Re: core performance

On Mon, 30 Sep 2024 08:57:26 -0700 Stephen Hemminger wrote: > > After placing counters all over the code, we realize that some threads are > > uniformly slow, in other words there is no application level issue that is > > throttling one thread over the other. We come to t

Re: core performance

On Mon, 23 Sep 2024 20:31:16 + (UTC) amit sehas wrote: > We are seeing different dpdk threads (launched via rte_eal_remote_launch()), > demonstrate very different performance. Are the DPDK threads running on isolated cpus? Are the DPDK threads doing any system calls (use strace to check)?

Re: core performance

On Thu, 26 Sep 2024 17:03:17 + (UTC) amit sehas wrote: > If there is a way to determine: > > vCPU thread utilization numbers over a period of time, such as a few hours > > or which processes are consuming the most CPU > > top always indicates that the server is consuming the most CPU. > >

Re: core performance

On Tue, 24 Sep 2024 14:40:49 + (UTC) amit sehas wrote: > Thanks for your response, and thanks for your input on the set_priority,  > > The best guess we have at this point is that this is not a dpdk performance > issue. This is an issue with some threads running into more context switches

Re: core performance

On Mon, 23 Sep 2024 23:17:54 + (UTC) amit sehas wrote: > only for the critical threads we could utilize:  rte_thread_set_priority to  > RTE_THREAD_PRIORITY_REALTIME_CRITICAL Really bad idea on Linux. Realtime priority will cause kernel starvation.

Re: Accuracy of rte_get_tsc_hz() compared to linux

On Fri, 20 Sep 2024 06:19:35 +0300 Isaac Boukris wrote: > On Fri, Sep 20, 2024 at 1:21 AM Stephen Hemminger > wrote: > > > > On Thu, 19 Sep 2024 01:04:40 +0300 > > Isaac Boukris wrote: > > > > > Hi, > > > > > > On Intel(R) Xeo

Re: Accuracy of rte_get_tsc_hz() compared to linux

On Fri, 20 Sep 2024 09:26:05 +0200 David Marchand wrote: > On Fri, Sep 20, 2024 at 12:22 AM Stephen Hemminger > wrote: > > Sigh. exposing tsc frequency through sysfs is a Redhat extension > > that never got merged upstream. > > Counter sight :-). > > Not sure w

Re: Accuracy of rte_get_tsc_hz() compared to linux

On Thu, 19 Sep 2024 01:04:40 +0300 Isaac Boukris wrote: > Hi, > > On Intel(R) Xeon(R) Gold 6130 CPU @ 2.10GHz (see lscpu output at the end). > > The rte_get_tsc_hz() returns 210 KHz but using it causes our > timestamps to lag behind real time (roughly a sec per 10 min). I > noticed the kern

Re: Accuracy of rte_get_tsc_hz() compared to linux

On Thu, 19 Sep 2024 01:04:40 +0300 Isaac Boukris wrote: > Hi, > > On Intel(R) Xeon(R) Gold 6130 CPU @ 2.10GHz (see lscpu output at the end). > > The rte_get_tsc_hz() returns 210 KHz but using it causes our > timestamps to lag behind real time (roughly a sec per 10 min). I > noticed the kern

Re: Accuracy of rte_get_tsc_hz() compared to linux

On Thu, 19 Sep 2024 01:04:40 +0300 Isaac Boukris wrote: > Hi, > > On Intel(R) Xeon(R) Gold 6130 CPU @ 2.10GHz (see lscpu output at the end). > > The rte_get_tsc_hz() returns 210 KHz but using it causes our > timestamps to lag behind real time (roughly a sec per 10 min). I > noticed the kern

Re: Accuracy of rte_get_tsc_hz() compared to linux

On Thu, 19 Sep 2024 01:04:40 +0300 Isaac Boukris wrote: > I've run the helloworld application on an isolated cpu: > taskset -c 10 ./dpdk-helloworld --log-level=lib.eal:debug --no-huge > > The results are: > EAL: TSC frequency arch ~210 KHz > EAL: TSC frequency linux ~2095082 KHz > EAL: TSC f

Re: Struggling with meson in dpdk 21.11

On Mon, 16 Sep 2024 18:42:52 +0100 David Aldrich wrote: > $ cd /opt/intel/dpdk-stable-21.11.7 > $ sudo meson -Dexamples=all -Dprefix="/" > -Ddisable_drivers=common/mvep,common/mlx5,net/mvneta,net/mvpp2,net/nfb,net/mlx4,net/mlx5,\ > crypto/qat,crypto/aesni_gcm,crypto/aesni_mb,crypto/armv8,crypto/c

Re: Netvsc vs Failsafe Performance

On Thu, 12 Sep 2024 13:47:37 -0700 Nandini Rangaswamy wrote: > Thanks for your response Long Li. > I see with netvsc the maximum number of Tx descriptors is restricted to > 4096 whereas the number of Rx descriptors is restricted to 8192. > But, for failsafe PMD , we see that both the number of Tx

Re: DPDK and E810 NIC

On Thu, 12 Sep 2024 16:35:18 + "Lombardo, Ed" wrote: > Hi, > Does DPDK 22.11 with Intel E810 NIC guarantee the mbufs are 4 KB aligned? > > Thanks, > Ed Probably not. The mbuf pool is created by the application. Alignment depends on the size and options passed to rte_pktmbuf_pool_create.

