From: Bruce Richardson <bruce.richardson@intel.com>
To: Mingjin Ye <mingjinx.ye@intel.com>
Cc: <dev@dpdk.org>, <stable@dpdk.org>,
Anatoly Burakov <anatoly.burakov@intel.com>,
Vladimir Medvedkin <vladimir.medvedkin@intel.com>
Subject: Re: [PATCH v2] net/ixgbe: fix min Rx/Tx descriptors
Date: Tue, 25 Feb 2025 15:53:10 +0000 [thread overview]
Message-ID: <Z73nZkQwPIavFL7B@bricha3-mobl1.ger.corp.intel.com> (raw)
In-Reply-To: <20250225091236.357008-1-mingjinx.ye@intel.com>
On Tue, Feb 25, 2025 at 09:12:36AM +0000, Mingjin Ye wrote:
> The minimum free packet threshold (tx_free_thresh) and the minimum RS bit
> threshold (tx_rs_thresh) both have a default value of 32. Therefore, the
> default minimum number of ring descriptors value is 64.
>
> For reference, see "Configuration of Transmit Queues" in
> doc/guides/prog_guide/ethdev/ethdev.rst
>
> Fixes: dee5f1fd5fc7 ("ixgbe: get queue info and descriptor limits")
> Cc: stable@dpdk.org
>
> Signed-off-by: Mingjin Ye <mingjinx.ye@intel.com>
> ---
> v2: Change doc.
> ---
> doc/guides/nics/ixgbe.rst | 5 +++--
> drivers/net/intel/ixgbe/ixgbe_rxtx.h | 2 +-
> 2 files changed, 4 insertions(+), 3 deletions(-)
>
> diff --git a/doc/guides/nics/ixgbe.rst b/doc/guides/nics/ixgbe.rst
> index c5c6a6c34b..aaed324e15 100644
> --- a/doc/guides/nics/ixgbe.rst
> +++ b/doc/guides/nics/ixgbe.rst
> @@ -68,11 +68,12 @@ Ensure that the following pre-conditions are satisfied:
>
> * (rxq->nb_rx_desc % rxq->rx_free_thresh) == 0
>
> -* rxq->nb_rx_desc < (IXGBE_MAX_RING_DESC - RTE_PMD_IXGBE_RX_MAX_BURST)
> +* rxq->nb_rx_desc >= IXGBE_MIN_RING_DESC
> +
> +* rxq->nb_rx_desc <= IXGBE_MAX_RING_DESC
>
> These conditions are checked in the code.
>
> -Scattered packets are not supported in this mode.
> If an incoming packet is greater than the maximum acceptable length of one "mbuf" data size (by default, the size is 2 KB),
> vPMD for RX would be disabled.
>
These two lines in the doc should be removed as well, since they also imply
the unavailability of scattered Rx.
Fixing this by dropping them on apply.
> diff --git a/drivers/net/intel/ixgbe/ixgbe_rxtx.h b/drivers/net/intel/ixgbe/ixgbe_rxtx.h
> index 278f665108..54569c7ade 100644
> --- a/drivers/net/intel/ixgbe/ixgbe_rxtx.h
> +++ b/drivers/net/intel/ixgbe/ixgbe_rxtx.h
> @@ -26,7 +26,7 @@
> * descriptors should meet the following condition:
> * (num_ring_desc * sizeof(rx/tx descriptor)) % 128 == 0
> */
> -#define IXGBE_MIN_RING_DESC 32
> +#define IXGBE_MIN_RING_DESC 64
> #define IXGBE_MAX_RING_DESC 8192
>
> #define RTE_PMD_IXGBE_TX_MAX_BURST 32
> --
> 2.25.1
>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Applied to dpdk-next-net-intel.
Thanks,
/Bruce
prev parent reply other threads:[~2025-02-25 15:53 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-21 8:23 [PATCH] " Mingjin Ye
2025-02-21 14:33 ` Bruce Richardson
2025-02-21 14:36 ` Bruce Richardson
2025-02-25 9:12 ` [PATCH v2] " Mingjin Ye
2025-02-25 15:53 ` Bruce Richardson [this message]
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=Z73nZkQwPIavFL7B@bricha3-mobl1.ger.corp.intel.com \
--to=bruce.richardson@intel.com \
--cc=anatoly.burakov@intel.com \
--cc=dev@dpdk.org \
--cc=mingjinx.ye@intel.com \
--cc=stable@dpdk.org \
--cc=vladimir.medvedkin@intel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).