DPDK L2fwd 源碼閱讀
代碼部分
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright(c) 2010-2016 Intel Corporation
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdint.h>
#include <inttypes.h>
#include <sys/types.h>
#include <sys/queue.h>
#include <netinet/in.h>
#include <setjmp.h>
#include <stdarg.h>
#include <ctype.h>
#include <errno.h>
#include <getopt.h>
#include <signal.h>
#include <stdbool.h>
#include <rte_common.h>
#include <rte_log.h>
#include <rte_malloc.h>
#include <rte_memory.h>
#include <rte_memcpy.h>
#include <rte_eal.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_random.h>
#include <rte_debug.h>
#include <rte_ether.h>
#include <rte_ethdev.h>
#include <rte_mempool.h>
#include <rte_mbuf.h>
static volatile bool force_quit;
/* MAC updating enabled by default */
static int mac_updating = 1;
/* MAC updating，默認開啓。若不開啓，則是和basicfw同樣的模式。開啓後，會有以下影響：
The source MAC address is replaced by the TX_PORT MAC address
源MAC地址會改寫成發送端口的MAC地址
The destination MAC address is replaced by 02:00:00:00:00:TX_PORT_ID
改寫目的MAC地址，改寫爲 02:00:00:00:00:<發送端口的port id>
*/
#define RTE_LOGTYPE_L2FWD RTE_LOGTYPE_USER1
#define MAX_PKT_BURST 32
#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */
#define MEMPOOL_CACHE_SIZE 256
/*
* Configurable number of RX/TX ring descriptors
*/
#define RTE_TEST_RX_DESC_DEFAULT 1024
#define RTE_TEST_TX_DESC_DEFAULT 1024
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 l2fwd_ports_eth_addr[RTE_MAX_ETHPORTS];
/* mask of enabled ports */
static uint32_t l2fwd_enabled_port_mask = 0;
/* list of enabled ports */
static uint32_t l2fwd_dst_ports[RTE_MAX_ETHPORTS];
static unsigned int l2fwd_rx_queue_per_lcore = 1; // 每一個邏輯核最多能夠用來處理幾個端口/隊列（L2fwd 一個端口分配各一個收發隊列）
#define MAX_RX_QUEUE_PER_LCORE 16
#define MAX_TX_QUEUE_PER_PORT 16
struct lcore_queue_conf { // 邏輯核上的隊列配置
unsigned n_rx_port; // 該 lcore 上綁定多少個端口，也做爲下一個數組的下標（0 ~ n-1）。
unsigned rx_port_list[MAX_RX_QUEUE_PER_LCORE]; // 存放一系列端口號，綁定哪些端口。
} __rte_cache_aligned;
// 這也就是 poll module driver 思想。綁定 lcore 和 port，特定的 lcore 輪詢對應的一個或多個 port
struct lcore_queue_conf lcore_queue_conf[RTE_MAX_LCORE]; // 數組下標是 lcore id
static struct rte_eth_dev_tx_buffer *tx_buffer[RTE_MAX_ETHPORTS]; // 用於緩衝將來要發送的數據包的結構，API rte_eth_tx_buffer 和 rte_eth_tx_buffer_flush使用的結構
static struct rte_eth_conf port_conf = {
.rxmode = { // RX feature 見 flow_filtering
.split_hdr_size = 0,
.ignore_offload_bitfield = 1,
.offloads = DEV_RX_OFFLOAD_CRC_STRIP,
},
.txmode = { // TX feature
.mq_mode = ETH_MQ_TX_NONE, // mq_多隊列選項，有一些宏來定義用多隊列發包的方法
},
};
struct rte_mempool * l2fwd_pktmbuf_pool = NULL;
/* Per-port statistics struct */
struct l2fwd_port_statistics {
uint64_t tx; // 發包的數量
uint64_t rx; // 收包的數量
uint64_t dropped; // 丟包的數量
} __rte_cache_aligned;
struct l2fwd_port_statistics port_statistics[RTE_MAX_ETHPORTS];
#define MAX_TIMER_PERIOD 86400 /* 1 day max */
/* A tsc-based timer responsible for triggering statistics printout */
// timer 負責每隔一段時間觸發打印數據
static uint64_t timer_period = 10; /* default period is 10 seconds */
