Is the VPP project addressing the use of master/slave nomenclature in the code
base,
documentation and CLI? We are doing this for DPDK and it would be good if the
replacement wording used in DPDK matched the wording used in FD.io projects.
Particularly problematic is the use of master/slave in b
On Fri, 10 May 2019 12:49:51 +
"Benoit Ganne (bganne) via Lists.Fd.Io" wrote:
> I guess you are relying on DPDK here. Are you able to use the card with DPDK
> testpmd?
> If not, you may be missing Mellanox OFED driver, depending upon DPDK version.
> Otherwise you can switch to VPP 19.04 and
On Fri, 12 Apr 2019 09:19:37 +
"Benoit Ganne (bganne)" wrote:
> Hi Stephen,
>
> Thanks. Ok, so we should implement the VF control protocol on the netsvc
> device. That said, it looks to me that we could use the AF_PACKET for this,
> no need for an optimized, poll-mode netsvc driver in VPP.
On Thu, 11 Apr 2019 10:24:45 -0700
"Stephen Hemminger via Lists.Fd.Io"
wrote:
> On Thu, 11 Apr 2019 09:30:12 +
> "Benoit Ganne (bganne)" wrote:
>
> > Hi Stephen,
> >
> > > The rdma-core stuff is likely to be a problem on Azure. The Mel
On Thu, 11 Apr 2019 09:30:12 +
"Benoit Ganne (bganne)" wrote:
> Hi Stephen,
>
> > The rdma-core stuff is likely to be a problem on Azure. The Mellanox
> > device is always hidden as a secondary device behind a synthetic virtual
> > device based on VMBus. There are two DPDK different ways thi
On Mon, 8 Apr 2019 18:07:48 +0200
Damjan Marion wrote:
> > 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:
&
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 sample config for using the rdma-core
> > instead of DPDK would like
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 ?
> >
> > https://gerrit.fd.io/r/#/c/18521/
> >
> > So will this make mlx4/5 dpdk compilation defa
On Sun, 17 Mar 2019 06:53:02 +
Matan Azrad wrote:
> Hi
>
> From: Stephen Hemminger
> > wrote:
> >
> > > Hi
> > >
> > > From: Stephen Hemminger
> > > > The vdev_netvsc virtual driver that is used to do initialization on
>
On Thu, 14 Mar 2019 11:26:05 +
Matan Azrad wrote:
> Hi
>
> From: Stephen Hemminger
> > The vdev_netvsc virtual driver that is used to do initialization on Hyper-
> > V/Azure won't work without failsafe and tap device.
> > If the related devices aren'
uild.
Signed-off-by: Stephen Hemminger
---
drivers/net/vdev_netvsc/vdev_netvsc.c | 14 ++
1 file changed, 14 insertions(+)
diff --git a/drivers/net/vdev_netvsc/vdev_netvsc.c
b/drivers/net/vdev_netvsc/vdev_netvsc.c
index 801f54c96e01..9c262358b5ee 100644
--- a/drivers/net/vdev_netvsc/vdev_ne
Looks like a change went into DPDK which rearranged the rte_sched (hQOS) fields
in the next release. This breaks build on VPP.
Not hard to fix in VPP, but let's wait and see if DPDK intends to break API or
if it was just developer not paying attention.
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive a
On Wed, 09 Jan 2019 00:18:13 -0800
"Nixon Raj via Lists.Fd.Io" wrote:
> *Setup:*
>
> ·Platform – GNU/Linux
>
> ·Kernel – 4.4.0-131-generic
>
> ·Processor – x86_64
>
> ·OS - Ubuntu 16.04
>
>
>
> *MLNX_OFED Driver Version :*
>
> ·4.1-1.0.2.0
>
> Fol
On Sun, 16 Dec 2018 11:40:42 +0100
"Damjan Marion via Lists.Fd.Io" wrote:
> slightly related: not sure if people notified, but recently I added option to
> specify interface name from the startup.conf.
>
> i.e.
> dpdk {
> dev :12:00.0 { name eth0 }
> dev :12:00.1 { name eth1 }
> }
On Thu, 13 Dec 2018 02:53:23 +
"Yang, Liang" wrote:
>
VPP 18.01 uses DPDK 17.11 which doesn't require OFED to work:
doc/guides/rel_notes/release_17_11.rst
* Refactored driver to get rid of dependency on the components provided by
Mellanox OFED and instead rely on the current and pu
Fri, Dec 14, 2018 at 12:00 PM Dave Barach (dbarach)
wrote:
> Please revert https://gerrit.fd.io/r/#/c/16429/ and report results.
>
> -Original Message-
> From: vpp-dev@lists.fd.io On Behalf Of Stephen
> Hemminger
> Sent: Friday, December 14, 2018 2:58 PM
> To: vpp-dev@
String tests now failing on Debian testing.