Re: rte_eth_tx_burst return 0 after some time

On Mon, 9 Sep 2024 15:25:23 +0200 Alan Arondel wrote: > Hello Everyone, > > I'm trying to add an export module to my application. I use DPDK > version 20.11, a 82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb > and the vfio-pci driver. > port configuration is the following: > > port_conf->tx

Re: Netvsc vs Failsafe Performance

s = RTE_ETH_TX_OFFLOAD_UDP_CKSUM | RTE_ETH_TX_OFFLOAD_IPV4_CKSUM, > }, > > Regards, > Nandini > > On Tue, Sep 3, 2024 at 5:03 PM Stephen Hemminger > wrote: > > > On Tue, 3 Sep 2024 14:43:28 -0700 > > Nandini Rangaswamy wrote: > > > > > Hi

Re: configuring RSS offloads with Netvsc PMD

On Wed, 28 Aug 2024 10:32:17 -0700 Nandini Rangaswamy wrote: > Hi Long and Stephen, > I am trying to configure RSS offloads from my DPDK App with netvsc PMD. > Netvsc seems to be supporting the following offloads: > RTE_ETH_RSS_NONFRAG_IPV4_UDP RTE_ETH_RSS_NONFRAG_IPV4_TCP > RTE_ETH_RSS_NONFRAG_I

Re: [GRO] check whether ip_id continuity needs to be checked when two TCP packets are merged.

On Thu, 20 Apr 2023 02:30:41 + "Hu, Jiayu" wrote: > Hi Cheng, > > > -Original Message- > > From: jiangheng (G) > > Sent: Saturday, April 15, 2023 10:46 PM > > To: users@dpdk.org; Hu, Jiayu ; d...@dpdk.org > > Subject: [GRO] check whether ip_id continuity needs to be checked when > >

Re: reuse the packets after tx burst

eems to be some more gap in my understanding. Could you please help > understand the issue? > > Thanks & Regards > -- > Lokesh Chakka. > > > On Mon, Aug 12, 2024 at 8:22 PM Stephen Hemminger < > step...@networkplumber.org> wrote: > > > On Mon, 1

Re: reuse the packets after tx burst

On Mon, 12 Aug 2024 15:55:50 +0530 Lokesh Chakka wrote: > hello, > > Here is a small piece of code : > > while( condition ) > { > > if( rte_eth_tx_burst( port_id, 0, mbuf, num_of_pkts_per_queue ) != > num_of_pkts_per_queue ) > { > fprintf( stderr, "%d %s\n", rte_errno

Re: RSS for ENA

On Sun, 11 Aug 2024 19:55:08 +0400 (+04) Ivan Malov wrote: > Hi Fabio, > > Have you considered to select MQ mode 'RSS' [1] via 'dev_conf.rxmode.mq_mode' > during 'rte_eth_dev_configure' [2] stage? Just to double-check. > > Also, the 'RSS_HASH' flag could possibly mean the availability of 32-bit

Re: DPDK: Create multiple RSS flows with unique set of queues for different patterns

On Thu, 8 Aug 2024 11:19:13 + Raghavan V wrote: > Hi Team, > > Is there any possible way to create multiple RSS flows to distribute packets > to set of queues when a particular Ip pattern matches. > For e.g., > I have 40 RX queues setup, > Flow 1: Match a particular IP pattern and distribut

Re: Query regarding netvsc PMD : VF removal

On Thu, 25 Jul 2024 11:41:59 -0700 Nandini Rangaswamy wrote: > Hi Stephen, > I am using the DPDK 22.11.5 LTS. Should the DPDK code take care of > unbinding synthetic interface from uio_hv_generic or should it be done by > the app when it gets hotplug notification? > Regards, > Nandini The synthe

Re: Query regarding netvsc PMD : VF removal

On Thu, 25 Jul 2024 10:52:18 -0700 Nandini Rangaswamy wrote: > Hi, > I am integrating my DPDK app (using DPDK version 22.11) with Netvsc PMD. I > was testing the use case of VF removal with the DPDK app. > I registered for hotplug notification in the DPDK app and enabled DPDK > logs. I see the AP

Re: FDIR packet distribution with specific multiple RX queues.

