Re: [dpdk-users] Unable to launch testpmd with Mellanox ConnectX-3 Pro NIC

[Timur Bogdanov]

Yes, the problem was in this parameter and after changing it to "-1"
testpmd application has been started successfully.

BUT, it started successfully only on server where Mellanox OFED is installed.

On  another server a rdma-core was installed from sources. (rpm's were
built and installed)
I also changed the value of log_num_mgm_entry_size parameter to "-1"
and restarted a server (since where is no openibd service on this
server) and got the same error.
Maybe mlx4_core kernel module parameter should be changed in some
other config file?

Anyway, I can also install and use OFED instead of RDMA but the RDMA
is pointed as recommended on instructions page
"http://dpdk.org/doc/guides/nics/mlx4.html; and it is interesting to
bring it to working state.
/Regards, Timur


On Thu, Jan 18, 2018 at 11:48 AM, Adrien Mazarguil
 wrote:
> On Tue, Jan 16, 2018 at 06:59:31PM +0300, Timur Bogdanov wrote:
>> Hi,
>>
>> I'm trying to use dpdk with Mellanox ConnectX-3 Pro NIC.
>> I built PMD for it according to instructions on
>> "http://dpdk.org/doc/guides/nics/mlx4.html; and tried to launch
>> testpmd app but got following error:
> 
>> PMD: net_mlx4: 0xda13c0: cannot attach flow rules (code 95, "Operation
>> not supported"), flow error type 2, cause 0x7f2869cdab80, message:
>> flow rule rejected by device
>>
>> Fail to start port 0
> 
>> What can be the reason of testpmd does not start correctly?
>
> Did you provide by any chance -7 instead of -1 as a value for mlx4_core.ko's
> log_num_mgm_entry_size parameter (as recommended by the above
> documentation)?
>
> Timothy (CC'ed) reported that -7 does not quite work with the default flow
> rules (too many limitations) and results in the above error message. -1
> should be used, -7 is only for specific use cases and should probably not
> even be documented in this file.
>
> --
> Adrien Mazarguil
> 6WIND

Re: [dpdk-users] Unable to launch testpmd with Mellanox ConnectX-3 Pro NIC

[Adrien Mazarguil]

On Thu, Jan 18, 2018 at 03:11:16PM +0300, Timur Bogdanov wrote:
> Yes, the problem was in this parameter and after changing it to "-1"
> testpmd application has been started successfully.
> 
> BUT, it started successfully only on server where Mellanox OFED is installed.
> 
> On  another server a rdma-core was installed from sources. (rpm's were
> built and installed)
> I also changed the value of log_num_mgm_entry_size parameter to "-1"
> and restarted a server (since where is no openibd service on this
> server) and got the same error.
> Maybe mlx4_core kernel module parameter should be changed in some
> other config file?

In case MLNX_OFED is *not* installed, do both rdma-core and kernel version
meet the minimum requirements?

- rdma-core v15
- Linux 4.14

Note while the above versions are fine for mlx5 (ConnectX-4, ConnectX-5),
they provide reduced performance and RSS capabilities for mlx4 (ConnectX-3),
for which I recommend to use at least:

- rdma-core v16
- Linux 4.15 (not released yet, 4.15-rc8 will do in the meantime)

> Anyway, I can also install and use OFED instead of RDMA but the RDMA
> is pointed as recommended on instructions page
> "http://dpdk.org/doc/guides/nics/mlx4.html; and it is interesting to
> bring it to working state.
> /Regards, Timur

rdma-core requires an up-to-date kernel. If this can't be satisfied,
MLNX_OFED is the only alternative (the mlnx-ofa_kernel package).

> On Thu, Jan 18, 2018 at 11:48 AM, Adrien Mazarguil
>  wrote:
> > On Tue, Jan 16, 2018 at 06:59:31PM +0300, Timur Bogdanov wrote:
> >> Hi,
> >>
> >> I'm trying to use dpdk with Mellanox ConnectX-3 Pro NIC.
> >> I built PMD for it according to instructions on
> >> "http://dpdk.org/doc/guides/nics/mlx4.html; and tried to launch
> >> testpmd app but got following error:
> > 
> >> PMD: net_mlx4: 0xda13c0: cannot attach flow rules (code 95, "Operation
> >> not supported"), flow error type 2, cause 0x7f2869cdab80, message:
> >> flow rule rejected by device
> >>
> >> Fail to start port 0
> > 
> >> What can be the reason of testpmd does not start correctly?
> >
> > Did you provide by any chance -7 instead of -1 as a value for mlx4_core.ko's
> > log_num_mgm_entry_size parameter (as recommended by the above
> > documentation)?
> >
> > Timothy (CC'ed) reported that -7 does not quite work with the default flow
> > rules (too many limitations) and results in the above error message. -1
> > should be used, -7 is only for specific use cases and should probably not
> > even be documented in this file.
> >
> > --
> > Adrien Mazarguil
> > 6WIND

-- 
Adrien Mazarguil
6WIND

Re: [dpdk-users] Does BONDING_MODE_8023AD is works in 17.11?

[Thomas Monjalon]

No reply after 2 months, adding maintainer Cc.

