Re: [vpp-dev] SIIT-DC - IPv4 to IPv6 translation

Hey all, This project has come back to the top of the pile, and I still don't have a solution. I spent some time reading the source code for the map implementation, and while I can generally follow along I'm no C programmer. That said, it looks to me like the part that fails for me is the

Re: [vpp-dev] Regarding DPDK's rte_timer api's usage with VPP

How about replacing this part of rte_timer_subsystem_init(): mz = rte_memzone_lookup(mz_name); if (mz == NULL) { mz = rte_memzone_reserve_aligned(mz_name, mem_size, SOCKET_ID_ANY, 0, RTE_CACHE_LINE_SIZE); if (mz ==

Re: [vpp-dev] Fixing nat44ed vrf api handlers

I split it up and it's ready for review: https://gerrit.fd.io/r/c/vpp/+/38459 https://gerrit.fd.io/r/c/vpp/+/38551 I have last one question: In case API doesn't return all data (e.g nat44_ed_vrf_tables_send_details missing  table_vrf_id assign of value) and if I decide to add it. Is it

Re: [vpp-dev] How to check stack size of process node

Thanks a lot Dave! On Sat, Mar 25, 2023, 19:45 Dave Barach wrote: > Find the current process index: vlib_node_main_t *nm = >node_main; > current_process_index = nm->current_process_index; > > > > Find the process object: vlib_process_t *p = vec_elt (nm->processes, > current_process_index); >

[vpp-dev] Regarding DPDK's rte_timer api's usage with VPP

Hi, I am bringing in some legacy code which worked with DPDK standalone, and converting it into a VPP plugin (VPP 22.10) The legacy code uses the DPDK rte_timer api's Now as soon as my VPP plugin calls the DPDK API rte_timer_subsystem_init, I get the following error from EAL of DPDK EAL:

Re: [vpp-dev] VPP LCP Route Not Reflecting After Interface State Change

I was not able to use *linux_cp/linux_nl* (vpp 23.02-release) because with the same config, the interfaces are not even coming up, that is why I switched back to *lcpng_if_plugin and lcpng_nl_plugin* On Sun, Mar 26, 2023 at 11:38 AM Pim van Pelt via lists.fd.io wrote: > Hoi, > > Does the same

Re: [vpp-dev] VPP LCP Route Not Reflecting After Interface State Change

Hoi, Does the same behavior happen with linux_cp_plugin and linux_nl_plugin enabled instead? I saw a change in linux_cp that will walk the fib and remove routes associated with down interfaces; and I think this is because FRR does not remove them while Bird does. Can you try with

[vpp-dev] VPP LCP Route Not Reflecting After Interface State Change

*Hi,* *I am facing an issue with the LCP route update when a particular interface changes state (i.e. when I manually shut it down and when I bring it up).* *Before shutting interface down, below is the state both in FRR and Linux table:* *FRR table:* ingress-node-vpp-58dcb69b5f-g9rzp:/# vtysh

Re: [vpp-dev] How to check stack size of process node

Find the current process index: vlib_node_main_t *nm = >node_main; current_process_index = nm->current_process_index; Find the process object: vlib_process_t *p = vec_elt (nm->processes, current_process_index); Find the stack base: p->stack Take the address of a local variable in a

Re: [vpp-dev] How to check stack size of process node

Hi, Please share any thoughts on this. Thanks, On Sat, Mar 18, 2023, 13:18 chetan bhasin via lists.fd.io wrote: > Hi vpp-team, > > > Could you please provide a way via which a process node stack size can be > calculated. We are creating a process node, how to figure out the value > of

Re: [vpp-dev] Traffic shaping functionality in VPP?

Hello! I'm not expert, just network engineer. I'm interested and ready to take part in testing. -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#22762): https://lists.fd.io/g/vpp-dev/message/22762 Mute This Topic:

Re: [vpp-dev] [QUESTION] How to add virtual interfaces on ARM board

You can run multiple VPP instances [1] and connect them using memif interface, which is shared memory-based software interface. VPP also has packet generator, to emulate the PC1, PC2 in your topology. In this way, you can achieve the topology based on pure software implementation. [1]

Re: [vpp-dev] Traffic shaping functionality in VPP?

