Re: [vpp-dev] IPsec crash with async crypto

Hi Matt, Did you try checking if quic plugin is loaded, just to see if there’s a connection there. Regards, Florin > On May 26, 2021, at 3:19 PM, Matthew Smith via lists.fd.io > wrote: > > Hi, > > I saw VPP crash several times during some tests that were running to evaluate > IPsec perfo

Re: [vpp-dev] unformat_vnet_uri not implemented following RFC 3986

Hi, That unformat function and the associated session layer apis (e.g., vnet_connect_uri) are mainly used for testing and their production use is discouraged. Provided that functionality is not lost, if anybody wants to do the work, I don’t see why we wouldn’t want to make the unformat functio

Re: [vpp-dev] IPsec crash with async crypto

anch in case there were > recent/pending patches that people know of that might be relevant. That quic > commit is from about 2 weeks ago, which is the last time I merged upstream > changes. > > Thanks, > -Matt > > > On Wed, May 26, 2021 at 5:58 PM Florin Coras

Re: [vpp-dev] VCL app requires source address/interface control due to loopback

Hi Sastry, I thought you were looking at vrfs in older vpp versions. Both source and vrf are supported by vcl on master/2106 and both can be configured using vppcom_session_attr. See VPPCOM_ATTR_SET_LCL_ADDR and VPPCOM_ATTR_SET_VRF. Regards, Florin > On May 28, 2021, at 3:47 AM, Sastry Sista

Re: [vpp-dev] VCL app requires source address/interface control due to loopback

Hi Sastry, Check if vppcom_app_create returned an error. Regards, Florin > On May 31, 2021, at 7:04 AM, Sastry Sista wrote: > > Hi Florin, > Thank you. Yes. I need to upgrade. Or I am thinking of > customizing in fdio 20.05 release. > > Small question, vcl_test_client i

Re: [vpp-dev] VCL app requires source address/interface control due to loopback

Hi Sastry, vppcom_app_create() can return an error even if binary api attachment is successful. To check if application has successfully attached to vpp’s session layer, see “show app”. To debug vcl, set VCL_DEBUG env variable to at least 1. Connects, if delivered by vcl to vpp, are handled i

Re: [vpp-dev] VCL app requires source address/interface control due to loopback

Not entirely sure what happens there but retval lower is -17, which is invalid remote ip. Make sure your code correctly initializes the server address. vclEndptFromAddress you seem to be using is meant to work with Envoy addresses so double check the changes you’ve mead to it. Alternatively, jus

Re: [vpp-dev] VCL app requires source address/interface control due to loopback

Hi Sastry, Inline. > On May 31, 2021, at 11:46 AM, Sastry Sista wrote: > > Hi Florin, > Thank you for the help. I guess its due to > INVALID_RMP_IP which is 17. Will check why its going as for IP. We are > filling it fine. > > So, My next step would be to implement

Re: [vpp-dev] VCL app requires source address/interface control due to loopback

Hi Sastry, Inline. > On Jun 1, 2021, at 11:48 AM, Sastry Sista wrote: > > Hi Florin, > >Thank you for the bit more clarity. I have few > question further to the items: > > 1. In a single worker case, What is the difference between session_handle > from vppcom_sessio

Re: [vpp-dev] Pools allocation per numa node

Hi Marina, You might be able to with a VLIB_MAIN_LOOP_ENTER_FUNCTION handler. Regards, Florin > On Jun 2, 2021, at 10:57 AM, marina.vasilev...@insidepacket.com wrote: > > Hi, > Is it possible to create a fixed size pool on the worker's numa node? > I am using pool_init_fixed. > I have worker

Re: [vpp-dev] Pools allocation per numa node

Hi Marina, In that case you should be good. If you think the os is not mmap-ing memory on the right numa, maybe try clib_mem_set_numa_affinity/set_mempolicy. Also note that “show memory” shows memory allocated through clib_mem_* functions but, as you’ve noticed, pool_init_fixed directly call

Re: [vpp-dev] VCL app requires source address/interface control due to loopback

Hi Sastry, Inline. > On Jun 3, 2021, at 5:21 AM, Sastry Sista wrote: > > Hi Florin, > Thank you so much and its really great and timely inputs > you provided and no dictionary words can really express my sincere > appreciation. Emotionally can be expressed. Truly amazing.

