0x01 緣由
繼續學習DPDK示例，主要熟悉每個環節和設計理念，今天要學習的是一個相對簡答的服務，僅僅從一個網口抓取數據包轉發到另外一個網口，這樣做雙向轉發，相當於橋的功能。其他基礎業務都不做。
0x02 直接上源碼分析
#include <stdint.h>
#include <inttypes.h>
#include <rte_eal.h>
#include <rte_ethdev.h>
#include <rte_cycles.h>
#include <rte_lcore.h>
#include <rte_mbuf.h>
#define RX_RING_SIZE 128
#define TX_RING_SIZE 512
#define NUM_MBUFS 8191
#define MBUF_CACHE_SIZE 250
#define BURST_SIZE 32
static const struct rte_eth_conf port_conf_default = {
.rxmode = { .max_rx_pkt_len = ETHER_MAX_LEN }
};
/* basicfwd.c: Basic DPDK skeleton forwarding example. */
/*
* 用全局默認的配置來初始化網口。在內存池中分配接收隊列和發送隊列。
*/
static inline int
port_init(uint8_t port, struct rte_mempool *mbuf_pool)
{
struct rte_eth_conf port_conf = port_conf_default; //全部配置模式
const uint16_t rx_rings = 1, tx_rings = 1; //每個網口隊列多少，這裏都爲1
int retval;
uint16_t q;
if (port >= rte_eth_dev_count()) //檢查網口編號
return -1;
/* 配置以太網設備 */
retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf);
if (retval != 0)
return retval;
/* 爲每個以太網網口分配和設置1個接收隊列 */
for (q = 0; q < rx_rings; q++) {
retval = rte_eth_rx_queue_setup(port, q, RX_RING_SIZE,
rte_eth_dev_socket_id(port), NULL, mbuf_pool);
if (retval < 0)
return retval;
}
/* 爲每個以太網網口分配和設置1個發送隊列 */
for (q = 0; q < tx_rings; q++) {
retval = rte_eth_tx_queue_setup(port, q, TX_RING_SIZE,
rte_eth_dev_socket_id(port), NULL);
if (retval < 0)
return retval;
}
/* 開啓以太網網口 */
retval = rte_eth_dev_start(port);
if (retval < 0)
return retval;
/* 打印網卡地址 MAC address. */
struct ether_addr addr;
rte_eth_macaddr_get(port, &addr);
printf("Port %u MAC: %02" PRIx8 " %02" PRIx8 " %02" PRIx8
" %02" PRIx8 " %02" PRIx8 " %02" PRIx8 "\n",
(unsigned)port,
addr.addr_bytes[0], addr.addr_bytes[1],
addr.addr_bytes[2], addr.addr_bytes[3],
addr.addr_bytes[4], addr.addr_bytes[5]);
/* 網口開啓混雜模式 */
rte_eth_promiscuous_enable(port);
return 0;
}
/*
* 一個線程處理一對網口，數據包一進一出。
*/
static __attribute__((noreturn)) void
lcore_main(void)
{
const uint8_t nb_ports = rte_eth_dev_count(); //網口數
uint8_t port;
/*
* 當有NUMA結構時，檢查網口是否在同一個NUMA node節點上，只有在一個NUMA node上時輪詢線程效率最好。
*/
for (port = 0; port < nb_ports; port++)
if (rte_eth_dev_socket_id(port) > 0 &&
rte_eth_dev_socket_id(port) !=
(int)rte_socket_id())
printf("WARNING, port %u is on remote NUMA node to "
"polling thread.\n\tPerformance will "
"not be optimal.\n", port);
printf("\nCore %u forwarding packets. [Ctrl+C to quit]\n",
rte_lcore_id());
/* 死循環處理數據包的搬運 */
for (;;) {
/*
* 一個端口接收包，然後直接轉發到這對數據包上。
* 如 0 -> 1, 1 -> 0, 2 -> 3, 3 -> 2 等。
*/
for (port = 0; port < nb_ports; port++) {
/* 從一個端口接收數據包 */
struct rte_mbuf *bufs[BURST_SIZE];
const uint16_t nb_rx = rte_eth_rx_burst(port, 0,
bufs, BURST_SIZE);
if (unlikely(nb_rx == 0))
continue;
/* Send burst of TX packets, to second port of pair. */
const uint16_t nb_tx = rte_eth_tx_burst(port ^ 1, 0,
bufs, nb_rx);
/* 釋放沒有發送的數據包。 */
if (unlikely(nb_tx < nb_rx)) {
uint16_t buf;
for (buf = nb_tx; buf < nb_rx; buf++)
rte_pktmbuf_free(bufs[buf]);
}
}
}
}
/*
* The main function, which does initialization and calls the per-lcore
* functions.