Hi Elias, You can find such solution in VPP 18.04 where VPP dpdk plugin is modified to enable HQoS scheduler and shaping function which runs on a separate VPP thread on TX path. The feature was deprecated in later releases. Hope that helps. Thanks, Jasvinder. > -Original Message- >

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi Zhang, Thanks for confirming! Give me a few more days to check if there’s any other improvements to be made in that area. Regards, Florin > On Mar 23, 2023, at 12:00 AM, Zhang Dongya wrote: > > Hi, > > The new patch works as expected, no assert triggered abort anymore. > > Really

[vpp-dev] Intel iAVF interrupt support

General question, is there any particular reason the probe for interrupt support is not performed for Intel iAVF driver? The spec indicated support for interrupts, so I enabled the probe and was able to set the rx-mode interrupt for this device. I was wondering if this was intentional? Thanks

[vpp-dev] Traffic shaping functionality in VPP?

Hello VPP experts, We have been using VPP for NAT44 for a while, which has worked great. We contributed some fixes a couple of years ago and have been using VPP without issues since then. Now we are considering the possibility of using VPP for a different usecase as well, related to "broadband

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi, The new patch works as expected, no assert triggered abort anymore. Really appreciate your help and thanks a lot. Florin Coras 于2023年3月22日周三 11:54写道： > Hi Zhang, > > Awesome! Thanks! > > Regards, > Florin > > On Mar 21, 2023, at 7:41 PM, Zhang Dongya > wrote: > > Hi Florin, > > Thanks a

Re: [vpp-dev] [QUESTION] How to add virtual interfaces on ARM board

Hi Xiaodong, Thanks for your reply. I'm studying your link and also searching some other topics & messages. Your link about host interface is AF_PACKET, right? I searched other posts mentioned tap has better performance than host interface. Can I use tap for my requirement? Dorian

Re: [vpp-dev] [QUESTION] How to add virtual interfaces on ARM board

Maybe you can try host interface in this case, since you are going to share the control traffic and the user traffic on the only NIC. Check https://s3-docs.fd.io/vpp/23.06/gettingstarted/progressivevpp/interface.html#create-vpp-host-interface for more details. Regards, Xiaodong On Wed, Mar 22,

[vpp-dev] [QUESTION] How to add virtual interfaces on ARM board

Hi, I'm a newbie and study vpp recently. I succeed cross compiling vpp (including my own plugin) , and it can be started up on my arm64 board (aarch64 ubuntu 18.04).  But there is only one physical NIC (eth1)  which I can use on the board, and I don't need dpdk, so there is only local0 when I

Re: [vpp-dev] #vnet A bug which may cause assertion error in vnet/session

Thank you for your reply. I did use a VMware virtual machine before, I switched to a physical NIC for testing and now there is no problem setting rx-num to 5. Also, I tested redis using redis-benchmark, the specific command is as follows: sudo taskset -c 9 bash -c

Re: [vpp-dev] Fixing nat44ed vrf api handlers

If you decide to split the patch and do a second version. I would like to see the first version set as deprecated. So when removed we can put it again in without having to have _v2 _v3 etc. Best regards, Filip Varga st 22. 3. 2023 o 15:33 Daniel Béreš napísal(a): > Thanks for the reasonable

Re: [vpp-dev] Fixing nat44ed vrf api handlers

Thanks for the reasonable explanations. So the option could be splitting it into two patches. The first could fix replies and the second could contain a new experimental API nat44_ed_vrf_tables_send_details_v2. I think it might be okay after that. Daniel -=-=-=-=-=-=-=-=-=-=-=- Links: You

Re: [vpp-dev] Fixing nat44ed vrf api handlers

Some more context: after discussion with Ole: I think I might have overstepped the authority in terms of "-2" - it is component maintainers' decision if they want to put even completely breaking change into their component that sets the world on fire - if the CI lets that through - it is their

Re: [vpp-dev] Fixing nat44ed vrf api handlers

Hi, Yes I fully agree with Andrew on changing APIs. Though the api was broken in the first place. If used incorrect message is returned. Because of that I am not even sure if it is functional at all. It is more likely that nobody before addressed this issue because this feature is not used. So I

