Re: [vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

I tried the native virtio driver with gso enabled, the throughput (without any tuning) is close to 16Gbps. It's a big improvement, though there is still some gap between vpp and Linux kernel. Does it suggest that the virtio driver in dpdk has some issues? Regards, Xiaodong On Wed, Oct 12, 2022

[vpp-dev] #vpp-dev: No packets generated from Vhost user interface

Hi, I have bought up a VPP on ubuntu with QEMU hypervisor. I spawn a new VM with vhost inetrface. No packets are seen on vhost interface and what I see memory region allocated is 0. Can you please help how to mitigate this ? vpp# show version vpp v22.10-rc1~4-g61bae8a54~b6 built by root on

Re: [vpp-dev] Is there any VPP agent which provides interface to control VPP?

Hoi, Related - take a look at https://github.com/pimvanpelt/vppcfg.git notably the user guide . Several of our community use this tool, but it does not go the route of yang and netconf, but rather "just" compiling down a YAML

[vpp-dev] Is there any VPP agent which provides interface to control VPP?

Hi everyone, I am working on a project which uses VPP as the data plane. I hope to control and manage VPP through interface like RESTful, NETCONF, etc. I find that honeycomb project seems to be deprecated and doesn't support new versions of VPP. The Ligato vpp-agent is active but works in

Re: [vpp-dev] Move VNET features to plugins

Hi Neale, Comments inline... On 10/17/22 10:46 PM, Neale Ranns wrote: Hi Dave, I fully support pluginification  Is it fair though to say that if the remaining functions of vnet have a dependency on one of the modules below then that module is not a good candidate to move to a plugin?

Re: [vpp-dev] VPP SSWAN plugin git cherry pick to stable 22.10

Hi Andrew, cherry-pick for stable/2210: https://gerrit.fd.io/r/c/vpp/+/37413 Thanks Yulong Pei From: Andrew  Yourtchenko Sent: Tuesday, October 18, 2022 1:58 PM To: Pei, Yulong Cc: vpp-dev@lists.fd.io; Andrew Yourtchenko (ayourtch) ; Ji, Kai ; Zhang, Roy Fan ; Oginski, GabrielX Subject:

Re: [vpp-dev] VPP SSWAN plugin git cherry pick to stable 22.10

Hi Yulong, Cool, thanks! Then could you please make a cherry-pick into stable/2210 branch, and add me as a reviewer ? I will merge it. --a > On 18 Oct 2022, at 03:51, Pei, Yulong wrote: > >  > Hi Andrew, > > I have been working on CSIT IPSec test for a long time, CSIT IPSec test use >

Re: [vpp-dev] Move VNET features to plugins

Hi Dave, I fully support pluginification  Is it fair though to say that if the remaining functions of vnet have a dependency on one of the modules below then that module is not a good candidate to move to a plugin? I thinking about the dependency between IPIP and TEIB. Some of the IPIP

Re: [vpp-dev] VPP SSWAN plugin git cherry pick to stable 22.10

Hi Andrew, I have been working on CSIT IPSec test for a long time, CSIT IPSec test use VPP python API for configuration, “SSWAN plugin https://gerrit.fd.io/r/c/vpp/+/36552” have no impact for CSIT IPSec test since it is only plugin for strongswan, and it do not build by defaut when building

Re: [vpp-dev] pcap_write error: bad address

hi Dave： I have been  gdb before，  vl(pm->pcap_data)    =   2,806,013,189， pm->n_pcap_data_written  = 0. int  is 32 bits,size_t  is 64 bits.  n=0xA740 5D05   cast to size_t  is  0x A740 5D05. we can't use  n for   write  param. code  fragment： int n = vec_len (pm->pcap_data) -

[vpp-dev] Move VNET features to plugins

Folks, There has been a long standing chore to move VNET features to plugins for which I've created a Jira ticket [0] to coordinate getting this work done for VPP 23.02 release. Can the maintainers of the VNET features [1] please sign up for the associated subtask in [0] and complete the

Re: [vpp-dev] pcap_write error: bad address #pcap

Use gdb to inspect the pcap_main_t. In particular, determine vec_len(pm->pcap_data) [“(gdb) vl(pm->pcap_data)”] and pm->n_pcap_data_written. For reasonable N pcap_write(...) is known to work. D. From: vpp-dev@lists.fd.io On Behalf Of aihua1...@163.com Sent: Sunday, October 16, 2022

