Re: [vpp-dev] number of csit-vpp jobs failing on vpp master branch - RCA wip

Can it be that you're building the packages with tls support and afterwards you’re installing them on a host without libmbedtls-dev? Florin > On Mar 6, 2018, at 7:51 AM, Marek Gradzki -X (mgradzki - PANTHEON > TECHNOLOGIES@Cisco) wrote: > > + hc2vpp (all hc2vpp csit jobs

Re: [vpp-dev] VPP As A Router Between Namespaces - 10ms latency

I encountered the similar issue before. Try replacing iperf3 with iperf2. Hao On 3/6/18, 8:34 AM, "vpp-dev@lists.fd.io on behalf of Sara Gittlin" wrote: Also the throughput is very poor - iperf3 TCP ~ 2Mbps what is wrong here ?

Re: [vpp-dev] VPP DPDK build failure with Mellanox interface(aarch64)

> Thanks for the clarification. > I'm trying to understand if there is a way to avoid the branch build breakage. You could imagine that you could be more clever estimating the chance of a conflict. In this particular case though, there was no overlap in changeset, so I'd imagine that automatic

Re: [vpp-dev] VPP DPDK build failure with Mellanox interface(aarch64)

Ole, That is what I thought, but I wanted to see if there's any way to close the gap. In this case it is clear that the cost of automatic detection or avoidance is way to high.  I'm fine with leaving things as they are. Thanks, -daw- On 03/06/2018 02:21 PM, Ole Troan wrote: Thanks for the

Re: [vpp-dev] VPP DPDK build failure with Mellanox interface(aarch64)

Dave, > That is what I thought, but I wanted to see if there's any way to close the > gap. In this case it is clear that the cost of automatic detection or > avoidance is way to high. I'm fine with leaving things as they are. One tooling improvement we could make, would be to send out a big

Re: [vpp-dev] VPP DPDK build failure with Mellanox interface(aarch64)

Yep.  Ed Kern and I are investigating how to make that happen. Thanks, -daw- On 03/06/2018 05:09 PM, Ole Troan wrote: Dave, That is what I thought, but I wanted to see if there's any way to close the gap. In this case it is clear that the cost of automatic detection or avoidance is way to

Re: [vpp-dev] vpp-comparison-18.01 - Invitation to comment

We don't have anything right now, but its in my test list to run this week. I can provide some input for what I'm getting for results then. -Christian, - Original Message - From: "Anita Tragler" To: "Thomas F Herbert" , "Christian

Re: [vpp-dev] VPP DPDK build failure with Mellanox interface(aarch64)

Hi, verify of 10920 would fail if it was rebased before submission. JVPP generation was updated recently to use service definitions Instead of inferring message type based on its name. 10920 was verified against previous version. Here is updated version of 10920 with updated service

[vpp-dev] VPP performance trending and analysis - need feedback

Hi, We’ve been working with Tibor and few other csit-dev and vpp-dev folks on the design to improve VPP performance trend tracking and automate anomaly detection (regression/progression). Result of this work is a design write-up published here:

Re: [vpp-dev] number of csit-vpp jobs failing on vpp master branch - RCA wip

+ hc2vpp (all hc2vpp csit jobs affected) Marek From: vpp-dev@lists.fd.io [mailto:vpp-dev@lists.fd.io] On Behalf Of Maciek Konstantynowicz (mkonstan) Sent: 6 marca 2018 15:55 To: vpp-dev@lists.fd.io Cc: csit-...@lists.fd.io Subject: [vpp-dev] number of csit-vpp jobs failing on vpp master branch

[vpp-dev] VPP with namespace BW 0Mbits/sec

I tried the vpp namespace example and tested with iperf3 for performance benchmark, but I am getting bandwidth as 0Mbits/sec. Why VPP is performing poorly when compared to OVS. Is ovs better than VPP? Should I go with OVS? Regards, Swathin

[vpp-dev] 18.04 API freeze in two weeks

A friendly early warning folks: API freeze for the 18.04 release is in two weeks! Milestone Date Deliverables F0 2018-03-21 APIs frozen. Only low-risk changes accepted on main branch. Cheers, Chris

