Re: [vpp-dev] VPP/How To Build The Sample Plugin

consigned the patch to > /dev/null. > > Ray K > > On 31/05/2017 17:31, Damjan Marion (damarion) wrote: >>> >>> On 31 May 2017, at 18:18, Kinsella, Ray wrote: >>> >>> >>> Ok - but that doesn't get us any closer to helping newbies use

Re: [vpp-dev] VPP/How To Build The Sample Plugin

Something like: https://gerrit.fd.io/r/#/c/6962/ > On 31 May 2017, at 18:50, Damjan Marion (damarion) wrote: > > What about: > > export VPP_WITH_SAMPLE_PLUGIN=yes > make build > make run > > Does this work for you? > >> On 31 May 2017, at 18:45, Kins

Re: [vpp-dev] [FD.io Helpdesk #41302] Missing jvpp 1704 artifacts in fd.io.snapshot repository

Personally I think that jar filenames should not contain dot releases are bugfix-only releases as they should be drop-in replacements. If you still want to go that way, please use version script. On 6 Jun 2017, at 18:09, Marek Gradzki -X (mgradzki - PANTHEON TECHNOLOGIES at Cisco) mailto:mgra

Re: [vpp-dev] Dreaded MLX5

> On 7 Jun 2017, at 17:18, Bernier, Daniel wrote: > > Hi, > > Maybe someone has seen this before. Trying to compile stable branch on in > order to support ConnectX-5 interfaces. > > - Installed MLNX_OFED on the host > - Created a container with all the required packages t

[vpp-dev] vppctl v2 RFC

I just submitted latest revision of new vppctl implementation. https://gerrit.fd.io/r/7230 I would like to hear feedback. It can be simply tested with: make build make run and in other window (without sudo): build-root/install-vpp_debug-native/vpp/bin/vppctl Additional startup conf is: unix

Re: [vpp-dev] Performance of VPP bridge with Mellanox 40G NIC

Hi Vladimir, > On 21 Jun 2017, at 15:41, Vladimir Torgovitsky > wrote: > > Hi, > I'm testing performance of different NICs and have an issue with Mellanox 40G > ConnectX-4 device, where VPP performance seem to be similar to Linux and > doesn't improve. > I am testing throughput of UDP traffic

Re: [vpp-dev] debug own plugin

> On 29 Jun 2017, at 11:25, Tobias Sundqvist wrote: > > Hi I am devloping a crypto node using vpp (version 17.02) on Ubuntu. I first > setup the nodes that I am going to use and it works fine just forwarding the > packets as it should. > But now I have implemented some crypto functions inside

Re: [vpp-dev] fatal error: rte_config.h: No such file or directory

> On 28 Jun 2017, at 11:00, Samuel S wrote: > > i need to include dpdk.h from plugins/dpdk/device/ > but when i include this header compiler give this error: > fatal error: rte_config.h: No such file or directory > #include > > who can i fix this probleam? Can you provide whole build sequen

Re: [vpp-dev] DPDK PMD

> On 27 Jun 2017, at 20:07, Burt Silverman wrote: > > I came across the idea of running DPDK in non poll mode for low power/albeit > lower performance, but I don't remember where. I am just wondering if anyone > in VPP has done that, and if you have an easy way to configure that when > runnin

Re: [vpp-dev] 50GE interface support on VPP

Hi Daniel, Can you try with this patch? https://gerrit.fd.io/r/#/c/7418/ Regards, Damjan On 4 Jul 2017, at 22:14, Bernier, Daniel mailto:daniel.bern...@bell.ca>> wrote: Hi, I have ConnectX-4 50GE interfaces running on VPP and for some reason, they appear as “Unknown” even when running as 4

Re: [vpp-dev] [discuss] Question about VPP support for ARM 64

GCC is able to compile ARM64 code with 256-bit vectors even if target platform have only 128-bit registers. I.e. for the u8x32 version of that function it generates: ARM64: dpdk_buffer_init_from_template(void*, void*, void*, void*, void*): ld1 {v0.16b - v1.16b}, [x4], 32 st1

Re: [vpp-dev] [discuss] Question about VPP support for ARM 64

: Dave Barach (dbarach) [mailto:dbar...@cisco.com] > Sent: Saturday, August 19, 2017 7:42 AM > To: George Zhao > Cc: vpp-dev@lists.fd.io; disc...@lists.fd.io; csit-...@lists.fd.io; Damjan > Marion (damarion) > Subject: RE: [discuss] Question about VPP support for ARM 6

