Re: [vpp-dev] VPP crashing if we configure srv6 policy with five sids in the sidlist

Another question: why is the buffer size not larger by default? Does increasing it create other problems? -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21852): https://lists.fd.io/g/vpp-dev/message/21852 Mute This Topic:

Re: [vpp-dev] VPP crashing if we configure srv6 policy with five sids in the sidlist

Thank you for your reply Is there no way to change this parameter without recompiling VPP? -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21851): https://lists.fd.io/g/vpp-dev/message/21851 Mute This Topic: https://lists.fd.io/mt/93495917/21656

Re: [vpp-dev] VPP crashing if we configure srv6 policy with five sids in the sidlist

Simone, This should help: vpp-dev@lists.fd.io | VLIB headroom buffer size modfification Cheers, Pablo. From: vpp-dev@lists.fd.io On Behalf Of simone nafra via lists.fd.io Sent: martes, 6 de septiembre de 2022 9:02 To: vpp-dev@lists.fd.io

[vpp-dev] VPP crashing if we configure srv6 policy with five sids in the sidlist

Hi, As shown in thread number #21611 also I trying to implement an SRv6 network through VPP 22.06 I encounter the problem that after a certain number of nodes (SID List >= 6) the Ingress router no longer forwards packets from the interface and after a while VPP crashes In my topology the

[vpp-dev] One proposal for community meeting

Hi, As I see in Dave's message, our Community Meeting will be held next Tuesday (9.13). I am wondering if I can have some time to present my patch - packetforge (5 minutes). It's been a long time since it was last reviewed, and I think perhaps it is not clear to understand. The patch link

[vpp-dev] IOAM decap problem

hi, I am testing IOAM using https://github.com/CiscoDevNet/iOAM/tree/master/scripts/vpp_sandbox/example/simple-ip6 The problem seems to be similar with https://lists.fd.io/g/vpp-dev/topic/32270029#13405 in the decap node , run show trace: 01:50:03:884443: af-packet-input af_packet: hw_if_index

[vpp-dev] Fix for vpp-csit-verify-device-master-ubuntu2204-x86_64-1n-skx job failures

Folks, We're in the process of upgrading our CI infrastructure to use Ubuntu-22.04 LTS.  An issue was discovered that causes the vpp-device jobs (vpp-csit-verify-device-master-ubuntu2204-x86_64-1n-*) to fail due to memory exhaustion. Damjan helped identify the root cause & correct fix [1],

Re: [vpp-dev] vlib_log assert in dataplane workers

A single printf() costs more clock cycles than processing a packet through the entire forwarding graph. It's not OK to call vlib_log() in data plane code. D. From: vpp-dev@lists.fd.io On Behalf Of Vadim Platonov via lists.fd.io Sent: Friday, September 2, 2022 8:14 AM To:

[vpp-dev] vlib_log assert in dataplane workers

Hi, Could you explain the reason of the assert https://github.com/FDio/vpp/blob/master/src/vlib/log.c#L146? Is this the performance reason? Could we use vlib_log on dataplane workers? Best Regards, Vadim Platonov -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group.

[vpp-dev] 2022-09-01 FD.io VPP (master branch) Gerrit Change Report

Folks, I have updated a gerrit change report generator authored by Ole Troan [0] to produce a report that categorizes the state of the Gerrit review queue.  Each gerrit change is labeled with the following status: == === Status Complete 

[vpp-dev] benchmark for a patch

Hello folks, Is it possible to trigger a benchmark (csit, only 1 test case) for a specific patch which is not merged? -- Best regards Stanislav Zaikin -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21842):

[vpp-dev] 3 weeks to VPP 22.10 RC1 milestone

Hi all, With the first day of September being imminent, also it’s quickly approaching the time of the VPP 22.10 RC1 milestone: in three weeks from today. On 21st of September i will pull the branch stable/2210 which will be accepting only bugfixes and low-risk commits in preparation to the

Re: [vpp-dev] hash api?

Ben, Thanks so much. Hemant -Original Message- From: vpp-dev@lists.fd.io On Behalf Of Benoit Ganne (bganne) via lists.fd.io Sent: Wednesday, August 31, 2022 3:11 AM To: vpp-dev@lists.fd.io Subject: Re: [vpp-dev] hash api? > I did poke around hash.h but didn’t find the api I need.

Re: [vpp-dev] hash api?

