Re: [vpp-dev] Issue with tap FDs of bvi interface.
Hi Stanislav, Following are the steps to reproduce in VPP 20.09: ip link add name vcsr-f1c1 type veth peer name f1c1 ip link set dev f1c1 up ip link set dev vcsr-f1c1 up create host-interface name vcsr-f1c1 lcp create host-vcsr-f1c1 host-if Ethernet0 check in show tap Check for fd in /proc//fd check in "show unix files" Thanks Pragya On Fri, 3 Mar, 2023, 8:34 pm Stanislav Zaikin, wrote: > Hi Pragya, > > Could you provide me with the steps to reproduce? > > On Tue, 28 Feb 2023 at 14:10, Pragya Nand Bhagat < > pragya.nand.bhaga...@gmail.com> wrote: > >> Hi Stanislav, >> >> I debug it further. Here are the steps >> >> 1> In my config I am creating a veth interface in kernel >> 2> for that interface I am creating a hostif interface using "create >> host-interface name " >> 3> This intern create 4 fds in "show unix files" >> 4> >> [image: image.png] >> >> 5> I think this 59 fd is fd of af_packet socket for hostif. Correct me >> if I am wrong. >> 6> but I don't see any inode entry for it in /proc//fd >> 7> So according to my understanding for other tap creation it tries to >> take 59 as free fd and allocate >> 8> that happens to be in bvi tap interface creation >> 9> and that causes traffic flow issues. >> >> Do you see its a valid analysis? Please provide your comments and let me >> know your thoughts on this. >> >> Thanks, >> Pragya >> >> >> On Tue, Feb 28, 2023 at 4:13 PM Pragya Nand Bhagat via lists.fd.io >> wrote: >> >>> Hi Stanislav, >>> >>> Thanks for the response. >>> Please find the response inline >>> >>> >>> Do you see any errors in `show log`? >>> >>>>[Pragya] No I don't see any error log >>> >>> Do you see this fd 59 in `show unix files`? >>> >>>>[Pragya] Yes, I can see 59 in show unix files >>> "show unix files" fetch the fd from "/proc/self/fd/" >>> but if we go and see /proc//fd we don't see any file inode being >>> created. >>> >>> So according to OS 59 is never assigned and for subsequent interface >>> creation it try to have that same tap fd which is 59 here. >>> I think that causes the issue where the traffic flow is not OK. >>> >>> Can you suggest how I can debug and address this issue? >>> >>> Thanks, >>> Pragya >>> >>> >>> On Fri, Feb 24, 2023 at 3:24 PM Stanislav Zaikin >>> wrote: >>> >>>> Hello Pragya, >>>> >>>> Do you see any errors in `show log`? >>>> Do you see this fd 59 in `show unix files`? >>>> >>>> On Fri, 24 Feb 2023 at 07:59, Pragya Nand Bhagat < >>>> pragya.nand.bhaga...@gmail.com> wrote: >>>> >>>>> Hi All, >>>>> >>>>> I'm using an older version of vpp 20.09 . >>>>> When I create a bvi interface using bvi create cli. >>>>> A corresponding tap is created with same name as follows: >>>>> >>>>> >>>>> >>>>> *itf-pair: [19] bvi100 tap-39-bvi100 bvi100 960 type tap * >>>>> >>>>> But one FD of the tap interface is *missing* when I check in linux. >>>>> >>>>> vpp# *show tap tap-39-bvi100* >>>>> >>>>> Interface: tap-39-bvi100 (ifindex 40) >>>>> >>>>> name "bvi100" >>>>> >>>>> host-ns "(nil)" >>>>> >>>>> host-mac-addr: e4:43:4b:21:f3:86 >>>>> >>>>> *vhost-fds 213 214* >>>>> >>>>> * tap-fds 59* >>>>> >>>>> gso-enabled 0 >>>>> >>>>> csum-enabled 0 >>>>> >>>>> >>>>> In above output there should be 3 FDs associated with the tap but* >>>>> one of them is missing.* >>>>> >>>>> [root@0-9 /]# ls -l /proc/37/fd | grep 59 >>>>> >>>>> lrwx-- 1 root root 64 Feb 23 12:03 159 -> /dev/vhost-net >>>>> >>>>> *FD 59 is missing*, as a result of which packet transfer between >>>>> linux and mdp is not happening. >>>>> >>>>> Is there some checkin/patch to fix this issue? >>>>> Any help in debugging this issue will be helpful . >>>>> >>>>> Thanks >>>>> Pragya Nand >>>>> >>>>> >>>>> >>>>> >>>> >>>> -- >>>> Best regards >>>> Stanislav Zaikin >>>> >>>> >>>> >>>> >>> >>> >>> >> >> >> > > -- > Best regards > Stanislav Zaikin > > > > -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#22666): https://lists.fd.io/g/vpp-dev/message/22666 Mute This Topic: https://lists.fd.io/mt/97201480/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] Issue related to number of bvi interface creation.
Hi All,
I'm using vpp 20.09.
When I create around 180 - 200 bvi interface vpp gets stuck and I'm unable
to login using vppctl.
#!/bin/bash
for var in
{202..1199}
do
echo "creating bvi $var"
vppctl bvi create instance $var
sleep 1
done
same happens with loopback interface.
Following is the trace that I get:
For bvi interface:
#0 0x7fa23f185d47 in sched_yield () from /lib64/libc.so.6
#1 0x7fa2431cbffe in spin_acquire_lock (sl=sl@entry=0x7fa1fa29e384)
at /vpp/src/vppinfra/dlmalloc.c:468
#2 0x7fa2431cd948 in mspace_malloc ()
at /vpp/src/vppinfra/dlmalloc.c:4416
#3 0x7fa2431cf077 in mspace_get_aligned (msp=0x7fa1fa29e010,
n_user_data_bytes=92, n_user_data_bytes@entry=72,
align=, align@entry=8, align_offset=align_offset@entry=8)
at /vpp/src/vppinfra/dlmalloc.c:4254
#4 0x7fa24322ce75 in clib_mem_alloc_aligned_at_offset
(os_out_of_memory_on_failure=1, align_offset=8, align=8, size=72)
at /vpp/src/vppinfra/mem.h:142
#5 vec_resize_allocate_memory (v=v@entry=0x0,
length_increment=length_increment@entry=64, data_bytes=72, data_bytes@entry
=64,
header_bytes=8, header_bytes@entry=0, data_align=data_align@entry=8,
numa_id=numa_id@entry=255)
at /vpp/src/vppinfra/vec.c:67
#6 0x7fa243201ffe in _vec_resize_inline (numa_id=,
data_align=, header_bytes=,
data_bytes=, length_increment=,
v=)
at /vpp/src/vppinfra/vec.h:172
#7 serialize_vector_write (m=, s=0x7fa1c87e7280)
at /vpp/src/vppinfra/serialize.c:903
#8 serialize_vector_write (m=, s=0x7fa1c87e7280)
at /vpp/src/vppinfra/serialize.c:897
#9 0x7fa243201cee in serialize_write_not_inline (m=0x7fa1c87e7220,
s=0x7fa1c87e7280, n_bytes_to_write=4,
flags=)
at /vpp/src/vppinfra/serialize.c:729
#10 0x7fa243390ede in serialize_stream_read_write (flags=2, n_bytes=4,
s=0x7fa1c87e7280, header=0x7fa1c87e7220)
at /vpp/src/vppinfra/serialize.h:140
#11 serialize_get (n_bytes=4, m=0x7fa1c87e7220)
at /vpp/src/vppinfra/serialize.h:180
#12 serialize_integer (n_bytes=4, x=, m=0x7fa1c87e7220)
at /vpp/src/vppinfra/serialize.h:187
#13 vl_api_serialize_message_table (am=0x7fa2433a4f40 ,
vector=vector@entry=0x0)
at /vpp/src/vlibapi/api_shared.c:213
#14 0x7fa2433913b5 in vl_msg_api_trace_save (am=am@entry=0x7fa2433a4f40
, which=which@entry=VL_API_TRACE_RX,
---Type to continue, or q to quit---
fp=fp@entry=0x562d89b34bb0)
at /vpp/src/vlibapi/api_shared.c:262
#15 0x7fa243393856 in vl_msg_api_post_mortem_dump ()
at /vpp/src/vlibapi/api_shared.c:976
#16 0x562d867a0be9 in os_panic ()
at /vpp/src/vpp/vnet/main.c:374
#17 0x7fa2431cf7c5 in mspace_free (msp=0x7fa1fa29e010,
mem=0x7fa1fa2a7eb0)
at /vpp/src/vppinfra/dlmalloc.c:4512
#18 0x7fa2431cfce2 in mspace_put (msp=, p_arg=p_arg@entry
=0x7fa1fa2a7eb8)
at /vpp/src/vppinfra/dlmalloc.c:4321
#19 0x7fa24322cf55 in clib_mem_free (p=0x7fa1fa2a7eb8)
at /vpp/src/vppinfra/mem.h:224
#20 vec_resize_allocate_memory (v=v@entry=0x7fa1fa2a7ec0,
length_increment=, data_bytes=,
header_bytes=8, header_bytes@entry=0, data_align=data_align@entry=64,
numa_id=numa_id@entry=255)
at /vpp/src/vppinfra/vec.c:119
#21 0x7fa2432e186c in _vec_resize_inline (numa_id=,