Re: [vpp-dev] [discuss] Question about VPP support for ARM 64

uname -a output: $>> uname -a Linux OD1K 4.4.0-92-generic #115-Ubuntu SMP Thu Aug 10 09:10:33 UTC 2017 aarch64 aarch64 aarch64 GNU/Linux thanks George 发件人：Damjan Marion (damarion) 收件人：George Zhao 抄送：dbarach,discuss,csit-dev,vpp-dev 时间：2017-08-20 10:03:27 主题:Re: [vpp-dev] [discuss] Questi

Re: [vpp-dev] [discuss] Question about VPP support for ARM 64

t. Last time I was looking there was no way to find it out from sysfs but maybe new kernels expose that info. Regards, Brian On 08/22 17:55:20, George Zhao wrote: Thanks Demjan, Confirmed that your patches worked on our system as well. George From: Damjan Marion (damarion) [mailto:damar..

Re: [vpp-dev] Please review patch 8117

Tom, let me know when they are verified and I will merge them…. Thanks, Damjan On 25 Aug 2017, at 18:16, Thomas F Herbert mailto:therb...@redhat.com>> wrote: Ignore previous message for now. I have to re-base the patch. On 08/25/2017 11:53 AM, Thomas F Herbert wrote: All, Could someone ple

Re: [vpp-dev] Duplicate Prefetching of 128 bytes memory.

> On 27 Aug 2017, at 12:04, mrityunjay.kum...@wipro.com wrote: > > Dear Team > I would like bring it to your kind notice of below code of vpp-1707-dpdk > plunging. > > static_always_inline void dpdk_prefetch_buffer_by_index (vlib_main_t * vm, > u32 bi) > { > vlib_buffer_t *b; > struct rte

Re: [vpp-dev] using wget instead of curl in the DPDK Makefile

On 30 Aug 2017, at 09:54, Shachar Beiser mailto:shacha...@mellanox.com>> wrote: Hi , Hi, I would like to use wget in the dpdk/Makefile since curl options are limited. Can I assume that the wget is installed ? Is that OK with the community ? -Shachar Beiser. Will b

Re: [vpp-dev] About the order of  VLIB_INIT_FUNCTION called between different plugins

Yes, also please note that you can at any time use vlib_get_plugin_symbol(..) function to get pointer to symbol in another plugin. If you get NULL then another plugin is not loaded. So something like this should work, assuming that you want to go that way... static clib_error_t * bar_init (vlib

Re: [vpp-dev] Dynamically change number of cores used by VPP?

On 30 Aug 2017, at 13:59, Tobias Sundqvist mailto:tobias.sundqv...@tieto.com>> wrote: Hi I guess the silence tells that there are no way of dynamically scale the number of cores used by VPP when VPP already has started. If anyone has any idea if it is dynamically possible to change the way the

Re: [vpp-dev] Не удаётся просматреть код

Если вы отправляете электронную почту на английском, кто-то может помочь вам …. > On 1 Sep 2017, at 15:11, Алексей Болдырев > wrote: > > При попытке открыть: https://gerrit.fd.io/r/ > Пишет Working... > Потом: > Code Review - Error > Server Unavailable > 504 Gateway Time-out > > В чём причин

Re: [vpp-dev] query on hugepages usage in VPP

why do you need so much memory? Currently, for default number of buffers (16K per socket) VPP needs around 40MB of hugepage memory so allocating 1G will be huge waste of memory…. Thanks, Damjan On 5 Sep 2017, at 11:15, Balaji Kn mailto:balaji.s...@gmail.com>> wrote: Hello, Can you help me o

Re: [vpp-dev] query on hugepages usage in VPP

:10 PM, Damjan Marion (damarion) mailto:damar...@cisco.com>> wrote: why do you need so much memory? Currently, for default number of buffers (16K per socket) VPP needs around 40MB of hugepage memory so allocating 1G will be huge waste of memory…. Thanks, Damjan On 5 Sep 2017, at 11:1

Re: [vpp-dev] Hugepage/Memory Allocation Rework

HI Billy, On 6 Sep 2017, at 16:55, Billy McFall mailto:bmcf...@redhat.com>> wrote: Damjan, On the VPP call yesterday, you described the patch you are working on to rework how VPP allocates and uses hugepages. Per request from Jerome Tollet, I wrote VPP-958 t

Re: [vpp-dev] query on hugepages usage in VPP

huge pages. In that case can I increase heap memory with startup configuration "heapsize" parameter? Regards, Balaji On Wed, Sep 6, 2017 at 8:27 PM, Damjan Marion (damarion) mailto:damar...@cisco.com>> wrote: On 6 Sep 2017, at 16:49, Balaji Kn mailto:balaji.s...@gmail.com>&

