[ConnectX 6Dx]Issue using Tx scheduling feature in DPDK
Hello, DPDK Version: 21.11 Firmware version : 22.32.1010 MLNX_OFED version: MLNX_OFED_LINUX-5.5-1.0.3.2-ubuntu20.04-x86_64 We are trying to use the DPDK tx scheduling feature on a ConnectX6 DX adapter. We experience some issues with the feature not working. The test is using Test-pmd in txonly mode. Here are the command used: sudo ./dpdk-testpmd -l 0-3 -n 4 -- -i --portmask=0x1 --nb-cores=1 --eth-peer=0,01:00:5e:00:00:08 --tx-ip=10.10.1.168,239.0.0.8 testpmd> set fwd txonly testpmd> set burst 64 testpmd> set txtimes 100,1 By doing this I expect the feature working. Am i missing something ? I also added a print in txonly.c and clearly sees that the feature is not enabled dynf = rte_mbuf_dynflag_lookup (RTE_MBUF_DYNFLAG_TX_TIMESTAMP_NAME, NULL); if (dynf >= 0) timestamp_mask = 1ULL << dynf; dynf = rte_mbuf_dynfield_lookup (RTE_MBUF_DYNFIELD_TIMESTAMP_NAME, NULL); if (dynf >= 0) timestamp_off = dynf; both function ( rte_mbuf_dynfield_lookup and rte_mbuf_dynflag_lookup) returns -1 I also tried to enabled the feature. testpmd> port config 0 tx_offload send_on_timestamp on but when doing this DPDK tells me that I don't have these offload capabilities Hope you will be able to help me. Regards Antoine
RE: Does ACL support field size of 8 bytes?
Hi Ido, > I've lots of good experience with ACL but can't make it work with u64 values > I know it can be split to 2xu32 fields, but it makes it more complex to use > and a wastes double number of fields (we hit the > RTE_ACL_MAX_FIELDS 64 limit) Wow, that's a lot of fields... > According to the documentation and rte_acl.h fields size can be 8 bytes (u64) > e.g. > 'The size parameter defines the length of the field in bytes. Allowable > values are 1, 2, 4, or 8 bytes.' > (from > https://doc.dpdk.org/guides-21.11/prog_guide/packet_classif_access_ctrl.html#rule-definition) > > Though there's a hint it's less recommended > 'Also, it is best to define fields of 8 or more bytes as 4 byte fields so > that the build processes can eliminate fields that are all wild.' > > It's also not clear how it fits in a group (i.e. what's input_index stride) > which is only 4 bytes > 'All subsequent fields has to be grouped into sets of 4 consecutive > bytes.' > > I couldn't find any example or test app that's using 8 bytes > e.g. for IPv6 address 4xu32 fields are always used and not 2xu64 > > Should it work? > Did anyone try it successfully and/or can share an example? You are right: though it is formally supported, we do not test it, and AFAIK no-one used it till now. As we do group fields by 4B long chunks anyway, 8B field is sort of awkward and confusing. To be honest, I don't even remember what was the rationale beyond introducing it at first place. Anyway, just submitted patches that should fix 8B field support (at least it works for me now): https://patches.dpdk.org/project/dpdk/list/?series=22676 Please give it a try. In long term it probably would be good to hear from you and other users, should we keep 8B support at all, or might be it would be easier just to abandon it. Thanks Konstantin
Mellanox & Qlogic & Molex & Intel
