DPDK的内存池

rte_pktmbuf_pool_create

/**
@param name：          内存池名
@param n：             mbuf数量
@param cache_size：    每个core缓存的大小
@param priv_size：     私有数据大小
@param data_room_size：mbuf大小RTE_MBUF_DEFAULT_DATAROOM + RTE_PKTMBUF_HEADROOM
@param socket_id：     指定SOCKET_ID号， NUMA场景下是NUMA id，否则可设置为SOCKET_ID_ANY;
*/
rte_struct rte_mempool* rte_pktmbuf_pool_create	(const char * 	name,
								unsigned 	n,
								unsigned 	cache_size,
								uint16_t 	priv_size,
								uint16_t 	data_room_size,
								int 	socket_id 
)	

ret_mbuf

单segment 的 ret_mbuf结构

多segment 的 ret_mbuf结构

rte_mempool 创建

rte_pktmbuf_pool_create函数源码

/* 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);
}

rte_pktmbuf_pool_create_by_ops函数：

1：创建并初始化mempool
2：申请obj,并填充到mempool

struct rte_mempool *
rte_pktmbuf_pool_create_by_ops(const char *name, unsigned int n,
	unsigned int cache_size, uint16_t priv_size, uint16_t data_room_size,
	int socket_id, const char *ops_name)
{
	struct rte_mempool *mp;
	struct rte_pktmbuf_pool_private mbp_priv;
	const char *mp_ops_name = ops_name;
	unsigned elt_size;
	int ret;

	if (RTE_ALIGN(priv_size, RTE_MBUF_PRIV_ALIGN) != priv_size) {
		RTE_LOG(ERR, MBUF, "mbuf priv_size=%u is not aligned\n",
			priv_size);
		rte_errno = EINVAL;
		return NULL;
	}
	/**
	* 指定在mempool中的每个元素的大小，即为上面提到的缓冲区大小加上private data的大小
	* 再加上struct rte_mbuf结构的大小
	*/
	elt_size = sizeof(struct rte_mbuf) + (unsigned)priv_size +
		(unsigned)data_room_size;
	memset(&mbp_priv, 0, sizeof(mbp_priv));
	mbp_priv.mbuf_data_room_size = data_room_size;
	mbp_priv.mbuf_priv_size = priv_size;
	//rte_mempool_create_empty()创建内存池
	mp = rte_mempool_create_empty(name, n, elt_size, cache_size,
		 sizeof(struct rte_pktmbuf_pool_private), socket_id, 0);
	if (mp == NULL)
		return NULL;

	if (mp_ops_name == NULL)
		mp_ops_name = rte_mbuf_best_mempool_ops();
	ret = rte_mempool_set_ops_byname(mp, mp_ops_name, NULL);
	if (ret != 0) {
		RTE_LOG(ERR, MBUF, "error setting mempool handler\n");
		rte_mempool_free(mp);
		rte_errno = -ret;
		return NULL;
	}
	rte_pktmbuf_pool_init(mp, &mbp_priv);
	// 申请obj，填充到mp里面,在rte_mempool_populate_default函数内会申请obj内存，并将所有的obj存入mp中
	ret = rte_mempool_populate_default(mp);
	if (ret < 0) {
		rte_mempool_free(mp);
		rte_errno = -ret;
		return NULL;
	}

	rte_mempool_obj_iter(mp, rte_pktmbuf_init, NULL);

	return mp;
}

rte_mempool_create_empty函数：创建一个空的mempool，并初始化mempool.

struct rte_mempool *
rte_mempool_create_empty(const char *name, unsigned n, unsigned elt_size,
	unsigned cache_size, unsigned private_data_size,
	int socket_id, unsigned flags)
{
	char mz_name[RTE_MEMZONE_NAMESIZE];
	struct rte_mempool_list *mempool_list;
	struct rte_mempool *mp = NULL;
	struct rte_tailq_entry *te = NULL;
	const struct rte_memzone *mz = NULL;
	size_t mempool_size;
	unsigned int mz_flags = RTE_MEMZONE_1GB|RTE_MEMZONE_SIZE_HINT_ONLY;
	struct rte_mempool_objsz objsz;
	unsigned lcore_id;
	int ret;

	/* compilation-time checks */
	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool) &
			  RTE_CACHE_LINE_MASK) != 0);
	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool_cache) &
			  RTE_CACHE_LINE_MASK) != 0);
#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool_debug_stats) &
			  RTE_CACHE_LINE_MASK) != 0);
	RTE_BUILD_BUG_ON((offsetof(struct rte_mempool, stats) &
			  RTE_CACHE_LINE_MASK) != 0);
#endif
	//获取rte_mempool_tailq队列，从中取出头节点，我们创建的mempool结构填充好，就挂接在这个节点上。
	mempool_list = RTE_TAILQ_CAST(rte_mempool_tailq.head, rte_mempool_list);