[vpp-dev] physmem rework patch

Dear vpp-devers, As I mentioned on the last community call, there is patch which significantly changes the way how VPP is allocating wired memory, including the dpdk hugepages. Patch is available here and it is passing verify jobs: https://gerrit.fd.io/r/#/c/7701/ With this change, VPP is ab

Re: [vpp-dev] physmem rework patch

ult of 1024, my system should stay at 8192 (provided there is enough free hugepages), correct? Yes, VPP will pre-alloc more only if there is no free pages…. Thanks, Billy On Thu, Sep 7, 2017 at 6:30 AM, Damjan Marion (damarion) mailto:damar...@cisco.com>> wrote: Dear vpp-devers, As I

Re: [vpp-dev] VPP contribute

On 11 Sep 2017, at 13:47, Shachar Beiser mailto:shacha...@mellanox.com>> wrote: Hi , I contribute to the VPP for the first time. I am following the instructions in your web-site : https://wiki.fd.io/view/VPP/Pulling,_Building,_Running,_Hacking_and_Pushing_VPP_Code#Setting_up_Gerr

Re: [vpp-dev] net/mlx5: install libmlx5 & libibverbs if no OFED

I need to take a a deeper look into it. I’m currently on business travel so It will take a bit more time. If I get it right this still uses dynamically linked libraries so we cannot enable mlx4/5 PMDs as default. Is that correct? Thanks., Damjan On 19 Sep 2017, at 06:29, Shachar Beiser ma

Re: [vpp-dev] net/mlx5: install libmlx5 & libibverbs if no OFED

with IPSec MB libs... On 19 Sep 2017, at 09:12, Shachar Beiser mailto:shacha...@mellanox.com>> wrote: Hi Damjan, Can you please explain why dynamic linkage preventing to enable “mlx4/5 PMDs as default” ? -Shachar Beiser. From: Damjan Marion (damarion) [mailto:damar...@cis

Re: [vpp-dev] Poor L3/L4 Performance

Dear Alessio, It is hard to guess where is the problem out of your description, but I would not be surprised that your implementation of those graph nodes is not properly performance tuned. One missing prefetch can hurt performance really badly. If you are able to share your code I can take a q

Re: [vpp-dev] vpp_configure_args_vpp = --disable-japi compilation issue

On 3 Oct 2017, at 11:47, Avinash Dhar Dubey mailto:mailbox.avin...@gmail.com>> wrote: Hello, I am trying to compile vpp with flag vpp_configure_args_vpp = --disable-japi by modifying the file datapath/vpp/build-data/platforms/vpp.mk. Its resulting in broken deb packages. A

Re: [vpp-dev] 50GE interface support on VPP

tch in following mail is part of v17.10 release. Attached logs. Thanks, Nitin From: vpp-dev-boun...@lists.fd.io<mailto:vpp-dev-boun...@lists.fd.io> mailto:vpp-dev-boun...@lists.fd.io>> on behalf of Damjan Marion (damarion) mailto:damar...@cisco.com

[vpp-dev] MACCHIATObin and VPP

If people are interested, there is ongoing work[1] to bring VPP up on Marvell MACCHIATObin[2] board. Interesting ARM64 community board with SFP+ ports. [1] https://github.com/MarvellEmbeddedProcessors/vpp-marvell [2] http://macchiatobin.net — Damjan

Re: [vpp-dev] 50GE interface support on VPP

VPP on aarch64. Thanks, Nitin From: Damjan Marion (damarion) mailto:damar...@cisco.com>> Sent: Wednesday, November 1, 2017 3:09 PM To: Saxena, Nitin Cc: Bernier, Daniel; vpp-dev@lists.fd.io<mailto:vpp-dev@lists.fd.io> Subject: Re: [vpp-dev] 50GE interf

Re: [vpp-dev] 50GE interface support on VPP

b_max = 65535, nb_min = 0, nb_align = 1, nb_seg_max = 0, nb_mtu_seg_max = 0}, tx_desc_lim = {nb_max = 65535, nb_min = 0, nb_align = 1, nb_seg_max = 0, nb_mtu_seg_max = 0}, speed_capa = 0, nb_rx_queues = 0, nb_tx_queues = 0} Thanks, Nitin From: Damjan Marion (d

Re: [vpp-dev] 50GE interface support on VPP

m able to receive packets via this NIC to VPP from outside world? Any concern here? -Nitin From: Damjan Marion (damarion) mailto:damar...@cisco.com>> Sent: Wednesday, November 1, 2017 5:39:24 PM To: Saxena, Nitin Cc: Bernier, Daniel; vpp-dev@lists.fd.io<