[vpp-dev] snat support bind to specific subnets

Hi Ole, Filip, Klement, Neale, John, Steven, , I have a demand about snat. With in a vpc, different subnets need use different snat ip to the internet, but the vpp snat feature now do not support snat ip bind to specific subnets. I have two ideas to resolve this: 1. modify and develop snat

[vpp-dev] pcap_write error: bad address #pcap

dear all: pcap_write,use type int n; if  n is negative。  int n = vec_len (pm->pcap_data) - pm->n_pcap_data_written; write func will failed，errno = 14. n = write (pm->file_descriptor, vec_elt_at_index (pm->pcap_data, pm->n_pcap_data_written), n); int   cast   to  size_t  may case  some overflow？

Re: [vpp-dev] A question about fib-id with ip neighbor

Hi Neale & Community, I found the proxy info of "ip neighbor cli" should also be removed, is it right? I have added a fix as gerrit review id 37424 to resolve these. gerrit link: https://gerrit.fd.io/r/c/vpp/+/37424 short description: Delete redundant

Re: [vpp-dev] VPP SSWAN plugin git cherry pick to stable 22.10

Hi Andrew, I think the patch is for SSWAN plugin only, the VPP code is untouched. I don’t see any impact this patch will bring to IPsec source code, I cc’d Fan & Radu for suggestion. Regards Kai From: vpp-dev@lists.fd.io On Behalf Of Andrew Yourtchenko Sent: Friday, October 14, 2022 11:04

Re: [vpp-dev] VPP SSWAN plugin git cherry pick to stable 22.10

Hi Kai, Having a second look at it - the plugin is offloading IPSec; So I would like some of the CSIT folks/IPSec maintainers to chime in with confirmation that they are comfortable with this… I think I might need to rescind the previous “no risk” assessment. --a > On 14 Oct 2022, at 11:50,

Re: [vpp-dev] VPP SSWAN plugin git cherry pick to stable 22.10

Hi Andrew, Thank you for the reply, I’m agree with you, the https://gerrit.fd.io/r/c/vpp/+/36183 is way too big and risky for stable 22.10 now. In this case, can I kindly to ask you consider to merge VPP SSWAN plugin (https://gerrit.fd.io/r/c/vpp/+/36552) for 22.10 stable ? This patches only

Re: [vpp-dev] VPP SSWAN plugin git cherry pick to stable 22.10

Kaj, *release manager hat on* we are past RC2 milestone - which means only critical fixes for CSIT tests go in. if the commit was just the plugin itself, in principle might be possible to entertain the idea, since a separate plugin is relatively low risk. But

Re: [vpp-dev] VPP SSWAN plugin git cherry pick to stable 22.10

Hello We recently added fix plugin for vpp-sswan (https://gerrit.fd.io/r/c/vpp/+/36552) and I wonder if is it too late for this patch to be picked to stable 22.10 ? To make things more complicate, there is also a fix linked library patch for vpp-sswan https://gerrit.fd.io/r/c/vpp/+/37388

Re: [vpp-dev] A question about last used timestamp in ipsec sa

Hi ben The firtst reason is the SA bytes/packets only show there is some trafffic that use this sa , we must record and calculation the last time in IKE processs, and this is not accurate that based on the poll frequency. This is the major reason , we want this timestamp is more

Re: [vpp-dev] Crash in VPP22.06 in ip4_mtrie_16_lookup_step

Hi Prashant, > I found the root cause for this in my plugin. I was using the handoff > functions incorrectly. > There is no problem in VPP. After fixing my plugin, the usecase runs as > solid in 22.06 as in 21.06. Glad to hear, and thanks for the feedback! Best ben > On Wed, 12 Oct 2022, 18:26

Re: [vpp-dev] A question about last used timestamp in ipsec sa

As you'd have to poll SA timestamp counters anyway to check the timestamp, why not just poll existing SA bytes/packets counters instead to see if some traffic is going through? Best ben > -Original Message- > From: vpp-dev@lists.fd.io On Behalf Of Guangming > Sent: Friday, October 14,

[vpp-dev] A question about last used timestamp in ipsec sa

Hi，Neale , Radu and Fan Now the ipsec in VPP did not record the traffic timestamp in sa and spd like linux kernel . So we can not Implement the full DPD function In IKE control daemon that only send DPD when no traffic . What is the good method to add timestamp . This method should be

