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 > <fcoras.lists=gmail....@lists.fd.io> 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 <theoliviadun...@gmail.com >> <mailto:theoliviadun...@gmail.com>> 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: vpp-dev+ow...@lists.fd.io Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com] -=-=-=-=-=-=-=-=-=-=-=-