data_align=, header_bytes=,
data_bytes=, length_increment=,
v=)
at /vpp/src/vppinfra/vec.h:172
#22 vlib_validate_combined_counter (cm=0x7fa1fe7dc880, index=index@entry
=356)
at /vpp/src/vlib/counter.c:116
#23 0x7fa2413d7b09 in vnet_create_sw_interface_no_callbacks
(vnm=vnm@entry=0x7fa241ae5200 ,
template=template@entry=0x7fa1c87e7620)
at /vpp/src/vnet/interface.c:571
#24 0x7fa2413db081 in vnet_register_interface (vnm=vnm@entry=0x7fa241ae5200
,
dev_class_index=dev_class_index@entry=6,
dev_instance=dev_instance@entry=177,
hw_class_index=23,
hw_instance=hw_instance@entry=355)
at /vpp/src/vnet/interface.c:815
#25 0x7fa24140b75a in ethernet_register_interface
(vnm=vnm@entry=0x7fa241ae5200
, dev_class_index=6,
dev_instance=177, address=address@entry=0x7fa200ce4e60 "\002\376'\371",
,
hw_if_index_return=hw_if_index_return@entry=0x7fa200ce4e00,
flag_change=flag_change@entry=0x7fa241895cd0 )
at /vpp/src/vnet/ethernet/interface.c:349
#26 l2_bvi_create
For loopback :
#0 0x7fa23f185d47 in sched_yield () from /lib64/libc.so.6
#1 0x7fa2431cbffe in spin_acquire_lock (sl=sl@entry=0x7fa1fa29e384)
at /vpp/src/vppinfra/dlmalloc.c:468
#2 0x7fa2431cd948 in mspace_malloc ()
at /vpp/src/vppinfra/dlmalloc.c:4416
#3 0x7fa2431cf077 in mspace_get_aligned (msp=0x7fa1fa29e010,
n_user_data_bytes=92, n_user_data_bytes@entry=72,
align=, align@entry=8, align_offset=align_offset@entry=8)
at /vpp/src/vppinfra/dlmalloc.c:4254
#4 0x7fa24322ce75 in clib_mem_alloc_aligned_at_offset
(os_out_of_memory_on_failure=1, align_offset=8, align=8, size=72)
at /vpp/src/vppinfra/mem.h:142
#5 vec_resize_allocate_memory (v=v@entry=0x0,
length_increment=length_increment@entry=64, data_bytes=72,
Re: [vpp-dev] Issue with tap FDs of bvi interface.
Hi Stanislav, I debug it further. Here are the steps 1> In my config I am creating a veth interface in kernel 2> for that interface I am creating a hostif interface using "create host-interface name " 3> This intern create 4 fds in "show unix files" 4> [image: image.png] 5> I think this 59 fd is fd of af_packet socket for hostif. Correct me if I am wrong. 6> but I don't see any inode entry for it in /proc//fd 7> So according to my understanding for other tap creation it tries to take 59 as free fd and allocate 8> that happens to be in bvi tap interface creation 9> and that causes traffic flow issues. Do you see its a valid analysis? Please provide your comments and let me know your thoughts on this. Thanks, Pragya On Tue, Feb 28, 2023 at 4:13 PM Pragya Nand Bhagat via lists.fd.io wrote: > Hi Stanislav, > > Thanks for the response. > Please find the response inline > > > Do you see any errors in `show log`? > >>>>[Pragya] No I don't see any error log > > Do you see this fd 59 in `show unix files`? > >>>>[Pragya] Yes, I can see 59 in show unix files > "show unix files" fetch the fd from "/proc/self/fd/" > but if we go and see /proc//fd we don't see any file inode being > created. > > So according to OS 59 is never assigned and for subsequent interface > creation it try to have that same tap fd which is 59 here. > I think that causes the issue where the traffic flow is not OK. > > Can you suggest how I can debug and address this issue? > > Thanks, > Pragya > > > On Fri, Feb 24, 2023 at 3:24 PM Stanislav Zaikin > wrote: > >> Hello Pragya, >> >> Do you see any errors in `show log`? >> Do you see this fd 59 in `show unix files`? >> >> On Fri, 24 Feb 2023 at 07:59, Pragya Nand Bhagat < >> pragya.nand.bhaga...@gmail.com> wrote: >> >>> Hi All, >>> >>> I'm using an older version of vpp 20.09 . >>> When I create a bvi interface using bvi create cli. >>> A corresponding tap is created with same name as follows: >>> >>> >>> >>> *itf-pair: [19] bvi100 tap-39-bvi100 bvi100 960 type tap * >>> >>> But one FD of the tap interface is *missing* when I check in linux. >>> >>> vpp# *show tap tap-39-bvi100* >>> >>> Interface: tap-39-bvi100 (ifindex 40) >>> >>> name "bvi100" >>> >>> host-ns "(nil)" >>> >>> host-mac-addr: e4:43:4b:21:f3:86 >>> >>> *vhost-fds 213 214* >>> >>> * tap-fds 59* >>> >>> gso-enabled 0 >>> >>> csum-enabled 0 >>> >>> >>> In above output there should be 3 FDs associated with the tap but* one >>> of them is missing.* >>> >>> [root@0-9 /]# ls -l /proc/37/fd | grep 59 >>> >>> lrwx-- 1 root root 64 Feb 23 12:03 159 -> /dev/vhost-net >>> >>> *FD 59 is missing*, as a result of which packet transfer between linux >>> and mdp is not happening. >>> >>> Is there some checkin/patch to fix this issue? >>> Any help in debugging this issue will be helpful . >>> >>> Thanks >>> Pragya Nand >>> >>> >>> >>> >> >> -- >> Best regards >> Stanislav Zaikin >> >> >> >> > > > -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#22630): https://lists.fd.io/g/vpp-dev/message/22630 Mute This Topic: https://lists.fd.io/mt/97201480/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
Re: [vpp-dev] Issue with tap FDs of bvi interface.
Hi Stanislav, Thanks for the response. Please find the response inline Do you see any errors in `show log`? >>>>[Pragya] No I don't see any error log Do you see this fd 59 in `show unix files`? >>>>[Pragya] Yes, I can see 59 in show unix files "show unix files" fetch the fd from "/proc/self/fd/" but if we go and see /proc//fd we don't see any file inode being created. So according to OS 59 is never assigned and for subsequent interface creation it try to have that same tap fd which is 59 here. I think that causes the issue where the traffic flow is not OK. Can you suggest how I can debug and address this issue? Thanks, Pragya On Fri, Feb 24, 2023 at 3:24 PM Stanislav Zaikin wrote: > Hello Pragya, > > Do you see any errors in `show log`? > Do you see this fd 59 in `show unix files`? > > On Fri, 24 Feb 2023 at 07:59, Pragya Nand Bhagat < > pragya.nand.bhaga...@gmail.com> wrote: > >> Hi All, >> >> I'm using an older version of vpp 20.09 . >> When I create a bvi interface using bvi create cli. >> A corresponding tap is created with same name as follows: >> >> >> >> *itf-pair: [19] bvi100 tap-39-bvi100 bvi100 960 type tap * >> >> But one FD of the tap interface is *missing* when I check in linux. >> >> vpp# *show tap tap-39-bvi100* >> >> Interface: tap-39-bvi100 (ifindex 40) >> >> name "bvi100" >> >> host-ns "(nil)" >> >> host-mac-addr: e4:43:4b:21:f3:86 >> >> *vhost-fds 213 214* >> >> * tap-fds 59* >> >> gso-enabled 0 >> >> csum-enabled 0 >> >> >> In above output there should be 3 FDs associated with the tap but* one >> of them is missing.* >> >> [root@0-9 /]# ls -l /proc/37/fd | grep 59 >> >> lrwx-- 1 root root 64 Feb 23 12:03 159 -> /dev/vhost-net >> >> *FD 59 is missing*, as a result of which packet transfer between linux >> and mdp is not happening. >> >> Is there some checkin/patch to fix this issue? >> Any help in debugging this issue will be helpful . >> >> Thanks >> Pragya Nand >> >> >> >> > > -- > Best regards > Stanislav Zaikin > > > > -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#22629): https://lists.fd.io/g/vpp-dev/message/22629 Mute This Topic: https://lists.fd.io/mt/97201480/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] Issue with tap FDs of bvi interface.
