DPDK usage discussions
 help / color / mirror / Atom feed
From: Tal Shnaiderman <talshn@nvidia.com>
To: Robert Hable <Robert.Hable@spusu.at>,
	Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>,
	Ophir Munk <ophirmu@nvidia.com>
Cc: "users@dpdk.org" <users@dpdk.org>,
	Adham Masarwah <adham@nvidia.com>,
	Idan Hackmon <idanhac@nvidia.com>,
	Eilon Greenstein <eilong@nvidia.com>
Subject: RE: Windows examples failed to start using mellanox card
Date: Tue, 26 Jul 2022 14:14:10 +0000	[thread overview]
Message-ID: <MW4PR12MB566893C165F607975BDE148DA4949@MW4PR12MB5668.namprd12.prod.outlook.com> (raw)
In-Reply-To: <PAXP190MB174181FC9041CB1B5E4080C5E1899@PAXP190MB1741.EURP190.PROD.OUTLOOK.COM>

Hi Robert,

I investigated the reason you're getting the error message: it's a result of a PMD query unsupported by devices lower than ConnectX-6 however has no functional affect since the PMD behaves differently on those devices. 

I'll work on a patch lower the severity of this message as I understand it is confusing, for now you can continue working with the PMD and ignore this message.

Thanks for your help,

Tal.

