DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Wiles, Keith" <keith.wiles@intel.com>
To: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH 1/2] net/tap: remove redundant syscall on Tx
Date: Tue, 14 Mar 2017 13:52:22 +0000	[thread overview]
Message-ID: <BA5B46C0-CB25-4102-B062-046D08C1BA7A@intel.com> (raw)
In-Reply-To: <f8b03c0556b9d7adad14058b5f8c4af26be6d504.1489495663.git.adrien.mazarguil@6wind.com>


> On Mar 14, 2017, at 8:51 PM, Adrien Mazarguil <adrien.mazarguil@6wind.com> wrote:
> 
> Polling the Tx queue file descriptor before writing to it is not mandatory
> since it is configured as non-blocking.
> 
> Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
> Acked-by: Pascal Mazon <pascal.mazon@6wind.com>

Acked-by: Keith Wiles <keith.wiles@intel.com>

> ---
> drivers/net/tap/rte_eth_tap.c | 26 ++++++++------------------
> 1 file changed, 8 insertions(+), 18 deletions(-)
> 
> diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
> index efc4426..c757a7c 100644
> --- a/drivers/net/tap/rte_eth_tap.c
> +++ b/drivers/net/tap/rte_eth_tap.c
> @@ -43,7 +43,6 @@
> #include <sys/ioctl.h>
> #include <sys/mman.h>
> #include <unistd.h>
> -#include <poll.h>
> #include <arpa/inet.h>
> #include <linux/if.h>
> #include <linux/if_tun.h>
> @@ -242,7 +241,6 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
> {
> 	struct rte_mbuf *mbuf;
> 	struct tx_queue *txq = queue;
> -	struct pollfd pfd;
> 	uint16_t num_tx = 0;
> 	unsigned long num_tx_bytes = 0;
> 	int i, n;
> @@ -250,26 +248,18 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
> 	if (unlikely(nb_pkts == 0))
> 		return 0;
> 
> -	pfd.events = POLLOUT;
> -	pfd.fd = txq->fd;
> 	for (i = 0; i < nb_pkts; i++) {
> -		n = poll(&pfd, 1, 0);
> -
> +		/* copy the tx frame data */
> +		mbuf = bufs[num_tx];
> +		n = write(txq->fd,
> +			  rte_pktmbuf_mtod(mbuf, void *),
> +			  rte_pktmbuf_pkt_len(mbuf));
> 		if (n <= 0)
> 			break;
> 
> -		if (pfd.revents & POLLOUT) {
> -			/* copy the tx frame data */
> -			mbuf = bufs[num_tx];
> -			n = write(pfd.fd, rte_pktmbuf_mtod(mbuf, void*),
> -				  rte_pktmbuf_pkt_len(mbuf));
> -			if (n <= 0)
> -				break;
> -
> -			num_tx++;
> -			num_tx_bytes += mbuf->pkt_len;
> -			rte_pktmbuf_free(mbuf);
> -		}
> +		num_tx++;
> +		num_tx_bytes += mbuf->pkt_len;
> +		rte_pktmbuf_free(mbuf);
> 	}
> 
> 	txq->stats.opackets += num_tx;
> -- 
> 2.1.4
> 

Regards,
Keith

  parent reply	other threads:[~2017-03-14 13:52 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-03-14 12:51 Adrien Mazarguil
2017-03-14 12:51 ` [dpdk-dev] [PATCH 2/2] net/tap: add Rx trigger Adrien Mazarguil
2017-03-14 13:57   ` Wiles, Keith
2017-03-14 13:52 ` Wiles, Keith [this message]
2017-03-14 17:04   ` [dpdk-dev] [PATCH 1/2] net/tap: remove redundant syscall on Tx 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=BA5B46C0-CB25-4102-B062-046D08C1BA7A@intel.com \
    --to=keith.wiles@intel.com \
    --cc=adrien.mazarguil@6wind.com \
    --cc=dev@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).