DPDK usage discussions
 help / color / mirror / Atom feed
From: Ananda Sathyanarayana <ananda@versa-networks.com>
To: Aaron Hughes <hughesac@gmail.com>,
	"users@dpdk.org" <users@dpdk.org>,
	"masutani.hitoshi@lab.ntt.co.jp" <masutani.hitoshi@lab.ntt.co.jp>
Cc: Vignesh Chinnakkannu <vigc@versa-networks.com>
Subject: Re: [dpdk-users] Failed to initialize one specific port of X710-DA4 in i40e pmd
Date: Fri, 20 Dec 2019 13:53:21 +0000	[thread overview]
Message-ID: <CY4PR11MB0054F6DCC49438DEF835E87EE32D0@CY4PR11MB0054.namprd11.prod.outlook.com> (raw)
In-Reply-To: <CAP=pv7MCktADmtqVjYADdB6ZuN9Y=Gp7EF4UN=_4v+_h8tfkKA@mail.gmail.com>

Hi Aaron, Masutani-san, all,

We are also facing this issue in one of the setups. If you were able to get to the bottom of this issue, can you please let us know the cause and the solution.

Thanks,
Ananda

-----Original Message-----
From: users <users-bounces@dpdk.org> On Behalf Of Aaron Hughes
Sent: Friday, August 24, 2018 9:55 AM
To: users@dpdk.org; masutani.hitoshi@lab.ntt.co.jp
Subject: Re: [dpdk-users] Failed to initialize one specific port of X710-DA4 in i40e pmd

Does anyone know what tool can be used to configure/view the settings for the XL710?  I would like to view the DCB and TC settings.  Based on the i40e README you can't use dcbtool and I don't see anyway to do it with ethtool.  One of the ports on the XL710 is working for me but the other one is showing the error about the TC map.

I see this message from the kernel's i40e driver for the port that isn't working with DPDK:
Non-contiguous TC - Disabling DCB

https://downloadmirror.intel.com/25282/eng/README.txt

On Thu, Aug 23, 2018 at 7:54 PM Aaron Hughes <hughesac@gmail.com> wrote:

