When not using DPDK but at high sample rates (200Msps) I have a bash script that runs through and makes the changes suggested on the ettus website. For mtu:
sudo ip link set mtu 9000 enp1s0f0 sudo ip link set mtu 9000 enp1s0f1 I believe I also set it to 9000 in the uhd.conf file for when I am using DPDK with dpdk_mtu=9000 Thanks for your help on this by the way From: Marcus D. Leech <patchvonbr...@gmail.com> Sent: Wednesday, June 23, 2021 1:17 PM To: Wolsieffer, Carl L. ERDC-RDE-CRL-NH CIV <carl.l.wolsief...@erdc.dren.mil>; usrp-users@lists.ettus.com Subject: Re: [USRP-users] Re: intermittent TX error using DPDK and x310 On 06/22/2021 04:52 PM, Wolsieffer, Carl L. ERDC-RDE-CRL-NH CIV wrote: At lower rates, say 20Msps, the warning appears to go away outside of DPDK, but if I run it at 200Msps (outside of DPDK) it can still show up (along with a few U’s of course) What MTU are you using at the higher rates? This may be just a network hardware issue, and your network hardware needs a bit of performance tweaking. From: Marcus D. Leech <patchvonbr...@gmail.com> Sent: Tuesday, June 22, 2021 4:42 PM To: Wolsieffer, Carl L. ERDC-RDE-CRL-NH CIV <carl.l.wolsief...@erdc.dren.mil> Subject: Re: [USRP-users] Re: intermittent TX error using DPDK and x310 On 06/22/2021 04:34 PM, Wolsieffer, Carl L. ERDC-RDE-CRL-NH CIV wrote: Okay, brought PC home and interestingly enough these two errors: [ERROR] [UHD] Device discovery error: send_to: Network is unreachable [ERROR] [USRP2] USRP2 Network discovery error send_to: Network is unreachable Go away and come back depending on if I have a physical Ethernet connecting PC to the ol’ world-wide web. Even if I #ifconfig <interface> down or specify “dpdk_mac=aa:bb:cc:dd:ee:ff” in the --args. I’m not sure these errors are critical as UHD eventually finds my specified advice and continues with the procedure. I still however get this error intermittently whether there’s an internet connection or not: [ERROR] [CTRLEP] Caught exception during async message handling: map::at Do you get this message when you don't use DPDK, probably at lower sample rates? Not clear to me what this means or how it may be impacting my transmitted waveform – any thoughts on this? Thanks! Casey From: Wolsieffer, Carl L. ERDC-RDE-CRL-NH CIV via USRP-users <usrp-users@lists.ettus.com><mailto:usrp-users@lists.ettus.com> Sent: Tuesday, June 22, 2021 12:45 PM To: Marcus D Leech <patchvonbr...@gmail.com><mailto:patchvonbr...@gmail.com> Cc: usrp-users <usrp-users@lists.ettus.com><mailto:usrp-users@lists.ettus.com> Subject: [USRP-users] Re: intermittent TX error using DPDK and x310 Hmm I guess I partially take back my earlier claim as I can’t seem to repeat the case where the errors are not present when either unit is connected individually. I still have the output log from last week so I know it was free of errors at one time and I’m not crazy. Only difference in setup is I do not have PC connected to internet this week whereas it had a wired internet connection last week. When using outside of DPDK and at lower speeds, the errors are gone From: Marcus D Leech <patchvonbr...@gmail.com<mailto:patchvonbr...@gmail.com>> Sent: Tuesday, June 22, 2021 11:20 AM To: Wolsieffer, Carl L. ERDC-RDE-CRL-NH CIV <carl.l.wolsief...@erdc.dren.mil<mailto:carl.l.wolsief...@erdc.dren.mil>> Cc: usrp-users <usrp-users@lists.ettus.com<mailto:usrp-users@lists.ettus.com>> Subject: Re: [USRP-users] intermittent TX error using DPDK and x310 So if either of them are connected singularly, things work, otherwise, even dealing with a single unit causes this error? What if you don’t use dpdk, but run at lower speeds, just to see if this is a network/DPDK config issue? Sent from my iPhone On Jun 22, 2021, at 11:14 AM, Wolsieffer, Carl L. ERDC-RDE-CRL-NH CIV <carl.l.wolsief...@erdc.dren.mil<mailto:carl.l.wolsief...