Re: [vpp-dev] Regarding TCP Keepalives

Hi Vijay, VPP’s tcp implementation does not support keepalives so I’m assuming you’d like to intercept/drop packets that flow through vpp. As far as I know, there’s no straight forward way to do that. So you might have to implement a tcp connection tracker and some heuristic to detect keepaliv

Re: [vpp-dev] Regarding TCP Keepalives

eepalives" ==> I assume > VPP does not initiate one but can respond to any KA sent by the peer? > > Is this understanding right? > > > Regards. > > On Wed, Jun 9, 2021 at 8:00 PM Florin Coras <mailto:fcoras.li...@gmail.com>> wrote: > Hi Vijay,

Re: [vpp-dev] dtls connect error with custom crypto engine #vpp-dev

Hi, Yup, let’s make it 28. Can you push a patch? Regards, Florin > On Jun 16, 2021, at 8:22 PM, jiangxiaom...@outlook.com wrote: > > Hi Florin, > I tried dtls proto with my custom crypto engine, and got error with > dtls_connect. Vpp bracn is 21.06-rc2, here is the debug log: > > Breakpo

Re: [vpp-dev] VPP host stack thread ownership #hoststack

Hi Olivia, Inline. > On Jun 21, 2021, at 12:51 AM, Olivia Dunham wrote: > > Hi Florin, > > Digging further into this, I got to know that only the main core handles > `vnet_connect`. The TCP connection is owned by main core while it is in > active open state. Yes, that’s accurate. > But

Re: [vpp-dev] #vppcom, #vnet #vpp

Hi Nikhil, Use two listeners, i.e., call vnet_listen twice once with the ipv4 address and once with the ipv6 address. Regards, Florin > On Jun 22, 2021, at 7:26 AM, nikhil subhedar wrote: > > Hi All, > i am referring to echo_server code of src/plugins/hs_apps/. > My requirement , > 1)my tc

Re: [vpp-dev] why vlib_buffer_push_ip4 not support fragmentation and set df flag for tcp?

Fragmentation is expensive. Therefore, because tcp originates the packets locally, we do not want it to exceed the interface’s mtu. If you want to force larger bursts from tcp, try enabling tso if the egress interface supports it. Any particular reason why you’d like tcp to use such a large mss

Re: [vpp-dev] TCP packets are not reaching to TCP graph node (tcp46_input_inline) #vpp-dev #vppcom #vnet

Hi Nikhil, That should work. Check that the arc from your plugin to tcp are setup properly and maybe do a trace. Regards, Florin > On Jul 5, 2021, at 12:49 AM, nikhil subhedar wrote: > > Hi All, > > in our product we have plugin which will receive all the TCP packets and > based on the t

Re: [vpp-dev] Prefetches improvement for VPP Arm generic image

+1 Florin > On Jul 5, 2021, at 4:27 AM, Dave Barach wrote: > > “Going across the whole codebase and replacing prefetch macros is something > we should definitely avoid.” > > +1, for sure... FWIW... Dave > > From: vpp-dev@lists.fd.io > O

Re: [vpp-dev] Prefetches improvement for VPP Arm generic image

+1 Florin > On Jul 14, 2021, at 10:47 AM, Damjan Marion via lists.fd.io > wrote: > > > I spent a bit of time to look at this and come up with some reasonable > solution. > > First, 128-byte cacheline is not dead, recently announced Marvell Octeon 10 > have 128 byte cacheline. > > In curre

Re: [vpp-dev] question on gtpu_input graph node

Hi Andreas, Actually thanks for the link! Noticed you guys keep a set of vpp patches and some of them have not been merged yet. In particular, this [1] looked really useful and subsequently realized it was submitted but not merged because it failed checkstyle. Feel free to insist when that hap

Re: [vpp-dev] vppcom: why __vcl_worker_index is thread local? #vpp

It’s done on purpose in order to avoid constant locking. Applications should accept new session on the right thread. If you plan to distribute the load across multiple workers, then just have them all listen on the same ip:port tuple and vpp will load balance. Florin > On Nov 22, 2018, at 6:5

Re: [vpp-dev] How to actively close the client connections in http server? #vnet

Ow, so the issue is the reset. Could you try to call stream_session_disconnect instead of stream_session_cleanup in the handle? Florin > On Nov 22, 2018, at 6:51 AM, Andreas Schultz > wrote: > > Hi, > > Florin Coras mailto:fcoras.li...@gmail.com>> schrieb > am

Re: [vpp-dev] About in-band telnet/ssh support of VPP

We’re working on adding support via LDP/VCL but anything not finished is pretty much unusable. We’re trying to finish it as soon as possible but no idea if it’ll make it into 19.01 Florin > On Nov 27, 2018, at 6:08 AM, tianye wrote: > > That is a in-band solution. > No fun :-) > > > 在 2018年

