[vpp-dev] VPP API execution is slow for classify, policer and gtpu APIs

Getting a delay of 80-120ms delay in execution "policer_add_del", "vnet_classify_new_table" and "vnet_gtpu_add_mod_del_tunnel" Startup.conf CPU config is as: cpu { ## In the VPP there is one main thread and optionally the user can create worker(s) ## The main thread and worker thread(s) can b

[vpp-dev] VPP Classify and policer api execution is flow

Getting a delay of 80-120ms delay in execution "policer_add_del", "vnet_classify_new_table" and "vnet_gtpu_add_mod_del_tunnel" Startup.conf CPU config is as: cpu { ## In the VPP there is one main thread and optionally the user can create worker(s) ## The main thread and worker thread(s) can b

[vpp-dev] RSS queue group action in vnet/flow CLI

Hi, I have a patch sent 2 weeks ago, which is about to enable RSS queue group action in vnet/flow CLI, but no body review. The patch is below: https://gerrit.fd.io/r/c/vpp/+/35780 RSS queue group action is a supported action in DPDK. It can distribute packets among several assigned continuous q

[vpp-dev] Can vpp receive packet of 5G/4G module? #dpdk

Hi, Can vpp receive packets of 5G/4G module? And can the dpdk bind 5G NIC? Thanks. -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21256): https://lists.fd.io/g/vpp-dev/message/21256 Mute This Topic: https://lists.fd.io/mt/90455824/21656 Mute #dpdk:h

Re: [vpp-dev] How to check how many packets per vector is VPP processing ? #vpp

Hi David, The last column is actually packets per call. On Wed, 13 Apr 2022 at 10:35, wrote: > Hi Pim, > > Thanks for your answer. I tried the command "show runtime" but I cannot > see those information. That's what I see from vppctl : > > vpp# show runtime > Time 488589.1, 10 sec internal node

Re: [vpp-dev] User traffic is going down the wrong tunnel when multiple IKEv2/IPsec tunnels are added, removed then added.

Hi Neale, I think I mistakenly sent a reply just to you instead of to the group, so I'm sending the reply again. We are using ip session redirect for management traffic to make sure that packets are reachable between the vpps.  The ip session redirect is setup to reach the remote vpp's managem

Re: [vpp-dev] Intel E810 rte_eth_dev_start unknown error -5 rx missed #dpdk

Pim, Thank you very much, your intuition was right and indeed solved the problem. I get some weird output in dmesg, which I suspect is related to not up to date versions of individual components, but I can confirm it pings! [2.148347] ice :05:00.0: QinQ functionality cannot be enabled on

Re: [vpp-dev] Intel E810 rte_eth_dev_start unknown error -5 rx missed #dpdk

Hoi, I am not familiar with the message, but in the past I've had DPDK refuse to start if the wrong DDP was loaded: [0.431937] kernel: pci :0c:00.0: [8086:1592] type 00 class 0x02 [0.431959] kernel: pci :0c:00.0: reg 0x10: [mem 0xea00-0xebff 64bit pref] [0.431981] k

[vpp-dev] Intel E810 rte_eth_dev_start unknown error -5 rx missed #dpdk

Hello, This is my first message, hope I'm in the right place. I'm having troubles with an Intel E810-CAM2 card and VPP/DPDK: after assigning an IP address to the VPP interface and enabling it, I can't ping it. It looks like all packets get dropped (rx missed) and in show interfaces I can see the

Re: [vpp-dev] User traffic is going down the wrong tunnel when multiple IKEv2/IPsec tunnels are added, removed then added.

Hi Sonia, How are you routing into the tunnels, and what changes to that routing do you make when removing and adding tunnels. /neale From: vpp-dev@lists.fd.io on behalf of Sonia Rovner via lists.fd.io Date: Tuesday, 12 April 2022 at 22:57 To: vpp-dev@lists.fd.io Subject: [vpp-dev] User tra

Re: [vpp-dev] Queries regarding mfib and multicast support in VPP

Hi Arun, From: vpp-dev@lists.fd.io on behalf of arunmittal88 via lists.fd.io Date: Tuesday, 12 April 2022 at 15:24 To: vpp-dev@lists.fd.io Subject: [vpp-dev] Queries regarding mfib and multicast support in VPP Hi, Just want to know if the mfib-lookup node is attached to the default packet pr

Re: [vpp-dev] How to check how many packets per vector is VPP processing ? #vpp

Hi Pim, Thanks for your answer. I tried the command "show runtime" but I cannot see those information. That's what I see from vppctl : vpp# show runtime Time 488589.1, 10 sec internal node vector rate 1.00 loops/sec 6214808.56 vector rates in 2.3584e1, out 2.2146e1, drop 1.4381e0, punt 0.e0

[vpp-dev] How to add compile flag to VPP makefile

Hi, I am just doing a test and need to include Python.h in the vnet/pg code. When I "make build", it reports error that Python.h is not found. In my environment, I find out that I need to add the flag "-I/usr/include/Python3.9 -lpython3.9" when I compile a code with Python.h using gcc directly.

Re: [vpp-dev] create af_xdp interface with exception kernel info "Kernel error message: virtio_net: Too few free TX rings available"

Hmm sounds like the virtio driver does not return an error to userspace when failing to create txq? With af_xdp we try to create 1 txq per VPP worker, up to the number available txq advertised by the kernel for the interface. If the txq creation failed, we just use the txq we got. Unless there i