[vpp-dev] DPDK 17.11

DPDK 17.11 support is merged this morning but it is still not default. Before making it default, will be good if people can give it a try and report issues. It is as simple as: make dpdk-install-dev DPDK_VERSION=17.11 Thanks, — Damjan ___ vpp-dev

[vpp-dev] openSUSE build fails

Folks, I'm hearing from multiple people that OpenSUSE verify job is failing (again). So generally speaking i would like to question having verify jobs for multiple distros. Is there really a value in compiling same code on different distros. Yes I know gcc version can be different, but that ca

Re: [vpp-dev] openSUSE build fails

On 15 Dec 2017, at 08:52, Marco Varlese mailto:mvarl...@suse.de>> wrote: Damjan, On Thu, 2017-12-14 at 16:04 +, Damjan Marion (damarion) wrote: Folks, I'm hearing from multiple people that OpenSUSE verify job is failing (again). I haven't heard (or read) anything over

Re: [vpp-dev] Please install missing RPMs: \npackage python34 is not installed

Have you tried to do "make instal-dep" in the top level directory? > On 15 Dec 2017, at 04:05, 重新开始 <15803846...@qq.com> wrote: > > Hi, everyone >I build vpp on centos 7.3, and had executed make install-dep. It is ok. > but when i make build vpp . it print "Please install missing RPMs: \npa

Re: [vpp-dev] Some memif API and Naming Questions

Jon, Each memif connection between master and slave is uniquely identified by AF_UNIX socket and ID pair. This is first law of memif :) On unix side AF_UNIX socket is identified by filename in the filesystem but that is too long so in VPP each AF_UNIX socket have assigned file_id and that index

Re: [vpp-dev] Some memif API and Naming Questions

> > On other side it is perfectly fine to have one slave connected to 2 different > masters where both connections have same interface ID. That's why > interface name is constructed out of 2 numbers. Having only interface_id > in interface name will simply not work in this case. > > This I need

Re: [vpp-dev] Some memif API and Naming Questions

On 14 Jan 2018, at 19:51, Jon Loeliger mailto:j...@netgate.com>> wrote: On Sun, Jan 14, 2018 at 12:10 PM, Damjan Marion (damarion) mailto:damar...@cisco.com>> wrote: master 1: create memif id 33 master socket /tmp/memif1.sock Interface name: memif-0/33 Here! You know that

Re: [vpp-dev] Some memif API and Naming Questions

! Let me review, and see if I understand (better) what you are saying and proposing. You said: On Sun, Jan 14, 2018 at 12:10 PM, Damjan Marion (damarion) mailto:damar...@cisco.com>> wrote: If "create memif socket file id [master|slave|" works for you i would suggest that we

Re: [vpp-dev] Port mirroring support in vpp

Have you tried with SPAN? On 17 Jan 2018, at 10:07, Juraj Linkeš mailto:juraj.lin...@pantheon.tech>> wrote: Hi VPP devs, I’m trying to figure out whether it’s possible to set up port mirroring on a vhost-user port in VPP. The case I’m trying to make work is simple: I have traffic between two

Re: [vpp-dev] Error when trying to add interface to vpp on ARM server.

On 31 Jan 2018, at 10:34, adarsh m via vpp-dev mailto:vpp-dev@lists.fd.io>> wrote: Hi, Pls check i am trying to bring up vpp with interface on ARM server but facing issue while doing so, pls let me know if there is any existing issue or method to correct this issue. ubuntu@vasily:~$ sudo se

Re: [vpp-dev] Error when trying to add interface to vpp on ARM server.

HugePages_Free: 5120 ubuntu@vasily:~$ On Wednesday 31 January 2018, 9:30:19 PM IST, Damjan Marion (damarion) mailto:damar...@cisco.com>> wrote: On 31 Jan 2018, at 10:34, adarsh m via vpp-dev mailto:vpp-dev@lists.fd.io>> wrote: Hi, Pls check i am trying to bring up vpp wi

Re: [vpp-dev] Error when trying to add interface to vpp on ARM server.

43454]: EAL: VFIO support initialized Feb 01 19:37:16 vasily vnet[43454]: EAL: VFIO support initialized On Thursday 1 February 2018, 4:48:35 PM IST, Damjan Marion (damarion) mailto:damar...@cisco.com>> wrote: Unfortunately log you provided is incomplete and truncated so I cannot help m

Re: [vpp-dev] Error when trying to add interface to vpp on ARM server.

s is on ARM board. and yes i have modified the specific pcie address to added in startup.conf dpdk { socket-mem 1024 dev 0002:f9:00.0 } On Thursday 1 February 2018, 5:20:59 PM IST, Damjan Marion (damarion) mailto:damar...@cisco.com>> wrote: Please keep mailing list in

Re: [vpp-dev] Does VPP support flow control (pause frame)?