Hi All, I'm using an older version of vpp 20.09 . When I create a bvi interface using bvi create cli. A corresponding tap is created with same name as follows: *itf-pair: [19] bvi100 tap-39-bvi100 bvi100 960 type tap * But one FD of the tap interface is *missing* when I check in linux. vpp# *show tap tap-39-bvi100* Interface: tap-39-bvi100 (ifindex 40) name "bvi100" host-ns "(nil)" host-mac-addr: e4:43:4b:21:f3:86 *vhost-fds 213 214* * tap-fds 59* gso-enabled 0 csum-enabled 0 In above output there should be 3 FDs associated with the tap but* one of them is missing.* [root@0-9 /]# ls -l /proc/37/fd | grep 59 lrwx-- 1 root root 64 Feb 23 12:03 159 -> /dev/vhost-net *FD 59 is missing*, as a result of which packet transfer between linux and mdp is not happening. Is there some checkin/patch to fix this issue? Any help in debugging this issue will be helpful . Thanks Pragya Nand -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#22621): https://lists.fd.io/g/vpp-dev/message/22621 Mute This Topic: https://lists.fd.io/mt/97201480/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
Re: [vpp-dev] unknown entry coming up in l2fib
Hi , As I was using an older version(20.09) it had an issue in function l2fib_make_key. It works in latest version. Thanks Pragya Nand Bhagat On Tue, Dec 27, 2022 at 10:05 AM Pragya Nand Bhagat < pragya.nand.bhaga...@gmail.com> wrote: > Hi All, > > I'm trying to configure a bridge and a corresponding bvi by function calls > from inside linux-cp plugin. > > Following are the function calls that I make: > > *For creating bridge_domain:* > l2_bridge_domain_add_del_args_t _a, *a = &_a; > clib_memset (a, 0, sizeof (*a)); > a->is_add = op_flag;//for add or delete > a->bd_id = bd_id;// 100 > //default values > a->flood = 1; > a->uu_flood = 1; > a->forward = 1; > a->learn = 1; > a->arp_term = 0; > a->arp_ufwd = 0; > a->mac_age = 0; > a->bd_tag = 0x0; > bd_add_del(a); > > *For creating bvi:* > l2_bvi_create (bd_id, , _sw_if_index);//bd_id is the > bridge_domain id > >//mac is a custom map > > *For moving bvi to the bridge_domain:* > set_int_l2_mode (vm, vnm, MODE_L2_BRIDGE, bvi_sw_if_index, > bd_id/*bd_index*/, L2_BD_PORT_TYPE_BVI, 0/*shg*/, 0) > > After above step following is the l2fib output: > > vpp# show l2fib verbose > Mac-Address BD-Idx If-Idx BSN-ISN Age(min) static filter bvi > Interface-Name > 00:00:00:00:00:001 39 0/0 no * - * >bvi100 > L2FIB total/learned entries: 1/0 Last scan time: 0.e0sec Learn > limit: 4194304 > > Any particular reason or step that I'm missing because of which > above behaviour occurs. > > > Thank You > Pragya Nand > > > > > -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#22442): https://lists.fd.io/g/vpp-dev/message/22442 Mute This Topic: https://lists.fd.io/mt/95899048/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] unknown entry coming up in l2fib
Hi All, I'm trying to configure a bridge and a corresponding bvi by function calls from inside linux-cp plugin. Following are the function calls that I make: *For creating bridge_domain:* l2_bridge_domain_add_del_args_t _a, *a = &_a; clib_memset (a, 0, sizeof (*a)); a->is_add = op_flag;//for add or delete a->bd_id = bd_id;// 100 //default values a->flood = 1; a->uu_flood = 1; a->forward = 1; a->learn = 1; a->arp_term = 0; a->arp_ufwd = 0; a->mac_age = 0; a->bd_tag = 0x0; bd_add_del(a); *For creating bvi:* l2_bvi_create (bd_id, , _sw_if_index);//bd_id is the bridge_domain id //mac is a custom map *For moving bvi to the bridge_domain:* set_int_l2_mode (vm, vnm, MODE_L2_BRIDGE, bvi_sw_if_index, bd_id/*bd_index*/, L2_BD_PORT_TYPE_BVI, 0/*shg*/, 0) After above step following is the l2fib output: vpp# show l2fib verbose Mac-Address BD-Idx If-Idx BSN-ISN Age(min) static filter bvi Interface-Name 00:00:00:00:00:001 39 0/0 no * - * bvi100 L2FIB total/learned entries: 1/0 Last scan time: 0.e0sec Learn limit: 4194304 Any particular reason or step that I'm missing because of which above behaviour occurs. Thank You Pragya Nand -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#22389): https://lists.fd.io/g/vpp-dev/message/22389 Mute This Topic: https://lists.fd.io/mt/95899048/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] qwery regarding lcp
Hi All, Is there a provision to create lcp pair between already existing interface(vlan) in host and an loopback interface . Example: interface on host root@mavenir-Default-string:/# ip link show Vlan100 26981: Vlan100@Bridge: mtu 9100 qdisc noqueue state UP mode DEFAULT grou0 link/ether a4:bf:01:89:9d:cb brd ff:ff:ff:ff:ff:ff interface on vpp is a loopback interface created by foll command: create loopback interface instance 100 which creates loop100 Thanks Pragya Nand -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#22158): https://lists.fd.io/g/vpp-dev/message/22158 Mute This Topic: https://lists.fd.io/mt/94933342/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
Re: [vpp-dev] option to drop untagged /tagged packet in vpp.
Hi All, Has anyone faced similar issue in the past? where they try to drop all untagged packets coming to a interface ? or when they try to create a subinterface for untagged packet ? Thanks Pragya Nand On Fri, Aug 26, 2022 at 8:04 AM Pragya Nand Bhagat < pragya.nand.bhaga...@gmail.com> wrote: > Hi All, > > Is there a way in vpp to drop untagged packets received on a interface > which has different subinterfaces for different vlan. > When I create a subinterface using : > vpp# create sub-interfaces host-ve_b 100 > host-ve_b.100 > vpp# create sub-interfaces host-ve_b 10 untagged > create sub-interfaces: vlan is already in use > > > Will I be able to drop untagged packets if I create subinterface for > untagged packet and disable it (assuming above command works). > > Is there a better way to drop untagged packets coming on a interface ? > > If I create a subinterface for untagged and a default interface(for all > other tagged vlan) then will the main interface not receive any packets as > all scenarios are handled. > > Thanks > Pragya Nand > -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21835): https://lists.fd.io/g/vpp-dev/message/21835 Mute This Topic: https://lists.fd.io/mt/93262804/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] option to drop untagged /tagged packet in vpp.
Hi All, Is there a way in vpp to drop untagged packets received on a interface which has different subinterfaces for different vlan. When I create a subinterface using : vpp# create sub-interfaces host-ve_b 100 host-ve_b.100 vpp# create sub-interfaces host-ve_b 10 untagged create sub-interfaces: vlan is already in use Will I be able to drop untagged packets if I create subinterface for untagged packet and disable it (assuming above command works). Is there a better way to drop untagged packets coming on a interface ? If I create a subinterface for untagged and a default interface(for all other tagged vlan) then will the main interface not receive any packets as all scenarios are handled. Thanks Pragya Nand -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21825): https://lists.fd.io/g/vpp-dev/message/21825 Mute This Topic: https://lists.fd.io/mt/93262804/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
Re: [vpp-dev] VPP crashing when lcp is enabled and I try to add an interface to a linux bridge.
