DPDK usage discussions
 help / color / mirror / Atom feed
* net_mlx5: unable to recognize master/representors on the multiple IB devices
@ 2022-01-14 10:10 Rocio Dominguez
  2022-01-16 13:23 ` Thomas Monjalon
  0 siblings, 1 reply; 15+ messages in thread
From: Rocio Dominguez @ 2022-01-14 10:10 UTC (permalink / raw)
  To: users

[-- Attachment #1: Type: text/plain, Size: 5919 bytes --]

Hi,

I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.

I'm using:

OS SLES 15 SP2
DPDK 19.11.4 (the official supported version for SLES 15 SP2)
MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
Mellanox adapters firmware 12.28.2006 (corresponding to this MLNX_OFED version)
kernel 5.3.18-24.34-default


This is my SRIOV configuration for DPDK capable PCI slots:

            {
                "resourceName": "mlnx_sriov_netdevice",
                "resourcePrefix": "mellanox.com",
                "isRdma": true,
                "selectors": {
                    "vendors": ["15b3"],
                    "devices": ["1014"],
                    "drivers": ["mlx5_core"],
                    "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3", "0000:d8:00.4", "0000:d8:00.5"],
                    "isRdma": true
                }

The sriov device plugin starts without problems, the devices are correctly allocated:

{
  "cpu": "92",
  "ephemeral-storage": "419533922385",
  "hugepages-1Gi": "8Gi",
  "hugepages-2Mi": "4Gi",
  "intel.com/intel_sriov_dpdk": "0",
  "intel.com/sriov_cre": "3",
  "mellanox.com/mlnx_sriov_netdevice": "4",
  "mellanox.com/sriov_dp": "0",
  "memory": "183870336Ki",
  "pods": "110"
}

The Mellanox NICs are binded to the kernel driver mlx5_core:

pcgwpod009-c04:~ # dpdk-devbind --status

Network devices using kernel driver
===================================
0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe unused=vfio-pci
0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe unused=vfio-pci
0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe unused=vfio-pci
0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe unused=vfio-pci
0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0 drv=mlx5_core unused=vfio-pci
0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1 drv=mlx5_core unused=vfio-pci
0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p1 drv=ixgbe unused=vfio-pci
0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p2 drv=ixgbe unused=vfio-pci
0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci
0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_1 drv=ixgbevf unused=vfio-pci
0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci
0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_3 drv=ixgbevf unused=vfio-pci
0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p1 drv=ixgbe unused=vfio-pci
0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p2 drv=ixgbe unused=vfio-pci
0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0 drv=mlx5_core unused=vfio-pci
0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1 drv=mlx5_core unused=vfio-pci
0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014' if=enp216s0f2 drv=mlx5_core unused=vfio-pci
0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014' if=enp216s0f3 drv=mlx5_core unused=vfio-pci
0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014' if=enp216s0f4 drv=mlx5_core unused=vfio-pci
0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014' if=enp216s0f5 drv=mlx5_core unused=vfio-pci

The interfaces are up:

pcgwpod009-c04:~ # ibdev2netdev -v
0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4 QSFP28 fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4 QSFP28 fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4 QSFP28 fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4 QSFP28 fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f2 (Up)
0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f3 (Up)
0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f4 (Up)
0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f5 (Up)
pcgwpod009-c04:~ #


But when I run my application the Mellanox adapters are probed and I obtain the following error:

{"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
{"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] net_mlx5: unable to recognize master/representors on the multiple IB devices"}
{"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}
{"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be used"}
{"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Bus (pci) probe failed."}
{"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}
{"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] No network ports could be enabled!"}

Could you please help me with this issue?


Thanks,

Rocío

[-- Attachment #2: Type: text/html, Size: 14457 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-01-14 10:10 net_mlx5: unable to recognize master/representors on the multiple IB devices Rocio Dominguez
@ 2022-01-16 13:23 ` Thomas Monjalon
  2022-01-16 15:30   ` Asaf Penso
  0 siblings, 1 reply; 15+ messages in thread
From: Thomas Monjalon @ 2022-01-16 13:23 UTC (permalink / raw)
  To: Rocio Dominguez; +Cc: users, matan, viacheslavo, rasland

+Cc mlx5 experts


14/01/2022 11:10, Rocio Dominguez:
> Hi,
> 
> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
> 
> I'm using:
> 
> OS SLES 15 SP2
> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
> Mellanox adapters firmware 12.28.2006 (corresponding to this MLNX_OFED version)
> kernel 5.3.18-24.34-default
> 
> 
> This is my SRIOV configuration for DPDK capable PCI slots:
> 
>             {
>                 "resourceName": "mlnx_sriov_netdevice",
>                 "resourcePrefix": "mellanox.com",
>                 "isRdma": true,
>                 "selectors": {
>                     "vendors": ["15b3"],
>                     "devices": ["1014"],
>                     "drivers": ["mlx5_core"],
>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3", "0000:d8:00.4", "0000:d8:00.5"],
>                     "isRdma": true
>                 }
> 
> The sriov device plugin starts without problems, the devices are correctly allocated:
> 
> {
>   "cpu": "92",
>   "ephemeral-storage": "419533922385",
>   "hugepages-1Gi": "8Gi",
>   "hugepages-2Mi": "4Gi",
>   "intel.com/intel_sriov_dpdk": "0",
>   "intel.com/sriov_cre": "3",
>   "mellanox.com/mlnx_sriov_netdevice": "4",
>   "mellanox.com/sriov_dp": "0",
>   "memory": "183870336Ki",
>   "pods": "110"
> }
> 
> The Mellanox NICs are binded to the kernel driver mlx5_core:
> 
> pcgwpod009-c04:~ # dpdk-devbind --status
> 
> Network devices using kernel driver
> ===================================
> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe unused=vfio-pci
> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe unused=vfio-pci
> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe unused=vfio-pci
> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe unused=vfio-pci
> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0 drv=mlx5_core unused=vfio-pci
> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1 drv=mlx5_core unused=vfio-pci
> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p1 drv=ixgbe unused=vfio-pci
> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p2 drv=ixgbe unused=vfio-pci
> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci
> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_1 drv=ixgbevf unused=vfio-pci
> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci
> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_3 drv=ixgbevf unused=vfio-pci
> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p1 drv=ixgbe unused=vfio-pci
> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p2 drv=ixgbe unused=vfio-pci
> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0 drv=mlx5_core unused=vfio-pci
> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1 drv=mlx5_core unused=vfio-pci
> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014' if=enp216s0f2 drv=mlx5_core unused=vfio-pci
> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014' if=enp216s0f3 drv=mlx5_core unused=vfio-pci
> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014' if=enp216s0f4 drv=mlx5_core unused=vfio-pci
> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014' if=enp216s0f5 drv=mlx5_core unused=vfio-pci
> 
> The interfaces are up:
> 
> pcgwpod009-c04:~ # ibdev2netdev -v
> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4 QSFP28 fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4 QSFP28 fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4 QSFP28 fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4 QSFP28 fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f2 (Up)
> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f3 (Up)
> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f4 (Up)
> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f5 (Up)
> pcgwpod009-c04:~ #
> 
> 
> But when I run my application the Mellanox adapters are probed and I obtain the following error:
> 
> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] net_mlx5: unable to recognize master/representors on the multiple IB devices"}
> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}
> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be used"}
> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Bus (pci) probe failed."}
> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}
> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] No network ports could be enabled!"}
> 
> Could you please help me with this issue?
> 
> 
> Thanks,
> 
> Rocío
> 






^ permalink raw reply	[flat|nested] 15+ messages in thread

* RE: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-01-16 13:23 ` Thomas Monjalon
@ 2022-01-16 15:30   ` Asaf Penso
  2022-01-17 20:20     ` Rocio Dominguez
  0 siblings, 1 reply; 15+ messages in thread
From: Asaf Penso @ 2022-01-16 15:30 UTC (permalink / raw)
  To: NBU-Contact-Thomas Monjalon (EXTERNAL), Rocio Dominguez
  Cc: users, Matan Azrad, Slava Ovsiienko, Raslan Darawsheh

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com>
>Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko
><viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
>Subject: Re: net_mlx5: unable to recognize master/representors on the
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one) Mellanox
>> adapters firmware 12.28.2006 (corresponding to this MLNX_OFED version)
>> kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3", "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk": "0",
>>   "intel.com/sriov_cre": "3",
>>   "mellanox.com/mlnx_sriov_netdevice": "4",
>>   "mellanox.com/sriov_dp": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severi
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize
>> master/representors on the multiple IB devices"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severi
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severi
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
>> used"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","severi
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","severi
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
>> actual 0 ports."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","severi
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>


^ permalink raw reply	[flat|nested] 15+ messages in thread

* RE: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-01-16 15:30   ` Asaf Penso
@ 2022-01-17 20:20     ` Rocio Dominguez
  2022-01-20  7:16       ` Asaf Penso
  0 siblings, 1 reply; 15+ messages in thread
From: Rocio Dominguez @ 2022-01-17 20:20 UTC (permalink / raw)
  To: Asaf Penso, NBU-Contact-Thomas Monjalon (EXTERNAL)
  Cc: users, Matan Azrad, Slava Ovsiienko, Raslan Darawsheh

Hi Asaf,

Thanks for the prompt answer.

I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE repositories the corresponding RPM package for SLES 15 SP2 is not available, the latest one is DPDK 19.11.10.

I have installed it but the problem persists. It's probably solved in 19.11.11.

There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also, not sure if it could be a problem to install it in SLES 15 SP2. I will try it anyway.

Also I will try to find other way to load the 19.11.11 in SLES 15 SP2 apart from using RPM or zipper, any suggestion is appreciated.

Thanks,

Rocío

-----Original Message-----
From: Asaf Penso <asafp@nvidia.com> 
Sent: Sunday, January 16, 2022 4:31 PM
To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>; Rocio Dominguez <rocio.dominguez@ericsson.com>
Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com>
>Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko 
><viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
>Subject: Re: net_mlx5: unable to recognize master/representors on the 
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one) 
>> Mellanox adapters firmware 12.28.2006 (corresponding to this 
>> MLNX_OFED version) kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3", 
>> "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are 
>> correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk": "0",
>>   "intel.com/sriov_cre": "3",
>>   "mellanox.com/mlnx_sriov_netdevice": "4",
>>   "mellanox.com/sriov_dp": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe 
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe 
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe 
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe 
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0 
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1 
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if= 
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if= 
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0 
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1 
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"} 
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize 
>> master/representors on the multiple IB devices"} 
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver = 
>> net_mlx5."} 
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be 
>> used"} 
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."} 
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, 
>> actual 0 ports."} 
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i 
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be 
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>

^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-01-17 20:20     ` Rocio Dominguez
@ 2022-01-20  7:16       ` Asaf Penso
  2022-01-20 19:48         ` Rocio Dominguez
  0 siblings, 1 reply; 15+ messages in thread
From: Asaf Penso @ 2022-01-20  7:16 UTC (permalink / raw)
  To: Rocio Dominguez, NBU-Contact-Thomas Monjalon (EXTERNAL)
  Cc: users, Matan Azrad, Slava Ovsiienko, Raslan Darawsheh

[-- Attachment #1: Type: text/plain, Size: 8872 bytes --]

Although inbox drivers come with a pre installed DPDK, you can manually download, compile, install, and work with whatever version you wish.

Let us know the results, and we'll continue from there.

Regards,
Asaf Penso
________________________________
From: Rocio Dominguez <rocio.dominguez@ericsson.com>
Sent: Monday, January 17, 2022 10:20:58 PM
To: Asaf Penso <asafp@nvidia.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>
Cc: users@dpdk.org <users@dpdk.org>; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hi Asaf,

Thanks for the prompt answer.

I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE repositories the corresponding RPM package for SLES 15 SP2 is not available, the latest one is DPDK 19.11.10.

I have installed it but the problem persists. It's probably solved in 19.11.11.

There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also, not sure if it could be a problem to install it in SLES 15 SP2. I will try it anyway.

Also I will try to find other way to load the 19.11.11 in SLES 15 SP2 apart from using RPM or zipper, any suggestion is appreciated.

Thanks,

Rocío

-----Original Message-----
From: Asaf Penso <asafp@nvidia.com>
Sent: Sunday, January 16, 2022 4:31 PM
To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>; Rocio Dominguez <rocio.dominguez@ericsson.com>
Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com>
>Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko
><viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
>Subject: Re: net_mlx5: unable to recognize master/representors on the
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
>> Mellanox adapters firmware 12.28.2006 (corresponding to this
>> MLNX_OFED version) kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3",
>> "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are
>> correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk": "0",
>>   "intel.com/sriov_cre": "3",
>>   "mellanox.com/mlnx_sriov_netdevice": "4",
>>   "mellanox.com/sriov_dp": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize
>> master/representors on the multiple IB devices"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver =
>> net_mlx5."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
>> used"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
>> actual 0 ports."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>

[-- Attachment #2: Type: text/html, Size: 13777 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

* RE: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-01-20  7:16       ` Asaf Penso
@ 2022-01-20 19:48         ` Rocio Dominguez
  2022-01-31 11:49           ` Asaf Penso
  0 siblings, 1 reply; 15+ messages in thread
From: Rocio Dominguez @ 2022-01-20 19:48 UTC (permalink / raw)
  To: Asaf Penso, NBU-Contact-Thomas Monjalon (EXTERNAL)
  Cc: users, Matan Azrad, Slava Ovsiienko, Raslan Darawsheh

[-- Attachment #1: Type: text/plain, Size: 17016 bytes --]

Hi Asaf,

I have manually compile and install the DPDK 19.11.11.

Executing testpmd in the Mellanox NICs VFs where I want to run my app gives this result:

pcgwpod009-c04:~/dpdk-stable-19.11.11 # ./x86_64-native-linux-gcc/app/testpmd -l 8-15 -n 4 -w d8:00.2 -w d8:00.3 -w d8:00.4 -w d8:00.5 -- --rxq=2 --txq=2 -i
EAL: Detected 96 lcore(s)
EAL: Detected 2 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: PCI device 0000:d8:00.2 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
EAL: PCI device 0000:d8:00.3 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
EAL: PCI device 0000:d8:00.4 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
EAL: PCI device 0000:d8:00.5 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
Interactive-mode selected
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0
testpmd: preferred mempool ops selected: ring_mp_mc
testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1
testpmd: preferred mempool ops selected: ring_mp_mc
Configuring Port 0 (socket 1)
Port 0: 36:FE:F0:D2:90:27
Configuring Port 1 (socket 1)
Port 1: 72:AC:33:BF:0A:FA
Configuring Port 2 (socket 1)
Port 2: 1E:8D:81:60:43:E0
Configuring Port 3 (socket 1)
Port 3: C2:3C:EA:94:06:B4
Checking link statuses...
Done
testpmd>

But when I run my Data Plane app, the result is

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.609+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_linux_packet_mmap_setup] block_size: 67108864, frame_size: 4096, block_nr: 1, frame_nr: 16384, mem_size: 67108864"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: pci devices added: 1, vhost user devices added: 0"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_MELLANOX_COM_MLNX_SRIOV_NETDEVICE=0000:d8:00.5 found"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:00.5 --base-virtaddr=0x200000000 --iova-mode=va --legacy-mem --no-shconf "}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 96 lcore(s)"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 2 NUMA nodes"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.636+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probing VFIO support..."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: VFIO support could not be initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.567+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.5 (socket 1)"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] net_mlx5: unable to recognize master/representors on the multiple IB devices"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Requested device 0000:d8:00.5 cannot be used"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Bus (pci) probe failed."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] No network ports could be enabled!"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] libpio packet module is NOT initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] pktsock packet module is NOT initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] linux packet module is initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] tap packet module is NOT initialized"}

Any idea on what could be the problem?

Thanks,

Rocío


From: Asaf Penso <asafp@nvidia.com>
Sent: Thursday, January 20, 2022 8:17 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>
Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices

Although inbox drivers come with a pre installed DPDK, you can manually download, compile, install, and work with whatever version you wish.