Re: [vpp-dev] vppcom: why __vcl_worker_index is thread local? #vpp

I am working on enabling forking with LDP but keep in mind that we mainly support it for testing purposes. That is, it can’t work with statically linked applications and we don’t plan on supporting all possible socket/setsockopts/getsockopts/fcntl options. Florin > On Nov 28, 2018, at 3:15 AM

Re: [vpp-dev] Verify issues (GRE)

Hi Juraj, Those tests exercise the stack in vpp, so they don’t use up linux stack ports. Moreover, both cut-through and through-the-stack tests use self.shm_prefix when connecting to vpp’s binary api. So, as long as that variable is properly updated, VCL and implicitly LDP will attach and use

Re: [vpp-dev] Verify issues (GRE)

> worker process is not handled in this case, though I wonder why > run_in_venv_with_cleanup.sh doesn't clean it up. > > Juraj > > From: Florin Coras [mailto:fcoras.li...@gmail.com] > Sent: Thursday, November 29, 2018 5:04 PM > To: Juraj Linkeš > Cc: Ole Troa

[vpp-dev] sshd with vpp's host stack and LD_PRELOAD

Folks, I know there has been quite some interest in running sshd with the host stack, so here’s a quick update on where that stands. Dave and I have been working on supporting applications that fork children with vcl and, to actually test the code, we’ve decided to run sshd on top of it. Bec

Re: [vpp-dev] VPP/Envoy integration status

Hi Dai, No. The release plan is just a statement of intent. The actual release notes are here [1]. I know there are ongoing efforts in this area but I’m not sure about their current status. Florin [1] https://git.fd.io/vpp/tree/RELEASE.md > On Dec 6, 2018, at 2:34 PM, via Lists.Fd.Io > w

Re: [vpp-dev] regarding cross compiling

Let me reiterate what Dave said: the committer community saw real value in moving to cmake. Those extra build minutes are subtracted from the lives of those who build vpp on a daily basis. Florin > On Dec 19, 2018, at 8:46 AM, Andrew Pinski wrote: > > On Wed, Dec 19, 2018 at 11:29 AM Dave Ba

Re: [vpp-dev] VPP Failing (all?) Verify Jobs

Hi Jon, Yeah, it’s an osleap problem. As far as I can tell, the issue is not with make install-dep step but with this one [1]. Not entirely sure about the solution but maybe a “-f” would force the installation of the newer package? Marco, Vanessa, Ed, any other suggestions? Florin [1] https:

Re: [vpp-dev] VPP Failing (all?) Verify Jobs

Paul came up with a better fix [1]. Rebasing of the patches should solve the verify problems now. Florin [1] https://gerrit.fd.io/r/#/c/16631/ > On Dec 27, 2018, at 9:54 AM, Florin Coras via Lists.Fd.Io > wrote: > > Hi Jon, > > Yeah, it’s an osleap problem. As far as I c

Re: [vpp-dev] Sequence Number Checking in TCP Protocol

Hi Brayan, I’m not entirely sure I understand your question. Obviously, we have sequence validation in tcp as per rfc 793. For details, see tcp_segment_validate in tcp_input.c. As part of that function, we also check for paws as per rfc 1323/7323. Hope this helps, Florin > On Dec 29, 2018,

Re: [vpp-dev] Sequence Number Checking in TCP Protocol

he wants RFC 6528. > > Jim > >> On Dec 29, 2018, at 10:59 AM, Florin Coras wrote: >> >> Hi Brayan, >> >> I’m not entirely sure I understand your question. Obviously, we have >> sequence validation in tcp as per rfc 793. For details, see >> t

Re: [vpp-dev] Sequence Number Checking in TCP Protocol

> On Dec 29, 2018, at 8:26 PM, Jim Thompson wrote: > > > >> On Dec 29, 2018, at 6:42 PM, Florin Coras wrote: >> >> Hi Jim, >> >> That has to do with the initial sequence number generation. > > Understood. Thus the title of "Defe

Re: [vpp-dev] VPP 19.01 + SPDK

Hi Ram, Tomasz cc'ed, amongst others, have been working on integrating SPDK with VPP's host stack. Maybe the patch here [1] can provide some answers. Florin [1] https://review.gerrithub.io/c/spdk/spdk/+/417056 > On Jan 2, 2019, at 2:05 PM, Ramaraj Pandian wrote: > > Hello, > > I am new

Re: [vpp-dev] Sequence Number Checking in TCP Protocol

Hi Jim, Here’s the patch [1]. Regards, Florin [1] https://gerrit.fd.io/r/#/c/16675/ > On Dec 29, 2018, at 10:59 PM, Florin Coras via Lists.Fd.Io > wrote: > > > >> On Dec 29, 2018, at 8:26 PM, Jim Thompson wrote: >> >> >> >>>

