Content-Type: multipart/mixed; boundary="===============8562313334701762278==" MIME-Version: 1.0 From: Paolo Abeni To: mptcp at lists.01.org Subject: [MPTCP] Re: [PATCH v3 00/13] mptcp: support for queuing data at mptcp-level Date: Mon, 05 Oct 2020 08:31:24 +0200 Message-ID: <1ae96fe38254afe04d222abc665ee258b77de77b.camel@redhat.com> In-Reply-To: 876a5ca0-9627-7fab-5006-50f48d45c2d6@tessares.net X-Status: X-Keywords: X-UID: 6192 --===============8562313334701762278== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable On Sat, 2020-10-03 at 18:35 +0200, Matthieu Baerts wrote: > Hi Paolo, > = > On 03/10/2020 12:48, Matthieu Baerts wrote: > > - Results: d157a0e07d13..d577ff3cf895 > > = > > tests + export are in progress! > = > I got two errors with the selftests: > = > = > # selftests: net/mptcp: diag.sh > # no msk on netns creation [ ok ] > # after MPC handshake [ ok ] > # ....chk remote_key [ ok ] > # ....chk no fallback [ ok ] > # check fallback [ ok ] > # many msk socket present [ fail ] expected = > 200 found 201 > not ok 4 selftests: net/mptcp: diag.sh # exit=3D6 This is still to be investigated, I guess It has to do with the newly introduced msk socket timeout > # selftests: net/mptcp: simult_flows.sh > # balanced bwidth 4693 max 5005 [ OK ] > # balanced bwidth - reverse direction 4493 max 5005 [ OK ] > # balanced bwidth with unbalanced delay 5283 max 5005 [ = > fail ] > # client exit code 0, server 0 > # \nnetns ns3-0-W3sXrt socket stat for 10003: > # State Recv-Q Send-Q Local Address:Port Peer Address:Port Process = > = > # TIME-WAIT 0 0 10.0.3.3:10003 10.0.2.1:34523 = > timer:(timewait,59sec,0) > # = > # TIME-WAIT 0 0 10.0.3.3:10003 10.0.1.1:44230 = > timer:(timewait,59sec,0) > # = > # \nnetns ns1-0-W3sXrt socket stat for 10003: > # State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess > # -rw------- 1 root root 8388608 Oct 3 13:23 /tmp/tmp.IeFESgOht2 > # -rw------- 1 root root 8388608 Oct 3 13:24 /tmp/tmp.w7zJOAA5WT > # -rw------- 1 root root 81920 Oct 3 13:24 /tmp/tmp.bITD2uHm5f > # -rw------- 1 root root 81920 Oct 3 13:23 /tmp/tmp.fhMf6gzhah > # balanced bwidth with unbalanced delay - reverse direction 4560 max = > 5005 [ OK ] > not ok 5 selftests: net/mptcp: simult_flows.sh # exit=3D1 This is still under investigation, likely not easy to fix. We still have some out-of-[mptcp-level]window packet, expecially at connection start. I'm *guessing* they cause this b/w fluctuation. Cheers, Paolo --===============8562313334701762278==--