> I did poke around hash.h but didn’t find the api I need. Would vpp > consider adding crc32 and crc16? ECMP and Network Packet Broker use > hashes. We typically use crc32c if supported by HW or xxhash, see clib_bihash_hash_16_8_32() for example. For ECMP we also have ip4_compute_flow_hash() and

Re: [vpp-dev] VPP LDP ERROR

Hi wanghe, Hard to say exactly what’s happening there but, at a high level, vls tries to clone a vcl session from one worker to another and the rpc does not return after 3s. Are you running this at scale or does this happen with few sessions? Also, make sure that a session does not

Re: [vpp-dev] hash api?

I did poke around hash.h but didn't find the api I need. Would vpp consider adding crc32 and crc16? ECMP and Network Packet Broker use hashes. Thanks, Hemant From: vpp-dev@lists.fd.io On Behalf Of hemant via lists.fd.io Sent: Tuesday, August 30, 2022 10:51 AM To: vpp-dev@lists.fd.io

Re: [vpp-dev] option to drop untagged /tagged packet in vpp.

Hi All, Has anyone faced similar issue in the past? where they try to drop all untagged packets coming to a interface ? or when they try to create a subinterface for untagged packet ? Thanks Pragya Nand On Fri, Aug 26, 2022 at 8:04 AM Pragya Nand Bhagat < pragya.nand.bhaga...@gmail.com> wrote:

[vpp-dev] VPP LDP ERROR

Hi, vpp experts my vpp version is 22.06 vcl.conf { ... multi-thread-workers } im use multi thread program with LDP hoststack, vcl.conf config 'multi-thread-workers', my program will listen many ports, but now program run will error error message: vls_mt_session_migrate:1065 failed

Re: [vpp-dev] ipip0 or ipsec0 is not getting created after executing "ikev2 initiate sa-init pr1"

Hi Nilesh, there is 'show event-logger' command for that. From: vpp-dev@lists.fd.io on behalf of Nilesh Inamdar Sent: Monday, August 29, 2022 12:17 PM To: vpp-dev@lists.fd.io Subject: Re: [vpp-dev] ipip0 or ipsec0 is not getting created after executing

[vpp-dev] About vpp qos

Hi, vpp experts im study qos, but i found that hqos is not support, do you have plan for support it? if i want use vpp qos, can you give me some suggesions? best regards wanghe -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21832):

Re: [vpp-dev] ipip0 or ipsec0 is not getting created after executing "ikev2 initiate sa-init pr1"

Hi Filip, Thank you for helping. You were right. After adding the right esp encryption algorithm that does integrity as well, it worked. I had one more query. I wanted to see ikev2 debugs. So I had set "ikev2 set logging level 5". But I do know where the debugs will get dumped. Can you please

Re: [vpp-dev] ipip0 or ipsec0 is not getting created after executing "ikev2 initiate sa-init pr1"

Hi Nilesh, looks like you didn't configure esp-integ-alg (it is not a good idea not to use integrity algorithm) . So, either configure esp-integ-alg, or use crypto algorithm that does integrity check too, like "esp-crypto-alg aes-gcm-16 256" Filip From:

[vpp-dev] ipip0 or ipsec0 is not getting created after executing "ikev2 initiate sa-init pr1"

Hi Team, I am trying to bringup IPSec session between 2 VPP. After configuring and executing "ikev2 initiate sa-init pr1", the tunnel ipip0 or ipsec0 is not getting created. I see that Child SA is not getting programmed correctly. Topology: vpp-responder (fpeth0) (192.168.4.1)

Re: [vpp-dev] Help needed to bringup IPSec session between 2 VPP using IKEv2 plugin

Hi Shelton, Thanks for looking into it. I tried configuring algorithms on the Responder side as well. But I'm still getting same issue. Following are new logs after configuring algorithms on the Responder side. # Initiator logs

Re: [vpp-dev] Query regarding neos mpls fib entry for tunnel interface

Hi Neale, Thanks a lot for the help. Thanks & Regards, Sreejith On Fri, 26 Aug, 2022, 4:34 AM Neale Ranns, wrote: > > > > > *From: *vpp-dev@lists.fd.io on behalf of sreejith n > via lists.fd.io > *Date: *Thursday, 25 August 2022 at 13:10 > *To: *vpp-dev@lists.fd.io > *Subject: *[vpp-dev]

[vpp-dev] VPP use rdma

Hi The network card of MLX CX6 uses sriov to direct VF to the virtual machine, and then uses the "create interface rdma" command provided by VPP to create an interface. At the same time, use "set interface mac" to configure the RDMA interface in VPP as the MAC address of VF. Currently, you

[vpp-dev] option to drop untagged /tagged packet in vpp.