Re: [vpp-dev] VPP DPDK build failure with Mellanox interface(aarch64)

Hi Marek, Thanks for the analysis.  VPP's gerrit "Submit Type" is "Rebase if Necessary".  This means that occasionally we may encounter build breakage due to dependent patches.  Changing the type to "Fast forward only" is NOT worth the extra time/effort to avoid this. In general, dependent

[vpp-dev] vpp_main with iperf3 not working #vpp

[Edited Message Follows] Hi, Had anyone tried the newer version of vpp with iperf3? When I tried the latest release of VPP, I am getting some weird result. The vpp_main is using 100% CPU(suspecting that it is going into a never-ending loop). I tried the router namespace example just to check

[vpp-dev] number of csit-vpp jobs failing on vpp master branch - RCA wip

Heads-up - resolution in progress.. -Maciek Begin forwarded message: From: Maciek Konstantynowicz > Subject: number of csit-vpp jobs failing on vpp master branch - RCA wip Date: 6 March 2018 at 14:54:39 GMT To:

Re: [vpp-dev] VPP DPDK build failure with Mellanox interface(aarch64)

Dave, these patches were not dependent, but rather in conflict. And this is the responsibility of merge job to detect them. If such situation happens patch should be reverted. So I think everything was done right. I am totally fine with “Rebase if necessary”. But personally I often rebase

Re: [vpp-dev] VPP DPDK build failure with Mellanox interface(aarch64)

Marek, Thanks for the clarification. I'm trying to understand if there is a way to avoid the branch build breakage. Cheers, -daw- On 3/6/2018 11:12 AM, Marek Gradzki -X (mgradzki - PANTHEON TECHNOLOGIES@Cisco) wrote: Dave, these patches were not dependent, but rather in conflict. And

[vpp-dev] VPP As A Router Between Namespaces - 10ms latency

Hi, i have 2 namespaces connected with veth-pairs to vpp - see setup here [https://wiki.fd.io/view/VPP/Configure_VPP_As_A_Router_Between_Namespaces] i see very big latency ~10ms when i ping between the 2 namespaces i expected to see latency in the order of 10's us

Re: [vpp-dev] VPP As A Router Between Namespaces - 10ms latency

Also the throughput is very poor - iperf3 TCP ~ 2Mbps what is wrong here ? On Tue, Mar 6, 2018 at 6:20 PM, Sara Gittlin wrote: > Hi, > i have 2 namespaces connected with veth-pairs to vpp - see setup here >

Re: [vpp-dev] subunit requirement

Hi Tom, I assume you are talking about the rpm packaging, and not the RPM_DEPENDS from the root Makefile, right ? If so then feel free to remove it, as I believe it is only needed to run the tests. Otherwise I still believe it should be part of the "make install-dep" target. Best regards, On 5

[vpp-dev] No rule to make target 'my_plugin/my_plugin.api.json',

Hi, i created a plugin - just copy/rename an existing folder to the src/plugin do the required changes in : src/configure.ac src/plugins/Makefile.am src/plugins/my_plugin.am and the build was ok !!! and my-plugin was loaded and running !!! then i did a minor change in my-plugin (and then

Re: [vpp-dev] No rule to make target 'my_plugin/my_plugin.api.json',

OK - Solved On Tue, Mar 6, 2018 at 3:35 PM, Sara Gittlin wrote: > Hi, > i created a plugin - just copy/rename an existing folder to the src/plugin > do the required changes in : > src/configure.ac > src/plugins/Makefile.am > src/plugins/my_plugin.am > > and the build

[vpp-dev] debugCli crash during deletion of a classifiersession

I had tried below commands and it resulted in a seg-fault: classify table mask l3 ip4 src  proto   l4 src_port dst_port classify session table-index 0 hit-next 10 match l3 ip4 src 33.44.33.10  opaque-index 5 classify session table-index 0 hit-next 10  opaque-index 5 del last command with 'del'