Just to clarify, the filtering behavior I’m looking for is often known as “full
cone” or “pure cone” NAT.
> On Sep 29, 2020, at 6:33 PM, Joshua Moore wrote:
>
>
> Hello,
>
> I have a need to relax the session lookup criteria on out2in packet
> processing with NAT44 determinate mode. The beh
On Tue, Sep 29, 2020 at 07:29 AM, Pablo wrote:
>
> Yes, those are supported.
Hi Pablo,
What we infer of the documentation link that you shared is that we can
configure encap or inline at per policy level. But, H.Insert and H.Encaps are
headend node behaviour. So how are these two related?
-=-
#9 0x7fff6da8fae4 in ice_alloc_rx_queue_mbufs (rxq=0x7fe2406de580) at
/home/ubuntu/vpp/build-root/build-vpp_debug-native/external/dpdk-20.08/drivers/net/ice/ice_rxtx.c:193
#10 0x7fff6da9fa4b in ice_rx_queue_start (dev=0x7fff7146dec0
, rx_queue_id=5) at
/home/ubuntu/vpp/build-root/build-
[Edited Message Follows]
I think the problem has some relationship with rx queue number of NIC.
dpdk {
dev :65:00.0 { num-rx-queues 16 }
}
Using this config, when bring up interface. There would be 384 buffers
available.
dpdk {
dev :65:00.0 { num-rx-queues 8 }
}
Using this config, when
I think the problem has some relationship with rx queue number of NIC.
>
> dpdk {
> dev :65:00.0 { num-rx-queues 16 }
> }
> Using this config, when bring up interface. There would be 384 buffers
> available.
>
>
>
> dpdk {
> dev :65:00.0 { num-rx-queues 8 }
> }
> Using this config, wh
Hi, vpp-dev,
I am using vpp 20.09RC2. When I bring up the interface, the vnet buffers will
dramatically decreased.
Is this a memory leaking?
>
>
>
> DBGvpp# show version
>
>
>
> vpp v20.09-rc2~0-ga87deb77d built by ubuntu on ubuntu-740-1 at
> 2020-09-30T01:45:40
>
>
>
>
>
>
>
> DBG
Hello,
I have a need to relax the session lookup criteria on out2in packet
processing with NAT44 determinate mode. The behavior I am looking for is so
that as long as there is an initial session for a given destination IP:port
then any return packet to the translated port should be allowed regardl
Yep, definitely looks like this is unsupported. I moved to separated in/out
interfaces and packets started flowing appropriately.
On Tue, Sep 29, 2020 at 2:35 PM Joshua Moore via lists.fd.io wrote:
> Hello,
>
> Do we know if the same in/out interface for NAT in deterministic mode is
> supporte
Hello,
Do we know if the same in/out interface for NAT in deterministic mode is
supported in VPP? I am seeing a strange behavior where return traffic is not
matching the session. For example, see session below where a DNS request is
initially captured outbound to 8.8.8.8: http://jcm.me/session.
Please see in line below against “”.
From: Jon Loeliger
Sent: Tuesday, September 29, 2020 12:36 PM
To: hem...@mnkcg.com
Cc: vpp-dev
Subject: Re: [vpp-dev] table lookup api?
On Tue, Sep 29, 2020 at 9:31 AM mailto:hem...@mnkcg.com> >
wrote:
Maybe we need to clarify some terms here. W
> On 29.09.2020., at 19:29, Joshua Moore wrote:
>
> The driver here is performance. I like the idea of assigning CPUs dedicated
> to the DPDK namespace and avoiding kernel interrupts. My understanding was
> that IOMMU was needed for this but I may be completely off with that thinking.
no, IO
The driver here is performance. I like the idea of assigning CPUs dedicated to
the DPDK namespace and avoiding kernel interrupts. My understanding was that
IOMMU was needed for this but I may be completely off with that thinking.
It doesn’t seem in retrospect of this discussion that IOMMU offers
I am not sure if it worth to try to add “iommu=pt intel_iommu=on” in the GRUB?
We normally do it in both Linux host/guest, but in the case of ESXi not sure if
that will help with the vfio-pci IOMMU issue…
Regards,
Yichen
From: on behalf of "Damjan Marion via lists.fd.io"
Reply-To: "dmar...@m
On Tue, Sep 29, 2020 at 9:31 AM wrote:
> Hi Jon,
>
>
>
> I see, thanks. I have to go back to the drawing board.
>
>
>
> I am developing a P4 to VPP compiler. If VPP has any API to create a
> table and lookup the table, it would ease compiler development. I am
> chasing lookup because the looku
Thanks Dave for your relentless efforts in making VPP better, not just from
performance perspective but also from its usability point of view. Contribution
like perfmon, pcap tracing, G2 graph viewer and list goes on …are sheer
examples of visionary PTL.
Congratulations to Damjan!. Both of you
Joshua,
What is your motivation for using IOMMU inside VM?