Hi All, Is there a way in vpp to drop untagged packets received on a interface which has different subinterfaces for different vlan. When I create a subinterface using : vpp# create sub-interfaces host-ve_b 100 host-ve_b.100 vpp# create sub-interfaces host-ve_b 10 untagged create sub-interfaces:

Re: [vpp-dev] Query regarding neos mpls fib entry for tunnel interface

From: vpp-dev@lists.fd.io on behalf of sreejith n via lists.fd.io Date: Thursday, 25 August 2022 at 13:10 To: vpp-dev@lists.fd.io Subject: [vpp-dev] Query regarding neos mpls fib entry for tunnel interface Hi All, I have a query regarding neos mpls fib entry for tunnel interface. I have

Re: [vpp-dev] Help needed to bringup IPSec session between 2 VPP using IKEv2 plugin

Did you make sure the algorithms (for both encryption and authentication) used for initiator and responder match? It looks like you didn't configure the algorithms for either IKE SA or IPsec SA the responder, I don't know if the default setting will work. If you are unsure about it either, I'd

[vpp-dev] Help needed to bringup IPSec session between 2 VPP using IKEv2 plugin

Hi Team, I am new to VPP. I am trying to bringup IPSec session between 2 VPP using IKEv2 plugin. I followed this link : https://wiki.fd.io/view/VPP/IPSec_and_IKEv2 After doing all the configuration and executing "ikev2 initiate sa-init pr1", I am guessing that child SA is not getting installed

[vpp-dev] Query regarding neos mpls fib entry for tunnel interface

Hi All, I have a query regarding neos mpls fib entry for tunnel interface. I have observed when we create mpls fib entry with neos bit set for tunnel label it always sets forwarding as drop ("dpo-drop mpls"). For the eos bit the issue is not seen the forwarding is set correctly. Is this expected

Re: [vpp-dev] VPP crashing when lcp is enabled and I try to add an interface to a linux bridge.

Hi Pragya, I'm not aware of any plans to implement support for that. The main focus of linux-cp/linux-nl so far has been to connect L3 networking on the host system to VPP. What's the use case you are trying to support? Bridging packets between VPP hardware interfaces in L2 mode? Or bridging

Re: [vpp-dev] VPP crashing when lcp is enabled and I try to add an interface to a linux bridge.

Hi Matthew, Yes I meant the same. Automatically creating a bridge domain in VPP and adding/removing member interfaces based on netlink messages. Thank You Pragya Nand On Wed, Aug 24, 2022 at 12:25 AM Matthew Smith via lists.fd.io wrote: > > On Tue, Aug 23, 2022 at 7:40 AM Pragya Nand Bhagat <

Re: [vpp-dev] Gerrit review request for packetforge - 36149

I have refined the packetforge script and add the function to disable/delete flow rules. Please take a look and review if convenient, thanks! https://gerrit.fd.io/r/c/vpp/+/36149 -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21818):

Re: [vpp-dev] VPP crashing when lcp is enabled and I try to add an interface to a linux bridge.

On Tue, Aug 23, 2022 at 7:40 AM Pragya Nand Bhagat < pragya.nand.bhaga...@gmail.com> wrote: > Hi Matthew, > > Thanks for looking into this issue. > After applying the patch the crash is not seen. > > However as mentioned earlier, we have faced this issue when configuring > the bridge domain and

Re: [vpp-dev] make install-dep fails

Hi Dave, Got it, thanks. Hemant From: vpp-dev@lists.fd.io On Behalf Of Dave Wallace Sent: Tuesday, August 23, 2022 11:59 AM To: vpp-dev@lists.fd.io Subject: Re: [vpp-dev] make install-dep fails Hi Hemant, I would recommend using a more recent Ubuntu LTS release as support for Ubuntu

Re: [vpp-dev] make install-dep fails

Hi Hemant, I would recommend using a more recent Ubuntu LTS release as support for Ubuntu 18.04 was deprecated a many releases ago. All of our CI/CD & CSIT infrastructure are migrating to Ubuntu 22.04 for the upcoming VPP 22.10 release.  I anticipate that support for Ubuntu 20.04 will be

[vpp-dev] make install-dep fails

I am using Ubuntu 18.04. I cloned the vpp repo today. I see a failure to get enchant-2 and libffi7. I installed libffi-dev and enchant but still see the failure. git clone https://gerrit.fd.io/r/vpp $ sudo make install-deps Hit:2 http://us.archive.ubuntu.com/ubuntu bionic InRelease Hit:3

Re: [vpp-dev] vlib buffer allocate/free consumes too many CPU cycles

+1, Ben has it exactly right... Dave On 8/23/22, 4:04 AM, "Benoit Ganne (bganne) via lists.fd.io" wrote: vlib_buffer_validate_alloc_free() should only be called with debug builds to debug buffer allocation issues. Debug builds are slow, because there is no optimizations and lots of

Re: [vpp-dev] VPP crashing when lcp is enabled and I try to add an interface to a linux bridge.