Re: [vpp-dev] A question about fib-id with ip neighbor

Hi Huawei, The fib-ID should be removed from the cmd’s help. /neale From: lihuawei Date: Friday, 14 October 2022 at 16:01 To: Neale Ranns , vpp-dev@lists.fd.io Subject: A question about fib-id with ip neighbor Hi Neale, As the following picture shows: I have not see any support for the

[vpp-dev] A question about fib-id with ip neighbor

Hi Neale, As the following picture shows: I have not see any support for the fib-id in the code, but fib-id is in cmd’s help. Is the fib-id deleted before？Or it will to be add in the future? Anyone knows about this, please help. Thanks and Regards, Huawei LI -=-=-=-=-=-=-=-=-=-=-=- Links:

Re: [vpp-dev] Crash in VPP22.06 in ip4_mtrie_16_lookup_step

Thanks Benoit. I found the root cause for this in my plugin. I was using the handoff functions incorrectly. There is no problem in VPP. After fixing my plugin, the usecase runs as solid in 22.06 as in 21.06. Regards -Prashant On Wed, 12 Oct 2022, 18:26 Benoit Ganne (bganne) via lists.fd.io,

Re: [vpp-dev] vpp crash when close a host-stack tcp session in syn-sent state.

Thanks a lot, I will give a try. Florin Coras 于2022年10月14日周五 01:01写道： > Hi, > > [cc Vanessa] > > Could you please open a ticket here [1]? Hopefully this can be solved. > > Regards, > Florin > > [1] > https://jira.linuxfoundation.org/plugins/servlet/desk/portal/2/create/37 > > On Oct 12, 2022,

[vpp-dev] nova.exception.VirtualInterfaceCreateException: Virtual Interface creation failed #vpp-dev

I am seeing below error when I try to spawn a instance on VPP with DPDK and openstack openstack server create --flavor CSR-small --image csr-1000v-17-03-05 --nic net-id=suresh-nw1 CSR1k-VPP-suresh-nw1 Oct 13 23:04:02 gna200405 nova-compute[2579]: DEBUG nova.virt.libvirt.vif [None

Re: [vpp-dev] vpp crash when close a host-stack tcp session in syn-sent state.

Hi, [cc Vanessa] Could you please open a ticket here [1]? Hopefully this can be solved. Regards, Florin [1] https://jira.linuxfoundation.org/plugins/servlet/desk/portal/2/create/37 > On Oct 12, 2022, at 10:42 PM, Zhang Dongya wrote: > > Yes, I can login to link [1] and can see my account

Re: [vpp-dev] Gomemif migration

Thanks Matus for your patch & the notification To give context for users of the memif go native library this means : - The code that was previously hosted in VPP under extras/gomemif will move to https://github.com/FDio/govpp under extras/gomemif - The go-libmemif library (C/Go bindings) is not

[vpp-dev] Gomemif migration

Hello, I submitted a patch to migrate Gomemif to GoVPP repository. https://gerrit.fd.io/r/c/vpp/+/37393 Best regards Matus Halaj -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#22021): https://lists.fd.io/g/vpp-dev/message/22021 Mute This Topic:

Re: [vpp-dev] Build VPP with clean Jenkins workspace

OK, good to know for future patches. Thanks for help and the quick response, much appreciated! Regards, Marcel -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#22020): https://lists.fd.io/g/vpp-dev/message/22020 Mute This Topic:

Re: [vpp-dev] vpp crash when close a host-stack tcp session in syn-sent state.

Yes, I can login to link [1] and can see my account have been registered in LF 5 years, however, when I login the gerrit web ui, it still reports Forbidden error, my account username is ZhangDongya. Ok, I will try to use git command line to give a try. Florin Coras 于2022年10月13日周四 10:12写道： > An

Re: [vpp-dev] vpp crash when close a host-stack tcp session in syn-sent state.

An LF account should suffice. Could you confirm your lf credentials work here [1]? And, in case you haven’t seen this already, here are the steps to get you started on pushing the patch, once the above is solved [2]. Regards, Florin [1] https://identity.linuxfoundation.org/

Re: [vpp-dev] vpp crash when close a host-stack tcp session in syn-sent state.

Thanks a lot,I just add a check for tx_fifo there locally and it seems works. BTW, I'd like to help to submit a patch, however I don't know the reason when I trying to login gerrit using my linux foundation id, it always reports Forbidden error, do you know where I can get help to solve this ?

