On 4/15/21 5:45 PM, David Marchand wrote:
> On Thu, Apr 15, 2021 at 5:33 PM Maxime Coquelin
> <maxime.coque...@redhat.com> wrote:
>> On 4/7/21 12:17 PM, Balazs Nemeth wrote:
>>> Now that all allocation and freeing has been moved together, use the
>>> faster bulk versions instead of handling packets one by one.
>>>
>>> Signed-off-by: Balazs Nemeth <bnem...@redhat.com>
>>> ---
>>> lib/librte_vhost/virtio_net.c | 11 ++++++-----
>>> 1 file changed, 6 insertions(+), 5 deletions(-)
>>>
>>> diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
>>> index 496f750e3..2f0c97b91 100644
>>> --- a/lib/librte_vhost/virtio_net.c
>>> +++ b/lib/librte_vhost/virtio_net.c
>>> @@ -2469,10 +2469,10 @@ virtio_dev_tx_packed(struct virtio_net *dev,
>>> {
>>> uint32_t pkt_idx = 0;
>>> uint32_t remained = count;
>>> - uint16_t i;
>>>
>>> - for (i = 0; i < count; ++i)
>>> - pkts[i] = rte_pktmbuf_alloc(mbuf_pool);
>>> + if (rte_pktmbuf_alloc_bulk(mbuf_pool, pkts, count)) {
>>> + return 0;
>>> + }
>>
>> OK, get it now :)
>> Maybe just add a comment in previous patches that it is going to be
>> handled when moving to bulk allocation.
>
> Looking at the whole series, it is easy to read and understand as a
> single patch.
> And it avoids this intermediate issue.
I agree with David, better to squash the first three patches.
Thanks,
Maxime
