On 6/22/2021 11:57 AM, wangyunjian wrote:
> From: Yunjian Wang <wangyunj...@huawei.com>
>
> In kni_allocate_mbufs(), we alloc mbuf for alloc_q as this code.
> allocq_free = (kni->alloc_q->read - kni->alloc_q->write - 1) \
> & (MAX_MBUF_BURST_NUM - 1);
> The value of allocq_free maybe zero, for example :
> The ring size is 1024. After init, write = read = 0. Then we fill
> kni->alloc_q to full. At this time, write = 1023, read = 0.
>
> Then the kernel send 32 packets to userspace. At this time, write
> = 1023, read = 32. And then the userspace receive this 32 packets.
> Then fill the kni->alloc_q, (32 - 1023 - 1) & 31 = 0, fill nothing.
> ...
> Then the kernel send 32 packets to userspace. At this time, write
> = 1023, read = 992. And then the userspace receive this 32 packets.
> Then fill the kni->alloc_q, (992 - 1023 - 1) & 31 = 0, fill nothing.
>
> Then the kernel send 32 packets to userspace. The kni->alloc_q only
> has 31 mbufs and will drop one packet.
>
> Absolutely, this is a special scene. Normally, it will fill some
> mbufs everytime, but may not enough for the kernel to use.
>
> In this patch, we always keep the kni->alloc_q to full for the kernel
> to use.
>
> Fixes: 49da4e82cf94 ("kni: allocate no more mbuf than empty slots in queue")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Cheng Liu <liuchen...@huawei.com>
> Signed-off-by: Yunjian Wang <wangyunj...@huawei.com>
Acked-by: Ferruh Yigit <ferruh.yi...@intel.com>
What do you think to change patch title to something like:
kni: fix mbuf allocation for alloc FIFO
