Re: [vpp-dev] crash when pressing TAB on CLI

This may fix the problem: https://gerrit.fd.io/r/#/c/14711/ -- Damjan > On 6 Sep 2018, at 14:32, Dave Barach via Lists.Fd.Io > wrote: > > In future, please refer to https://wiki.fd.io/view/VPP/BugReports > . The issue you’re reporting is not >

Re: [vpp-dev] cmake is on

oticed is there is a buffer overrun bug in qsort.c that > causes cli crashed occasionally. > > Please comment how to fix. Personally I’d like to remove qsort.c, like before. > > Regards, > Kingwel > > From: vpp-dev@lists.fd.io On Behalf Of Damjan Marion > via Lists.Fd

Re: [vpp-dev] cmake is on

LINE_SIZE == 1 << CLIB_LOG2_CACHE_LINE_BYTES, > > === > > I am failing to see translation of Autoconf changes from commit id: > 473f46135c3fd77dad5614215cc279b1164e9a74 to CMake. > > Thanks, > > Nitin > >> On Sun

Re: [vpp-dev] Disable VOM

Today, you can manually edit build-data/platforms/vpp.mk and remove vom from vpp_root_packages, and build packages by yourself... Same applies to japi... diff --git a/build-data/platforms/vpp.mk b/build-data/platforms/vpp.mk index 0687946d..1640c3dc 100644 --- a/build-data/platforms/vpp.mk +++

Re: [vpp-dev] Disable VOM

Plan is to move from current hardcoded model to cmake CPack for packaging and also make VOM separate package as part of that work. At the moment I don't have ETA, it is best effort activity... -- Damjan > On 5 Sep 2018, at 15:15, Ondrej Fabry -X (ofabry - PANTHEON TECHNOLOGIES at > Cisco)

Re: [vpp-dev] hardware offload enable/disable question

Dear Simon, It may be that simply there was no good reason for enabling those offloads. We can re-evaluate case-by-case, if you can provide some analysis what are the needed code changes in the vpp to consume specific offload and what is perf loss or gain doing that... Thanks, — Damjan >

Re: [vpp-dev] cmake is on

lib/libvppcom.so.18.10 lib/libvlibmemoryclient.so.18.10 lib/libvlib.so.18.10 > lib/libsvm.so.18.10 lib/libvppinfra.so.18.10 -lm -ldl -lrt -lpthread && : > lib/libvppcom.so.18.10: undefined reference to `mheap_put' > lib/libvlibmemoryclient.so.18.10: undefined reference to `mheap_get_align

[vpp-dev] cmake is on

Dear all, We just switched from autotools to cmake and retired all autotools related files in src/. All verify jobs are ok, and we also tried it on 3 different x86 and 2 different ARM Aarch64 machines. Due to blast radius, i will not be surprised that some small issues pop out, but i don't

Re: [vpp-dev] Destination Options processing in VPP

-- Damjan > On 21 Aug 2018, at 18:51, Tom Herbert wrote: > > On Tue, Aug 21, 2018 at 9:24 AM, Damjan Marion > wrote: >> >> Hi Tom and welcome to vpp-dev, >> >> >>> On 21 Aug 2018, at 16:28, Tom Herbert wrote: >>> >>> Hello, >>> >>> I have some questions regarding

Re: [vpp-dev] Destination Options processing in VPP

Hi Tom and welcome to vpp-dev, > On 21 Aug 2018, at 16:28, Tom Herbert wrote: > > Hello, > > I have some questions regarding Destination Options processing in VPP. > Basically, I'd like to know they are properly supported per RFC8200. Probably not. > I > not, then I'd like to request the

Re: [vpp-dev] num-mbufs

> On 20 Aug 2018, at 23:44, Bly, Mike wrote: > > Hello, > > I am looking to understand the math and reasoning behind the 16K DPDK MBUFs > per socket allocation. It is more educated guess than reasoning and math. > > From: vpp/src/plugins/dkdp/device/dpdk.h > > #define NB_MBUF

Re: [vpp-dev] CMake

indstring $(MAKECMDGOALS),verify pkg-deb pkg-rpm test test-debug),) export vpp_uses_cmake?=yes endif > > I don't see vpp-api mentioned in src/CMakeLists.txt. Should it be > mentioned? It waits for volunteer to take care for vpp-api :) > > Thanks, > Klement > > On S