Re: [vpp-dev] Build VPP with clean Jenkins workspace

Marcel, The build failure was caused by the fact that your gerrit change was not based on top of master and because there was another gerrit change merged [0] which changed the PKG_SUFFIX in build/external/Makefile [0].  Thus build was not updating vpp-ext-deps in the CI docker container

Re: [vpp-dev] libnl as external dependency?

Hi Pim, Not any problems at all. Until you start to play with vxlan interfaces, bridge af and so on :) I'm living on a bleeding edge with some custom patches to libnl (planning to upstream them as well). So, for my case I need to link statically libnl to the plugin (not to depend on the host

Re: [vpp-dev] libnl as external dependency?

Hoi Stanislav, What's the issue with using libnl3-dev from Ubuntu/Debian? Are you imagining adding patches from libnl (I'd love to learn more, if you do :-). groet, Pim On Wed, Oct 12, 2022 at 4:58 PM Stanislav Zaikin wrote: > Hello folks, > > I have a patch to download, build and link

[vpp-dev] VPP22.10 NAT44 VRF-to-Public

Hi Folks, I'm new to VPP and trying to work on one setup where I have internal interface inside VRF and would like to provide internet connectivity to hosts via NAT. The egress interface to upstream network has private IP but has default route to upstream router then to internet. What I'm doing

[vpp-dev] clang-15 fixes

Guys, I submitted patch which fixes issues reported by clang 15. https://gerrit.fd.io/r/c/vpp/+/37387 Mainly it is about variables which are computed but never used after…. Please take a look if your code is listed in this patch. — Damjan -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all

Re: [vpp-dev] vpp crash when close a host-stack tcp session in syn-sent state.

Hi, It looks like a bug. We should make sure the fifo exists, which is typically the case unless transport is stuck in half-open. Note that tcp does timeout and cleanups those stuck half-open sessions, but we should allow the app to cleanup as well. Let me know if you plan to push a patch

[vpp-dev] VPP 22.10 RC2 artifacts are available!

Hi all, VPP 22.19 RC2 milestone is complete, artifacts are available at packagecloud.io This sets us on to the finish line to the release, which is supposed to happen in two weeks. We are now merging only the critical fixes into stable/2210 branch in preparation for the release. --a /* your

[vpp-dev] libnl as external dependency?

Hello folks, I have a patch to download, build and link statically libnl3 for linux-cp netlink plugin (as part of vpp-ext-deps and aligned with other packages in build/external/packages/). Would it be useful for the rest of the community? For instance, not to be dependent on the libnl version in

[vpp-dev] 2022-10-12 FD.io VPP (master branch) Gerrit Change Report

New report generated today https://gist.github.com/dwallacelf/90f2c3b1a2a59b5bc186d89650826f6b Please review the report and update/review/merge changes as appropriate. Thanks, -daw- On 9/27/22 10:09 AM, Dave Wallace via lists.fd.io wrote: New report generated today:

[vpp-dev] vpp-debug-verify job enabled per-patch non-voting

Folks, After removing the most egregious make test testcases which fail on the vpp_debug image, I have re-instated the vpp-debug-verify job as non-voting per-patch [0].  I will continue to work on fixing or removing testcases which are failing on non-related patches. Please look for

Re: [vpp-dev] Crash in VPP22.06 in ip4_mtrie_16_lookup_step

I did not heard anything like this. Can you try to reproduce with latest master? Do you have some proprietary plugins loaded also? Best ben > -Original Message- > From: vpp-dev@lists.fd.io On Behalf Of Prashant > Upadhyaya > Sent: Wednesday, October 12, 2022 11:32 > To: vpp-dev >

Re: [vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

Hi, You can use VPP native virtio driver in VM. ./dpdk-devbind.py -b vfio-pci 00:03.0 00:04.0 cd /home/vpp set loggin class pci level debug set loggin class virtio level debug create int virtio :00:03.0 gso-enabled create int virtio :00:04.0 gso-enabled

[vpp-dev] Crash in VPP22.06 in ip4_mtrie_16_lookup_step

Hi, I am migrating from VPP21.06 where my usecase works without issues overnight, but in VPP22.06 it gives the following crash in 7 to 8 minutes of run. Just wondering if this is a known issue or if anybody else has seen this. Further, when I run in VPP22.06 with a single worker thread, this

[vpp-dev] Geneve Tunnel

Hello all, i have the following topology: With the following configuration (VPP-Host1, VPP-Host2 has the same config with the other addresses): *set int state GigabitEthernet2/6/0 upset int ip address GigabitEthernet2/6/0 10.10.1.1/24 create host-interface name

[vpp-dev] vpp crash when close a host-stack tcp session in syn-sent state.