On Thu, 18 Jul 2024 16:39:35 + Raghavan V wrote: > Hi Stephen, > Thanks for your response. > > As our application has limitations while using RSS, > I would prefer a similar approach to RTE_ACTION_TYPE_QUEUE. There is no action like this since hardware does not support it. Multi queue suppo

Re: Regarding net_netvsc driver registration with VMBUS

On Wed, 17 Jul 2024 09:17:07 -0700 Nandini Rangaswamy wrote: > Hi Stephen, > I am using dpdk 22.11 . I used testpmd with the same and it worked . Also > , I compared testpmd logs with that if the app and did not find difference > except that netvsc driver not being probed. Can you give inputs on

Re: Regarding net_netvsc driver registration with VMBUS

On Wed, 17 Jul 2024 08:46:31 -0700 Nandini Rangaswamy wrote: > Hi Stephen, > Please find below the logs: > > *Args passed to eal_init* > 2024-07-17T06:17:32.722 |108390| MSG[NET] dpdk_rte_init:426 > rte_eal_init - vc > 2024-07-17T06:17:32.722 |108390| MSG[NET] dpdk_rte_init:426 > r

Re: dpdk-dumpcap

On Sun, 7 Jul 2024 20:58:39 + "Lombardo, Ed" wrote: > Hi, > I am looking to debug my issue with dpdk and E810 NIC for transmit with GRE > header. The dpdk-dumpcap utility is my focus to see what dpdk is > transmitting. I have carefully studied the mbufs for the packet and looks > correct

Re: Regarding multi-segmented mbufs

On Wed, 3 Jul 2024 14:15:58 -0400 fwefew 4t4tg <7532ya...@gmail.com> wrote: > The DPDK documentation > https://doc.dpdk.org/guides/prog_guide/mbuf_lib.html provides helpful > information but comes up a tad short re: multi-segmented mbufs. See > Fig. 14.3 An mbuf with Three Segments. > > See https

Re: Issue with Cannot allocate memory when using 32-bit DPDK application

On Wed, 3 Jul 2024 10:18:34 +0800 (GMT+08:00) 洪全 wrote: > My CPU architecture is x86-64 If you have x86 then there is no good reason to bother with 32 bit. The lack of virtual space is going to limit you probably to 1Gb or less of huge pages.

Re: Issue with Cannot allocate memory when using 32-bit DPDK application

On Tue, 2 Jul 2024 18:17:08 +0800 (GMT+08:00) 洪全 wrote: > Dear DPDK community, > > > I am encountering an issue when attempting to run a 32-bit DPDK application > on Linux. Specifically, I am facing a "Cannot allocate memory" error during > initialization. While I can mitigate this issue by u

Re: dumpcap: weird failure with six IPv6 hosts in the filter

On Mon, 17 Jun 2024 23:43:19 +0300 Isaac Boukris wrote: > On Mon, Jun 17, 2024 at 10:37 PM Isaac Boukris wrote: > > > > > Just a quick update that I still see the issue in my env with the > > > master branch (24.07.0-rc0), I'm now testing by adding the filter to > > > 'sample_filters' in test_

Re: dumpcap: weird failure with six IPv6 hosts in the filter

On Mon, 17 Jun 2024 10:11:47 +0300 Isaac Boukris wrote: > Hi Stephen, > > For instance, the following filter fais as follows (if I omit one host > it works): > -f "host 1::1 or host 1::1 or host 1::1 or host 1::1 or host 1::1 or host > 1::1" > > EAL: Error - exiting with code: 1 > Cause: Pac

Re: dumpcap: weird failure with six IPv6 hosts in the filter

On Mon, 17 Jun 2024 10:11:47 +0300 Isaac Boukris wrote: > Hi Stephen, > > For instance, the following filter fais as follows (if I omit one host > it works): > -f "host 1::1 or host 1::1 or host 1::1 or host 1::1 or host 1::1 or host > 1::1" > > EAL: Error - exiting with code: 1 > Cause: Pac

Re: Compiling testpmd with DPDK netvsc PMD

On Fri, 7 Jun 2024 16:31:51 -0700 Nandini Rangaswamy wrote: > Hi David, > Thanks for your email. I inspected meson build output and do see that > netvsc is in the list of enabled drivers. > === > Drivers Enabled > === > > common: > iavf, mlx5, qat, > bus: >

Re: Compiling testpmd with DPDK netvsc PMD

On Mon, 10 Jun 2024 09:50:42 +0200 David Marchand wrote: > Hello, > > On Sat, Jun 8, 2024 at 1:32 AM Nandini Rangaswamy > wrote: > > Thanks for your email. I inspected meson build output and do see that > > netvsc is in the list of enabled drivers. > > === > > Drivers Enabled > > =

Re: Reg DPDK Support in Ubuntu - 24.04 LTS

On Tue, 7 May 2024 12:47:10 +0530 Harrish SJ wrote: > Hi DPDK Community, > > We understand that latest DPDK release 24.03 is qualified in Ubuntu OS - > 22.04.4 LTS. Ref : https://doc.dpdk.org/guides/rel_notes/release_24_03.html > We would like to understand when latest Ubuntu - 24.04 LTS will