Hi , Please help to quote as below, destination: 宁波 China, thanks! 请提供如下价格,货到宁波,谢谢! Quantity(pcs) Item PN Model Part Vendor 100 300 500 Remark 1 MCX512A-ACAT 2x25Gb SFP28 ConnectX-5 EN Adapter Card 10/25GbE PCIe card Mellanox 100 300 500 2 MCX631102AS-ADAT 2x25G SFP28 ConnectX-6 Lx EN Adapter Card 25GbE Crypto Disabled PCIe card Mellanox 100 300 500 二选 一 3 MCX631102AN-ADAT PCIe card Mellanox 100 300 500 6 MCX542B-ACAN ConnectX®-5 EN network interface card for OCP, with host management, 25GbE dual-port SFP28, PCIe3.0 x8, UEFI Enabled, no bracket Halogen free OCP mezz Mellanox 100 300 500 7 MCX545B-CCUN ConnectX®-5 EN 1x 100GbE QSFP28 PCIe 3.0 x16 UEFI Enabled OCP mezz Mellanox 100 300 500 4 QLE2742-SR-CK PCIe 3.0, x8, Dual / 2-ports, 32GFC, SR-Optic, SFP+, Low Profile PCIe card Qlogic 100 300 500 5 QLE2672-CK 16Gb Dual-port FC HBA, PCI-E x8, LC multi-mode optic, Box, 2xSFP included PCIe card Qlogic 100 300 500 6 XXV710DA2OCP1 Ethernet network adaptor for OCP (2x25Gb 2*SPF+ EN Adapter Card 10/25GbE) OCP mezz Intel 60 300 7 BCM957414M4142C NeXtreme M225P network adaptor (2*25Gb SFP28, PCIe3.0 x8 10/25 Gbs) OCP mezz Broadcom 60 300 8 MCX4421A-ACQN Mellanox ConnectX-4 LX EN Network Interface Card For OCP2.0 2x25Гбит/сек Dual Port 2xSFP28 Host Management Mezzanine OCP 2.0 Type 1 PCI-E 3.0(MCX4421A-ACQN) OCP mezz Mellanox 100 300 500 9 205058-3020 NPIO 8x STR to 2* 4x RA, 750mm cable Molex 2000 Yours/Ken k...@whbam.com
Re: AMD EPYC 7713 64-Core: cannot enable turbo boost
Right now we are using an Intel XEON and to be able to enable turbo boost we had to change a setting (Power performance tuning) in the BIOS sticking it to "OS control EPB". Is there something to do in the BIOS of EPYC? Il giorno mar 26 apr 2022 alle ore 18:25 Antonio Di Bacco < a.dibacco...@gmail.com> ha scritto: > That's fantastic: > > # sudo cpupower -c 99 frequency-info info > analyzing CPU 99: > driver: acpi-cpufreq > CPUs which run at the same hardware frequency: 99 > CPUs which need to have their frequency coordinated by software: 99 > maximum transition latency: Cannot determine or is not supported. > hardware limits: 1.50 GHz - 3.72 GHz > available frequency steps: 2.00 GHz, 1.70 GHz, 1.50 GHz > available cpufreq governors: conservative ondemand userspace powersave > performance schedutil > current policy: frequency should be within 1.50 GHz and 3.72 GHz. > The governor "userspace" may decide which speed to use > within this range. > current CPU frequency: 2.00 GHz (asserted by call to hardware) > boost state support: > Supported: yes > Active: yes > Boost States: 0 > Total States: 3 > Pstate-P0: 2000MHz > Pstate-P1: 1700MHz > Pstate-P2: 1500MHz > > Il giorno mar 26 apr 2022 alle ore 12:00 Tummala, Sivaprasad < > sivaprasad.tumm...@amd.com> ha scritto: > >> [AMD Official Use Only - General] >> >> >> >> Hi Antonio, >> >> >> >> We are looking into this. Could you please share the below info: >> >> # cpupower -c frequency-info info >> >> analyzing CPU : >> >> driver: acpi-cpufreq >> >> >> >> >> >> *From:* Antonio Di Bacco >> *Sent:* Monday, April 25, 2022 10:43 PM >> *To:* users@dpdk.org >> *Subject:* AMD EPYC 7713 64-Core: cannot enable turbo boost >> >> >> >> [CAUTION: External Email] >> >> Trying to enable turbo boost on EPYC 7713 with this APIS: >> >> >> >> rte_power_init(lcore) >> rte_power_freq_enable_turbo(lcore) >> rte_power_freq_max(lcore) >> >> >> >> I receive this messages: >> >> >> >> DPDK:POWER: Env isn't set yet! >> DPDK:POWER: Attempting to initialise ACPI cpufreq power management... >> DPDK:POWER: Power management governor of lcore 99 has been set to >> 'userspace' successfully >> DPDK:POWER: Initialized successfully for lcore 99 power management >> DPDK:POWER: Failed to enable turbo on lcore 99 >> >