Hi Matthew, Yes I meant the same. Automatically creating a bridge domain in VPP and adding/removing member interfaces based on netlink messages. Thank You Pragya Nand On Wed, Aug 24, 2022 at 12:25 AM Matthew Smith via lists.fd.io wrote: > > On Tue, Aug 23, 2022 at 7:40 AM Pragya Nand Bhagat < > pragya.nand.bhaga...@gmail.com> wrote: > >> Hi Matthew, >> >> Thanks for looking into this issue. >> After applying the patch the crash is not seen. >> >> However as mentioned earlier, we have faced this issue when configuring >> the bridge domain and adding a member port to it. >> >>1. create a bridge [ brctl addbr 100] >>2. try adding a interface to it [ brctl addif 100 Ethernet0 ] >> >> *Is there any plan to support this in VPP Linux cp* >> >> > Hi Pragya, > > What do you mean by "support this"? Are you talking about automatically > creating a bridge domain in VPP and adding/removing member interfaces based > on netlink messages? Or something else? > > -Matt > > > >> On Sat, Aug 20, 2022 at 2:13 AM Matthew Smith via lists.fd.io > netgate@lists.fd.io> wrote: >> >>> >>> Hi Pragya, >>> >>> This patch should fix it - https://gerrit.fd.io/r/c/vpp/+/36961. Can >>> you apply it to your build and confirm whether it resolves the issue? >>> >>> Thanks, >>> -Matt >>> >>> >>> On Wed, Aug 17, 2022 at 6:55 AM Pragya Nand Bhagat < >>> pragya.nand.bhaga...@gmail.com> wrote: >>> >>>> Hi All, >>>> >>>> I'm seeing a crash in VPP when we try to add a port to a bridge . >>>> VPP is running with the lcp plugin. >>>> >>>> >>>> lcp default netns '' >>>> lcp lcp-auto-subint off >>>> lcp lcp-sync on >>>> lcp del-static-on-link-down off >>>> lcp del-dynamic-on-link-down off >>>> >>>> itf-pair: [0] port0/0 tap1 Ethernet0 96 type tap >>>> Following are the steps to recreate : >>>> >>>> >>>> >>>>1. create a bridge [ brctl addbr 100] >>>>2. try adding a interface to it [ brctl addif 100 Ethernet0 ] >>>>3. VPP crashes >>>> >>>> We got the following stack trace . >>>> >>>> >>>> Thread 1 "vpp_main" received signal SIGSEGV, Segmentation fault. >>>> 0x7f1239448c30 in nl_addr_get_family () from >>>> /lib/x86_64-linux-gnu/libnl-3.so.200 >>>> (gdb) bt >>>> #0 0x7f1239448c30 in nl_addr_get_family () from >>>> /lib/x86_64-linux-gnu/libnl-3.so.200 >>>> #1 0x7f12393b9025 in lcp_router_mk_addr (rna=0x0, >>>> ia=0x7f123703ade0) at /vpp/src/plugins/linux-cp/lcp_router.c:589 >>>> #2 lcp_router_neigh_add (rn=0x674b80) at >>>> /vpp/src/plugins/linux-cp/lcp_router.c:763 >>>> #3 0x7f12393c2bcd in nl_neigh_add (rn=0x674b80, arg=>>> out>) at /vpp/src/plugins/linux-cp/lcp_nl.c:232 >>>> #4 nl_route_dispatch (obj=0x674b80, arg=) at >>>> /vpp/src/plugins/linux-cp/lcp_nl.c:311 >>>> #5 0x7f123944e8ee in ?? () from >>>> /lib/x86_64-linux-gnu/libnl-3.so.200 >>>> #6 0x7f1239404bb4 in ?? () from >>>> /lib/x86_64-linux-gnu/libnl-route-3.so.200 >>>> #7 0x7f123944b5c3 in nl_cache_parse () from >>>> /lib/x86_64-linux-gnu/libnl-3.so.200 >>>> #8 0x7f12394502cb in nl_msg_parse () from >>>> /lib/x86_64-linux-gnu/libnl-3.so.200 >>>> #9 0x7f12393c2033 in nl_route_process_msgs () at >>>> /vpp/src/plugins/linux-cp/lcp_nl.c:344 >>>> #10 nl_route_process (vm=0x7f123ac6d700, node=, >>>> frame=) at /vpp/src/plugins/linux-cp/lcp_nl.c:557 >>>> #11 0x7f127b1dbbe7 in vlib_process_bootstrap (_a=) >>>> at /vpp/src/vlib/main.c:1222 >>>> #12 0x7f127b0e4258 in clib_calljmp () at >>>> /vpp/src/vppinfra/longjmp.S:123 >>>> #13 0x7f1239245d60 in ?? () >>>> #14 0x7f127b1d38b0 in vlib_process_startup (vm=0x7f123ac6d700, >>>> p=0x7f123c12bd80, f=0x0) at /vpp/src/vlib/main.c:1247 >>>> #15 dispatch_process (vm=0x7f123ac6d700, p=0x7f123c12bd80, f=0x0, >>>> last_time_stamp=) at /vpp/src/vlib/main.c:1303 >>>> #16 0x in ?? () >>>> >>>> >>>> Looks like interface netlink event is not handled for scenarios when an >>>> interface is added to bridge. >>>> Please revert if any other information is required. >>>> >>>> >>>> >>>> Thank You >>>> >>>> Pragya Nand >>>> >>>> >>>> >>>> >>> >>> >>> >> >> >> > > > -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21819): https://lists.fd.io/g/vpp-dev/message/21819 Mute This Topic: https://lists.fd.io/mt/93078810/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
Re: [vpp-dev] VPP crashing when lcp is enabled and I try to add an interface to a linux bridge.
Hi Matthew, Thanks for looking into this issue. After applying the patch the crash is not seen. However as mentioned earlier, we have faced this issue when configuring the bridge domain and adding a member port to it. 1. create a bridge [ brctl addbr 100] 2. try adding a interface to it [ brctl addif 100 Ethernet0 ] *Is there any plan to support this in VPP Linux cp* If there is any existing solution, could you please guide us? Thanks Pragya Nand Bhagat On Sat, Aug 20, 2022 at 2:13 AM Matthew Smith via lists.fd.io wrote: > > Hi Pragya, > > This patch should fix it - https://gerrit.fd.io/r/c/vpp/+/36961. Can you > apply it to your build and confirm whether it resolves the issue? > > Thanks, > -Matt > > > On Wed, Aug 17, 2022 at 6:55 AM Pragya Nand Bhagat < > pragya.nand.bhaga...@gmail.com> wrote: > >> Hi All, >> >> I'm seeing a crash in VPP when we try to add a port to a bridge . >> VPP is running with the lcp plugin. >> >> >> lcp default netns '' >> lcp lcp-auto-subint off >> lcp lcp-sync on >> lcp del-static-on-link-down off >> lcp del-dynamic-on-link-down off >> >> itf-pair: [0] port0/0 tap1 Ethernet0 96 type tap >> Following are the steps to recreate : >> >> >> >>1. create a bridge [ brctl addbr 100] >>2. try adding a interface to it [ brctl addif 100 Ethernet0 ] >>3. VPP crashes >> >> We got the following stack trace . >> >> >> Thread 1 "vpp_main" received signal SIGSEGV, Segmentation fault. >> 0x7f1239448c30 in nl_addr_get_family () from >> /lib/x86_64-linux-gnu/libnl-3.so.200 >> (gdb) bt >> #0 0x7f1239448c30 in nl_addr_get_family () from >> /lib/x86_64-linux-gnu/libnl-3.so.200 >> #1 0x7f12393b9025 in lcp_router_mk_addr (rna=0x0, ia=0x7f123703ade0) >> at /vpp/src/plugins/linux-cp/lcp_router.c:589 >> #2 lcp_router_neigh_add (rn=0x674b80) at >> /vpp/src/plugins/linux-cp/lcp_router.c:763 >> #3 0x7f12393c2bcd in nl_neigh_add (rn=0x674b80, arg=) >> at /vpp/src/plugins/linux-cp/lcp_nl.c:232 >> #4 nl_route_dispatch (obj=0x674b80, arg=) at >> /vpp/src/plugins/linux-cp/lcp_nl.c:311 >> #5 0x7f123944e8ee in ?? () from /lib/x86_64-linux-gnu/libnl-3.so.200 >> #6 0x7f1239404bb4 in ?? () from >> /lib/x86_64-linux-gnu/libnl-route-3.so.200 >> #7 0x7f123944b5c3 in nl_cache_parse () from >> /lib/x86_64-linux-gnu/libnl-3.so.200 >> #8 0x7f12394502cb in nl_msg_parse () from >> /lib/x86_64-linux-gnu/libnl-3.so.200 >> #9 0x7f12393c2033 in nl_route_process_msgs () at >> /vpp/src/plugins/linux-cp/lcp_nl.c:344 >> #10 nl_route_process (vm=0x7f123ac6d700, node=, >> frame=) at /vpp/src/plugins/linux-cp/lcp_nl.c:557 >> #11 0x7f127b1dbbe7 in vlib_process_bootstrap (_a=) at >> /vpp/src/vlib/main.c:1222 >> #12 0x7f127b0e4258 in clib_calljmp () at >> /vpp/src/vppinfra/longjmp.S:123 >> #13 0x7f1239245d60 in ?? () >> #14 0x7f127b1d38b0 in vlib_process_startup (vm=0x7f123ac6d700, >> p=0x7f123c12bd80, f=0x0) at /vpp/src/vlib/main.c:1247 >> #15 dispatch_process (vm=0x7f123ac6d700, p=0x7f123c12bd80, f=0x0, >> last_time_stamp=) at /vpp/src/vlib/main.c:1303 >> #16 0x in ?? () >> >> >> Looks like interface netlink event is not handled for scenarios when an >> interface is added to bridge. >> Please revert if any other information is required. >> >> >> >> Thank You >> >> Pragya Nand >> >> >> >> > > > -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21812): https://lists.fd.io/g/vpp-dev/message/21812 Mute This Topic: https://lists.fd.io/mt/93078810/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] VPP crashing when lcp is enabled and I try to add an interface to a linux bridge.
