DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Wiles, Keith" <keith.wiles@intel.com>
To: Mohan Prasad <kcmohanprasad@gmail.com>,
	"Richardson, Bruce" <bruce.richardson@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] DPDK: receive single packet at a time
Date: Thu, 31 Mar 2016 12:40:18 +0000	[thread overview]
Message-ID: <BE67E5D6-88F6-48A1-9EF7-0E474E94B7CB@intel.com> (raw)
In-Reply-To: <CADSKuqvJkihP-Epgs-YAHqU37LV0T=QCWUKe6xnFhsT5eGD9+g@mail.gmail.com>


From:  Mohan Prasad <kcmohanprasad@gmail.com>
Date:  Thursday, March 31, 2016 at 6:42 AM
To:  Bruce Richardson <bruce.richardson@intel.com>
Cc:  Keith Wiles <keith.wiles@intel.com>, "dev@dpdk.org" <dev@dpdk.org>
Subject:  Re: [dpdk-dev] DPDK: receive single packet at a time


>Could not get it working by disabling the vector PMD, Do you have any example where it works?
>
>
>

I would expect the examples like l2fwd or l2fwd work in this way if the PMD is not enabled. The pktgen-dpdk I know will work with a single packet send and received. The code is on the dpdk.org/download directory.

>
>Thanks,
>Mohan
>
>
>On Wed, Mar 30, 2016 at 11:06 AM, Mohan Prasad 
><kcmohanprasad@gmail.com> wrote:
>
>Hi Bruce,
>
>Could not get it working by disabling the vector PMD, Do you have any example where it works?
>
>Thanks,
>Mohan
>
>
>On Tue, Mar 29, 2016 at 6:46 PM, Bruce Richardson 
><bruce.richardson@intel.com> wrote:
>
>On Tue, Mar 29, 2016 at 06:31:58PM +0530, Mohan Prasad wrote:
>> Hi,
>>
>> I have tried this and it does not work
>>
>
>What type of NIC are you using. If you are using ixgbe or i40e, try disabling
>the vector PMD in your build-time configuration to see if it makes a difference.
>
>However, why do you want to receive just a single packet at a time. Why not just
>receive a burst of packets and then process them one at a time? It's much more
>efficient that way, and you should get better performance from your application.
>
>/Bruce
>
>
>> Thanks,
>> Mohan
>> On Mar 29, 2016 6:26 PM, "Wiles, Keith" <keith.wiles@intel.com> wrote:
>>
>> > >Hi,
>> > >
>> > >Is there any option to receive single packet at a time with dpdk?
>> >
>> > Not sure if this is the answer you are looking for, but if you just
>> > request a single packet with
>> >
>> > struct rte_mbuf *mbuf;
>> > rte_eth_rx_burst(port_id, queue_id, &mbuf, 1);
>> >
>> > will return only one packet as a time.
>> > >
>> > >Thanks,
>> > >Mohan
>> > >
>> >
>> >
>> > Regards,
>> > Keith
>> >
>> >
>> >
>> >
>> >
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>


Regards,
Keith



  reply	other threads:[~2016-03-31 12:40 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-29 11:32 Mohan Prasad
2016-03-29 12:56 ` Wiles, Keith
2016-03-29 13:01   ` Mohan Prasad
2016-03-29 13:08     ` Wiles, Keith
2016-03-29 13:21       ` Mohan Prasad
2016-03-29 13:16     ` Bruce Richardson
2016-03-30  5:36       ` Mohan Prasad
2016-03-31 11:42         ` Mohan Prasad
2016-03-31 12:40           ` Wiles, Keith [this message]
2016-03-31 12:43             ` Wiles, Keith

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=BE67E5D6-88F6-48A1-9EF7-0E474E94B7CB@intel.com \
    --to=keith.wiles@intel.com \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=kcmohanprasad@gmail.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).