Re: [vpp-dev] A question about enable AVX512 instruction in VPP

On 17 Oct 2019, at 20:02, Zhang Yuwei mailto:yuwei1.zh...@intel.com>> wrote: Hi Dear VPP guys, I would like to do some investigation about AVX512 instruction support in VPP, I saw there are already some implementations but AVX2 is still the default option. Could anybody tell

Re: [vpp-dev] Basic l2 bridging does not work

> On 17 Oct 2019, at 09:59, Chuan Han wrote: > > It seems R740 vpp works fine. All packets coming from port 1 go to port 2. > > vpp# sh int > Name IdxState MTU (L3/IP4/IP6/MPLS) > Counter Count > eth0 2 up

Re: [vpp-dev] Basic l2 bridging does not work

> On 16 Oct 2019, at 16:14, Chuan Han via Lists.Fd.Io > wrote: > > Hi, vpp experts, > > We are trying to make basic l2 bridge works within vpp. > > We have two servers: r230 and r740, each of which has two phy nics. Two > servers are connected via cable. On each server, we bring these two

Re: [vpp-dev] VPP Interfaces from with (Docker) Containers?

BTW I strongly suggest that you don't use uio_pci_generic. Starting with kernel 4.4 vfio-pci even supports no-iommu mode for systems which lack IOMMU. uio_pci_generic is on the black list for a long time by the kernel community, MSI and MSI-X interrupt support was never added Also,

Re: [vpp-dev] sh hardware-interfaces extended stats are not showing up

to Nueno <mailto:carlitonu...@gmail.com>> wrote: > Hi David, > > I tried "vppctl interface collect detailed-stats enable" but it doesn't work. > > I will git bisect as Damjan mentioned and try to see what changed. > > Thanks > > On Wed, Aug

Re: [vpp-dev] Can vlib_time_now be used in worker threads

> On 19 Sep 2019, at 07:42, Vamsi Krishna wrote: > > Hi, > > Can the vlib_time_now api be used in worker threads? Looking at the code, > this api does not seam to be thread safe. > But there are a few places where it is used in nodes that do packet > processing. For example in nat, cdp and

Re: [vpp-dev] How to compile VPP with external(prebuilt) DPDK #vpp

You can just invoke cmake directly and it should find installed dpdk libraries. I.e. mkdir build cd build cmake -Gninja /path/to/vpp ninja You can also use standard cmake way to specify directories... — Damjan > On Sep 17, 2019, at 10:13 AM, Jaemin Park wrote: > > Hello, > > I'd like to

Re: [vpp-dev] gprof?

> On 13 Sep 2019, at 18:58, Christian Hopps wrote: > > > >> On Sep 13, 2019, at 12:41 PM, Christian Hopps wrote: >> >> Signed PGP part >> >> >>> On Sep 13, 2019, at 12:23 PM, Damjan Marion wrote: >>> >>> >>> On 13 Sep 2019, at 18:15, Christian Hopps wrote: Is it

Re: [vpp-dev] gprof?

> On 13 Sep 2019, at 18:15, Christian Hopps wrote: > > Is it possible to profile vpp with gprof? > > I google a bit but I'm not turning anything up. I have made some build > changes to compile/link with -pg (starting with the gcov target), and a > change to not handle SIGPROF. This produced

Re: [vpp-dev] Issue with DPDK 19.08 / i40e driver

00075eb7a48 in clib_calljmp () from > /home/aloaugus/vpp/build-root/install-vpp_debug-native/vpp/lib/libvppinfra.so.20.01 > #21 0x7fffb8460940 in ?? () > #22 0x764149ec in vlib_process_startup (vm=0x766b5dc0 > , p=0x259, f=0x0) at /home/aloaugus/vpp/src/vlib/main.c:14

Re: [vpp-dev] Bug in plugins/dpdk/device/init.c related to eal_init_args found using AddressSanitizer

see: https://wiki.fd.io/view/VPP/Pulling,_Building,_Running,_Hacking_and_Pushing_VPP_Code Section 6 > On 12 Sep 2019, at 11:11, Elias Rudberg wrote: > > OK, now I created a Jira issue about it: >

Re: [vpp-dev] Issue with DPDK 19.08 / i40e driver

> On 11 Sep 2019, at 16:43, Mathias Raoul wrote: > > Hello, > > I have an issue with VPP and i40e driver, when I try to switch the interface > to up, the program stop with a segmentation fault. My configuration details > are below. > > It might be a compatibility issue, because the DPDK

