I agree with Ole. See
https://www2.eecs.berkeley.edu/Pubs/TechRpts/2005/EECS-2005-24.pdf
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Burt Silverman
Sent: Thursday, June 29, 2017 12:49 PM
To: Ole Troan
Cc: Soheil Abbasloo
You can also use the command-line arg "... dpdk { ... poll-sleep
... } ..." to reduce CPU utilization at low vector rates.
Thanks… Dave
-Original Message-
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Damjan Marion (damarion)
Sent: Thursday, June
I think we discussed this at the last vpp project call, but anyhow: we won't
have a vpp project call on 4-July-2017 due to the US Independence Day holiday.
Thanks... Dave
___
vpp-dev mailing list
vpp-dev@lists.fd.io
: Thursday, June 22, 2017 2:56 PM
To: Dave Barach (dbarach) <dbar...@cisco.com>; vpp-dev <vpp-dev@lists.fd.io>
Subject: Re: [vpp-dev] Fortville DPDK PMD: TCP checksum offload hassles
I have to admit that I did not know about this API until I saw your email and
had a chat with some
roy [mailto:sergio.gonzalez.mon...@intel.com]
Sent: Thursday, June 22, 2017 1:08 PM
To: Dave Barach (dbarach) <dbar...@cisco.com>; vpp-dev <vpp-dev@lists.fd.io>
Subject: Re: [vpp-dev] Fortville DPDK PMD: TCP checksum offload hassles
On 22/06/2017 16:11, Dave Barach (dbarach) wrote:
Fol
Folks,
I'm having a hard time trying to convince an Intel Fortville (i40e) PMD / NIC
to compute and insert TCP correct TCP checksums.
In addition to the typical struct rte_mbuf setup, I add the following:
if (b->flags & VLIB_BUFFER_TCP_CHECKSUM_OFFLOAD)
{
mb->packet_type =
Dear Zhangpan,
This behavior is 100% attributable to the low-vector-rate epoll_pwait(...) call
in .../src/vlib/unix/input.c. If the vector rate is less than 2, vpp currently
sleeps for 10ms between polls. We can discuss how to parameterize and/or change
this behavior.
HTH... Dave
From:
node->cached_next_index will be zero at the beginning of time. Depending on the
particulars involved, that might even be correct.
If not, the enqueue_x1/enqueue_x2 macros will fix the erroneous speculative
enqueues.
vlib_put_next_frame(...) maintains node->cached_next_index...
Thanks... Dave
Dear Marco,
Please supply missing relevant data: complete configurations including
interface addresses, packet trace captures, gdb backtrace preferably from a
TAG=vpp_debug image.
Thanks… Dave
-Original Message-
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
The example you cite is not terribly convincing. The only alternative to a
large number of ip route add/del parameters would be a large number of discrete
APIs with considerable parameter overlap.
API messages need handlers, pretty-print functions, and test code; all of which
require
17 9:25 AM
To: Dave Barach (dbarach) <dbar...@cisco.com>; vpp-dev@lists.fd.io
Subject: Re: [vpp-dev] Need some help on VPP
Thank you. As you mentioned function f, could you please tell for which
function respected stack is created and what is that function f is responsible
for?
On Tuesday 30 M
+1, nice work!
Thanks... Dave
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Luke, Chris
Sent: Tuesday, May 23, 2017 3:00 PM
To: vpp-dev@lists.fd.io
Subject: [vpp-dev] VPP now has basic tab completion
Thanks to the work of Yoann we now have some
Gerrit.fd.io is more or less unusable at the moment. Please take a look.
Thanks… Dave
-Original Message-
From: FD.io Helpdesk via RT [mailto:fdio-helpd...@rt.linuxfoundation.org]
Sent: Tuesday, May 23, 2017 10:08 AM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Subject: [FD.io He
I've seen this a few times this morning. Please check the logs...
Thanks... Dave
[cid:image001.jpg@01D2D3AC.659624E0]
Thanks... Dave
___
vpp-dev mailing list
vpp-dev@lists.fd.io
https://lists.fd.io/mailman/listinfo/vpp-dev
Please attempt to bind the VIC device(s) manually - to uio_pci_generic - using
dpdk-devbind.
Until / unless that works, there isn't a chance that vpp will drive the
devices. You may have better luck with the igb_uio kernel module, or not...
Thanks… Dave
-Original Message-
From:
Pools are not inherently thread-safe.