*/
int
main(int argc, char *argv[])
{
struct rte_mempool *mbuf_pool; //使用內存池空間來容納ring隊列，接收和發送數據包
unsigned nb_ports; //網卡數
uint8_t portid; //網卡編號
/* Initialize the Environment Abstraction Layer (EAL). */
int ret = rte_eal_init(argc, argv);
if (ret < 0)
rte_exit(EXIT_FAILURE, "Error with EAL initialization\n");
argc -= ret;
argv += ret;
/* 檢查網卡是否爲偶數 send/receive */
nb_ports = rte_eth_dev_count();
if (nb_ports < 2 || (nb_ports & 1))
rte_exit(EXIT_FAILURE, "Error: number of ports must be even\n");
/* 創建一個內存池來容納mbufs。大小按網口多少來分配。相當於每個網口都要有一個接受和發送隊列。*/
mbuf_pool = rte_pktmbuf_pool_create("MBUF_POOL", NUM_MBUFS * nb_ports,
MBUF_CACHE_SIZE, 0, RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id());
if (mbuf_pool == NULL)
rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n");
/* 初始化所有網口配置 */
for (portid = 0; portid < nb_ports; portid++)
if (port_init(portid, mbuf_pool) != 0)
rte_exit(EXIT_FAILURE, "Cannot init port %"PRIu8 "\n",
portid);
if (rte_lcore_count() > 1)
printf("\nWARNING: Too many lcores enabled. Only 1 used.\n");
/* 僅僅用一個主線程調用，相當與一個線程處理一對網口的數據包。*/
lcore_main();
return 0;
}
0x03 運行實例
[root@Huawei x86_64-native-linuxapp-gcc]# ./basicfwd -l 1 -n 4
EAL: Detected lcore 0 as core 0 on socket 0
EAL: Detected lcore 1 as core 1 on socket 0
EAL: Detected lcore 2 as core 2 on socket 0
EAL: Detected lcore 3 as core 3 on socket 0
EAL: Detected lcore 4 as core 4 on socket 0
EAL: Detected lcore 5 as core 5 on socket 0
EAL: Detected lcore 6 as core 6 on socket 0
EAL: Detected lcore 7 as core 7 on socket 0
EAL: Detected lcore 8 as core 0 on socket 1
EAL: Detected lcore 9 as core 1 on socket 1
EAL: Detected lcore 10 as core 2 on socket 1
EAL: Detected lcore 11 as core 3 on socket 1
EAL: Detected lcore 12 as core 4 on socket 1
EAL: Detected lcore 13 as core 5 on socket 1
EAL: Detected lcore 14 as core 6 on socket 1
EAL: Detected lcore 15 as core 7 on socket 1
EAL: Detected lcore 16 as core 0 on socket 0
EAL: Detected lcore 17 as core 1 on socket 0
EAL: Detected lcore 18 as core 2 on socket 0
EAL: Detected lcore 19 as core 3 on socket 0
EAL: Detected lcore 20 as core 4 on socket 0
EAL: Detected lcore 21 as core 5 on socket 0
EAL: Detected lcore 22 as core 6 on socket 0
EAL: Detected lcore 23 as core 7 on socket 0
EAL: Detected lcore 24 as core 0 on socket 1
EAL: Detected lcore 25 as core 1 on socket 1
EAL: Detected lcore 26 as core 2 on socket 1
EAL: Detected lcore 27 as core 3 on socket 1
EAL: Detected lcore 28 as core 4 on socket 1
EAL: Detected lcore 29 as core 5 on socket 1
EAL: Detected lcore 30 as core 6 on socket 1
EAL: Detected lcore 31 as core 7 on socket 1
EAL: Support maximum 128 logical core(s) by configuration.