Hi All, I'm seeing a crash in VPP when we try to add a port to a bridge . VPP is running with the lcp plugin. lcp default netns '' lcp lcp-auto-subint off lcp lcp-sync on lcp del-static-on-link-down off lcp del-dynamic-on-link-down off itf-pair: [0] port0/0 tap1 Ethernet0 96 type tap Following are the steps to recreate : 1. create a bridge [ brctl addbr 100] 2. try adding a interface to it [ brctl addif 100 Ethernet0 ] 3. VPP crashes We got the following stack trace . Thread 1 "vpp_main" received signal SIGSEGV, Segmentation fault. 0x7f1239448c30 in nl_addr_get_family () from /lib/x86_64-linux-gnu/libnl-3.so.200 (gdb) bt #0 0x7f1239448c30 in nl_addr_get_family () from /lib/x86_64-linux-gnu/libnl-3.so.200 #1 0x7f12393b9025 in lcp_router_mk_addr (rna=0x0, ia=0x7f123703ade0) at /vpp/src/plugins/linux-cp/lcp_router.c:589 #2 lcp_router_neigh_add (rn=0x674b80) at /vpp/src/plugins/linux-cp/lcp_router.c:763 #3 0x7f12393c2bcd in nl_neigh_add (rn=0x674b80, arg=) at /vpp/src/plugins/linux-cp/lcp_nl.c:232 #4 nl_route_dispatch (obj=0x674b80, arg=) at /vpp/src/plugins/linux-cp/lcp_nl.c:311 #5 0x7f123944e8ee in ?? () from /lib/x86_64-linux-gnu/libnl-3.so.200 #6 0x7f1239404bb4 in ?? () from /lib/x86_64-linux-gnu/libnl-route-3.so.200 #7 0x7f123944b5c3 in nl_cache_parse () from /lib/x86_64-linux-gnu/libnl-3.so.200 #8 0x7f12394502cb in nl_msg_parse () from /lib/x86_64-linux-gnu/libnl-3.so.200 #9 0x7f12393c2033 in nl_route_process_msgs () at /vpp/src/plugins/linux-cp/lcp_nl.c:344 #10 nl_route_process (vm=0x7f123ac6d700, node=, frame=) at /vpp/src/plugins/linux-cp/lcp_nl.c:557 #11 0x7f127b1dbbe7 in vlib_process_bootstrap (_a=) at /vpp/src/vlib/main.c:1222 #12 0x7f127b0e4258 in clib_calljmp () at /vpp/src/vppinfra/longjmp.S:123 #13 0x7f1239245d60 in ?? () #14 0x7f127b1d38b0 in vlib_process_startup (vm=0x7f123ac6d700, p=0x7f123c12bd80, f=0x0) at /vpp/src/vlib/main.c:1247 #15 dispatch_process (vm=0x7f123ac6d700, p=0x7f123c12bd80, f=0x0, last_time_stamp=) at /vpp/src/vlib/main.c:1303 #16 0x in ?? () Looks like interface netlink event is not handled for scenarios when an interface is added to bridge. Please revert if any other information is required. Thank You Pragya Nand -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21802): https://lists.fd.io/g/vpp-dev/message/21802 Mute This Topic: https://lists.fd.io/mt/93078810/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] Facing issue in inter bridge routing .
Hi All, Inside vpp I have two bridge-domains and each of them has a loopback interface as bvi. Each bridge domain also has a host-interface . Following is the set of command used. Linux CLIs to configure veth: ip link add ve_A type veth peer name ve_B ip link add ve_C type veth peer name ve_D ifconfig ve_A 1.1.1.1/24 ifconfig ve_C 2.2.2.2/24 CLIs on VPP create host-interface name ve_B create host-interface name ve_D set interface state host-ve_B up set interface state host-ve_D up create loopback interface create loopback interface set interface ip address loop0 1.1.1.2/24 set interface ip address loop1 2.2.2.3/24 set interface state loop0 up set interface state loop1 up create bridge-domain 100 create bridge-domain 200 set interface l2 bridge host-ve_B 100 set interface l2 bridge host-ve_D 200 set interface l2 bridge loop0 100 bvi set interface l2 bridge loop1 200 bvi [image: image.png] ping -I ve_A 1.1.1.2 from host is working. ping -I ve_C 2.2.2.3 from host is working. but *ping -I ve_A 2.2.2.3 fails.* vpp# show mode l3 local0 l2 bridge host-ve_B bd_id 100 shg 0 l2 bridge host-ve_D bd_id 200 shg 0 l2 bridge loop0 bd_id 100 bvi shg 0 l2 bridge loop1 bd_id 200 bvi shg 0 vpp# show interface address host-ve_B (up): L2 bridge bd-id 100 idx 1 shg 0 host-ve_D (up): L2 bridge bd-id 200 idx 2 shg 0 local0 (dn): loop0 (up): L2 bridge bd-id 100 idx 1 shg 0 bvi L3 1.1.1.2/24 ip4 table-id 4 fib-idx 1 loop1 (up): L2 bridge bd-id 200 idx 2 shg 0 bvi L3 2.2.2.3/24 ip4 table-id 4 fib-idx 1 And following is the output of show errors: vpp# show error Count Node Reason Severity 3 arp-reply RX interface is unnumbered to diffe error 3 af-packet-inputtimed out block error 3 af-packet-input total received block error 3 l2-learn L2 learn packets error 3 l2-input L2 input packets error 3 l2-flood L2 flood packets error Following is the packet trace. vpp# show trace --- Start of thread 0 vpp_main --- Packet 1 17:47:50:154354: af-packet-input af_packet: hw_if_index 1 rx-queue 0 next-index 4 block 132: address 0x7fb423c4 version 2 seq_num 133 pkt_num 0 tpacket3_hdr: status 0x2001 len 42 snaplen 42 mac 92 net 106 sec 0x62f4832a nsec 0x31ace5eb vlan 0 vlan_tpid 0 vnet-hdr: flags 0x00 gso_type 0x00 hdr_len 0 gso_size 0 csum_start 0 csum_offset 0 17:47:50:154368: ethernet-input ARP: 8a:f5:4b:3c:07:19 -> ff:ff:ff:ff:ff:ff 17:47:50:154376: l2-input l2-input: sw_if_index 1 dst ff:ff:ff:ff:ff:ff src 8a:f5:4b:3c:07:19 [l2-learn l2-flood ] 17:47:50:154386: l2-learn l2-learn: sw_if_index 1 dst ff:ff:ff:ff:ff:ff src 8a:f5:4b:3c:07:19 bd_index 1 17:47:50:154390: l2-flood l2-flood: sw_if_index 1 dst ff:ff:ff:ff:ff:ff src 8a:f5:4b:3c:07:19 bd_index 1 17:47:50:154395: arp-input request, type ethernet/IP4, address size 6/4 8a:f5:4b:3c:07:19/1.1.1.1 -> 00:00:00:00:00:00/2.2.2.3 17:47:50:154397: arp-reply request, type ethernet/IP4, address size 6/4 8a:f5:4b:3c:07:19/1.1.1.1 -> 00:00:00:00:00:00/2.2.2.3 17:47:50:154409: error-drop rx:loop0 17:47:50:154411: drop arp-reply: RX interface is unnumbered to different subnet Packet 2 17:47:51:174342: af-packet-input af_packet: hw_if_index 1 rx-queue 0 next-index 4 block 133: address 0x7fb423c5 version 2 seq_num 134 pkt_num 0 tpacket3_hdr: status 0x2001 len 42 snaplen 42 mac 92 net 106 sec 0x62f4832b nsec 0x32721b32 vlan 0 vlan_tpid 0 vnet-hdr: flags 0x00 gso_type 0x00 hdr_len 0 gso_size 0 csum_start 0 csum_offset 0 17:47:51:174362: ethernet-input ARP: 8a:f5:4b:3c:07:19 -> ff:ff:ff:ff:ff:ff 17:47:51:174370: l2-input l2-input: sw_if_index 1 dst ff:ff:ff:ff:ff:ff src 8a:f5:4b:3c:07:19 [l2-learn l2-flood ] 17:47:51:174374: l2-learn l2-learn: sw_if_index 1 dst ff:ff:ff:ff:ff:ff src 8a:f5:4b:3c:07:19 bd_index 1 17:47:51:174377: l2-flood l2-flood: sw_if_index 1 dst ff:ff:ff:ff:ff:ff src 8a:f5:4b:3c:07:19 bd_index 1 17:47:51:174381: arp-input request, type ethernet/IP4, address size 6/4 8a:f5:4b:3c:07:19/1.1.1.1 -> 00:00:00:00:00:00/2.2.2.3 17:47:51:174384: arp-reply request, type ethernet/IP4, address size 6/4 8a:f5:4b:3c:07:19/1.1.1.1 -> 00:00:00:00:00:00/2.2.2.3 17:47:51:174396: error-drop rx:loop0 17:47:51:174398: drop arp-reply: RX interface is unnumbered to different subnet I also tried adding both these loopback to a different ip table . but couldn't get it working. Do I need to enable routing functionality ? Thanks Pragya Nand -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21789):
Re: [vpp-dev] Bridge-domain function and usage.
