DPDK系列之四十一数据收发整体流程源码分析之一整体流程

最新推荐文章于 2024-03-11 09:46:03 发布

fpcc

最新推荐文章于 2024-03-11 09:46:03 发布

阅读量497

点赞数 5

分类专栏：网络开发文章标签： DPDK

本文链接：https://blog.csdn.net/fpcc/article/details/135887041

版权

网络开发专栏收录该内容

49 篇文章 19 订阅

订阅专栏

一、说明

在前面的分析中基本介绍了DPDK中的各种模块的技术架构，从这篇开始，就从头开始对整个代码的流程进行分析，然后在此基础上，初步掌握了DPDK的代码架构和功能分析后，再对基于DPDK的上层应用进行分析。
这是一个从分到合，从基础到应用的过程。在这个过程中需要不断的回顾和补充原来的知识。

二、数据包流程

在前面详细分析过数据包的转运流程，其实做一种IO接口，一定是分成两部分，即数据的接收和发送。从宏观上看，无论数据的接收和发送，都需要网卡到队列（Ring）然后到应用层的这么一个过程。DPDK的特点是尽量不打扰内核，并通过DMA（RDMA）的方式将数据利用队列将应用层与网卡进行交互。
而在这个交互的过程中，又有几种方式，如轮询、中断和混合三种方式。明白了这些，再加上前面的相关文章的分析，那么整体的流程和细节的程序大致已经把握了，那么最重要的就是看DPDK的源码是如何实现这些的。

三、源码分析

闲言少叙，直接进入正题(examples\skeleton\basicfwd.c)：
先看入口函数：

/*
 * The main function, which does initialization and calls the per-lcore
 * functions.
 */
int
main(int argc, char *argv[])
{
	struct rte_mempool *mbuf_pool;
	unsigned nb_ports;
	uint16_t portid;

	/* 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;

	/* Check that there is an even number of ports to send/receive on. */
	nb_ports = rte_eth_dev_count_avail();
	if (nb_ports < 2 || (nb_ports & 1))
		rte_exit(EXIT_FAILURE, "Error: number of ports must be even\n");

	/* Creates a new mempool in memory to hold the mbufs. */
	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");

	/* Initialize all ports. */
	RTE_ETH_FOREACH_DEV(portid)
		if (port_init(portid, mbuf_pool) != 0)
			rte_exit(EXIT_FAILURE, "Cannot init port %"PRIu16 "\n",
					portid);

	if (rte_lcore_count() > 1)
		printf("\nWARNING: Too many lcores enabled. Only 1 used.\n");

	/* Call lcore_main on the master core only. */
	lcore_main();

	/* clean up the EAL */
	rte_eal_cleanup();

	return 0;
}

从代码上看，首先是主函数中需要调用rte_eal_init对所有的相关参数和设置进行初始化：

/* Launch threads, called at application init(). */
int rte_eal_init(int argc, char **argv)
{
......

	/* checks if the machine is adequate */
	if (!rte_cpu_is_supported()) {
		rte_eal_init_alert("unsupported cpu type.");
		rte_errno = ENOTSUP;
		return -1;
	}

	if (!rte_atomic32_test_and_set(&run_once)) {
		rte_eal_init_alert("already called initialization.");
		rte_errno = EALREADY;
		return -1;
	}

......

	/* Call each registered callback, if enabled */
	rte_option_init();

	return fctret;
}

这个函数已经分析过多次了，但是其中其实还有很多的细节没有分析到位，这个只有真正的用到哪块才会认真的去看每一行代码。这个代码其实就是大量的参数、配置、大页内存等待的初始化。反正代码里大量的init估计即使不明白初始化啥也知道是初始化的功能。
其下就是检查偶数个端的函数：

uint16_t
rte_eth_dev_count_avail(void)
{
	uint16_t p;
	uint16_t count;

	count = 0;

	RTE_ETH_FOREACH_DEV(p)
		count++;

	return count;
}

然后开始创建内存池：

/* helper to create a mbuf pool */
struct rte_mempool *
rte_pktmbuf_pool_create(const char *name, unsigned int n,
	unsigned int cache_size, uint16_t priv_size, uint16_t data_room_size,
	int socket_id)
{
	return rte_pktmbuf_pool_create_by_ops(name, n, cache_size, priv_size,
			data_room_size, socket_id, NULL);
}

然后调用端口初始化函数：

/* basicfwd.c: Basic DPDK skeleton forwarding example. */

/*
 * Initializes a given port using global settings and with the RX buffers
 * coming from the mbuf_pool passed as a parameter.
 */
static inline int
port_init(uint16_t port, struct rte_mempool *mbuf_pool)
{
	struct rte_eth_conf port_conf = port_conf_default;
	const uint16_t rx_rings = 1, tx_rings = 1;
......

	/* Enable RX in promiscuous mode for the Ethernet device. */
	retval = rte_eth_promiscuous_enable(port);
	if (retval != 0)
		return retval;

	return 0;
}

然后通过rte_lcore_count() 来判断逻辑核心的数量，如果多于1个，在本程序其实没啥意义。
最后调用函数：

static __attribute__((noreturn)) void
lcore_main(void)
{
	uint16_t port;

	/*
	 * Check that the port is on the same NUMA node as the polling thread
	 * for best performance.
	 */
	RTE_ETH_FOREACH_DEV(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());

	/* Run until the application is quit or killed. */
	for (;;) {
		/*
		 * Receive packets on a port and forward them on the paired
		 * port. The mapping is 0 -> 1, 1 -> 0, 2 -> 3, 3 -> 2, etc.
		 */
		RTE_ETH_FOREACH_DEV(port) {

			/* Get burst of RX packets, from first port of pair. */
			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);

			/* Free any unsent packets. */
			if (unlikely(nb_tx < nb_rx)) {
				uint16_t buf;
				for (buf = nb_tx; buf < nb_rx; buf++)
					rte_pktmbuf_free(bufs[buf]);
			}
		}
	}
}

真正的处理数据收发，如果退出，则需要调用rte_eal_cleanup()来清理现场，并返回。

int
rte_eal_cleanup(void)
{
	/* if we're in a primary process, we need to mark hugepages as freeable
	 * so that finalization can release them back to the system.
	 */
	if (rte_eal_process_type() == RTE_PROC_PRIMARY)
		rte_memseg_walk(mark_freeable, NULL);

	rte_service_finalize();
#ifdef VFIO_PRESENT
	vfio_mp_sync_cleanup();
#endif
	rte_mp_channel_cleanup();
	eal_cleanup_config(&internal_config);
	return 0;
}