Let us know the results, and we'll continue from there.

Regards,
Asaf Penso
________________________________
From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 17, 2022 10:20:58 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hi Asaf,

Thanks for the prompt answer.

I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE repositories the corresponding RPM package for SLES 15 SP2 is not available, the latest one is DPDK 19.11.10.

I have installed it but the problem persists. It's probably solved in 19.11.11.

There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also, not sure if it could be a problem to install it in SLES 15 SP2. I will try it anyway.

Also I will try to find other way to load the 19.11.11 in SLES 15 SP2 apart from using RPM or zipper, any suggestion is appreciated.

Thanks,

Rocío

-----Original Message-----
From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Sunday, January 16, 2022 4:31 PM
To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>; Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net<mailto:thomas@monjalon.net>>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
>Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko
><viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
>Subject: Re: net_mlx5: unable to recognize master/representors on the
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
>> Mellanox adapters firmware 12.28.2006 (corresponding to this
>> MLNX_OFED version) kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3",
>> "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are
>> correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk": "0",
>>   "intel.com/sriov_cre": "3",
>>   "mellanox.com/mlnx_sriov_netdevice": "4",
>>   "mellanox.com/sriov_dp": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize
>> master/representors on the multiple IB devices"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver =
>> net_mlx5."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
>> used"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
>> actual 0 ports."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>

[-- Attachment #2: Type: text/html, Size: 31566 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

* RE: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-01-20 19:48         ` Rocio Dominguez
@ 2022-01-31 11:49           ` Asaf Penso
  2022-01-31 12:01             ` Rocio Dominguez
  0 siblings, 1 reply; 15+ messages in thread
From: Asaf Penso @ 2022-01-31 11:49 UTC (permalink / raw)
  To: Rocio Dominguez, NBU-Contact-Thomas Monjalon (EXTERNAL)
  Cc: users, Matan Azrad, Slava Ovsiienko, Raslan Darawsheh

[-- Attachment #1: Type: text/plain, Size: 18258 bytes --]

I see two differences below.
First, in testpmd the version is 19.11.11, and in your application, it's 20.08. See this print:
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}

Second, in your application, I see the VFIO driver is not started properly:
20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}

Regards,
Asaf Penso

From: Rocio Dominguez <rocio.dominguez@ericsson.com>
Sent: Thursday, January 20, 2022 9:49 PM
To: Asaf Penso <asafp@nvidia.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>
Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hi Asaf,

I have manually compile and install the DPDK 19.11.11.

Executing testpmd in the Mellanox NICs VFs where I want to run my app gives this result:

pcgwpod009-c04:~/dpdk-stable-19.11.11 # ./x86_64-native-linux-gcc/app/testpmd -l 8-15 -n 4 -w d8:00.2 -w d8:00.3 -w d8:00.4 -w d8:00.5 -- --rxq=2 --txq=2 -i
EAL: Detected 96 lcore(s)
EAL: Detected 2 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: PCI device 0000:d8:00.2 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
EAL: PCI device 0000:d8:00.3 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
EAL: PCI device 0000:d8:00.4 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
EAL: PCI device 0000:d8:00.5 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
Interactive-mode selected
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0
testpmd: preferred mempool ops selected: ring_mp_mc
testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1
testpmd: preferred mempool ops selected: ring_mp_mc
Configuring Port 0 (socket 1)
Port 0: 36:FE:F0:D2:90:27
Configuring Port 1 (socket 1)
Port 1: 72:AC:33:BF:0A:FA
Configuring Port 2 (socket 1)
Port 2: 1E:8D:81:60:43:E0
Configuring Port 3 (socket 1)
Port 3: C2:3C:EA:94:06:B4
Checking link statuses...
Done
testpmd>

But when I run my Data Plane app, the result is

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.609+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_linux_packet_mmap_setup] block_size: 67108864, frame_size: 4096, block_nr: 1, frame_nr: 16384, mem_size: 67108864"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: pci devices added: 1, vhost user devices added: 0"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_MELLANOX_COM_MLNX_SRIOV_NETDEVICE=0000:d8:00.5 found"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:00.5 --base-virtaddr=0x200000000 --iova-mode=va --legacy-mem --no-shconf "}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 96 lcore(s)"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 2 NUMA nodes"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.636+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probing VFIO support..."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: VFIO support could not be initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.567+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.5 (socket 1)"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] net_mlx5: unable to recognize master/representors on the multiple IB devices"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Requested device 0000:d8:00.5 cannot be used"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Bus (pci) probe failed."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] No network ports could be enabled!"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] libpio packet module is NOT initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] pktsock packet module is NOT initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] linux packet module is initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] tap packet module is NOT initialized"}

Any idea on what could be the problem?

Thanks,

Rocío


From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Thursday, January 20, 2022 8:17 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices

Although inbox drivers come with a pre installed DPDK, you can manually download, compile, install, and work with whatever version you wish.

Let us know the results, and we'll continue from there.

Regards,
Asaf Penso
________________________________
From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 17, 2022 10:20:58 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hi Asaf,

Thanks for the prompt answer.

I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE repositories the corresponding RPM package for SLES 15 SP2 is not available, the latest one is DPDK 19.11.10.

I have installed it but the problem persists. It's probably solved in 19.11.11.

There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also, not sure if it could be a problem to install it in SLES 15 SP2. I will try it anyway.

Also I will try to find other way to load the 19.11.11 in SLES 15 SP2 apart from using RPM or zipper, any suggestion is appreciated.

Thanks,

Rocío

-----Original Message-----
From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Sunday, January 16, 2022 4:31 PM
To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>; Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net<mailto:thomas@monjalon.net>>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
>Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko
><viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
>Subject: Re: net_mlx5: unable to recognize master/representors on the
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
>> Mellanox adapters firmware 12.28.2006 (corresponding to this
>> MLNX_OFED version) kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3",
>> "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are
>> correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk": "0",
>>   "intel.com/sriov_cre": "3",
>>   "mellanox.com/mlnx_sriov_netdevice": "4",
>>   "mellanox.com/sriov_dp": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize
>> master/representors on the multiple IB devices"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver =
>> net_mlx5."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
>> used"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
>> actual 0 ports."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>

[-- Attachment #2: Type: text/html, Size: 33975 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

* RE: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-01-31 11:49           ` Asaf Penso
@ 2022-01-31 12:01             ` Rocio Dominguez
  2022-01-31 17:02               ` Asaf Penso
  0 siblings, 1 reply; 15+ messages in thread
From: Rocio Dominguez @ 2022-01-31 12:01 UTC (permalink / raw)
  To: Asaf Penso, NBU-Contact-Thomas Monjalon (EXTERNAL)
  Cc: users, Matan Azrad, Slava Ovsiienko, Raslan Darawsheh

[-- Attachment #1: Type: text/plain, Size: 19528 bytes --]

Hi Asaf,

Yes, it seems that DPDK version 20.08 code is built-in with the VNF I'm deploying, so it is always using this version, which apparently doesn't have the patch that overrides this error.

I think the patch is the following:
https://patches.dpdk.org/project/dpdk/patch/20200603150602.4686-7-ophirmu@mellanox.com/

and the code part that solves the error is:
+       if (mlx5_class_get(pci_dev->device.devargs) != MLX5_CLASS_NET) {
+                DRV_LOG(DEBUG, "Skip probing - should be probed by other mlx5"
+                        " driver.");
+                return 1;
+       }
Could you please confirm?

Thanks,

Rocío

From: Asaf Penso <asafp@nvidia.com>
Sent: Monday, January 31, 2022 12:49 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>
Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

I see two differences below.
First, in testpmd the version is 19.11.11, and in your application, it's 20.08. See this print:
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}

Second, in your application, I see the VFIO driver is not started properly:
20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}

Regards,
Asaf Penso

From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Thursday, January 20, 2022 9:49 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hi Asaf,

I have manually compile and install the DPDK 19.11.11.

Executing testpmd in the Mellanox NICs VFs where I want to run my app gives this result:

pcgwpod009-c04:~/dpdk-stable-19.11.11 # ./x86_64-native-linux-gcc/app/testpmd -l 8-15 -n 4 -w d8:00.2 -w d8:00.3 -w d8:00.4 -w d8:00.5 -- --rxq=2 --txq=2 -i
EAL: Detected 96 lcore(s)
EAL: Detected 2 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: PCI device 0000:d8:00.2 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
EAL: PCI device 0000:d8:00.3 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
EAL: PCI device 0000:d8:00.4 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
EAL: PCI device 0000:d8:00.5 on NUMA socket 1
EAL:   probe driver: 15b3:1014 net_mlx5
Interactive-mode selected
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0
testpmd: preferred mempool ops selected: ring_mp_mc
testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1
testpmd: preferred mempool ops selected: ring_mp_mc
Configuring Port 0 (socket 1)
Port 0: 36:FE:F0:D2:90:27
Configuring Port 1 (socket 1)
Port 1: 72:AC:33:BF:0A:FA
Configuring Port 2 (socket 1)
Port 2: 1E:8D:81:60:43:E0
Configuring Port 3 (socket 1)
Port 3: C2:3C:EA:94:06:B4
Checking link statuses...
Done
testpmd>

But when I run my Data Plane app, the result is

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.609+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_linux_packet_mmap_setup] block_size: 67108864, frame_size: 4096, block_nr: 1, frame_nr: 16384, mem_size: 67108864"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: pci devices added: 1, vhost user devices added: 0"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_MELLANOX_COM_MLNX_SRIOV_NETDEVICE=0000:d8:00.5 found"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:00.5 --base-virtaddr=0x200000000 --iova-mode=va --legacy-mem --no-shconf "}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 96 lcore(s)"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 2 NUMA nodes"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.636+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probing VFIO support..."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: VFIO support could not be initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.567+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.5 (socket 1)"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] net_mlx5: unable to recognize master/representors on the multiple IB devices"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Requested device 0000:d8:00.5 cannot be used"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Bus (pci) probe failed."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] No network ports could be enabled!"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] libpio packet module is NOT initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] pktsock packet module is NOT initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] linux packet module is initialized"}
{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] tap packet module is NOT initialized"}

Any idea on what could be the problem?

Thanks,

Rocío


From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Thursday, January 20, 2022 8:17 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices

Although inbox drivers come with a pre installed DPDK, you can manually download, compile, install, and work with whatever version you wish.

Let us know the results, and we'll continue from there.

Regards,
Asaf Penso
________________________________
From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 17, 2022 10:20:58 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hi Asaf,

Thanks for the prompt answer.

I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE repositories the corresponding RPM package for SLES 15 SP2 is not available, the latest one is DPDK 19.11.10.

I have installed it but the problem persists. It's probably solved in 19.11.11.

There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also, not sure if it could be a problem to install it in SLES 15 SP2. I will try it anyway.

Also I will try to find other way to load the 19.11.11 in SLES 15 SP2 apart from using RPM or zipper, any suggestion is appreciated.

Thanks,

Rocío

-----Original Message-----
From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Sunday, January 16, 2022 4:31 PM
To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>; Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net<mailto:thomas@monjalon.net>>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
>Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko
><viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
>Subject: Re: net_mlx5: unable to recognize master/representors on the
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
>> Mellanox adapters firmware 12.28.2006 (corresponding to this
>> MLNX_OFED version) kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3",
>> "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are
>> correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk": "0",
>>   "intel.com/sriov_cre": "3",
>>   "mellanox.com/mlnx_sriov_netdevice": "4",
>>   "mellanox.com/sriov_dp": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize
>> master/representors on the multiple IB devices"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver =
>> net_mlx5."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
>> used"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
>> actual 0 ports."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>

[-- Attachment #2: Type: text/html, Size: 38237 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-01-31 12:01             ` Rocio Dominguez
@ 2022-01-31 17:02               ` Asaf Penso
  2022-02-03 10:30                 ` Rocio Dominguez
  0 siblings, 1 reply; 15+ messages in thread
From: Asaf Penso @ 2022-01-31 17:02 UTC (permalink / raw)
  To: Rocio Dominguez, NBU-Contact-Thomas Monjalon (EXTERNAL)
  Cc: users, Matan Azrad, Slava Ovsiienko, Raslan Darawsheh

[-- Attachment #1: Type: text/plain, Size: 20371 bytes --]

We'll need to check, but how do you want to proceed?
You either need 19.11 LTS or 20.11 LTS to work properly.

Regards,
Asaf Penso
________________________________
From: Rocio Dominguez <rocio.dominguez@ericsson.com>
Sent: Monday, January 31, 2022 2:01:43 PM
To: Asaf Penso <asafp@nvidia.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>
Cc: users@dpdk.org <users@dpdk.org>; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices


Hi Asaf,



Yes, it seems that DPDK version 20.08 code is built-in with the VNF I’m deploying, so it is always using this version, which apparently doesn’t have the patch that overrides this error.



I think the patch is the following:

https://patches.dpdk.org/project/dpdk/patch/20200603150602.4686-7-ophirmu@mellanox.com/



and the code part that solves the error is:

+       if (mlx5_class_get(pci_dev->device.devargs) != MLX5_CLASS_NET) {

+                DRV_LOG(DEBUG, "Skip probing - should be probed by other mlx5"

+                        " driver.");

+                return 1;

+       }

Could you please confirm?



Thanks,



Rocío



From: Asaf Penso <asafp@nvidia.com>
Sent: Monday, January 31, 2022 12:49 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>
Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



I see two differences below.

First, in testpmd the version is 19.11.11, and in your application, it’s 20.08. See this print:

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}



Second, in your application, I see the VFIO driver is not started properly:

20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}



Regards,

Asaf Penso



From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Thursday, January 20, 2022 9:49 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,



I have manually compile and install the DPDK 19.11.11.



Executing testpmd in the Mellanox NICs VFs where I want to run my app gives this result:



pcgwpod009-c04:~/dpdk-stable-19.11.11 # ./x86_64-native-linux-gcc/app/testpmd -l 8-15 -n 4 -w d8:00.2 -w d8:00.3 -w d8:00.4 -w d8:00.5 -- --rxq=2 --txq=2 -i

EAL: Detected 96 lcore(s)

EAL: Detected 2 NUMA nodes

EAL: Multi-process socket /var/run/dpdk/rte/mp_socket

EAL: Selected IOVA mode 'VA'

EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size

EAL: Probing VFIO support...

EAL: VFIO support initialized

EAL: PCI device 0000:d8:00.2 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.3 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.4 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.5 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

Interactive-mode selected

testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0

testpmd: preferred mempool ops selected: ring_mp_mc

testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1

testpmd: preferred mempool ops selected: ring_mp_mc

Configuring Port 0 (socket 1)

Port 0: 36:FE:F0:D2:90:27

Configuring Port 1 (socket 1)

Port 1: 72:AC:33:BF:0A:FA

Configuring Port 2 (socket 1)

Port 2: 1E:8D:81:60:43:E0

Configuring Port 3 (socket 1)

Port 3: C2:3C:EA:94:06:B4

Checking link statuses...

Done

testpmd>



But when I run my Data Plane app, the result is



{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.609+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_linux_packet_mmap_setup] block_size: 67108864, frame_size: 4096, block_nr: 1, frame_nr: 16384, mem_size: 67108864"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: pci devices added: 1, vhost user devices added: 0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_MELLANOX_COM_MLNX_SRIOV_NETDEVICE=0000:d8:00.5 found"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:00.5 --base-virtaddr=0x200000000 --iova-mode=va --legacy-mem --no-shconf "}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 96 lcore(s)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 2 NUMA nodes"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.636+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probing VFIO support..."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: VFIO support could not be initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.567+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.5 (socket 1)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] net_mlx5: unable to recognize master/representors on the multiple IB devices"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Requested device 0000:d8:00.5 cannot be used"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Bus (pci) probe failed."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] No network ports could be enabled!"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] libpio packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] pktsock packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] linux packet module is initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] tap packet module is NOT initialized"}



Any idea on what could be the problem?



Thanks,



Rocío





From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Thursday, January 20, 2022 8:17 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices



Although inbox drivers come with a pre installed DPDK, you can manually download, compile, install, and work with whatever version you wish.