Re: [vpp-dev] Fixing nat44ed vrf api handlers

Hey Daniel,I had a quick look and it looks like the APIs in question are also not marked as experimental ?If I am right, then to me seems like a silent behavior change to a production API - something we have heard repeated complaints from the downstream consumers for….I had -2’d it for now - we

[vpp-dev] Fixing nat44ed vrf api handlers

Hello Guys, I wrote a short patch to fix a couple api handlers for nat44ed [1] . ( https://gerrit.fd.io/r/c/vpp/+/38459 ) It was probably forgotten, so I'm reminding myself. I still have a question about whether it is possible to cherry-pick the patch to vpp v23.02 and 22.10. [1] 

Re: [vpp-dev] #vnet A bug which may cause assertion error in vnet/session

Thank you for you reply. I did use a VMware virtual machine before, I switched to a physical NIC for testing and now there is no problem setting rx-num to 5. Also, I tested redis using redis-benchmark, the specific command is as follows: sudo taskset -c 9 bash -c

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi Zhang, Awesome! Thanks! Regards, Florin > On Mar 21, 2023, at 7:41 PM, Zhang Dongya wrote: > > Hi Florin, > > Thanks a lot, the previous patch and with reset disabled have been running 1 > day without issue. > > I will enable reset and with your new patch, will provide feedback later.

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi Florin, Thanks a lot, the previous patch and with reset disabled have been running 1 day without issue. I will enable reset and with your new patch, will provide feedback later. Florin Coras 于2023年3月22日周三 02:12写道： > Hi, > > Okay, resetting of half-opens definitely not supported. I updated

Re: [vpp-dev] #vnet A bug which may cause assertion error in vnet/session

Hi, The problem seems to be that you’re using a vmxnet3 interface, so I suspect this might be a vm configuration issue. Your current config should work but could end up being inefficient. With respect to your problem, I just built redis and ran redis-server and cli over LDP. Everything

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi, Okay, resetting of half-opens definitely not supported. I updated the patch to just clean them up on forced reset, without sending a reset to make sure session lookup table cleanup still happens. Regards, Florin > On Mar 20, 2023, at 9:13 PM, Zhang Dongya wrote: > > Hi, > > After

Re: [vpp-dev] #vnet A bug which may cause assertion error in vnet/session

Thank you for your reply. I tried to change num-tx-queues from 2 to 5, but it got a SIGSEGV, the backtrace is: #0  0x7fffb453ff89 in rte_write32_relaxed (addr=0x80007ef0, value=0) at ../src-dpdk/lib/eal/include/generic/rte_io.h:310 #1  rte_write32 (addr=0x80007ef0, value=0) at

Re: [vpp-dev] VNET Device Drivers; increased memory footprint for af_packet v3

Hi, Excuse me for the misunderstanding. Most probably this is not an issue in VPP. In the mentioned 'previous version of vpp (git version 45207e0fb2) the af_packet_create_v2 api was used, so the memory increase is expected. So, the question had lapsed. /Laszlo

[vpp-dev] VNET Device Drivers; increased memory footprint for af_packet v3

Hello fellow VPP developers! I experienced an increase in memory allocation related to af_packet v3. VPP is built from source from git version: e416893a5. The AF_PACKET interface is created by the go bin-api call AfPacketCreateV3 (invoking af_packet_create_v3 api call in VPP). The amount of

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi, After review my code, I found that I have add a flag to the vnet_disconnect API which will call session_reset instead of session_close, the reason I do this is to make intermediate firewall just flush the state and reconstruct if I later reconnect. It seems in session_reset logic, for half

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi, That last thing is pretty interesting. It’s either the issue fixed by this patch [1] or sessions are somehow cleaned up multiple times. If it’s the latter, I’d really like to understand how that happens. Regards, Florin [1] https://gerrit.fd.io/r/c/vpp/+/38507 > On Mar 20, 2023, at

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi, After merge this patch and update the test environment, the issue still persists. Let me clear my client app config: 1. register a reset callback, which will call vnet_disconnect there and also trigger reconnect by send event to the ctrl process.) 2. register a connected callback, which will