/* Print out statistics on packets dropped */
static void
print_stats(void)
{
uint64_t total_packets_dropped, total_packets_tx, total_packets_rx;
unsigned portid;
total_packets_dropped = 0;
total_packets_tx = 0;
total_packets_rx = 0;
const char clr[] = { 27, '[', '2', 'J', '\0' };
const char topLeft[] = { 27, '[', '1', ';', '1', 'H','\0' };
/* Clear screen and move to top left */
printf("%s%s", clr, topLeft);
printf("\nPort statistics ====================================");
for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) {
/* skip disabled ports */
if ((l2fwd_enabled_port_mask & (1 << portid)) == 0)
continue;
printf("\nStatistics for port %u ------------------------------"
"\nPackets sent: %24"PRIu64
"\nPackets received: %20"PRIu64
"\nPackets dropped: %21"PRIu64,
portid,
port_statistics[portid].tx,
port_statistics[portid].rx,
port_statistics[portid].dropped);
total_packets_dropped += port_statistics[portid].dropped;
total_packets_tx += port_statistics[portid].tx;
total_packets_rx += port_statistics[portid].rx;
}
printf("\nAggregate statistics ==============================="
"\nTotal packets sent: %18"PRIu64
"\nTotal packets received: %14"PRIu64
"\nTotal packets dropped: %15"PRIu64,
total_packets_tx,
total_packets_rx,
total_packets_dropped);
printf("\n====================================================\n");
}
static void
l2fwd_mac_updating(struct rte_mbuf *m, unsigned dest_portid) // 改寫包的 MAC 層信息
{
struct ether_hdr *eth;
void *tmp;
eth = rte_pktmbuf_mtod(m, struct ether_hdr *);
/* 02:00:00:00:00:xx */
tmp = ð->d_addr.addr_bytes[0]; // 改寫目的 MAC 地址爲 02:00:00:00:00:<發送端口的port id>
*((uint64_t *)tmp) = 0x000000000002 + ((uint64_t)dest_portid << 40);
/* src addr */
// 改寫 源 MAC 地址 改寫成發送端口的MAC地址
ether_addr_copy(&l2fwd_ports_eth_addr[dest_portid], ð->s_addr);
}
static void
l2fwd_simple_forward(struct rte_mbuf *m, unsigned portid)
{
unsigned dst_port;
int sent;
struct rte_eth_dev_tx_buffer *buffer;
dst_port = l2fwd_dst_ports[portid]; // 與之配對的端口
if (mac_updating) // 若是開啓了 mac updating 模式
l2fwd_mac_updating(m, dst_port); // 調整 MAC 地址
buffer = tx_buffer[dst_port]; // 該端口的 tx_buffer
sent = rte_eth_tx_buffer(dst_port, 0, buffer, m); // 將收到的包緩存在 tx_buffer 裏，用於將來的發送。
// 返回值 若是爲0，表示 pkt 已經被緩存
// 返回值 N>0，表示因爲緩衝區被flush致使N個pkt被髮送。
if (sent)
port_statistics[dst_port].tx += sent;
}
/* main processing loop */
static void
l2fwd_main_loop(void)
{
struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
struct rte_mbuf *m;
int sent;
unsigned lcore_id;
uint64_t prev_tsc, diff_tsc, cur_tsc, timer_tsc;
unsigned i, j, portid, nb_rx;
struct lcore_queue_conf *qconf;
const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S *
BURST_TX_DRAIN_US;
struct rte_eth_dev_tx_buffer *buffer;
prev_tsc = 0;
timer_tsc = 0;
lcore_id = rte_lcore_id(); // 獲取本身的 lcore id
qconf = &lcore_queue_conf[lcore_id];
if (qconf->n_rx_port == 0) { // 由於對每個 lcore 都執行 main 線程，若是該 lcore 上沒有綁定端口，就無事可作。
RTE_LOG(INFO, L2FWD, "lcore %u has nothing to do\n", lcore_id);
return;
}