Re: [vpp-dev] vpp + spdk - spdk crash on getting work item

Ramaraj, You’ll have to check with the SPDK guys, but I think they’re still based on ubuntu 18.07. If you’re trying to run SPDK with vcl, so not using the patch that I previously pointed you to, probably it won’t work. VCL needs explicit configuration of workers and, from the crash lower, I

Re: [vpp-dev] wireshark vpp dispatch trace dissector merged

Awesome! Florin > On Jan 17, 2019, at 5:11 AM, Dave Barach via Lists.Fd.Io > wrote: > > I’m pleased to announce that our dispatch trace wireshark dissector has been > merged. At some point in the indefinite future, everyone’s favorite distro > will include a copy of wireshark which knows how

Re: [vpp-dev] RFC: buffer manager rework

Awesome! Looking forward to using it in the host stack ;-) Florin > On Jan 25, 2019, at 9:08 AM, Damjan Marion via Lists.Fd.Io > wrote: > > > I am very close to the finish line with buffer management rework patch, and > would like to > ask people to take a look before it is merged. > > htt

Re: [vpp-dev] Packet copy in plugins/nsim

VPP typically works best if configured with a relatively small number of buffers. On the other hand, nsim can induce a large amount of delay, so the buffers cannot be used to temporarily store the data. Florin > On Jan 29, 2019, at 3:19 AM, Raj wrote: > > Hello all, > > While I was browsing

Re: [vpp-dev] VPP send map-register with R=0 on LISP

Does this [1] solve the issue? Florin [1] https://gerrit.fd.io/r/#/c/17151/ > On Jan 29, 2019, at 4:34 PM, Yosvany wrote: > > VPP with LISP send the reachable bit to 0. When use one iid to vni different > that 0. > > How can change the reachable bit to 1 on map-register. > > I am testin

Re: [vpp-dev] Packet copy in plugins/nsim

Hi Raj, > On Jan 30, 2019, at 6:49 AM, Raj wrote: > > Hello Florin, > > Thanks a lot for your reply. > > On Tue, Jan 29, 2019 at 9:15 PM Florin Coras wrote: >> >> VPP typically works best if configured with a relatively small number of >> buffers.

Re: [vpp-dev] VPP delete map-reply from cisco router

Yosvany, The trace you provided shows that the packet was processed okay and then dropped. Do you see any lisp errors if you do “show error” or in syslog? It may turn out to be that we don’t have a parser for some record in the map-reply. Note that testing has been done exclusively with ODL Li

Re: [vpp-dev] VPP delete map-reply from cisco router

e new > wireshark extensions? > > On Wed, Jan 30, 2019 at 1:23 PM Florin Coras <mailto:fcoras.li...@gmail.com>> wrote: > Yosvany, > > The trace you provided shows that the packet was processed okay and then > dropped. Do you see any lisp errors if you do “show error”

Re: [vpp-dev] VPP send map-register with R=0 on LISP

de enero de 2019 8:37:45 PM GMT-05:00, Florin Coras > mailto:fcoras.li...@gmail.com>> escribió: > Does this [1] solve the issue? > > Florin > > [1] https://gerrit.fd.io/r/#/c/17151/ <https://gerrit.fd.io/r/#/c/17151/> > > On Jan 29, 2019, at 4:34 PM, Yosvany

Re: [vpp-dev] VPP send map-register with R=0 on LISP

remote 192.168.76.60 >14401This is other cisco router sonly working as > XTR > vpp# > vpp# > vpp# > vpp# > vpp# show one st > statistics status > vpp# show one statistics details > [src-EID, dst-EID] [loc-rloc, rmt

Re: [vpp-dev] Packet copy in plugins/nsim

Hi Raj, Partly. Check “show buffers” Florin > On Jan 31, 2019, at 1:04 AM, Raj wrote: > > Hi Florin, > > On Wed, Jan 30, 2019 at 10:01 PM Florin Coras wrote: > >> Because if it can work with all of its buffers cached, without flushing them >> to main memor

Re: [vpp-dev] VPP 19.01 release is out!