Re: [vpp-dev] CMake

> On 18 Aug 2018, at 17:36, Andrew Pinski wrote: > > On Sat, Aug 18, 2018 at 3:38 AM Damjan Marion via Lists.Fd.Io > mailto:dmarion=me@lists.fd.io>> wrote: >> [snip] >> Feedback, issue reports and contributions to get CMake be a full replacement >> for

[vpp-dev] CMake

Dear all, Yesterday we merged a patch which introduces CMake build system in VPP. https://git.fd.io/vpp/commit/?id=612dd6a9 It is initial patch, and additional work is needed, but in general it manages to compile VPP binaries significantly faster than what we have today with autotools. In

Re: [vpp-dev] DPDK plugin - port ID and index

Are you on some old vpp version? We did recently what i think you are asking for, port_id is now decoupled from device_index... -- Damjan > On 17 Aug 2018, at 10:15, Andrzej Ostruszka wrote: > > Hello all > > I'm new to VPP so please bear with my ignorance in its >

Re: [vpp-dev] Bonding error -- uio_interrupt

interesting, works fine for me on c3000, but i use vfio. Try with vfio, either with enabling iommu or using noiommu mode (kernel 4.4+) -- Damjan > On 17 Aug 2018, at 03:22, carlito nueno wrote: > > Hi, > > I am trying to bond two Intel 82599 on Intel Atom C3000. But I am > getting

Re: [vpp-dev] Regarding symmetric RSS hash with DPDK plugin

you should be able to do that by enabling same number of rx queues to number of workers +1 (main thread) and set rx placement to match tx queue assignment. VPP statically maps on tx side queue to thread, so main thread is always using queue 0, worker 0 uses queue 1and so on Issue is that

Re: [vpp-dev] Performance and CLI response degradation with inactive port

Can you share more details on hardware used? Both Dave and me noticed this on denverton device (Atom C3xxx) with onboard 10G ports. I was able to repro this with dpdk testpmd, so (at least our issue) is not VPP related. -- Damjan > On 9 Aug 2018, at 00:45, j...@yeager1.com wrote: > >

Re: [vpp-dev] Is plugin compilation out of source tree still supported by vpp?

It might be that documentation is outdated, but we definitely build sample plugin out-of-tree as part of each commit verify job... -- Damjan > On 16 Aug 2018, at 10:48, ololjiiu373...@163.com wrote: > > Hi, all > > I'm a newbie of vpp and tried to compile sample_plugin out of source tree. I

Re: [vpp-dev] memif questions/comments

> On 13 Aug 2018, at 04:43, Jeff wrote: > > Hello VPP folks, Hello, > > I have several questions/comments on memif and libmemif. > > 1) I believe "mq[x].last_tail = 0" is missing from > memif_init_regions_and_queues(). Aer you referring to vpp or libmemif? We have same function name at

Re: [vpp-dev] tx-errors on VPP controlled dpdk device

Try to dump hardware counters with "show hardware" That my give you more information what's wrong... As you are using VF, my wild guess is that you may have promisc mode disabled. Try to dump PF details with 'ip link show dev XXX" -- Damjan > On 1 Aug 2018, at 00:52,

Re: [vpp-dev] Manual patch verify request: gerrit 13769

Is incremental checksum really needed here, or we can just move to new vectorized checksum calculation (already used in ip-input)? -- Damjan > On 27 Jul 2018, at 22:17, Dave Barach via Lists.Fd.Io > wrote: > > Thanks very much... Dave > > From: Tina Tsou mailto:tina.t...@arm.com>> >

Re: [csit-dev] [vpp-dev] Parallel test execution in VPP Test Framework

Dear All, My personal preference is that make test framework implements cpu assignment code. It should't be rocket science to parse /sys/devices/system/cpu/online and give one cpu to each instance. It will also help to test framework to understand how many parallel jobs it can run...