> -----Original Message-----
> From: Robert Hable <Robert.Hable@spusu.at>
> Sent: Wednesday, July 13, 2022 10:58 AM
> To: Tal Shnaiderman <talshn@nvidia.com>; Dmitry Kozlyuk
> <dmitry.kozliuk@gmail.com>; Ophir Munk <ophirmu@nvidia.com>
> Cc: users@dpdk.org; Adham Masarwah <adham@nvidia.com>; Idan Hackmon
> <idanhac@nvidia.com>; Eilon Greenstein <eilong@nvidia.com>
> Subject: AW: Windows examples failed to start using mellanox card
> 
> External email: Use caution opening links or attachments
> 
> 
> Hello,
> 
> I am using dpdk on a regular machine without any VMs. Here are the device
> information from the device manager:
> Driver Version : 2.90.25506.0
> Firmware Version : 14.32.1010
> Port Number : 2
> Bus Type : PCI-E 5.0 GT/s x8
> Link Speed : 1.0 Gbps/Full Duplex
> Part Number : MCX4121A-XCAT
> Serial Number : MT1802K30345
> Device Id : 4117
> Revision Id : 0
> Current MAC Address : EC-0D-9A-D9-AA-43
> Permanent MAC Address : EC-0D-9A-D9-AA-43 Network Status : Connected
> Adapter Friendly Name : Ethernet 6 Port Type : ETH
> IPv4 Address #1 : 172.21.2.114
> IPv6 Address #1 : fe80::e14a:1ee5:54f6:b76d%2
> 
> Let me know if you need additional information.
> 
> Kind regards,
> Robert
> 
> -----Ursprüngliche Nachricht-----
> Von: Tal Shnaiderman <talshn@nvidia.com>
> Gesendet: Dienstag, 12. Juli 2022 16:36
> An: Robert Hable <robert.hable@massresponse.com>; Dmitry Kozlyuk
> <dmitry.kozliuk@gmail.com>; Ophir Munk <ophirmu@nvidia.com>
> Cc: users@dpdk.org; Adham Masarwah <adham@nvidia.com>; Idan Hackmon
> <idanhac@nvidia.com>; Eilon Greenstein <eilong@nvidia.com>
> Betreff: RE: Windows examples failed to start using mellanox card
> 
> Hi Robert,
> 
> I'm glad to hear the issue is resolved, but I still want to understand why you get
> the error print as I'm not able to reproduce it on my side.
> 
> Are you using a Virtual Machine or is it a back-to-back setup? Can you also state
> the WINOF2 FW version you're using?
> 
> Thanks,
> 
> Tal.
> 
> > -----Original Message-----
> > From: Robert Hable <robert.hable@massresponse.com>
> > Sent: Tuesday, July 12, 2022 5:03 PM
> > To: Tal Shnaiderman <talshn@nvidia.com>; Dmitry Kozlyuk
> > <dmitry.kozliuk@gmail.com>; Ophir Munk <ophirmu@nvidia.com>
> > Cc: users@dpdk.org
> > Subject: AW: Windows examples failed to start using mellanox card
> >
> > External email: Use caution opening links or attachments
> >
> >
> > Hello,
> >
> > thank you for your help!
> > Initially i did set DevxFsRules to 0. After setting it to 0xFFFFFF it now works.
> > I still get the following error but testpmd seems to work for me now
> > as it is sending and receiving packets according to the task-manager.
> >         mlx5_common: DevX read access NIC register=0X9055 failed
> > errno=0
> > status=0 syndrome=0
> >
> > So currently my issue seems to be solved.
> >
> > Kind regards,
> > Robert
> >
> > -----Ursprüngliche Nachricht-----
> > Von: Tal Shnaiderman <talshn@nvidia.com>
> > Gesendet: Dienstag, 12. Juli 2022 12:24
> > An: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>; Ophir Munk
> > <ophirmu@nvidia.com>; Robert Hable <robert.hable@massresponse.com>
> > Cc: users@dpdk.org
> > Betreff: RE: Windows examples failed to start using mellanox card
> >
> > Small correction, please try with the value 0xFFFFFF.
> >
> > > Subject: RE: Windows examples failed to start using mellanox card
> > >
> > > Hi Robert,
> > >
> > > Did you set the registry key (DevxFsRules) in the Windows registry?
> > >
> > > https://docs.nvidia.com/networking/display/winof2v290/Configuring+th
> > > e+
> > > Drive
> > > r+Registry+Keys
> > >
> > > If not, can you try setting it to the value (0xFFFFFFFF) and see it
> > > the issue still occurs after adapter restart?
> > >
> > > Thanks,
> > >
> > > Tal.
> > >
> > > > Subject: Re: Windows examples failed to start using mellanox card
> > > >
> > > > External email: Use caution opening links or attachments
> > > >
> > > >
> > > > Tal, Ophir, could you advise?
> > > >
> > > > 2022-07-11 14:10 (UTC+0000), Robert Hable:
> > > > > Hello,
> > > > >
> > > > > I am having trouble running DPDK on Windows. I am trying to use
> > > > > the
> > > > example programs and testpmd, but they fail with some errors (see
> > > > outputs below). The testpmd program also does not go into
> > > > interactive mode and exits after a keypress.
> > > > > I am using Windows Server 2022 with a Mellanox ConnectX-4 LX
> > > > > Card using
> > > > Win-OF 2 2.90.50010 / SDK 2.90.25518.
> > > > > I am using the current build (DPDK Version 22.07-rc3).
> > > > >
> > > > > I followed to DPDK Windows guide, but currently I always get the
> > > > > following
> > > > error:
> > > > > mlx5_common: DevX read access NIC register=0X9055 failed errno=0
> > > > > status=0 syndrome=0
> > > > >
> > > > > does anybody have an idea how to resolve this problem, or at