Let us know the results, and we'll continue from there.



Regards,

Asaf Penso

________________________________

From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 17, 2022 10:20:58 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,

Thanks for the prompt answer.

I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE repositories the corresponding RPM package for SLES 15 SP2 is not available, the latest one is DPDK 19.11.10.

I have installed it but the problem persists. It's probably solved in 19.11.11.

There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also, not sure if it could be a problem to install it in SLES 15 SP2. I will try it anyway.

Also I will try to find other way to load the 19.11.11 in SLES 15 SP2 apart from using RPM or zipper, any suggestion is appreciated.

Thanks,

Rocío

-----Original Message-----
From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Sunday, January 16, 2022 4:31 PM
To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>; Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net<mailto:thomas@monjalon.net>>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
>Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko
><viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
>Subject: Re: net_mlx5: unable to recognize master/representors on the
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
>> Mellanox adapters firmware 12.28.2006 (corresponding to this
>> MLNX_OFED version) kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3",
>> "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are
>> correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk": "0",
>>   "intel.com/sriov_cre": "3",
>>   "mellanox.com/mlnx_sriov_netdevice": "4",
>>   "mellanox.com/sriov_dp": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize
>> master/representors on the multiple IB devices"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver =
>> net_mlx5."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
>> used"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
>> actual 0 ports."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>

[-- Attachment #2: Type: text/html, Size: 37257 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

* RE: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-01-31 17:02               ` Asaf Penso
@ 2022-02-03 10:30                 ` Rocio Dominguez
  2022-02-03 10:49                   ` Asaf Penso
  0 siblings, 1 reply; 15+ messages in thread
From: Rocio Dominguez @ 2022-02-03 10:30 UTC (permalink / raw)
  To: Asaf Penso, NBU-Contact-Thomas Monjalon (EXTERNAL)
  Cc: users, Matan Azrad, Slava Ovsiienko, Raslan Darawsheh

[-- Attachment #1: Type: text/plain, Size: 30215 bytes --]

Hi Asaf,

We have replaced the Mellanox NICs by Intel NICs trying to avoid this problem, but it's not working also, this time with the following error:

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.377+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"8"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_INTEL_COM_INTEL_SRIOV_DPDK=0000:d8:02.1 found"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:02.1 --base-virtaddr=0x200000000 --legacy-mem --no-shconf "}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Detected 96 lcore(s)"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Detected 2 NUMA nodes"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Probing VFIO support..."}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: VFIO support initialized"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.358+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL:   using IOMMU type 1 (Type 1)"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Probe PCI driver: net_i40e_vf (8086:154c) device: 0000:d8:02.1 (socket 1)"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Releasing pci mapped resource for 0000:d8:02.1"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40000000"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40010000"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Requested device 0000:d8:02.1 cannot be used"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Bus (pci) probe failed."}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init] No network ports could be enabled!"}

As using Intel NICs, now I have create the VFs and bind them to vfio-pci driver

pcgwpod009-c04:~ # dpdk-devbind --status

N Network devices using DPDK-compatible driver
============================================
0000:d8:02.0 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf
0000:d8:02.1 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf
0000:d8:02.2 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf
0000:d8:02.3 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf

Network devices using kernel driver
===================================
0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe unused=vfio-pci
0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe unused=vfio-pci
0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe unused=vfio-pci
0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe unused=vfio-pci
0000:3b:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p1 drv=i40e unused=vfio-pci
0000:3b:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p2 drv=i40e unused=vfio-pci
0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p1 drv=ixgbe unused=vfio-pci
0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p2 drv=ixgbe unused=vfio-pci
0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_0 drv=ixgbevf unused=vfio-pci
0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_1 drv=ixgbevf unused=vfio-pci
0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci
0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci
0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p1 drv=ixgbe unused=vfio-pci
0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p2 drv=ixgbe unused=vfio-pci
0000:d8:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p1 drv=i40e unused=vfio-pci
0000:d8:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p2 drv=i40e unused=vfio-pci

The interfaces are up:

pcgwpod009-c04:~ # ip link show dev p8p1
290: p8p1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000
    link/ether 40:a6:b7:0d:98:b0 brd ff:ff:ff:ff:ff:ff
    vf 0     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
    vf 1     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
    vf 2     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
    vf 3     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
pcgwpod009-c04:~ #

The testpmd is working:

pcgwpod009-c04:~ # testpmd -l 8-15 -n 4 -w d8:02.0 -w d8:02.1 -w d8:02.2 -w d8:02.3 -- --rxq=2 --txq=2 -i
EAL: Detected 96 lcore(s)
EAL: Detected 2 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: PCI device 0000:d8:02.0 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
EAL:   using IOMMU type 1 (Type 1)
EAL: PCI device 0000:d8:02.1 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
EAL: PCI device 0000:d8:02.2 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
EAL: PCI device 0000:d8:02.3 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
Interactive-mode selected
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0
testpmd: preferred mempool ops selected: ring_mp_mc
testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1
testpmd: preferred mempool ops selected: ring_mp_mc
Configuring Port 0 (socket 1)
Port 0: FE:72:DB:BE:05:EF
Configuring Port 1 (socket 1)
Port 1: 5E:C5:3E:86:1A:84
Configuring Port 2 (socket 1)
Port 2: 42:F0:5D:B0:1F:B3
Configuring Port 3 (socket 1)
Port 3: 46:00:42:2F:A2:DE
Checking link statuses...
Done
testpmd>

Any idea on what could be causing the error this time?

Thanks,

Rocío

From: Asaf Penso <asafp@nvidia.com>
Sent: Monday, January 31, 2022 6:02 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>
Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices

We'll need to check, but how do you want to proceed?
You either need 19.11 LTS or 20.11 LTS to work properly.

Regards,
Asaf Penso
________________________________
From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 31, 2022 2:01:43 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices


Hi Asaf,



Yes, it seems that DPDK version 20.08 code is built-in with the VNF I'm deploying, so it is always using this version, which apparently doesn't have the patch that overrides this error.



I think the patch is the following:

https://patches.dpdk.org/project/dpdk/patch/20200603150602.4686-7-ophirmu@mellanox.com/<https://protect2.fireeye.com/v1/url?k=31323334-501d5122-313273af-454445555731-cfe08b886ec13ca0&q=1&e=a23c8b9f-0b11-4341-81c9-8931cfbdf633&u=https%3A%2F%2Fpatches.dpdk.org%2Fproject%2Fdpdk%2Fpatch%2F20200603150602.4686-7-ophirmu%40mellanox.com%2F>



and the code part that solves the error is:

+       if (mlx5_class_get(pci_dev->device.devargs) != MLX5_CLASS_NET) {

+                DRV_LOG(DEBUG, "Skip probing - should be probed by other mlx5"

+                        " driver.");

+                return 1;

+       }

Could you please confirm?



Thanks,



Rocío



From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Monday, January 31, 2022 12:49 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



I see two differences below.

First, in testpmd the version is 19.11.11, and in your application, it's 20.08. See this print:

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}



Second, in your application, I see the VFIO driver is not started properly:

20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}



Regards,

Asaf Penso



From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Thursday, January 20, 2022 9:49 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,



I have manually compile and install the DPDK 19.11.11.



Executing testpmd in the Mellanox NICs VFs where I want to run my app gives this result:



pcgwpod009-c04:~/dpdk-stable-19.11.11 # ./x86_64-native-linux-gcc/app/testpmd -l 8-15 -n 4 -w d8:00.2 -w d8:00.3 -w d8:00.4 -w d8:00.5 -- --rxq=2 --txq=2 -i

EAL: Detected 96 lcore(s)

EAL: Detected 2 NUMA nodes

EAL: Multi-process socket /var/run/dpdk/rte/mp_socket

EAL: Selected IOVA mode 'VA'

EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size

EAL: Probing VFIO support...

EAL: VFIO support initialized

EAL: PCI device 0000:d8:00.2 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.3 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.4 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.5 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

Interactive-mode selected

testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0

testpmd: preferred mempool ops selected: ring_mp_mc

testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1

testpmd: preferred mempool ops selected: ring_mp_mc

Configuring Port 0 (socket 1)

Port 0: 36:FE:F0:D2:90:27

Configuring Port 1 (socket 1)

Port 1: 72:AC:33:BF:0A:FA

Configuring Port 2 (socket 1)

Port 2: 1E:8D:81:60:43:E0

Configuring Port 3 (socket 1)

Port 3: C2:3C:EA:94:06:B4

Checking link statuses...

Done

testpmd>



But when I run my Data Plane app, the result is



{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.609+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_linux_packet_mmap_setup] block_size: 67108864, frame_size: 4096, block_nr: 1, frame_nr: 16384, mem_size: 67108864"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: pci devices added: 1, vhost user devices added: 0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_MELLANOX_COM_MLNX_SRIOV_NETDEVICE=0000:d8:00.5 found"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:00.5 --base-virtaddr=0x200000000 --iova-mode=va --legacy-mem --no-shconf "}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 96 lcore(s)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 2 NUMA nodes"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.636+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probing VFIO support..."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: VFIO support could not be initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.567+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.5 (socket 1)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] net_mlx5: unable to recognize master/representors on the multiple IB devices"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Requested device 0000:d8:00.5 cannot be used"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Bus (pci) probe failed."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] No network ports could be enabled!"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] libpio packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] pktsock packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] linux packet module is initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] tap packet module is NOT initialized"}



Any idea on what could be the problem?



Thanks,



Rocío





From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Thursday, January 20, 2022 8:17 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices



Although inbox drivers come with a pre installed DPDK, you can manually download, compile, install, and work with whatever version you wish.



Let us know the results, and we'll continue from there.



Regards,

Asaf Penso

________________________________

From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 17, 2022 10:20:58 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,

Thanks for the prompt answer.

I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE repositories the corresponding RPM package for SLES 15 SP2 is not available, the latest one is DPDK 19.11.10.

I have installed it but the problem persists. It's probably solved in 19.11.11.

There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also, not sure if it could be a problem to install it in SLES 15 SP2. I will try it anyway.

Also I will try to find other way to load the 19.11.11 in SLES 15 SP2 apart from using RPM or zipper, any suggestion is appreciated.

Thanks,

Rocío

-----Original Message-----
From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Sunday, January 16, 2022 4:31 PM
To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>; Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net<mailto:thomas@monjalon.net>>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
>Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko
><viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
>Subject: Re: net_mlx5: unable to recognize master/representors on the
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
>> Mellanox adapters firmware 12.28.2006 (corresponding to this
>> MLNX_OFED version) kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3",
>> "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are
>> correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk": "0",
>>   "intel.com/sriov_cre": "3",
>>   "mellanox.com/mlnx_sriov_netdevice": "4",
>>   "mellanox.com/sriov_dp": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize
>> master/representors on the multiple IB devices"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver =
>> net_mlx5."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
>> used"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
>> actual 0 ports."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>

[-- Attachment #2: Type: text/html, Size: 58395 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

* RE: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-02-03 10:30                 ` Rocio Dominguez
@ 2022-02-03 10:49                   ` Asaf Penso
  2022-02-04 12:54                     ` Rocio Dominguez
  0 siblings, 1 reply; 15+ messages in thread
From: Asaf Penso @ 2022-02-03 10:49 UTC (permalink / raw)
  To: Rocio Dominguez, NBU-Contact-Thomas Monjalon (EXTERNAL),
	Ferruh Yigit, Qi Zhang
  Cc: users, Matan Azrad, Slava Ovsiienko, Raslan Darawsheh

[-- Attachment #1: Type: text/plain, Size: 31445 bytes --]

Hello Rocio,

For Intel's NIC it would be better to take it with @Ferruh Yigit<mailto:ferruh.yigit@intel.com>/@Qi Zhang<mailto:qi.z.zhang@intel.com>
For Nvidia's let's continue together.

Regards,
Asaf Penso

From: Rocio Dominguez <rocio.dominguez@ericsson.com>
Sent: Thursday, February 3, 2022 12:30 PM
To: Asaf Penso <asafp@nvidia.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>
Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hi Asaf,

We have replaced the Mellanox NICs by Intel NICs trying to avoid this problem, but it's not working also, this time with the following error:

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.377+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"8"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_INTEL_COM_INTEL_SRIOV_DPDK=0000:d8:02.1 found"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:02.1 --base-virtaddr=0x200000000 --legacy-mem --no-shconf "}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Detected 96 lcore(s)"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Detected 2 NUMA nodes"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Probing VFIO support..."}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: VFIO support initialized"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.358+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL:   using IOMMU type 1 (Type 1)"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Probe PCI driver: net_i40e_vf (8086:154c) device: 0000:d8:02.1 (socket 1)"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Releasing pci mapped resource for 0000:d8:02.1"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40000000"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40010000"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Requested device 0000:d8:02.1 cannot be used"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Bus (pci) probe failed."}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init] No network ports could be enabled!"}

As using Intel NICs, now I have create the VFs and bind them to vfio-pci driver

pcgwpod009-c04:~ # dpdk-devbind --status

N Network devices using DPDK-compatible driver
============================================
0000:d8:02.0 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf
0000:d8:02.1 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf
0000:d8:02.2 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf
0000:d8:02.3 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf

Network devices using kernel driver
===================================
0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe unused=vfio-pci
0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe unused=vfio-pci
0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe unused=vfio-pci
0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe unused=vfio-pci
0000:3b:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p1 drv=i40e unused=vfio-pci
0000:3b:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p2 drv=i40e unused=vfio-pci
0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p1 drv=ixgbe unused=vfio-pci
0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p2 drv=ixgbe unused=vfio-pci
0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_0 drv=ixgbevf unused=vfio-pci
0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_1 drv=ixgbevf unused=vfio-pci
0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci
0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci
0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p1 drv=ixgbe unused=vfio-pci
0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p2 drv=ixgbe unused=vfio-pci
0000:d8:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p1 drv=i40e unused=vfio-pci
0000:d8:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p2 drv=i40e unused=vfio-pci

The interfaces are up:

pcgwpod009-c04:~ # ip link show dev p8p1
290: p8p1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000
    link/ether 40:a6:b7:0d:98:b0 brd ff:ff:ff:ff:ff:ff
    vf 0     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
    vf 1     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
    vf 2     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
    vf 3     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
pcgwpod009-c04:~ #

The testpmd is working:

pcgwpod009-c04:~ # testpmd -l 8-15 -n 4 -w d8:02.0 -w d8:02.1 -w d8:02.2 -w d8:02.3 -- --rxq=2 --txq=2 -i
EAL: Detected 96 lcore(s)
EAL: Detected 2 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: PCI device 0000:d8:02.0 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
EAL:   using IOMMU type 1 (Type 1)
EAL: PCI device 0000:d8:02.1 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
EAL: PCI device 0000:d8:02.2 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
EAL: PCI device 0000:d8:02.3 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
Interactive-mode selected
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0
testpmd: preferred mempool ops selected: ring_mp_mc
testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1
testpmd: preferred mempool ops selected: ring_mp_mc
Configuring Port 0 (socket 1)
Port 0: FE:72:DB:BE:05:EF
Configuring Port 1 (socket 1)
Port 1: 5E:C5:3E:86:1A:84
Configuring Port 2 (socket 1)
Port 2: 42:F0:5D:B0:1F:B3
Configuring Port 3 (socket 1)
Port 3: 46:00:42:2F:A2:DE
Checking link statuses...
Done
testpmd>

Any idea on what could be causing the error this time?

Thanks,

Rocío

From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Monday, January 31, 2022 6:02 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices

We'll need to check, but how do you want to proceed?
You either need 19.11 LTS or 20.11 LTS to work properly.

Regards,
Asaf Penso
________________________________
From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 31, 2022 2:01:43 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices


Hi Asaf,



Yes, it seems that DPDK version 20.08 code is built-in with the VNF I'm deploying, so it is always using this version, which apparently doesn't have the patch that overrides this error.