RTE_LOG(INFO, L2FWD, "entering main loop on lcore %u\n", lcore_id);
for (i = 0; i < qconf->n_rx_port; i++) {
portid = qconf->rx_port_list[i];
RTE_LOG(INFO, L2FWD, " -- lcoreid=%u portid=%u\n", lcore_id,
portid); // 顯示一下 lcore 和 port 的對應關係
}
while (!force_quit) {
cur_tsc = rte_rdtsc(); // 獲取從開機起至當前的時間戳
/*
* TX burst queue drain
* 發送邏輯
*/
diff_tsc = cur_tsc - prev_tsc;
if (unlikely(diff_tsc > drain_tsc)) { // 時間到了
// 若是tx_buffer滿，會發送一批 pkt 出去。若是沒滿，爲了保證沒有沒被髮出的 pkt，因此每一個一小段時間，也會發送隊列中的包
for (i = 0; i < qconf->n_rx_port; i++) { // 對 lcore 負責的每一個端口
portid = l2fwd_dst_ports[qconf->rx_port_list[i]]; // 與之配對的端口
buffer = tx_buffer[portid];
sent = rte_eth_tx_buffer_flush(portid, 0, buffer); // 將 buffer 裏的 pkt 所有從 port id 的 0號 Tx queue 發出去
if (sent) // 返回值是成功發出的 pkt 數量
port_statistics[portid].tx += sent;
}
/* if timer is enabled */
if (timer_period > 0) {
/* advance the timer */
timer_tsc += diff_tsc;
/* if timer has reached its timeout */
if (unlikely(timer_tsc >= timer_period)) {
/* do this only on master core */
if (lcore_id == rte_get_master_lcore()) { // 若是計時器到了，就打印一下信息。只在主核心打印信息
print_stats();
/* reset the timer */
timer_tsc = 0;
}
}
}
prev_tsc = cur_tsc;
}
/*
* Read packet from RX queues
* 接收邏輯
*/
for (i = 0; i < qconf->n_rx_port; i++) { // 對 lcore 負責的每一個端口
portid = qconf->rx_port_list[i]; // 獲取端口號
nb_rx = rte_eth_rx_burst(portid, 0,
pkts_burst, MAX_PKT_BURST); // 收包，收到該端口的 0 號 rx queue
port_statistics[portid].rx += nb_rx; // 更新端口上的收包計數器
for (j = 0; j < nb_rx; j++) { // 對每個包
m = pkts_burst[j]; // 包的 mbuf 指針
// Prefetch: 預取一個 cache 行。參數是要取的地址，類型 void *
// rte_pktmbuf_mtod：返回 mbuf 中 data 的起始地址
rte_prefetch0(rte_pktmbuf_mtod(m, void *));
l2fwd_simple_forward(m, portid); // 收包後進行 L2fwd !!
}
}
}
}
static int
l2fwd_launch_one_lcore(__attribute__((unused)) void *dummy)
{
l2fwd_main_loop();
return 0;
}
/* display usage */
static void
l2fwd_usage(const char *prgname)
{
printf("%s [EAL options] -- -p PORTMASK [-q NQ]\n"
" -p PORTMASK: hexadecimal bitmask of ports to configure\n"
" -q NQ: number of queue (=ports) per lcore (default is 1)\n"
" -T PERIOD: statistics will be refreshed each PERIOD seconds (0 to disable, 10 default, 86400 maximum)\n"
" --[no-]mac-updating: Enable or disable MAC addresses updating (enabled by default)\n"
" When enabled:\n"
" - The source MAC address is replaced by the TX port MAC address\n"
" - The destination MAC address is replaced by 02:00:00:00:00:TX_PORT_ID\n",
prgname);
}
static int
l2fwd_parse_portmask(const char *portmask)
{
char *end = NULL;
unsigned long pm;
/* parse hexadecimal string */
pm = strtoul(portmask, &end, 16); // 將字符串 portmask 轉成 16 進制無符號長整形
if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0'))
return -1;
if (pm == 0)
return -1;
return pm;
}
static unsigned int
l2fwd_parse_nqueue(const char *q_arg)
{
char *end = NULL;
unsigned long n;
/* parse hexadecimal string */
n = strtoul(q_arg, &end, 10);
if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0'))
return 0;
if (n == 0)
return 0;
if (n >= MAX_RX_QUEUE_PER_LCORE)
return 0;
return n;