Compiler is catching error before test!
FAILED: plugins/unittest/CMakeFiles/unittest_plugin.dir/string_test.c.o
ccache /usr/lib/ccache/cc -DHAVE_MEMFD_CREATE -Dunittest_plugin_EXPORTS
-I/home/shemminger/git/vpp/src -I. -Iinclude
-I/home/shemminger/gi
On Mon, 10 Dec 2018 09:32:26 -0800
Damjan Marion wrote:
> Stephen,
>
> Can you make this dependency optional? CMake detect presence of libuuid and
> then
> conditionally compile vmbus code?
>
> In some cases that library might not be present, specially in some embedded
> cases...
>
> That wi
The VMBus changes keep failing build on CentOs because of
missing install of new dependency (libuuid-devel).
See: https://gerrit.fd.io/r/15311
The RPM_DEPENDS is updated in the Makefile, and it works on a local CentOs 7.6
VM.
I suspect that the build CI doesn't do 'make install-dep' so it
doesn'
Build is failing for me on latest up to date version of Fedora and VPP.
This is a clean new VM, and did the install of dependencies but Makefile
is still confused.
$ make build
Please install missing RPMs: \npackage cmake3 is not installed\n
by executing "make install-dep"\n
Also looks like ech
Ok. Thanks I didn't want to head down the dead end
On Fri, Nov 16, 2018, 2:09 AM Damjan Marion
>
> > On 16 Nov 2018, at 02:02, Stephen Hemminger
> wrote:
> >
> > I just discovered the clang-format file and noticed that Linux kernel
> used
> > the ForEach
I just discovered the clang-format file and noticed that Linux kernel used
the ForEachMacros option to format for() wrappers.
VPP seems to be riddled with INDENT-OFF when it does vector loops. (2123 times!)
Has anyone looked into replacing these with ForEachMacros?
-=-=-=-=-=-=-=-=-=-=-=-
Links: Y
On Wed, 31 Oct 2018 00:24:36 -0700
Florin Coras wrote:
> No reader-writer locks are 100's of times slower. In fact reader
> write locks are slower than normal spin lock.
>
> >>>
> >>> I guess you meant that in general, and I can see how for scenarios with
> >> multiple write
I was playing around with sample plugin, it looks like the documentation is out
of date
with current VPP especially autoconf etc.
Could someone walkthrough the documentation and make sure the example works.
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply O
On Mon, 29 Oct 2018 14:58:07 -0700
Florin Coras wrote:
> > On Oct 29, 2018, at 1:42 PM, Stephen Hemminger
> > wrote:
> >
> > On Mon, 29 Oct 2018 13:20:27 -0700
> > Florin Coras wrote:
> >
> >> Hi Stephen,
> >>
> >> No, we
On Mon, 29 Oct 2018 13:20:27 -0700
Florin Coras wrote:
> Hi Stephen,
>
> No, we don’t support RCU. Wouldn’t rw-locks be enough to support your
> usecases?
>
> Florin
>
> > On Oct 29, 2018, at 12:40 PM, Stephen Hemminger
> > wrote:
> >
> > I
Is it possible to do Read Copy Update with VPP? Either using Userspace RCU
(https://librcu.org)
or manually. RCU is very efficient way to handle read mostly tables and other
dynamic cases
such as plugins.
The several things that are needed are non-preempt, atomic update of a pointer
and a mecha
On Wed, 24 Oct 2018 23:09:15 +0200
Damjan Marion wrote:
> —
> Damjan
>
> > On 24 Oct 2018, at 23:04, Stephen Hemminger
> > wrote:
> >
> > On Wed, 24 Oct 2018 21:07:15 +0200
> > Damjan Marion wrote:
> >
> >>> On 24 Oct 2018, at 20
On Wed, 24 Oct 2018 21:07:15 +0200
Damjan Marion wrote:
> > On 24 Oct 2018, at 20:41, Stephen Hemminger
> > wrote:
> >
> > On Wed, 24 Oct 2018 11:31:38 -0700
> > "Stephen Hemminger" > <mailto:step...@networkplumber.org>> wrote:
>
On Wed, 24 Oct 2018 11:31:38 -0700
"Stephen Hemminger" wrote:
> On Wed, 24 Oct 2018 16:27:24 +
> "Sirshak Das" wrote:
>
> > FYI just to be on same page things are not broken in 1810 so I don’t think
> > its needed. Its only broken in current maste
On Wed, 24 Oct 2018 16:27:24 +
"Sirshak Das" wrote:
> FYI just to be on same page things are not broken in 1810 so I don’t think
> its needed. Its only broken in current master.