Re: [vpp-dev] Intel XXV710 SR-IOV packet loss

d besides why > would we receive different number of processed packets with 7 VFs and dropped > by 16 millions of packets using 8 VFs? and the same result goes with 9 or > 10 VFS as with 8 VFs.. > Od: Damjan Marion via Lists.Fd.Io <mailto:dmarion=me@lists.fd.io>> &g

Re: [vpp-dev] Intel XXV710 SR-IOV packet loss

Isn't that just a hardware limit of the card? > On 4 Sep 2019, at 12:45, Miroslav Kováč wrote: > > Yes we have tried that as well, with AVF we received simlar results as well > Od: Damjan Marion mailto:dmar...@me.com>> > Odoslané: streda, 4. septembra 2019 12:44:33 > Komu: Miroslav Kováč >

Re: [vpp-dev] Intel XXV710 SR-IOV packet loss

Have you tried to use native AVF driver instead? > On 4 Sep 2019, at 12:42, Miroslav Kováč wrote: > > Hello, > > We are trying a setup with intel 25 GB card XXV710 and sr-iov. We need sr-iov > to sort packets based on vlan in between the VFs. We are using trex on one > machine to generate

Re: [EXT] [vpp-dev] Marvell OCTEONTx2 plugin

nd OCTEONTX2. Perhaps you can look at my patches and see > whether what you are suggesting is possible with the existing plugin? > > Thanks, > > Damjan > > > On 19 Aug 2019, at 20:03, Nitin Saxena <mailto:nsax...@marvell.com>> wrote: > > Hi Damjan,

Re: [vpp-dev] OPNFV-VSPERF VPP Upgrade

> On 29 Aug 2019, at 20:48, Sridhar K. N. Rao wrote: > > Hi, > > I’m from OPNFV-VSPERF project where VPP is one of the upstream projects for > us. We are planning to upgrade VPP from > 17.07 to 19.04 and DPDK from 17.08 to 18.11. > I just wanted to check here VPP 19.04 and DPDK 18.11 are

Re: [vpp-dev] memif impacting other workers

> On 28 Aug 2019, at 21:06, Satya Murthy wrote: > > Hi, > > We are seeing one strange issue when we use memif. > > We have vpp with 2 workers. This VPP is running as memif-server. > worker-0 ==> rx-placement with memif > worker-1 ==> rx-placement with an IP interface ( dpdk based ) > > As

Re: [vpp-dev] vpp show no packet and high rx-miss

> On 28 Aug 2019, at 18:23, William Tu wrote: > > On Wed, Aug 28, 2019 at 7:58 AM Damjan Marion wrote: >> >> >> Havre you bound NIC to vfio-pci or uio_pci_generic? >> > I'm using uio_pci_generic. > Should I use vfio-pci? Yes, uio_pci_generic doesn’t work when IOMMU is enabled.

Re: [vpp-dev] sh hardware-interfaces extended stats are not showing up

It is not intentional so somebody needs to debug it… "git bisect" might be good choice here. > On 28 Aug 2019, at 13:50, Devis Reagan wrote: > > Can any one help on this ? Extended stats not shown in vpp 19.08 via ‘show > hardware-interfaces’ command > > Thanks > > On Tue, Aug 27, 2019

Re: [vpp-dev] vpp show no packet and high rx-miss

Havre you bound NIC to vfio-pci or uio_pci_generic? > On 27 Aug 2019, at 23:32, William Tu wrote: > > Hi, > > I'm new to vpp and hit an error when receiving no packet from PCI > device. My setup is below: > > /etc/vpp# cat startup.conf > unix { > nodaemon > log /var/log/vpp/vpp.log >

Re: [vpp-dev] 19.04.2 and sub-numa cluster support

> On 26 Aug 2019, at 20:00, sheckman wrote: > > We have been using vpp-18.07 and socket-mem to assign memory to the sub-numa > node where our vpp instances have been running in containers. > > socket-mem 0,1024,0,0. e.g. > > In 19.04, that has been deprecated. > > Now, we get memory on ALL

Re: [vpp-dev] How to measure performance of memif

I typically used 2 vpp instances, one doing xconnect between physical NIC and memif interface, another VPP instance routing between 2 memif interfaces. i.e. trex-port1 — (p)vpp1(m) — (m)vpp2(m) — (m)vpp1(p) — trex-port2 Where (p) is physical nic interface, and (m) is memif interface. On the

Re: [vpp-dev] VPP 19.08 release is available!