	/* asked for zero items */
	if (n == 0) {
		rte_errno = EINVAL;
		return NULL;
	}

	/* asked cache too big */
	if (cache_size > RTE_MEMPOOL_CACHE_MAX_SIZE ||
	    CALC_CACHE_FLUSHTHRESH(cache_size) > n) {
		rte_errno = EINVAL;
		return NULL;
	}

	/* "no cache align" imply "no spread" */
	if (flags & MEMPOOL_F_NO_CACHE_ALIGN)
		flags |= MEMPOOL_F_NO_SPREAD;

	/* calculate mempool object sizes. */
	// 计算了每个obj的大小，这个obj又是由三个部分组成的，objhdr,elt_size,objtlr，即头，数据区，尾
	if (!rte_mempool_calc_obj_size(elt_size, flags, &objsz)) {
		rte_errno = EINVAL;
		return NULL;
	}

	rte_mcfg_mempool_write_lock();

	/*
	 * reserve a memory zone for this mempool: private data is
	 * cache-aligned
	 */
	private_data_size = (private_data_size +
			     RTE_MEMPOOL_ALIGN_MASK) & (~RTE_MEMPOOL_ALIGN_MASK);


	/* try to allocate tailq entry */
	te = rte_zmalloc("MEMPOOL_TAILQ_ENTRY", sizeof(*te), 0);
	if (te == NULL) {
		RTE_LOG(ERR, MEMPOOL, "Cannot allocate tailq entry!\n");
		goto exit_unlock;
	}
	//mempool_size这个名字太有误导性，这里指的是计算mempool的头结构的大小
	// cache计算的是所有核上的cache之和
	mempool_size = MEMPOOL_HEADER_SIZE(mp, cache_size);
	mempool_size += private_data_size;
	mempool_size = RTE_ALIGN_CEIL(mempool_size, RTE_MEMPOOL_ALIGN);

	ret = snprintf(mz_name, sizeof(mz_name), RTE_MEMPOOL_MZ_FORMAT, name);
	if (ret < 0 || ret >= (int)sizeof(mz_name)) {
		rte_errno = ENAMETOOLONG;
		goto exit_unlock;
	}
	//创建内存池的内存，大小为mempool_size 也就是分配这个mempool头结构大小的空间
	mz = rte_memzone_reserve(mz_name, mempool_size, socket_id, mz_flags);
	if (mz == NULL)
		goto exit_unlock;

	/* init the mempool structure */
	mp = mz->addr;
	memset(mp, 0, MEMPOOL_HEADER_SIZE(mp, cache_size));
	ret = strlcpy(mp->name, name, sizeof(mp->name));
	if (ret < 0 || ret >= (int)sizeof(mp->name)) {
		rte_errno = ENAMETOOLONG;
		goto exit_unlock;
	}
	
	mp->mz = mz;
	mp->size = n;
	mp->flags = flags;
	mp->socket_id = socket_id;
	mp->elt_size = objsz.elt_size;
	mp->header_size = objsz.header_size;
	mp->trailer_size = objsz.trailer_size;
	/* Size of default caches, zero means disabled. */
	mp->cache_size = cache_size;
	mp->private_data_size = private_data_size;
	STAILQ_INIT(&mp->elt_list);
	STAILQ_INIT(&mp->mem_list);

	/*
	 * local_cache pointer is set even if cache_size is zero.
	 * The local_cache points to just past the elt_pa[] array.
	 */
	mp->local_cache = (struct rte_mempool_cache *)
		RTE_PTR_ADD(mp, MEMPOOL_HEADER_SIZE(mp, 0));