I think the patch is the following:

https://patches.dpdk.org/project/dpdk/patch/20200603150602.4686-7-ophirmu@mellanox.com/<https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fprotect2.fireeye.com%2Fv1%2Furl%3Fk%3D31323334-501d5122-313273af-454445555731-cfe08b886ec13ca0%26q%3D1%26e%3Da23c8b9f-0b11-4341-81c9-8931cfbdf633%26u%3Dhttps%253A%252F%252Fpatches.dpdk.org%252Fproject%252Fdpdk%252Fpatch%252F20200603150602.4686-7-ophirmu%2540mellanox.com%252F&data=04%7C01%7Casafp%40nvidia.com%7C0b6b2b393538425ee41308d9e70033bd%7C43083d15727340c1b7db39efd9ccc17a%7C0%7C0%7C637794810376687733%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=%2BPjs73ra1Ng3eNj2Qcjs75FMfeWWr%2F8R48SFx2f%2BCM4%3D&reserved=0>



and the code part that solves the error is:

+       if (mlx5_class_get(pci_dev->device.devargs) != MLX5_CLASS_NET) {

+                DRV_LOG(DEBUG, "Skip probing - should be probed by other mlx5"

+                        " driver.");

+                return 1;

+       }

Could you please confirm?



Thanks,



Rocío



From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Monday, January 31, 2022 12:49 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



I see two differences below.

First, in testpmd the version is 19.11.11, and in your application, it's 20.08. See this print:

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}



Second, in your application, I see the VFIO driver is not started properly:

20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}



Regards,

Asaf Penso



From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Thursday, January 20, 2022 9:49 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,



I have manually compile and install the DPDK 19.11.11.



Executing testpmd in the Mellanox NICs VFs where I want to run my app gives this result:



pcgwpod009-c04:~/dpdk-stable-19.11.11 # ./x86_64-native-linux-gcc/app/testpmd -l 8-15 -n 4 -w d8:00.2 -w d8:00.3 -w d8:00.4 -w d8:00.5 -- --rxq=2 --txq=2 -i

EAL: Detected 96 lcore(s)

EAL: Detected 2 NUMA nodes

EAL: Multi-process socket /var/run/dpdk/rte/mp_socket

EAL: Selected IOVA mode 'VA'

EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size

EAL: Probing VFIO support...

EAL: VFIO support initialized

EAL: PCI device 0000:d8:00.2 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.3 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.4 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.5 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

Interactive-mode selected

testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0

testpmd: preferred mempool ops selected: ring_mp_mc

testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1

testpmd: preferred mempool ops selected: ring_mp_mc

Configuring Port 0 (socket 1)

Port 0: 36:FE:F0:D2:90:27

Configuring Port 1 (socket 1)

Port 1: 72:AC:33:BF:0A:FA

Configuring Port 2 (socket 1)

Port 2: 1E:8D:81:60:43:E0

Configuring Port 3 (socket 1)

Port 3: C2:3C:EA:94:06:B4

Checking link statuses...

Done

testpmd>



But when I run my Data Plane app, the result is



{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.609+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_linux_packet_mmap_setup] block_size: 67108864, frame_size: 4096, block_nr: 1, frame_nr: 16384, mem_size: 67108864"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: pci devices added: 1, vhost user devices added: 0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_MELLANOX_COM_MLNX_SRIOV_NETDEVICE=0000:d8:00.5 found"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:00.5 --base-virtaddr=0x200000000 --iova-mode=va --legacy-mem --no-shconf "}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 96 lcore(s)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 2 NUMA nodes"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.636+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probing VFIO support..."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: VFIO support could not be initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.567+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.5 (socket 1)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] net_mlx5: unable to recognize master/representors on the multiple IB devices"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Requested device 0000:d8:00.5 cannot be used"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Bus (pci) probe failed."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] No network ports could be enabled!"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] libpio packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] pktsock packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] linux packet module is initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] tap packet module is NOT initialized"}



Any idea on what could be the problem?



Thanks,



Rocío





From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Thursday, January 20, 2022 8:17 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices



Although inbox drivers come with a pre installed DPDK, you can manually download, compile, install, and work with whatever version you wish.



Let us know the results, and we'll continue from there.



Regards,

Asaf Penso

________________________________

From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 17, 2022 10:20:58 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,

Thanks for the prompt answer.

I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE repositories the corresponding RPM package for SLES 15 SP2 is not available, the latest one is DPDK 19.11.10.

I have installed it but the problem persists. It's probably solved in 19.11.11.

There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also, not sure if it could be a problem to install it in SLES 15 SP2. I will try it anyway.

Also I will try to find other way to load the 19.11.11 in SLES 15 SP2 apart from using RPM or zipper, any suggestion is appreciated.

Thanks,

Rocío

-----Original Message-----
From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Sunday, January 16, 2022 4:31 PM
To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>; Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net<mailto:thomas@monjalon.net>>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
>Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko
><viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
>Subject: Re: net_mlx5: unable to recognize master/representors on the
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
>> Mellanox adapters firmware 12.28.2006 (corresponding to this
>> MLNX_OFED version) kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3",
>> "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are
>> correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk": "0",
>>   "intel.com/sriov_cre": "3",
>>   "mellanox.com/mlnx_sriov_netdevice": "4",
>>   "mellanox.com/sriov_dp": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize
>> master/representors on the multiple IB devices"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver =
>> net_mlx5."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
>> used"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
>> actual 0 ports."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>

[-- Attachment #2: Type: text/html, Size: 60703 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

* RE: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-02-03 10:49                   ` Asaf Penso
@ 2022-02-04 12:54                     ` Rocio Dominguez
  2022-02-04 14:09                       ` Asaf Penso
  0 siblings, 1 reply; 15+ messages in thread
From: Rocio Dominguez @ 2022-02-04 12:54 UTC (permalink / raw)
  To: Asaf Penso, NBU-Contact-Thomas Monjalon (EXTERNAL),
	Ferruh Yigit, Qi Zhang
  Cc: users, Matan Azrad, Slava Ovsiienko, Raslan Darawsheh

[-- Attachment #1: Type: text/plain, Size: 32749 bytes --]

Hi Asaf,

Finally I solved the problem with Intel NICs. I am using Dual NUMA, and I realized that my application is using cpus from NUMA 0 while I was assigning a NIC from NUMA 1. Using a NIC from NUMA 0 solved the problem.

I don't know if the problem with Mellanox NICs could be solved in the same way. But for the moment, we will use Intel NICs.

Thanks,

Rocío

From: Asaf Penso <asafp@nvidia.com>
Sent: Thursday, February 3, 2022 11:50 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>; Ferruh Yigit <ferruh.yigit@intel.com>; Qi Zhang <qi.z.zhang@intel.com>
Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,

For Intel's NIC it would be better to take it with @Ferruh Yigit<mailto:ferruh.yigit@intel.com>/@Qi Zhang<mailto:qi.z.zhang@intel.com>
For Nvidia's let's continue together.

Regards,
Asaf Penso

From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Thursday, February 3, 2022 12:30 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hi Asaf,

We have replaced the Mellanox NICs by Intel NICs trying to avoid this problem, but it's not working also, this time with the following error:

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.377+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"8"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_INTEL_COM_INTEL_SRIOV_DPDK=0000:d8:02.1 found"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:02.1 --base-virtaddr=0x200000000 --legacy-mem --no-shconf "}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Detected 96 lcore(s)"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Detected 2 NUMA nodes"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Probing VFIO support..."}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: VFIO support initialized"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.358+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL:   using IOMMU type 1 (Type 1)"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Probe PCI driver: net_i40e_vf (8086:154c) device: 0000:d8:02.1 (socket 1)"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Releasing pci mapped resource for 0000:d8:02.1"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40000000"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40010000"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Requested device 0000:d8:02.1 cannot be used"}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Bus (pci) probe failed."}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}
{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init] No network ports could be enabled!"}

As using Intel NICs, now I have create the VFs and bind them to vfio-pci driver

pcgwpod009-c04:~ # dpdk-devbind --status

N Network devices using DPDK-compatible driver
============================================
0000:d8:02.0 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf
0000:d8:02.1 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf
0000:d8:02.2 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf
0000:d8:02.3 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf

Network devices using kernel driver
===================================
0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe unused=vfio-pci
0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe unused=vfio-pci
0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe unused=vfio-pci
0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe unused=vfio-pci
0000:3b:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p1 drv=i40e unused=vfio-pci
0000:3b:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p2 drv=i40e unused=vfio-pci
0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p1 drv=ixgbe unused=vfio-pci
0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p2 drv=ixgbe unused=vfio-pci
0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_0 drv=ixgbevf unused=vfio-pci
0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_1 drv=ixgbevf unused=vfio-pci
0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci
0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci
0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p1 drv=ixgbe unused=vfio-pci
0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p2 drv=ixgbe unused=vfio-pci
0000:d8:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p1 drv=i40e unused=vfio-pci
0000:d8:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p2 drv=i40e unused=vfio-pci

The interfaces are up:

pcgwpod009-c04:~ # ip link show dev p8p1
290: p8p1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000
    link/ether 40:a6:b7:0d:98:b0 brd ff:ff:ff:ff:ff:ff
    vf 0     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
    vf 1     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
    vf 2     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
    vf 3     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
pcgwpod009-c04:~ #

The testpmd is working:

pcgwpod009-c04:~ # testpmd -l 8-15 -n 4 -w d8:02.0 -w d8:02.1 -w d8:02.2 -w d8:02.3 -- --rxq=2 --txq=2 -i
EAL: Detected 96 lcore(s)
EAL: Detected 2 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: PCI device 0000:d8:02.0 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
EAL:   using IOMMU type 1 (Type 1)
EAL: PCI device 0000:d8:02.1 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
EAL: PCI device 0000:d8:02.2 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
EAL: PCI device 0000:d8:02.3 on NUMA socket 1
EAL:   probe driver: 8086:154c net_i40e_vf
Interactive-mode selected
testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0
testpmd: preferred mempool ops selected: ring_mp_mc
testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1
testpmd: preferred mempool ops selected: ring_mp_mc
Configuring Port 0 (socket 1)
Port 0: FE:72:DB:BE:05:EF
Configuring Port 1 (socket 1)
Port 1: 5E:C5:3E:86:1A:84
Configuring Port 2 (socket 1)
Port 2: 42:F0:5D:B0:1F:B3
Configuring Port 3 (socket 1)
Port 3: 46:00:42:2F:A2:DE
Checking link statuses...
Done
testpmd>

Any idea on what could be causing the error this time?

Thanks,

Rocío

From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Monday, January 31, 2022 6:02 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices

We'll need to check, but how do you want to proceed?
You either need 19.11 LTS or 20.11 LTS to work properly.

Regards,
Asaf Penso
________________________________
From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 31, 2022 2:01:43 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices


Hi Asaf,



Yes, it seems that DPDK version 20.08 code is built-in with the VNF I'm deploying, so it is always using this version, which apparently doesn't have the patch that overrides this error.



I think the patch is the following:

https://patches.dpdk.org/project/dpdk/patch/20200603150602.4686-7-ophirmu@mellanox.com/<https://protect2.fireeye.com/v1/url?k=31323334-501d5122-313273af-454445555731-487e56eb04c55cc6&q=1&e=5f658968-17f8-498f-9acc-81014ffbff4c&u=https%3A%2F%2Fnam11.safelinks.protection.outlook.com%2F%3Furl%3Dhttps%253A%252F%252Fprotect2.fireeye.com%252Fv1%252Furl%253Fk%253D31323334-501d5122-313273af-454445555731-cfe08b886ec13ca0%2526q%253D1%2526e%253Da23c8b9f-0b11-4341-81c9-8931cfbdf633%2526u%253Dhttps%25253A%25252F%25252Fpatches.dpdk.org%25252Fproject%25252Fdpdk%25252Fpatch%25252F20200603150602.4686-7-ophirmu%252540mellanox.com%25252F%26data%3D04%257C01%257Casafp%2540nvidia.com%257C0b6b2b393538425ee41308d9e70033bd%257C43083d15727340c1b7db39efd9ccc17a%257C0%257C0%257C637794810376687733%257CUnknown%257CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%253D%257C3000%26sdata%3D%252BPjs73ra1Ng3eNj2Qcjs75FMfeWWr%252F8R48SFx2f%252BCM4%253D%26reserved%3D0>



and the code part that solves the error is:

+       if (mlx5_class_get(pci_dev->device.devargs) != MLX5_CLASS_NET) {

+                DRV_LOG(DEBUG, "Skip probing - should be probed by other mlx5"

+                        " driver.");

+                return 1;

+       }

Could you please confirm?



Thanks,



Rocío



From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Monday, January 31, 2022 12:49 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



I see two differences below.

First, in testpmd the version is 19.11.11, and in your application, it's 20.08. See this print:

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}



Second, in your application, I see the VFIO driver is not started properly:

20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}



Regards,

Asaf Penso



From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Thursday, January 20, 2022 9:49 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,



I have manually compile and install the DPDK 19.11.11.



Executing testpmd in the Mellanox NICs VFs where I want to run my app gives this result:



pcgwpod009-c04:~/dpdk-stable-19.11.11 # ./x86_64-native-linux-gcc/app/testpmd -l 8-15 -n 4 -w d8:00.2 -w d8:00.3 -w d8:00.4 -w d8:00.5 -- --rxq=2 --txq=2 -i

EAL: Detected 96 lcore(s)

EAL: Detected 2 NUMA nodes

EAL: Multi-process socket /var/run/dpdk/rte/mp_socket

EAL: Selected IOVA mode 'VA'

EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size

EAL: Probing VFIO support...

EAL: VFIO support initialized

EAL: PCI device 0000:d8:00.2 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.3 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.4 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.5 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

Interactive-mode selected

testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0

testpmd: preferred mempool ops selected: ring_mp_mc

testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1

testpmd: preferred mempool ops selected: ring_mp_mc

Configuring Port 0 (socket 1)

Port 0: 36:FE:F0:D2:90:27

Configuring Port 1 (socket 1)

Port 1: 72:AC:33:BF:0A:FA

Configuring Port 2 (socket 1)

Port 2: 1E:8D:81:60:43:E0

Configuring Port 3 (socket 1)

Port 3: C2:3C:EA:94:06:B4

Checking link statuses...

Done

testpmd>



But when I run my Data Plane app, the result is



{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.609+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_linux_packet_mmap_setup] block_size: 67108864, frame_size: 4096, block_nr: 1, frame_nr: 16384, mem_size: 67108864"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: pci devices added: 1, vhost user devices added: 0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_MELLANOX_COM_MLNX_SRIOV_NETDEVICE=0000:d8:00.5 found"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:00.5 --base-virtaddr=0x200000000 --iova-mode=va --legacy-mem --no-shconf "}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 96 lcore(s)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 2 NUMA nodes"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.636+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probing VFIO support..."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: VFIO support could not be initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.567+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.5 (socket 1)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] net_mlx5: unable to recognize master/representors on the multiple IB devices"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Requested device 0000:d8:00.5 cannot be used"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Bus (pci) probe failed."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] No network ports could be enabled!"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] libpio packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] pktsock packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] linux packet module is initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] tap packet module is NOT initialized"}



Any idea on what could be the problem?



Thanks,



Rocío





From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Thursday, January 20, 2022 8:17 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices



Although inbox drivers come with a pre installed DPDK, you can manually download, compile, install, and work with whatever version you wish.



Let us know the results, and we'll continue from there.



Regards,

Asaf Penso

________________________________

From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 17, 2022 10:20:58 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,

Thanks for the prompt answer.

I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE repositories the corresponding RPM package for SLES 15 SP2 is not available, the latest one is DPDK 19.11.10.

I have installed it but the problem persists. It's probably solved in 19.11.11.

There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also, not sure if it could be a problem to install it in SLES 15 SP2. I will try it anyway.

Also I will try to find other way to load the 19.11.11 in SLES 15 SP2 apart from using RPM or zipper, any suggestion is appreciated.