> On 7 Feb 2018, at 19:12, Li, Charlie wrote: > > Hi All, > > Does VPP support flow control? > > If yes, how to turn on/off flow control? Not supported today but can be it shouldn't be too hard to add. ___ vpp-dev mailing list vpp-dev@lists.fd.io

Re: [vpp-dev] Build Errors

Hi Bill, Error output copy/pasted here or to pastebin will be a good start. Thanks, Damjan > On 13 Oct 2016, at 15:55, Billy McFall wrote: > > I am getting build errors from a newly created sandbox based off master. The > build errors are coming from a patch submitted 3 weeks ago. One of th

[vpp-dev] DO_NOT_MERGE

Folks, We just got 1st DO_NOT_MERGE patch merged in. Can we going forward stop this practice, and use “-2” or Drafts instead? Thanks, Damjan ___ vpp-dev mailing list vpp-dev@lists.fd.io https://lists.fd.io/mailman/listinfo/vpp-dev

Re: [vpp-dev] DO_NOT_MERGE

Drafts, except that Drafts are not public. We *can* switch to having gerrit make Drafts public (I'd be fine with that). Ed On Tue, Oct 18, 2016 at 10:13 AM, Damjan Marion (damarion) mailto:damar...@cisco.com>> wrote: Folks, We just got 1st DO_NOT_MERGE patch merged in. Can we goin

Re: [vpp-dev] DO_NOT_MERGE

ncy is very important for community > development. > > Thanks, > -daw- > > On 10/18/16 1:13 PM, Damjan Marion (damarion) wrote: >> Folks, >> >> We just got 1st DO_NOT_MERGE patch merged in. >> >> Can we going forwa

Re: [vpp-dev] [csit-dev] DO_NOT_MERGE

Cc: csit-...@lists.fd.io<mailto:csit-...@lists.fd.io>; Damjan Marion (damarion) mailto:damar...@cisco.com>>; vpp-dev mailto:vpp-dev@lists.fd.io>> Subject: Re: [vpp-dev] [csit-dev] DO_NOT_MERGE But if the contributor -1 it then I'm ok putting -2 on it as a lock if I'

Re: [vpp-dev] [csit-dev] DO_NOT_MERGE

>> For those patches like the csit operational testing patch that I just >> merged, I prefer -2 so everyone can see the status of tests and help out if >> possible. >> >> I agree with Ed, that transparency is very important for community >> development. >>

Re: [vpp-dev] VPP gerrit 3551 vpp-csit-verify-virl-master failure analysis

Hi Dave, Yes, i know. This time for reason. Surprisingly:) Thanks, D. On 21 Oct 2016, at 20:55, Dave Wallace mailto:dwallac...@gmail.com>> wrote: Damjan, I've been monitoring the build failures on the VPP gerrit queue and found that the most recent failure for https://gerrit.fd.io/r/#/c/35

Re: [vpp-dev] VPP project committer nomination: Neale Ranns

+1 On 26 Oct 2016, at 20:36, John Lo (loj) mailto:l...@cisco.com>> wrote: +1 -John From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On Behalf Of Florin Coras Sent: Wednesday, October 26, 2016 1:42 PM To: Dave Barach (dbarach) Cc: vpp

Re: [vpp-dev] [csit-dev] vhost multi-queue patch - verify job failing

ilto:hagb...@gmail.com>>; Maciek Konstantynowicz (mkonstan) mailto:mkons...@cisco.com>>; csit-...@lists.fd.io<mailto:csit-...@lists.fd.io>; Damjan Marion (damarion) mailto:damar...@cisco.com>>; vpp-dev mailto:vpp-dev@lists.fd.io>> Subject: Re: [csit-dev] vhost multi-qu

Re: [vpp-dev] Can we build dpdk as .so files?

If I remember correctly I tested this only with manually built DPDK. It was also working fine with .so files coming from ubuntu packages. > On 9 Nov 2016, at 17:42, Nagaprabhanjan Bellaru wrote: > > Hi, > > I want to know if we can build dpdk as .so files? I tried enabling the > CONFIG_RTE_S

Re: [vpp-dev] "shpw pci" shows Intel XL710 NICs, but DPDK reports no ports..