Hi Matthew, Thanks for looking into this issue. After applying the patch the crash is not seen. However as mentioned earlier, we have faced this issue when configuring the bridge domain and adding a member port to it. 1. create a bridge [ brctl addbr 100] 2. try adding a interface to it [

Re: [vpp-dev] vlib buffer allocate/free consumes too many CPU cycles

vlib_buffer_validate_alloc_free() should only be called with debug builds to debug buffer allocation issues. Debug builds are slow, because there is no optimizations and lots of additional checks. Please make sure you are using a release build before benchmarking (eg. make build-release). Best

[vpp-dev] vlib buffer allocate/free consumes too many CPU cycles

hi team, recently I am doing plugin dev with VPP, I found all threads are spending too many CPU cycles with locking/unlocking (with one numa node)buffer_main's buffer_known_hash_lockp, it hinders burst performance. ``` +6.00% vpp_wk_4 libvlib.so.22.02.0[.]

Re: [vpp-dev] mysql proxy by using vpp host stack #vpp-hoststack

Hi, Probably libevent statically links libc. If possible, try to recompile libevent and make it dynamic. Regards, Florin > On Aug 20, 2022, at 8:06 PM, weizhen9...@163.com wrote: > > Hi, > Now I implement mysql proxy by using libevent.so. And I want to implement > mysql proxy by vpp

Re: [vpp-dev] TCP Stack Performance Benchmark

Hi Anthony, Sounds great! Let me know what you find. As for wrk, maybe give it a try. Typically, we’ve focused ldp testing on server side, e.g., nginx/envoy, since that was what folks were interested in. We should probably take a closer look at client side as well. Regards, Florin > On

[vpp-dev] mysql proxy by using vpp host stack #vpp-hoststack

Hi, Now I implement mysql proxy by using libevent.so. And I want to implement mysql proxy by vpp hoststack. But I find the dynamic library libevent.so can not callback the libvcl_preload. Is this plan possible? Thanks. -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group.

Re: [vpp-dev] VPP crashing when lcp is enabled and I try to add an interface to a linux bridge.

Hi Pragya, This patch should fix it - https://gerrit.fd.io/r/c/vpp/+/36961. Can you apply it to your build and confirm whether it resolves the issue? Thanks, -Matt On Wed, Aug 17, 2022 at 6:55 AM Pragya Nand Bhagat < pragya.nand.bhaga...@gmail.com> wrote: > Hi All, > > I'm seeing a crash in

Re: [vpp-dev] TCP Stack Performance Benchmark

Hi Florin, Thank you for the reply. I have seen with Netperf that actually there is TCP traffic going back and forth, a connection is established and then the client side crashes. I'll try to dig deeper to see what might be causing that. All I see on the server side is a received invalid

Re: [vpp-dev] TCP Stack Performance Benchmark

Hi Anthony, I for one have not tried netperf, so not sure why it’s not working. Assuming it is directly using epoll/select, i.e., no libevent/ev it should work unless it uses a weird threading model. So, it might be worth investigating why it’s crashing. Do you need both server and client

[vpp-dev] Frame leak in vlib_worker_thread_node_refork

Hi all! We've noticed that each refork causes VPP to leak every frame allocated at each worker. It happens at src/vlib/threads.c:916 as vector of next frames is free'd without clearing frame allocations. In turn that causes a fairly significant memory leak in the main heap (up to 200MiB per

[vpp-dev] VPP crashing when lcp is enabled and I try to add an interface to a linux bridge.