Coding techniques: allocating a pool per thread [preferred], guarding pool
accesses with spinlocks or pthread mutex / condvar pairs, preallocate and
barrier sync [tricky].
Thanks… Dave
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io]
Copying vpp-dev [and Neale Ranns AKA Dr. Fib...]
Thanks… Dave
From: 薛欣颖 [mailto:xy...@fiberhome.com]
Sent: Tuesday, May 16, 2017 2:16 AM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Subject: Failed to ping between two VPP
Hi Dave,
When I use stable 17.04,there is something wrong when
You’ll need to characterize what you’re seeing better than “multiple time
slower” before it would be worth speculating on what’s going on.
We do not routinely test vpp when compiled w/ -DCLIB_VEC64.
Can you describe the use-case which requires a main heap larger than 4gb?
Thanks… Dave
From:
Please see https://gerrit.fd.io/r/#/c/6387. Any idea why this happened?
13:06:41 + VIRL_SID[${index}]='ERROR: Simulation started OK but devices never
changed to ACTIVE state
13:06:41 Last VIRL response:
13:06:41 {u'\''session-OYbjfr'\'': {u'\''~mgmt-lxc'\'': {u'\''vnc-console'\'':
False,
Please see https://jenkins.fd.io/job/vpp-csit-verify-virl-master/4951/console,
excerpt below. Probably not related to the patch.
I've already pressed the "recheck" button.
Thanks... Dave
13:03:53 + scp -i priv_key -o StrictHostKeyChecking=no -o
UserKnownHostsFile=/dev/null -o BatchMode=yes -o
Writing on behalf of the emacs directory: +1, fine by me, please go ahead and
move the files.
-Original Message-
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Damjan Marion (damarion)
Sent: Tuesday, April 18, 2017 6:26 AM
To: vpp-dev
on a regular basis ?
>
> I just want to know if I did something wrong or whether there might be an
> actual issue here.
>
> Thanks,
> Mircea
>
>
> -Original Message-
> From: Dave Barach (dbarach) [mailto:dbar...@cisco.com]
> Sent: Monday, April 1
All bets are off since the dpdk plugin didn't load correctly. You'll need to
track down ibv_fork_init(...)...
Thanks... Dave
-Original Message-
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Mircea Orban
Sent: Monday, April 17, 2017 12:24 PM
To:
Any idea what could have cause this failure?
https://jenkins.fd.io/job/vpp-verify-master-ubuntu1404/4739/
Thanks... Dave
___
vpp-dev mailing list
vpp-dev@lists.fd.io
https://lists.fd.io/mailman/listinfo/vpp-dev
I’d rather not move the API test tool. It’s compiled into vpp itself these
days, to facilitate binary API - and vpp_api_test - debugging.
I worked hard enough on the problem so that vpp manages to inhale vpp_api_test
plugins, so that essentially the entire binary API can be exercised through
...@redhat.com]
Sent: Wednesday, March 29, 2017 10:46 AM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Cc: Thomas F Herbert <therb...@redhat.com>
Subject: Re: [vpp-dev] Strange C Dyanmic Loading Failure
Thanks, let me know what I can do to help.
On Wed, Mar 29, 2017 at 10:43 AM, Dave Barach (dba
FWIW: I sent diffs to fix the build-system integration over the weekend, as
well as a fair fraction of the FIB 2.0 integration...
Thanks… Dave
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Ni, Hongjun
Sent: Monday, March 27, 2017 10:32 PM
To: Ed Warnicke
at it
will crash as described.
Thanks… Dave
From: Adrian Daniel Calianu [mailto:adrian.cali...@gmail.com]
Sent: Monday, March 27, 2017 10:27 AM
To: Jon Loeliger <j...@netgate.com>
Cc: vpp-dev <vpp-dev@lists.fd.io>; Dave Barach (dbarach) <dbar...@cisco.com>
Subject: Re: [vpp-dev] S
Dear Billy,
Looks like a stale tree...
vm = vlib_mains[os_get_cpu_number ()] from within vpp_api_test was always a
mistake. I cleaned this up a while ago. Vpp_api_test was spuriously linked
against libvlib.so, leading to this very crash in vpp_api_test until I cleaned
up the set of libraries,
+1. See diffs below, which are a start on the problem / fix first-order build
and infra issues. The “router” component needs FIB 2.0 brain-police.
