Re: [vpp-dev] PPPOE

> On Jun 16, 2017, at 3:29 PM, Vincent Jardin wrote: > > FYI, 6WIND provides a full PPP stack (L2TP, PPPoE) server and clients. It > tooks years to develop it and unfortunately it has dependencies that prevent > using it with VPP. But it works fine with DPDK. It is available both under > so

Re: [vpp-dev] VPP S-NAT rename

there is also some impact in jira https://jira.fd.io/browse/VPP-441 https://jira.fd.io/browse/VPP-707 I don't think I have access to that level, or I'd attempt to fix it. Jim On Wed, Aug 23, 2017 at 9:02 AM, Matus Fabian -X (matfabia - PANTHEON TECHNOLOGIES at Cisco) wrote: > Hi, > > > > I’ve

Re: [vpp-dev] how to use vpp api by c language ?

> On Sep 23, 2017, at 12:19 PM, 重新开始 <15803846...@qq.com> wrote: > > Hi, everyone, >I want to call the vpp apis using c language. Who know how to use? Is > there one sample which i reference? Thank you very much! https://wiki.fd.io/view/VPP/How_To_Use_The_C_API

Re: [vpp-dev] Packet data and vlib_buffer contiguity

Francois, We did a bit of throughput testing with VPP back in April. The machines used are detailed in a someone infamous 1 April blog post. https://www.netgate.com/blog/building-a-behemoth-router.html Basically a pair of boxes with i7-6950X, some water cooling, and Intel XL710 cards (we als

Re: [vpp-dev] Packet data and vlib_buffer contiguity

DoS > attacks have pushed the limits a little bit. So, in my view, 64 line rate is > necessary for security "boxes" and for building DDoS resilient Cloud/NFV > infrastructures. Applications in VMs may end up offloading TCP to the host > VPP to just absorb DDoS and

Re: [vpp-dev] Discussion Topic: creating demo branches in git.fd.io/vpp

+2, (3 w/jdl) though be prepared to see questions about when the repo will be updated for the rest of time. (GitHub can be a kind of roach motel for code.) Cherry-picking is OK, when it’s a 1-2x thing, but when you start carrying diverging branches, the occurrence of “oops, forgot that one” sta

Re: [vpp-dev] user mode TCP stack..

> On Dec 20, 2017, at 10:21 PM, Shiv Dev wrote: > > Hi VPP Team, > > Is there a user mode TCP stack available as part of VPP ? https://gerrit.fd.io/r/gitweb?p=tldk.git;a=summary “The TLDK (Transport Layer Development Kit) project will implement a set of libraries for L4 protocol processin

Re: [vpp-dev] bond

src/vnet/ethernet/ptp_ethernet* https://github.com/FDio/vpp/commit/15ac81c16fba83033090299413a3a2dbb848a0f9 > On Jan 3, 2018, at 2:57 AM, lin huang wrote: > > Hi yugang, > It seems that vpp doesn’t support that features. > > Refer to: https://wiki.fd.io/view/VPP/Features > > From:

Re: [vpp-dev] bond

> On Jan 3, 2018, at 3:40 AM, Ole Troan wrote: > > Ewan is asking for 802.3ad presumably? Possibly. Likely even. ___ vpp-dev mailing list vpp-dev@lists.fd.io https://lists.fd.io/mailman/listinfo/vpp-dev

Re: [vpp-dev] VPP on EC2

Both C5 and M5 instances are based on the Nitro (KVM) Hypervisor and use Elastic Network Adapters (ENA) and NVMe interfaces for EBS connectivity. > On Feb 13, 2018, at 1:37 AM, Jerome Tollet wrote: > > Hi Daniel, > What Linux distribution are you running? Couple of month ago, I ran Ubuntu > 16

Re: [vpp-dev] VPP client: test_client vs VAT

> On Apr 8, 2018, at 7:00 PM, Gudimetla, Leela Sankar > wrote: > > Why does the VPP not provide a client library to access the APIs instead of > writing code to call each API ? > src/vpp-api/vom/ is a C++ wrapper. -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this grou

Re: [**EXTERNAL**] Re: [vpp-dev] VPP client: test_client vs VAT

client library available, then it would be much easy to > call the direct feature API and get going with this API stuff. > > Could you please throw some light on this? > > Thanks, > Leela sankar > > On 4/8/18, 5:39 PM, "vpp-dev@lists.fd.io on behalf of Jim Thompson&