Awesome! Thanks, Andrew! Florin > On Jan 31, 2019, at 1:05 PM, Andrew Yourtchenko wrote: > > Hi all, > > I am happy to announce that 19.01 release is now available. > > Release artificats can be found on both Nexus and Packagecloud. > > Thanks to all the contributors and committers, and also

[vpp-dev] vpp-verify-master-centos failures

It seems centos verify jobs are failing with errors of the type: 00:27:16 FAILED: vnet/CMakeFiles/vnet.dir/span/node.c.o 00:27:16 ccache /opt/rh/devtoolset-7/root/bin/cc -DWITH_LIBSSL=1 -Dvnet_EXPORTS -I/w/workspace/vpp-verify-master-centos7/src -I. -Iinclude -Wno-address-of-packed-member -m

Re: [vpp-dev] VPP send map-register with R=0 on LISP

e any Information > Show one eid-table remote > > Conclusion: Cisco XTR receive a bad Map-Reply from VPP. > > · Another problem is that VPP is making a Loop sendingmap-request > to MR/MS. In this map-request can se a map-reply. > > > De: Florin Coras

Re: [vpp-dev] L2 with LISP

end you more details. > > Can send me one example how implement LISP with L2 and bd, (What comand need > use and what make MAC ADDRES TO RLOC???) > > > > > De: vpp-dev@lists.fd.io <mailto:vpp-dev@lists.fd.io> > [mailto:vpp-dev@lists.fd.io <mailto:vpp-de

Re: [vpp-dev] vpp-verify-master-centos failures

super fast turning around these changes, so hopefully in a >>> couple hours. >>> >>> Apologies for the trouble. We have seen a 4-6x increase (depending on OS) >>> in the last 5 months >>> and so it finally started pinching my memory reserva

Re: [vpp-dev] iperf3 with vcl

Hi Ram, What os and what vpp version? We’re constantly running iperf3 in our CI in ubuntu 18.04. Thanks, Florin > On Feb 20, 2019, at 6:07 PM, Ramaraj Pandian wrote: > > I am trying to run iperf server and client to measure performance between two > vpp instances as per “https://wiki.fd.io/v

Re: [vpp-dev] iperf3 with vcl

Hi Florin, Its vpp 19.01 on centos, seems like there is a patch available, I > will try that. Thanks. > > From: vpp-dev@lists.fd.io [mailto:vpp-dev@lists.fd.io] On Behalf Of Florin > Coras > Sent: Thursday, February 21, 2019 8:40 AM > To: Ramaraj Pandian > Cc: vpp-dev@lists

Re: [vpp-dev] New vpp project committer nomination: Paul Vinciguerra

+1 Florin > On Feb 27, 2019, at 5:20 AM, Dave Barach via Lists.Fd.Io > wrote: > > +1... Dave > > From: vpp-dev@lists.fd.io > On Behalf Of Dave Barach via Lists.Fd.Io > Sent: Wednesday, February 27, 2019 7:38 AM > To: vpp-dev@lists.fd.

Re: [vpp-dev] New vpp project committer: Paul Vinciguerra

Congrats, Paul!! Florin > On Feb 28, 2019, at 2:37 PM, Dave Barach via Lists.Fd.Io > wrote: > > Please join me in congratulating Paul on his election as a vpp project > committer! > > Thanks... Dave > > -=-=-=-=-=-=-=-=-=-=-=- > Links: You receive all messages sent to this group. > > Vie

Re: [vpp-dev] multi-threaded application, "epoll_wait" and "epoll_ctl" have "received signal SIGABRT, Aborted".

Interesting. What application are you running and does this [1] fix the issue for you? In short, many of vls’ apis check if the call is coming in on a new pthread and program vcl accordingly if yes. The patch makes sure vls_attr does that as well. Thanks, Florin [1] https://gerrit.fd.io/r/#/c

Re: [vpp-dev] multi-threaded application, "epoll_wait" and "epoll_ctl" have "received signal SIGABRT, Aborted".

eturn rv; > } > @@ -773,8 +776,10 @@ vls_epoll_ctl (vls_handle_t ep_vlsh, int op, > vls_handle_t vlsh, >vls_table_rlock (); >ep_vls = vls_get_and_lock (ep_vlsh); >vls = vls_get_and_lock (vlsh); > + vls_mt_guard (0, VLS_MT_OP_XPOLL); >ep_sh = vls_to_sh (ep_vls); >

Re: [vpp-dev] multi-threaded application, "epoll_wait" and "epoll_ctl" have "received signal SIGABRT, Aborted".

se, you’d probably have to change your app to directly work with vls or vcl. Hope this helps, Florin > > Thanks, > Sharath. > > > On Sat 30 Mar, 2019, 1:27 AM Florin Coras, <mailto:fcoras.li...@gmail.com>> wrote: > Just so I understand, does the patch not fi

Re: [vpp-dev] Packet with custom ip-proto value drops in ip4-local node

Hi Satish, From the error counters lower, it seems that ip local is not the one to drop the packets. Also, if the packet is not tcp or udp, checksum should not computed, as per ip4_local_check_l4_csum [1]. Also, packets that fail the source ip check should be dropped with IP4_ERROR_SPOOFED_LOC