}
static int
l2fwd_parse_timer_period(const char *q_arg)
{
char *end = NULL;
int n;
/* parse number string */
n = strtol(q_arg, &end, 10);
if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0'))
return -1;
if (n >= MAX_TIMER_PERIOD)
return -1;
return n;
}
static const char short_options[] =
"p:" /* portmask */
"q:" /* number of queues */
"T:" /* timer period */
;
#define CMD_LINE_OPT_MAC_UPDATING "mac-updating"
#define CMD_LINE_OPT_NO_MAC_UPDATING "no-mac-updating"
enum {
/* long options mapped to a short option */
/* first long only option value must be >= 256, so that we won't
* conflict with short options */
CMD_LINE_OPT_MIN_NUM = 256,
};
static const struct option lgopts[] = {
{ CMD_LINE_OPT_MAC_UPDATING, no_argument, &mac_updating, 1},
{ CMD_LINE_OPT_NO_MAC_UPDATING, no_argument, &mac_updating, 0},
{NULL, 0, 0, 0}
};
/* Parse the argument given in the command line of the application */
static int
l2fwd_parse_args(int argc, char **argv)
{
int opt, ret, timer_secs;
char **argvopt;
int option_index;
char *prgname = argv[0]; // l2fwd
argvopt = argv;
while ((opt = getopt_long(argc, argvopt, short_options,
lgopts, &option_index)) != EOF) { // linux 下解析命令行參數的函數。支持由兩個橫槓開頭的長選項。
// 關於這個函數能夠 man getopt_long
switch (opt) { // 解析成功時返回字符
/* portmask */
case 'p': // 端口掩碼
l2fwd_enabled_port_mask = l2fwd_parse_portmask(optarg); // 解析成功時，將字符後面的參數放到 optarg 裏
if (l2fwd_enabled_port_mask == 0) {
printf("invalid portmask\n");
l2fwd_usage(prgname);
return -1;
}
break;
/* nqueue */
case 'q': // A number of queues (=ports) per lcore (default is 1)
// q 後面跟着的數字是每一個邏輯核心上要綁定多少個隊列（端口）
// 例如 -q 4 意味着該應用使用一個 lcore 輪詢 4個端口。若是共有16個端口，則只須要4個lcore
l2fwd_rx_queue_per_lcore = l2fwd_parse_nqueue(optarg);
if (l2fwd_rx_queue_per_lcore == 0) {
printf("invalid queue number\n");
l2fwd_usage(prgname);
return -1;
}
break;
/* timer period */
case 'T':
timer_secs = l2fwd_parse_timer_period(optarg);
if (timer_secs < 0) {
printf("invalid timer period\n");
l2fwd_usage(prgname);
return -1;
}
timer_period = timer_secs;
break;
/* long options */
case 0: // 解析到了長選項 會返回0，長選項形如 --arg=param or --arg param.
break;
default:
l2fwd_usage(prgname);
return -1;
}
}
if (optind >= 0) // optind 是 argv 中下一個要被處理的參數的 index
argv[optind-1] = prgname;
ret = optind-1;
optind = 1; /* reset getopt lib */ // 解析完全部的參數要讓 optind 從新指向 1
return ret;
}
/* Check the link status of all ports in up to 9s, and print them finally */
static void
check_all_ports_link_status(uint32_t port_mask)
{
#define CHECK_INTERVAL 100 /* 100ms */
#define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */
uint16_t portid;
uint8_t count, all_ports_up, print_flag = 0;
struct rte_eth_link link;
printf("\nChecking link status");
fflush(stdout);
for (count = 0; count <= MAX_CHECK_TIME; count++) {
if (force_quit)
return;
all_ports_up = 1;
RTE_ETH_FOREACH_DEV(portid) {
if (force_quit)
return;
if ((port_mask & (1 << portid)) == 0)
continue;
memset(&link, 0, sizeof(link));
rte_eth_link_get_nowait(portid, &link);
/* print link status if flag set */