Re: [vpp-dev] #vnet A bug which may cause assertion error in vnet/session

Hi, First of all, could you try this [1] with latest vpp? It’s really interesting that iperf does not exhibit this issue. Regarding your config, some observations: - I see you have configured 4 worker. I would then recommend to use 4 rx-queues and 5 tx-queues (main can send packets), as

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi, Understood and yes, connect will synchronously fail if port is not available, so you should be able to retry it later. Regards, Florin > On Mar 20, 2023, at 1:58 AM, Zhang Dongya wrote: > > Hi, > > It seems the issue occurs when there are disconnect called because our > network

Re: [vpp-dev] #vnet A bug which may cause assertion error in vnet/session

Thanks for your reply. I give a more detailed backtrace and config in https://lists.fd.io/g/vpp-dev/message/22731. ( https://lists.fd.io/g/vpp-dev/message/22731, ) My installation method is to clone vpp from github and make build on Ubuntu 22.04(Kernel version is 5.19)，and I use make run for

Re: [vpp-dev] #vnet A bug which may cause assertion error in vnet/session

Thank you for your reply. This is the stacktrace captured by gdb: 2: /home/chenweihao/vpp_dev/src/vnet/session/session.c:233 (session_is_valid) assertion `! pool_is_free (session_main.wrk[thread_index].sessions, _e)' fails Thread 4 "vpp_wk_1" received signal SIGABRT, Aborted. [Switching to

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi, It seems the issue occurs when there are disconnect called because our network can't guarantee a tcp can't be reset even when 3 ways handshake is completed (firewall issue :( ). When we find the app layer timeout, we will first disconnect (because we record the session handle, this session

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi, Inline. > On Mar 19, 2023, at 6:47 PM, Zhang Dongya wrote: > > Hi, > > It can be aborted both in established state or half open state because I will > do timeout in our app layer. [fc] Okay! Is the issue present irrespective of the state of the session or does it happen only after a

Re: [vpp-dev] VPP not dropping packets with incorrect vlan tags on untagged interface

Hi, Did anyone get a chance to look at this issue? If anyone has any sort of input, that will be of great help. Please let me know if any additional information is needed. Thank you. Best regards, Parameswaran -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group.

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi, It can be aborted both in established state or half open state because I will do timeout in our app layer. Regarding your question, - Yes we add a builtin in app relys on C apis that mainly use vnet_connect/disconnect to connect or disconnect session. - We call these api in a vpp ctrl

Re: [vpp-dev] #vnet A bug which may cause assertion error in vnet/session

I just tried iperf3 in cut-through mode, i.e., server and client attached to the same vpp instance running 4 workers, with 128 connections and this seems to be working fine. Could you try that out and see if it’s also working for you? It might be that this is something specific to how Redis

Re: [vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi, When you abort the connection, is it fully established or half-open? Half-opens are cleaned up by the owner thread after a timeout, but the 5-tuple should be assigned to the fully established session by that point. tcp_half_open_connection_cleanup does not cleanup the bihash instead

Re: [vpp-dev] #vnet A bug which may cause assertion error in vnet/session

Hi, That may very well be a problem introduced by the move of connects to first worker. Unfortunately, I we don’t have tests for all of those corner cases yet. However, to replicate this issue, could you provide a bit more details about your setup and the exact backtrace? It looks like you’re

[vpp-dev] bridge domain is not forwarding to all ports #vpp

Hi All, I have created a bridge domain with three interface. host-interface, and two physical interface (sriov VF). vpp# sh bridge-domain 20 detail BD-ID   Index   BSN  Age(min)  Learning  U-Forwrd   UU-Flood   Flooding  ARP-Term  arp-ufwd   BVI-Intf 20       1      0     off        on        on 

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Hi, Fix confirmed. Git master branch runs the test code without any error. Thanks for everyone participating in this thread! Best regards, Hao Tian -Original Message- From: vpp-dev@lists.fd.io on behalf of Hao Tian Sent: Friday, March 17, 2023 11:17 AM To: vpp-dev@lists.fd.io

[vpp-dev] Sigabrt in tcp46_input_inline for tcp_lookup_is_valid

Hi list, recently in our application, we constantly triggered such abrt issue which make our connectivity interrupt for a while: Mar 19 16:11:26 ubuntu vnet[2565933]: received signal SIGABRT, PC 0x7fefd3b2000b Mar 19 16:11:26 ubuntu vnet[2565933]:

[vpp-dev] #vnet A bug which may cause assertion error in vnet/session

Hi vpp-team, I'm new to VPP and I'm trying to run Redis 6.0.18 in VCL with LD_PRELOAD using VPP 22.10 and VPP 23.02. I found that assert fails frequently in VPP 23.02, and after checking, I found that the assert fails in the session_get function in vnet/session/session.h. The cause was an

[vpp-dev] How to check stack size of process node

Hi vpp-team, Could you please provide a way via which a process node stack size can be calculated. We are creating a process node, how to figure out the value of process_log2_n_stack_bytes?? Thanks, -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online

Re: [vpp-dev] can't establish tcp connection with new introduced transport_endpoint_freelist

Great! Thanks for confirming! Regards, Florin > On Mar 16, 2023, at 8:29 PM, Zhang Dongya wrote: > > yes, this is exactly what I want do, this patch works as expected, thanks a > lot. > > Florin Coras mailto:fcoras.li...@gmail.com>> > 于2023年3月15日周三 01:22写道： >> Hi, >> >> Are you looking

Re: [vpp-dev] can't establish tcp connection with new introduced transport_endpoint_freelist

yes, this is exactly what I want do, this patch works as expected, thanks a lot. Florin Coras 于2023年3月15日周三 01:22写道： > Hi, > > Are you looking for behavior similar to the one when random local ports > are allocated when, if port is used, we check if the 5-tuple is available? > > Don’t think we

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Hi Dave, I tested the change and found some issue. Please check gerrit comments. Thanks! Best regards, Hao Tian -Original Message- From: vpp-dev@lists.fd.io on behalf of Dave Barach Sent: Friday, March 17, 2023 1:50 AM To: vpp-dev@lists.fd.io Subject: Re: [vpp-dev] Race condition

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Hi Dave, What if just to use highest bit of key as free mark? While having clib_crc32c_uses_intrinsics defined, hash result will be 32bit only, highest bit of 64bit key is completely “free”. If not defined, - highest but can be just stripped off while computation in clib_bihash_*. With such

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Please see https://gerrit.fd.io/r/c/vpp/+/38507 -Original Message- From: vpp-dev@lists.fd.io mailto:vpp-dev@lists.fd.io> > On Behalf Of Hao Tian Sent: Wednesday, March 15, 2023 10:14 PM To: vpp-dev@lists.fd.io Subject:

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Hi Dave, Thanks for your work. I am ready to test whenever needed. Best regards, Hao Tian From: vpp-dev@lists.fd.io on behalf of Dave Barach Sent: Thursday, March 16, 2023 7:02 AM To: vpp-dev@lists.fd.io Subject: Re: [vpp-dev] Race condition between

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Hi Andrew, Thanks for the insight, the idea about treating it as optimization is quite interesting. This is fine for newly added code, but I'm a bit concerned about existing code - there are a lot of bihash callers that use the value from bihash as vec/pool/... index as long as the search

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

I'm doing a bit of work to straighten out the template, hopefully without causing a measurable performance regression. Hao's test code is a bit of a corner-case: there is exactly one record in the database which the code thrashes as hard as possible. D. -Original Message- From:

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Hao, I noticed the same behavior when stress-testing the multi thread session handling for the ACL plugin a while ago. I thought this trade off is there to avoid having to do the hard locks in bihash code, rather than it being a bug. As you say - the special value comes only if the deletion is

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Hi, I tried but could not come up with any way that is able to ensure the kvp being valid upon return without using the full bucket lock. Maybe we can make a copy of the value before returning, validate the copy and return that copy instead. Critical section can be shrinked to cover only the

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Doubling the number of atomic ops was expected to cause a severe performance regression. This hack demonstrates that the test code wasn't responsible. A bit of extra suspicion in clib_bihash_search_inline_2_with_hash() will likely solve the problem without the huge performance regression. D.