Hi, I am now trying to use vpp host-stack to negotiate a valid TCP session, however, I found if I call vnet_disconnect_session when the TCP stuck in syn-sent state (this may be caused by I have shutdown the remove side). Vpp will crash in the following code which call svm_fifo_clear_deq_ntf

[vpp-dev] Build VPP with clean Jenkins workspace

Hi all, I submitted a patch to add support for a new version of the ipsecmb library, used by the crypto_ipsecmb plugin. https://gerrit.fd.io/r/c/vpp/+/37358 A previous build downloaded and built the new version of the library and the build passed, great! Subsequent builds are now failing

Re: [vpp-dev] VPP Zoom meeting requires login

Hi Jeff, > Hello, I tried to join the VPP meeting this morning on Zoom but it > required login. I tried creating an account using my company email, but > this was somehow restricted. > Can the Zoom meeting be updated to not require login? You should be able to connect to

[vpp-dev] VPP Zoom meeting requires login

Hello, I tried to join the VPP meeting this morning on Zoom but it required login. I tried creating an account using my company email, but this was somehow restricted. Can the Zoom meeting be updated to not require login? Thanks, Jeff -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages

Re: [vpp-dev] Q) Why does the timeout of ACL plugin get halved?

This is the *list* timeout, which is indeed set to be half the session timeout, as you notice. The logic in acl_fa_check_idle_sessions dequeues the sessions from the list every list timeout (which as you note is half the session timeout) - regardless of whether the session is active or not,

[vpp-dev] Low performance observered when nat44 is enabled

Hi all, While performance testing vpp stable/2206 using TRex, I am seeing a huge drop in performance when nat44 is enabled. I was seeing 14Mbps of packet drop when TRex was pushing at 20kpps on an Xeon(R) Gold 6342 CPU with E-810 100G NIC. During the run I could see congestion drops in

[vpp-dev] Q) Why does the timeout of ACL plugin get halved?

Hi, all. When I try the ACL plugin, I find that transient timeout of the TCP connection gets halved. For example, the session entry for a finished TCP session gets cleaned after 60 seconds, even if the TCP idle timeout is set to default 120 seconds. This is the relevant code.

[vpp-dev] ASAN error on VPP version v23.02-rc0-40-g06923b33a

VPP is built with follow command: make build VPP_EXTRA_CMAKE_ARGS="-DVPP_ENABLE_SANITIZE_ADDR=ON" I run vpp on Microsoft hyper-v vm with Ubuntu20.04, use a vmbus adapter as NIC. It seems if I run vpp with follow *startup.conf* , it will *ALWAYS* failed cause of asan error: starup.conf *unix {*

[vpp-dev] ASAN error on version v23.02-rc0-40-g06923b33a when startup is configured with session #vpp-dev

VPP is built with follow command: *make build VPP_EXTRA_CMAKE_ARGS="-DVPP_ENABLE_SANITIZE_ADDR=ON" * I run vpp on Microsoft hyper-v vm with Ubuntu20.04, use a vmbus adapter as NIC. It seems if I run vpp with follow *startup.conf* , it will ALWAYS failed cause of asan error: starup.conf unix {

Re: [vpp-dev] How to forward masked IP packets to IP nodes?

Hi, Yes, you can look at src/plugins/pppoe/ which does exactly that for example, esp. src/plugins/pppoe/pppoe_decap.c:pppoe_input_node() Best ben > -Original Message- > From: vpp-dev@lists.fd.io On Behalf Of Burcu YUKSEL > Sent: Tuesday, October 11, 2022 8:17 > To: vpp-dev@lists.fd.io

[vpp-dev] VPP 22.10 RC2 milestone is tomorrow

Hi all, Just a small reminder that the VPP 22.10 RC2 milestone is tomorrow. After that only the critical fixes will be accepted in stable/2210 branch. Thanks a lot! --a /* your friendly 22.10 release manager */ -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group.

Re: [vpp-dev] How to forward masked IP packets to IP nodes?