Thanks,

Rocío

-----Original Message-----
From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Sunday, January 16, 2022 4:31 PM
To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>; Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net<mailto:thomas@monjalon.net>>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
>Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko
><viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
>Subject: Re: net_mlx5: unable to recognize master/representors on the
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
>> Mellanox adapters firmware 12.28.2006 (corresponding to this
>> MLNX_OFED version) kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3",
>> "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are
>> correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk": "0",
>>   "intel.com/sriov_cre": "3",
>>   "mellanox.com/mlnx_sriov_netdevice": "4",
>>   "mellanox.com/sriov_dp": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize
>> master/representors on the multiple IB devices"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver =
>> net_mlx5."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
>> used"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
>> actual 0 ports."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>

[-- Attachment #2: Type: text/html, Size: 62829 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-02-04 12:54                     ` Rocio Dominguez
@ 2022-02-04 14:09                       ` Asaf Penso
  2022-02-04 14:55                         ` Muhammad Zain-ul-Abideen
  0 siblings, 1 reply; 15+ messages in thread
From: Asaf Penso @ 2022-02-04 14:09 UTC (permalink / raw)
  To: Rocio Dominguez, NBU-Contact-Thomas Monjalon (EXTERNAL),
	Ferruh Yigit, Qi Zhang
  Cc: users, Matan Azrad, Slava Ovsiienko, Raslan Darawsheh

[-- Attachment #1: Type: text/plain, Size: 34207 bytes --]

Great, thanks for the update.
I think the community can benefit if you try with Mellanox NIC and find an issue that will be resolved.

Regards,
Asaf Penso
________________________________
From: Rocio Dominguez <rocio.dominguez@ericsson.com>
Sent: Friday, February 4, 2022 2:54:20 PM
To: Asaf Penso <asafp@nvidia.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>; Ferruh Yigit <ferruh.yigit@intel.com>; Qi Zhang <qi.z.zhang@intel.com>
Cc: users@dpdk.org <users@dpdk.org>; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices


Hi Asaf,



Finally I solved the problem with Intel NICs. I am using Dual NUMA, and I realized that my application is using cpus from NUMA 0 while I was assigning a NIC from NUMA 1. Using a NIC from NUMA 0 solved the problem.



I don’t know if the problem with Mellanox NICs could be solved in the same way. But for the moment, we will use Intel NICs.



Thanks,



Rocío



From: Asaf Penso <asafp@nvidia.com>
Sent: Thursday, February 3, 2022 11:50 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>; Ferruh Yigit <ferruh.yigit@intel.com>; Qi Zhang <qi.z.zhang@intel.com>
Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hello Rocio,



For Intel’s NIC it would be better to take it with @Ferruh Yigit<mailto:ferruh.yigit@intel.com>/@Qi Zhang<mailto:qi.z.zhang@intel.com>

For Nvidia’s let’s continue together.



Regards,

Asaf Penso



From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Thursday, February 3, 2022 12:30 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,



We have replaced the Mellanox NICs by Intel NICs trying to avoid this problem, but it’s not working also, this time with the following error:



{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.377+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"8"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_INTEL_COM_INTEL_SRIOV_DPDK=0000:d8:02.1 found"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:02.1 --base-virtaddr=0x200000000 --legacy-mem --no-shconf "}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Detected 96 lcore(s)"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Detected 2 NUMA nodes"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Probing VFIO support..."}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: VFIO support initialized"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.358+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL:   using IOMMU type 1 (Type 1)"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Probe PCI driver: net_i40e_vf (8086:154c) device: 0000:d8:02.1 (socket 1)"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Releasing pci mapped resource for 0000:d8:02.1"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40000000"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40010000"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Requested device 0000:d8:02.1 cannot be used"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Bus (pci) probe failed."}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init] No network ports could be enabled!"}



As using Intel NICs, now I have create the VFs and bind them to vfio-pci driver



pcgwpod009-c04:~ # dpdk-devbind --status



N Network devices using DPDK-compatible driver

============================================

0000:d8:02.0 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf

0000:d8:02.1 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf

0000:d8:02.2 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf

0000:d8:02.3 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf



Network devices using kernel driver

===================================

0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe unused=vfio-pci

0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe unused=vfio-pci

0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe unused=vfio-pci

0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe unused=vfio-pci

0000:3b:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p1 drv=i40e unused=vfio-pci

0000:3b:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p2 drv=i40e unused=vfio-pci

0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p1 drv=ixgbe unused=vfio-pci

0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p2 drv=ixgbe unused=vfio-pci

0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_0 drv=ixgbevf unused=vfio-pci

0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_1 drv=ixgbevf unused=vfio-pci

0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci

0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci

0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p1 drv=ixgbe unused=vfio-pci

0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p2 drv=ixgbe unused=vfio-pci

0000:d8:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p1 drv=i40e unused=vfio-pci

0000:d8:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p2 drv=i40e unused=vfio-pci



The interfaces are up:



pcgwpod009-c04:~ # ip link show dev p8p1

290: p8p1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000

    link/ether 40:a6:b7:0d:98:b0 brd ff:ff:ff:ff:ff:ff

    vf 0     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off

    vf 1     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off

    vf 2     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off

    vf 3     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off

pcgwpod009-c04:~ #



The testpmd is working:



pcgwpod009-c04:~ # testpmd -l 8-15 -n 4 -w d8:02.0 -w d8:02.1 -w d8:02.2 -w d8:02.3 -- --rxq=2 --txq=2 -i

EAL: Detected 96 lcore(s)

EAL: Detected 2 NUMA nodes

EAL: Multi-process socket /var/run/dpdk/rte/mp_socket

EAL: Selected IOVA mode 'VA'

EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size

EAL: Probing VFIO support...

EAL: VFIO support initialized

EAL: PCI device 0000:d8:02.0 on NUMA socket 1

EAL:   probe driver: 8086:154c net_i40e_vf

EAL:   using IOMMU type 1 (Type 1)

EAL: PCI device 0000:d8:02.1 on NUMA socket 1

EAL:   probe driver: 8086:154c net_i40e_vf

EAL: PCI device 0000:d8:02.2 on NUMA socket 1

EAL:   probe driver: 8086:154c net_i40e_vf

EAL: PCI device 0000:d8:02.3 on NUMA socket 1

EAL:   probe driver: 8086:154c net_i40e_vf

Interactive-mode selected

testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0

testpmd: preferred mempool ops selected: ring_mp_mc

testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1

testpmd: preferred mempool ops selected: ring_mp_mc

Configuring Port 0 (socket 1)

Port 0: FE:72:DB:BE:05:EF

Configuring Port 1 (socket 1)

Port 1: 5E:C5:3E:86:1A:84

Configuring Port 2 (socket 1)

Port 2: 42:F0:5D:B0:1F:B3

Configuring Port 3 (socket 1)

Port 3: 46:00:42:2F:A2:DE

Checking link statuses...

Done

testpmd>



Any idea on what could be causing the error this time?



Thanks,



Rocío



From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Monday, January 31, 2022 6:02 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices



We'll need to check, but how do you want to proceed?

You either need 19.11 LTS or 20.11 LTS to work properly.



Regards,

Asaf Penso

________________________________

From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 31, 2022 2:01:43 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,



Yes, it seems that DPDK version 20.08 code is built-in with the VNF I’m deploying, so it is always using this version, which apparently doesn’t have the patch that overrides this error.



I think the patch is the following:

https://patches.dpdk.org/project/dpdk/patch/20200603150602.4686-7-ophirmu@mellanox.com/<https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fprotect2.fireeye.com%2Fv1%2Furl%3Fk%3D31323334-501d5122-313273af-454445555731-487e56eb04c55cc6%26q%3D1%26e%3D5f658968-17f8-498f-9acc-81014ffbff4c%26u%3Dhttps%253A%252F%252Fnam11.safelinks.protection.outlook.com%252F%253Furl%253Dhttps%25253A%25252F%25252Fprotect2.fireeye.com%25252Fv1%25252Furl%25253Fk%25253D31323334-501d5122-313273af-454445555731-cfe08b886ec13ca0%252526q%25253D1%252526e%25253Da23c8b9f-0b11-4341-81c9-8931cfbdf633%252526u%25253Dhttps%2525253A%2525252F%2525252Fpatches.dpdk.org%2525252Fproject%2525252Fdpdk%2525252Fpatch%2525252F20200603150602.4686-7-ophirmu%25252540mellanox.com%2525252F%2526data%253D04%25257C01%25257Casafp%252540nvidia.com%25257C0b6b2b393538425ee41308d9e70033bd%25257C43083d15727340c1b7db39efd9ccc17a%25257C0%25257C0%25257C637794810376687733%25257CUnknown%25257CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%25253D%25257C3000%2526sdata%253D%25252BPjs73ra1Ng3eNj2Qcjs75FMfeWWr%25252F8R48SFx2f%25252BCM4%25253D%2526reserved%253D0&data=04%7C01%7Casafp%40nvidia.com%7C1b38d6419d3143a3ab4608d9e7dd7816%7C43083d15727340c1b7db39efd9ccc17a%7C0%7C0%7C637795760671604452%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=E9OFPSnMUQamrsjxPezWD7Dthg%2B71rfAd8o%2FRv1PJyU%3D&reserved=0>



and the code part that solves the error is:

+       if (mlx5_class_get(pci_dev->device.devargs) != MLX5_CLASS_NET) {

+                DRV_LOG(DEBUG, "Skip probing - should be probed by other mlx5"

+                        " driver.");

+                return 1;

+       }

Could you please confirm?



Thanks,



Rocío



From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Monday, January 31, 2022 12:49 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



I see two differences below.

First, in testpmd the version is 19.11.11, and in your application, it’s 20.08. See this print:

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}



Second, in your application, I see the VFIO driver is not started properly:

20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}



Regards,

Asaf Penso



From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Thursday, January 20, 2022 9:49 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,



I have manually compile and install the DPDK 19.11.11.



Executing testpmd in the Mellanox NICs VFs where I want to run my app gives this result:



pcgwpod009-c04:~/dpdk-stable-19.11.11 # ./x86_64-native-linux-gcc/app/testpmd -l 8-15 -n 4 -w d8:00.2 -w d8:00.3 -w d8:00.4 -w d8:00.5 -- --rxq=2 --txq=2 -i

EAL: Detected 96 lcore(s)

EAL: Detected 2 NUMA nodes

EAL: Multi-process socket /var/run/dpdk/rte/mp_socket

EAL: Selected IOVA mode 'VA'

EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size

EAL: Probing VFIO support...

EAL: VFIO support initialized

EAL: PCI device 0000:d8:00.2 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.3 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.4 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.5 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

Interactive-mode selected

testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0

testpmd: preferred mempool ops selected: ring_mp_mc

testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1

testpmd: preferred mempool ops selected: ring_mp_mc

Configuring Port 0 (socket 1)

Port 0: 36:FE:F0:D2:90:27

Configuring Port 1 (socket 1)

Port 1: 72:AC:33:BF:0A:FA

Configuring Port 2 (socket 1)

Port 2: 1E:8D:81:60:43:E0

Configuring Port 3 (socket 1)

Port 3: C2:3C:EA:94:06:B4

Checking link statuses...

Done

testpmd>



But when I run my Data Plane app, the result is



{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.609+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_linux_packet_mmap_setup] block_size: 67108864, frame_size: 4096, block_nr: 1, frame_nr: 16384, mem_size: 67108864"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: pci devices added: 1, vhost user devices added: 0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_MELLANOX_COM_MLNX_SRIOV_NETDEVICE=0000:d8:00.5 found"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:00.5 --base-virtaddr=0x200000000 --iova-mode=va --legacy-mem --no-shconf "}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 96 lcore(s)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 2 NUMA nodes"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.636+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probing VFIO support..."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: VFIO support could not be initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.567+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.5 (socket 1)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] net_mlx5: unable to recognize master/representors on the multiple IB devices"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Requested device 0000:d8:00.5 cannot be used"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Bus (pci) probe failed."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] No network ports could be enabled!"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] libpio packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] pktsock packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] linux packet module is initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] tap packet module is NOT initialized"}



Any idea on what could be the problem?



Thanks,



Rocío





From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Thursday, January 20, 2022 8:17 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices



Although inbox drivers come with a pre installed DPDK, you can manually download, compile, install, and work with whatever version you wish.



Let us know the results, and we'll continue from there.



Regards,

Asaf Penso

________________________________

From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 17, 2022 10:20:58 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,

Thanks for the prompt answer.

I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE repositories the corresponding RPM package for SLES 15 SP2 is not available, the latest one is DPDK 19.11.10.

I have installed it but the problem persists. It's probably solved in 19.11.11.

There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also, not sure if it could be a problem to install it in SLES 15 SP2. I will try it anyway.

Also I will try to find other way to load the 19.11.11 in SLES 15 SP2 apart from using RPM or zipper, any suggestion is appreciated.

Thanks,

Rocío

-----Original Message-----
From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Sunday, January 16, 2022 4:31 PM
To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>; Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net<mailto:thomas@monjalon.net>>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
>Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko
><viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
>Subject: Re: net_mlx5: unable to recognize master/representors on the
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
>> Mellanox adapters firmware 12.28.2006 (corresponding to this
>> MLNX_OFED version) kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3",
>> "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are
>> correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk": "0",
>>   "intel.com/sriov_cre": "3",
>>   "mellanox.com/mlnx_sriov_netdevice": "4",
>>   "mellanox.com/sriov_dp": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize
>> master/representors on the multiple IB devices"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver =
>> net_mlx5."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
>> used"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
>> actual 0 ports."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>

[-- Attachment #2: Type: text/html, Size: 62201 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

* Re: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-02-04 14:09                       ` Asaf Penso
@ 2022-02-04 14:55                         ` Muhammad Zain-ul-Abideen
  2022-02-07 17:14                           ` Rocio Dominguez
  0 siblings, 1 reply; 15+ messages in thread
From: Muhammad Zain-ul-Abideen @ 2022-02-04 14:55 UTC (permalink / raw)
  To: Asaf Penso
  Cc: Rocio Dominguez, NBU-Contact-Thomas Monjalon (EXTERNAL),
	Ferruh Yigit, Qi Zhang, users, Matan Azrad, Slava Ovsiienko,
	Raslan Darawsheh

[-- Attachment #1: Type: text/plain, Size: 34282 bytes --]

Was the mlx card on cpu2?

