Hi slava,
Is this fixed in main branch now?
If yes could you please point me out the proper commit?
Thanks
Didier
On 3/17/20 10:25 AM, Slava Ovsiienko wrote:
*From:* Didier Pallard <[email protected]>
*Sent:* Tuesday, March 17, 2020 11:19
*To:* Slava Ovsiienko <[email protected]>
*Cc:* [email protected]; [email protected]; Matan Azrad <[email protected]>
*Subject:* Re: [dpdk-dev] [PATCH] net/mlx5: fix Rx descriptor status
returned value
>>>well, please do if you don't mind,
OK, I will.
>>>You will validate it quicker, and I'm currently working on a
different topic.
>>>Btw, do you think it's possible to have an implementation of
[r,t]x_status_descriptor functions for vectorized implementation?
>>>thanks
Yes, we are planning this update.
With best regards, Slava
didier
On Tue, Mar 17, 2020 at 9:33 AM Slava Ovsiienko
<[email protected] <mailto:[email protected]>> wrote:
>> From: Didier Pallard <[email protected]
<mailto:[email protected]>>
>> Sent: Monday, March 16, 2020 19:24
>> To: Slava Ovsiienko <[email protected]
<mailto:[email protected]>>
>> Cc: [email protected] <mailto:[email protected]>; [email protected]
<mailto:[email protected]>; Matan Azrad <[email protected]
<mailto:[email protected]>>
>> Subject: Re: [dpdk-dev] [PATCH] net/mlx5: fix Rx descriptor
status returned value
>> Well, you're right, another way to fix the problem could be to
set up the queue size assuming the provided number
>> is a number of packets in queue rather than a number of mbufs
in queue.
Yes, it is intended in queue setup routine. But, for mlx5 we have
a bug for regular mlx5_rx_burst if scattering is enabled,
the Rx queue is created with size wqe_n elements, should be wqe_n
<< sges_n instead, to be able to receive the requested
number of packets (wqe_n). I think we must fix. Would you like to
update your patch, or should I provide mine?
>> But not sure it's better, it's also important for the
application/user to know the number of mbufs that could fit in a
rx/tx queue,
>> whatever the number of packets that it covers, since it is very
important to size the memory pools correctly to avoid any
>> mbuf shortage during system life.
>> Thanks
>> Didier
To estimate - the number of "DPDK descriptors" should be
multiplied by the maximal length of scattered packet chain.
With best regards, Slava
> -----Original Message-----
> From: dev <mailto:[email protected]
<mailto:[email protected]>> On Behalf Of Didier Pallard
> Sent: Friday, March 13, 2020 11:57
> To: mailto:[email protected] <mailto:[email protected]>
> Cc: mailto:[email protected] <mailto:[email protected]>
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix Rx descriptor status
returned value
>
> Two bugs in rx_queue_count function:
> - One entry may contain several segments, so 'used' must be
multiplied
> by number of segments per entry to properly reflect the queue
usage.
> - rx_queue_count returns the number of entries used in queue, so
it ranges
> from 0 to max number of entries in queue, not this number minus
> one.
>
> Fixes: 8788fec1f269 ("net/mlx5: implement descriptor status API")
> Cc: mailto:[email protected] <mailto:[email protected]>
> Signed-off-by: Didier Pallard <mailto:[email protected]
<mailto:[email protected]>>
> ---
> drivers/net/mlx5/mlx5_rxtx.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/net/mlx5/mlx5_rxtx.c
b/drivers/net/mlx5/mlx5_rxtx.c index
> 5ac63da8039d..17f80c25443e 100644
> --- a/drivers/net/mlx5/mlx5_rxtx.c
> +++ b/drivers/net/mlx5/mlx5_rxtx.c
> @@ -500,7 +500,7 @@ rx_queue_count(struct mlx5_rxq_data *rxq)
> used += n;
> cqe = &(*rxq->cqes)[cq_ci & cqe_cnt];
> }
> - used = RTE_MIN(used, (1U << rxq->elts_n) - 1);
> + used = RTE_MIN(used * (1 << rxq->sges_n), 1U << rxq->elts_n);
> return used;
> }
>
> --
> 2.24.1