> On 21 Aug 2019, at 22:57, Andrew Yourtchenko wrote: > > So you are in release management business next 10 years, good :) -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#13805): https://lists.fd.io/g/vpp-dev/message/13805 Mute This Topic:

Re: [vpp-dev] ValueError: Fieldname 'async' is a python keyword and is not accessible via the python API

t; <https://git.fd.io/vpp/diff/src/plugins/tlsopenssl/tls_openssl.api?id=be4d1aa> > >> On Aug 21, 2019, at 7:41 AM, Damjan Marion via Lists.Fd.Io >> mailto:dmarion=me@lists.fd.io>> wrote: >> >> >> May be due to the fact that I use newer ubuntu

Re: [EXT] [vpp-dev] Marvell OCTEONTx2 plugin

it be ok to provide patches > against DPDK release (from dpdk.org <http://dpdk.org/>) OR does it need to be > hosted publicly? > > Thanks, > Nitin > From: vpp-dev@lists.fd.io <mailto:vpp-dev@lists.fd.io> <mailto:vpp-dev@lists.fd.io>> on behalf of Damjan Marion vi

Re: [vpp-dev] Marvell OCTEONTx2 plugin

Dear Nitin, Where we can find “libmarvelldpdk”? Google search doesn’t show single occurrence. We don’t support contributions linked to closed source libraries… — Damjan > On 19 Aug 2019, at 16:53, Nitin Saxena wrote: > > Hi, > > Following is the link for README.md >

Re: [vpp-dev] A method to measure the allocated memory size for IKE SA

OK, that is not exactly what you asked in your first email. If you want to find out size of struct and all child/indirect data, you will need to sum all of them manually. Most of them are vectors, so you cal use vl() helper in gdb to get length. I.e. (gdb) p sizeof (ikev2_rekey_t) *

Re: [vpp-dev] A method to measure the allocated memory size for IKE SA

> On 13 Aug 2019, at 05:01, jmpar...@gmail.com wrote: > > Hi, all > > I'd like to measure the allocated memory size for the whole structure of IKE > SA (ikev2_sa_t). > Because ikev2_sa_t has many other struct types, it is not simple for me to > measure the memory size. > > Is there any

Re: [vpp-dev] Trouble with checkstyle?

Are you using ubuntu 19.04 or some other recent distro with new version of gnu indent? After many years they released new version with lot of bug fixes. We use old version with many bugs, and our repo is full of products of those bugs like the one you pasted bellow... — Damjan > On 9 Aug

Re: [vpp-dev] FAQ or Documentation request

> On 22 Jul 2019, at 20:11, Brian Dickson wrote: > > Speaking mostly as a user, there is some really important information needed > for using VPP, which is not documented (at all, or at least anywhere that can > be found). > > I would like to make a request that someone take up this request

Re: [vpp-dev] Macros to support prefetch w/o code copy.

> On 12 Jul 2019, at 15:40, Christian Hopps wrote: > > Thanks for the review.. I have a comments and a question inline... > >> On Jul 12, 2019, at 9:11 AM, Damjan Marion wrote: >> >>> ... >> >> Hi Cristian, >> >> You are not fist one trying to do that, few of us did and we all failed :).

Re: [vpp-dev] Macros to support prefetch w/o code copy.

> > On 12 Jul 2019, at 06:14, Christian Hopps wrote: > > [re-sending w/o extra email addresses] > > Hi vpp-dev, > > So I'm writing a plugin to support IPTFS > (https://tools.ietf.org/html/draft-hopps-ipsecme-iptfs-01), and during this > process I've written a macro to support prefetching

Re: [vpp-dev] PPTP in VPP

> On 11 Jul 2019, at 15:11, Vladislav Romanov wrote: > > Hi all, > > I have a question. > If it is possible to release PPTP protocol in VPP with bandwidth 50-100 > mbit/sec? What do you mean by release? decap/encap? -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this

Re: [vpp-dev] pool_get_aligned causing crash

> On 10 Jul 2019, at 17:29, hari_akkin via Lists.Fd.Io > wrote: > > Hi Damjan, > > Below is the backtrace > 0x750124d5 in __memset_avx2_unaligned_erms () from /lib64/libc.so.6 > (gdb) bt > #0 0x750124d5 in __memset_avx2_unaligned_erms () from > /lib64/libc.so.6 > #1

Re: [vpp-dev] libmemif non packaged in deb/rpm anymore from 19.04 [regression?]

> On 9 Jul 2019, at 22:23, Luca Muscariello (lumuscar) > wrote: > > Let me try again. > > This patch was merged to get packaged libmemif in 19.01 > > https://gerrit.fd.io/r/#/c/16436/ > > It has disappeared with 19.04. > Is this still somewhere? No it

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

> On 9 Jul 2019, at 16:28, Ray Kinsella wrote: > > It is accurate to say it is bit-rotting, it not accurate to say it is > orphaned. > >> >> I believe that, but obviously nobody is interested to do so. Neither >> original authors or users of that code. > > Well that is not entirely

Re: [vpp-dev] libmemif non packaged in deb/rpm anymore from 19.04 [regression?]