@erdc.dren.mil>> wrote: Yes that’s correct, one is the default 192.168.40.2 and the other I changed to 192.168.50.2 From: Marcus D Leech <patchvonbr...@gmail.com<mailto:patchvonbr...@gmail.com>> Sent: Tuesday, June 22, 2021 10:50 AM To: Wolsieffer, Carl L. ERDC-RDE-CRL-NH CIV <carl.l.wolsief...@erdc.dren.mil<mailto:carl.l.wolsief...@erdc.dren.mil>> Cc: usrp-users <usrp-users@lists.ettus.com<mailto:usrp-users@lists.ettus.com>> Subject: Re: [USRP-users] intermittent TX error using DPDK and x310 The devices have distinct IP addresses on all their connected ports presumably? Sent from my iPhone On Jun 22, 2021, at 10:38 AM, Wolsieffer, Carl L. ERDC-RDE-CRL-NH CIV via USRP-users <usrp-users@lists.ettus.com<mailto:usrp-users@lists.ettus.com>> wrote: Hello, Finally got DPDK running on my ubuntu 20.04 machine. I have two x310's over a 10Gbe each going to their own port on a intel x520. If I have just a single x310 hooked up, the rx_samples_to_file and tx_samples_from_file both work flawlessly at 200 Msps. If they are both hooked up, I get a few errors when transmitting that I am not able to discern are going to cause me trouble or not. This is a typical output upon calling tx_from_samples. The [ERROR] [UHD] and [ERROR] [USRP2] don't seem to be a major issue, since the PC is finding the x310 without a problem, but I don't know what the [ERROR] [CTRLEP] at the end is trying to tell me. Any thoughts? root@fmcw-sounder:/usr/local/lib/uhd/examples# ./tx_samples_from_file --file test_samples.dat --gain 0 --freq 2400000000 --lo-offset 100000000 --rate 200000000 --args "addr=192.168.50.2,use_dpdk=1" Creating the usrp device with: addr=192.168.50.2,use_dpdk=1... [INFO] [UHD] linux; GNU C++ version 9.3.0; Boost_107100; UHD_4.0.0.HEAD-0-g90ce6062 [WARNING] [PREFS] Loaded config from /root/.uhd. This location is considered deprecated, consider moving your config file to /root/.config instead. EAL: Detected 12 lcore(s) EAL: Detected 1 NUMA nodes EAL: Multi-process socket /var/run/dpdk/rte/mp_socket EAL: No free hugepages reported in hugepages-1048576kB EAL: Probing VFIO support... EAL: VFIO support initialized EAL: PCI device 0000:01:00.0 on NUMA socket -1 EAL: Invalid NUMA socket, default to 0 EAL: probe driver: 8086:10fb net_ixgbe EAL: using IOMMU type 1 (Type 1) EAL: Ignore mapping IO port bar(2) EAL: PCI device 0000:01:00.1 on NUMA socket -1 EAL: Invalid NUMA socket, default to 0 EAL: probe driver: 8086:10fb net_ixgbe EAL: Ignore mapping IO port bar(2) [ERROR] [UHD] Device discovery error: send_to: Network is unreachable [ERROR] [USRP2] USRP2 Network discovery error send_to: Network is unreachable [INFO] [X300] X300 initialization sequence... [INFO] [X300] Maximum frame size: 8000 bytes. [INFO] [X300] Radio 1x clock: 200 MHz Using Device: Single USRP: Device: X-Series Device Mboard 0: X310 RX Channel: 0 RX DSP: 0 RX Dboard: A RX Subdev: UBX RX RX Channel: 1 RX DSP: 1 RX Dboard: B RX Subdev: Unknown (0xffff) - 0 TX Channel: 0 TX DSP: 0 TX Dboard: A TX Subdev: UBX TX TX Channel: 1 TX DSP: 1 TX Dboard: B TX Subdev: Unknown (0xffff) - 0 Setting TX Rate: 200.000000 Msps... Actual TX Rate: 200.000000 Msps... Setting TX Freq: 2400.000000 MHz... Setting TX LO Offset: 100.000000 MHz... Actual TX Freq: 2400.000000 MHz... Setting TX Gain: 0.000000 dB... Actual TX Gain: 0.000000 dB... Checking TX: TXLO: locked ... [WARNING] [0/Radio#0] Attempting to set tick rate to 0. Skipping. Done! [ERROR] [CTRLEP] Caught exception during async message handling: map::at root@fmcw-sounder:/usr/local/lib/uhd/examples# Thanks! Casey <tx_output.txt> _______________________________________________ USRP-users mailing list -- usrp-users@lists.ettus.com<mailto:usrp-users@lists.ettus.com> To unsubscribe send an email to usrp-users-le...@lists.ettus.com<mailto:usrp-users-le...@lists.ettus.com>
_______________________________________________ USRP-users mailing list -- usrp-users@lists.ettus.com To unsubscribe send an email to usrp-users-le...@lists.ettus.com