Re: [vpp-dev] VPP 19.04 centos7 RPM package dependency errors

Are we building rpms on a host that has mbedtls installed? Just uninstalling it should disable the tlsmbedtls plugin, which is what we pretty much want. Florin > On Apr 11, 2019, at 1:00 PM, Dave Wallace wrote: > > Tom/Billy, > > Do you know what the current status is with the VPP rpm's on

Re: [vpp-dev] VPP 19.04 centos7 RPM package dependency errors

run in the container? It seems that even python3 has some dependency errors. I guess that once we align the vagrant version with it, things should just work. Florin > On Apr 11, 2019, at 1:55 PM, Ed Kern (ejk) wrote: > > > >> On Apr 11, 2019, at 2:22 PM, Florin Coras &

Re: [vpp-dev] VCL, ld-preload and VPP shared memory better understanding

Hi Ido, You can find some high level documentation about vcl here [1]. In particular, check the presentations at the bottom of the page and [2]. For more details, you’ll have to read the code. If you need to exercise vcl, you may want to try using iperf [3] or the the vcl test server/client ap

Re: [vpp-dev] [csit-dev] VPP 19.04 Release is complete!

Awesome! Thanks for managing this one, Dave! Cheers, Florin > On Apr 24, 2019, at 3:06 PM, Dave Wallace wrote: > > Folks, > > I am pleased to announce that the VPP 19.04 Release is complete and the > release artifacts are available on > PackageCloud:https://packagecloud.io/fdio/release > <

Re: [vpp-dev] how to trace tcp4-output?

Hi Andreas, The tracing should work but because we’re reusing the syn packet to build the syn-ack, it might not show correctly. Could you breakpoint the tcp4-output and try to see if the trace code is hit? As for the checksum, tcp only tags the packet with a request to have it offloaded. If t

Re: [vpp-dev] how to trace tcp4-output?

Unfortunately, as things stand, the tunnel should compute the checksum before encapsulating the traffic. Otherwise the output node won’t be able to find the right headers. Will look into simplifying this. Florin > On Apr 29, 2019, at 8:18 AM, Andreas Schultz > wrote: > > Thanks, that help

Re: [vpp-dev] how to trace tcp4-output?

re-assembly/segmentation. Florin > On Apr 29, 2019, at 9:38 AM, Andreas Schultz > wrote: > > Am Mo., 29. Apr. 2019 um 18:21 Uhr schrieb Florin Coras > mailto:fcoras.li...@gmail.com>>: > Unfortunately, as things stand, the tunnel should compute the checksum before >

Re: [vpp-dev] finding a virtual memory leak in VPP

Hi Andreas, Maybe you allocate a lot of shared memory segments for UPF? I seem to remember you were using the host stack, are you using it in this test? Florin > On May 9, 2019, at 9:17 AM, Andreas Schultz > wrote: > > Hi, > > Something in VPP (most likely my UPF/GTP plugin) is causing an

Re: [vpp-dev] build error in VPP master branch

Did you try make wipe/wipe-release? Florin > On May 16, 2019, at 7:45 PM, Zhiyong Yang wrote: > > Hi guys, > > Does anybody run into the trouble as below? How to fix it? > fatal error: quicly/defaults.h: No such file or directory > > thanks > Zhiyong > -=-=-=-=-=-=-=-=-=-=-=- > Links: You

Re: [vpp-dev] VCL hoststack test & asserts

Hi Nathan, Just a quick reply. I regularly run make test-debug TEST=vcl so please continue to do that and please report any issues you may encounter. Something is weird because packets make it to udp-ping-local which shouldn’t be hit at all. Will take a look as soon as I can. Thanks, Florin

Re: [vpp-dev] VCL hoststack test & asserts

://gerrit.fd.io/r/#/c/19816/ <https://gerrit.fd.io/r/#/c/19816/> > On May 22, 2019, at 9:35 AM, Florin Coras via Lists.Fd.Io > wrote: > > Hi Nathan, > > Just a quick reply. I regularly run make test-debug TEST=vcl so please > continue to do that and please report a

Re: [vpp-dev] sock_test_client/sock_test_server #vnet

Hi, That script has not been recently maintained. Can’t you use instead vcl/ldp? From the logs, probably the server is not binding correctly. Florin > On May 31, 2019, at 6:28 PM, nataraj.bat...@gmail.com wrote: > > Update on sock_test_client/sock_test_server: > > After running with LD_PRE

Re: [vpp-dev] setsockopt with TCP_NODELAY

Hi Nataraj, TCP defaults to TCP_NODELAY behavior, unless you need Nagle’s algorithm on, you should be fine. As for the socket options, no. At this time, ldp cannot change properties for established tcp connections. What sort of things are you missing? Thanks, Florin > On Jun 12, 2019, at 1