I’m pretty sure that Pierre meant to write: “netlink and router plugin are NOT
really maintained. It is not surprising that they do not compile
Gerrit 5859 (https://gerrit.fd.io/r/#/c/5859) is almost certainly not
responsible for the "make test" failure shown below. Does anyone know what's
going on? I'm going to press the "recheck" button and hope for the best.
Thanks... Dave
2:53:54
Dear Luk,
The "vpp-install," "install-packags," "install-deb" etc. targets will build the
set of plugins configured in src/configure.ac:
For example:
$ cd build-root
$ make PLATFORM=vpp TAG=vpp vpp-install
HTH. Dave
-Original Message-
From: vpp-dev-boun...@lists.fd.io
Simply remove the “dpdk” stanza from /etc/vpp/startup.conf if you want to run
vpp without the dpdk plugin.
Thanks… Dave
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Feng Pan
Sent: Wednesday, March 22, 2017 1:47 PM
To: vpp-dev
Perhaps someone in the community can help you. I have neither cycles nor
equipment available to work on the problem. Just to ask: what kind of hardware
are you using, or are you using a qemu model?
From: 薛欣颖 [mailto:xy...@fiberhome.com]
Sent: Sunday, March 19, 2017 11:18 PM
To: Dave Barach
Linguaglossa
Sent: Wednesday, March 8, 2017 9:54 AM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Cc: vpp-dev@lists.fd.io
Subject: Re: [vpp-dev] [Dev question on changing the VLIB_FRAME_SIZE]
Thank you for your reply,
I actually re-built everything ( make wipe-release && make buil
Please make absolutely sure that (a) you’ve compiled the tree from scratch, and
(b) that you’re not tripping over previously-installed shared libraries built
with a different VLIB_FRAME_SIZE.
Why are you interested in changing VLIB_FRAME_SIZE in the first place?
Thanks… Dave
From:
...@zte.com.cn]
Sent: Wednesday, March 8, 2017 2:50 AM
To: hongjun...@intel.com
Cc: alaga...@gmail.com; Dave Barach (dbarach) <dbar...@cisco.com>;
zhao.zhig...@zte.com.cn; gu.ji...@zte.com.cn; pan.feng...@zte.com.cn;
vpp-dev@lists.fd.io
Subject: 答复: RE: R[vpp-dev] Signal events between graph
+1... Crud, missed that... Thanks… Dave
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Neale Ranns (nranns)
Sent: Monday, March 6, 2017 11:07 AM
To: Matej Klotton -X (mklotton - PANTHEON TECHNOLOGIES at Cisco)
; vpp-dev@lists.fd.io
Cc:
I'm not sure if this is significant, but you wrote: "In a testcase I'm sending
tagged frame with tag 20 and I'm expecting received packed with tag 10"
The packet tracer shows the reverse: a packet received on vlan 10 and sent on
vlan 20.
00:00:18:038106: dpdk-input
GigabitEthernet0/4/0 rx
Cool... Thanks… Dave
From: Jon Loeliger [mailto:j...@netgate.com]
Sent: Sunday, March 5, 2017 10:06 AM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Cc: Florin Coras <fcoras.li...@gmail.com>; vpp-dev <vpp-dev@lists.fd.io>
Subject: Re: [vpp-dev] Missing session.api.h file
O
See https://gerrit.fd.io/r/#/c/5622...
Thanks… Dave
From: Dave Barach (dbarach)
Sent: Friday, March 3, 2017 10:50 PM
To: Jon Loeliger <j...@netgate.com>
Cc: Florin Coras <fcoras.li...@gmail.com>; vpp-dev <vpp-dev@lists.fd.io>
Subject: RE: [vpp-dev] Missing session.api.h
too sleepy to do it accurately right now.
Thanks… Dave
From: Jon Loeliger [mailto:j...@netgate.com]
Sent: Friday, March 3, 2017 10:43 PM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Cc: Florin Coras <fcoras.li...@gmail.com>; vpp-dev <vpp-dev@lists.fd.io>
Subject: Re:
BUG: multiple registrations of
'vl_api_sw_interface_tag_add_del_reply_t_handler' means pretty much what it
says. Two places in the code are registering handlers for that specific
message. Last registrant wins.
I found and fixed 30 of these when I first added the check. Most were
relatively
Cool... Thanks... Dave
From: John Lo (loj)
Sent: Thursday, March 2, 2017 4:32 PM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Cc: vpp-dev <vpp-dev@lists.fd.io>
Subject: RE: sw_interface_set_vxlan_bypass API message - 2x incompatible
handlers...