It is typically used by hypervisor to protect from misbehaving VMs.
So unless you want to do nested virtualisation, IOMMU inside your VM doesn’t
bring lot of value.
Can you simply try to turn off iommu in the VM and turn
“enable_unsafe_n
Hi Jon,
I see, thanks. I have to go back to the drawing board.
I am developing a P4 to VPP compiler. If VPP has any API to create a table and
lookup the table, it would ease compiler development. I am chasing lookup
because the lookup result drives subsequent processing in the data pla
Hi Chinmaya,
Yes, those are supported.
T.Insert and T.Encaps were renamed into H.Insert and H.Encaps; and they are not
localsid behaviors but rather an SR Headend behavior.
Documentation is in here:
https://docs.fd.io/vpp/20.09/db/db5/srv6_policy_doc.html
Cheers,
Pablo.
From: vpp-dev@lists.fd
Hi,
I am checking the localsid behaviors supported in VPP v20.05.1 and cannot find
T.Insert, T.Encaps, H.Insert and H.Encaps in the list.
Are these behaviors supported in VPP? If not, are there any plans to add
support for them?
Thanks and Regards,
Chinmaya Agarwal.
-=-=-=-=-=-=-=-=-=-=-=-
Link
On Fri, Sep 25, 2020 at 4:35 PM hemant via lists.fd.io wrote:
> In the classify API mentioned in the subject of this email, I could use an
> example with tables to understand table_index, next_table_index, and
> miss_next_index. I know VPP maintains an index for a table.
>
>
>
> Say, the tables
On Mon, Sep 28, 2020 at 1:15 PM hemant via lists.fd.io wrote:
> I have created a table in VPP using the vnet_classify_add_del_session()
> API.
>
>
>
> What API do I use to lookup this table?
>
>
>
> Thanks,
>
>
>
> Hemant
>
There is no API to do a Classifier table lookup. When the table was
cr
> Of course there's a PCI switch. My main purpose of leveraging SR-IOV with
> VF allocation is to allow the internal eswitch on the Intel NIC to handle
> switching in hardware
A PCIe switch is a different beast than the internal "Ethernet switch" you are
mentioning.
The PCIe topology in your serv
Ben,
Of course there's a PCI switch. My main purpose of leveraging SR-IOV with
VF allocation is to allow the internal eswitch on the Intel NIC to handle
switching in hardware instead of the vswitch on the ESXI hypervisor. I
don't really care so much about isolation of the PCI devices nor the risk
Hi Joshua,
Glad it solves the vfio issue. Looking at the dmesg output, I suspect the issue
is that the PCIe topology advertised is not fully supported by vfio + IOMMU: it
looks like your VF is behind a PCIe switch, so the CPU PCIe IOMMU root-complex
port cannot guarantee full isolation: all dev
Hello Ben,
echo 1 | sudo tee /sys/module/vfio/parameters/enable_unsafe_noiommu_mode
sudo dpdk-devbind --bind=vfio-pci :13:00.0
The above commands successfully resulted in vfio-pci driver binding to the
NIC. However, as soon as I assigned the NIC to VPP and restarted the
service, my VM CPU sho
Hi Prashant,
> 1. What is the expected performance benefit if RDMA driver is used in
> VPP instead of DPDK driver ?
- out-of-the-box support for Mellanox CX4/5 NIC in VPP. DPDK Mellanox support
is not compiled by default in VPP, but you can enable it by adding
DPDK_MLX[4|5]_PMD=y in your env w
Hi Filip,
thanks for your kindly response. very glad to hear that vpp team still
maintained snat plugin. I will do my best to provide patch to the bug I found,
but not sure my fix is really valid, very appreciate to receive some advise or
response from vpp expert like u.
Thanks again.
-=-=-=-=
Hi,
Yes snat plugin is still maintained but it is undergoing big refactor and
separation of features. Some of them already happend some will be done just in
a few days. If you still encounter the issue reported here in the community
feel free to provide a patch and put me on review though i hav
+1
--
Thanks & Regards,
Murthy
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#17573): https://lists.fd.io/g/vpp-dev/message/17573
Mute This Topic: https://lists.fd.io/mt/77123394/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lis
Hi Joshua,
We'd need the whole dmesg. It looks like vfio-pci either failed to load or is
not usable (probably an IOMMU issue) but it might be something else.
Alternatively, you can try to disable vfio IOMMU support and bind to vfio again:
~# echo 1 | sudo tee /sys/module/vfio/parameters/enable_un
Thanks a lot. I will use gerrit instead.
/Dimitris
From: "Luke, Chris"
Date: Monday, 28. September 2020 at 19:50
To: Dimitrios Markou , "vpp-dev@lists.fd.io"
Subject: RE: Can I submit commit to vpp GitHub repo instead of gerrit?
Like Damjan said, we use Gerrit. Those GitHub PR’s won’t be revi
31 matches
Mail list logo