Hello Ben, Thank you for your answer. I have added ethernet_register_input_type() in ip4_init() as you recommend. After this I want to forward the packets to IP nodes so they can follow the same path as IP packets and reach memif-output. Is this possible to forward custom packets to IP nodes

Re: [vpp-dev] Gerrit Review Id 37303

Hi Huawei, Patch merged. Thank you. /neale From: vpp-dev@lists.fd.io on behalf of lihuawei via lists.fd.io Date: Tuesday, 11 October 2022 at 13:17 To: vpp-dev@lists.fd.io Subject: [vpp-dev] Gerrit Review Id 37303 Hi community, I have added a fix as gerrit review id 37303. gerrit link:

[vpp-dev] Gerrit Review Id 37379

Hi Dave, I have added a fix as gerrit review id 37379. gerrit link: https://gerrit.fd.io/r/c/vpp/+/37379 short description: "set policer classify interface loop1 ip4-table 0 del" may raise crash when worker threads handoff process ip4-policer-classify

[vpp-dev] Gerrit Review Id 37303

Hi community, I have added a fix as gerrit review id 37303. gerrit link: https://gerrit.fd.io/r/c/vpp/+/37303 short description: Vpp will crash when create vxlan/vxlan-gpe/geneve/gtpu tunnel with 0.0.0.0 dst ip in debug build. The

Re: [vpp-dev] Combined statistics for all traffic mapped to a MPLS LSP path

Hi Mohit, In which case to calculate the total amount of traffic sent over an LSP you should sum the counts of all IP and MPLS FIB entries that use/pint-to the LSP; i.e. those that have the output label of the LSP. /neale From: vpp-dev@lists.fd.io on behalf of Gupta, Mohit via lists.fd.io

Re: [vpp-dev] Combined statistics for all traffic mapped to a MPLS LSP path

Hi Neale, Thanks for your response. We can install the LSP by configuring MPLS FIB and IP FIB. The detailed instructions are given concisely in https://wiki.fd.io/view/VPP/MPLS_FIB Brief instructions on installing a LSP is as under : 1. Configure Ingress LER to add a mpls label on incoming

Re: [vpp-dev] vpp-2206 bug

Yes, it’s undefined behavior for __builtin_clz with 0 input. And it seems rare to initialize bihash with 0 bucket, but not sure of the input for other use cases with min_log2/max_log2. Or, there could be a “ASSERT (x != 0)” in min_log2/max_log2 to alert 0 input. [1]

Re: [vpp-dev] arm64 / clearfog + VPP

Hi Pim, Looking at https://doc.dpdk.org/guides/nics/dpaa2.html, it looks like it does not use the PCIe bus but something specific called the "FSL MC bus". Normally, VPP DPDK plugin should build a list of eligible devices at startup, by scanning PCIe or VMBus (HyperV virtualized bus) but it does

[vpp-dev] arm64 / clearfog + VPP

Hoi folks, I got my hands on a 16 core ARM board, which has a SoC from NXP LX2160A, which exposes 4x25/1x100 + 4x10 interfaces - https://www.solid-run.com/embedded-networking/nxp-lx2160a-family/clearfog-cx-lx2160-carrier/ The documentation mentions that DPDK is supported using librte_net_dpaa2

Re: [vpp-dev] Questions about no-multi-seg

> From a old message, you saidthat set no-multi-seg will get good > performance . https://lists.fd.io/g/vpp-dev/message/18489 > My question is when i do not neeed Jumbo MTU in my scenario, is set > no-multi-seg and no-tx-checksum-offload in startup.conf a good option It depends from the

[vpp-dev] Questions about no-multi-seg

Hi , ben From a old message, you saidthat set no-multi-seg will get good performance . https://lists.fd.io/g/vpp-dev/message/18489 My question is when i do not neeed Jumbo MTU in my scenario, is set no-multi-seg and no-tx-checksum-offload in startup.conf a good option ?

[vpp-dev] Gerrit Review Id 37298

Hi, I have added a fix as gerrit review id 37298. *Problem Statement:* While configuring End.AD.Flow localsid, vpp gives error if we configure vlan sub interface as iif interface. vpp# sr localsid address 2001:f1:f1:11::111 behavior end.ad.flow nh 9.9.10.102 oif GigabitEthernet0/9/0 iif

[vpp-dev] vpp-2206 bug

Hi, vpp experts when i use bihash_init_8_8 ( p, "test"，0，0）function in arm64 machine, it will cause abort() gcc version is 9.3.0 the reason is when buckets is 0, src/vppinfra/clib.h min_log2() function will use count_leading_zero(0), but return value is different between x86 and arm64，x86 is 63

Re: [vpp-dev] How to forward masked IP packets to IP nodes?