Hi Steven, I'm sending unknown unicast packets with source and destination mac as : IP4: a4:bf:01:89:9d:cf -> ab:cd:ef:ab:cd:ef 802.1q vlan 100 Please have a look in the packet trace. Thanks Pragya Nand On Tue, Aug 2, 2022 at 4:51 AM steven luong via lists.fd.io wrote: > Pragya, > > > > UU-Flood stands for Unknown Unicast Flooding. It does not flood multicast > or broadcast packets. You need “Flooding” on to flood multicast/broadcast > packets. > > > > Steven > > > > *From: * on behalf of Pragya Nand Bhagat < > pragya.nand.bhaga...@gmail.com> > *Reply-To: *"vpp-dev@lists.fd.io" > *Date: *Monday, August 1, 2022 at 2:59 AM > *To: *"vpp-dev@lists.fd.io" > *Subject: *Re: [vpp-dev] Bridge-domain function and usage. > > > > Hi Stanislav, > > Following is the trace : > > > > with flooding enabled: > > > > vpp# show bridge-domain 100 det > BD-ID Index BSN Age(min) Learning U-Forwrd UU-Flood Flooding > ARP-Term arp-ufwd Learn-co Learn-li BVI-Intf >100 1 0off onon > floodon offoff1 >16777216 N/A > span-l2-input l2-input-classify l2-input-feat-arc l2-policer-classify > l2-input-acl vpath-input-l2 l2-ip-qos-record l2-input-vtr l2-learn l2-rw > l2-fwd l2-flood l2-flood l2-output > >Interface If-idx ISN SHG BVI TxFlood > VLAN-Tag-Rewrite > port0/0 1 10- * > none > port0/1 2108 0- * > none > port0/2 3 10- * > none > > Packet 1 > > 00:11:47:356640: dpdk-input > port0/0 rx queue 0 > buffer 0xfc9fc3: current data 0, length 60, buffer-pool 0, ref-count 1, > trace handle 0x0 >ext-hdr-valid > PKT MBUF: port 0, nb_segs 1, pkt_len 60 > buf_len 2176, data_len 60, ol_flags 0x180, data_off 128, phys_addr > 0x3f27f140 > packet_type 0x0 l2_len 0 l3_len 0 outer_l2_len 0 outer_l3_len 0 > rss 0x0 fdir.hi 0x0 fdir.lo 0x0 > Packet Offload Flags > PKT_RX_IP_CKSUM_GOOD (0x0080) IP cksum of RX pkt. is valid > PKT_RX_IP_CKSUM_NONE (0x0090) no IP cksum of RX pkt. > PKT_RX_L4_CKSUM_GOOD (0x0100) L4 cksum of RX pkt. is valid > PKT_RX_L4_CKSUM_NONE (0x0108) no L4 cksum of RX pkt. > ARP: a4:bf:01:89:9d:cf -> ff:ff:ff:ff:ff:ff > request, type ethernet/IP4, address size 6/4 > a4:bf:01:89:9d:cf/30.30.30.6 -> 01:03:05:07:09:00/30.30.30.6 > 00:11:47:356665: ethernet-input > frame: flags 0x3, hw-if-index 1, sw-if-index 1 > ARP: a4:bf:01:89:9d:cf -> ff:ff:ff:ff:ff:ff > 00:11:47:357793: l2-input > l2-input: sw_if_index 1 dst ff:ff:ff:ff:ff:ff src a4:bf:01:89:9d:cf > [l2-learn l2-flood ] > 00:11:47:357796: l2-learn > l2-learn: sw_if_index 1 dst ff:ff:ff:ff:ff:ff src a4:bf:01:89:9d:cf > bd_index 1 > 00:11:47:357799: l2-flood > l2-flood: sw_if_index 1 dst ff:ff:ff:ff:ff:ff src a4:bf:01:89:9d:cf > bd_index 1 > l2-flood: sw_if_index 1 dst ff:ff:ff:ff:ff:ff src a4:bf:01:89:9d:cf > bd_index 1 > 00:11:47:357804: l2-output > l2-output: sw_if_index 3 dst ff:ff:ff:ff:ff:ff src a4:bf:01:89:9d:cf > data 08 06 00 01 08 00 06 04 00 01 a4 bf > l2-output: sw_if_index 2 dst ff:ff:ff:ff:ff:ff src a4:bf:01:89:9d:cf > data 08 06 00 01 08 00 06 04 00 01 a4 bf > 00:11:47:357807: port0/2-output > port0/2 > ARP: a4:bf:01:89:9d:cf -> ff:ff:ff:ff:ff:ff > request, type ethernet/IP4, address size 6/4 > a4:bf:01:89:9d:cf/30.30.30.6 -> 01:03:05:07:09:00/30.30.30.6 > 00:11:47:357812: port0/1-output > port0/1 > ARP: a4:bf:01:89:9d:cf -> ff:ff:ff:ff:ff:ff > request, type ethernet/IP4, address size 6/4 > a4:bf:01:89:9d:cf/30.30.30.6 -> 01:03:05:07:09:00/30.30.30.6 > 00:11:47:357813: port0/2-tx > port0/2 tx queue 0 > buffer 0xfc9fc3: current data 0, length 60, buffer-pool 0, ref-count 1, > trace handle 0x0 >ext-hdr-valid >l2-hdr-offset 0 l3-hdr-offset 14 > PKT MBUF: port 0, nb_segs 1, pkt_len 60 > buf_len 2176, data_len 60, ol_flags 0x180, data_off 128, phys_addr > 0x3f27f140 > packet_type 0x0 l2_len 0 l3_len 0 outer_l2_len 0 outer_l3_len 0 > rss 0x0 fdir.hi 0x0 fdir.lo 0x0 > Packet Offload Flags > PKT_RX_IP_CKSUM_GOOD (0x0080) IP cksum of RX pkt. is valid > PKT_RX_IP_CKSUM_NONE (0x0090) no IP cksum of RX pkt. > PKT_RX_L4_CKSUM_GOOD (0x0100) L4 cksum of RX pkt. is valid > PKT_RX_L4_CKSUM_NONE (0x0108) no L4 cksum of RX pkt. > ARP: a4:bf:01:89:9d:cf -> ff:ff:ff:ff:ff:ff > request, type ethernet/IP4, address size 6/4
Re: [vpp-dev] Bridge-domain function and usage.
