURE,
+ "Fail to add ptype cb\n");
+ }
+
+ if (app_mode == APP_MODE_PMD_MGMT && !baseline_enabled) {
+ ret = rte_power_ethdev_pmgmt_queue_enable(
+ lcore_id, portid, queueid,
+ pmgmt_type);
+ if (ret < 0)
+ rte_exit(EXIT_FAILURE,
+ "rte_power_ethdev_pmgmt_queue_enable: err=%d, port=%d\n",
+ ret, portid);
+ }
}
}
+ /* >8 End of power library initialization. */
printf("\n");
/* start ports */
- for (portid = 0; portid < nb_ports; portid++) {
+ RTE_ETH_FOREACH_DEV(portid) {
if ((enabled_port_mask & (1 << portid)) == 0) {
continue;
}
* to itself through 2 cross-connected ports of the
* target machine.
*/
- if (promiscuous_on)
- rte_eth_promiscuous_enable(portid);
+ if (promiscuous_on) {
+ ret = rte_eth_promiscuous_enable(portid);
+ if (ret != 0)
+ rte_exit(EXIT_FAILURE,
+ "rte_eth_promiscuous_enable: err=%s, port=%u\n",
+ rte_strerror(-ret), portid);
+ }
/* initialize spinlock for each port */
rte_spinlock_init(&(locks[portid]));
+
+ if (!parse_ptype)
+ if (!check_ptype(portid))
+ rte_exit(EXIT_FAILURE,
+ "PMD can not provide needed ptypes\n");
+ }
+
+ check_all_ports_link_status(enabled_port_mask);
+
+ if (app_mode == APP_MODE_EMPTY_POLL) {
+
+ 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");
}
- check_all_ports_link_status((uint8_t)nb_ports, enabled_port_mask);
/* launch per-lcore init on every lcore */
- rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER);
- RTE_LCORE_FOREACH_SLAVE(lcore_id) {
+ if (app_mode == APP_MODE_LEGACY) {
+ rte_eal_mp_remote_launch(main_legacy_loop, NULL, CALL_MAIN);
+ } else if (app_mode == APP_MODE_EMPTY_POLL) {
+ empty_poll_stop = false;
+ rte_eal_mp_remote_launch(main_empty_poll_loop, NULL,
+ SKIP_MAIN);
+ } else if (app_mode == APP_MODE_TELEMETRY) {
+ unsigned int i;
+
+ /* Init metrics library */
+ rte_metrics_init(rte_socket_id());
+ /** Register stats with metrics library */
+ for (i = 0; i < NUM_TELSTATS; i++)
+ ptr_strings[i] = telstats_strings[i].name;
+
+ ret = rte_metrics_reg_names(ptr_strings, NUM_TELSTATS);
+ if (ret >= 0)
+ telstats_index = ret;
+ else
+ rte_exit(EXIT_FAILURE, "failed to register metrics names");
+
+ RTE_LCORE_FOREACH_WORKER(lcore_id) {
+ rte_spinlock_init(&stats[lcore_id].telemetry_lock);
+ }
+ rte_timer_init(&telemetry_timer);
+ rte_telemetry_register_cmd("/l3fwd-power/stats",
+ handle_app_stats,
+ "Returns global power stats. Parameters: None");
+ rte_eal_mp_remote_launch(main_telemetry_loop, NULL,
+ SKIP_MAIN);
+ } else if (app_mode == APP_MODE_INTERRUPT) {
+ rte_eal_mp_remote_launch(main_intr_loop, NULL, CALL_MAIN);
+ } else if (app_mode == APP_MODE_PMD_MGMT) {
+ /* reuse telemetry loop for PMD power management mode */
+ rte_eal_mp_remote_launch(main_telemetry_loop, NULL, CALL_MAIN);
+ }
+
+ if (app_mode == APP_MODE_EMPTY_POLL || app_mode == APP_MODE_TELEMETRY)
+ launch_timer(rte_lcore_id());
+
+ RTE_LCORE_FOREACH_WORKER(lcore_id) {
if (rte_eal_wait_lcore(lcore_id) < 0)
return -1;
}
+ if (app_mode == APP_MODE_PMD_MGMT) {
+ for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+ if (rte_lcore_is_enabled(lcore_id) == 0)
+ continue;
+ qconf = &lcore_conf[lcore_id];
+ for (queue = 0; queue < qconf->n_rx_queue; ++queue) {
+ portid = qconf->rx_queue_list[queue].port_id;
+ queueid = qconf->rx_queue_list[queue].queue_id;
+
+ rte_power_ethdev_pmgmt_queue_disable(lcore_id,
+ portid, queueid);
+ }
+ }
+ }
+
+ RTE_ETH_FOREACH_DEV(portid)
+ {
+ if ((enabled_port_mask & (1 << portid)) == 0)
+ continue;
+
+ ret = rte_eth_dev_stop(portid);
+ if (ret != 0)
+ RTE_LOG(ERR, L3FWD_POWER, "rte_eth_dev_stop: err=%d, port=%u\n",
+ ret, portid);
+
+ rte_eth_dev_close(portid);
+ }
+
+ if (app_mode == APP_MODE_EMPTY_POLL)
+ rte_power_empty_poll_stat_free();
+
+ if ((app_mode == APP_MODE_LEGACY || app_mode == APP_MODE_EMPTY_POLL) &&
+ deinit_power_library())
+ rte_exit(EXIT_FAILURE, "deinit_power_library failed\n");
+
+ if (rte_eal_cleanup() < 0)
+ RTE_LOG(ERR, L3FWD_POWER, "EAL cleanup failed\n");
+
return 0;
}