Re: High packet capturing rate in DPDK enabled port

On Sun, 5 May 2024 13:09:42 +0600 Fuji Nafiul wrote: > I have a DPDK-enabled port (Linux server) that serves around 5,000-50,000 > concurrent calls, per packet size of 80 bytes to 200 bytes. so in peak > time, I require packet capture + file writing speed of around 1GByte/s or 8 > Gbit/sec (at le

Re: No free hugepages reported

On Sun, 31 Mar 2024 16:28:19 +0530 Lokesh Chakka wrote: > Hello, > > I've installed dpdk in Ubuntu 23.10 with the command "sudo apt -y install > dpdk*" > > added "nodev /mnt/huge hugetlbfs pagesize=1GB 0 0" in /etc/fstab > added "vm.nr_hugepages=1024" in /etc/sysctl.conf > > rebooted the mach

Re: --lcores: what it does and does not do

On Sat, 30 Mar 2024 17:45:41 -0400 fwefew 4t4tg <7532ya...@gmail.com> wrote: > // If program run with --lcores=(1)@2,(2)@4 this loop will > // create and run two threads lcore 1 pinned to CPU 2 and lcore 2 > // pinned to CPU 4. the output will look like: > // hello from core 1

Re: --lcores: what it does and does not do

On Sat, 30 Mar 2024 12:06:15 -0400 fwefew 4t4tg <7532ya...@gmail.com> wrote: > I've made a DPDK test program that does the following on the same machine > and for the same NIC. This is a test; it does nothing practical: > > * Creates 1 RX queue then reads and pretty prints contents in a loop > *

Re: MLX5 VF stops transmitting when the Physical Function is added to a Linux bridge

On Mon, 25 Mar 2024 15:59:36 +0100 Antonio Di Bacco wrote: > I have a Connect X5 card (PF ens1f0np0) directly connected to another server: > > 1) create VF on PF on both servers > 2) change mac address of VFs to my own addressing > 3) start testpmd on server 1 in txonly mode to transmit to serve

Re: dpdk-testpmd on XDP

On Fri, 22 Mar 2024 18:57:54 +0100 Alessio Igor Bogani wrote: > Hi Stephen, > > Thank you for your support! > > On Wed, 20 Mar 2024 at 17:24, Stephen Hemminger > wrote: > [...] > > Then you need to build bpf tools from the same kernel directory and use > [...

Re: dpdk-testpmd on XDP

On Wed, 20 Mar 2024 08:22:05 +0100 Alessio Igor Bogani wrote: > Stephen, > > Thanks for your reply! > > On Tue, 19 Mar 2024 at 17:07, Stephen Hemminger > wrote: > > > > On Tue, 19 Mar 2024 11:48:53 +0100 > > Alessio Igor Bogani wrote: > > > >

Re: dpdk-testpmd on XDP

On Tue, 19 Mar 2024 11:48:53 +0100 Alessio Igor Bogani wrote: > The only suspicious part in the output of the dpdk-testpmd utility is: > [...] > libxdp: XDP flag not supported by libxdp. > libbpf: prog 'xdp_dispatcher': BPF program load failed: Invalid argument > libbpf: prog 'xdp_dispatcher': --

Re: is RSS and Flow director can work together

On Mon, 11 Mar 2024 09:17:01 + Balakrishnan K wrote: > Hi All, > I want to use the dpdk application with RSS and flow director. > is possible to use both at a time in application. > In RSS, I am using > action_rss_tcp.types = ETH_RSS_NONFRAG_IPV4_TCP | ETH_RSS_L3_SRC_ONLY | > ETH_RSS_L3_

Re: testpmd: no probed ethernet devices i219-v vfio-pci

On Fri, 8 Mar 2024 21:19:08 + sonntex wrote: > Hi, > > I am trying to configure dpdk on my laptop and get "no probed ethernet > devices" in dpdk-testpmd utility: > > laptop :: ~ % sudo dpdk-testpmd -l 0-1 -n 4 --log-level=debug -- -i > EAL: Detected CPU lcores: 8 > EAL: Detected NUMA nodes:

Re: Symmetric RSS Hashing support in DPDK

On Wed, 6 Mar 2024 07:28:40 + Balakrishnan K wrote: > Hello, >Our application needs symmetric hashing to handle the reverse traffic on > the same core, also to > Improve performance by distributing the traffic across core. > Tried using rss config as below . > action_rss_tcp.types = ETH_

Re: DPDK Pdump tool is not able to attach to DPDK test pmd primary application

On Thu, 22 Feb 2024 19:27:01 + Sameer Vaze wrote: > I don't think the pdump application is doing the transmit/receive. Am I > missing something in the command line arguments I passed below that would > configure it to transmit/receive? > > Passing in the rx-dev and tx-dev as pcap should no