17/11/2017 23:24, Алексей Телятников:
> Greetings. I have issue with link-aggregation in DPDK. My HP A5820X 
> switch does not recive LACP from DPDK application.
> 
> Has anyone worked with BONDING_MODE_8023AD?
> 
> I have: DPDK 17.11 HEAD & 11.1-RELEASE-p4 FreeBSD
> 
> Also I build examples/bond with little changes:
> 
> --- a/examples/bond/main.c
> +++ b/examples/bond/main.c
> @@ -226,7 +226,7 @@ bond_port_init(struct rte_mempool *mbuf_pool)
>  uint16_t nb_rxd = RTE_RX_DESC_DEFAULT;
>  uint16_t nb_txd = RTE_TX_DESC_DEFAULT;
> 
> -   retval = rte_eth_bond_create("bond0", BONDING_MODE_ALB,
> +   retval = rte_eth_bond_create("net_bonding0", BONDING_MODE_8023AD,
>  0 /*SOCKET_ID_ANY*/);
>  if (retval < 0)
>  rte_exit(EXIT_FAILURE,
> 
> Run it:
> 
> $ sudo build/bond_app
> EAL: Sysctl reports 16 cpus
> EAL: Detected 16 lcore(s)
> EAL: Contigmem driver has 1 buffers, each of size 32GB
> EAL: Mapped memory segment 1 @ 0x8023ff000: physaddr:0x8, len 
> 34359738368
> EAL: PCI device :03:00.0 on NUMA socket 0
> EAL:   probe driver: 8086:1521 net_e1000_igb
> EAL:   :03:00.0 not managed by UIO driver, skipping
> EAL: PCI device :03:00.3 on NUMA socket 0
> EAL:   probe driver: 8086:1521 net_e1000_igb
> EAL:   :03:00.3 not managed by UIO driver, skipping
> EAL: PCI device :05:00.0 on NUMA socket 0
> EAL:   probe driver: 8086:10fb net_ixgbe
> EAL: PCI device :05:00.1 on NUMA socket 0
> EAL:   probe driver: 8086:10fb net_ixgbe
> User device list:
> PMD: ixgbe_dev_link_status_print():  Port 0: Link Down
> Port 0 MAC: 90:e2:ba:d0:a3:c4
> PMD: ixgbe_dev_link_status_print():  Port 1: Link Down
> Port 1 MAC: 90:e2:ba:d0:a3:c5
> EAL: Initializing pmd_bond for net_bonding0
> PMD: Using mode 4, it is necessary to do TX burst and RX burst at least 
> every 100ms.
> EAL: Create bonded device net_bonding0 on port 2 in mode 4 on socket 0.
> PMD: ixgbe_dev_link_status_print():  Port 0: Link Down
> PMD: ixgbe_dev_link_status_print():  Port 1: Link Down
> Port 2 MAC: 90:e2:ba:d0:a3:c4
> Starting lcore_main on core 1:0 Our IP:7.0.0.10
> bond6>show
> 90:e2:ba:d0:a3:c4
> 90:e2:ba:d0:a3:c5
> Active_slaves:0 packets received:Tot:0 Arp:0 IPv4:0
> 
> Active slaves always 0. I tried configure bond in testpmd. Same problem.
> 
> On the switch all ports is in up state but:
> 
> Received LACP Packets: 0 packet(s)
> 
> 

[dpdk-users] kni interface about X710

[Xiao, Xiaohong (NSB - CN/Shanghai)]

Hello
We are trying to create kni interfaces on the X710 ethernet interface, so that 
the function kni_ioctl_create() is called. But we falls to below “else” branch 
and get a random MAC address on the created kni interface.
And we also noticed that, for igb/ixgbe devices, no above issue �C it goes with 
below “if” branch.
Is there a plan to develop a function like i40e_kni_probe() to provide similar 
function of existing igb_kni_probe() / ixgbe_kni_probe()？Or can you please 
suggest a way how to set the real MAC here?

Thanks a lot.
Xiao Xiaohong

if (kni->lad_dev)
   memcpy(net_dev->dev_addr, kni->lad_dev->dev_addr, ETH_ALEN);
 else
   /*
   * Generate random mac address. eth_random_addr() is the newer
   * version of generating mac address in linux kernel.
   */
 {
random_ether_addr(net_dev->dev_addr);

Re: [dpdk-users] Unable to launch testpmd with Mellanox ConnectX-3 Pro NIC

[Adrien Mazarguil]

On Tue, Jan 16, 2018 at 06:59:31PM +0300, Timur Bogdanov wrote:
> Hi,
> 
> I'm trying to use dpdk with Mellanox ConnectX-3 Pro NIC.
> I built PMD for it according to instructions on
> "http://dpdk.org/doc/guides/nics/mlx4.html; and tried to launch
> testpmd app but got following error:

> PMD: net_mlx4: 0xda13c0: cannot attach flow rules (code 95, "Operation
> not supported"), flow error type 2, cause 0x7f2869cdab80, message:
> flow rule rejected by device
> 
> Fail to start port 0

> What can be the reason of testpmd does not start correctly?

Did you provide by any chance -7 instead of -1 as a value for mlx4_core.ko's
log_num_mgm_entry_size parameter (as recommended by the above
documentation)?

Timothy (CC'ed) reported that -7 does not quite work with the default flow
rules (too many limitations) and results in the above error message. -1
should be used, -7 is only for specific use cases and should probably not
even be documented in this file.

-- 
Adrien Mazarguil
6WIND