if (print_flag == 1) {
if (link.link_status)
printf(
"Port%d Link Up. Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
("full-duplex") : ("half-duplex\n"));
else
printf("Port %d Link Down\n", portid);
continue;
}
/* clear all_ports_up flag if any link down */
if (link.link_status == ETH_LINK_DOWN) {
all_ports_up = 0;
break;
}
}
/* after finally printing all link status, get out */
if (print_flag == 1)
break;
if (all_ports_up == 0) {
printf(".");
fflush(stdout);
rte_delay_ms(CHECK_INTERVAL);
}
/* set the print_flag if all ports up or timeout */
if (all_ports_up == 1 || count == (MAX_CHECK_TIME - 1)) {
print_flag = 1;
printf("done\n");
}
}
}
static void
signal_handler(int signum)
{
if (signum == SIGINT || signum == SIGTERM) {
printf("\n\nSignal %d received, preparing to exit...\n",
signum);
force_quit = true; //當咱們退出是ctrl+c不是直接將進程殺死，而是會將force_quit置爲true，讓程序天然退出，這樣程序就來得及完成最後退出以前的操做。
}
}
int
main(int argc, char **argv)
{
struct lcore_queue_conf *qconf;
int ret;
uint16_t nb_ports;
uint16_t nb_ports_available = 0;
uint16_t portid, last_port;
unsigned lcore_id, rx_lcore_id;
unsigned nb_ports_in_mask = 0;
unsigned int nb_lcores = 0;
unsigned int nb_mbufs;
/* init EAL */
// 解析 EAL 的參數
ret = rte_eal_init(argc, argv);
if (ret < 0)
rte_exit(EXIT_FAILURE, "Invalid EAL arguments\n");
argc -= ret;
argv += ret;
force_quit = false;
signal(SIGINT, signal_handler);
signal(SIGTERM, signal_handler);
/* parse application arguments (after the EAL ones) */
// 解析 l2fwd 的運行參數
ret = l2fwd_parse_args(argc, argv);
if (ret < 0)
rte_exit(EXIT_FAILURE, "Invalid L2FWD arguments\n");
printf("MAC updating %s\n", mac_updating ? "enabled" : "disabled"); // 默認開啓 mac updating 這一功能。
/* convert to number of cycles */
timer_period *= rte_get_timer_hz(); // 得到CPU主頻，單位hz (1s多少個cycle)，位於rte_cycles.h
nb_ports = rte_eth_dev_count(); // 網口數量
if (nb_ports == 0)
rte_exit(EXIT_FAILURE, "No Ethernet ports - bye\n");
/* check port mask to possible port mask */
// 檢查掩碼和可用網口數量是否有衝突
if (l2fwd_enabled_port_mask & ~((1 << nb_ports) - 1))
rte_exit(EXIT_FAILURE, "Invalid portmask; possible (0x%x)\n",
(1 << nb_ports) - 1);
/* reset l2fwd_dst_ports */
for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++)
l2fwd_dst_ports[portid] = 0; // 先重置這個數組
last_port = 0;
/*
* Each logical core is assigned a dedicated TX queue on each port.
*/
RTE_ETH_FOREACH_DEV(portid) { // 使用RTE_ETH_FOREACH_DEV()宏來訪問全部的 ethdev
/* skip ports that are not enabled */
if ((l2fwd_enabled_port_mask & (1 << portid)) == 0)
continue;
if (nb_ports_in_mask % 2) {
l2fwd_dst_ports[portid] = last_port;
l2fwd_dst_ports[last_port] = portid;
}
else
last_port = portid;
nb_ports_in_mask++; // 這些邏輯能夠實現 basicfwd 那樣的一對對端口互相轉發。
}
if (nb_ports_in_mask % 2) {
printf("Notice: odd number of ports in portmask.\n");
l2fwd_dst_ports[last_port] = last_port; // 若是是奇數個端口，會有最後一個端口的 dst_port 是本身
}
rx_lcore_id = 0; // 從邏輯核心id 0開始
qconf = NULL;
/* Initialize the port/queue configuration of each logical core */
// 在每個端口上，配置邏輯核、配置隊列。
RTE_ETH_FOREACH_DEV(portid) {