ta_len 1446, ol_flags 0x180, data_off 128, phys_addr 0x3f04fac0 packet_type 0x211 l2_len 0 l3_len 0 outer_l2_len 0 outer_l3_len 0 rss 0x0 fdir.hi 0x0 fdir.lo 0x0 Packet Offload Flags PKT_RX_IP_CKSUM_GOOD (0x0080) IP cksum of RX pkt. is valid PKT_RX_IP_CKSUM_NONE (0x0090) no IP cksum of RX pkt. PKT_RX_L4_CKSUM_GOOD (0x0100) L4 cksum of RX pkt. is valid PKT_RX_L4_CKSUM_NONE (0x0108) no L4 cksum of RX pkt. Packet Types RTE_PTYPE_L2_ETHER (0x0001) Ethernet packet RTE_PTYPE_L3_IPV4 (0x0010) IPv4 packet without extension headers RTE_PTYPE_L4_UDP (0x0200) UDP packet IP4: a4:bf:01:89:9d:cf -> ab:cd:ef:ab:cd:ef 802.1q vlan 100 UDP: 30.30.30.6 -> 40.40.40.5 tos 0x00, ttl 64, length 1428, checksum 0xe907 dscp CS0 ecn NON_ECN fragment id 0x0001 UDP: 1025 -> 12 length 1408, checksum 0xfb26 01:01:13:194994: ethernet-input frame: flags 0x3, hw-if-index 1, sw-if-index 1 IP4: a4:bf:01:89:9d:cf -> ab:cd:ef:ab:cd:ef 802.1q vlan 100 01:01:13:195001: l2-input l2-input: sw_if_index 1 dst ab:cd:ef:ab:cd:ef src a4:bf:01:89:9d:cf [l2-learn ] 01:01:13:195004: l2-learn l2-learn: sw_if_index 1 dst ab:cd:ef:ab:cd:ef src a4:bf:01:89:9d:cf bd_index 1 01:01:13:195006: feature-bitmap-drop feat_bitmap_drop: feature bitmap 0x0001 01:01:13:195007: error-drop rx:port0/0 01:01:13:195009: drop feature-bitmap-drop: L2 feature forwarding disabled If we disable flooding in a Bridge Domain then will it not forward,broadcast or multicast any packets .although UU-Flood is enabled. If you could please explain this. Thank You Pragya Nand On Fri, Jul 22, 2022 at 5:18 PM Stanislav Zaikin wrote: > Hi Pragya, > > Could you attach a trace? > > On Fri, 22 Jul 2022 at 13:14, Pragya Nand Bhagat < > pragya.nand.bhaga...@gmail.com> wrote: > >> Hi All, >> >> Please have a look on the below issue: >> I have attached my conf file. >> >> Or is the bridge-domain functionality broken . >> >> Thanks >> Pragya Nand >> >> On Wed, Jul 20, 2022 at 9:57 AM Pragya Nand Bhagat via lists.fd.io >> wrote: >> >>> Hi All, >>> >>> I'm trying to create a bridge domain and add ports to it for layer 2 >>> functionality. >>> There are 3 physical ports. >>> I have used the following commands : >>> >>> create bridge-domain 100 >>> set interface l2 bridge port0/0 100 >>> set interface l2 bridge port0/1 100 >>> set interface l2 bridge port0/2 100 >>> >>> set bridge-domain flood 100 disable >>> >>> vpp# show bridge-domain >>> BD-ID Index BSN Age(min) Learning U-Forwrd UU-Flood >>> Flooding ARP-Term arp-ufwd Learn-co Learn-li BVI-Intf >>>100 1 0 off onon >>>flood offoffoff 1 >>>16777216 N/A >>> >>> I have the expectation if I disable flooding on the bridge domain and as >>> UU-Flood is enabled it'll still flood on all the ports part of bridge >>> domain. >>> >>> Above is not happening . >>> >>> Also when I try to add mac in l2fib on port using : >>> >>> l2fib add 52:54:00:53:18:55 200 port0/0 static >>> >>> vpp should unicast the packet which is also not happening . >>> >>> I'm using vpp version 22.06 . >>> >>> Please suggest how to achieve this or if I missed something . >>> >>> Thank You >>> Pragya Nand >>> >>> >>> >>> >>> >>> >>> >>> >> >> >> > > -- > Best regards > Stanislav Zaikin > > > > -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21749): https://lists.fd.io/g/vpp-dev/message/21749 Mute This Topic: https://lists.fd.io/mt/92498639/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
Re: [vpp-dev] Bridge-domain function and usage.
Hi All, Please have a look on the below issue: I have attached my conf file. Or is the bridge-domain functionality broken . Thanks Pragya Nand On Wed, Jul 20, 2022 at 9:57 AM Pragya Nand Bhagat via lists.fd.io wrote: > Hi All, > > I'm trying to create a bridge domain and add ports to it for layer 2 > functionality. > There are 3 physical ports. > I have used the following commands : > > create bridge-domain 100 > set interface l2 bridge port0/0 100 > set interface l2 bridge port0/1 100 > set interface l2 bridge port0/2 100 > > set bridge-domain flood 100 disable > > vpp# show bridge-domain > BD-ID Index BSN Age(min) Learning U-Forwrd UU-Flood Flooding > ARP-Term arp-ufwd Learn-co Learn-li BVI-Intf >100 1 0 off onon > flood offoffoff 1 > 16777216 N/A > > I have the expectation if I disable flooding on the bridge domain and as > UU-Flood is enabled it'll still flood on all the ports part of bridge > domain. > > Above is not happening . > > Also when I try to add mac in l2fib on port using : > > l2fib add 52:54:00:53:18:55 200 port0/0 static > > vpp should unicast the packet which is also not happening . > > I'm using vpp version 22.06 . > > Please suggest how to achieve this or if I missed something . > > Thank You > Pragya Nand > > > > > > > > vpp.conf Description: Binary data -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21706): https://lists.fd.io/g/vpp-dev/message/21706 Mute This Topic: https://lists.fd.io/mt/92498639/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] Bridge-domain function and usage.
Hi All, I'm trying to create a bridge domain and add ports to it for layer 2 functionality. There are 3 physical ports. I have used the following commands : create bridge-domain 100 set interface l2 bridge port0/0 100 set interface l2 bridge port0/1 100 set interface l2 bridge port0/2 100 set bridge-domain flood 100 disable vpp# show bridge-domain BD-ID Index BSN Age(min) Learning U-Forwrd UU-Flood Flooding ARP-Term arp-ufwd Learn-co Learn-li BVI-Intf 100 1 0 offonon flood off off off116777216 N/A I have the expectation if I disable flooding on the bridge domain and as UU-Flood is enabled it'll still flood on all the ports part of bridge domain. Above is not happening . Also when I try to add mac in l2fib on port using : l2fib add 52:54:00:53:18:55 200 port0/0 static vpp should unicast the packet which is also not happening . I'm using vpp version 22.06 . Please suggest how to achieve this or if I missed something . Thank You Pragya Nand -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21686): https://lists.fd.io/g/vpp-dev/message/21686 Mute This Topic: https://lists.fd.io/mt/92498639/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/1480452/21656/631435203/xyzzy [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
Re: [vpp-dev] Help needed in bringing up memif with shm_open.
Hi ,
Thanks Ben and Daniel for looking into this.
Both the issues which I was facing is resolved now.
steps that i took was :
I added "shm_unlink" after "shm_open call".
For the rx issue which I was getting , as suggested by Ben i used gdb to
debug into the libmemif.
and I realised a "memif_refill_queue" call is required on slave before
master can transmit data, calling memif_refill_queue() on slave provides
buffers for master.
Are you able to run with shm_open without using shm_unlink ?
If you could please post what was your observation.
Thank You
Pragya Nand
On Wed, May 25, 2022 at 1:16 PM Daniel Béreš via lists.fd.io wrote:
> Hi,
>
> To sync up, can you run loopback example?
>
> I tried to reproduce your problem on 3.10.0-229.1.2.rt56.141.2.el7_1.x86_64
> but I got different result.
>
> diff --git a/extras/libmemif/src/CMakeLists.txt
> b/extras/libmemif/src/CMakeLists.txt
> index ddb8a52..a11a65f 100644
> --- a/extras/libmemif/src/CMakeLists.txt
> +++ b/extras/libmemif/src/CMakeLists.txt
> @@ -41,6 +41,12 @@ if(LIB_BSD)
>target_link_libraries(memif ${LIB_BSD})
> endif()
>
> +find_library(LIB_LRT rt)
> +if(LIB_BSD)
> + add_compile_definitions(HAS_LIB_LRT)
> + target_link_libraries(memif ${LIB_LRT})
> +endif()
> +
> foreach(file ${MEMIF_HEADERS})
>get_filename_component(dir ${file} DIRECTORY)
> install(
> diff --git a/extras/libmemif/src/main.c b/extras/libmemif/src/main.c
> index 21b3994..132ce8d 100644
> --- a/extras/libmemif/src/main.c
> +++ b/extras/libmemif/src/main.c
> @@ -184,6 +184,7 @@ memif_get_version_str ()
>
> #define DBG_TX_BUF (0)
> #define DBG_RX_BUF (1)
> +#define MEMIF_DBG_SHM 1
>
> #ifdef MEMIF_DBG_SHM
> static void
> @@ -1234,13 +1235,17 @@ memif_add_region (memif_connection_t *conn, uint8_t
> has_buffers)
>r->region_size = (has_buffers == 0) ? r->buffer_offset : r->buffer_offset +
> conn->run_args.buffer_size * (1 << conn->run_args.log2_ring_size) *
> (conn->run_args.num_s2m_rings + conn->run_args.num_m2s_rings);
> -
> +/*
>if ((r->fd = memfd_create ("memif region 0", MFD_ALLOW_SEALING)) == -1)
> return memif_syscall_error_handler (errno);
> +*/
> + if ((r->fd = shm_open ("memif region 0", O_RDWR | O_CREAT, S_IRWXU)) == -1)
> +return memif_syscall_error_handler (errno);
>
> +/*
>if ((fcntl (r->fd, F_ADD_SEALS, F_SEAL_SHRINK)) == -1)
> return memif_syscall_error_handler (errno);
> -
> +*/
>if ((ftruncate (r->fd, r->region_size)) == -1)
> return memif_syscall_error_handler (errno);
>
>
>
>
>
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#21468): https://lists.fd.io/g/vpp-dev/message/21468
Mute This Topic: https://lists.fd.io/mt/91224655/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-
Re: [vpp-dev] Help needed in bringing up memif with shm_open.