	/* Init all default caches. */
	if (cache_size != 0) {
		for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++)
			mempool_cache_init(&mp->local_cache[lcore_id],
					   cache_size);
	}

	te->data = mp;

	rte_mcfg_tailq_write_lock();
	//创建的mempool挂接到mempool_list。
	TAILQ_INSERT_TAIL(mempool_list, te, next);
	rte_mcfg_tailq_write_unlock();
	rte_mcfg_mempool_write_unlock();

	return mp;

exit_unlock:
	rte_mcfg_mempool_write_unlock();
	rte_free(te);
	rte_mempool_free(mp);
	return NULL;
}
}

rte_mempool_calc_obj_size函数：

/* get the header, trailer and total size of a mempool element. */
// 获取 mempool 存储元素的头部、尾部和总大小，可以理解为mbuf的大小
uint32_t
rte_mempool_calc_obj_size(uint32_t elt_size, uint32_t flags,
	struct rte_mempool_objsz *sz)
{
	struct rte_mempool_objsz lsz;

	sz = (sz != NULL) ? sz : &lsz;
	//obj 头部大小
	sz->header_size = sizeof(struct rte_mempool_objhdr);
	if ((flags & MEMPOOL_F_NO_CACHE_ALIGN) == 0)
		sz->header_size = RTE_ALIGN_CEIL(sz->header_size,
			RTE_MEMPOOL_ALIGN);
	// obj 尾部大小
#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
	sz->trailer_size = sizeof(struct rte_mempool_objtlr);
#else
	sz->trailer_size = 0;
#endif

	/* element size is 8 bytes-aligned at least */
	// obj 对齐后的element size
	sz->elt_size = RTE_ALIGN_CEIL(elt_size, sizeof(uint64_t));

	/* expand trailer to next cache line */
	if ((flags & MEMPOOL_F_NO_CACHE_ALIGN) == 0) {
		sz->total_size = sz->header_size + sz->elt_size +
			sz->trailer_size;
		sz->trailer_size += ((RTE_MEMPOOL_ALIGN -
				  (sz->total_size & RTE_MEMPOOL_ALIGN_MASK)) &
				 RTE_MEMPOOL_ALIGN_MASK);
	}

	/*
	 * increase trailer to add padding between objects in order to
	 * spread them across memory channels/ranks
	 */
	if ((flags & MEMPOOL_F_NO_SPREAD) == 0) {
		unsigned new_size;
		new_size = optimize_object_size(sz->header_size + sz->elt_size +
			sz->trailer_size);
		sz->trailer_size = new_size - sz->header_size - sz->elt_size;
	}

	/* this is the size of an object, including header and trailer */
	//obj 的总大小
	sz->total_size = sz->header_size + sz->elt_size + sz->trailer_size;

	return sz->total_size;
}

rte_mempool_populate_default函数：创建所有obj的内存，并存入ring队列

int
rte_mempool_populate_default(struct rte_mempool *mp)
{
	unsigned int mz_flags = RTE_MEMZONE_1GB|RTE_MEMZONE_SIZE_HINT_ONLY;
	char mz_name[RTE_MEMZONE_NAMESIZE];
	const struct rte_memzone *mz;
	ssize_t mem_size;
	size_t align, pg_sz, pg_shift = 0;
	rte_iova_t iova;
	unsigned mz_id, n;
	int ret;
	bool need_iova_contig_obj;
	size_t max_alloc_size = SIZE_MAX;
	////调用 common_ring_alloc---->ring_alloc
	ret = mempool_ops_alloc_once(mp);
	if (ret != 0)
		return ret;

	/* mempool must not be populated */
	if (mp->nb_mem_chunks != 0)
		return -EEXIST;

	need_iova_contig_obj = !(mp->flags & MEMPOOL_F_NO_IOVA_CONTIG);
	ret = rte_mempool_get_page_size(mp, &pg_sz);
	if (ret < 0)
		return ret;

	if (pg_sz != 0)
		pg_shift = rte_bsf32(pg_sz);

	for (mz_id = 0, n = mp->size; n > 0; mz_id++, n -= ret) {
		size_t min_chunk_size;
		//获取内存池中元素内存总大小 n*(mp->header_size + mp->elt_size + mp->trailer_size)
		mem_size = rte_mempool_ops_calc_mem_size(
			mp, n, pg_shift, &min_chunk_size, &align);

		if (mem_size < 0) {
			ret = mem_size;
			goto fail;
		}

		ret = snprintf(mz_name, sizeof(mz_name),
			RTE_MEMPOOL_MZ_FORMAT "_%d", mp->name, mz_id);
		if (ret < 0 || ret >= (int)sizeof(mz_name)) {
			ret = -ENAMETOOLONG;
			goto fail;
		}

		/* if we're trying to reserve contiguous memory, add appropriate
		 * memzone flag.
		 */
		if (min_chunk_size == (size_t)mem_size)
			mz_flags |= RTE_MEMZONE_IOVA_CONTIG;