> On 9 Jul 2019, at 15:36, Luca Muscariello via Lists.Fd.Io > wrote: > > > Hi, > > libmemif was made available in the binary distribution as deb/rpm in > vpp-lib and vpp-dev starting from 19.01 thanks to a patch that Mauro > submitted in Dec. > > https://gerrit.fd.io/r/#/c/16436/ > >

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

> On 9 Jul 2019, at 01:23, Brian Dickson wrote: > > > > On Mon, Jul 8, 2019 at 3:39 PM Damjan Marion wrote: > > > > On 8 Jul 2019, at 22:23, Brian Dickson > > wrote: > > > > > > > > On Thu, Jul 4, 2019 at 1:19 PM Jim Thompson via Lists.Fd.Io > > wrote: > > > > On Jul 1, 2019, at

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

> On 8 Jul 2019, at 22:23, Brian Dickson wrote: > > > > On Thu, Jul 4, 2019 at 1:19 PM Jim Thompson via Lists.Fd.Io > wrote: > > 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 >>

Re: [vpp-dev] dpdk plugin link problem

> On 4 Jul 2019, at 23:56, Jonathan Richardson via Lists.Fd.Io > wrote: > > Hello, > > I'm having trouble compiling the dpdk plugin using vpp 19.01.1 and dpdk > 18.01. I'm using > yocto with glibc 2.27. It fails to link in the glibc functions that > libdpdk uses: > >

Re: [vpp-dev] centos jobs failing

Even more cleaner one will be to add “-“ in front of sudo which tells make to ignore return code :) Btw i’m responsible for this one, that line was quick fix to address another stupidity of rpm which fails to upgrade package when real file is replaced with symbolic link — Damjan > On 2

Re: [vpp-dev] Many "tx packet drops (no available descriptors)" #vpp

> On 1 Jul 2019, at 17:14, amir...@rad.com wrote: > > Hi All, > > I'm using VPP 19.02.1 with DPDK 18.11.0. > When running traffic through VM I can see many drop packets due to "tx packet > drops (no available descriptors)" on the VirtualEthernet ports. > I've tried to change some of the DPDK

Re: [E] Re: [vpp-dev] VPP worker threads getting stuck

please try latest master or 19.04. I think i saw something similar due to dpdk bug in one of prior releases. i don't remember exact version numbers involved but it was around timeframe when v18.07 was released…. > On 1 Jul 2019, at 12:56, Inderpal Singh wrote: > > Hi, > > Thanks for the

Re: [vpp-dev] VPP worker threads getting stuck

> On 20 Jun 2019, at 09:26, via Lists.Fd.Io > wrote: > > Hi, > > I am running my vpp based plugin on i40 NIC. After running the IP traffic for > some time(5-10 mins), all the VPP threads got stuck in dpdk driver code. > Do we have any fix available for this.? If you are running latest

Re: [vpp-dev] VPP on POWER9

o get to a prompt... > > Passing traffic would take a respectable amount of work... > > D > > -Original Message- > From: vpp-dev@lists.fd.io On Behalf Of Damjan Marion > via Lists.Fd.Io > Sent: Thursday, June 27, 2019 12:14 PM > To: Dave Barach (dbarach) &g

Re: [vpp-dev] MemIf interface selection for TX traffic

> On 1 Jul 2019, at 12:40, Satya Murthy wrote: > > Hi , > > Have a question on the Memif TX interface selection. > > I have VPP with 2 worker threads connecting to an external application. > Have two memif interfaces, so that each thread can make use of one Memif > interface dedicately. > >

Re: [vpp-dev] Commit Subjects

> On 17 Jun 2019, at 23:40, Jon Loeliger via Lists.Fd.Io > wrote: > > On Mon, Jun 17, 2019 at 3:43 PM Damjan Marion > wrote: > >> On 17 Jun 2019, at 22:41, Jon Loeliger > > wrote: >> >> On Mon, Jun 17, 2019 at 3:33 PM Damjan Marion >

Re: [vpp-dev] VPP on POWER9

If i remember correctly, there was major foobar with longjump code. Our code is written for older PPC and it doesn’t work ok on Power9. Probably matter of hours to get it fixed... — Damjan > On 27 Jun 2019, at 16:41, Dave Barach via Lists.Fd.Io > wrote: > > It worked a few years ago, at