Re: [vpp-dev] Regarding /var/run/.rte_config

Dear Prashant, "git blame" is your friend. He can easily tell you which patch introduced that functionality. And than you can try to cherry-pick it on top of 18.01 -- Damjan > On 28 Jul 2018, at 07:27, Prashant Upadhyaya wrote: > > Hi again Damjan, > > I am currently using VPP release

Re: [vpp-dev] Regarding /var/run/.rte_config

Dear Prashant, Try "pcap rx trace" and "pcap tx trace" command. https://git.fd.io/vpp/tree/src/plugins/dpdk/device/cli.c#n373 Also please note that VPP packet generator (pg) supports both pcap play and capture... -- Damjan > On 26 Jul 2018, at 12:42, Prashant Upadhyaya wrote: > > Hi

Re: [vpp-dev] Regarding /var/run/.rte_config

Dear Prashant, We had lot of operational issues with dpdk leftover files in the past, so we took special care to made them disappear ASAP. Even if they are present you will not be able to use secondary process, we simply don't support that use case. Secondary process will not be able to access

Re: [vpp-dev] Sample plugin doest not show up with vpp 18.07

variable in sample.c file or if > we remove the key word extern in sample.h. I have tried removing extern and > it works but defining sample_main in .c file should also work. > > > > > On 2018-07-20 19:02, Damjan Marion via Lists.Fd.Io wrote: > >> >>

Re: [vpp-dev] Sample plugin doest not show up with vpp 18.07

This should be the proper fix for your issue: https://gerrit.fd.io/r/#/c/13589/ Please confirm... -- Damjan > On 20 Jul 2018, at 15:52, abdul.ma...@sofioni.com wrote: > > When I ran vpp 18.07 in interactive mode I found that vpp was unable to load > sample_plugin due to an error of

Re: [vpp-dev] All master/latest patches currently failing validation...

It failed again for some other reason, but that patch simply cannot be wrong, it can just not fix the problem so i merged it and rebased few patches. -- Damjan > On 17 Jul 2018, at 22:53, Dave Barach via Lists.Fd.Io > wrote: > > We missed a step when pulling the release throttle which

Re: [vpp-dev] Revert of gerrit 13408 / "vppinfra: AVX2 blend" in progress..

Version 1 of the same patch failed properly, for the same error message, then I removed permute inline functions and left blend as i missed that same error happens also for blend. Not sure what exactly happened, but it doesn't look like it is not configured for voting as it worked properly

Re: [vpp-dev] Is VPP IPSec implementation thread safe?

OK, yes, that is needed as it will take care for buffers which are cloned. Potential optimisation here would be to reuse buffer if vlib_buffer_t->n_add_refs != 0. -- Damjan > On 6 Jul 2018, at 12:27, Kingwel Xie wrote: > > Sorry, Damjan. Maybe I confused you. > > This is what I am talking

Re: [vpp-dev] Is VPP IPSec implementation thread safe?

We don't use recycle anymore (except at one place), mainly due ot the issue how dpdk works. -- Damjan > On 6 Jul 2018, at 11:27, Kingwel Xie wrote: > > Well, there is a vector named recycle to remember all old buffers, which > consequently means a lot of mem resize, mem_cpy when vector rate

Re: [vpp-dev] Loop a port/vlan? #vpp

I guess xconnect with same sub-interface will just work, but never tried. I.e. set interface l2 xconnect FooEthernet0/0.100 FooEthernet0/0.100 -- Damjan > On 5 Jul 2018, at 23:26, crypto.tr...@gmail.com wrote: > > Hi, > > Looking for a way to setup a remote loop for testing. In my

Re: [vpp-dev] Interface up Stuck for Mellanox CX-4 VF with VPP master and DPDK 18.05 on aarch64

Capturing backtrace for each thread might be good start. Thanks! -- Damjan > On 3 Jul 2018, at 20:03, Sirshak Das wrote: > > Hi all, > > I am facing an issue with my VPP installation on Qualcomm Centriq with > Mellanox MT27700 [CX-4] card. The MOFED versions I have is 4.3-3.0.2.1 > and

Re: [vpp-dev] Is VPP IPSec implementation thread safe?

> On 3 Jul 2018, at 02:36, Kingwel Xie wrote: > > Hi Damjan, > > Thanks for the heads-up. Never come to that. I’m still thinking it is > acceptable if we are doing IPSec. Buffer copying is a significant overhead. What i wanted to say by copying is writing encrypted data into new buffer

<    2   3   4   5   6   7