[vpp-dev] VPP not dropping packets with incorrect vlan tags on untagged interface

Hi Experts, I'm using VPP v22.02.0-26. I have a physical interface TwentyFiveGigabitEthernet3/0/0/4096 in bridge-domain 10(untagged) and I have configured "l2 efp-filter" on all the interfaces. I expected that at the ingress of interface TwentyFiveGigabitEthernet3/0/0/4096, only untagged

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Hi, I've done the change you asked, and the "suspicious value" warnings are all gone. Here is the diff: diff --git a/src/vppinfra/bihash_template.h b/src/vppinfra/bihash_template.h index c4e120e4a..b9f658db3 100644 --- a/src/vppinfra/bihash_template.h +++ b/src/vppinfra/bihash_template.h @@

Re: [vpp-dev] lcpng with dhcp client on Linux

Sali Pim I just found the solution. set interface unnumbered GigabitEthernet3/0/0 use tap2 This in combination with RequestBroadcast worked and I've got an IP on Linux. Thank you for your help, for your work on lcpng and for your articles on ipng.ch they are very interesting and helpful.

Re: [vpp-dev] can't establish tcp connection with new introduced transport_endpoint_freelist

Hi, Are you looking for behavior similar to the one when random local ports are allocated when, if port is used, we check if the 5-tuple is available? Don’t think we explicitly supported this before but here’s a patch [1]. Regards, Florin [1] https://gerrit.fd.io/r/c/vpp/+/38486 > On Mar

Re: [vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Quick experiment: in src/vppinfra/bihash_template.h:clib_bihash_search_inline_2_with_hash(), replace this: if (PREDICT_FALSE (b->lock)) { volatile BVT (clib_bihash_bucket) * bv = b; while (bv->lock) CLIB_PAUSE (); } With: BV(clib_bihash_lock_bucket(b)); and make

[vpp-dev] VPP 23.06 release plan is available

Hi all, I’ve prepared the 23.06 release plan - and linked it off the usual place on VPP wiki: https://wiki.fd.io/view/VPP#Get_Involved Tl;dr: release the last Wednesday of June, RC2 two weeks prior; RC1 three weeks prior to RC2. Looks like this schedule works well. Same logic as usual -

[vpp-dev] Race condition between bihash deletion and searching - misuse or bug?

Hi all, I found that bihash might return zero'ed value (0xff's) if deletion and searching were performed in parallel on different threads. This is reproducible by only ~100 lines of code, from 21.06 all the way up to git master, and on multiple machines from Coffee Lake to Tiger Lake. The

Re: [vpp-dev] can't establish tcp connection with new introduced transport_endpoint_freelist

Just use this patch and the connection can be reconnected after closed. However, I find another possible bug when using local ip + local port for different target server due to transport_endpoint_mark_used return error if it find local ip + port being created. I think it should increase the

Re: [vpp-dev] can't establish tcp connection with new introduced transport_endpoint_freelist

Hi, Could you try this out [1]? I’ve hit this issue myself today but with udp sessions. Unfortunately, as you’ve correctly pointed out, we were forcing a cleanup only on the non-fixed local port branch. Regards, Florin [1] https://gerrit.fd.io/r/c/vpp/+/38473 > On Mar 13, 2023, at 7:35

[vpp-dev] can't establish tcp connection with new introduced transport_endpoint_freelist

Hi list, We have update coded from the upstream session changes to our code base and find a possible bug which cause tcp connection can't be established anymore. Our scenario is that we will connect to a remote tcp server with specified local port and local ip, however, new vpp code have

Re: [vpp-dev] Jenkins Emergency Maintenance

Production upgrade complete. If you have any issues, please open a ticket at support.linuxfoundation.org. Thank you, Vanessa On 3/13/23 13:00, Vanessa Valderrama wrote: Sandbox upgrade complete Starting on production now On 3/13/23 12:30, Vanessa Valderrama wrote: *What*: The Linux

Re: [vpp-dev] All UDP packet being dropped at “ipsec4_input_node” when IPSEC policy configured

Thank you for bringing this to the fore. I am noticing something interesting along the same lines as well during my investigation. I am using strongswan as the initiator and VPP Ikev2 as the responder. My observations are: 1. Strongswan initiator forceencap=yes and VPP responder ikev2 profile