Hi All, I'm seeing a crash in VPP when we try to add a port to a bridge . VPP is running with the lcp plugin. lcp default netns '' lcp lcp-auto-subint off lcp lcp-sync on lcp del-static-on-link-down off lcp del-dynamic-on-link-down off itf-pair: [0] port0/0 tap1 Ethernet0 96 type tap

[vpp-dev] TCP Stack Performance Benchmark

Hi all, I am currently trying to compare TCP performance between the host TCP vs VPP TCP stack. Mainly I am focused on latency but am struggling to find tools to make the comparison. I have tried looking at iPerf as this has been used with VPP through VCL but this only provides UDP latency

Re: [vpp-dev] NAT44 for TCP/UDP

Hi Ashwini, Thank you. I am looking into it. Best regards, Filip Varga po 15. 8. 2022 o 21:33 Ashwini Kadam napísal(a): > Hi Filip, > > Please let me know your thoughts on what the issue is and how it can be > resolved. We are working towards a demo and hoping to use VPP in it. This > is

Re: [vpp-dev] NAT44 for TCP/UDP

Hi Filip, Please let me know your thoughts on what the issue is and how it can be resolved. We are working towards a demo and hoping to use VPP in it. This is kind of a blocker right now. Regards, Ashwini Kadam -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group.

Re: [vpp-dev] Free a vlib buffer from out a VPP worker thread

Short answer: yes. Here's an example of how to start a foreign thread taken from the [golang dialect] g2 viewer plugin (*): /* *INDENT-OFF* */ VLIB_REGISTER_THREAD (ego_g2_thread_reg, static) = { .name = "g2-thread", .short_name = "g2", .function = ego_g2_thread_fn, .use_pthreads

Re: [vpp-dev] Free a vlib buffer from out a VPP worker thread

Dave, Does VPP support the concept of additional threads that are spawned from within a plugin, lets call them 'external threads', and the allocation of a vlib_main_t / vlib_buffer_pool_thread_t for these external threads, or should all interactions such as freeing a buffer, be

[vpp-dev] ikev2 CREATE_CHILD_SA with KE (aka PFS)

Hi, In RFC 7296, CREATE_CHILD_SA Exchange may contain the KE payload to enable stronger guarantees of forward secrecy. When the KEi payload is included in the CREATE_CHILD_SA request, responder should reply with the KEr payload and complete the key exchange, in accordance with the RFC. Could you

Re: [vpp-dev] NAT44 for TCP/UDP

Hi Filip, Please let me know your thoughts on what the issue is and how it can be resolved. Regards, Ashwini Kadam -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21795): https://lists.fd.io/g/vpp-dev/message/21795 Mute This Topic:

Re: [vpp-dev] Free from a vlib buffer from out a VPP worker thread

As long as the thread has an associated vlib_main_t / vlib_buffer_pool_thread_t not accidentally shared with another thread, you shouldn't have any problems... FWIW... Dave From: vpp-dev@lists.fd.io On Behalf Of Simon Barber via lists.fd.io Sent: Thursday, August 11, 2022 6:42 AM To:

[vpp-dev] Free from a vlib buffer from out a VPP worker thread

Hi, Does anybody anticipate any issues calling vlib_buffer_free_one to free a buffer when running on a thread that is not registered as a VPP worker thread. Initial testing indicates that it works. Regards Simon -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group.

[vpp-dev] #plugin Query related to VPP unittest framework integration

Hi, We are trying you integrate FDIO unittest framework into our product. Basically we have built some custom plugins and integrated those as VPP plugins. We have our build environment where VPP is built including these custom plugins. When we launch VPP inside our cluster it is working fine.

Re: [vpp-dev] Facing issue in inter bridge routing .

Hi Pragya Nand, The reachability from 1.1.1.1 to 2.2.2.3 on the host is failing as ARP request 1.1.1.1 -> 2.2.2.3 gets dropped in VPP. Normally both target and source IPs for ARP are expected to be in the same subnet of the Rx interface. You can try enabling proxy ARP on the Rx interface for the

Re: [vpp-dev] NAT44 for TCP/UDP

Hi Filip, Please also find attached the VPP trace for tcp data when nat44 forwarding is disabled. Regards, Ashwini Kadam --- Start of thread 0 vpp_main --- Packet 1 00:02:25:661524: dpdk-input wan1920 rx queue 0 buffer 0xff681f: current data 0, length 74,

[vpp-dev] Facing issue in inter bridge routing .

Hi All, Inside vpp I have two bridge-domains and each of them has a loopback interface as bvi. Each bridge domain also has a host-interface . Following is the set of command used. Linux CLIs to configure veth: ip link add ve_A type veth peer name ve_B ip link add ve_C type veth peer name ve_D

Re: [vpp-dev] NAT44 for TCP/UDP

Hi Filip, The VPP trace for dpdk-input in last email incuded TCP requests from HOST C to Host A by iperf3 server and client via VPP. Please find below the vpp trace for dpdk-input for ICMP ping requests from Host C to Host A via VPP. As mentioned above this work. Incuded trace for comparison.