Re: [vpp-dev] setsockopt with TCP_NODELAY

_MAXSEG(to much lower than interface MTU) and TCP_KEEPINTVL. These options > need to be communicating to the vnet right? I was looking for that. > > Thanks, > -Nataraj > > On Wed, Jun 12, 2019 at 11:14 AM Florin Coras <mailto:fcoras.li...@gmail.com>> wrote: > Hi

Re: [vpp-dev] Transparent proxy app

Hi, By default the stack only accepts “for-us” packets, i.e., packets that have as destination ip one vpp’s interface ips. To support transparent proxying you’d have to 1) write your own feature that intercepts traffic and delivers it to the stack and 2) your own transparent proxy app. Flori

Re: [vpp-dev] Commit Subjects

Hi Jon, Yup, it has to match a maintainer “I” entry and yes, that’s where the script is. :-) Florin > On Jun 17, 2019, at 1:16 PM, Jon Loeliger via Lists.Fd.Io > wrote: > > And now this: > > === ERROR === > Unknown feature 'Consolida

Re: [vpp-dev] TLS client app

Hi, No, we’re not exposing the server certificate in the session connected notification because that api is generic, i.e., used for all transports. If you need to grab the server certificate out of a tls connection, you’ll need to add a separate api that for a given session handles returns the

Re: [vpp-dev] test-debug in the CI

This [1] seems to solve sctp issues with debug images locally. Florin [1] https://gerrit.fd.io/r/c/20337/ > On Jun 25, 2019, at 12:10 PM, Dave Barach via Lists.Fd.Io > wrote: > > The BIER tests cause ASSERT failures. I’ll have a quick look, then turn the >

Re: [vpp-dev] A question about TCP statck in version 19.04, when passive FIN coming in first, then APP close with TX fifo not empty, it seem can't have chance to send FIN out. #vnet

Hi, That is correct. You want to provide the patch or should I do it? Thanks, Florin > On Jun 28, 2019, at 6:10 AM, guangwei wrote: > > Now, I'am searching the TCP stack of VPP 19.04, and have a doubt, please look > following comment in line. > > tcp46_rcv_process_inline > { > ... >

Re: [vpp-dev] A question about TCP statck in version 19.04, when passive FIN coming in first, then APP close with TX fifo not empty, it seem can't have chance to send FIN out. #vnet

Here’s the patch [1]. Thanks, Florin [1] https://gerrit.fd.io/r/c/20404/ <https://gerrit.fd.io/r/c/20404/> > On Jun 28, 2019, at 7:54 AM, guangwei wrote: > > Yes, please fixed it, I'am just searching the code, no environment to verify > it. > > > > At

Re: [vpp-dev] VPP 19.04 TCP stack issue: I think TCP stack notify the FIN reception immaturely #vnet

Hi, Well, yes. VPP tcp won’t send out of order fins because it waits for all the data to be acked before sending the fin. Still, others may do it, so here’s a quick fix for that [1]. Thanks, Florin [1] https://gerrit.fd.io/r/c/20403/ > On Jun 28, 2019, at

[vpp-dev] centos jobs failing

It seems the centos package expired in packagecloud. Ed is working on the problem. Florin-=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#13415): https://lists.fd.io/g/vpp-dev/message/13415 Mute This Topic: https://lists.fd.io/mt/32277567/21656 Gro

Re: [vpp-dev] TCP host stack

Hi, Yes, it should. But there are several things that must be considered: - the proxy code is not optimized at all. It’s just a toy - fifos (buffers for connections) are not auto-tunnable at this point. To achieve a high throughput you need to manually configure large fifos. Here’s[1] how we do

Re: [EXTERNAL] [vpp-dev] VPP Router Plugin or alternatives

Just a quick note on punting tcp: we can punt TCP flows that do not match a configured session but at this time, we can’t punt to a specific node, instead they are punted to ip4/6-punt. As for TCP-MD5, it could be implemented, but I have my hands full these days. And, to rant for a second, why

Re: [vpp-dev] VCL defaults to app-local-scope

Hi Alok, VCL, on master, defaults to no scope set. Local and global scope are set only if requested in vcl.config as “app-local-scope” or “app-global-scope” or if set via environment variables, like in your example lower. For more details check vcl_cfg.c. Session layer interprets no scope set

Re: [vpp-dev] VCL defaults to app-local-scope

Hi Alok, Inline. > On Jul 11, 2019, at 5:19 PM, Alok Nikhil (anikhil) via Lists.Fd.Io > wrote: > > Thanks Florin! That works. > > Just a couple of more questions - > 1) You mentioned the VCL library was undergoing a refactor. Is it now stable > enough for production use? Yes, VCL refactor