Re: [vpp-dev] NAT dose not exist in MAINTAINERS file

Dear Emma, This is exact reason why we introduced commit checks. It will help us to keep MAINTAINERS file up to date, without this check nobody will notice that nat is missing there. Ole is our nat guy, please amend your patch with MAINTAINERS update and add Ole as maintainer... — Damjan >

Re: [vpp-dev] Issue in receiving Multicast IPv6 packets with vpp 18.01 with Mellanox(ConnectX-4) NIC

> On 21 Jun 2019, at 10:43, amito...@gmail.com wrote: > > Thanks Damjan for the reply. > > Actually, i have tried with vpp19.04 as well with same Mellanox NIC, but the > problem that i am observing is that when vpp is coming up, dpdk is not able > to detect the Mellanox interfaces. I tried

Re: [vpp-dev] Issue in receiving Multicast IPv6 packets with vpp 18.01 with Mellanox(ConnectX-4) NIC

18.01 is unsupported for a long time. i suggest trying with 19.04 or latest master as a 1st step. Also trying with other nic may give some clue where problem is — Damjan > On Jun 20, 2019, at 9:09 AM, amito...@gmail.com wrote: > > Hi, > > I am running standard vpp18.01(without any

Re: [vpp-dev] VPP CSIT robot framework #automation

Might be worth trying to ask same question on csit-dev mailing list — Damjan > On Jun 19, 2019, at 8:15 AM, Devis Reagan wrote: > > Team , Could you help on this query > > Thanks , > Devis Reagan > >> On Tue, Jun 18, 2019 at 11:47 AM Devis Reagan via Lists.Fd.Io >> wrote: >> Dear

Re: [vpp-dev] VPP tap interface issue on Arm servers

Vhost-net kernel module is around for years so I will not he surprised that it is simply disabled in custom kernel built for mcbin. — Damjan > On Jun 18, 2019, at 4:41 PM, Dave Barach via Lists.Fd.Io > wrote: > > Dear Lijan, > > The aarch64 development resources in the LF data center

Re: [vpp-dev] Commit Subjects

> On 17 Jun 2019, at 22:41, Jon Loeliger wrote: > > On Mon, Jun 17, 2019 at 3:33 PM Damjan Marion > wrote: > > I tried to be as much descriptive as possible in those messages, but looks > like I failed :( > > Damjan, > > No problem. I am working on some

Re: [vpp-dev] Commit Subjects

I tried to be as much descriptive as possible in those messages, but looks like I failed :( > On 17 Jun 2019, at 22:20, Florin Coras wrote: > > Hi Jon, > > Yup, it has to match a maintainer “I” entry and yes, that’s where the script > is. :-) > > Florin > >> On Jun 17, 2019, at 1:16 PM,

Re: [vpp-dev] IS-IS : router plugin ISIS + tap-inject #vpp #vpp_hard_code

ISIS is not IP protocol, it just carries IP routing information. ISIS frames are encapsulated in LLC so you need to punt somehow specific LLC traffic to FRR. Not sure I can help more, as I don’t have clue about router plugin… > On 15 Jun 2019, at 08:45, morteza wrote: > > [Edited Message

[vpp-dev] MAINTAINERS update

Dear all, After the yesterday discussion, I submitted update for MAINTAINERS file. https://gerrit.fd.io/r/20089 I kindly ask all folks who maintain parts of the code to take a look and add missing/update existing entries… Thanks, Damjan-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] Libmemif fails to build with GLIBC 2.27+

libmemif is compiled as part of per-patch verify jobs, including ubuntu 18.04 so must be something special in your setup. Can you paste your whole console log, starting with clean git checkout to pastebin? — Damjan > On Jun 3, 2019, at 4:17 PM, Rafał Krych wrote: > > Hello, > > I think it

Re: [vpp-dev] vlib_buffer_free_no_next seems free all the vlib_buffer chain in version 19.04 #vpp #vnet

> On 11 Jun 2019, at 19:01, guangwei wrote: > > I'am now working on version 19.04, and find the behavior of > vlib_buffer_free_no_next is different between 18.07 and 19.04, I think it's > the bug for 19.04: > > always_inline void > vlib_buffer_free_no_next (vlib_main_t * vm, >/*

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

> On 4 Jun 2019, at 09:08, Satya Murthy wrote: > > Hi Damjan, > > In the example you mentioned where bar_init() is trying to find if foo_plugin > is really loaded or not. > If foo_plugin is found to be not loaded, a warning is printed and returning a > 0. > > But this does not gaurantee

Re: [vpp-dev] cache hits/misses per graph node

> On 30 May 2019, at 11:30, Satya Murthy wrote: > > Hi, > > Is there any built-in framework/CLI within VPP, that keeps track of cache > hits/misses for D-cache and I-Cache at graph node or plugin level ? (or) we > need to use general linux perf tools for getting this data ? Even if we do >

[vpp-dev] gerrit

If people didn’t notice, after gerrit upgrade yesterday, there is new UI available. There is switch at the bottom right… Nice thing about it, it doesn’t show FD.io logo over the half of the page. -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group.