Thanks Dave, I will clean up the
Dear John,
I imagine that you might be the right person to warn about this...
There are two incompatible implementations of
vl_api_sw_interface_set_vxlan_bypass_t_handler. One in .../src/vpp/api/api.c,
and the other one is in .../src/vnet/vxlan.c.
One is feature-arc based, the other is not.
+1, exactly right, thanks Ole... Dave
-Original Message-
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of otr...@employees.org
Sent: Thursday, March 2, 2017 7:17 AM
To: vpp-dev
Subject: [vpp-dev] VPP API Freeze date coming up --
d at main thread?
Ewan
yug...@telincn.com<mailto:yug...@telincn.com>
From: Luke, Chris<mailto:chris_l...@comcast.com>
Date: 2017-03-01 20:14
To: yug...@telincn.com<mailto:yug...@telincn.com>; Dave Barach
(dbarach)<mailto:dbar...@cisco.com>; E
"If you're reading this message, vpp w/ dpdk-as-a-plugin is now running my home
gateway."
No issues noted... Nice job, Damjan!
dbarach@vppgate:~$ telnet 0 5002
Trying 0.0.0.0...
Connected to 0.
Escape character is '^]'.
_____ _ ___
__/ __/ _ \ (_)__| | / / _ \/
Please explain what you're trying to do in detail. There should be no need to
ever do something like that.
Vlib_buffer_t's are embedded in private headroom space, tangent to the packet
DMA target [which starts at (struct mbuf *)mb->data_off].
Here's how we create the mempools:
rmp =
See also src/vnet/unix/tuntap.c, which seems to already do pretty much what
you’re describing. It’s disabled by default. Use the command-line argument
“tuntap { enable }” to kick the tires.
In addition to the concerns which Chris mentioned, adding ‘system(“foo”)’ calls
to vpp is not a security
If the value could be construed as a pool index - e.g. a sw_if_index - I always
use u32 and ~0...
Thanks… Dave
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Jon Loeliger
Sent: Thursday, February 23, 2017 5:03 PM
To: vpp-dev
Subject:
For example: https://gerrit.fd.io/r/#/c/5498
Thanks... Dave
13:54:14.203 TRACE exec_command on ('10.30.51.236', 22): sudo -S rm -f
/tmp/qga.sock
13:54:14.306 TRACE exec_command on ('10.30.51.236', 22) took
0.106814861298 seconds
13:54:14.306 TRACE chan_recv/_stderr took
The Linux kernel is turfing the TCP (SYN) packets.
If you run wireshark or tcpdump, you’ll rapidly confirm that reasonable-looking
SYNs are being sent. Check to see if missing routes or iptables are responsible.
IIRC Keith Burns managed to make this work, copying him.
Thanks… Dave
From:
Hey Burt,
8 + 9 => make a new .../build-data/platforms/amd-senior-citizen.mk file, and
build PLATFORM=amd-senior-citizen. It wouldn’t be a problem to merge a patch
with that piece of the puzzle.
From the Shameless Commerce Department at Car Talk Plaza: you could also buy a
new computer.
Try it with a debug image. Mask==0x1 => SIGSEGV, with probability 1.
Thanks… Dave
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of William McCall
Sent: Monday, February 20, 2017 7:58 AM
To: Ni, Hongjun
Cc: Siamak Abdollahzade
A bit more inline, see drb>>>
Thanks… Dave
-Original Message-
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Neale Ranns (nranns)
Sent: Saturday, February 18, 2017 3:52 PM
To: pxv3...@rit.edu; vpp-dev@lists.fd.io
Cc: Shailesh Vajpayee
Please fix merge conflict(s) in https://gerrit.fd.io/r/#/c/4715/5
Thanks… Dave
From: Andrej Macak -X (amacak - PANTHEON TECHNOLOGIES at Cisco)
Sent: Friday, February 17, 2017 9:34 AM
To: vpp-dev@lists.fd.io
Cc: michal.janc...@pantheon.tech; Dave Barach (dbarach) <dbar...@cisco.com>;
Dear Vanessa,
Have we an estimate for how long the Jenkins queue will be effectively unusable
due to what appear to be 300 jobs in the queue?
How about spinning up extra slaves to clear the backlog?
