Re: [vpp-dev] VPP Repo status?

As a data point, I just did a fresh clone using that URL: https://gerrit.fd.io/r/vpp/ with no hiccups. Ed On Mon, Feb 13, 2017 at 7:57 PM, Bill Fischofer wrote: > Sorry if this has already been answered. I have a clone of the VPP > repo from a few months ago that I

[vpp-dev] VPP Repo status?

Sorry if this has already been answered. I have a clone of the VPP repo from a few months ago that I went to update this evening and got this error message: git pull fatal: unable to access 'https://gerrit.fd.io/r/vpp/': Problem with the SSL CA cert (path? access rights?) Has the repo moved?

Re: [vpp-dev] Use RSS in VPP 17.01

Hi, John/all, Thanks for your pointer, and I am able to bring up my VPP with multiple queues! I am doing a PVP test, which basically I am expecting Traffic Generator -> VPP on Host -> Loopback VM (testpmd) -> VPP on Host -> Traffic Generator. I can see the packets are delivered to the Loopback

[vpp-dev] flow distribute

Hi, ALL I would like to pick out one kind of flow which without five tuple session and lead them to the specified CPU worker. The benifet is that we need no locker in the session creation procedure. What your guys opinion? Regards, Ewan. yug...@telincn.com

Re: [vpp-dev] VPP cannot find interface QLogic 57810

Martin, There have been several DPDK build changes since I was last working on the VPP dpdk driver infra, but the following patch will enable the BNX2X PMD in .../custom-config. +Damjan for his input as this may not be the best way to add the BNX2X PMD to VPP. %< diff --git

Re: [vpp-dev] Failing Out-of-tree Builds

On Fri, Feb 10, 2017 at 9:12 AM, Jon Loeliger wrote: > On Thu, Feb 9, 2017 at 11:16 PM, Akshaya Nadahalli (anadahal) < > anada...@cisco.com> wrote: > >> Hi Jon, >> >> fib_urpf_list.h needs to included inside the source file and need not be >> installed in /usr/include. Thanks

Re: [vpp-dev] libpneum compilation flags

Thanks, Gabriel, and Damjan. It appears to me that the glibc getconf program is using its own mechanisms for determining cache line size, rather than using the information that the kernel has. That is my reading of the glibc code, so I do not believe Damjan you will see any different behavior with

Re: [vpp-dev] VPP performance degradation with multiple nic polling

> On 13 Feb 2017, at 17:34, yusuf khan wrote: > > Hi, > > Comments inline. > > Br, > Yusuf > > On Mon, Feb 13, 2017 at 9:20 PM, Damjan Marion > wrote: > > > On 10 Feb 2017, at 18:03, yusuf khan

Re: [vpp-dev] VPP performance degradation with multiple nic polling

Hi, Comments inline. Br, Yusuf On Mon, Feb 13, 2017 at 9:20 PM, Damjan Marion wrote: > > > On 10 Feb 2017, at 18:03, yusuf khan wrote: > > > > Hi, > > > > I am testing vpp performance for l3 routing. I am pumping traffic from > moongen which is

Re: [vpp-dev] libpneum compilation flags

On 13 Feb 2017, at 17:11, Gabriel Ganne > wrote: Hi Burt, Thank you for your input. I pushed a new version of my commit (https://gerrit.fd.io/r/#/c/4576/) where I tried to do things more clearly. I had a look here

Re: [vpp-dev] Query regarding running worker thread in VPP Debug mode

Hi Damjan, Thank you for the kind reply. Sorry I had a doubt in the code I observed we have support for worker threads in "af_packet" and "netmap" is it used with dpdk platform only. I thought I can add similar support for ODP. Thanks & Regards, Sreejith On 13 February 2017 at 17:51, Damjan

Re: [vpp-dev] Query regarding running worker thread in VPP Debug mode

Hi Sreejith, You cannot use vpp_lite with multiple threads, vpp_lite buffer manager is not thread safe. Thanks, Damjan > On 13 Feb 2017, at 11:28, Sreejith Surendran Nair > wrote: > > Hi All, > > I am working on VPP/ODP integration project. I am trying

[vpp-dev] Query regarding running worker thread in VPP Debug mode

Hi All, I am working on VPP/ODP integration project. I am trying to run VPP in debug mode with multi-thread support. I have configured the startup conf file with "workers" . But as I try to configure the interface and make it up, there is crash occuring due to assertion failure(cpu ). I have