DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Zhang, Qi Z" <qi.z.zhang@intel.com>
To: "Xing, Beilei" <beilei.xing@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>, "stable@dpdk.org" <stable@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH] net/i40e: fix Rx instability with vector mode
Date: Thu, 25 Oct 2018 16:47:09 +0000	[thread overview]
Message-ID: <039ED4275CED7440929022BC67E70611532DB803@SHSMSX103.ccr.corp.intel.com> (raw)
In-Reply-To: <1540453252-128654-1-git-send-email-beilei.xing@intel.com>



> -----Original Message-----
> From: Xing, Beilei
> Sent: Thursday, October 25, 2018 2:41 AM
> To: Zhang, Qi Z <qi.z.zhang@intel.com>
> Cc: dev@dpdk.org; stable@dpdk.org
> Subject: [PATCH] net/i40e: fix Rx instability with vector mode
> 
> Previously, there is instability during vector Rx if descriptor number is not
> power of 2, e.g. process hang and some Rx packets are unexpectedly empty.
> That's because vector Rx mode assumes Rx descriptor number is power of 2
> when doing bit mask.
> This patch allows vector mode only when the number of Rx descriptor is
> power of 2.
> 
> Fixes: 8e109464c022 ("i40e: allow vector Rx and Tx usage")
> Fixes: a3c83a2527e1 ("net/i40e: enable runtime queue setup")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Beilei Xing <beilei.xing@intel.com>
> ---
>  doc/guides/nics/i40e.rst     |  7 +++++++
>  drivers/net/i40e/i40e_rxtx.c | 18 +++++++++++++++++-
>  2 files changed, 24 insertions(+), 1 deletion(-)
> 
> diff --git a/doc/guides/nics/i40e.rst b/doc/guides/nics/i40e.rst index
> ab3928a..bfacbd1 100644
> --- a/doc/guides/nics/i40e.rst
> +++ b/doc/guides/nics/i40e.rst
> @@ -172,6 +172,13 @@ Runtime Config Options
> 
>    -w 84:00.0,use-latest-supported-vec=1
> 
> +Vector RX Pre-conditions
> +~~~~~~~~~~~~~~~~~~~~~~~~
> +For Vector RX it is assumed that the number of descriptor rings will be
> +a power of 2. With this pre-condition, the ring pointer can easily
> +scroll back to the head after hitting the tail without a conditional
> +check. In addition Vector RX can use this assumption to do a bit mask using
> ``ring_size - 1``.
> +
>  Driver compilation and testing
>  ------------------------------
> 
> diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c index
> a827456..aa46d83 100644
> --- a/drivers/net/i40e/i40e_rxtx.c
> +++ b/drivers/net/i40e/i40e_rxtx.c
> @@ -1735,10 +1735,17 @@ i40e_dev_rx_queue_setup_runtime(struct
> rte_eth_dev *dev,
>  		 * i40e_set_rx_function.
>  		 */
>  		ad->rx_bulk_alloc_allowed = true;
> -		ad->rx_vec_allowed = true;
>  		dev->data->scattered_rx = use_scattered_rx;
>  		if (use_def_burst_func)
>  			ad->rx_bulk_alloc_allowed = false;
> +		/**
> +		 * Vector mode is allowed only when number of Rx queue
> +		 * descriptor is a power of 2.
> +		 */
> +		if ((rxq->nb_rx_desc & (rxq->nb_rx_desc - 1)))
> +			ad->rx_vec_allowed = false;
> +		else
> +			ad->rx_vec_allowed = true;
>  		i40e_set_rx_function(dev);
>  		return 0;
>  	}
> @@ -1811,6 +1818,15 @@ i40e_dev_rx_queue_setup(struct rte_eth_dev
> *dev,
>  		return -EINVAL;
>  	}
> 
> +	/**
> +	 * Vector mode is allowed only when number of Rx queue
> +	 * descriptor is a power of 2.
> +	 */
> +	if ((nb_desc & (nb_desc - 1)))
> +		ad->rx_vec_allowed = false;
> +	else
> +		ad->rx_vec_allowed = true;

rx_vec_allowed will be overwritten unexpectedly for multi-queues case

We may only to overwrite with below condition check.

If (first_queue || ad->rx_vec_allowed)
	ad->rx_vec_allowed = ! (nb_desc & (nb_desc - 1));

> +
>  	/* Free memory if needed */
>  	if (dev->data->rx_queues[queue_idx]) {
>  		i40e_dev_rx_queue_release(dev->data->rx_queues[queue_idx]);
> --
> 2.5.5

  reply	other threads:[~2018-10-25 16:47 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-25  7:40 Beilei Xing
2018-10-25 16:47 ` Zhang, Qi Z [this message]
2018-10-26  6:33 ` [dpdk-dev] [PATCH v2] " Beilei Xing
2018-10-26  8:47   ` Ananyev, Konstantin
2018-10-26 15:41     ` Zhang, Qi Z
2018-10-29  1:48       ` Xing, Beilei
2018-10-26 11:11   ` Bruce Richardson
2018-10-26 15:49     ` Zhang, Qi Z
2018-11-01  5:53   ` [dpdk-dev] [PATCH v3] " Beilei Xing
2018-11-01 11:48     ` Ananyev, Konstantin
2018-11-01 13:13       ` Zhang, Qi Z
2018-11-05  3:18     ` [dpdk-dev] [PATCH v4] " Beilei Xing
2018-11-05 11:05       ` Ananyev, Konstantin
2018-11-05 15:53         ` Zhang, Qi Z

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=039ED4275CED7440929022BC67E70611532DB803@SHSMSX103.ccr.corp.intel.com \
    --to=qi.z.zhang@intel.com \
    --cc=beilei.xing@intel.com \
    --cc=dev@dpdk.org \
    --cc=stable@dpdk.org \
    /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).