/* skip ports that are not enabled */
if ((l2fwd_enabled_port_mask & (1 << portid)) == 0)
continue;
/* get the lcore_id for this port */
// 爲該端口配置一個邏輯核。
while (rte_lcore_is_enabled(rx_lcore_id) == 0 ||
lcore_queue_conf[rx_lcore_id].n_rx_port ==
l2fwd_rx_queue_per_lcore) {
/*從lcore id = 0 開始循環：
若是：若是該 lcore id 有效（已經被佔用），則檢查下一個邏輯核。
若是該 lcore 是空閒的，要檢查該 lcore 上綁定了多少個端口，若是到達了最大端口數量限制也會循環。*/
rx_lcore_id++;
if (rx_lcore_id >= RTE_MAX_LCORE) // RTE_MAX_LCORE 宏 64
rte_exit(EXIT_FAILURE, "Not enough cores\n"); // 邏輯核心不足
}
// 跳出循環時，rx_lcore_id 變量存儲了一個可用的 lcore id，綁定該端口到這個 lcore
if (qconf != &lcore_queue_conf[rx_lcore_id]) {
/* Assigned a new logical core in the loop above. */
qconf = &lcore_queue_conf[rx_lcore_id];
nb_lcores++;
// qconf 是一個指針，指向當前進行配置的 lcore 的，用於存放配置信息的結構體
}
qconf->rx_port_list[qconf->n_rx_port] = portid;
qconf->n_rx_port++;
// 綁定就是在這個核處理的端口列表中加上當前這個端口，而後該核綁定的端口數加 1。
printf("Lcore %u: RX port %u\n", rx_lcore_id, portid);
}
nb_mbufs = RTE_MAX(nb_ports * (nb_rxd + nb_txd + MAX_PKT_BURST +
nb_lcores * MEMPOOL_CACHE_SIZE), 8192U);
// mbuf中的元素個數，取 8192 和 （端口數 * （隊列長度 * 2 + 一個 Burst 的 pkt 數量 + 邏輯核數 * cache size）） 二者中較大的一個。
/* create the mbuf pool */
// 初始化內存池，用於 rx 隊列接收 pkt 用
l2fwd_pktmbuf_pool = rte_pktmbuf_pool_create("mbuf_pool", nb_mbufs,
MEMPOOL_CACHE_SIZE, 0, RTE_MBUF_DEFAULT_BUF_SIZE,
rte_socket_id());
if (l2fwd_pktmbuf_pool == NULL)
rte_exit(EXIT_FAILURE, "Cannot init mbuf pool\n");
/* Initialise each port */
// 端口初始化
RTE_ETH_FOREACH_DEV(portid) {
struct rte_eth_rxconf rxq_conf; // rx queue 的配置信息
struct rte_eth_txconf txq_conf; // tx queue 的配置信息
struct rte_eth_conf local_port_conf = port_conf; // 配置端口時使用的配置信息
struct rte_eth_dev_info dev_info; // 以太網設備的信息
/* skip ports that are not enabled */
if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) {
printf("Skipping disabled port %u\n", portid);
continue;
}
nb_ports_available++;
/* init port */
printf("Initializing port %u... ", portid);
fflush(stdout); // 清除寫緩衝區，強迫未寫入磁盤的內容當即寫入
rte_eth_dev_info_get(portid, &dev_info); // 獲取以太網設備信息
if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
local_port_conf.txmode.offloads |=
DEV_TX_OFFLOAD_MBUF_FAST_FREE; // mbuf fast free，支持快速發包
ret = rte_eth_dev_configure(portid, 1, 1, &local_port_conf); // 配置收發隊列各 1 條
/*本程序中，Rx隊列只能有一條，確保一個 lcore 負責輪詢一個 port
Tx 隊列則能夠根據可用的 lcore 數目更改。*/
if (ret < 0)
rte_exit(EXIT_FAILURE, "Cannot configure device: err=%d, port=%u\n",
ret, 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=%u\n",
ret, portid);
rte_eth_macaddr_get(portid,&l2fwd_ports_eth_addr[portid]); // 獲取設備的MAC地址，寫在後一個結構體裏
/* init one RX queue */
// 配置 rx 隊列
fflush(stdout);
rxq_conf = dev_info.default_rxconf;
rxq_conf.offloads = local_port_conf.rxmode.offloads;
ret = rte_eth_rx_queue_setup(portid, 0, nb_rxd,
rte_eth_dev_socket_id(portid),
&rxq_conf,
l2fwd_pktmbuf_pool);
if (ret < 0)
rte_exit(EXIT_FAILURE, "rte_eth_rx_queue_setup:err=%d, port=%u\n",
ret, portid);
/* init one TX queue on each port */
// 每一個 port 配置一條 tx 隊列
fflush(stdout);