On Fri, Feb 4, 2022, 7:09 PM Asaf Penso <asafp@nvidia.com> wrote:

> Great, thanks for the update.
> I think the community can benefit if you try with Mellanox NIC and find an
> issue that will be resolved.
>
> Regards,
> Asaf Penso
> ------------------------------
> *From:* Rocio Dominguez <rocio.dominguez@ericsson.com>
> *Sent:* Friday, February 4, 2022 2:54:20 PM
> *To:* Asaf Penso <asafp@nvidia.com>; NBU-Contact-Thomas Monjalon
> (EXTERNAL) <thomas@monjalon.net>; Ferruh Yigit <ferruh.yigit@intel.com>;
> Qi Zhang <qi.z.zhang@intel.com>
> *Cc:* users@dpdk.org <users@dpdk.org>; Matan Azrad <matan@nvidia.com>;
> Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <
> rasland@nvidia.com>
> *Subject:* RE: net_mlx5: unable to recognize master/representors on the
> multiple IB devices
>
>
> Hi Asaf,
>
>
>
> Finally I solved the problem with Intel NICs. I am using Dual NUMA, and I
> realized that my application is using cpus from NUMA 0 while I was
> assigning a NIC from NUMA 1. Using a NIC from NUMA 0 solved the problem.
>
>
>
> I don’t know if the problem with Mellanox NICs could be solved in the same
> way. But for the moment, we will use Intel NICs.
>
>
>
> Thanks,
>
>
>
> Rocío
>
>
>
> *From:* Asaf Penso <asafp@nvidia.com>
> *Sent:* Thursday, February 3, 2022 11:50 AM
> *To:* Rocio Dominguez <rocio.dominguez@ericsson.com>; NBU-Contact-Thomas
> Monjalon (EXTERNAL) <thomas@monjalon.net>; Ferruh Yigit <
> ferruh.yigit@intel.com>; Qi Zhang <qi.z.zhang@intel.com>
> *Cc:* users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <
> viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
> *Subject:* RE: net_mlx5: unable to recognize master/representors on the
> multiple IB devices
>
>
>
> Hello Rocio,
>
>
>
> For Intel’s NIC it would be better to take it with @Ferruh Yigit
> <ferruh.yigit@intel.com>/@Qi Zhang <qi.z.zhang@intel.com>
>
> For Nvidia’s let’s continue together.
>
>
>
> Regards,
>
> Asaf Penso
>
>
>
> *From:* Rocio Dominguez <rocio.dominguez@ericsson.com>
> *Sent:* Thursday, February 3, 2022 12:30 PM
> *To:* Asaf Penso <asafp@nvidia.com>; NBU-Contact-Thomas Monjalon
> (EXTERNAL) <thomas@monjalon.net>
> *Cc:* users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <
> viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
> *Subject:* RE: net_mlx5: unable to recognize master/representors on the
> multiple IB devices
>
>
>
> Hi Asaf,
>
>
>
> We have replaced the Mellanox NICs by Intel NICs trying to avoid this
> problem, but it’s not working also, this time with the following error:
>
>
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:37.377+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"8"},"message":"[add_pio_pci_devices_from_env_to_config]
> pci device from PCIDEVICE_INTEL_COM_INTEL_SRIOV_DPDK=0000:d8:02.1 found"}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init]
> CTRL: requesting 1024 MiB of hugepage memory for DPDK"}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> USER1: DPDK version: DPDK 20.08.0"}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix
> pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:02.1
> --base-virtaddr=0x200000000 --legacy-mem --no-shconf "}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: Detected 96 lcore(s)"}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: Detected 2 NUMA nodes"}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: Selected IOVA mode 'VA'"}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs
> found for that size"}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: Probing VFIO support..."}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: VFIO support initialized"}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:38.358+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL:   using IOMMU type 1 (Type 1)"}
>
> *{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: Probe PCI driver: net_i40e_vf (8086:154c) device: 0000:d8:02.1 (socket
> 1)"}*
>
> *{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: Releasing pci mapped resource for 0000:d8:02.1"}*
>
> *{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40000000"}*
>
> *{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40010000"}*
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: Requested device 0000:d8:02.1 cannot be used"}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> EAL: Bus (pci) probe failed."}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio]
> USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}
>
> {"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init]
> No network ports could be enabled!"}
>
>
>
> As using Intel NICs, now I have create the VFs and bind them to vfio-pci
> driver
>
>
>
> pcgwpod009-c04:~ # dpdk-devbind --status
>
>
>
> N Network devices using DPDK-compatible driver
>
> ============================================
>
> 0000:d8:02.0 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci
> unused=iavf
>
> 0000:d8:02.1 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci
> unused=iavf
>
> 0000:d8:02.2 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci
> unused=iavf
>
> 0000:d8:02.3 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci
> unused=iavf
>
>
>
> Network devices using kernel driver
>
> ===================================
>
> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
> unused=vfio-pci
>
> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
> unused=vfio-pci
>
> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
> unused=vfio-pci
>
> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
> unused=vfio-pci
>
> 0000:3b:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p1
> drv=i40e unused=vfio-pci
>
> 0000:3b:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p2
> drv=i40e unused=vfio-pci
>
> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p1
> drv=ixgbe unused=vfio-pci
>
> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p2
> drv=ixgbe unused=vfio-pci
>
> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_0
> drv=ixgbevf unused=vfio-pci
>
> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_1
> drv=ixgbevf unused=vfio-pci
>
> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
> drv=ixgbevf unused=vfio-pci
>
> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed' if=
> drv=ixgbevf unused=vfio-pci
>
> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p1
> drv=ixgbe unused=vfio-pci
>
> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p2
> drv=ixgbe unused=vfio-pci
>
> 0000:d8:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p1
> drv=i40e unused=vfio-pci
>
> 0000:d8:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p2
> drv=i40e unused=vfio-pci
>
>
>
> The interfaces are up:
>
>
>
> pcgwpod009-c04:~ # ip link show dev p8p1
>
> 290: p8p1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP
> mode DEFAULT group default qlen 1000
>
>     link/ether 40:a6:b7:0d:98:b0 brd ff:ff:ff:ff:ff:ff
>
>     vf 0     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof
> checking on, link-state auto, trust off
>
>     vf 1     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof
> checking on, link-state auto, trust off
>
>     vf 2     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof
> checking on, link-state auto, trust off
>
>     vf 3     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof
> checking on, link-state auto, trust off
>
> pcgwpod009-c04:~ #
>
>
>
> The testpmd is working:
>
>
>
> pcgwpod009-c04:~ # testpmd -l 8-15 -n 4 -w d8:02.0 -w d8:02.1 -w d8:02.2
> -w d8:02.3 -- --rxq=2 --txq=2 -i
>
> EAL: Detected 96 lcore(s)
>
> EAL: Detected 2 NUMA nodes
>
> EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
>
> EAL: Selected IOVA mode 'VA'
>
> EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs
> found for that size
>
> EAL: Probing VFIO support...
>
> EAL: VFIO support initialized
>
> EAL: PCI device 0000:d8:02.0 on NUMA socket 1
>
> EAL:   probe driver: 8086:154c net_i40e_vf
>
> EAL:   using IOMMU type 1 (Type 1)
>
> EAL: PCI device 0000:d8:02.1 on NUMA socket 1
>
> EAL:   probe driver: 8086:154c net_i40e_vf
>
> EAL: PCI device 0000:d8:02.2 on NUMA socket 1
>
> EAL:   probe driver: 8086:154c net_i40e_vf
>
> EAL: PCI device 0000:d8:02.3 on NUMA socket 1
>
> EAL:   probe driver: 8086:154c net_i40e_vf
>
> Interactive-mode selected
>
> testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176,
> socket=0
>
> testpmd: preferred mempool ops selected: ring_mp_mc
>
> testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176,
> socket=1
>
> testpmd: preferred mempool ops selected: ring_mp_mc
>
> Configuring Port 0 (socket 1)
>
> Port 0: FE:72:DB:BE:05:EF
>
> Configuring Port 1 (socket 1)
>
> Port 1: 5E:C5:3E:86:1A:84
>
> Configuring Port 2 (socket 1)
>
> Port 2: 42:F0:5D:B0:1F:B3
>
> Configuring Port 3 (socket 1)
>
> Port 3: 46:00:42:2F:A2:DE
>
> Checking link statuses...
>
> Done
>
> testpmd>
>
>
>
> Any idea on what could be causing the error this time?
>
>
>
> Thanks,
>
>
>
> Rocío
>
>
>
> *From:* Asaf Penso <asafp@nvidia.com>
> *Sent:* Monday, January 31, 2022 6:02 PM
> *To:* Rocio Dominguez <rocio.dominguez@ericsson.com>; NBU-Contact-Thomas
> Monjalon (EXTERNAL) <thomas@monjalon.net>
> *Cc:* users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <
> viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
> *Subject:* Re: net_mlx5: unable to recognize master/representors on the
> multiple IB devices
>
>
>
> We'll need to check, but how do you want to proceed?
>
> You either need 19.11 LTS or 20.11 LTS to work properly.
>
>
>
> Regards,
>
> Asaf Penso
> ------------------------------
>
> *From:* Rocio Dominguez <rocio.dominguez@ericsson.com>
> *Sent:* Monday, January 31, 2022 2:01:43 PM
> *To:* Asaf Penso <asafp@nvidia.com>; NBU-Contact-Thomas Monjalon
> (EXTERNAL) <thomas@monjalon.net>
> *Cc:* users@dpdk.org <users@dpdk.org>; Matan Azrad <matan@nvidia.com>;
> Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <
> rasland@nvidia.com>
> *Subject:* RE: net_mlx5: unable to recognize master/representors on the
> multiple IB devices
>
>
>
> Hi Asaf,
>
>
>
> Yes, it seems that DPDK version 20.08 code is built-in with the VNF I’m
> deploying, so it is always using this version, which apparently doesn’t
> have the patch that overrides this error.
>
>
>
> I think the patch is the following:
>
>
> https://patches.dpdk.org/project/dpdk/patch/20200603150602.4686-7-ophirmu@mellanox.com/
> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fprotect2.fireeye.com%2Fv1%2Furl%3Fk%3D31323334-501d5122-313273af-454445555731-487e56eb04c55cc6%26q%3D1%26e%3D5f658968-17f8-498f-9acc-81014ffbff4c%26u%3Dhttps%253A%252F%252Fnam11.safelinks.protection.outlook.com%252F%253Furl%253Dhttps%25253A%25252F%25252Fprotect2.fireeye.com%25252Fv1%25252Furl%25253Fk%25253D31323334-501d5122-313273af-454445555731-cfe08b886ec13ca0%252526q%25253D1%252526e%25253Da23c8b9f-0b11-4341-81c9-8931cfbdf633%252526u%25253Dhttps%2525253A%2525252F%2525252Fpatches.dpdk.org%2525252Fproject%2525252Fdpdk%2525252Fpatch%2525252F20200603150602.4686-7-ophirmu%25252540mellanox.com%2525252F%2526data%253D04%25257C01%25257Casafp%252540nvidia.com%25257C0b6b2b393538425ee41308d9e70033bd%25257C43083d15727340c1b7db39efd9ccc17a%25257C0%25257C0%25257C637794810376687733%25257CUnknown%25257CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%25253D%25257C3000%2526sdata%253D%25252BPjs73ra1Ng3eNj2Qcjs75FMfeWWr%25252F8R48SFx2f%25252BCM4%25253D%2526reserved%253D0&data=04%7C01%7Casafp%40nvidia.com%7C1b38d6419d3143a3ab4608d9e7dd7816%7C43083d15727340c1b7db39efd9ccc17a%7C0%7C0%7C637795760671604452%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=E9OFPSnMUQamrsjxPezWD7Dthg%2B71rfAd8o%2FRv1PJyU%3D&reserved=0>
>
>
>
> and the code part that solves the error is:
>
> +       if (mlx5_class_get(pci_dev->device.devargs) != MLX5_CLASS_NET) {
>
> +                DRV_LOG(DEBUG, "Skip probing - should be probed by other
> mlx5"
>
> +                        " driver.");
>
> +                return 1;
>
> +       }
>
> Could you please confirm?
>
>
>
> Thanks,
>
>
>
> Rocío
>
>
>
> *From:* Asaf Penso <asafp@nvidia.com>
> *Sent:* Monday, January 31, 2022 12:49 PM
> *To:* Rocio Dominguez <rocio.dominguez@ericsson.com>; NBU-Contact-Thomas
> Monjalon (EXTERNAL) <thomas@monjalon.net>
> *Cc:* users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <
> viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
> *Subject:* RE: net_mlx5: unable to recognize master/representors on the
> multiple IB devices
>
>
>
> I see two differences below.
>
> First, in testpmd the version is 19.11.11, and in your application, it’s
> 20.08. See this print:
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> USER1: DPDK version: DPDK 20.08.0"}
>
>
>
> Second, in your application, I see the VFIO driver is not started properly:
>
> 20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> EAL:   cannot open VFIO container, error 2 (No such file or directory)"}
>
>
>
> Regards,
>
> Asaf Penso
>
>
>
> *From:* Rocio Dominguez <rocio.dominguez@ericsson.com>
> *Sent:* Thursday, January 20, 2022 9:49 PM
> *To:* Asaf Penso <asafp@nvidia.com>; NBU-Contact-Thomas Monjalon
> (EXTERNAL) <thomas@monjalon.net>
> *Cc:* users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <
> viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
> *Subject:* RE: net_mlx5: unable to recognize master/representors on the
> multiple IB devices
>
>
>
> Hi Asaf,
>
>
>
> I have manually compile and install the DPDK 19.11.11.
>
>
>
> Executing testpmd in the Mellanox NICs VFs where I want to run my app
> gives this result:
>
>
>
> pcgwpod009-c04:~/dpdk-stable-19.11.11 #
> ./x86_64-native-linux-gcc/app/testpmd -l 8-15 -n 4 -w d8:00.2 -w d8:00.3 -w
> d8:00.4 -w d8:00.5 -- --rxq=2 --txq=2 -i
>
> EAL: Detected 96 lcore(s)
>
> EAL: Detected 2 NUMA nodes
>
> EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
>
> EAL: Selected IOVA mode 'VA'
>
> EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs
> found for that size
>
> EAL: Probing VFIO support...
>
> EAL: VFIO support initialized
>
> EAL: PCI device 0000:d8:00.2 on NUMA socket 1
>
> EAL:   probe driver: 15b3:1014 net_mlx5
>
> EAL: PCI device 0000:d8:00.3 on NUMA socket 1
>
> EAL:   probe driver: 15b3:1014 net_mlx5
>
> EAL: PCI device 0000:d8:00.4 on NUMA socket 1
>
> EAL:   probe driver: 15b3:1014 net_mlx5
>
> EAL: PCI device 0000:d8:00.5 on NUMA socket 1
>
> EAL:   probe driver: 15b3:1014 net_mlx5
>
> Interactive-mode selected
>
> testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176,
> socket=0
>
> testpmd: preferred mempool ops selected: ring_mp_mc
>
> testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176,
> socket=1
>
> testpmd: preferred mempool ops selected: ring_mp_mc
>
> Configuring Port 0 (socket 1)
>
> Port 0: 36:FE:F0:D2:90:27
>
> Configuring Port 1 (socket 1)
>
> Port 1: 72:AC:33:BF:0A:FA
>
> Configuring Port 2 (socket 1)
>
> Port 2: 1E:8D:81:60:43:E0
>
> Configuring Port 3 (socket 1)
>
> Port 3: C2:3C:EA:94:06:B4
>
> Checking link statuses...
>
> Done
>
> testpmd>
>
>
>
> But when I run my Data Plane app, the result is
>
>
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.609+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_linux_packet_mmap_setup]
> block_size: 67108864, frame_size: 4096, block_nr: 1, frame_nr: 16384,
> mem_size: 67108864"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init]
> CTRL: pci devices added: 1, vhost user devices added: 0"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[add_pio_pci_devices_from_env_to_config]
> pci device from PCIDEVICE_MELLANOX_COM_MLNX_SRIOV_NETDEVICE=0000:d8:00.5
> found"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init]
> CTRL: requesting 1024 MiB of hugepage memory for DPDK"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> USER1: DPDK version: DPDK 20.08.0"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix
> pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:00.5
> --base-virtaddr=0x200000000 --iova-mode=va --legacy-mem --no-shconf "}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> EAL: Detected 96 lcore(s)"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> EAL: Detected 2 NUMA nodes"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.636+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> EAL: Selected IOVA mode 'VA'"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs
> found for that size"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> EAL: Probing VFIO support..."}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> EAL:   cannot open VFIO container, error 2 (No such file or directory)"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> EAL: VFIO support could not be initialized"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:17.567+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.5 (socket
> 1)"}
>
> *{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> net_mlx5: unable to recognize master/representors on the multiple IB
> devices"}*
>
> *{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> common_mlx5: Failed to load driver = net_mlx5."}*
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> EAL: Requested device 0000:d8:00.5 cannot be used"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> EAL: Bus (pci) probe failed."}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio]
> USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init]
> No network ports could be enabled!"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu]
> libpio packet module is NOT initialized"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu]
> pktsock packet module is NOT initialized"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu]
> linux packet module is initialized"}
>
> {"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu]
> tap packet module is NOT initialized"}
>
>
>
> Any idea on what could be the problem?
>
>
>
> Thanks,
>
>
>
> Rocío
>
>
>
>
>
> *From:* Asaf Penso <asafp@nvidia.com>
> *Sent:* Thursday, January 20, 2022 8:17 AM
> *To:* Rocio Dominguez <rocio.dominguez@ericsson.com>; NBU-Contact-Thomas
> Monjalon (EXTERNAL) <thomas@monjalon.net>
> *Cc:* users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <
> viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
> *Subject:* Re: net_mlx5: unable to recognize master/representors on the
> multiple IB devices
>
>
>
> Although inbox drivers come with a pre installed DPDK, you can manually
> download, compile, install, and work with whatever version you wish.
>
>
>
> Let us know the results, and we'll continue from there.
>
>
>
> Regards,
>
> Asaf Penso
> ------------------------------
>
> *From:* Rocio Dominguez <rocio.dominguez@ericsson.com>
> *Sent:* Monday, January 17, 2022 10:20:58 PM
> *To:* Asaf Penso <asafp@nvidia.com>; NBU-Contact-Thomas Monjalon
> (EXTERNAL) <thomas@monjalon.net>
> *Cc:* users@dpdk.org <users@dpdk.org>; Matan Azrad <matan@nvidia.com>;
> Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <
> rasland@nvidia.com>
> *Subject:* RE: net_mlx5: unable to recognize master/representors on the
> multiple IB devices
>
>
>
> Hi Asaf,
>
> Thanks for the prompt answer.
>
> I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE
> repositories the corresponding RPM package for SLES 15 SP2 is not
> available, the latest one is DPDK 19.11.10.
>
> I have installed it but the problem persists. It's probably solved in
> 19.11.11.
>
> There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also,
> not sure if it could be a problem to install it in SLES 15 SP2. I will try
> it anyway.
>
> Also I will try to find other way to load the 19.11.11 in SLES 15 SP2
> apart from using RPM or zipper, any suggestion is appreciated.
>
> Thanks,
>
> Rocío
>
> -----Original Message-----
> From: Asaf Penso <asafp@nvidia.com>
> Sent: Sunday, January 16, 2022 4:31 PM
> To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>; Rocio
> Dominguez <rocio.dominguez@ericsson.com>
> Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <
> viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
> Subject: RE: net_mlx5: unable to recognize master/representors on the
> multiple IB devices
>
> Hello Rocio,
> IIRC, there was a fix in a recent stable version.
> Would you please try taking latest 19.11 LTS and tell whether you still
> see the issue?
>
> Regards,
> Asaf Penso
>
> >-----Original Message-----
> >From: Thomas Monjalon <thomas@monjalon.net>
> >Sent: Sunday, January 16, 2022 3:24 PM
> >To: Rocio Dominguez <rocio.dominguez@ericsson.com>
> >Cc: users@dpdk.org; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko
> ><viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
> >Subject: Re: net_mlx5: unable to recognize master/representors on the
> >multiple IB devices
> >
> >+Cc mlx5 experts
> >
> >
> >14/01/2022 11:10, Rocio Dominguez:
> >> Hi,
> >>
> >> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
> >>
> >> I'm using:
> >>
> >> OS SLES 15 SP2
> >> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
> >> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
> >> Mellanox adapters firmware 12.28.2006 (corresponding to this
> >> MLNX_OFED version) kernel 5.3.18-24.34-default
> >>
> >>
> >> This is my SRIOV configuration for DPDK capable PCI slots:
> >>
> >>             {
> >>                 "resourceName": "mlnx_sriov_netdevice",
> >>                 "resourcePrefix": "mellanox.com",
> >>                 "isRdma": true,
> >>                 "selectors": {
> >>                     "vendors": ["15b3"],
> >>                     "devices": ["1014"],
> >>                     "drivers": ["mlx5_core"],
> >>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3",
> >> "0000:d8:00.4",
> >"0000:d8:00.5"],
> >>                     "isRdma": true
> >>                 }
> >>
> >> The sriov device plugin starts without problems, the devices are
> >> correctly
> >allocated:
> >>
> >> {
> >>   "cpu": "92",
> >>   "ephemeral-storage": "419533922385",
> >>   "hugepages-1Gi": "8Gi",
> >>   "hugepages-2Mi": "4Gi",
> >>   "intel.com/intel_sriov_dpdk": "0",
> >>   "intel.com/sriov_cre": "3",
> >>   "mellanox.com/mlnx_sriov_netdevice": "4",
> >>   "mellanox.com/sriov_dp": "0",
> >>   "memory": "183870336Ki",
> >>   "pods": "110"
> >> }
> >>
> >> The Mellanox NICs are binded to the kernel driver mlx5_core:
> >>
> >> pcgwpod009-c04:~ # dpdk-devbind --status
> >>
> >> Network devices using kernel driver
> >> ===================================
> >> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
> >> unused=vfio-pci
> >> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
> >> unused=vfio-pci
> >> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
> >> unused=vfio-pci
> >> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
> >> unused=vfio-pci
> >> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
> >> drv=mlx5_core unused=vfio-pci
> >> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
> >> drv=mlx5_core unused=vfio-pci
> >> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
> >> if=p3p1 drv=ixgbe unused=vfio-pci
> >> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
> >> if=p3p2 drv=ixgbe unused=vfio-pci
> >> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
> >> drv=ixgbevf unused=vfio-pci
> >> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
> >> if=p3p1_1 drv=ixgbevf unused=vfio-pci
> >> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
> >> drv=ixgbevf unused=vfio-pci
> >> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
> >> if=p3p1_3 drv=ixgbevf unused=vfio-pci
> >> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
> >> if=p4p1 drv=ixgbe unused=vfio-pci
> >> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
> >> if=p4p2 drv=ixgbe unused=vfio-pci
> >> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
> >> drv=mlx5_core unused=vfio-pci
> >> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
> >> drv=mlx5_core unused=vfio-pci
> >> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
> >> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
> >> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
> >> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
> >> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
> >> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
> >> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
> >> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
> >>
> >> The interfaces are up:
> >>
> >> pcgwpod009-c04:~ # ibdev2netdev -v
> >> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
> >QSFP28
> >> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
> >> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
> >QSFP28
> >> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
> >> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
> >QSFP28
> >> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
> >> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
> >QSFP28
> >> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
> >> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
> >> enp216s0f2 (Up)
> >> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
> >> enp216s0f3 (Up)
> >> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
> >> enp216s0f4 (Up)
> >> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
> >> enp216s0f5 (Up) pcgwpod009-c04:~ #
> >>
> >>
> >> But when I run my application the Mellanox adapters are probed and I
> >obtain the following error:
> >>
> >> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
> >> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
> >> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
> >> i
> >> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
> >> "6"},"message":"[pio] net_mlx5: unable to recognize
> >> master/representors on the multiple IB devices"}
> >> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
> >> i
> >> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
> >> "6"},"message":"[pio] common_mlx5: Failed to load driver =
> >> net_mlx5."}
> >> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
> >> i
> >> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
> >> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
> >> used"}
> >> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
> >> i
> >> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
> >> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
> >> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
> >> i
> >> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
> >> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
> >> actual 0 ports."}
> >> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
> >> i
> >> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
> >> :"6"},"message":"[pktio_libpio_init] No network ports could be
> >> enabled!"}
> >>
> >> Could you please help me with this issue?
> >>
> >>
> >> Thanks,
> >>
> >> Rocío
> >>
> >
> >
> >
> >
>

