[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2024-12-05 Thread Marcus D. Leech
On 05/12/2024 14:15, Houshang wrote: Hello It 8s not rj45.it is sfp If your baseline performance cannot even support 25Msps in "benchmark_rate", it's unlikely that DPDK will push you   into a territory where you can support 125Msps. I assume that you've done the performance tu

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2024-12-05 Thread Marcus D. Leech
On 05/12/2024 14:15, Houshang wrote: Hello It 8s not rj45.it is sfp My mistake. On Thu, Dec 5, 2024, 7:47 PM Marcus D. Leech wrote: On 05/12/2024 12:27, Houshang wrote: Hi Marcus Here it is: ad@bm-super11-intel:~$ sudo /usr/local/lib/uhd/examples/be

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2024-12-05 Thread Houshang
Hello It 8s not rj45.it is sfp On Thu, Dec 5, 2024, 7:47 PM Marcus D. Leech wrote: > On 05/12/2024 12:27, Houshang wrote: > > Hi Marcus > Here it is: > > ad@bm-super11-intel:~$ sudo /usr/local/lib/uhd/examples/benchmark_rate > --args "type=n3xx,product=n310,addr=10.10.0.100,master_clock_rate=125

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2024-12-05 Thread Marcus D. Leech
On 05/12/2024 12:27, Houshang wrote: Hi Marcus Here it is: ad@bm-super11-intel:~$ sudo /usr/local/lib/uhd/examples/benchmark_rate --args "type=n3xx,product=n310,addr=10.10.0.100,master_clock_rate=125e6" --rx_rate 25e6 --tx_rate 25e6 My recollection of your config is that 10.10.0.100 is the RJ

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2024-12-05 Thread Houshang
And this is for the prob command: ad@bm-super11-intel:~$ uhd_usrp_probe --args "type=n3xx,product=n310,addr=10.10.0.100" [INFO] [UHD] linux; GNU C++ version 11.4.0; Boost_107400; DPDK_23.11; UHD_4.7.0.HEAD-0-ga5ed1872 [INFO] [MPMD] Initializing 1 device(s) in parallel with args: mgmt_addr=10.10.0

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2024-12-05 Thread Marcus D. Leech
On 05/12/2024 11:44, houshang.az...@accelleran.com wrote: Hello Have you managed to fix this? I have a similar issue as you can see below. Thanks Well, again, what happens when you do the simple benchmark_rate test *WITHOUT* DPDK involved? |ad@bm-super11-intel:~/accelleran$ sudo dpdk-d

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2024-12-05 Thread Houshang
Hi Marcus Here it is: ad@bm-super11-intel:~$ sudo /usr/local/lib/uhd/examples/benchmark_rate --args "type=n3xx,product=n310,addr=10.10.0.100,master_clock_rate=125e6" --rx_rate 25e6 --tx_rate 25e6 [INFO] [UHD] linux; GNU C++ version 11.4.0; Boost_107400; DPDK_23.11; UHD_4.7.0.HEAD-0-ga5ed1872 [00:

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2024-12-05 Thread houshang . azizi
Hello Have you managed to fix this? I have a similar issue as you can see below. Thanks `ad@bm-super11-intel:~/accelleran$ sudo dpdk-devbind.py --status` `Network devices using DPDK-compatible driver` `` `:43:00.1 'Ethernet Controller X710 for

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2024-01-11 Thread Michael Dickens
Thanks for reporting back your success & how you got there! - MLD On Mon, Jan 8, 2024 at 11:55 AM wrote: > I should have updated this chain a bit ago. But I managed to solve the > issue a few days ago. > > I managed to get it to work and there is a few things that went wrong that > when I fixed

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2024-01-08 Thread jmaloyan
I should have updated this chain a bit ago. But I managed to solve the issue a few days ago. I managed to get it to work and there is a few things that went wrong that when I fixed the problem was solved… It is mentioned in the tutorials that the “uhd.conf” file needs to specify exactly the am

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2024-01-08 Thread Michael Dickens
Hi Joe - What does "uhd_find_devices" return for "mgmt_addr" on the USRP? Is the 1 GbE/RJ-45 link connected to the same LAN as the host computer attached to the USRP? I'm literally right now working with another customer and Ettus R&D on this exact same issue and we have determined that the 1 GbE

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2023-12-22 Thread jmaloyan
After reading through the documentation again, I learned I should only specify the NIC ports used in the UHD arguments in my conf file, I believe this was able to resolve some of my issues, it still does not successfully begin the benchmarking. For example, if I specify 1 management_address/mgm

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2023-12-20 Thread jmaloyan
I tried the command without use_dpdk=1, and it worked fine(aside from the underflows and dropped samples) - if that is what you mean by side-step. If I specify the type/product(and set use_dpdk=1), I still get errors. `./benchmark_rate --rx_rate 491.52e6 --rx_channels 0 --tx_rate 491.52e6 --tx_

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2023-12-20 Thread Marcus D. Leech
On 20/12/2023 17:49, jmalo...@umass.edu wrote: In the past when I collected data from the x410 without DPDK, it would work just fine to use solely 1 network port. I tried using the management address now, but I still get errors, but it is slightly different. Notably there is not a “no chdr_c

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2023-12-20 Thread jmaloyan
In the past when I collected data from the x410 without DPDK, it would work just fine to use solely 1 network port. I tried using the management address now, but I still get errors, but it is slightly different. Notably there is not a “no chdr_connection available” error. `./benchmark_rate --rx

[USRP-users] Re: Benchmarking x410 with Mellanox with DPDK

2023-12-20 Thread Rob Kossler via USRP-users
Hi Joe, Perhaps you need a different "mgmt_addr" and "addr"? I seem to recall that it was necessary to have a management address that was the typical RJ45 and then a data streaming address that went to the high speed IO. My memory is for the N series USRPs - I have no experiment with the X410. Ro