Thanks... Dave
___
vpp-dev mailing list
Please see https://gerrit.fd.io/r/#/c/5150. We plan to merge the code prior to
the 17.04 FC0 date.
Thanks... Dave
___
vpp-dev mailing list
vpp-dev@lists.fd.io
https://lists.fd.io/mailman/listinfo/vpp-dev
The top-level Makefile lists the current build dependencies relative to both
the centos and the Ubuntu distros.
Thanks… Dave
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Raghav Kaushik (rakaushi)
Sent: Tuesday, February 14, 2017 6:01 PM
To:
((void *) msg);
}
From: Jon Loeliger [mailto:j...@netgate.com]
Sent: Friday, February 10, 2017 4:46 PM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Cc: vpp-dev <vpp-dev@lists.fd.io>; Edward Warnicke <hagb...@gmail.com>
Subject: Re: VPP API Synchronization Question
On Fri, Feb 1
on a separate pthread. The api
test tool uses the world’s crudest synchronization scheme.
Contact me off-list if you can’t figure out what’s wrong.
Thanks… Dave
From: Jon Loeliger [mailto:j...@netgate.com]
Sent: Friday, February 10, 2017 12:12 PM
To: vpp-dev <vpp-dev@lists.fd.io>
Cc
day, February 8, 2017 11:15 PM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Cc: Pierre Pfister (ppfister) <ppfis...@cisco.com>; vpp-dev@lists.fd.io
Subject: Re: [vpp-dev] classify and redirect to tap
I am using IRB config.
I am using CLI and CLI docs to find these features.
Sorry, but I cou
Assuming that you’re using an IRB config: I’d suggest using the ip input
feature arc; enable the feature on the IRB loopback interface and off you go.
FYI: we’re planning a significant rework of the L2 feature path. I’m guessing
that you don’t care about intercepting 192.168.1.10 tcp ->
here, please confirm that I’m understanding what you need
to do.
Thanks… Dave
From: John Pearson [mailto:johnpearson...@gmail.com]
Sent: Tuesday, February 7, 2017 7:00 PM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Cc: vpp-dev@lists.fd.io
Subject: Re: [vpp-dev] classify and redirect to tap
If you continue to have trouble, please push a draft patch and I’ll take a
look...
Thanks… Dave
From: Sreejith Surendran Nair [mailto:sreejith.surendrann...@linaro.org]
Sent: Tuesday, February 7, 2017 11:24 AM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Cc: vpp-dev <vpp-dev@li
There’s no need to call pool_alloc(...) in typical cases. Pools are vectors
(dynamic arrays), they expand as necessary.
During initial development, please always run TAG=vpp_debug or equivalent
images. If you make mistakes with vector-based data structure(s), the code
tends to ASSERT(...)
See vlib_buffer_advance(...). Depending on what you want to do - which you
didn’t share - that may be all you need.
In any event, these buffer metadata fields are involved:
current_data, current_length, total_length_not_including_first_buffer,
next_buffer, flags
Take a careful look at
Dear John,
Read at face value, you’ll probably want to implement an output feature to take
care of it. Before I jump in and start describing the mechanics involved:
please describe the use-case in some detail.
The easiest-to-code solution would probably cost an annoying amount of
performance
Item added to https://wiki.fd.io/view/VPP/Meeting#Agenda
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Ed Warnicke
Sent: Monday, February 6, 2017 7:37 PM
To: Luke, Chris
Cc: vpp-dev ; Damjan Marion
Dear Neale,
Thanks very much, seems like patches are verifying again... I rebased another
patch a second ago.
Dave
From: Neale Ranns (nranns)
Sent: Sunday, February 5, 2017 1:59 PM
To: Dave Barach (dbarach) <dbar...@cisco.com>; vpp-dev@lists.fd.io
Cc: csit-...@lists.fd.io
Subject: Re: [v
Would the owners of these failures please repair them at their earliest
possible convenience? We won't be able to merge patches [without using a
hammer] until the problem is fixed...
Thanks... Dave
16:51:00 [vpp-verify-master-ubuntu1404] $ /bin/bash
/tmp/hudson7704395251888577201.sh
Forwarding to csit-dev... A patch against master/latest verified OK on LF infra
half an hour ago...