[-- Attachment #2: Type: text/html, Size: 58385 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

* RE: net_mlx5: unable to recognize master/representors on the multiple IB devices
  2022-02-04 14:55                         ` Muhammad Zain-ul-Abideen
@ 2022-02-07 17:14                           ` Rocio Dominguez
  0 siblings, 0 replies; 15+ messages in thread
From: Rocio Dominguez @ 2022-02-07 17:14 UTC (permalink / raw)
  To: Muhammad Zain-ul-Abideen, Asaf Penso
  Cc: NBU-Contact-Thomas Monjalon (EXTERNAL),
	Ferruh Yigit, Qi Zhang, users, Matan Azrad, Slava Ovsiienko,
	Raslan Darawsheh

[-- Attachment #1: Type: text/plain, Size: 36487 bytes --]

There was 1 Mellanox NIC on NUMA 0 and other one on NUMA 1.
Both have been replaced so I cannot test them now.

Regards,

Rocío

From: Muhammad Zain-ul-Abideen <zain2294@gmail.com>
Sent: Friday, February 4, 2022 3:55 PM
To: Asaf Penso <asafp@nvidia.com>
Cc: Rocio Dominguez <rocio.dominguez@ericsson.com>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net>; Ferruh Yigit <ferruh.yigit@intel.com>; Qi Zhang <qi.z.zhang@intel.com>; users <users@dpdk.org>; Matan Azrad <matan@nvidia.com>; Slava Ovsiienko <viacheslavo@nvidia.com>; Raslan Darawsheh <rasland@nvidia.com>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices

Was the mlx card on cpu2?

On Fri, Feb 4, 2022, 7:09 PM Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>> wrote:
Great, thanks for the update.
I think the community can benefit if you try with Mellanox NIC and find an issue that will be resolved.

Regards,
Asaf Penso
________________________________
From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Friday, February 4, 2022 2:54:20 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>; Ferruh Yigit <ferruh.yigit@intel.com<mailto:ferruh.yigit@intel.com>>; Qi Zhang <qi.z.zhang@intel.com<mailto:qi.z.zhang@intel.com>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices


Hi Asaf,



Finally I solved the problem with Intel NICs. I am using Dual NUMA, and I realized that my application is using cpus from NUMA 0 while I was assigning a NIC from NUMA 1. Using a NIC from NUMA 0 solved the problem.



I don’t know if the problem with Mellanox NICs could be solved in the same way. But for the moment, we will use Intel NICs.



Thanks,



Rocío



From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Thursday, February 3, 2022 11:50 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>; Ferruh Yigit <ferruh.yigit@intel.com<mailto:ferruh.yigit@intel.com>>; Qi Zhang <qi.z.zhang@intel.com<mailto:qi.z.zhang@intel.com>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hello Rocio,



For Intel’s NIC it would be better to take it with @Ferruh Yigit<mailto:ferruh.yigit@intel.com>/@Qi Zhang<mailto:qi.z.zhang@intel.com>

For Nvidia’s let’s continue together.



Regards,

Asaf Penso



From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Thursday, February 3, 2022 12:30 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,



We have replaced the Mellanox NICs by Intel NICs trying to avoid this problem, but it’s not working also, this time with the following error:



{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.377+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"8"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_INTEL_COM_INTEL_SRIOV_DPDK=0000:d8:02.1 found"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.378+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:02.1 --base-virtaddr=0x200000000 --legacy-mem --no-shconf "}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Detected 96 lcore(s)"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.384+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Detected 2 NUMA nodes"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.386+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Probing VFIO support..."}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:37.387+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: VFIO support initialized"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.358+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL:   using IOMMU type 1 (Type 1)"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Probe PCI driver: net_i40e_vf (8086:154c) device: 0000:d8:02.1 (socket 1)"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Releasing pci mapped resource for 0000:d8:02.1"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40000000"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.704+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Calling pci_unmap_resource for 0000:d8:02.1 at 0xa40010000"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Requested device 0000:d8:02.1 cannot be used"}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.828+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] EAL: Bus (pci) probe failed."}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}

{"version":"0.2.0","timestamp":"2022-02-02T14:43:38.891+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_libpio_init] No network ports could be enabled!"}



As using Intel NICs, now I have create the VFs and bind them to vfio-pci driver



pcgwpod009-c04:~ # dpdk-devbind --status



N Network devices using DPDK-compatible driver

============================================

0000:d8:02.0 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf

0000:d8:02.1 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf

0000:d8:02.2 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf

0000:d8:02.3 'Ethernet Virtual Function 700 Series 154c' drv=vfio-pci unused=iavf



Network devices using kernel driver

===================================

0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe unused=vfio-pci

0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe unused=vfio-pci

0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe unused=vfio-pci

0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe unused=vfio-pci

0000:3b:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p1 drv=i40e unused=vfio-pci

0000:3b:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p1p2 drv=i40e unused=vfio-pci

0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p1 drv=ixgbe unused=vfio-pci

0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p3p2 drv=ixgbe unused=vfio-pci

0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_0 drv=ixgbevf unused=vfio-pci

0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed' if=p3p1_1 drv=ixgbevf unused=vfio-pci

0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci

0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed' if= drv=ixgbevf unused=vfio-pci

0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p1 drv=ixgbe unused=vfio-pci

0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb' if=p4p2 drv=ixgbe unused=vfio-pci

0000:d8:00.0 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p1 drv=i40e unused=vfio-pci

0000:d8:00.1 'Ethernet Controller XXV710 for 25GbE SFP28 158b' if=p8p2 drv=i40e unused=vfio-pci



The interfaces are up:



pcgwpod009-c04:~ # ip link show dev p8p1

290: p8p1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000

    link/ether 40:a6:b7:0d:98:b0 brd ff:ff:ff:ff:ff:ff

    vf 0     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off

    vf 1     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off

    vf 2     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off

    vf 3     link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off

pcgwpod009-c04:~ #



The testpmd is working:



pcgwpod009-c04:~ # testpmd -l 8-15 -n 4 -w d8:02.0 -w d8:02.1 -w d8:02.2 -w d8:02.3 -- --rxq=2 --txq=2 -i

EAL: Detected 96 lcore(s)

EAL: Detected 2 NUMA nodes

EAL: Multi-process socket /var/run/dpdk/rte/mp_socket

EAL: Selected IOVA mode 'VA'

EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size

EAL: Probing VFIO support...

EAL: VFIO support initialized

EAL: PCI device 0000:d8:02.0 on NUMA socket 1

EAL:   probe driver: 8086:154c net_i40e_vf

EAL:   using IOMMU type 1 (Type 1)

EAL: PCI device 0000:d8:02.1 on NUMA socket 1

EAL:   probe driver: 8086:154c net_i40e_vf

EAL: PCI device 0000:d8:02.2 on NUMA socket 1

EAL:   probe driver: 8086:154c net_i40e_vf

EAL: PCI device 0000:d8:02.3 on NUMA socket 1

EAL:   probe driver: 8086:154c net_i40e_vf

Interactive-mode selected

testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0

testpmd: preferred mempool ops selected: ring_mp_mc

testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1

testpmd: preferred mempool ops selected: ring_mp_mc

Configuring Port 0 (socket 1)

Port 0: FE:72:DB:BE:05:EF

Configuring Port 1 (socket 1)

Port 1: 5E:C5:3E:86:1A:84

Configuring Port 2 (socket 1)

Port 2: 42:F0:5D:B0:1F:B3

Configuring Port 3 (socket 1)

Port 3: 46:00:42:2F:A2:DE

Checking link statuses...

Done

testpmd>



Any idea on what could be causing the error this time?



Thanks,



Rocío



From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Monday, January 31, 2022 6:02 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices



We'll need to check, but how do you want to proceed?

You either need 19.11 LTS or 20.11 LTS to work properly.



Regards,

Asaf Penso

________________________________

From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 31, 2022 2:01:43 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,



Yes, it seems that DPDK version 20.08 code is built-in with the VNF I’m deploying, so it is always using this version, which apparently doesn’t have the patch that overrides this error.