Re: [vpp-dev] Maintainer router plugin

> On Apr 11, 2018, at 12:19 PM, Ole Troan wrote: > > VPP API used to program routes. learn interface events, addresses etc. Pure > user-land no involvement from kernel. > We’re also not “fans” of the router plugin. (And we’ve done a lot of work on it.) We have a system (today) that uses t

Re: [vpp-dev] [csit-dev] VPP with DPDK Cryptodev CSIT IPsec tests

There is a pending patch to use ISA-L rather than the Intel IPsec MB lib. Just FYI. On Thu, Jan 5, 2017 at 7:14 AM, Maciek Konstantynowicz (mkonstan) wrote: > Sergio, thx for following up. Are VPP packages with Cryptodev built today as > part of any of the vpp verify jobs? Cause they should be,

Re: [vpp-dev] Minnowboard Turbot dual-e

Deliveries in March. We had one running VPP at the DPDK Summit in August. https://twitter.com/NetgateUSA/status/776928173804052480 On Thu, Jan 26, 2017 at 3:13 AM, Damjan Marion (damarion) wrote: > > With regards to home gateway discussion on the last call here is > dual GigE version of Minno

Re: [vpp-dev] Out of Tree Build Failure on vnet/rewrite.h

Either that, or Cisco moves to builds apps the same way. You guys & gals break the tree for us about twice per month lately. > On Mar 31, 2017, at 2:29 AM, Neale Ranns (nranns) wrote: > > > Ed, > > Is that something we can add to the verify jobs? > > /neale > > From: Jon Loeliger > D

Re: [vpp-dev] syslog in snat

> On May 13, 2017, at 11:58 PM, Andrew Taylor > wrote: > > Hi, > > Could you please explain what is "Syslog based SNAT login" in Release Plan > 17.07 Added here, so you could ask https://wiki.fd.io/index.php?title=Projects%2Fvpp%2FRelease_Plans%2FRelease_Plan_17.07&d

Re: [vpp-dev] Is VPP IPSec implementation thread safe?

All, I don't know if any of the previously-raised issues occur in real-life. Goodness knows we've run billions of IPsec packets in the test harnesses (harnessi?) here without seeing them. There are a couple issues with IPsec and multicore that haven't been raised, however, so I'm gonna hijack the

Re: [vpp-dev] Is VPP IPSec implementation thread safe?

> On Jul 1, 2018, at 11:05 PM, Vamsi Krishna wrote: > > How is the performance of this code in terms of throughput, are there any > benchmarks that can be referred to? Four host setup (2 hosts for tunnel endpoints, 2 hosts outside tunnel as source & sink) Source / sink Xeon E3-1275 v3 w/40G

Re: [vpp-dev] DPDK and VPP Relationship

> On Jul 11, 2018, at 6:38 AM, Dave Barach via Lists.Fd.Io > wrote: > > In short, the kernel is simply not involved in packet processing. > ... unless you’re running netmap, and even then, you don’t take the described ctx switch hit or “copy” hit. The kernel does run the driver(s) in netma

Re: [vpp-dev] FD.io VPP Docs (L2)

Ray, VPP definitely needs support for EtherType 0x0842. :-) Slightly more seriously, a MVRP implementation would be nice. If 802.1d is important, 802.1w/s might eventually be important, but STP is gross. Being able to do fun things with 802.1p (breaking out the PCP field) could be useful.

Re: [vpp-dev] Tx packet drops - dpdk tx failure

We’ve seen 4.6Gbps IPsec on a single core of a C5 instance, and that’s throttled by the 5gbps in and out of the VPC “limit” courtesy of Amazon. (The other 400Mbps is framing overhead.) But here, obviously, “large packets” (we were using iperf3 on the tunnel). Jim > On Oct 5, 2018, at 6:38 AM,

Re: [vpp-dev] Basic forwarding setup

https://wiki.fd.io/view/VPP/Command-line_Interface_(CLI)_Guide#set_interface vpp# set interface l2 bridge TenGigabitEthernet0/8/0 100 vpp# set interface l2 bridge TenGigabitEthernet0/9/0 100 vpp# set interface state TenGigabitEthernet0/8/0 up vpp# set interface state TenGigabitEthernet0/9/0 up vpp

Re: [vpp-dev] auto-abandon

It would seem to make it difficult to find a half-implemented feature. “Has anyone tried this before?” Case in-point: L3SPAN (#9336), which seems abandoned, but is of interest. Jim > On Oct 26, 2018, at 3:01 PM, Damjan Marion via Lists.Fd.Io > wrote: > > > Folks, > > Gerrit have this nic