Re: [vpp-dev] RAW IP VIA VPP

> On 29 May 2019, at 08:12, amitmulay...@gmail.com wrote: > > Hi guys > i have an issue that i want to consulte. > > VPP as we know dosent "support" usb devices meaning that if i have a wwan0 > port the vpp will not take it > if i wanted to connect it to vpp the way was via tap in the vpp

Re: [vpp-dev] Plugin Versions

> On 27 May 2019, at 13:54, Vratko Polak -X (vrpolak - PANTHEON TECHNOLOGIES at > Cisco) via Lists.Fd.Io wrote: > > SemVer says: > > Patch version Z (x.y.Z | x > 0) MUST be incremented if only backwards > > compatible bug fixes are introduced. > > A bug fix is defined as an internal change

Re: [vpp-dev] Plugin Versions

> On 25 May 2019, at 18:42, Paul Vinciguerra wrote: > > Sorry. Let me try again. > > The semver definition seems to say that backend changes that don't change the > API, still should have the patch version increased. > Bug fixes not affecting the API increment the patch version > New

Re: [vpp-dev] Plugin Versions

> On 25 May 2019, at 13:43, Paul Vinciguerra wrote: > > Hi Damian, > > That's what I initially thought as well. The semver doc says: > For this system to work, you first need to declare a public API. This may > consist of documentation or be enforced by the code itself. Regardless, it is

Re: [vpp-dev] Plugin Versions

if plugin code didn’t change there is no reason to bump api version, on other side plugin version needs to change as it is linked against different core libraries…. > On 25 May 2019, at 03:57, Paul Vinciguerra wrote: > > Is there any reason for having plugin versions that are distinct from

Re: [vpp-dev] VPP crash in show PCI command

Can you try to replace: format_vlib_pci_vpd, d->vpd_r, 0); with format_vlib_pci_vpd, d->vpd_r, NULL); in show_pci_fn() - src/vlib/pci/pci.c > On 24 May 2019, at 07:45, siddarth rai wrote: > > I believe you can see this issue with any NIC. (Invalid value being returned > from var_arg). It

Re: [vpp-dev] VPP crash in show PCI command

> On 23 May 2019, at 15:21, siddarth rai wrote: > > Hello, > > I am using an older version of VPP(18.01) but I checked the code of 19.04 and > I couldn't find any change in problematic area. > > I sometimes get a crash with "Show PCI" command. > > From the core, it seems to be crashing

Re: [vpp-dev] VPP calls mheap_get_search_free_bin but never return

> On May 15, 2019, at 12:33 PM, Mikado wrote: > > Hi, Hi! — Damjan-=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#13091): https://lists.fd.io/g/vpp-dev/message/13091 Mute This Topic: https://lists.fd.io/mt/31665117/21656 Group Owner:

Re: [vpp-dev] Some Emacs lisp to auto run indent on save.

> On 19 May 2019, at 18:43, Christian Hopps wrote: > > Hi vpp-devs, > > Having gotten bit by a checkstyle failure on my first submission, I decided > to port the "go-like" functionality of auto-formatting the file (using indent > since that's what vpp uses) on file save in Emacs.. Here's

Re: [vpp-dev] how to change the name of network in vpp project #vpp

Uncommenting those lines may help.. — Damjan > On May 14, 2019, at 2:47 PM, cmh2014011...@gmail.com wrote: > > I want to change the name of name of network interface in > /etc/vpp/startup.conf just like show in the picture, but it does not work . > My system is centos7 and my vpp version is

Re: [vpp-dev] rdma driver

> On 13 May 2019, at 19:15, Billy wrote: > > > > On Mon, May 13, 2019 at 10:18 AM Benoit Ganne (bganne) via Lists.Fd.Io > > wrote: > Hi Thomas, > > > The external rdma driver includes parts of ib-verbs which are provided as > > part of

Re: [vpp-dev] git commit template

> On 7 May 2019, at 10:39, Ole Troan wrote: > > Hi, > > I just uploaded: > > https://gerrit.fd.io/r/19391 make: git commit template > > The proposal is to use a new git commit template that tags commits with a > type. > Which can be one of feature, docs, make etc. > > The problem this