EAL: Detected 32 lcore(s)
EAL: Setting up physically contiguous memory...
EAL: Ask a virtual area of 0x200000 bytes
EAL: Virtual area found at 0x7f45f8000000 (size = 0x200000)
EAL: Ask a virtual area of 0x7c00000 bytes
EAL: Virtual area found at 0x7f45f0200000 (size = 0x7c00000)
EAL: Ask a virtual area of 0x200000 bytes
EAL: Virtual area found at 0x7f45efe00000 (size = 0x200000)
EAL: Ask a virtual area of 0x7c00000 bytes
EAL: Virtual area found at 0x7f45e8000000 (size = 0x7c00000)
EAL: Ask a virtual area of 0x400000 bytes
EAL: Virtual area found at 0x7f45e7a00000 (size = 0x400000)
EAL: Requesting 64 pages of size 2MB from socket 0
EAL: Requesting 64 pages of size 2MB from socket 1
EAL: TSC frequency is ~2593994 KHz
EAL: Master lcore 1 is ready (tid=f83f2880;cpuset=[1])
EAL: PCI device 0000:04:00.0 on NUMA socket 0
EAL: probe driver: 8086:1521 rte_igb_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:04:00.1 on NUMA socket 0
EAL: probe driver: 8086:1521 rte_igb_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:04:00.2 on NUMA socket 0
EAL: probe driver: 8086:1521 rte_igb_pmd
EAL: PCI memory mapped at 0x7f45f7f00000
EAL: PCI memory mapped at 0x7f45f7efc000
PMD: eth_igb_dev_init(): port_id 0 vendorID=0x8086 deviceID=0x1521
EAL: PCI device 0000:04:00.3 on NUMA socket 0
EAL: probe driver: 8086:1521 rte_igb_pmd
EAL: PCI memory mapped at 0x7f45f0100000
EAL: PCI memory mapped at 0x7f45f8408000
PMD: eth_igb_dev_init(): port_id 1 vendorID=0x8086 deviceID=0x1521
EAL: PCI device 0000:05:00.0 on NUMA socket 0
EAL: probe driver: 8086:1522 rte_igb_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:05:00.1 on NUMA socket 0
EAL: probe driver: 8086:1522 rte_igb_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:05:00.2 on NUMA socket 0
EAL: probe driver: 8086:1522 rte_igb_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:05:00.3 on NUMA socket 0
EAL: probe driver: 8086:1522 rte_igb_pmd
EAL: Not managed by a supported kernel driver, skipped
PMD: eth_igb_rx_queue_setup(): sw_ring=0x7f45eff90fc0 hw_ring=0x7f45eff91400 dma_addr=0x67391400
PMD: eth_igb_tx_queue_setup(): sw_ring=0x7f45eff7ee40 hw_ring=0x7f45eff80e80 dma_addr=0x67380e80
PMD: eth_igb_start(): <<
Port 0 MAC: a0 36 9f 03 a8 ca
PMD: eth_igb_rx_queue_setup(): sw_ring=0x7f45eff6e7c0 hw_ring=0x7f45eff6ec00 dma_addr=0x6736ec00
PMD: eth_igb_tx_queue_setup(): sw_ring=0x7f45eff5c640 hw_ring=0x7f45eff5e680 dma_addr=0x6735e680
PMD: eth_igb_start(): <<
Port 1 MAC: a0 36 9f 03 a8 cb
Core 1 forwarding packets. [Ctrl+C to quit]
注：這篇文章轉載，我在筆記本電腦上用虛擬機會導致卡死，並報錯:例如kernel:NMI watchdog: BUG: soft lockup - CPU#0 stuck for 30s，根據查找結果是筆記本電腦的性能之類的問題。
0x04 總結
思路比較簡單，一個網口用兩個緩存來緩存數據包，然後將數據包轉發出去。此處用到了內存池結構。