Re: KNI RTNETLINK operation not supported

On Tue, 20 Feb 2024 23:23:03 + John He wrote: > I am using a CentOS 7.9 VMware VM, kernel version > > kernel-3.10.0-1160.92.1.el7.x86_64 > > I have created a KNI interface but when I run > > ip link set up > > I get > > RTNETLINK answers: Operation not supported > > This same software

Re: DPDK Pdump tool is not able to attach to DPDK test pmd primary application

On Wed, 14 Feb 2024 22:44:46 + Sameer Vaze wrote: > Hey Folks, > > I see the following message when I attempt to attach pdump to the testpmd > sample application: > > Pdump output: > EAL: Failed to hotplug add device > EAL: Error - exiting with code: 1 > Cause: vdev creation failed:creat

Re: DDP and symmetric RSS hash

On Mon, 29 Jan 2024 19:18:38 +0300 Виктория Доможакова wrote: > Hi, > I'm trying to set toeplitz symmetric hash function for packets from DDP. > I've created flows for pppoe/pppol2tpv2/l2tpv2 headers in patterns and  > PCtypes as RSS hash types. But it is not working. > What should I do to config

Re: Split traffic between the Linux stack and DPDK application

On Mon, 29 Jan 2024 18:09:28 +0200 Pavel Vazharov wrote: > Hi there, > > A DPDK can run on top of XDP sockets and use custom XDP program to split > the traffic between the Linux stack and the DPDK application. This way > still allows zero copy between the kernel and the DPDK application. > Is th

Re: Questions about running XDP sockets on top of bonding device or on the physical interfaces behind the bond

On Thu, 25 Jan 2024 10:48:07 +0200 Pavel Vazharov wrote: > Hi there, > > I'd like to ask for advice for a weird issue that I'm facing trying to run > XDP on top of a bonding device (802.3ad) (and also on the physical > interfaces behind the bond). > > I've a DPDK application which runs on top o

Re: DPDK Netvsc - RNDIS reports VF but device not found, retrying

On Tue, 23 Jan 2024 21:06:22 +0200 Oleksandr Nahnybida wrote: > > > > > > I also installed rdma-core/libibverbs1 (dpdk was compiled > > > with ibverbs_link=shared) Try without ibverbs_link shared? Maybe Mlx5 maintainers are: M: Dariusz Sosnowski M: Viacheslav Ovsiienko M: Ori Kam M: Suanm

Re: DPDK Netvsc - RNDIS reports VF but device not found, retrying

On Tue, 23 Jan 2024 19:51:33 +0200 Oleksandr Nahnybida wrote: > azureuser@dpdk0:~$ ethtool -i enP47056s2 > driver: mlx5_core > version: 5.15.0-1053-azure > firmware-version: 16.30.1284 (MSF12) > expansion-rom-version: > bus-info: b7d0:00:02.0 > > I also installed rdma-core/libibverbs1 (d

Re: DPDK Netvsc - RNDIS reports VF but device not found, retrying

On Tue, 23 Jan 2024 14:34:12 +0200 Oleksandr Nahnybida wrote: > Hello, > > I am trying to set up dpdk with netvsc as master pmd on Azure following > https://learn.microsoft.com/en-us/azure/virtual-network/setup-dpdk?tabs=ubuntu > and > https://doc.dpdk.org/guides-22.11/nics/netvsc.html > > but

Re: Tapping a Tx port to access all the packets being Txed

On Thu, 11 Jan 2024 05:55:53 + Nicolson Ken (ニコルソン ケン) wrote: > Hi all, > > I'm wanting to basically tap a DPDK stream and for instance save all packets > being Txed by a PMD to a separate file. > > I know I could relatively easily modify an existing PMD to have two output > ports, but is

Re: Detecting if rte_eal_init() has already been called

On Wed, 27 Dec 2023 03:54:12 + Nicolson Ken (ニコルソン ケン) wrote: > Hi all, > > I'm loading two semi-independent DPDK-ready shared libraries into a master > process. If both call rte_eal_init() I get a fatal error about calling it a > second time. I tried the rte_eal_primary_proc_alive(NULL) A

Re: VM SR-IOV VF fails dpdk

On Tue, 12 Dec 2023 16:33:51 + "Lombardo, Ed" wrote: > Hi, > I am finding an issue on ESXi host running our Linux VM application. The > DPDK version is 17.11 and VM OS is 3.10.0-1160.81.1.el7.x86_64. > ESXi host version is 7.03. > The NIC is the Intel x710-DA2 in SR-IOV mode. Configured on

Re: DPDK used for building programs and the one used to run the programs

On Tue, 5 Dec 2023 14:47:47 +0100 Antonio Di Bacco wrote: > On the target machine I use to have a DPDK compiled after installing > the Mellanox 5/6 drivers. > I see that there are files related to MLX5 pmds in the target machine > (include files). > > To compile my programs I use a container whe

Re: how to make dpdk processes tolerable to segmantation fault?