Re: [vpp-dev] Jenkins Emergency Maintenance

Sandbox upgrade complete Starting on production now On 3/13/23 12:30, Vanessa Valderrama wrote: *What*: The Linux Foundation been made aware of a security issue with the Jenkins systems that needs immediate resolution *When*: We're starting the sandbox upgrade now Putting production in

[vpp-dev] Jenkins Emergency Maintenance

*What*: The Linux Foundation been made aware of a security issue with the Jenkins systems that needs immediate resolution *When*: We're starting the sandbox upgrade now Putting production in shutdown mode. The upgrade will be done at 18:00. (all running jobs will be aborted at this time)

[vpp-dev] All UDP packet being dropped at “ipsec4_input_node” when IPSEC policy configured

Hi Team, All UDP packet being dropped at “ipsec4_input_node” if ipsec inbound and outbound policy configured. Not that udp_encp is not enabled. Where TCP and ICMP has no such issue. System is treating normal UDP and UDP encapsulated ESP packet in same way. Probably we have to use DST and SRC

Re: [vpp-dev] Why does NAT44 EI (Endpoint-Independence) not have code that free LRU (Least Recently Used) sessions

Thank you so much, Filip, for your helpful response! Your explanation was clear and informative, and I really appreciate your taking the time to provide such a detailed answer. Best regards, Kyusik Shin -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply

Re: [vpp-dev] process node suspended indefinitely

Hi Dave, we are using VPP Version *21.10.* Thanks and regards, Sudhir On Fri, Mar 10, 2023 at 5:31 PM Dave Barach wrote: > I should have had the sense to ask this earlier: which version of vpp are > you using? > > > > The line number in your debug snippet is more than 100 lines off from >

Re: [vpp-dev] process node suspended indefinitely

I should have had the sense to ask this earlier: which version of vpp are you using? The line number in your debug snippet is more than 100 lines off from master/latest. The timer wheel code has been relatively untouched, but there have been several important fixes over the years... D.

Re: [vpp-dev] process node suspended indefinitely

Hi jinsh, Thanks for the help. I placed assert statement in *vlib_process_signal_event_**helper* function. But in this place the assert statement didn't hit. When I debugged further I found that my process node is not there in the *data_from_advancing_timing_wheel *vector. i believe due to this

Re: [vpp-dev] failure while building VPP v23.02 in centos 7 VM

Hi Sandeep, Our project build and run on Centos7 with vpp master very well, you can try the follow command: ` make VPP_SKIP_EXTERNAL= xdp-tools VPP_EXTRA_CMAKE_ARGS=" -DLDP_HAS_GNU_SOURCE=OFF -DCMAKE_PROGRAM_PATH:PATH='/opt/rh/devtoolset-9/root/bin'" build`, there may be compiler error with

Re: [vpp-dev] failure while building VPP v23.02 in centos 7 VM

Hoi, Preferred/supported build platform is Ubuntu LTS. It'll build well on Ubuntu Focal and Jammy. I additionally build and run on Debian Bullseye, which works well. groet, Pim On Fri, Mar 10, 2023 at 7:41 AM SANDEEP KUMAR wrote: > Thanks for the reply > Can you let me know which OS type and

Re: [vpp-dev] failure while building VPP v23.02 in centos 7 VM

Thanks for the reply Can you let me know which OS type and version is recommended for VPP v23.02? Thanks & Regards, Sandeep Kumar On Fri, Mar 10, 2023 at 12:49 AM Dave Wallace wrote: > Hi Sandeep, > > The VPP community no longer supports building on CentOS-7. The build > infrastructure for

Re: [vpp-dev] failure while building VPP v23.02 in centos 7 VM

Hi Sandeep, The VPP community no longer supports building on CentOS-7.  The build infrastructure for centos/redhat/rocky OS distros was left in place after support ended, but there are no active maintainers for this build infra nor are there any CI jobs to ensure that it still works. You

[vpp-dev] Memif Abstract Socket Support

Hi, Please I will like to know from which VPP version is the memif abstract socket implemented? Also is the following command syntax correct when the abstract socket is to used to create memif socket: *create memif socket id 1 filename @vpp/memif12* Thanks -=-=-=-=-=-=-=-=-=-=-=- Links: You