We never enabled bnx2 devices in VPP for very simple reason. We never had one to test it. You will need to hack a bit vnet/vnet/devices/dpdk/* to make them working. I will be happy to review and merge support if you make them working and send patch to gerrit. Thanks, Damjan On 12 Nov 2016, a

Re: [vpp-dev] omg,vlan sub-interface seems not working

Can you capture trace (trace add af-packet-input 5 / show trace) and share it here ? Thanks, Damjan On 22 Nov 2016, at 09:16, Chillance Zen mailto:chillance...@gmail.com>> wrote: hi,all when I was trying to use vlan sub-interface as a individual L3 interface (i.e. configure an IP address

Re: [vpp-dev] omg,vlan sub-interface seems not working

not local to subnet DBGvpp# show interface addr TenGigabitEthernet1/0/0 (dn): TenGigabitEthernet1/0/1 (dn): af_packet0 (up): af_packet0.100 (up): 130.140.25.1/24<http://130.140.25.1/24> af_packet1 (dn): local0 (dn): Thanks & Regards Linc On 24 November 2016 at 04:08, Damjan Mari

[vpp-dev] native vhost-user perf improvements

I know that several people are playing with VPP vhost-user implementation so just a heads-up about latest change in master which really helps with NDR performance. We are observing NDR gain of 41% in our testbeds. https://git.fd.io/vpp/commit/?id=4e969f9 Let me know if any issues, or just feed

Re: [vpp-dev] VPP Compilation Issue on Centos

Can you share “show pci” output form VPP? On 25 Nov 2016, at 13:53, Sreejith Surendran Nair mailto:sreejith.surendrann...@linaro.org>> wrote: Hi Christophe, Thanks a lot . I checked the lsmod output the pci looks loaded correctly but "dpdk driver" not able to detect it. [root@localhost dri

Re: [vpp-dev] VPP Compilation Issue on Centos

19259 1 uio_pci_generic [root@localhost vpp]# On 25 November 2016 at 18:43, Damjan Marion (damarion) mailto:damar...@cisco.com>> wrote: Can you share “show pci” output form VPP? On 25 Nov 2016, at 13:53, Sreejith Surendran Nair mailto:sreejith.surendrann...@linaro.org>> wrote: Hi

Re: [vpp-dev] VPP Compilation Issue on Centos

he complete output. [root@localhost vpp]# vppctl show pci Address Socket VID:PID Link Speed Driver Product Name :00:19.08086:1502 unknowne1000e [root@localhost vpp]# Thanks & Regards, Sreejith On 25 November 2016 at 09:00, Damjan Marion (damarion

Re: [vpp-dev] native vhost-user perf improvements

Hi Alec, Inline… On 29 Nov 2016, at 02:54, Alec Hothan (ahothan) mailto:ahot...@cisco.com>> wrote: Hi Damjan, Regarding the diffs, do you know in which error case(s) the retry will hit the most to cause such a big improvement in NDR? It is not about error case. It is about cases where there

[vpp-dev] Upcoming VPP 17.01 release freeze

Dear VPP developers and consumers, On Dec 7th we have planned code freeze for upcoming 17.01 release. That means that after that date no new features will be let into the repo and only bug fixes will be accepted (potentially we can accept smaller non-API low risk changes). Code freeze will last u

Re: [vpp-dev] MLX5 support in VPP

Hi Daniel, Activating PMD also requires having closed-source MLX libraries installed, as MLX PMD is just wrapper around them Fact that it depends on closed source libs prevents us from enabling MLX devices by default. So we will need to add configuration knob and that will require some tweaking

Re: [vpp-dev] [csit-dev] [it-infrastructure-alerts] Upstream Network Maintenance, Dec 1st and 2nd PT

Looks like IPv4 connectivity is broken after this change. I cannot reach gerrit, jira…. Luckily IPv6 connectivity works, so I had to create SOCKS tunnel to ipv6 enabled machine to access those sites. Another happy news is: verify jobs are not working again. Should we reconsider moving to gith

Re: [vpp-dev] MLX5 support in VPP

Hi Luke, Glad to see that you’re following our list :) On 1 Dec 2016, at 14:45, Luke Gorrie mailto:l...@snabb.co>> wrote: On 30 November 2016 at 21:24, Damjan Marion (damarion) mailto:damar...@cisco.com>> wrote: I was also thinking about building native driver for mlx using the

Re: [vpp-dev] [deb-dpdk] MLX5 support in VPP

Hi Luca, mlx5 DPDK driver depends on mellanox OFED library which is according to my understanding closed source. How do you deal with such cases? Thanks, Damjan On 1 Dec 2016, at 23:00, Luca Boccassi mailto:luca.bocca...@gmail.com>> wrote: Hi, We can certainly give it a shot, if it builds

[vpp-dev] VPP and DPDK

I think it is right time to start discussing post 17.01 release developments and here I would like to propose some changes related to DPDK integration. I see a need for changes in 2 areas: 1) building DPDK as part of VPP build and patch management 2) moving DPDK related code (input node, tx, buf

