Hi Vpp-Dev,

Need your help in understanding one the Memif related issue that we are facing 
in 18.10.
This code has been working in 18.01. As soon as we moved to 18.10, we are 
started seeing this issue.

When our graph node tries to send a message over Memif interface, the send is 
failing with a reason code "no free tx slots"

vpp# show node counters
   Count                    Node                  Reason
        81               memif0/0-tx              no free tx slots

Following is the "show memif" output for reference.

vpp# show memif
sockets
  id  listener    filename
  0   yes (1)     /run/vpp/memif.sock
 
interface memif0/0
  remote-name "Ctrlr"
  remote-interface "ctrlr_connection"
  socket-id 0 id 0 mode ip
  flags admin-up connected
  listener-fd 39 conn-fd 38
  num-s2m-rings 2 num-m2s-rings 2 buffer-size 0 num-regions 2
  region 0 size 131584 fd 40
  region 1 size 12288000 fd 41
    master-to-slave ring 0:
      region 0 offset 65792 ring-size 2048 int-fd 44
      head 2068 tail 20 flags 0x0000 interrupts 20
    master-to-slave ring 1:
      region 0 offset 98688 ring-size 2048 int-fd 45
      head 0 tail 0 flags 0x0000 interrupts 82
    slave-to-master ring 0:
      region 0 offset 0 ring-size 2048 int-fd 42
      head 102 tail 102 flags 0x0001 interrupts 0
    slave-to-master ring 1:
      region 0 offset 32896 ring-size 2048 int-fd 43
      head 0 tail 0 flags 0x0001 interrupts 0

We are creating the memif interface with the following command

vppctl create interface memif id 0 master ring-size 16 buffer-size 10240 
rx-queues 2 tx-queues 2 mode ip

Please let us know if something changed in 18.10 that we have to change the way 
we use memif.
Appreciate your inputs on this.

Thanks & Regards,
Satish
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#12784): https://lists.fd.io/g/vpp-dev/message/12784
Mute This Topic: https://lists.fd.io/mt/31100033/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Reply via email to