Hi VPP dev guys,
Does Anybody see the failures about vpp on master branch as
following? The failures must be reproduced on my 3 servers/boxes. How can I
fix it ?
vlib_physmem_shared_map_create: pmalloc_map_pages: failed to mmap 1 pages at
0x7fd94000 fd 25 numa 0 flags 0x4
Your kernel is refusing to do mmap().
We need a bit more info, kernel version, kernel parameters,
Are you on the latest master?
--
Damjan
> On 19 Nov 2018, at 10:25, Zhiyong Yang wrote:
>
> Hi VPP dev guys,
>
> Does Anybody see the failures about vpp on master branch as
Damjan,
I'm working on CentOS 7.5 and on the latest master for VPP.
Uname -r
3.10.0-862.14.4.el7.x86_64
[root@localhost vpp]# cat /etc/redhat-release
CentOS Linux release 7.5.1804 (Core)
Thanks
Zhiyong
From: vpp-dev@lists.fd.io [mailto:vpp-dev@lists.fd.io] On Behalf Of Damjan
Ma
kernel parameters?
--
Damjan
> On 19 Nov 2018, at 10:57, Yang, Zhiyong wrote:
>
> Damjan,
>
> I’m working on CentOS 7.5 and on the latest master for VPP.
> Uname –r
> 3.10.0-862.14.4.el7.x86_64
>
> [root@localhost vpp]# cat /etc/redhat-release
> CentOS Linux release 7.5.180
BOOT_IMAGE=/vmlinuz-3.10.0-862.14.4.el7.x86_64 root=/dev/mapper/centos-root ro
crashkernel=auto rd.lvm.lv=centos/root rd.lvm.lv=centos/swap rhgb quiet
default_hugepagesz=1G hugepagesz=1G hugepages=8 intel_iommu=on iommu=pt
isolcpus=1-20 LANG=en_US.UTF-8 nohz_full=1-20 rcu_nocbs=1-20
From: Damja
There is also an attempt to clean up processes left bind in a shell
script test/scripts/run_in_venv_with_cleanup.sh . I don't understand why
it doesn't work in this case...
Thanks,
Klement
Quoting Dave Wallace (2018-11-16 20:39:23)
>I'll see if I can reproduce the issue.
>
>I seem to rec
Hi,
I'd like to know some information about sctp.
Is this fully functional? Or just partly? Actually, I want to try simply with
CLI to verify sctp basic functions now. But it seems that there is no CLI, and
the binary APIs are also imperfect.
Do you have any plan in the next release? Including
Hi all,
Initial code for Sweetcomb project has been upstreamed as a code base.
It is contributed by Cisco (written by Rastislav Szabo) and HuachenTel.
https://gerrit.fd.io/r/#/c/16020/ Initial code commit for Sweetcomb project
But there are many rework to do and new features to be added.
If you a
Hi Dear VPP
I have two question about vpp coredump.
How can I use full-coredump parameter in my startup.conf to make a dump if vpp
crashes?
After crash, where this dump will be saved?
Here is my startup.conf:
unix {
nodaemon
log /tmp/vpp.log
full-coredump
cli-list
Hi Dear VPP
Is there any mechanism in VPP to restrict TCP half-open connection count? If
answer is yes how it can be configured?
Thanks,
Sincerely
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#11312): https://lists.fd.io/g/vpp-dev/message/11312
Hi all,
Please be aware that the code which was chosen as the initial commit of the
sweetcomb project is in PoC quality, I wrote it 2 years ago within few days.
Since then, many things has changed in both VPP and Sysrepo, so it definitely
needs a lot of work until it could be claimed as product
See https://wiki.fd.io/view/VPP/BugReports "Core Files" section.
From: vpp-dev@lists.fd.io On Behalf Of Rubina Bianchi
Sent: Monday, November 19, 2018 8:05 AM
To: vpp-dev@lists.fd.io
Subject: [vpp-dev] VPP coredump question
Hi Dear VPP
I have two question about vpp coredump.
How can I use full-
Hi All,
When I build and run the multithreaded version of icmp_responder, the ping from
VPP side is failing due to "no free slots" available.
Anyone faced this issue earlier and have a quick suggestion to fix this ?
The same thing is working fine with epoll version of icmp_responder.
Appreciate
If your question concerns the host stack, the answer is no.
Florin
> On Nov 19, 2018, at 5:08 AM, Rubina Bianchi wrote:
>
> Hi Dear VPP
>
> Is there any mechanism in VPP to restrict TCP half-open connection count? If
> answer is yes how it can be configured?
>
> Thanks,
> Sincerely
> -=-=-=-
Hi Rubina,
In case the question pertains to transient TCP sessions in ACL plugin - the
answer is no - however a new session takes the least recently used TCP
transient session slot, so there is a natural resource usage balancing.
--a
> On 19 Nov 2018, at 14:08, Rubina Bianchi wrote:
>
> Hi D
Hi!
I have a few questions in the MAP-E/MAP-T area.
First the easy one:
In the src/plugin/map/map.h file, there is a #include .
That works fine in the source tree and the source-tree-based builds.
However, once installed on a system where out-of-tree builds take place,
It makes for an odd system
Hi Rastislav,
Thank you for your code contribution and helpful comments!
You are top contributor to Sysrepo and Sysrepo-VPP.
Hope you can help us a lot on the long development cycle.
Thank you in advance!
Thanks,
Hongjun
From: sweetcomb-...@lists.fd.io [mailto:sweetcomb-...@lists.fd.io] On Behal
Sorry，
the complete data ：
Packet 1
00:08:58:771447: dpdk-input
TenGigabitEthernet6/0/0 rx queue 0
buffer 0x11f3e: current data 14, length 1500, free-list 0, clone-count 0,
totlen-nifb 0, trace 0x0
ext-hdr-valid
l4-cksum-computed l4-cksum-correct l2-hdr-o
Hi Andrew
So what is preallocated-half-open-connections parameters in tcp tag for?
Reference:
https://fdio-vpp.readthedocs.io/en/latest/gettingstarted/users/configuring/startup.html
From: Andrew 👽 Yourtchenko
Sent: Monday, November 19, 2018 5:18 PM
To: Rubina Bi
Hi Hongjun, Rastislav,
1. It is a good suggestion that Yang models keep compatible with IETF Yang
models and Honeycomb Yang models.
2. The same function of srvpp is now implemented in vapi(src\vpp-api\vapi),
and the apis are generated using python.
So, i think, the vapi is the bet
Hi Jon,
> I have a few questions in the MAP-E/MAP-T area.
>
> First the easy one:
>
> In the src/plugin/map/map.h file, there is a #include .
> That works fine in the source tree and the source-tree-based builds.
> However, once installed on a system where out-of-tree builds take place,
> It mak
21 matches
Mail list logo