Re: [vpp-dev] [tsc] collectd

There are collectd plugins available with different licenses but Apache 2.0 seems not be compatible with GPL 2.0. https://collectd.org/wiki/index.php/Category:License and https://www.gnu.org/licenses/license-list.html#apache2 So this looks like we have general problem of adding binary API sup

[vpp-dev] 17.01 stable branch to be created tomorrow - Dec 21st

Dear VPP developers, Tomorrow, we are planning to create stable 17.01 branch and release RC1 artifacts. As we still have some stuff int the review, please let me know if there is anything which is intended for 17.01 and it is still not merged. Also, I would like to ask committers to ping me

Re: [vpp-dev] 17.01 stable branch to be created tomorrow - Dec 21st

stable/1701 branch is created and tagged with RC1 tag. I will soon put 17.04-rc0 tag on the master and then master is back in business…. > On 20 Dec 2016, at 15:25, Damjan Marion (damarion) wrote: > > > Dear VPP developers, > > Tomorrow, we are planning to create stabl

[vpp-dev] change in source code tree

Dear vpp-dev members, I just submitted a patch to gerrit[1] which introduces significant improvement in VPP build speed and also reduces complexity of the build system. Number of autotools instances is reduced to one, and whole code is moved under the src/ tree. That effectively means that autoc

Re: [vpp-dev] change in source code tree

ssage- >> From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On >> Behalf Of Damjan Marion (damarion) >> Sent: Tuesday, December 27, 2016 20:35 >> To: vpp-dev >> Subject: [vpp-dev] change in source code tree >> >> Dear vpp-dev mem

Re: [vpp-dev] change in source code tree

nced in the doc. > >> -Original Message- >> From: Damjan Marion (damarion) [mailto:damar...@cisco.com] >> Sent: Wednesday, December 28, 2016 08:51 >> To: Luke, Chris >> Cc: vpp-dev >> Subject: Re: change in source code tree >> >> >> Finally

Re: [vpp-dev] change in source code tree

Dear Burt, > On 28 Dec 2016, at 15:08, Burt Silverman wrote: > > Hi Damjan, > > This looks really sweet. Finally, good riddance to ebuild. This change is not about getting a rid of ebuild, ebuild is still there. Main goal here was to reduce number of packages and speed up build process. Autot

[vpp-dev] vcgn plugin

After recent source tree re-org, we have one orphan sitting in plugins/vcgn. It is VCGN plugin which is outdated, and functionally it is replaced with the new SNAT plugin. Unless somebody have some good reasons against, and it is willing to fix and maintain VCGN plugin going forward, I think we

[vpp-dev] Avoid constant rebuilding of dpdk during the build process

Currently we are maintaining own set of DPDK patches and building DPDK from source, this is something which will unlikely change short term. Still it is quite time consuming and annoying that we are re-building dpdk over-and-over without real need to do so. I just submitted RFC patch to gerrit[

Re: [vpp-dev] Avoid constant rebuilding of dpdk during the build process

> On 10 Jan 2017, at 11:54, Kinsella, Ray wrote: > > > Seems like a welcome, logical, incremental step towards using DPDK binary > packaging. > > Would it make sense to always first try to pull and install the binary > package from the nexus server. Yes, absolutely, we are fetching tons o

[vpp-dev] pkg-config

I think it will be nice to have pkg-config (vpp.pc) file in vpp-dev repo, so external plugin developer can use it for passing proper parameters to configure/make, same like other proper development packages do. Does anybody have few free cycles and interest to crank it up? Thanks, Damjan ___

Re: [vpp-dev] pkg-config

plugin and wish to have > this exact feature. > > Do you have some good example to start? > > Thanks, > > Patrick > > Sent from my iPhone > >> On Jan 11, 2017, at 09:49, Damjan Marion (damarion) >> wrote: >> >> >> I think it wil

Re: [vpp-dev] Avoid constant rebuilding of dpdk during the build process

ent: vpp-dpdk-dev 16.11-vpp1 Please upgrade by invoking 'make dpdk-install-dev' from the top level directory. == make: Leaving directory '/home/damarion/cisco/vpp/dpdk’ Thanks, Damjan > On 10 Jan 2017, at 12:40, Da

Re: [vpp-dev] [csit-dev] sporadically failing functional tests: L2BD and VXLANoIPv4oVLAN

Can we please disable this test temporary as tests are failing? Thanks, Damjan On 16 Jan 2017, at 17:12, Maciek Konstantynowicz (mkonstan) mailto:mkons...@cisco.com>> wrote: Hi, Got the report above are failing from time to time: https://jenkins.fd.io/job/vpp-csit-verify-virl-master/3316/ h

