2017-01-18 11:28 GMT+01:00 Sergey Vyazmitinov <s.vyazmiti...@brain4net.com>:
> Optimized kni_allocate_mbufs and kni_free_mbufs by using mbuf bulk
> functions. This can improve performance more than two times.
>
> Signed-off-by: Sergey Vyazmitinov <s.vyazmiti...@brain4net.com>
> ---
> lib/librte_kni/rte_kni.c | 46
> +++++++++++++++++++++----------------------
> lib/librte_kni/rte_kni_fifo.h | 18 +++++++++++++++++
> 2 files changed, 40 insertions(+), 24 deletions(-)
>
> diff --git a/lib/librte_kni/rte_kni.c b/lib/librte_kni/rte_kni.c
> index a80cefd..ad746ad 100644
> --- a/lib/librte_kni/rte_kni.c
> +++ b/lib/librte_kni/rte_kni.c
[...]
> + /* Check if any mbufs not put into alloc_q, and then free them */
> + if (unlikely(put < count)) {
> + for (unsigned int j = put; j < count; j++) {
> + RTE_LOG(ERR, KNI, "Free allocated buffer\n");
> rte_pktmbuf_free(pkts[j]);
> + }
This could also use bulk free, even if only to shave two lines of code.
Best Regards,
Michał Mirosław
