DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Xing, Beilei" <beilei.xing@intel.com>
To: Martin Weiser <martin.weiser@allegro-packets.com>,
	"Zhang, Qi Z" <qi.z.zhang@intel.com>,
	"dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] i40e rte_eth_link_get_nowait() on X722 returns wrong link_speed value 20000 instead of 10000
Date: Wed, 10 Apr 2019 05:22:15 +0000	[thread overview]
Message-ID: <94479800C636CB44BD422CB454846E013CD92806@SHSMSX101.ccr.corp.intel.com> (raw)
Message-ID: <20190410052215.eXvlKzhCK6cmu9hFGWbCtS2c4pV5PjnSewjZG0_lZsg@z> (raw)
In-Reply-To: <71f2b044-b99b-be8c-8468-a38c8c42713c@allegro-packets.com>



> -----Original Message-----
> From: Martin Weiser [mailto:martin.weiser@allegro-packets.com]
> Sent: Tuesday, April 9, 2019 7:21 PM
> To: Xing, Beilei <beilei.xing@intel.com>; Zhang, Qi Z <qi.z.zhang@intel.com>;
> dev@dpdk.org
> Subject: Re: [dpdk-dev] i40e rte_eth_link_get_nowait() on X722 returns
> wrong link_speed value 20000 instead of 10000
> 
> Hi,
> 
> just bumping this since there has been no reply at all for a long time.
> Would it be better if I opened a bug for this?

Thanks for reporting.
Yes, you can open a bug on bugzilla, and we will check it if the bug exists.

> 
> Best,
> Martin
> 
> 
> Am 22.01.19 um 16:07 schrieb Martin Weiser:
> > Hi,
> >
> > We are using a Xeon D with an integrated X722 NIC that provides two
> > ports of 8086:37d2 and two ports of 8086:37d0. All four ports show the
> > same behavior: they return a link speed value of 20000 for a 10Gbps link.
> >
> > This only seems to happen when internally the update_link_reg()
> > function in i40e_ethdev.c is used. This requires the application to
> > use the
> > rte_eth_link_get_nowait() function and not use link status change
> > interrupts.
> > If you use e.g. testpmd with the option --no-lsc-interrupt you can
> > reproduce the behavior since it will suddenly show a link speed of
> > 20000 Mbps instead of 10000 Mbps.
> >
> >
> > Here are two examples of the register values read by update_link_reg():
> >
> > A 10Gbps link which produces the wrong link speed value:
> >
> > I40E_PRTMAC_LINKSTA: 0x60000080
> > I40E_PRTMAC_MACC:    0x3d00
> >
> >
> > A 1Gbps link which produces the correct link speed value:
> >
> > I40E_PRTMAC_LINKSTA: 0x48000081
> > I40E_PRTMAC_MACC:    0x3d00
> >
> >
> > Best regards,
> > Martin
> >
> 
> 


  parent reply	other threads:[~2019-04-10  5:22 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-22 15:07 Martin Weiser
2019-04-09 11:20 ` Martin Weiser
2019-04-09 11:20   ` Martin Weiser
2019-04-10  5:22   ` Xing, Beilei [this message]
2019-04-10  5:22     ` Xing, Beilei

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=94479800C636CB44BD422CB454846E013CD92806@SHSMSX101.ccr.corp.intel.com \
    --to=beilei.xing@intel.com \
    --cc=dev@dpdk.org \
    --cc=martin.weiser@allegro-packets.com \
    --cc=qi.z.zhang@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).