[vpp-dev] failure while building VPP v23.02 in centos 7 VM

Hi All, I am trying to build VPP v23.02 but getting an issue while performing the *make install-ext-deps* step in centos 7 VM, so please look at the following issue and help me to resolve it. *Prerequisites:* sudo yum groupinstall "Development Tools" sudo yum install -y numactl-devel

Re: [vpp-dev] process node suspended indefinitely

* I think you can query who stopped the current node's time wheel. always_inline void * vlib_process_signal_event_helper (vlib_node_main_t * nm, vlib_node_t * n, vlib_process_t * p, uword t, uword n_data_elts, uword n_data_elt_bytes) { if (add_to_pending) { u32 x =

Re: [vpp-dev] process node suspended indefinitely

I think you can assert in this function:, always_inline void * vlib_process_signal_event_helper (vlib_node_main_t * nm, vlib_node_t * n, vlib_process_t * p, uword t, uword n_data_elts, uword n_data_elt_bytes) { ... if (add_to_pending) { u32 x =

[vpp-dev] vpp is dropping arp packets #vnet

Hi All, I have brought up the vpp 20.09 on POD. It seems like vpp is unable to process the arp packet from SRIOV VF. Can you pl suggest what is the fix. vpp# sh int Name               Idx    State  MTU (L3/IP4/IP6/MPLS)     Counter          Count eth0                              1      up       

[vpp-dev] hqos configuration fails

Hi Everyone, I wanted to try out QOS in VPP, for which I am following https://docs.fd.io/vpp/17.10/qos_doc.html I have tried the steps and configs as mentioned in the link above. I am not able to bring up the vpp process. I am using vpp v22.06 I get following error vpp[108]: cpu_config:

Re: [vpp-dev] process node suspended indefinitely

Hi Dave, Please excuse my delayed response. It took some time to recreate this issue. I made changes to our process node as per your suggestion. now our process node code looks like this while (1) { vlib_process_wait_for_event_or_clock (vm, RTB_VPP_EPOLL_PROCESS_NODE_TIMER);

Re: [vpp-dev] Issue with tap FDs of bvi interface.

Hi Pragya, Could you give it a try with VPP master? I can't reproduce it on the master. On Fri, 3 Mar 2023 at 16:15, Pragya Nand Bhagat < pragya.nand.bhaga...@gmail.com> wrote: > Hi Stanislav, > > Following are the steps to reproduce in VPP 20.09: > > ip link add name vcsr-f1c1 type veth peer

Re: COMMERCIAL BULK: Re: [E] COMMERCIAL BULK: [vpp-dev] TLS app stuck after burst of traffic #vpp-hoststack

Hi Kevin, Understood. If you manage to confirm things are stable on latest vpp, maybe try to backport patches that changed tls tx functions. Worst case, you’ll have to backport some session layer patches as well. Regards, Florin > On Mar 7, 2023, at 5:24 AM, Kevin Yan wrote: > > Hi

Re: COMMERCIAL BULK: Re: [E] COMMERCIAL BULK: [vpp-dev] TLS app stuck after burst of traffic #vpp-hoststack

Hi Florin, Due to some reasons we need to stay on vpp20.09 for some time, that’s why I hope I can fix the issue on this version. Actually, I did some code changes in TLS layer to let session node force reschedule the TLS session when tx svm fifo is full or at least not empty,

Re: [E] COMMERCIAL BULK: [vpp-dev] TLS app stuck after burst of traffic #vpp-hoststack

Hi Kevin, That’s a really old version of vpp. TLS has seen several improvements since then in areas including scheduling after incomplete writes. If you get a chance to test vpp latest or a more recent release, do let us know if the issue still persists. Regards, Florin > On Mar 6, 2023,

Re: [E] COMMERCIAL BULK: [vpp-dev] TLS app stuck after burst of traffic #vpp-hoststack

Hi @Olivia Dunham, Recently I met the exact same issue, TLS TX svm fifo gets full after burst of traffic and it will never resume, meanwhile, TCP TX svm fifo is empty at that time I’m using VPP20.09, I believe there is some issue in TLS layer,

  1   2   3   4   5   6   7   8   9   10   >