Re: [vpp-dev] NAT44 for TCP/UDP

Hi Filip , Added the following NAT Config vpp# clear trace vpp# trace add dpdk-input 100 vpp# nat44 plugin enable sessions 63000 vpp# nat44 forwarding enable vpp# set interface nat44 in lan vpp# set interface nat44 out wan1920 vpp#  set interface nat44 out wan1930 vpp# nat44 add static mapping

[vpp-dev] Crash when creating AVF interface

VPP should not crash without a good reason, and possible issues with PAPI are not good enough a reason. So I opened a ticket [4] once I saw the backtrace. I will add more details there when I have any (e.g. what exactly is different from usual CSIT daily runs). Vratko. [4]

Re: [vpp-dev] NAT44 for TCP/UDP

Hi Ashwini, Can you also please send me a packet trace from VPP ? Thank you. Best regards, Filip Varga ut 9. 8. 2022 o 23:50 Ashwini Kadam napísal(a): > Hi Filip, > > I did try your recommendations . Updated NAT config to as below > > Test Case 1 > nat44 plugin enable sessions 63000 > nat44

Re: [vpp-dev] NAT44 for TCP/UDP

Hi Filip, I did try your recommendations . Updated NAT config to as below Test Case 1 nat44 plugin enable sessions 63000 nat44 forwarding enable set nat timeout udp 3000 tcp-established 7440 tcp-transitory 2400 icmp 600 set interface nat44 in lan set interface nat44 out wan1 set interface nat44

[vpp-dev] FW: [P4-design] Re: new language features for "5G" and "edge" use cases

As you can see from the lengthy discussion below, VPP is filling yet another need and so is P4. Hemant From: hemant via p4-design Sent: Tuesday, August 09, 2022 9:46 AM To: 'Gergely Pongracz' ; mbu...@vmware.com; jnfos...@cs.cornell.edu Cc: p4-des...@lists.p4.org Subject: RE:

Re: [vpp-dev] NAT44 for TCP/UDP

Hi Ashwini, I will look into your issue. But for reference I would advise against using a combination of inside interface and output-feature. OUTPUT-FEATURE or in other words output interface already contains nat44-inside node. Output-feature does postrouting - after ip4-lookup node decides

Re: [vpp-dev] ikev2 rekeying with multiple notify payloads

Hi Benoit, Thank you for the quick work! -- Best regards, Atzm WATANABE -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21781): https://lists.fd.io/g/vpp-dev/message/21781 Mute This Topic: https://lists.fd.io/mt/92887834/21656 Group Owner:

[vpp-dev] ikev2 repeated rekeying

Hi, In current implementation of ikev2 plugin, it seems to keep old inbound IPsec SA for a while after rekeying is done, and this old IPsec SA seems to be deleted by manager process later. But it is not deleted and remains forever if rekeying request comes again before deleting it, because 2

[vpp-dev] NAT44 for TCP/UDP

Hi All, I am trying to make NAT44 ed work for TCP/UDP traffic on my setup. My setup is as follows Host A, Host B <-VPP <- Host C Host A , Host B and Host C can communicate to each other via VPP. The VPP container has two interfaces. My current version of VPP is

Re: [vpp-dev] VPP worker thread going in D state

Hi Ben, It is coming out of D state and not staying there, we saw memif buffer exhaustion on client side so started debugging and saw VPP worker is going in D state and this happens after 2-3 hours of run. Will try to capture vpp worker stack and share. Line 39896:  6701 root      20   0 

Re: [vpp-dev] ikev2 rekeying with multiple notify payloads

Merged, thanks Atzm! Best ben > -Original Message- > From: vpp-dev@lists.fd.io On Behalf Of > atzm...@gmail.com > Sent: Monday, August 8, 2022 10:18 > To: vpp-dev@lists.fd.io > Subject: [vpp-dev] ikev2 rekeying with multiple notify payloads > > Hi, > > In RFC 7296, Child SA rekey

[vpp-dev] ikev2 rekeying with multiple notify payloads

Hi, In RFC 7296, Child SA rekey using CREATE_CHILD_SA may include multiple Notify payloads. VPP's current ikev2 plugin implementation seems to support multiple Notify payloads but to expect the REKEY_SA message is placed after any other Notify payloads. Some implementation sends rekey request

Re: [vpp-dev] VPP worker thread going in D state

Can you share the output of 'cat /proc//stack'? This should tell us where the worker is stuck in the kernel. Best ben > -Original Message- > From: vpp-dev@lists.fd.io On Behalf Of Satish Singh > Sent: Saturday, August 6, 2022 20:36 > To: vpp-dev@lists.fd.io; vpp-dev+h...@lists.fd.io >

Re: [vpp-dev] QoS support in VPP deprecated ??