On Thu, 30 Nov 2023 19:24:01 +0300 Dmitry Kozlyuk wrote: > 2023-11-30 13:45 (UTC+0600), Fuji Nafiul: > > In a normal c program, I saw that the segmentation fault in 1 loosely > > coupled thread doesn't necessarily affect other threads or the main > > program. There, I can check all the threads by

Re: Non eal registered thread flow

On Wed, 29 Nov 2023 14:21:55 -0800 Chris Ochs wrote: > Trying to get a handle on the best way to integrate with my existing > architecture. > > My main application is in Rust and it's a partitioned/batching flow. It's > an end server. I basically send type erased streams between partitions > usi

Re: Failed to load eBPF byte-code on TAP device

up_call_args done..: ret: -7 > [ 76.318224] ## bpf_check: end..: ret: -7 > [ 76.318224] ## BPF bpf_check return err: -7..: > = > > Only these logs which I add in the Kernel-code were printed and do not see > any other Kernel-logs

Re: Failed to load eBPF byte-code on TAP device

On Wed, 15 Nov 2023 15:38:55 +0530 madhukar mythri wrote: > Hi all, > > On the RHEL9.2 with DPDK 22.11.1 version, DPDK primary application failed > to add RSS flow on TAP sub-device, when loading the TAP BPF byte-code > instructions. > > This "struct bpf_insn l3_l4_hash_insns[]" array(from file

Re: support hardware question

> hi > Does dpdk support RealTek NICs? or is there any plan to support it? No. No volunteers, and no vendor involvement. But DPDK is not really important at 1G and below. You can use TAP to access kernel driver.

Re: Questions about the the pdump functionality

On Mon, 23 Oct 2023 18:32:48 +0300 Pavel Vazharov wrote: > Hi there, > > We've a DPDK based application from which we need to take packet dumps from > time to time when problems arise. We are planning to use librte_pdump > functions and the dpdk-dumppcap tool. > I've few questions in related to

Re: Whether the creatation of flow rules of i40e NIC support tcp port mask

On Tue, 17 Oct 2023 08:52:22 + "jiangheng (G)" wrote: > Hi beilei， > > I would like to create flows using tcp port mask, but it seems only mask > 0x or 0x0 work, Does flow rlue can be created using other mask? > > I40e dirver was using now. Why not create multiple rules each pointing

Re: Reg Packet Type Issue in Intel X710 NIC

On Mon, 16 Oct 2023 22:55:39 +0530 Harrish SJ wrote: > Thanks much Stephen for your inputs. Let me check the flags and get back. > Any inputs on GTP Packet type as UNKNOWN would be much helpful. > Thanks in advance, > > Regards and Thanks, > Harrish.S.J Packet type recognition in either done

Re: Reg Packet Type Issue in Intel X710 NIC

On Mon, 16 Oct 2023 22:47:18 +0530 Harrish SJ wrote: > Hi Team, > > We are observing below issues w.r.t Packet types in Intel X710 NIC > > NIC Details: (from dpdk-devbind -s) > Network devices using DPDK-compatible driver > > :81:00.1 'Ethernet C

Re: How to establish a uni-directional Ethernet link in the dpdk environment

On Sun, 15 Oct 2023 10:30:48 +0330 Alireza Sadeghpour wrote: > Hi, > > I am trying to establish a uni-directional Ethernet link where a singular > fiber is used to transmit data to the receiver in the DPDK environment. The > Rx of the transmit side and the Tx of the receive side are not physical

Re: How to configure ethernet controller registers in the dpdk environment

On Sat, 14 Oct 2023 18:32:24 +0330 Alireza Sadeghpour wrote: > > > Hi, > > I am trying to set some registers of the ethernet controller in the DPDK > environment, but I can't find the corresponding API to do this. is there > any API in the DP

Re: capturing .pcap file on NIC interface

On Fri, 6 Oct 2023 07:53:13 -0700 Prasad Chivakula wrote: > Hi > > I am trying to capture eCPRI packets on NIC card interface that is > connected to a Radio in our 5G set up. I would like to know how to use > dpdk-pdump to accomplish this? Do i have to rebuild dpdk with these > options, if so, c

Re: net/tap: eBPF failed to load BPF section and failed to create flows for TAP device

On Mon, 9 Oct 2023 07:04:49 + Kouilakonda Anudattu wrote: > I'm adding some additional details to provide more context. I'm encountering > this issue on Azure/Hyper-V platform with the existing DPDK-22.11.1 > tap_bpf_insns.h byte-code. Unless your use case demands rte_flow, use the netvsc

Re: net/tap: eBPF failed to load BPF section and failed to create flows for TAP device

On Mon, 9 Oct 2023 07:04:49 + Kouilakonda Anudattu wrote: > I'm adding some additional details to provide more context. I'm encountering > this issue on Azure/Hyper-V platform with the existing DPDK-22.11.1 > tap_bpf_insns.h byte-code. > > > Regards, > Anudattu. > > From: Kouilakonda Anu