txq_conf = dev_info.default_txconf;
txq_conf.txq_flags = ETH_TXQ_FLAGS_IGNORE;
txq_conf.offloads = local_port_conf.txmode.offloads;
ret = rte_eth_tx_queue_setup(portid, 0, nb_txd,
rte_eth_dev_socket_id(portid),
&txq_conf);
if (ret < 0)
rte_exit(EXIT_FAILURE, "rte_eth_tx_queue_setup:err=%d, port=%u\n",
ret, portid);
/* Initialize TX buffers */
// 爲每一個端口的 Tx 分配發送緩衝區
tx_buffer[portid] = rte_zmalloc_socket("tx_buffer",
RTE_ETH_TX_BUFFER_SIZE(MAX_PKT_BURST), 0,
rte_eth_dev_socket_id(portid)); // 爲 tx buffer 分配空間。
// 宏RTE_ETH_TX_BUFFER_SIZE(x) ：計算 tx buffer 的 size，參數x是包的個數
if (tx_buffer[portid] == NULL)
rte_exit(EXIT_FAILURE, "Cannot allocate buffer for tx on port %u\n",
portid);
rte_eth_tx_buffer_init(tx_buffer[portid], MAX_PKT_BURST); // 初始化 Tx buffer，參數是 buffer 指針和 buffer size。
/* rte_eth_tx_buffer_set_err_callback() 對於不能被髮送的 pkt 配置回調函數。
在嘗試發送一個 tx buffer 的全部 pkt，遇到問題不能所有成功發送，就會觸發設置好的回調函數。
默認行爲是丟包。若是要其餘的行爲（例如重傳，計數）則須要額外的代碼。也有設置好的API例如rte_eth_count_unsent_packet_callback()等，和本函數中用的也是。
參數 1. tx_buffer 指針，2.回調函數的指針。3. 回調函數的參數
*/
ret = rte_eth_tx_buffer_set_err_callback(tx_buffer[portid],
rte_eth_tx_buffer_count_callback, // 丟包，並更新計數器
&port_statistics[portid].dropped); // 計數器的指針放到第三個參數
if (ret < 0)
rte_exit(EXIT_FAILURE,
"Cannot set error callback for tx buffer on port %u\n",
portid);
/* Start device */
// 啓用設備
ret = rte_eth_dev_start(portid);
if (ret < 0)
rte_exit(EXIT_FAILURE, "rte_eth_dev_start:err=%d, port=%u\n",
ret, portid);
printf("done: \n");
rte_eth_promiscuous_enable(portid); // 混雜模式
printf("Port %u, MAC address: %02X:%02X:%02X:%02X:%02X:%02X\n\n",
portid,
l2fwd_ports_eth_addr[portid].addr_bytes[0],
l2fwd_ports_eth_addr[portid].addr_bytes[1],
l2fwd_ports_eth_addr[portid].addr_bytes[2],
l2fwd_ports_eth_addr[portid].addr_bytes[3],
l2fwd_ports_eth_addr[portid].addr_bytes[4],
l2fwd_ports_eth_addr[portid].addr_bytes[5]);
/* initialize port stats */
memset(&port_statistics, 0, sizeof(port_statistics));
}
if (!nb_ports_available) {
rte_exit(EXIT_FAILURE,
"All available ports are disabled. Please set portmask.\n");
}
check_all_ports_link_status(l2fwd_enabled_port_mask); // 檢查全部鏈路的狀態，能夠參考 flow_filtering
ret = 0;
/* launch per-lcore init on every lcore */
// 這裏就是DPDK的典型執行方法，分配全部 lcore 執行函數
rte_eal_mp_remote_launch(l2fwd_launch_one_lcore, NULL, CALL_MASTER);
RTE_LCORE_FOREACH_SLAVE(lcore_id) {
if (rte_eal_wait_lcore(lcore_id) < 0) {
ret = -1;
break;
}
}
RTE_ETH_FOREACH_DEV(portid) {
if ((l2fwd_enabled_port_mask & (1 << portid)) == 0)
continue;
printf("Closing port %d...", portid);
rte_eth_dev_stop(portid);
rte_eth_dev_close(portid);
printf(" Done\n");
}
printf("Bye...\n");
return ret;
}
二層轉發和普通的端口轉發有什麼區別呢？簡單來講有幾個：linux
| 特色 | L2fwd | basicfwd |
|---|---|---|
| 端口數量 | 二者都用端口掩碼來指定，L2fwd支持奇數個 | 只能是偶數個 |
| lcore數量 | 多個，每一個lcore負責一個port | 一個lcore，執行相似repeater的程序 |
| 轉發邏輯 | 轉發時會改寫MAC地址 | 只能是 0<-->1，2<-->3 這樣的 pair 互相轉發 |
| Tx_buffer | 有發包緩存隊列，收的包會緩存到發包隊列裏，一段時間後或者隊列滿後纔會轉發 | 沒有發包緩存，Rx收到包後直接Tx出去 |
運行狀況