Hi Saravana, As far as I know, it was lack of maintenance (by lack of interest from the community). There was no maintainer, and the code did not keep up and was broken. For it to re-instantiated, it would need to be updated for current master, and someone should volunteer to maintain it.

[vpp-dev] QoS support in VPP deprecated ??

Hi All, I am looking for using the VPP for our project with HQoS functionality and learned that it was deprecated after 1804 version of VPP. Kindly light some points why it is being deprecated ? Can this be ported to latest version of VPP? Thanks Saravana -- Best Regards, Saravana

[vpp-dev] VPP worker thread going in D state

Hi VPP experts, I am facing one issue with VPP 21.01, where the VPP worker thread is going in D(uninterruptible) state, not able to find the reason why this is happening? Could you please provide some help or pointer to what could be an issue? using below interfaces in VPP: 1) memif 2)

Re: [vpp-dev] VPP crashing if we configure srv6 policy with five sids in the sidlist

Can you provide the topology, configurations, and steps to recreate this crash? Steven From: on behalf of Chinmaya Aggarwal Reply-To: "vpp-dev@lists.fd.io" Date: Wednesday, July 13, 2022 at 4:07 AM To: "vpp-dev@lists.fd.io" Subject: Re: [vpp-dev] VPP crashing if we configure srv6 policy

Re: [vpp-dev] VPP crashs when using tap interfaces.

Hello, We are not supporting VPP 21.01. Please try with 22.06 or VPP master. Please run vpp in debug mode and share the backtrace if you still hit with the problem. BTW -br Mohsin From: on behalf of Khaled Salhi Reply-To: "vpp-dev@lists.fd.io" Date: Friday, August 5, 2022 at 9:16 AM To:

[vpp-dev] VPP crashs when using tap interfaces.

Hello, I'm using VPP 21.01 on Ubuntu 20.04 with a tap interface. VPP crashes when trying to verify this assert: /vpp/src/vlib/trace_funcs.h:63 (vlib_add_trace_inline) assertion `vnet_trace_placeholder' fails When I use the host interface (not tap), there's no crash. Did someone face the same

[vpp-dev] GTPU tunnel - teid and tteid use case

Hi Team, I am trying GTP-U in VPP. I followed the link below https://docs.fd.io/vpp/19.01/clicmd_src_plugins_gtpu.html . I have few clarifications 1) With the above configuration ,gtpu_tunne0 is configured with an IP from subnet [11.9.0.0/16] which is the peer side network [loop0 -

Re: [vpp-dev] LACP bond interface not working

Please check to make sure the interface can ping to each other prior to adding them to the bond. Type “show lacp details” to verify VPP receives LACP PDUs from each other and the state machine. Steven From: on behalf of Chinmaya Aggarwal Reply-To: "vpp-dev@lists.fd.io" Date: Tuesday, June

Re: [vpp-dev] Memory region shows empty for vhost interface

Agreed with Steven. I ran into the same issue recently. Please take a look at https://stackoverflow.com/questions/69710907/connect-qemu-kvm-vms-using-vhost-user-client-and-ovs-dpdk and https://www.redhat.com/en/blog/hands-vhost-user-warm-welcome-dpdk. Basically you will need to allocate enough

Re: [vpp-dev] Memory region shows empty for vhost interface

It is related to memoryBacking, missing hugepages, or missing shared option. What does your qemu launch command look like? Steven From: on behalf of Chinmaya Aggarwal Reply-To: "vpp-dev@lists.fd.io" Date: Thursday, July 14, 2022 at 3:31 AM To: "vpp-dev@lists.fd.io" Subject: [vpp-dev]

Re: [vpp-dev] VPP crashes when lcp host interface is added in network bridge

Please try debug image and provide a sane back trace. Steven From: on behalf of Chinmaya Aggarwal Reply-To: "vpp-dev@lists.fd.io" Date: Thursday, July 21, 2022 at 4:42 AM To: "vpp-dev@lists.fd.io" Subject: [vpp-dev] VPP crashes when lcp host interface is added in network bridge Hi, As