Hi, I'm able to send and receive packet when I compile with gcc version (Ubuntu 8.4.0-1ubuntu1~18.04) , GLIBC 2.27 and kernel 5.4.0-66-lowlatency. but when I compile with gcc gcc (GCC) 5.4.0, GLIBC 2.17 , and kernel 3.10.0-rt56 it fails at memif_buffer_alloc. Any idea why this behaviour can be . Thanks for all the suggestions and insights. Thank You Pragya Nand On Fri, May 20, 2022 at 10:26 AM Pragya Nand Bhagat via lists.fd.io wrote: > Hi All, > > I'm trying to connect two existing container application by using memif. > Unfortunately these are old codes and i'm stuck with old glibc and kernel . > So I'm trying to use shm_open instead of memfd_create . > > The issue that I'm facing is are as follows : > > It throws following error while trying to do tx : > > memif_tx_burst : Invalid argument. (This comes from src/main.c 1746 - 1750) > > When I try to do a rx I get the interrupt but the received packet is 0. > > It would be a great help if someone knows changes which are required for > libmemif to work with shm_open. > > I'm working on same and will share changes if it works. > > Thank You > > Pragya Nand Bhagat > > > > > -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21425): https://lists.fd.io/g/vpp-dev/message/21425 Mute This Topic: https://lists.fd.io/mt/91224655/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] Help needed in bringing up memif with shm_open.
Hi All, I'm trying to connect two existing container application by using memif. Unfortunately these are old codes and i'm stuck with old glibc and kernel . So I'm trying to use shm_open instead of memfd_create . The issue that I'm facing is are as follows : It throws following error while trying to do tx : memif_tx_burst : Invalid argument. (This comes from src/main.c 1746 - 1750) When I try to do a rx I get the interrupt but the received packet is 0. It would be a great help if someone knows changes which are required for libmemif to work with shm_open. I'm working on same and will share changes if it works. Thank You Pragya Nand Bhagat -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#21419): https://lists.fd.io/g/vpp-dev/message/21419 Mute This Topic: https://lists.fd.io/mt/91224655/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] issue in bringing up vhost-user interface using startup.conf file.
Hi All, I'm able to bring up the vhost-user interface after vpp is up using following command: create vhost-user socket /tmp/virt_sock/vhost3.sock server and it is reflected in "show vhost-user" vpp# show vhost-user Virtio vhost-user interfaces Global: coalesce frames 32 time 1e-3 Number of rx virtqueues in interrupt mode: 0 Number of GSO interfaces: 0 Thread 0: Polling queue count 1 Interface: VirtualEthernet0/0/0 (ifindex 2) Number of qids 2 virtio_net_hdr_sz 0 features mask (0xfffbdfffa27c): features (0x0): protocol features (0x0) socket filename /tmp/virt_sock/vhost3.sock type server errno "Success" rx placement: thread 0 on vring 1, polling tx placement Memory regions (total 0) *Issue is *when I try to bring up vhost-user interface using dpdk section in startup.conf. I add the following lines in dpdk section: log-level 8 socket-mem 1024,1024 huge-dir /mnt/huge_c0 vdev eth_vhost0,iface=/tmp/virt_sock/vhost4.sock The interface comes up : vpp# show interface Name IdxState MTU (L3/IP4/IP6/MPLS) Counter Count GigabitEthernet4/0/2 1 down 9000/0/0/0 VhostEthernet12 down 9000/0/0/0 local00 down 0/0/0/0 but I'm not able to see interface in output of "*show vhost-user".* *Are these two interface same or we need something else in dpdk section for an equivalent interface ?* *Also what shall we add in dpdk section to bringup a memif interface ?* *Is there some document related to dpdk section in vpp's startup.conf which has detailed description ?* It'll be a great help . Thank You Pragya Nand -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#20891): https://lists.fd.io/g/vpp-dev/message/20891 Mute This Topic: https://lists.fd.io/mt/89337122/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] Facing issue with forming packets in dpdk-testpmd.
Hi All, I'm trying to form a specific traffic flow with dpdk-testpmd before starting traffic using "*start tx_first*". I'm able to configure the destination mac using " *set eth-peer** (port_id) (peer_addr)*". I was not able to find a similar command for setting the destination ip address. I also found : testpmd> set fwd (io|mac|macswap|flowgen| \ rxonly|txonly|csum|icmpecho|noisy) • flowgen: Multi-flow generation mode. Originates a number of flows (with varying destination IP addresses), and terminate receive traffic. but I could not find any example usage . If someone could please point out how to use this option or how to configure dst-ip for a traffic originating from dpdk-testpmd. Thank You Pragya Nand Bhagat -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#20882): https://lists.fd.io/g/vpp-dev/message/20882 Mute This Topic: https://lists.fd.io/mt/89288568/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] Issue while developing a container application using libmemif.
Hi All, I'm writing an application to send and receive packets over the memif interface. I'm following steps mentioned in the following document to create server and client interface: https://s3-docs.fd.io/vpp/22.02/interfacing/libmemif/gettingstarted_doc.html The difference in server and client interface creation is in the variable memif_conn_args_t cargs; : https://s3-docs.fd.io/vpp/22.02/interfacing/libmemif/gettingstarted_doc.html#:~:text=memif_conn_args_t%20cargs%3B where is_master is set as 1 in case of server and as 0 in case of client. The issue that i'm facing is after i receive on_connect call back in server and i try to send 10 packets i get MEMIF_ERR_NOBUF_RING on server when it calls memif_buffer_alloc and program terminates from there. sender function : https://gerrit.fd.io/r/c/vpp/+/30573/8/extras/libmemif/examples/common/sender.c but if i add a sleep(1) before memif_buffer_alloc it works. I went through the following similar question and added the suggested change but still facing the same issue. https://lists.fd.io/g/vpp-dev/topic/some_questions_about_libmemif/35012940?p= Am I missing something . Thank You Pragya Nand Bhagat -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#20835): https://lists.fd.io/g/vpp-dev/message/20835 Mute This Topic: https://lists.fd.io/mt/88966380/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] Unable to find libmemif examples.
Hi All, I'm trying to use libmemif to create interface between container application and vpp based virtual router There are documents stating the usage of example apps : icmp_responder, icmp_responder-epoll, icmp_responder-mt . I'm not able to find the code for these apps so that i can build and understand the usage. Anyone knows where can i find these example apps ? Thank You Pragya Nand -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#20802): https://lists.fd.io/g/vpp-dev/message/20802 Mute This Topic: https://lists.fd.io/mt/88804525/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
Re: [vpp-dev] Request: Help in selecting interface for inter-container networking.
Hi Ben, Thanks a lot for the reply. could you please briefly elaborate on what scenarios do people use virto-user - vhost-user ? I see that DPDK document lists virtio_user for container networking. I'm referring the following link: https://doc.dpdk.org/guides/howto/virtio_user_for_container_networking.html Thank You Pragya Nand On Wed, Jan 19, 2022 at 2:33 PM Benoit Ganne (bganne) wrote: > Hi, > > > I'm trying to create an inter-container link A<-->B for high speed data > > transfer. > > I'm having a Container application on one side and Virtual-router(based > on > > vpp) on the other side. > > I have a choice between a virtio-user - vhost-user pair or use a MemIf > > interface. > > We usually use memif which was designed exactly for this. Memif is lighter > than virtio and your application can use eg. libmemif. > > Best > ben > -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#20755): https://lists.fd.io/g/vpp-dev/message/20755 Mute This Topic: https://lists.fd.io/mt/88530304/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
[vpp-dev] Request: Help in selecting interface for inter-container networking.
Hi All, I'm trying to create an inter-container link A<-->B for high speed data transfer. [image: image.png] I'm having a Container application on one side and Virtual-router(based on vpp) on the other side. I have a choice between a virtio-user - vhost-user pair or use a MemIf interface. Can anyone suggest which approach is better and support it with reason ? Thank You Pragya Nand Bhagat -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#20751): https://lists.fd.io/g/vpp-dev/message/20751 Mute This Topic: https://lists.fd.io/mt/88530304/21656 Group Owner: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-