Re: [vpp-dev] Build on Fedora 25 failed

Hi Kevin, If autoconf was missing before I will not be surprised if libtool is also missing. Try to install it. Thanks, Damjan > On 17 Jan 2017, at 19:51, Kevin Wilson wrote: > > Thanks to Burt, Connoly and Billy. > Still, after: > dnf group install 'C Development Tools and Libraries' > an

Re: [vpp-dev] VPP-556 - vpp crashing in an openstack odl stack

I also have two other questions: •what's the difference between a regular image and an TAG=vpp_debug image? vpp_debug_TAG_CFLAGS = -g -O0 -DCLIB_DEBUG -DFORTIFY_SOURCE=2 -march=$(MARCH) \ -fstack-protector-all -fPIC -Werror vpp_debug_TAG_LDFLAGS = -g -O0 -DCLIB_DEBUG -DFORTIFY_SOURCE=2 -

Re: [vpp-dev] Plugin for mpls over gre

> On 18 Jan 2017, at 16:59, Calvin Ference wrote: > > Hey VPP community, > > I was wondering if anyone had coded a plugin to do mpls over gre before? I'm > looking at getting my hands dirty in writing a plugin and I was thinking this > might be a good start, but if someone already did the

Re: [vpp-dev] Plugin for mpls over gre

> On 18 Jan 2017, at 22:39, Ed Warnicke wrote: > > Calvin, > > We've had some consumers express interest in MPLS over UDP: > https://tools.ietf.org/html/rfc7510 > > Would you be interested in working on that? Or maybe, https://tools.ietf.org/html/rfc2549 . :) Calvin let us know if you need

[vpp-dev] VPP 17.01 Released

The VPP 17.01 release i up. Many thanks to all contributors and testers and specially Ed for helping to roll this release over the finish line. .rpm and .deb packages are uploaded to the nexus server. New features in the VPP 17.01: - Integrated November 2016 DPDK release - Complete rework of Fo

[vpp-dev] plugin infrastructure changes

As discussed on the call, let’s continue discussion on the mailer. My RFC patch is at: https://gerrit.fd.io/r/#/c/4824/ copy/paste from commit log: == This patch replaces requirement for vlib_plugin_register function in the plugin so file and introduces new macro: VLIB_PLUGIN_REGISTER () =

[vpp-dev] igb_uio -> uio_pci_generic

Is anybody aware of any valid reason why we cannot switch to uio_pci_generic as default PCI uio driver in ubuntu packages? I think generally people don’t like out-of-tree modules, so as long as we are getting the same service from uio_pci_generic we should use it… Thanks, Damjan __

Re: [vpp-dev] igb_uio -> uio_pci_generic

> On 24 Jan 2017, at 18:26, Stephen Hemminger > wrote: > > On Tue, 24 Jan 2017 17:14:42 +0000 > "Damjan Marion (damarion)" wrote: > >> Is anybody aware of any valid reason why we cannot switch to uio_pci_generic >> as default PCI uio driver in ubuntu p

Re: [vpp-dev] igb_uio -> uio_pci_generic

> On 24 Jan 2017, at 18:40, Damjan Marion (damarion) wrote: > >> >> On 24 Jan 2017, at 18:26, Stephen Hemminger >> wrote: >> >> On Tue, 24 Jan 2017 17:14:42 + >> "Damjan Marion (damarion)" wrote: >> >>> Is anybod

Re: [vpp-dev] igb_uio -> uio_pci_generic

> On 24 Jan 2017, at 18:33, Ed Warnicke wrote: > > I can tell you why we did it to begin with (which I'm hoping is no longer a > valid reason). We originally did it because ubuntu 14.04 did not have any > appropriate usable packages for uio drivers. I for one would be overjoyed to > make t

Re: [vpp-dev] igb_uio -> uio_pci_generic

> On 25 Jan 2017, at 06:00, Stephen Hemminger > wrote: > > On Tue, 24 Jan 2017 23:05:55 -0500 > Burt Silverman wrote: > >> Hi Damjan, >> >> My understanding is that CONFIG_VFIO_NOIOMMU will never be set in a stock >> kernel, and you will need to build a custom kernel for that. I understand >

Re: [vpp-dev] Error reading from file descriptor 9: Input/output error

EAL throws this message to stderr, systemd collects it. There is no much of vpp involved here. On 25 Jan 2017, at 16:00, Kinsella, Ray mailto:ray.kinse...@intel.com>> wrote: Hi Damjan, I don't get how the the following message is being blurbed to the Syslog "PCI INTX mask not supported\n"

  1   2   >