Re: [vpp-dev] Build failing on Fedora

> On Nov 26, 2018, at 12:05 PM, Burt Silverman wrote: > > Hi Ed, > > Thank you for looking at my change, and I apologize for some laziness -- I > should have made it more clear that I was only doing part of the job -- not > adding the needed ifeq's so that this Fedora stuff would be isolated

Re: [vpp-dev] Build failing on Fedora

yum install epel-release > > > > > > On 11/26/2018 01:57 PM, Jim Thompson wrote: >> >> >>> On Nov 26, 2018, at 12:05 PM, Burt Silverman >> <mailto:bur...@gmail.com>> wrote: >>> >>> Hi Ed, >>> >>> Thank you for look

Re: [vpp-dev] Alphabetic PCI Major address

> On Dec 16, 2018, at 3:52 PM, sheckman wrote: > > Awesome! I wish that was there from day 1. Now I'm not so embarrased I > asked...;) > > What release did it make it into? It’s only three weeks old, so it will be in 19.01. https://gerrit.fd.io/r/#/c/16219/

Re: [vpp-dev] Any upcoming fd.io VPP events

The videos from the Pre-launch, the subsequent “/dev/boot” events in San Jose and Paris are available online. Why not work through those? Pre-launch https://youtube.com/playlist?list=PLWHpG2-3ZXXsomIWyDG1L72eLXay0Z1Yu /dev/boot - San Jose, CA https://youtube.com/playlist?list=PLWHpG2-3ZXXteDBr

Re: [vpp-dev] Sequence Number Checking in TCP Protocol

Florian, Maybe he wants RFC 6528. Jim > On Dec 29, 2018, at 10:59 AM, Florin Coras wrote: > > Hi Brayan, > > I’m not entirely sure I understand your question. Obviously, we have sequence > validation in tcp as per rfc 793. For details, see tcp_segment_validate in > tcp_input.c. As part

Re: [vpp-dev] Sequence Number Checking in TCP Protocol

+ F (localip, localport, remoteip, remoteport, secretkey) is present. (Where M is the current value of that 4 usec timer, F is MD5, and secretkey is some value we pick up or generate during VPP startup.) Jim > > Florin > >> On Dec 29, 2018, at 12:42 PM, Jim Thompson wrote: >

Re: [vpp-dev] Sequence Number Checking in TCP Protocol

>> wrote: >>> >>> >>> >>> On Dec 29, 2018, at 8:26 PM, Jim Thompson wrote: >>> >>> >>> >>>> On Dec 29, 2018, at 6:42 PM, Florin Coras wrote: >>>> >>>> Hi Jim, >>>> >&

Re: [vpp-dev] wwan0 intarface - vpp

There is a DPDK driver for Atheros 10K NICs (the QCA986x/988x is Ath 10k). https://github.com/telematik-tu-ilmenau/DPDK-WiFi (specifically /drivers/net/ath10k, written for DPDK 17.10) I don’t know anything about the quality or performance o

Re: [vpp-dev] VPP 19.01 release is out!

Thank you Andrew and all the VPP & CSIT contributors & community for another great release! Jim > On Jan 31, 2019, at 3:05 PM, Andrew Yourtchenko wrote: > > Hi all, > > I am happy to announce that 19.01 release is now available. > > Release artificats can be found on both Nexus and Packagec

Re: [vpp-dev] Question about GRE tunelling inside Microsoft Azure

GRE doesn’t work inside Azure, as they use it for their internal transport. “Multicast, broadcast, IP-in-IP encapsulated packets, and Generic Routing Encapsulation (GRE) packets are blocked within VNets.” https://docs.microsoft.com/en-us/azure/virtual-network/virtual-networks-faq Jim > On Feb

Re: [vpp-dev] vmxnet3 devices

> On Mar 7, 2019, at 11:52 AM, Damjan Marion via Lists.Fd.Io > wrote: > > > >> On 7 Mar 2019, at 18:33, Matthew Smith wrote: >> >> >> Hi all, >> >> At startup, the DPDK plugin attempts to take over most PCI network devices >> which are supported by a PMD and are not in use by the kernel

Re: [vpp-dev] RFC: IPSec Tunnel remodel

> On May 21, 2019, at 9:43 AM, Neale Ranns via Lists.Fd.Io > wrote: > > In the initial patch I removed the ipsec-gre code, for two reasons: > 1) I know no-one is using it, since it didn't work until a few weeks ago Given the presence of routed IPsec in VPP, there wasn’t a use-case for ipsec-

Re: f64 vs u64 time values [Re: [vpp-dev] Regarding vlib_time_now]