root@ubuntu:/home/chang/dpdk/examples/l2fwd/build# ./l2fwd -l 0-3 -n 4 -- -p 0x3EAL: Detected 8 lcore(s) EAL: No free hugepages reported in hugepages-1048576kB EAL: Multi-process socket /var/run/.rte_unix EAL: Probing VFIO support... EAL: PCI device 0000:02:01.0 on NUMA socket -1 EAL: Invalid NUMA socket, default to 0 EAL: probe driver: 8086:100f net_e1000_em EAL: PCI device 0000:02:02.0 on NUMA socket -1 EAL: Invalid NUMA socket, default to 0 EAL: probe driver: 8086:100f net_e1000_em EAL: PCI device 0000:02:03.0 on NUMA socket -1 EAL: Invalid NUMA socket, default to 0 EAL: probe driver: 8086:100f net_e1000_em EAL: PCI device 0000:02:04.0 on NUMA socket -1 EAL: Invalid NUMA socket, default to 0 EAL: probe driver: 8086:100f net_e1000_em MAC updating enabled Lcore 0: RX port 0 Lcore 1: RX port 1 Initializing port 0... done: Port 0, MAC address: 00:0C:29:F7:4D:25 Initializing port 1... done: Port 1, MAC address: 00:0C:29:F7:4D:2F Checking link statusdone Port0 Link Up. Speed 1000 Mbps - full-duplex Port1 Link Up. Speed 1000 Mbps - full-duplex L2FWD: entering main loop on lcore 1 L2FWD: -- lcoreid=1 portid=1 L2FWD: lcore 3 has nothing to do L2FWD: entering main loop on lcore 0 L2FWD: -- lcoreid=0 portid=0 Port statistics ==================================== Statistics for port 0 ------------------------------ Packets sent: 2152346 Packets received: 2166674 Packets dropped: 0 Statistics for port 1 ------------------------------ Packets sent: 2166674 Packets received: 2152371 Packets dropped: 0 Aggregate statistics =============================== Total packets sent: 4319020 Total packets received: 4319045 Total packets dropped: 0 ====================================================
用 wireshark 抓下包：ubuntu
能夠看到通過端口轉發的包的目的MAC地址被程序改變了。數組
可是改變了目的MAC地址，天然沒法通訊。因此這個程序仍是設置成測試速率用。若是把修改目的MAC地址的那一行代碼註釋掉，就能夠正常通訊。緩存
Sample guide 裏有一句話說：The L2 Forwarding application can also be used as a starting point for developing a new application based on the DPDK. 因此這個程序也是很是親民的=。=app
reference
做爲典型應用，搜索能搜到不少相關代碼閱讀的博客。dom
參考了：https://blog.csdn.net/yangye2014/article/details/78064634?locationNum=6&fps=1socket
相關文章
- 1. dpdk l2fwd
- 2. dpdk l2fwd (2)
- 3. 【源碼閱讀】AndPermission源碼閱讀
- 4. 【源碼閱讀】Gson源碼閱讀
- 5. 源碼閱讀
- 6. DPDK
- 7. 關於源碼閱讀：源碼資源、閱讀工具、閱讀思路
- 8. NGINX源碼閱讀
- 9. Muduo源碼閱讀
- 10. OwinBuilder源碼閱讀
- 更多相關文章...
- • RSS 閱讀器 - RSS 教程
- • PHP 實例 - AJAX RSS 閱讀器 - PHP教程
- • Java Agent入門實戰（二）-Instrumentation源碼概述
- • JDK13 GA發佈：5大特性解讀
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
- 1. No provider available from registry 127.0.0.1:2181 for service com.ddbuy.ser 解決方法
- 2. Qt5.7以上調用虛擬鍵盤(支持中文)，以及源碼修改(可拖動，水平縮放)
- 3. 軟件測試面試- 購物車功能測試用例設計
- 4. ElasticSearch（概念篇）：你知道的, 爲了搜索…
- 5. redux理解
- 6. gitee創建第一個項目
- 7. 支持向量機之硬間隔（一步步推導，通俗易懂）
- 8. Mysql 異步複製延遲的原因及解決方案
- 9. 如何在運行SEPM配置嚮導時將不可認的複雜數據庫密碼改爲簡單密碼
- 10. windows系統下tftp服務器使用
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. dpdk l2fwd
- 2. dpdk l2fwd (2)
- 3. 【源碼閱讀】AndPermission源碼閱讀
- 4. 【源碼閱讀】Gson源碼閱讀
- 5. 源碼閱讀
- 6. DPDK
- 7. 關於源碼閱讀：源碼資源、閱讀工具、閱讀思路
- 8. NGINX源碼閱讀
- 9. Muduo源碼閱讀
- 10. OwinBuilder源碼閱讀