> Hi Hitoshi,
>
> Did you ever figure out a solution to your problem with the X710?  I'm 
> seeing the same problem with an XL710 using DPDK version 17.05 on 
> Redhat
> 7.5:
>
> validate_tcmap_parameter(): Enabled TC map 0x80 not applicable to HW 
> support 0x1
> i40e_vsi_setup(): Failed to update TC bandwidth
> i40e_pf_setup(): Setup of main vsi failed
> eth_i40e_dev_init(): Failed to setup pf switch: -63
>
> Thanks,
> Aaron
>
> I am facing a failure of dpdk(16.11.3) initialization with testpmd
>> using i40e pmd on a specific physical port of X710-DA4.
>>
>> Without such specific port, testpmd can run successfully.
>>
>> My server box has two X710-DA4 cards and these two cards have the 
>> same failure.
>>
>> To clarify whether it is caused by hardware failure or by the lack of 
>> appropriate nic configuration, the following build options of dpdk 
>> are enabled.
>>
>> --------------
>> CONFIG_RTE_LIBRTE_ETHDEV_DEBUG=y
>> CONFIG_RTE_LIBRTE_I40E_DEBUG_INIT=y
>> CONFIG_RTE_LIBRTE_I40E_DEBUG_DRIVER=y
>> --------------
>>
>> My server box spec. is as follows :
>>
>> CPU        : Intel(R) Xeon(R) Gold 6136
>> MEMORY     : 128GB (16G x 8)
>> Motherboard: SYS-1029U-TR4
>> NIC1       : I350 x 4 (onboard nic)
>> NIC2       : XL710 dual
>> NIC3       : X710-DA4
>> NIC4       : X710-DA4
>> ------------------------------------------------------------
>> OS         : ubnutu 16.04.3 LTS(linux-image-4.4.0-87-generic)
>> DPDK       : 16.11.3
>>
>> testpmd's boot message is as follows :
>> --------------------------------------------
>> $ sudo ./testpmd -- -i
>>
>> EAL: Detected 24 lcore(s)
>> EAL: Probing VFIO support...
>> EAL: PCI device 0000:18:00.0 on NUMA socket 0
>> EAL:   probe driver: 8086:1521 net_e1000_igb
>> EAL: PCI device 0000:18:00.1 on NUMA socket 0
>> EAL:   probe driver: 8086:1521 net_e1000_igb
>> EAL: PCI device 0000:18:00.2 on NUMA socket 0
>> EAL:   probe driver: 8086:1521 net_e1000_igb
>> EAL: PCI device 0000:18:00.3 on NUMA socket 0
>> EAL:   probe driver: 8086:1521 net_e1000_igb
>> EAL: PCI device 0000:86:00.0 on NUMA socket 1
>> EAL:   probe driver: 8086:1583 net_i40e
>> EAL: PCI device 0000:86:00.1 on NUMA socket 1
>> EAL:   probe driver: 8086:1583 net_i40e
>> EAL: PCI device 0000:af:00.0 on NUMA socket 1
>> EAL:   probe driver: 8086:1572 net_i40e
>> PMD: i40e_set_symmetric_hash_enable_per_port(): Symmetric hash has 
>> already been disabled
>> PMD: eth_i40e_dev_init(): FW 5.0 API 1.5 NVM 05.00.05 eetrack 
>> 80002919
>> PMD: i40e_update_default_filter_setting(): Cannot remove the default 
>> macvlan filter
>> PMD: i40e_pf_setup(): i40e_vsi_setup finished
>> PMD: i40e_pf_setup(): Hardware capability of hash lookup table size: 
>> 512
>>
>> PMD: i40e_update_flow_control(): Link auto negotiation not completed
>> EAL: PCI device 0000:af:00.1 on NUMA socket 1
>> EAL:   probe driver: 8086:1572 net_i40e
>> EAL: PCI device 0000:af:00.2 on NUMA socket 1
>> EAL:   probe driver: 8086:1572 net_i40e
>> PMD: i40e_set_symmetric_hash_enable_per_port(): Symmetric hash has 
>> already been disabled
>> PMD: eth_i40e_dev_init(): FW 5.0 API 1.5 NVM 05.00.05 eetrack 
>> 80002919
>> PMD: validate_tcmap_parameter(): Enabled TC map 0x80 not applicable 
>> to HW support 0x1
>> PMD: i40e_vsi_setup(): Failed to update TC bandwidth
>> PMD: i40e_pf_setup(): Setup of main vsi failed
>> PMD: eth_i40e_dev_init(): Failed to setup pf switch: -63
>> rte_eth_dev_pci_probe: driver net_i40e: eth_dev_init(vendor_id=0x8086
>> device_id=0x1572) failed
>> EAL: Error - exiting with code: 1
>>      Cause: Requested device 0000:af:00.2 cannot be used
>> ---------------------------
>>
>> If you have solutions, could you tell me how this problem can be resolved ?
>>
>> Regards,
>> Hitoshi
>>
>>

  reply	other threads:[~2019-12-20 13:53 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-08-23 19:54 Aaron Hughes
2018-08-23 22:25 ` Hitoshi Masutani
2018-08-24 16:55 ` Aaron Hughes
2019-12-20 13:53   ` Ananda Sathyanarayana [this message]
  -- strict thread matches above, loose matches on Subject: below --
2018-03-23  5:50 Hitoshi Masutani

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=CY4PR11MB0054F6DCC49438DEF835E87EE32D0@CY4PR11MB0054.namprd11.prod.outlook.com \
    --to=ananda@versa-networks.com \
    --cc=hughesac@gmail.com \
    --cc=masutani.hitoshi@lab.ntt.co.jp \
    --cc=users@dpdk.org \
    --cc=vigc@versa-networks.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).