>
> From: Marco Varlese
> Sent: Wednesday, October 24, 2018 9:18 AM
> To: dmar...@me.com; Sirshak Das
> Cc: vpp
On Mon, 15 Oct 2018 23:51:04 +0200
Damjan Marion wrote:
> > On 15 Oct 2018, at 21:42, Stephen Hemminger
> > wrote:
> >
> > Has VPP ever considered using Meson, which seems to be where most userspace
> > projects are headed for build systems.
> >
> &
Has VPP ever considered using Meson, which seems to be where most userspace
projects are headed for build systems.
http://mesonbuild.com/Comparisons.html
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#10823): https://lists.fd.io/g/vpp-dev/message/1
The DPDK plugin has problems with non-PCI devices. It is using the old DPDK
assumptions that all
devices are really PCI. There are various special cases in there already, but
it needs to be
fixed properly by using the DPDK bus model.
The fix isn't hard, my question is how far back in DPDK histor
Sorry for top posting Gmail on phone is stupid.
A process can do introspection by doing dlopen with NULL as filename. Then
look up symbols from there.
On Fri, Sep 28, 2018, 5:22 PM Damjan Marion wrote:
>
>
> > On 28 Sep 2018, at 12:13, Stephen Hemminger
> wrote:
> >
Having supported hardware list buried in DPDK plugin code is a nuisance.
Could the table be generated at build time maybe from pmdinfo or using
dlopen to lookup symbols?
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#10702): https://lists.fd.io/g/vp
On Tue, 25 Sep 2018 15:16:04 +0200
Damjan Marion wrote:
> > On 25 Sep 2018, at 15:03, Stephen Hemminger
> > wrote:
> >
> > I noticed that the PCI domain in VPP is limited to 16 bits.
> > This is a problem on Azure/Hyper-V and other virtual environments.
>
On Tue, 25 Sep 2018 15:16:04 +0200
Damjan Marion wrote:
> > On 25 Sep 2018, at 15:03, Stephen Hemminger
> > wrote:
> >
> > I noticed that the PCI domain in VPP is limited to 16 bits.
> > This is a problem on Azure/Hyper-V and other virtual environments.
>
I noticed that the PCI domain in VPP is limited to 16 bits.
This is a problem on Azure/Hyper-V and other virtual environments.
In these environments, the host will generate a 32 bit synthetic value
when passing a PCI device through. The Linux kernel has 32 bit PCI
domains, and libpciaccess used by
I am looking into the best way to integrate setup of the Hyper-V/Azure Network
Poll Mode Driver
(netvsc PMD) from DPDK. The device shows up on vmbus (not PCI) therefore
setting it up transparently
in VPP requires some additional setup logic; it can be setup now via other
methods such as driverct
On Fri, 21 Sep 2018 23:01:12 +0200
Damjan Marion wrote:
> > On 21 Sep 2018, at 20:27, Stephen Hemminger
> > wrote:
> >
> > On Thu, 20 Sep 2018 21:04:17 +0200
> > Damjan Marion mailto:dmar...@me.com>> wrote:
> >
> >>> On
On Thu, 20 Sep 2018 18:56:28 +
"Steven Luong (sluong)" wrote:
> Stephen,
>
> Fix for vhost
> https://gerrit.fd.io/r/14920
>
> I'll take care of vmxnet3 later.
>
> Steven
>
> On 9/20/18, 10:57 AM, "vpp-dev@lists.fd.io on behalf of St
Doing this:
$ export UBUNTU="bionic"
$ unset -v RELEASE
$ export RELEASE=".stable.1807"
$ sudo rm /etc/apt/sources.list.d/99fd.io.list
$ echo "deb [trusted=yes]
https://nexus.fd.io/content/repositories/fd.io$RELEASE.ubuntu.$UBUNTU.main/ ./"
| sudo tee -a /etc/apt/sources.list.d/99fd.io.list
Is there a way to use virtio_user as an exception path with DPDK?
https://doc.dpdk.org/guides-17.11/howto/virtio_user_as_exceptional_path.html
Testing simple case, I see much better performance with this when forwarding
a 10G device to kernel.
Rx Tx
KNI 3
On Thu, 20 Sep 2018 20:15:34 +0200
Damjan Marion wrote:
> Damjan
>
> > On 20 Sep 2018, at 19:57, Stephen Hemminger
> > wrote:
> >
> >
> > Why is there not a simple link on FD.io developer web page to report bugs.
> > Reporting bugs page talks a
Why is there not a simple link on FD.io developer web page to report bugs.
Reporting bugs page talks about the data BUT DOESN'T GIVE THE PROCESS.
If you are using JIRA why not vpp-bugs mail alias?
I tried creating a virtio user device and noticed that the device name
displayed is garbage:
DBGv
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
> that with this option, the kernel cannot guarantee that applications a
On Tue, 24 Jan 2017 17:14:42 +
"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 packages?
>
> I think generally people don’t like out-of-tree modules, so as long as we are
> getting
> the s
48 matches
Mail list logo