Re: [dpdk-dev] [PATCH] kni: use bulk functions to allocate and free mbufs

[Yuanhan Liu <yuanhan.liu@linux.intel.com>]

On Wed, Jan 11, 2017 at 10:56:20AM -0800, Stephen Hemminger wrote:
> Please write generic code. Something like the following (untested).

Despite there are few compile errors (which are easy to fix), it works
fine.

More importantly, it saves near 2000 cycles if I apply the bulk free
to virtio_xmit_cleanup(). Only one mp is being used.

	--yliu

> 
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> index 4476d75379fd..b7a743ec5c87 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -306,6 +306,9 @@ extern "C" {
>  /** Alignment constraint of mbuf private area. */
>  #define RTE_MBUF_PRIV_ALIGN 8
>  
> +/** Maximum number of mbufs freed in bulk. */
> +#define RTE_MBUF_BULK_FREE 64
> +
>  /**
>   * Get the name of a RX offload flag
>   *
> @@ -1261,6 +1264,50 @@ static inline void rte_pktmbuf_free(struct rte_mbuf *m)
>  }
>  
>  /**
> + * Free n packets mbuf back into its original mempool.
> + *
> + * Free each mbuf, and all its segments in case of chained buffers. Each
> + * segment is added back into its original mempool.
> + *
> + * @param mbufs
> + *   The packets mbufs array to be freed.
> + * @param n
> + *   Number of packets.
> + */
> +static inline void rte_pktmbuf_free_bulk(struct rte_mbuf **mbufs,
> +					 unsigned n)
> +{
> +	struct rte_mbuf *tofree[RTE_MBUF_BULK_FREE];
> +	struct rte_mempool *mp;
> +	unsigned i, count = 0;
> +
> +	for (i = 0; i < n; i++) {
> +		struct rte_mbuf *m, *m_next;
> +
> +		for (m = mbufs[i]; m; m = m_next) {
> +			m_next = m->next;
> +			
> +			if (count > 0 &&
> +			    (unlikely(m->pool != mp || count == RTE_MBUF_BULK_FREE))) {
> +				rte_mempool_put_bulk(mp, tofree, count);
> +				count = 0;
> +			}
> +
> +			mp = m->pool;
> +
> +			if (likely(__rte_pktmbuf_prefree_seg(m))) {
> +				m->next = NULL;
> +				tofree[count++] = m;
> +			}
> +		}
> +	}
> +
> +	if (likely(count > 0))
> +		rte_mempool_put_bulk(mp, tofree, count);
> +}
> +
> +	
> +/**
>   * Creates a "clone" of the given packet mbuf.
>   *
>   * Walks through all segments of the given packet mbuf, and for each of them:
> 
> 
> This handles multiple pools and multi-segment and indirect mbufs.
>