From: Adrien Mazarguil <adrien.mazarguil@6wind.com>
To: Moti Haimovsky <motih@mellanox.com>
Cc: dev@dpdk.org
Subject: Re: [PATCH] net/mlx4: verify Tx max sges
Date: Fri, 5 Jan 2018 17:53:17 +0100 [thread overview]
Message-ID: <20180105165317.GV4256@6wind.com> (raw)
In-Reply-To: <1515082323-179525-1-git-send-email-motih@mellanox.com>
On Thu, Jan 04, 2018 at 06:12:03PM +0200, Moti Haimovsky wrote:
> Max number of Tx scatter-gather entries is a property of the device
> and is queried at init. This value was not changed in a while and
> most probably will not be changed in the future, Therefore and
> in order to enhance Tx performance, the Tx max-sge value is hardcoded
> in mlx4 PRM code.
> This patch adds a verification that the above assumption still holds
> and that the hardcoded value is still supported by the mlx4 hardware.
>
> Signed-off-by: Moti Haimovsky <motih@mellanox.com>
Except for a really minor nit below:
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
> ---
> drivers/net/mlx4/mlx4.c | 1 +
> drivers/net/mlx4/mlx4_prm.h | 5 ++++-
> 2 files changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/net/mlx4/mlx4.c b/drivers/net/mlx4/mlx4.c
> index 4bc4a6f..61c5bf4 100644
> --- a/drivers/net/mlx4/mlx4.c
> +++ b/drivers/net/mlx4/mlx4.c
> @@ -505,6 +505,7 @@ struct mlx4_conf {
> rte_errno = ENODEV;
> goto error;
> }
> + assert(device_attr.max_sge >= MLX4_MAX_SGE);
> for (i = 0; i < device_attr.phys_port_cnt; i++) {
> uint32_t port = i + 1; /* ports are indexed from one */
> struct ibv_context *ctx = NULL;
> diff --git a/drivers/net/mlx4/mlx4_prm.h b/drivers/net/mlx4/mlx4_prm.h
> index 217ea50..b382d59 100644
> --- a/drivers/net/mlx4/mlx4_prm.h
> +++ b/drivers/net/mlx4/mlx4_prm.h
> @@ -53,7 +53,10 @@
> #define MLX4_TXBB_SIZE (1 << MLX4_TXBB_SHIFT)
>
> /* Typical TSO descriptor with 16 gather entries is 352 bytes. */
> -#define MLX4_MAX_WQE_SIZE 512
> +#define MLX4_MAX_SGE 32
> +#define MLX4_MAX_WQE_SIZE \
> + (MLX4_MAX_SGE * sizeof(struct mlx4_wqe_data_seg) + \
> + sizeof(struct mlx4_wqe_ctrl_seg))
One extra indent space is needed before sizeof to align with parenthesis
contents.
--
Adrien Mazarguil
6WIND
next prev parent reply other threads:[~2018-01-05 16:53 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-04 16:12 [PATCH] net/mlx4: verify Tx max sges Moti Haimovsky
2018-01-05 16:53 ` Adrien Mazarguil [this message]
2018-01-10 15:19 ` Shahaf Shuler
2018-01-10 15:19 ` [PATCH V2] " Moti Haimovsky
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180105165317.GV4256@6wind.com \
--to=adrien.mazarguil@6wind.com \
--cc=dev@dpdk.org \
--cc=motih@mellanox.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.