I think the patch is the following:

https://patches.dpdk.org/project/dpdk/patch/20200603150602.4686-7-ophirmu@mellanox.com/<https://protect2.fireeye.com/v1/url?k=31323334-501d5122-313273af-454445555731-625e8327c0a815a3&q=1&e=a94986c6-7bee-47a1-bf94-b82012b0a645&u=https%3A%2F%2Fnam11.safelinks.protection.outlook.com%2F%3Furl%3Dhttps%253A%252F%252Fprotect2.fireeye.com%252Fv1%252Furl%253Fk%253D31323334-501d5122-313273af-454445555731-487e56eb04c55cc6%2526q%253D1%2526e%253D5f658968-17f8-498f-9acc-81014ffbff4c%2526u%253Dhttps%25253A%25252F%25252Fnam11.safelinks.protection.outlook.com%25252F%25253Furl%25253Dhttps%2525253A%2525252F%2525252Fprotect2.fireeye.com%2525252Fv1%2525252Furl%2525253Fk%2525253D31323334-501d5122-313273af-454445555731-cfe08b886ec13ca0%25252526q%2525253D1%25252526e%2525253Da23c8b9f-0b11-4341-81c9-8931cfbdf633%25252526u%2525253Dhttps%252525253A%252525252F%252525252Fpatches.dpdk.org%252525252Fproject%252525252Fdpdk%252525252Fpatch%252525252F20200603150602.4686-7-ophirmu%2525252540mellanox.com%252525252F%252526data%25253D04%2525257C01%2525257Casafp%25252540nvidia.com%2525257C0b6b2b393538425ee41308d9e70033bd%2525257C43083d15727340c1b7db39efd9ccc17a%2525257C0%2525257C0%2525257C637794810376687733%2525257CUnknown%2525257CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%2525253D%2525257C3000%252526sdata%25253D%2525252BPjs73ra1Ng3eNj2Qcjs75FMfeWWr%2525252F8R48SFx2f%2525252BCM4%2525253D%252526reserved%25253D0%26data%3D04%257C01%257Casafp%2540nvidia.com%257C1b38d6419d3143a3ab4608d9e7dd7816%257C43083d15727340c1b7db39efd9ccc17a%257C0%257C0%257C637795760671604452%257CUnknown%257CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%253D%257C3000%26sdata%3DE9OFPSnMUQamrsjxPezWD7Dthg%252B71rfAd8o%252FRv1PJyU%253D%26reserved%3D0>



and the code part that solves the error is:

+       if (mlx5_class_get(pci_dev->device.devargs) != MLX5_CLASS_NET) {

+                DRV_LOG(DEBUG, "Skip probing - should be probed by other mlx5"

+                        " driver.");

+                return 1;

+       }

Could you please confirm?



Thanks,



Rocío



From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Monday, January 31, 2022 12:49 PM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



I see two differences below.

First, in testpmd the version is 19.11.11, and in your application, it’s 20.08. See this print:

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}



Second, in your application, I see the VFIO driver is not started properly:

20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}



Regards,

Asaf Penso



From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Thursday, January 20, 2022 9:49 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,



I have manually compile and install the DPDK 19.11.11.



Executing testpmd in the Mellanox NICs VFs where I want to run my app gives this result:



pcgwpod009-c04:~/dpdk-stable-19.11.11 # ./x86_64-native-linux-gcc/app/testpmd -l 8-15 -n 4 -w d8:00.2 -w d8:00.3 -w d8:00.4 -w d8:00.5 -- --rxq=2 --txq=2 -i

EAL: Detected 96 lcore(s)

EAL: Detected 2 NUMA nodes

EAL: Multi-process socket /var/run/dpdk/rte/mp_socket

EAL: Selected IOVA mode 'VA'

EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size

EAL: Probing VFIO support...

EAL: VFIO support initialized

EAL: PCI device 0000:d8:00.2 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.3 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.4 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

EAL: PCI device 0000:d8:00.5 on NUMA socket 1

EAL:   probe driver: 15b3:1014 net_mlx5

Interactive-mode selected

testpmd: create a new mbuf pool <mbuf_pool_socket_0>: n=203456, size=2176, socket=0

testpmd: preferred mempool ops selected: ring_mp_mc

testpmd: create a new mbuf pool <mbuf_pool_socket_1>: n=203456, size=2176, socket=1

testpmd: preferred mempool ops selected: ring_mp_mc

Configuring Port 0 (socket 1)

Port 0: 36:FE:F0:D2:90:27

Configuring Port 1 (socket 1)

Port 1: 72:AC:33:BF:0A:FA

Configuring Port 2 (socket 1)

Port 2: 1E:8D:81:60:43:E0

Configuring Port 3 (socket 1)

Port 3: C2:3C:EA:94:06:B4

Checking link statuses...

Done

testpmd>



But when I run my Data Plane app, the result is



{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.609+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[pktio_linux_packet_mmap_setup] block_size: 67108864, frame_size: 4096, block_nr: 1, frame_nr: 16384, mem_size: 67108864"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: pci devices added: 1, vhost user devices added: 0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"7"},"message":"[add_pio_pci_devices_from_env_to_config] pci device from PCIDEVICE_MELLANOX_COM_MLNX_SRIOV_NETDEVICE=0000:d8:00.5 found"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] CTRL: requesting 1024 MiB of hugepage memory for DPDK"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: DPDK version: DPDK 20.08.0"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.610+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: rte_eal_init() args: pio -m 1024 -n 4 --no-telemetry --file-prefix pio-0 --master-lcore=4 --lcores=4@(4) --pci-whitelist 0000:d8:00.5 --base-virtaddr=0x200000000 --iova-mode=va --legacy-mem --no-shconf "}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 96 lcore(s)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.618+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Detected 2 NUMA nodes"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.636+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Selected IOVA mode 'VA'"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: 2048 hugepages of size 2097152 reserved, but no mounted hugetlbfs found for that size"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probing VFIO support..."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL:   cannot open VFIO container, error 2 (No such file or directory)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:16.637+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: VFIO support could not be initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.567+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci (15b3:1014) device: 0000:d8:00.5 (socket 1)"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] net_mlx5: unable to recognize master/representors on the multiple IB devices"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] common_mlx5: Failed to load driver = net_mlx5."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Requested device 0000:d8:00.5 cannot be used"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.569+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] EAL: Bus (pci) probe failed."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports, actual 0 ports."}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_libpio_init] No network ports could be enabled!"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] libpio packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] pktsock packet module is NOT initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] linux packet module is initialized"}

{"version":"0.2.0","timestamp":"2022-01-20T19:19:17.631+00:00","severity":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":"6"},"message":"[pktio_init_cpu] tap packet module is NOT initialized"}



Any idea on what could be the problem?



Thanks,



Rocío





From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Thursday, January 20, 2022 8:17 AM
To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: Re: net_mlx5: unable to recognize master/representors on the multiple IB devices



Although inbox drivers come with a pre installed DPDK, you can manually download, compile, install, and work with whatever version you wish.



Let us know the results, and we'll continue from there.



Regards,

Asaf Penso

________________________________

From: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Sent: Monday, January 17, 2022 10:20:58 PM
To: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>; NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>
Cc: users@dpdk.org<mailto:users@dpdk.org> <users@dpdk.org<mailto:users@dpdk.org>>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices



Hi Asaf,

Thanks for the prompt answer.

I have checked that the latest 19.11 LTS is 19.11.11, but in OpenSUSE repositories the corresponding RPM package for SLES 15 SP2 is not available, the latest one is DPDK 19.11.10.

I have installed it but the problem persists. It's probably solved in 19.11.11.

There is a RPM package in SLES 15 SP3 for DPDK 20.11.3, which is LTS also, not sure if it could be a problem to install it in SLES 15 SP2. I will try it anyway.

Also I will try to find other way to load the 19.11.11 in SLES 15 SP2 apart from using RPM or zipper, any suggestion is appreciated.

Thanks,

Rocío

-----Original Message-----
From: Asaf Penso <asafp@nvidia.com<mailto:asafp@nvidia.com>>
Sent: Sunday, January 16, 2022 4:31 PM
To: NBU-Contact-Thomas Monjalon (EXTERNAL) <thomas@monjalon.net<mailto:thomas@monjalon.net>>; Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko <viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
Subject: RE: net_mlx5: unable to recognize master/representors on the multiple IB devices

Hello Rocio,
IIRC, there was a fix in a recent stable version.
Would you please try taking latest 19.11 LTS and tell whether you still see the issue?

Regards,
Asaf Penso

>-----Original Message-----
>From: Thomas Monjalon <thomas@monjalon.net<mailto:thomas@monjalon.net>>
>Sent: Sunday, January 16, 2022 3:24 PM
>To: Rocio Dominguez <rocio.dominguez@ericsson.com<mailto:rocio.dominguez@ericsson.com>>
>Cc: users@dpdk.org<mailto:users@dpdk.org>; Matan Azrad <matan@nvidia.com<mailto:matan@nvidia.com>>; Slava Ovsiienko
><viacheslavo@nvidia.com<mailto:viacheslavo@nvidia.com>>; Raslan Darawsheh <rasland@nvidia.com<mailto:rasland@nvidia.com>>
>Subject: Re: net_mlx5: unable to recognize master/representors on the
>multiple IB devices
>
>+Cc mlx5 experts
>
>
>14/01/2022 11:10, Rocio Dominguez:
>> Hi,
>>
>> I'm doing a setup with Mellanox ConnectX-4 (MCX416A-CCA) NICs.
>>
>> I'm using:
>>
>> OS SLES 15 SP2
>> DPDK 19.11.4 (the official supported version for SLES 15 SP2)
>> MLNX_OFED_LINUX-5.5-1.0.3.2-sles15sp2-x86_64 (the latest one)
>> Mellanox adapters firmware 12.28.2006 (corresponding to this
>> MLNX_OFED version) kernel 5.3.18-24.34-default
>>
>>
>> This is my SRIOV configuration for DPDK capable PCI slots:
>>
>>             {
>>                 "resourceName": "mlnx_sriov_netdevice",
>>                 "resourcePrefix": "mellanox.com<https://protect2.fireeye.com/v1/url?k=31323334-501d5122-313273af-454445555731-d95593f91e5769a5&q=1&e=a94986c6-7bee-47a1-bf94-b82012b0a645&u=http%3A%2F%2Fmellanox.com%2F>",
>>                 "isRdma": true,
>>                 "selectors": {
>>                     "vendors": ["15b3"],
>>                     "devices": ["1014"],
>>                     "drivers": ["mlx5_core"],
>>                     "pciAddresses": ["0000:d8:00.2", "0000:d8:00.3",
>> "0000:d8:00.4",
>"0000:d8:00.5"],
>>                     "isRdma": true
>>                 }
>>
>> The sriov device plugin starts without problems, the devices are
>> correctly
>allocated:
>>
>> {
>>   "cpu": "92",
>>   "ephemeral-storage": "419533922385",
>>   "hugepages-1Gi": "8Gi",
>>   "hugepages-2Mi": "4Gi",
>>   "intel.com/intel_sriov_dpdk<http://intel.com/intel_sriov_dpdk>": "0",
>>   "intel.com/sriov_cre<http://intel.com/sriov_cre>": "3",
>>   "mellanox.com/mlnx_sriov_netdevice<https://protect2.fireeye.com/v1/url?k=31323334-501d5122-313273af-454445555731-be5ad5ed36751c22&q=1&e=a94986c6-7bee-47a1-bf94-b82012b0a645&u=http%3A%2F%2Fmellanox.com%2Fmlnx_sriov_netdevice>": "4",
>>   "mellanox.com/sriov_dp<https://protect2.fireeye.com/v1/url?k=31323334-501d5122-313273af-454445555731-4d7cdd3f927e3a6d&q=1&e=a94986c6-7bee-47a1-bf94-b82012b0a645&u=http%3A%2F%2Fmellanox.com%2Fsriov_dp>": "0",
>>   "memory": "183870336Ki",
>>   "pods": "110"
>> }
>>
>> The Mellanox NICs are binded to the kernel driver mlx5_core:
>>
>> pcgwpod009-c04:~ # dpdk-devbind --status
>>
>> Network devices using kernel driver
>> ===================================
>> 0000:18:00.0 'Ethernet Controller 10G X550T 1563' if=em1 drv=ixgbe
>> unused=vfio-pci
>> 0000:18:00.1 'Ethernet Controller 10G X550T 1563' if=em2 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.0 'Ethernet Controller 10G X550T 1563' if=em3 drv=ixgbe
>> unused=vfio-pci
>> 0000:19:00.1 'Ethernet Controller 10G X550T 1563' if=em4 drv=ixgbe
>> unused=vfio-pci
>> 0000:3b:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:3b:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp59s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:5e:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p1 drv=ixgbe unused=vfio-pci
>> 0000:5e:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p3p2 drv=ixgbe unused=vfio-pci
>> 0000:5e:10.0 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.2 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_1 drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.4 '82599 Ethernet Controller Virtual Function 10ed' if=
>> drv=ixgbevf unused=vfio-pci
>> 0000:5e:10.6 '82599 Ethernet Controller Virtual Function 10ed'
>> if=p3p1_3 drv=ixgbevf unused=vfio-pci
>> 0000:af:00.0 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p1 drv=ixgbe unused=vfio-pci
>> 0000:af:00.1 '82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb'
>> if=p4p2 drv=ixgbe unused=vfio-pci
>> 0000:d8:00.0 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f0
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.1 'MT27700 Family [ConnectX-4] 1013' if=enp216s0f1
>> drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.2 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f2 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.3 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f3 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.4 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f4 drv=mlx5_core unused=vfio-pci
>> 0000:d8:00.5 'MT27700 Family [ConnectX-4 Virtual Function] 1014'
>> if=enp216s0f5 drv=mlx5_core unused=vfio-pci
>>
>> The interfaces are up:
>>
>> pcgwpod009-c04:~ # ibdev2netdev -v
>> 0000:3b:00.0 mlx5_0 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f0 (Up)
>> 0000:3b:00.1 mlx5_1 (MT4115 - MT1646K01301) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp59s0f1 (Up)
>> 0000:d8:00.0 mlx5_2 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f0 (Up)
>> 0000:d8:00.1 mlx5_3 (MT4115 - MT1646K00538) CX416A - ConnectX-4
>QSFP28
>> fw 12.28.2006 port 1 (ACTIVE) ==> enp216s0f1 (Up)
>> 0000:d8:00.2 mlx5_4 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f2 (Up)
>> 0000:d8:00.3 mlx5_5 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f3 (Up)
>> 0000:d8:00.4 mlx5_6 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f4 (Up)
>> 0000:d8:00.5 mlx5_7 (MT4116 - NA)  fw 12.28.2006 port 1 (ACTIVE) ==>
>> enp216s0f5 (Up) pcgwpod009-c04:~ #
>>
>>
>> But when I run my application the Mellanox adapters are probed and I
>obtain the following error:
>>
>> {"proc_id":"6"},"message":"[pio] EAL: Probe PCI driver: mlx5_pci
>> (15b3:1014) device: 0000:d8:00.4 (socket 1)"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] net_mlx5: unable to recognize
>> master/representors on the multiple IB devices"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] common_mlx5: Failed to load driver =
>> net_mlx5."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Requested device 0000:d8:00.4 cannot be
>> used"}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.826+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] EAL: Bus (pci) probe failed."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"info","service_id":"eric-pc-up-data-plane","metadata":{"proc_id":
>> "6"},"message":"[pio] USER1: ports init fail in DPDK, expect 1 ports,
>> actual 0 ports."}
>> {"version":"0.2.0","timestamp":"2022-01-14T09:51:39.890+00:00","sever
>> i
>> ty":"error","service_id":"eric-pc-up-data-plane","metadata":{"proc_id"
>> :"6"},"message":"[pktio_libpio_init] No network ports could be
>> enabled!"}
>>
>> Could you please help me with this issue?
>>
>>
>> Thanks,
>>
>> Rocío
>>
>
>
>
>

[-- Attachment #2: Type: text/html, Size: 64784 bytes --]

^ permalink raw reply	[flat|nested] 15+ messages in thread

end of thread, other threads:[~2022-02-10  9:12 UTC | newest]

Thread overview: 15+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-01-14 10:10 net_mlx5: unable to recognize master/representors on the multiple IB devices Rocio Dominguez
2022-01-16 13:23 ` Thomas Monjalon
2022-01-16 15:30   ` Asaf Penso
2022-01-17 20:20     ` Rocio Dominguez
2022-01-20  7:16       ` Asaf Penso
2022-01-20 19:48         ` Rocio Dominguez
2022-01-31 11:49           ` Asaf Penso
2022-01-31 12:01             ` Rocio Dominguez
2022-01-31 17:02               ` Asaf Penso
2022-02-03 10:30                 ` Rocio Dominguez
2022-02-03 10:49                   ` Asaf Penso
2022-02-04 12:54                     ` Rocio Dominguez
2022-02-04 14:09                       ` Asaf Penso
2022-02-04 14:55                         ` Muhammad Zain-ul-Abideen
2022-02-07 17:14                           ` Rocio Dominguez

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).