Forgot to mention that if my hunch is accurate, probably you should try
increasing tls’s fifo segment memory by adding a tls stanza to startup.conf,
e.g.:
tls { first-segment-size 4g }
Where 4g can be larger if you have lots of sessions.
Regards,
Florin
> On Sep 14, 2021, at 8:45 AM, Florin Coras via lists.fd.io
> <[email protected]> wrote:
>
> Hi Olivia,
>
> Could you try this with latest code? We’ve had a number of fixes go in over
> the past months, including the one that you’ve mentioned lower. Hard to say
> if the issue has been fixed as tls might ignore the dequeue notifications
> from tcp for some reason. If I were to guess, this [1] might help.
>
> Regards,
> Florin
>
> [1] https://gerrit.fd.io/r/c/vpp/+/32389
> <https://gerrit.fd.io/r/c/vpp/+/32389>
>
>> On Sep 14, 2021, at 5:57 AM, Olivia Dunham <[email protected]
>> <mailto:[email protected]>> wrote:
>>
>> During sudden burst of traffic, the TCP fifo gets full. When this happens
>> the openssl TLS app de-schedules the transport. But once the TCP data is
>> sent out, the TLS is not resuming. VPP ends up in a state where TCP fifo is
>> empty, but the TLS fifo is full and no more Tx happens on TLS fifo.
>>
>> VPP version: 21.01
>>
>> We came across this commit - session tls: deq notifications for custom tx
>> <https://github.com/FDio/vpp/commit/1e6a0f64653c8142fa7032aba127ab4894bafc3c>
>> Not sure what is the issue fixed by this commit, but It doesn't seem to fix
>> the above mentioned issue.
>>
>>
>
>
>
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#20132): https://lists.fd.io/g/vpp-dev/message/20132
Mute This Topic: https://lists.fd.io/mt/85600873/21656
Mute #vpp-hoststack:https://lists.fd.io/g/vpp-dev/mutehashtag/vpp-hoststack
Group Owner: [email protected]
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [[email protected]]
-=-=-=-=-=-=-=-=-=-=-=-