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Rybalchenko, Kirill
Sent: Friday, February 3, 2017 7:59 AM
To: vpp-dev@lists.fd.io
Subject: [vpp-dev] CSIT test
OK, cool, will do... Thanks... Dave
-Original Message-
From: Jan Gelety -X (jgelety - PANTHEON TECHNOLOGIES at Cisco)
Sent: Thursday, February 2, 2017 9:44 AM
To: Dave Barach (dbarach) <dbar...@cisco.com>; Dave Wallace
<dwallac...@gmail.com>; csit-...@lists.fd.io
Cc: vpp-dev
See https://jenkins.fd.io/job/vpp-csit-verify-virl-master/3660/console:
14:11:40 + VIRL_SID[${index}]='ERROR: Simulation started OK but devices never
changed to ACTIVE state
14:11:40 Last VIRL response:
14:11:40 {u'\''session-__95OJ'\'': {u'\''~mgmt-lxc'\'': {u'\''vnc-console'\'':
False,
Done... Thanks... Dave
From: Marek Gradzki -X (mgradzki - PANTHEON TECHNOLOGIES at Cisco)
Sent: Monday, January 30, 2017 7:34 AM
To: Luke, Chris <chris_l...@comcast.com>; vpp-dev@lists.fd.io;
hc2...@lists.fd.io
Cc: Dave Barach (dbarach) <dbar...@cisco.com>; Damjan Marion (damar
you can
check them in Wireshark; to the extent that you don't already know what's
wrong...
Thanks... Dave
From: Miguel Angel Muñoz Gonzalez
[mailto:miguel.angel.munoz.gonza...@ericsson.com]
Sent: Friday, January 27, 2017 4:41 PM
To: Dave Barach (dbarach) <dbar...@cisco.com>; nsh_sfc
Loeliger [mailto:j...@netgate.com]
Sent: Friday, January 27, 2017 10:24 AM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Cc: vpp-dev <vpp-dev@lists.fd.io>
Subject: Re: [vpp-dev] SNAT Plugin Use
On Thu, Jan 26, 2017 at 4:38 PM, Jon Loeliger
<j...@netgate.com<mailto:j...@netgate.
(STR_VL_API_SNAT_ADD_ADDRESS_RANGE);
HTH... D.
From: Jon Loeliger [mailto:j...@netgate.com]
Sent: Thursday, January 26, 2017 3:29 PM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Cc: vpp-dev <vpp-dev@lists.fd.io>
Subject: Re: [vpp-dev] SNAT Plugin Use
On Wed, Jan 25, 2017 at 10:49 AM,
As Damjan wrote, the vpp graph dispatcher has known how to switch input nodes
between interrupt and polling mode since before the dpdk even existed.
Unfortunately, not all dpdk drivers support interrupt-mode processing, again,
as discussed.
As a clock-cycle / power-consumption mitigation
Vmxnet3 interfaces are strongly preferred: for performance, as well as to make
this specific issue disappear.
We have a patch floating around which turns off the disk-filling syslog
message, but if you simply switch to vmxnet3 interfaces the pain will go away
without rebuilding images, etc.
In case folks are interested, see: https://wiki.fd.io/view/VPP/VPP_Home_Gateway
Note that the exercise resulted in the addition of a couple of new features for
the snat plugin, and a jira ticket: https://jira.fd.io/browse/VPP-612
___
vpp-dev mailing
Hey Damjan,
Congrats to you and the entire community for all the hard work which went into
the 17.01 release!
Dave
From: Damjan Marion (damarion)
Sent: Friday, January 20, 2017 6:38 PM
To: vpp-internal(mailer list)
Subject: Fwd: [discuss] VPP 17.01 Released
Begin
Folks,
See https://jenkins.fd.io/job/vpp-verify-master-ubuntu1604/3378/console
11:00:46 E: Could not get lock /var/lib/dpkg/lock - open (11: Resource
temporarily unavailable)
11:00:46 E: Unable to lock the administration directory (/var/lib/dpkg/), is
another process using it?
I
Vpp already calls rte_eal_init(...) in .../src/vnet/dpdk/init.c:dpdk_config().
Please don't call rte_eal_init(..) elsewhere, it simply won't work.
At a higher level: what are you trying to do? It's hard to provide meaningful
help with so little information.
Thanks... Dave
From:
Please see https://gerrit.fd.io/r/#/c/4674. Lots more work to do, but as
given the tcp host stack manages to bring up tcp sessions.
Comments to me, Florin Coras (fco...@cisco.com), and/or Keith Burns
(k...@cisco.com).