Re: [vpp-dev] SIGABRT during dpdk_config

On 1 May 2019, at 18:43, Mohamed Mohamed via Lists.Fd.Io mailto:msherif4=yahoo@lists.fd.io>> wrote: Hi Damjan I am running container in privileged mode is there a way to narrow this down ? No idea, I never tried to run VPP in docker container… -- Damjan Thanks Mohamed Sent from my

Re: [vpp-dev] vpp dpdk crypto dev - are multiple crypto algorithms supported concurrently? #vpp

Majority of people who work on VPP actively (including me) are not very familiar about dpdk cryptodev which probably explains why you are not getting any response. Please note that there is currently undergoing big rework of ipsec / crypto where goals are improvement of native crypto,

Re: [vpp-dev] HQoS- Traffic shaping - Pipe profiles

Dear Abeeha, I’m afraid you will not get much luck here. DPDK HQoS support code was contributed long time ago, it is incomplete and not actively developed. Also seems that it is not used as i disabled it in master 3 months ago (due to some API changes) and I didn’t hear any complaint since.

Re: [vpp-dev] SIGABRT during dpdk_config

On 1 May 2019, at 16:11, Mohamed Mohamed via Lists.Fd.Io mailto:msherif4=yahoo@lists.fd.io>> wrote: Hi Folks: I am getting vpp crash during init with the following traces Program terminated with signal SIGABRT, Aborted. #0 0x7f0c7e3ea428 in __GI_raise (sig=sig@entry=6) at

Re: [vpp-dev] span does not work with vlan sub_interface

> On 30 Apr 2019, at 13:46, Berna Demir wrote: > > Hi > > I've used following commands to span packets of vlan sub_interface > to a tap interface, but nothing captured on tap interface in Linux. > > vpp_api_test> create_vlan_subif GigabitEthernet3/0/0 vlan 2100 > > vppctl> > set interface

Re: [vpp-dev] vip in VPP

> On 26 Apr 2019, at 14:15, Shahid Khan wrote: > > Not on different interfaces same subnet on parent and its sub interface > ... Parent interface will have real ip and sub interface will have VIP sub-interface is from fib perspective different interface and it is typically tagged with

Re: [vpp-dev] vip in VPP

This > On 26 Apr 2019, at 14:04, Shahid Khan wrote: > > Two Linux box active and standby.. Each running one instance of vpp..the host > side interface of two boxes are on vrrp ...as a side effect of vip assignment > on host side we want to enable/disable vip on interfaces owned by vpp

Re: [vpp-dev] vip in VPP

> On 26 Apr 2019, at 12:39, Shahid Khan wrote: > > hi, > > Does vpp support VIPs on interfaces...or can we create a sub interface and > assign it IP from same subnet as parent interface ? How is vpp going to decide which interface to use if there is packet for IP address from that subnet?

Re: [vpp-dev] python2 requirements

On 23 Apr 2019, at 19:11, Thomas F Herbert mailto:therb...@redhat.com>> wrote: Damjan, Renato, I am working on cleaning up Fedora dependencies. Do we have any need for python2 in vpp anymore? If python2 APIs are required, can python3 tools generate python2 APIs? no clue, I'm definitely

Re: [vpp-dev] vpp-devel install conflicts

> On 22 Apr 2019, at 20:24, Renato Botelho do Couto wrote: > > Hello, > > When I build vpp using 'make pkg-rpm' on a CentOS 7 without having > vpp-ext-deps installed it adds some includes to vpp-devel package that > makes it to conflict with rdma-core-devel and kernel-headers: > >

Re: [vpp-dev] VPP/RSS questions

> On 22 Apr 2019, at 20:37, Ranadip Das wrote: > > Hi, > > I am trying to play with the RSS feature by enabling multiple rx queues for > the dpdk interface. > However, when I do "show hardware-interfaces detail", I can see the lines > below for RSS. > > rss active:ipv4-tcp

Re: [vpp-dev] Memif "no free tx slots" in 18.10

> On 16 Apr 2019, at 08:39, satish.gu...@gmail.com wrote: > > Retrying this. > > > Hi Vpp-Dev, > > Need your help in understanding one the Memif related issue that we are > facing in 18.10. > This code has been working in 18.01. As soon as we moved to 18.10, we are > started seeing this

Re: [vpp-dev] VPP interfaces names

> On 11 Apr 2019, at 13:57, Mohamed Mohamed via Lists.Fd.Io > wrote: > > Hi All: > > Today DPDK bind script will name the interfaces based on their PCI address > so for example if I have the following 2 interfaces > 00:08.0 Ethernet controller: Intel Corporation 82540EM Gigabit Ethernet >