Re: [vpp-dev] nginx+vpp with epoll pattern failed #vpp #ngnix #epoll

Hi, It’s not clear from your email if you’re trying it out with ldp or directly with vcl. If you’re trying a direct integration with vcl, note that vcl epoll is edge triggered, so you must read all data before waiting for another rx event. Florin > On Jul 22, 2019, at 7:32 PM, fjc...@hotma

Re: [vpp-dev] echo server crash with my certs/self signed cert. (tls uri)

Hi Praveen, It looks like the tls listener was not properly initialized. I’d recommend running a debug image from gdb to get more info. Probably openssl complained about the parameters on listen but the error was not handled. If I’m right, this [1] should better handle the failed listen. Fl

Re: [vpp-dev] TCP host stack & small size fifo

Hi, It seems that linux is reluctant to send a segment smaller than the mss, so it probably delays sending it. Since there’s little fifo space, that’s pretty much unavoidable. Still, note that as you increase the number of sessions, if all send traffic at the same rate, then their fair share

Re: [vpp-dev] TCP host stack & small size fifo

uently, are the linux side sockets marked as no_delay ? > [2] > > [1]: https://en.wikipedia.org/wiki/Silly_window_syndrome > > [2]: > https://stackoverflow.com/questions/17842406/how-would-one-disable-nagles-algorithm-in-linux > > --a > > On 7/24/19, Florin Coras

Re: [vpp-dev] TCP host stack & small size fifo

=1JV1zSpggwEoWdeddDR8lcY3yeQRY6-B3> > > Среда, 24 июля 2019, 17:45 +03:00 от Florin Coras : > > Hi, > > It seems that linux is reluctant to send a segment smaller than the mss, so > it probably delays sending it. Since there’s little fifo space, that’s pretty > m

Re: [vpp-dev] TCP host stack & small size fifo

Hi Max, Note how whenever acks go from 192.168.0.1 to 192.168.0.200, the window is constantly 8k, it never drops, i.e., that buffer never fills. If you pick a segment, say seq 18825 -> 20273, it’s sent at time 0.000545 and it’s acked at 0.000570. So, the ack went out after 25us and by that tim

Re: [vpp-dev] echo server crash with my certs/self signed cert. (tls uri)

:02 myvpp1 vnet[1468]: tls_disconnect:550: Disconnecting 4000 > > ᐧ > > On Tue, Jul 23, 2019 at 10:59 PM Praveen Kariyanahalli > mailto:praveen.ha...@gmail.com>> wrote: > I havent changed anything in the listener handler (this is latest vpp code as > is). Just changed the c

Re: [vpp-dev] TCP host stack & small size fifo

Hi Max, > On Jul 25, 2019, at 5:51 AM, Max A. wrote: > > Hi Florin, > > > As explained above, as long as the sender is faster, this will happen. Still, > out of curiosity, can you try this [1] to see if it changes linux’s behavior > in any way? Although, I suspect the linux’s window probe t

Re: [vpp-dev] TCP host stack & small size fifo

Hi Max, > On Jul 25, 2019, at 6:09 AM, Max A. wrote: > > Hi Florin, > > I tried to increase the buffer size to 128k. The problem still arises, only > less often [1]. The smaller the buffer, the more often the problem occurs. Yup, for maximum throughput, fifo size needs to be large enough to

Re: [vpp-dev] TCP host stack & small size fifo

Hi Max, By the looks of it, the result is different, although not perfect. That is, you can now see multiple packets (more than the 14k) exchanged before window goes to zero. How are you reading the data in vcl, i.e., how large is your read buffer? I hope it’s at least around 8-14kB. Also,

Re: [vpp-dev] TCP host stack & small size fifo

Hi Max, Inline. > On Jul 28, 2019, at 10:47 AM, Max A. wrote: > > Hi Florin, > > I simplified the application. It sends the request and reads all the data > from the server using the 8 KB buffer. The fifo size is set to 8 KB. In the > attached dump [1] you can see that in packet number 14 th

Re: [vpp-dev] [tsc] FD.io Maintenance: 2019-07-30 @ 1700 UTC (10:00am PDT) - 2100 UTC (2:00pm PDT)

I definitely like the new UI. But now I’m getting: "! [remote rejected] HEAD -> refs/drafts/master (draft workflow is disabled)” Did something change? Thanks, Florin > On Jul 30, 2019, at 11:57 AM, Vanessa Valderrama > wrote: > > Maintenance is complete. All systems are now available.

<    1   2   3   4   5   6   7   8   >