> > > > > least get
> > > > some more information why it failed?
> > > > > Helloworld output:
> > > > > C:\dpdk\build\examples>dpdk-helloworld.exe
> > > > > EAL: Detected CPU lcores: 24
> > > > > EAL: Detected NUMA nodes: 2
> > > > > EAL: Multi-process support is requested, but not available.
> > > > > EAL: Probe PCI driver: mlx5_pci (15b3:1015) device: 0000:06:00.0
> > > > > (socket 0)
> > > > > mlx5_common: DevX read access NIC register=0X9055 failed errno=0
> > > > > status=0 syndrome=0
> > > > > mlx5_net: mlx5_os_dev_shared_handler_install: is not supported
> > > > > mlx5_net: Rx CQE 128B compression is not supported.
> > > > > EAL: Probe PCI driver: mlx5_pci (15b3:1015) device: 0000:06:00.1
> > > > > (socket 0)
> > > > > mlx5_common: DevX read access NIC register=0X9055 failed errno=0
> > > > > status=0 syndrome=0
> > > > > mlx5_net: mlx5_os_dev_shared_handler_install: is not supported
> > > > > mlx5_net: Rx CQE 128B compression is not supported.
> > > > > hello from core 1
> > > > > hello from core 2
> > > > > hello from core 3
> > > > > hello from core 4
> > > > > hello from core 5
> > > > > hello from core 6
> > > > > hello from core 7
> > > > > hello from core 8
> > > > > hello from core 16
> > > > > hello from core 22
> > > > > hello from core 11
> > > > > hello from core 12
> > > > > hello from core 13
> > > > > hello from core 14
> > > > > hello from core 15
> > > > > hello from core 9
> > > > > hello from core 17
> > > > > hello from core 18
> > > > > hello from core 19
> > > > > hello from core 20
> > > > > hello from core 21
> > > > > hello from core 23
> > > > > hello from core 0
> > > > > hello from core 10
> > > > >
> > > > > testpmd output:
> > > > > C:\dpdk\build\app>dpdk-testpmd.exe
> > > > > EAL: Detected CPU lcores: 24
> > > > > EAL: Detected NUMA nodes: 2
> > > > > EAL: Multi-process support is requested, but not available.
> > > > > EAL: Probe PCI driver: mlx5_pci (15b3:1015) device: 0000:06:00.0
> > > > > (socket 0)
> > > > > mlx5_common: DevX read access NIC register=0X9055 failed errno=0
> > > > > status=0 syndrome=0
> > > > > mlx5_net: mlx5_os_dev_shared_handler_install: is not supported
> > > > > mlx5_net: Rx CQE 128B compression is not supported.
> > > > > EAL: Probe PCI driver: mlx5_pci (15b3:1015) device: 0000:06:00.1
> > > > > (socket 0)
> > > > > mlx5_common: DevX read access NIC register=0X9055 failed errno=0
> > > > > status=0 syndrome=0
> > > > > mlx5_net: mlx5_os_dev_shared_handler_install: is not supported
> > > > > mlx5_net: Rx CQE 128B compression is not supported.
> > > > > testpmd: create a new mbuf pool <mb_pool_0>: n=331456,
> > > > > size=2176,
> > > > > socket=0
> > > > > testpmd: preferred mempool ops selected: ring_mp_mc
> > > > > testpmd: create a new mbuf pool <mb_pool_1>: n=331456,
> > > > > size=2176,
> > > > > socket=1
> > > > > testpmd: preferred mempool ops selected: ring_mp_mc Configuring
> > > > > Port
> > > > > 0 (socket 0)
> > > > > mlx5_net: port 0 failed to set defaults flows Fail to start port 0:
> > > > > Invalid argument Configuring Port 1 (socket 0)
> > > > > mlx5_net: port 1 failed to set defaults flows Fail to start port 1:
> > > > > Invalid argument Please stop the ports first Done No commandline
> > > > > core given, start packet forwarding Not all ports were started
> > > > > Press enter to exit
> > > > >
> > > > >
> > > > > Stopping port 0...
> > > > > Stopping ports...
> > > > > Done
> > > > >
> > > > > Stopping port 1...
> > > > > Stopping ports...
> > > > > Done
> > > > >
> > > > > Shutting down port 0...
> > > > > Closing ports...
> > > > > mlx5_net: mlx5_os_dev_shared_handler_uninstall: is not supported
> > > > > Port
> > > > > 0 is closed Done
> > > > >
> > > > > Shutting down port 1...
> > > > > Closing ports...
> > > > > mlx5_net: mlx5_os_dev_shared_handler_uninstall: is not supported
> > > > > Port
> > > > > 1 is closed Done
> > > > >
> > > > > Bye...
> > > > >
> > > > > Kind regards,
> > > > > Robert


      reply	other threads:[~2022-07-26 14:14 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-11 14:10 Robert Hable
2022-07-12  8:27 ` Dmitry Kozlyuk
2022-07-12  8:43   ` Tal Shnaiderman
2022-07-12 10:23     ` Tal Shnaiderman
2022-07-12 14:03       ` AW: " Robert Hable
2022-07-12 14:35         ` Tal Shnaiderman
2022-07-13  7:57           ` AW: " Robert Hable
2022-07-26 14:14             ` Tal Shnaiderman [this message]

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=MW4PR12MB566893C165F607975BDE148DA4949@MW4PR12MB5668.namprd12.prod.outlook.com \
    --to=talshn@nvidia.com \
    --cc=Robert.Hable@spusu.at \
    --cc=adham@nvidia.com \
    --cc=dmitry.kozliuk@gmail.com \
    --cc=eilong@nvidia.com \
    --cc=idanhac@nvidia.com \
    --cc=ophirmu@nvidia.com \
    --cc=users@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).