> On May 28, 2019, at 10:19 AM, Christian Hopps wrote: > > Paced tunnel packets on high speed links. So timing considerations -- a 10GHz > link can send a 1514 MTU (1548B) Ethernet frame every ~1230ns, a 40GHz link > every ~308ns, and a 100GHz link every ~123ns. Probably can't get all the way

Re: [vpp-dev] Transparent proxy app

Heh, I was about to look at this for a “captive portal” like app. (There is a silent ‘r’ in captive, but providers seem to love them.) > On Jun 14, 2019, at 9:39 AM, Florin Coras wrote: > > Hi, > > By default the stack only accepts “for-us” packets, i.e., packets that have > as destinatio

Re: [vpp-dev] VPP Router Plugin or alternatives

> On Jul 1, 2019, at 4:44 AM, Steuer Heribert wrote: > > Hello, > > I am trying to understand what the current status of the router plugin in > vppsb is. It seems not to compile with any recent version of VPP. > There is not much value in a data plane implementation without a proper > contr

[vpp-dev] Trouble with checkstyle?

So I’ve got this tiny patch to add a couple QAT PCIe IDs: But when I run checkstyle.sh, it moans, and wants me to run indent twice. Here’s the thing, the only thing that’s changed by the indent is the ELOG statements. The little piece I tried to add is unchanged, but checkstyle.sh passes without

Re: [vpp-dev] Ownership of src/vnet/cop/

https://github.com/FDio/vpp/blob/master/src/vnet/cop/cop.api#L33 I think it’s more metaphor than acronym. > On Aug 26, 2019, at 5:52 AM, Ray Kinsella wrote: > > Better yet - does anyone know what COP is an abbreviation of? > > Ray K > >> On 26/08/2019 09:06, Ole Troan wrote: >> If not, I wi

Re: [vpp-dev] efficient use of DPDK

> On Dec 3, 2019, at 12:56 PM, Ole Troan wrote: > > If you don't want that, wouldn't you just build something with a Trident 4? > ;-) Or Tofino, if you want to go that direction. Even then, the amount of packet-processing (especially the edge/exception conditions) can overwhelm a hardware-b

Re: [vpp-dev] arm hardware recommendation

https://shop.solid-run.com/product/SRM8040S00D16GE008S00CH/ > On Dec 22, 2019, at 2:50 PM, Paul Vinciguerra > wrote: > >  > Hi Damian, > > I looked at the lspci on the arm tests in the CI, and saw that we are running > against thunderX/thunderX2. > I requested a quote for a thunderX2 worksta

Re: [vpp-dev] MAINTAINER for extras/rpm?

We currently use CentOS. If that means we have to maintain this, so be it. Jim > On Dec 14, 2020, at 6:42 PM, Paul Vinciguerra > wrote: > >  > Hi Damjen, > > Thanks for approving my change. > > Hi Dave, > > That was what I wanted to understand. I think some folks here may use rpm's.

Re: [vpp-dev] Lunching eBPF on VPP

Much ado about very little in this thread. The subject of running eBPF in VPP goes back to at least May 2016. I don't know of any current plans to support running eBPF or P4 in VPP. There was a short-lived project to run eBPF VPP as a trace engine: https://gerrit.fd.io/r/q/ebpf and a different

Re: [vpp-dev] Lunching eBPF on VPP

On Mon, Mar 15, 2021 at 3:33 PM wrote: > Further, how many emails has vpp-dev seen regarding incorrect use of VPP > or its APIs? A compiler avoids such issues. When the VPP gtpu plugin > changed from 2 to 4 packets used in node_inline, at least one bug was > caused due to a cut-and-paste error

Re: [vpp-dev] Rejecting large frequency change

Discontinuous time jumps are bad, mkay? NTP doesn’t want to jump the clock, but will if you tell it to, or rather, if you allow it to, and it finds itself in a situation where that might be better than the alternative. NTP *wants* to adjust your clock very, very gradually. This is called “sle

Re: [vpp-dev] Advertising prefixes in VPP fib via BGP

> On Sep 20, 2021, at 5:07 PM, Pim van Pelt wrote: > > Matt: this is one of those places where having, in general, a sync from VPP > -> Linux would be useful. I think this is somewhat inadvisable. To quote someone else on-list, “VPP is not your control plane”. Jim -=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] CPU usage for vpp

the other thing to note is that not all NIC drivers support setting interrupt and/or adaptive mode. You should also ensure that you have I2e502306e27bd98f8037d1a0a396201e099b50b5 On Wed, Jul 20, 2022 at 2:06 PM Pim van Pelt wrote: > > Hoi Xiaodong, > > One thing to note, is that the interface mu