All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jerin Jacob <jerin.jacob@caviumnetworks.com>
To: Kiran Kumar <kkokkilagadda@caviumnetworks.com>
Cc: maciej.czekaj@caviumnetworks.com, ferruh.yigit@intel.com,
	dev@dpdk.org, stable@dpdk.org
Subject: Re: [PATCH v2] net/thunderx: avoid sq door bell writes on zero packets
Date: Wed, 11 Jul 2018 14:35:59 +0530	[thread overview]
Message-ID: <20180711090557.GA22077@jerin> (raw)
In-Reply-To: <1531297476-4604-1-git-send-email-kkokkilagadda@caviumnetworks.com>

-----Original Message-----
> Date: Wed, 11 Jul 2018 13:54:36 +0530
> From: Kiran Kumar <kkokkilagadda@caviumnetworks.com>
> To: jerin.jacob@caviumnetworks.com, maciej.czekaj@caviumnetworks.com,
>  ferruh.yigit@intel.com
> Cc: dev@dpdk.org, Kiran Kumar <kkokkilagadda@caviumnetworks.com>,
>  stable@dpdk.org
> Subject: [dpdk-dev] [PATCH v2] net/thunderx: avoid sq door bell writes on
>  zero packets
> X-Mailer: git-send-email 2.7.4
> 
> Avoid sq door bell write on zero packet case to reduce additional
> traffic on register bus.
> 
> Fixes: 1c421f18e0 ("net/thunderx: add single and multi-segment Tx")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Kiran Kumar <kkokkilagadda@caviumnetworks.com>

Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>

> ---
>  v2 Changes:
>  - changed summery and description.
>  - added same optimization to nicvf_xmit_pkts_multiseg
> 
>  drivers/net/thunderx/nicvf_rxtx.c | 24 ++++++++++++++----------
>  1 file changed, 14 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/net/thunderx/nicvf_rxtx.c b/drivers/net/thunderx/nicvf_rxtx.c
> index 72305d9..6e075e2 100644
> --- a/drivers/net/thunderx/nicvf_rxtx.c
> +++ b/drivers/net/thunderx/nicvf_rxtx.c
> @@ -162,12 +162,14 @@ nicvf_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
>  		free_desc -= TX_DESC_PER_PKT;
>  	}
> 
> -	sq->tail = tail;
> -	sq->xmit_bufs += i;
> -	rte_wmb();
> +	if (likely(i)) {
> +		sq->tail = tail;
> +		sq->xmit_bufs += i;
> +		rte_wmb();
> 
> -	/* Inform HW to xmit the packets */
> -	nicvf_addr_write(sq->sq_door, i * TX_DESC_PER_PKT);
> +		/* Inform HW to xmit the packets */
> +		nicvf_addr_write(sq->sq_door, i * TX_DESC_PER_PKT);
> +	}
>  	return i;
>  }
> 
> @@ -218,12 +220,14 @@ nicvf_xmit_pkts_multiseg(void *tx_queue, struct rte_mbuf **tx_pkts,
>  		}
>  	}
> 
> -	sq->tail = tail;
> -	sq->xmit_bufs += used_bufs;
> -	rte_wmb();
> +	if (likely(used_desc)) {
> +		sq->tail = tail;
> +		sq->xmit_bufs += used_bufs;
> +		rte_wmb();
> 
> -	/* Inform HW to xmit the packets */
> -	nicvf_addr_write(sq->sq_door, used_desc);
> +		/* Inform HW to xmit the packets */
> +		nicvf_addr_write(sq->sq_door, used_desc);
> +	}
>  	return i;
>  }
> 
> --
> 2.7.4
> 

  reply	other threads:[~2018-07-11  9:05 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-07-11  7:22 [PATCH] net/thunderx: Block sq door writes on zero pkts Kiran Kumar
2018-07-11  7:37 ` Jerin Jacob
2018-07-11  8:24 ` [PATCH v2] net/thunderx: avoid sq door bell writes on zero packets Kiran Kumar
2018-07-11  9:05   ` Jerin Jacob [this message]
2018-07-18  9:41     ` Ferruh Yigit

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=20180711090557.GA22077@jerin \
    --to=jerin.jacob@caviumnetworks.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=kkokkilagadda@caviumnetworks.com \
    --cc=maciej.czekaj@caviumnetworks.com \
    --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 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.