Re: [vpp-dev] Crash in rte_ipv6_phdr_cksum during tx

Build a debug vpp image and use gdb to debug the crash. Hemant From: vpp-dev@lists.fd.io On Behalf Of Vijay Kumar Sent: Thursday, August 04, 2022 12:17 AM To: vpp-dev Subject: [vpp-dev] Crash in rte_ipv6_phdr_cksum during tx Hi experts, Has anyone seen this below crash back-trace

[vpp-dev] Crash in rte_ipv6_phdr_cksum during tx

Hi experts, Has anyone seen this below crash back-trace happening during the TX? Cras was seen in this function rte_ipv6_phdr_cksum The QA was trying to run a call model with about 200 UEs trying to connect to VPP and the crash was seen. This doesn't always happen. Any pointers on this is

[vpp-dev] GoVPP import path changed to go.fd.io/govpp

Hi GoVPP & VPP users, Following up on the lasts GoVPP Community meetings discussions the GoVPP package path has been changed to `go.fd.io/govpp` This is part of an effort to also move the repository to github, add CI jobs, etc... If you are a GoVPP user, this means you should either : - Stay on

Re: [vpp-dev] Unable to set valid-lifetime in ipv6 ra

Mr. Hemant, Mr. Ole, thank you for your review. As you say, I think the keyword "fixed" is more appropriate. Therefore, I have replaced "no-decrement" with "fixed". Thanks, Takanori > From rfc4861: > >  Each prefix has an associated: > >

Re: [vpp-dev] VPP buffer pool allocation optimization guidance

> I am wondering if VPP could allow > VLIB_BUFFER_POOL_PER_THREAD_CACHE_SZ 512 to be changed to a build time > value as done in DPDK ? It is a define, you can change it - but I do not think it has been tested . Maybe we can make it configurable through cmake also. > Since in this specific use

Re: [vpp-dev] Copy packet forwarding performance issues

Ha I see, then I guess you can alloc multiple heads at once and then use vlib_buffer_attach_clone(). You usually need to duplicate the head of the packet you're cloning because it's going to be rewritten when you forward (ttl decrement, l2 rewrite etc). ben > -Original Message- > From:

Re: [vpp-dev] Copy packet forwarding performance issues

Hi, ben Thanks for your hint, i used vlib_buffer_clone() to copy packet， but the performance is drop i found that vlib_buffer_clone is use vlib_buffer_alloc()，is there other way to improve performance？ by the way，i also used rte_mbuf_from_vlib_buffer() to use dpdk‘s rte_mbuf to use dpdk buf

Re: [vpp-dev] Bridge-domain function and usage.

Hi Pargya, That’s a multicast destination address. /neale From: vpp-dev@lists.fd.io on behalf of Pragya Nand Bhagat via lists.fd.io Date: Tuesday, 2 August 2022 at 12:25 To: vpp-dev@lists.fd.io Subject: Re: [vpp-dev] Bridge-domain function and usage. Hi Steven, I'm sending unknown unicast

Re: [vpp-dev] Bridge-domain function and usage.

Hi Steven, I'm sending unknown unicast packets with source and destination mac as : IP4: a4:bf:01:89:9d:cf -> ab:cd:ef:ab:cd:ef 802.1q vlan 100 Please have a look in the packet trace. Thanks Pragya Nand On Tue, Aug 2, 2022 at 4:51 AM steven luong via lists.fd.io wrote: > Pragya, > > > >

Re: [vpp-dev] Bridge-domain function and usage.

Pragya, UU-Flood stands for Unknown Unicast Flooding. It does not flood multicast or broadcast packets. You need “Flooding” on to flood multicast/broadcast packets. Steven From: on behalf of Pragya Nand Bhagat Reply-To: "vpp-dev@lists.fd.io" Date: Monday, August 1, 2022 at 2:59 AM To:

Re: [vpp-dev] VPP buffer pool allocation optimization guidance

Hi Ben, I am wondering if VPP could allow VLIB_BUFFER_POOL_PER_THREAD_CACHE_SZ 512 to be changed to a build time value as done in DPDK ?  The i40e NIC has 4K max number of tx/rx descriptors. If we change the value of VLIB_BUFFER_POOL_PER_THREAD_CACHE_SZ from 512 to 8K - the number of buffers

Re: [vpp-dev] Unable to set valid-lifetime in ipv6 ra

>From rfc4861: Each prefix has an associated: AdvValidLifetime The value to be placed in the Valid Lifetime in the Prefix Information option, in seconds. The

<    5   6   7   8   9   10   11   12   13   14   >