Re: rte_rdtsc() - what is the performance impact of using rte_rdtsc() time

On Tue, 3 Oct 2023 15:49:00 +0530 Hari Haran wrote: > > > > The problem is that rte_rdtsc() stops speculative execution so doing > > lots of TSC instructions can hurt performance. > > > > To correlate TSC timestamp to system time, you need to compute the offsets > > once at startup. Alternatively

Re: tap device speed

On Mon, 2 Oct 2023 21:13:03 +0200 Antonio Di Bacco wrote: > I'm doing a test where we have a couple of tap devices, the two > devices are seen by testpmd that is setup in forward mode. > > On the linux side, the two tap devices are confined in different > network namespaces and in one namespace

Re: dumpcap: timestamp is years ahead when in pcapng format

On Thu, 21 Sep 2023 08:14:12 +0300 Isaac Boukris wrote: > > This is less accurate. The TSC (CPU clock frequency) is not necessarily > > an even multiple of nanoseconds. > > > > If you want to send patches please follow the contributing guidelines > > and run checkpatch on them. > > Yeah, I rea

Re: dumpcap: timestamp is years ahead when in pcapng format

t; seq 81, length 64 > > 2023-09-20 09:40:20.727638 IP A > Rocky8: ICMP echo reply, id 11, seq > > 81, length 64 > > 2023-09-20 09:40:21.727638 IP ... > > > > On Wed, Sep 20, 2023 at 8:59 PM Isaac Boukris wrote: > > > > > > On Tue, Sep

Re: dumpcap: timestamp is years ahead when in pcapng format

On Tue, 19 Sep 2023 19:35:55 +0300 Isaac Boukris wrote: > Looking with git log, i found the original line was: > return pcapng_time.ns + (delta * NSEC_PER_SEC) / rte_get_tsc_hz(); > > Testing that does show a wrapping issue, e.g. (it stays around 08:05). > > 2023-09-19 08:05:24.372037 IP _gatew

Re: rte_exit() does not terminate the program -- is it a bug or a new feature?

On Mon, 18 Sep 2023 20:23:25 +0200 Gabor LENCSE wrote: > Of course, I will review all my rte_exit calls... It'll take a while... > > I am just curious, as I have no idea, why my old code worked all right > with DPDK 16.11. Has rte_exit() been changed since then? Older versions of the DPDK did

Re: rte_exit() does not terminate the program -- is it a bug or a new feature?

On Sun, 17 Sep 2023 21:37:30 +0200 Gabor LENCSE wrote: > However, l2fwd also uses the "rte_exit()" function to terminate the > program. The only difference is that it calls the "rte_exit()" function > from the main program, and I do so in a thread started by the > "rte_eal_remote_launch()" fun

Re: Concurrent invocations of the dpdk-dumpcap tool

On Sun, 17 Sep 2023 00:11:31 +0300 Isaac Boukris wrote: > I'm testing with the 22.11.3 version code (latest LTS) but there don't > seem to be significant changes in master. > > Given the above I had the hunch the ring names collide in shared > memory, so I changed both the ring and the pool name

Re: rte_exit() does not terminate the program -- is it a bug or a new feature?

On Fri, 15 Sep 2023 20:28:44 +0200 Gabor LENCSE wrote: > Dear Stephen, > > Thank you very much for your answer! > > > Please get a backtrace. Simple way is to attach gdb to that process. > > I have recompiled siitperf with the "-g" compiler option and executed it > from gdb. When the progra

Re: rte_exit() does not terminate the program -- is it a bug or a new feature?

On Fri, 15 Sep 2023 10:24:01 +0200 Gabor LENCSE wrote: > Dear DPDK Developers and Users, > > I have met the following issue with my RFC 8219 compliant SIIT and > stateful NAT64/NAT44 tester, siitperf: > https://github.com/lencsegabor/siitperf > > Its main program starts two sending threads an

Re: Can independent dpdk applications in 2 separate pod use same cpu.

On Sat, 9 Sep 2023 13:04:23 + (UTC) Amy Smith wrote: > Hi,I have 2 independent dpdk application pods working now using different set > of cpu cores. For low cost use case I would like them to use same cpu. I have > 1 cpu core which I want both pods to share. Is it possible? Do I need to mak

Re: EAL: eal_memalloc_alloc_seg_bulk(): couldn't find suitable memseg_list

efine RTE_MAX_MEMSEG_PER_LIST 8192#define > RTE_MAX_MEM_MB_PER_LIST 32768#define RTE_MAX_MEMSEG_PER_TYPE 32768#define > RTE_MAX_MEM_MB_PER_TYPE 65536#define RTE_MAX_MEMZONE 2560 > >   > > 发件人: Don Trotter > 发送时间: 2023年9月8日 5:33 > 收件人: Stephen Hemminger > 抄送: users@dpdk.org > 主题:

Re: EAL: eal_memalloc_alloc_seg_bulk(): couldn't find suitable memseg_list

On Thu, 7 Sep 2023 19:58:35 + (UTC) Don Trotter wrote: > To clarify, the log message when my application called rte_mempool_create() > to create the "node_pool", and the call succeeded. > Thanks,Don Trotter > On Thursday, September 7, 2023 at 01:54:08 PM CDT, Don Trotter > wrote: >

Re: rte_rdtsc() - what is the performance impact of using rte_rdtsc() time

On Tue, 29 Aug 2023 20:25:54 +0530 Hari Haran wrote: > Hi All, > > Subject: rte_rdtsc() - what is the performance impact of using rte_rdtsc() > time under lcore thread while(1) > > Requirement: > >1. Store the packet received timestamp - based on it packets will be >removed from buffer

Re: vfio module crash when i used dpdk secondary process send pkts

On Thu, 24 Aug 2023 09:06:44 +0800 (CST) jinag <15720603...@163.com> wrote: > This is definitely a bug in the kernel, I am looking to see if there's a > bugfix patch in the kernel community. but maybe the app passed an incorrect > parameter that caused kernel crash? > The kernel version is 4.1

Re: vfio module crash when i used dpdk secondary process send pkts

On Tue, 22 Aug 2023 09:33:39 +0800 (CST) jinag <15720603...@163.com> wrote: > when I use dpdk to call rte_eth_tx_burst function for sending data from the > secondary process, vfio will crash: > > > PID: 60699 TASK: 8f0152235df00 CPU: 14 COMMAND: "testlstack02" > #0 [a7d8cecc39a8] mach

Re: Help Running Example

ll of > these, unless I misunderstand something. > > -Alan > > On Tue, Aug 8, 2023 at 11:25 AM Alan Beadle wrote: > > > > Thanks Stephen. It looks like my memory controller is in the same > > IOMMU group. I assume this means I won't be able to do t

Re: Help Running Example

On Mon, 7 Aug 2023 12:40:21 -0700 Stephen Hemminger wrote: > On Sun, 6 Aug 2023 11:33:43 -0400 > Alan Beadle wrote: > > > Hi, > > > > I need some help getting DPDK working. I am running Ubuntu 20.04 with > > a modified Linux 5.4 kernel, but I have also tried

Re: Help Running Example

On Sun, 6 Aug 2023 11:33:43 -0400 Alan Beadle wrote: > Hi, > > I need some help getting DPDK working. I am running Ubuntu 20.04 with > a modified Linux 5.4 kernel, but I have also tried the stock Ubuntu > 5.15 kernel with the same results. > > Here is my NIC info from lspci: > 00:1f.6 Ethernet

Re: How to add packet capture framework to a custom simple dpdk app

On Sun, 9 Jul 2023 10:36:53 +0600 Fuji Nafiul wrote: > Hi, > I am using dpdk_v22.11.1 on ubuntu_v22.04.2. I have a simple app derived > from skeleton and icmpecho which can reply to proper arp requests and also > can reply to appropriate pings. Now whats the proper steps to add a packet > capture

Re: Multiple rte_launch_remote multiple times on main lcore

On Tue, 27 Jun 2023 20:20:28 +0200 Antonio Di Bacco wrote: > This is very useful. Anyway, just on main_lcore, could I launch many > pthreads (with pthread_create) ? > > Does this interfere with DPDK? DPDK is not designed for random additional threads. You could use rte_ctrl_thread_create or do

Re: Wrapping DPDK log messages with an application logger

On Thu, 22 Jun 2023 19:08:25 +0300 Dmitry Kozlyuk wrote: > Hi, > > 2023-06-22 17:45 (UTC+0200), Lukáš Šišmiš: > > I would think there could be opportunity to pass my logging callback into > > DPDK but I have not found it. > > FWIW, I too think a callback would be better than what DPDK offers

Re: Multiple rte_launch_remote multiple times on main lcore

On Tue, 20 Jun 2023 17:33:59 +0200 Antonio Di Bacco wrote: > Is it possible to launch multiple threads on the main lcore? > Who will be in charge of scheduling those threads on the main lcore > (main lcore is isolated)? > > Not the OS I suppose. > > Thank you If you start trying to add threads

Re: Is the 25G Xeon D Integrated LAN supported?

On Mon, 19 Jun 2023 02:57:44 + "Yang, Tao Y" wrote: > Please see the release notes > > https://doc.dpdk.org/guides/rel_notes/release_23_03.html > Intel® platforms with Intel® NICs combinations > o CPU > § Intel® Atom™ CPU C3758 @ 2.20GHz > § Intel® Xeon® CPU D-1553N @ 2.30GHz > § Intel®

Re: Scheduling of multiple RX/TX queues on a single port

On Mon, 29 May 2023 23:02:45 +0800 Fengkai Sun wrote: > Hi list, > > I'm curious how DPDK programs the NIC to receive/transmit packets when > there are multiple queues on a single port. > > As for RX, the answer might be clear. > The NIC can only receive a packet once at a time, since the cable

  1   2   3   4   5   >