You should be able to use ethernet_register_input_type() to add support for your custom L2. Best ben > -Original Message- > From: vpp-dev@lists.fd.io On Behalf Of Burcu YUKSEL > Sent: Friday, October 7, 2022 18:15 > To: vpp-dev@lists.fd.io > Subject: [vpp-dev] How to forward masked IP

[vpp-dev] How to forward masked IP packets to IP nodes?

Hello everyone, W have a network packet set consisting of custom L2 and standard L3 packets. We want to forward these packets over VPP. When I tried to send custom L2 packet which has a non-standard ethernet type, it had been dropped in VPP. Related Node Stream: 00:14:05:507128:

[vpp-dev] VPP doesn't detect the i40e driver interface #vpp-dev

HI, VPP doesn't detect the i40e driver interface. Any help would be appreciated ? stack@gna200405:~/devstack$ sudo vppctl show interface Name               Idx    State  MTU (L3/IP4/IP6/MPLS)     Counter          Count BondEthernet0                     2     down         9000/0/0/0 local0       

Re: [vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

Hi Wentian, Please take a look at https://s3-docs.fd.io/vpp/22.10/cli-reference/clis/clicmd_src_vnet_gso.html for the GSO feature in VPP. I tried to turn on the TSO option too, however VPP doesn't seem to be able to forward traffic once TSO is turned on. The test case for vhost-user driver I had

Re: [vpp-dev] Combined statistics for all traffic mapped to a MPLS LSP path

Hi Mohit, VPP doesn’t have a single object with stats that represents an LSP in its broad sense. You’ll have to combine the states from the objects that use/point-to the LSP (or rather use the out-going label value of the LSP) – for example IP or MPLS FIB entries, or MPLS tunnel interfaces,

Re: [vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

Hi Xiaodong, Could you please tell me how to enable GSO in VPP? I read the startup.conf and searched the VPP documents but didn't find options about GSO. I found a TSO option in the default startup.conf. According to the comment, the "tso on" option must be enabled with

[vpp-dev] Combined statistics for all traffic mapped to a MPLS LSP path

Hi Team, I need to fetch all Rx/Tx statistics for all traffic that goes over a MPLS Label switched path, whether it is OAM/L2VPN/L3VPN etc. Basically, we are creating a MPLS LSP using RSVP-TE. Later other l2vpn/l3vpn services are enabled and mapped to the LSP. We have MPLS tunnels in VPP for

Re: [vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

I actually tried to enable GSO on both input and output interfaces in VPP, and got a little bit of difference for the result. In most cases the throughput would be the same, but in some cases I see a burst of 4.5Gbps (3x of the original rate). As Benoit said, even without GSO the throughput is

Re: [vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

Hi Benoit, I checked the packet sizes by tcpdump, and the result is similar to what you said. I ran iperf server on M2 and iperf client on M1, and tcpdump on both. I found that on M1(sender), most of the packet length in tcpdump were 65160, irrespective of which dataplane the router used.

Re: [vpp-dev] Geneve SIGSEGV

Hello Pim, i have the following topology: - Yes i can confirm, every host in 10.10.1, 10.10.2, 10.10.4 and 10.10.5 can reach every other host in any of those subnets - 10.10.3.1 cannot reach out to 10.10.3.2, that's what i meant with "pinging from both sides" The ARP- Request (captured with

Re: [vpp-dev] Geneve SIGSEGV

Hoi Stephan, Looking at your config, you have Gi2/6/0 which has a static to one another for 10.10.5/24 and 10.10.2/24 respectively 10.10.1/24 and 10.10.4/24. I assume any host in those 4 subnets will be able to reach each other (as the GENEVE tunnel is unrelated to it). Can you confirm? Then, I

Re: [vpp-dev] Geneve SIGSEGV

Hello, it worked, thanks! Now I have the problem, that if I ping it doesn't crash anymore, but there is an ecapsulatet ARP- Request, that doesn't get answered (captured with wireshark). Did i miss something else? New configuration: Router 1: set int state GigabitEthernet2/6/0 up set int ip

Re: [vpp-dev] Geneve SIGSEGV

Hoi, I think the crash is not our good way to demonstrate your config error, but you should consider creating the GENEVE tunnel in "l3-mode" if you want to use it as an L3 interface - by default the tunnel will be an L2 device (and as such, should not be able to receive an IP address). vpp#

[vpp-dev] Geneve SIGSEGV

Hello, I need to configure a geneve tunnel. I have a physical interface passed to VPP which should be used for the tunnel. I have the following configuration: *set int state GigabitEthernet2/6/0 upset int ip address GigabitEthernet2/6/0 10.10.1.1/24 create

Re: [vpp-dev] #vpp_papi vpp_papi.vpp_serializer.VPPSerializerValueError: Unknown message type vl_api_mss_clamp_dir_t

Hi folks, Can someone help me to resolve this error ? Any help would be greatly appreciated. Thanks, Suresh Vuppala -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21964): https://lists.fd.io/g/vpp-dev/message/21964 Mute This Topic:

Re: [vpp-dev] How to limit(police) upload/download per IP address?