		/* Allocate a memzone, retrying with a smaller area on ENOMEM */
		// 创建mempool中元素的全部内存，
		do {
			mz = rte_memzone_reserve_aligned(mz_name,
				RTE_MIN((size_t)mem_size, max_alloc_size),
				mp->socket_id, mz_flags, align);

			if (mz != NULL || rte_errno != ENOMEM)
				break;

			max_alloc_size = RTE_MIN(max_alloc_size,
						(size_t)mem_size) / 2;
		} while (mz == NULL && max_alloc_size >= min_chunk_size);

		if (mz == NULL) {
			ret = -rte_errno;
			goto fail;
		}

		if (need_iova_contig_obj)
			iova = mz->iova;
		else
			iova = RTE_BAD_IOVA;

		if (pg_sz == 0 || (mz_flags & RTE_MEMZONE_IOVA_CONTIG))
			//给每一个memhdr和obj赋值，将其设置到mp对应的链表里面同时把obj enqueue到ring里面去，允许用户获取
			ret = rte_mempool_populate_iova(mp, mz->addr,
				iova, mz->len,
				rte_mempool_memchunk_mz_free,
				(void *)(uintptr_t)mz);
		else
			ret = rte_mempool_populate_virt(mp, mz->addr,
				mz->len, pg_sz,
				rte_mempool_memchunk_mz_free,
				(void *)(uintptr_t)mz);
		if (ret < 0) {
			rte_memzone_free(mz);
			goto fail;
		}
	}

	return mp->size;

 fail:
	rte_mempool_free_memchunks(mp);
	return ret;
}

rte_mempool 获取内存

获取mempool中的内存调用接口 rte_mempool_get_bulk。以下为rte_mempool_get_bulk源码：

1：rte_mempool_default_cache 函数为 获取核(lcore_id)对应的cache。先从自己的core的cache拿到cache控制块&mp->local_cache[lcore_id]
2：rte_mempool_generic_get函数用于获取所需的内存

static __rte_always_inline int
rte_mempool_get_bulk(struct rte_mempool *mp, void **obj_table, unsigned int n)
{
	struct rte_mempool_cache *cache;
	//获取locre_id 对应的 cache
	cache = rte_mempool_default_cache(mp, rte_lcore_id());
	return rte_mempool_generic_get(mp, obj_table, n, cache);
}

static __rte_always_inline int
rte_mempool_generic_get(struct rte_mempool *mp, void **obj_table,
			unsigned int n, struct rte_mempool_cache *cache)
{
	int ret;
	ret = __mempool_generic_get(mp, obj_table, n, cache);
	if (ret == 0)
		__mempool_check_cookies(mp, obj_table, n, 1);
	return ret;
}

__mempool_generic_get函数：
1：首先判断cache->len当前的容量是否满足获取的个数，
2：如果不够的话，再往cache里面增加obj，最后再从cache里面获取obj。

static __rte_always_inline int
__mempool_generic_get(struct rte_mempool *mp, void **obj_table,
		      unsigned int n, struct rte_mempool_cache *cache)
{
	int ret;
	uint32_t index, len;
	void **cache_objs;

	/* No cache provided or cannot be satisfied from cache */
	if (unlikely(cache == NULL || n >= cache->size))
		goto ring_dequeue;

	cache_objs = cache->objs;

	/* Can this be satisfied from the cache? */
	// 判断cache->len当前的容量是否满足获取的个数
	if (cache->len < n) {
		/* No. Backfill the cache first, and then fill from it */
		uint32_t req = n + (cache->size - cache->len);

		/* How many do we require i.e. number to fill the cache + the request */
		// 当前容量不够，所以取req个obj，存入cache
		ret = rte_mempool_ops_dequeue_bulk(mp,
			&cache->objs[cache->len], req);
		if (unlikely(ret < 0)) {
			/*
			 * In the off chance that we are buffer constrained,
			 * where we are not able to allocate cache + n, go to
			 * the ring directly. If that fails, we are truly out of
			 * buffers.
			 */
			goto ring_dequeue;
		}

		cache->len += req;
	}

	/* Now fill in the response ... */
	// 从cache中获取obj
	for (index = 0, len = cache->len - 1; index < n; ++index, len--, obj_table++)
		*obj_table = cache_objs[len];

	cache->len -= n;

	__MEMPOOL_STAT_ADD(mp, get_success, n);

	return 0;

ring_dequeue:

	/* get remaining objects from ring */
	// 从ring 队列中获取obj
	ret = rte_mempool_ops_dequeue_bulk(mp, obj_table, n);

	if (ret < 0)
		__MEMPOOL_STAT_ADD(mp, get_fail, n);
	else
		__MEMPOOL_STAT_ADD(mp, get_success, n);

	return ret;
}

mbuf和mempool结构图解