Thanks. Dave
smime.p7s
Description: S/MIME cryptographic
+1... Hey John, thanks a lot for the detailed analysis...
Dave
From: John Lo (loj)
Sent: Wednesday, January 11, 2017 5:40 PM
To: Dave Barach (dbarach) <dbar...@cisco.com>; Juraj Linkes -X (jlinkes -
PANTHEON TECHNOLOGIES at Cisco) <jlin...@cisco.com>; vpp-dev@lists.fd.io
Subject:
Dear Juraj,
I took a look. It appears that the last operation in the post-mortem API trace
was to kill a vxlan tunnel. Is there a reasonable chance that other interfaces
in the bridge group containing the tunnel were still admin-up? Was the tunnel
interface removed from the bridge group prior
Dear Ole,
I have a quick/easy request for the Python language binding. See
pneum_connect(...). We need to make the client input queue size configurable,
with a default size of 32. See below.
Seems like a simple change to vpp_papi.py:connect(...) ->
pneum_wrap.c:wrap_connect(...) ->
Folks,
Gerrit.fd.io is behaving badly this morning: glacially slow, gateway timeouts,
disappearance of the +2 button for committers, etc.
We've alerted the LF. No ETA for happy camping.
Thanks... Dave
___
vpp-dev mailing list
vpp-dev@lists.fd.io
Take a look at vpp_api_test, specifically
.../vat/api_format.c:api_ip_add_del_route()...
Thanks... Dave
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of yug...@telincn.com
Sent: Saturday, December 31, 2016 7:23 AM
To: vpp-dev
Subject:
Workaround: you can make the pain go away by trashing the ioam plugin(s), e.g.
in /usr/lib/vpp_plugins.
Or, disable them in .../plugins/configure.ac in the obvious way, remove /
rebuild / reinstall the Debian plugin package.
Thanks… Dave
From: vpp-dev-boun...@lists.fd.io
Ed: correct me if I’m wrong, but IIRC we must not put GPLv2 into an fd.io
gerrit repo...
Thanks… Dave
From: Alec Hothan (ahothan)
Sent: Wednesday, December 14, 2016 4:06 PM
To: Joel Halpern <joel.halp...@ericsson.com>; Dave Barach (dbarach)
<dbar...@cisco.com>; t...@lists.fd.io;
I took a note to have a look at collectd during yesterday's vpp project call.
There appears to be a license issue. See
https://collectd.org/wiki/index.php/Plugin_architecture - "The [plugin] license
must be compatible to collectd's own license, the GPL 2."
Give that all fd.io code carries an
In /Makefile.am:
my_plugin_la_LIBADD = -l
for any / all values of that the plugin requires.
Thanks… Dave
From: mahdi akrami [mailto:akram...@gmail.com]
Sent: Wednesday, December 14, 2016 10:48 AM
To: Dave Barach (dbarach) <dbar...@cisco.com>
Subject: Re: [vpp-dev] Fwd: DPDK SDK in plug
5, 2016 at 4:26 PM
Subject: Re: [vpp-dev] DPDK SDK in plugin
To: "Dave Barach (dbarach)" <dbar...@cisco.com<mailto:dbar...@cisco.com>>
Hi Dave,
I compared DPDK and VPP hash libs and it seems that DPDK implementation is
about twice faster that VPP hash. I want to use DPDK hash i
The prevailing vector size is a self-timed, stable equilibrium value, arranged
by the graph dispatcher. Individual graph nodes don't have to worry about the
problem. Follow the coding patterns you'll see all over the place, and you
should be good.
The graph dispatcher is essentially a while(1)
Thanks... Dave
___
vpp-dev mailing list
vpp-dev@lists.fd.io
https://lists.fd.io/mailman/listinfo/vpp-dev
I’m sure that I can help, but this request isn’t specific enough.
Please upload a draft patch with a README describing the library / contents you
need to link into the plugin.
Thanks… Dave
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of mahdi akrami
Sent:
32 is an even divisor of CLIB_CACHE_LINE_BYTES for every platform that I can
think of.
The usual scheme: split the data across 2 (or more) elogs. Any special reason
you can’t do that?
Thanks… Dave
From: vpp-dev-boun...@lists.fd.io [mailto:vpp-dev-boun...@lists.fd.io] On
Behalf Of Alex Salig
801 - 900 of 920 matches
Mail list logo