> So there is no way to police per IPs. > In other words to incorporate separate limiter (1.0.0.1, 1.0.0.2, 1.0.0.3 > - 60in/20out, 1.0.0.10, 1.0.0.20, 1.0.0.30 - 90in/80out etc.) to all users > behind interface? I do not think so. Best ben -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all

Re: [vpp-dev] How to limit(police) upload/download per IP address?

So there is no way to police per IPs. In other words to incorporate separate limiter (1.0.0.1, 1.0.0.2, 1.0.0.3 - 60in/20out, 1.0.0.10, 1.0.0.20, 1.0.0.30 - 90in/80out etc.) to all users behind interface? От: vpp-dev@lists.fd.io от имени Benoit Ganne (bganne)

Re: [vpp-dev] How to limit(police) upload/download per IP address?

AFAICT, output policer is only supported per interface, not per flow. You should be able to apply an output policer on an interface with the command 'policer output name '. Best ben > -Original Message- > From: vpp-dev@lists.fd.io On Behalf Of ?? > Sent: Monday, October 3,

Re: [vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

Hi Wentian, Xiaodong, When testing VM-to-VM iperf (ie TCP) throughput like Wentian does, the most important factor is whether GSO is turned on: when using Linux as a router, it is by default whereas when using VPP as a router it is not. GSO means Linux is going to use 64K bytes TCP packets

[vpp-dev] How to limit(police) upload/download per IP address?

Hi, We need to limit user ingress/ergress speed per IP4. Is there any documentation how to perform this in VPP? I've made config based on this blog https://blog.51cto.com/u_15301988/5181021 and it works: set interface ip address GigabitEthernet0/4/0 100.0.0.1/24 set interface ip address

Re: [vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

Hi Wentian, I ran a perf test with a similar topo to your setup and got the same result. The only difference is that the iperf server is running on the host rather than in another VM. So the throughput is close to 20Gbps with Linux kernel data plane while only 1.5Gbps with VPP dataplane. I think

Re: [vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

Hi Xiaodong, Thank you for your reply! I'm exactly using the VPP 22.06 installed through apt from FD.io repo. The linux-cp and linux-nl plugins also come with the VPP from the repo. The virtual NICs on my VMs use the virtio(assigned by "model=virtio" when installing with virt-install). The

[vpp-dev] #vpp_papi. vpp_papi.vpp_serializer.VPPSerializerValueError: Unknown message type vl_api_mss_clamp_dir_t

I am hitting this error on starting vpp-agent service. Can someone help to overcome this? Oct 02 14:52:25 gnaosp001 vpp-agent[960833]: DEBUG vpp_papi.vpp_serializer [-] Unknown union type vl_api_ip4_address_t {{(pid=960833) __init__

回复: [vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

Hi Xiaodong, Thank you for your reply! I'm exactly using the VPP 22.06 installed through apt from FD.io repo. The linux-cp and linux-nl plugins also come with the VPP from the repo. The virtual NICs on my VMs use the virtio(assigned by "model=virtio" when installing with virt-install). The

Re: [vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

Which vpp version are you using in your testing? As of VPP 22.06, linux-cp and linux-nl plugins have been supported and the binary builds are available at FD.io repository ( https://s3-docs.fd.io/vpp/22.10/gettingstarted/installing/ubuntu.html). Can you install vpp from the FD.io repo and try

[vpp-dev] Throughput of VPP on KVM is Significantly Worse than Linux Kernel

Hi everyone, I am a beginner of VPP, and I'm trying to use VPP+FRR on KVM VMs as routers. I have installed VPP and FRR on Ubuntu 20.04.5 VMs, and made them running in a seperated network namespace. I use VPP Linux-cp plugin to synchronize the route from kernel stack to VPP. The VPP and FRR

<    3   4   5   6   7   8   9   10   11   12   >