DPDK patches and discussions
 help / color / mirror / Atom feed
From: Stefan Binna <stefan.binna@salzburgresearch.at>
To: "Mcnamara, John" <john.mcnamara@intel.com>,
	"dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] ieee1588fwd.c implementation
Date: Mon, 17 Aug 2015 10:47:40 +0200	[thread overview]
Message-ID: <55D19FAC.20609@salzburgresearch.at> (raw)
In-Reply-To: <B27915DBBA3421428155699D51E4CFE2022E6CEF@IRSMSX103.ger.corp.intel.com>

Hi,

I'm using the Intel NIC 82547L.
Furthermore I'm using DPDK-2.0.0, the last stable download from the 
official homepage.

Is there any method to "measure" the time the NIC takes to process the 
packet from the input port (e.g. port 0) to the output port (port 1)? 
Should be around 8 to 40 microseconds depending on the packet size?

Thanks. Best regards,
Stefan.

Am 14.08.2015 um 18:04 schrieb Mcnamara, John:
>> -----Original Message-----
>> From: Stefan Binna [mailto:stefan.binna@salzburgresearch.at]
>> Sent: Thursday, August 13, 2015 12:27 PM
>> To: Mcnamara, John; dev@dpdk.org
>> Subject: Re: [dpdk-dev] ieee1588fwd.c implementation
>>
>> I got PTP working and was able to transmit a valid PTPv2 packet over the
>> DPDK network card.
>>
>> Every time a PTP packet arrives I get following message in the testpmd
>> application: Port 0 Received PTP packet not filtered by hardware
>
> Hi,
>
> That may be due to 1 or 2 different issues:
>
>      1. You are using a NIC that doesn't support PTP timesyncing. What NIC are you using?
>      2. You are using a Fortville NIC but don't have the latest code from dpdk.org.
>
>
>> However, the hardware does not change the timestamp, when I check the
>> received packet.
> You will need to address the above issue first, but just to be clear, the NIC doesn't update the timestamp in the PTP packet. It sets a flag to say that the packet is a L2 PTP packet and that the timestamp of its arrival is available for reading.
>
> John
>

  reply	other threads:[~2015-08-17  8:47 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-08-12 16:01 Stefan Binna
2015-08-12 16:24 ` Mcnamara, John
2015-08-12 16:41   ` Stefan Binna
2015-08-12 17:09     ` Mcnamara, John
2015-08-12 17:32       ` Stefan Binna
2015-08-13 11:27         ` Stefan Binna
2015-08-14 16:04           ` Mcnamara, John
2015-08-17  8:47             ` Stefan Binna [this message]
2015-08-17 14:21               ` Mcnamara, John
2015-08-18  7:38                 ` Stefan Binna

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=55D19FAC.20609@salzburgresearch.at \
    --to=stefan.binna@salzburgresearch.at \
    --cc=dev@dpdk.org \
    --cc=john.mcnamara@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).