Re: [vpp-dev] VPP master branch is CLOSED for stable/1904 branch pull

> On 10 Apr 2019, at 22:52, Dave Wallace wrote: > > > > On 4/10/2019 4:43 PM, Damjan Marion wrote: >> >> >>> On 10 Apr 2019, at 21:12, Dave Wallace wrote: >>> >>> Folks, >>> >>> The VPP master branch is now closed for the branch pull of stable/1904. >>> >>> Please do NOT merge any

Re: [vpp-dev] VPP master branch is CLOSED for stable/1904 branch pull

> On 10 Apr 2019, at 21:12, Dave Wallace wrote: > > Folks, > > The VPP master branch is now closed for the branch pull of stable/1904. > > Please do NOT merge any patches until I give the all clear once the branch > pull has been completed and verified. > > I will send an update when

Re: [vpp-dev] Mellanox dependency changes

> On 8 Apr 2019, at 17:35, Stephen Hemminger wrote: > > On Sat, 30 Mar 2019 01:01:29 +0100 > Damjan Marion wrote: > >>> On 30 Mar 2019, at 00:58, Sirshak Das wrote: >>> >>> Apologies, DPDK build failure is not valid. wipe-release fixed it for me. >>> One help still required would be a

Re: [vpp-dev] buffer indirection, cloning, and copying

> On 4 Apr 2019, at 17:07, G. Paul Ziemba wrote: > > I dont have time to read that draft, but it looks to me that during > decryption you can simply spray plaintext into multiple buffers, no? > The relevant aspect of the spec is that multiple payload packets may be > included in a single

Re: [vpp-dev] buffer indirection, cloning, and copying

> On 4 Apr 2019, at 05:19, G. Paul Ziemba wrote: > > We do that by cloning, you can have multiple head buffers with small amount > if data to accommodate l2/l3 headers and then such buffers have b->next_buffer > pointing to shared tail buffer(s). Tail buffer(s) just need to have ref_count >

Re: [vpp-dev] marvell pp2

> On 3 Apr 2019, at 13:25, saint_sun 孙 via Lists.Fd.Io > wrote: > > Hi all, > I want to run vpp on marvell SOC board, anyone know how to set the > startup.conf? > I have insmod the musdk_cma and mv_pp_uio.ko. > Have you read src/plugins/marvell/README.md ? There is no special startup.conf

Re: [vpp-dev] Use of cmake breaks builds in master https://gerrit.fd.io/r/#/c/18600/

On 31 Mar 2019, at 05:39, Thomas F Herbert mailto:therb...@redhat.com>> wrote: Damjan, I attempted to fix a problem with use of cmake breaking CentOS builds with the patch introduced with the new rdma-core and quicly driver. I had this fixed with patch https://gerrit.fd.io/r/#/c/18600/ but

Re: [vpp-dev] Mellanox dependency changes

> On 30 Mar 2019, at 00:58, Sirshak Das wrote: > > Apologies, DPDK build failure is not valid. wipe-release fixed it for me. > One help still required would be a sample config for using the rdma-core > instead of DPDK would like see the performance difference. rdma-core is work in progress,

Re: [vpp-dev] Mellanox dependency changes

> On 28 Mar 2019, at 19:00, Stephen Hemminger > wrote: > > On Wed, 27 Mar 2019 12:06:22 -0400 > "Thomas F Herbert" wrote: > >> +Artem >> >> +vpp-dev >> >> >> On 03/27/2019 11:22 AM, Sirshak Das wrote: >>> >>> Hi Thomas >>> >>> Is this the patch under consideration ? >>> >>>

Re: [**EXTERNAL**] Re: [vpp-dev] VPP Performance question

Your nunbers are quite low, 1500 byte packets means you are bellow 1 Mpps. I saw in the past situations where DPDK 1G intel nic driver was causing problems, but hard to say if this is the same case. What is your CPU speed and type? NIC type? > On 28 Mar 2019, at 05:22, Chandra Mohan, Vijay

Re: [vpp-dev] buffer indirection, cloning, and copying

> On 26 Mar 2019, at 17:45, G. Paul Ziemba wrote: > > I'm still new to VPP, so I thank you more experienced folks for > your insights. I'm implementing a tunneling protocol which requires > fragmentation and aggregation of packets. > > In a traditional system with mbufs (or dpdk buffers), it

Re: [vpp-dev] VPP Performance question

Few hints: 1. When you observe “show run” statistics, you always do: 1. start traffic 2. clear run 3. wait a bit 4 show run Otherwise statistics will show you average which includes period without traffic. 2. debug CLI commands are typically causing barrier sync (unless handler is

<    1   2   3   4   5   6   7   >