Date: Sun, 2 Feb 2014 23:25:00 -0800 From: hiren panchasara <hiren.panchasara@gmail.com> To: "freebsd-net@freebsd.org" <freebsd-net@freebsd.org>, Jack F Vogel <jfv@freebsd.org> Subject: Re: Errors using span interface on if_bridge(4) Message-ID: <CALCpEUG09C773XKWA=tpeE42AbEvF1y9ipqPROP3rZoe-ZNu9g@mail.gmail.com> In-Reply-To: <CALCpEUEZmMvVRAf8DtRBpPtYgZDB3ufNaAhDpmrnVaiPXv3veg@mail.gmail.com> References: <CALCpEUH7YHhG3gw0wrObsJux=PWmJu2K6_tzCbCfXQ21ENYHdw@mail.gmail.com> <CALCpEUEuXR7_Q8_zt2TjnsOqt_rYMH5do=UEjssqkj684Xdimg@mail.gmail.com> <CALCpEUFLwZ6vismFKgyo1Q_P4iwzxS%2BjBozTV%2BO1kvap6U8brQ@mail.gmail.com> <CALCpEUE4V-CXkT3R0tzr1K075RBX_HKHPF%2BP-WTT15FkH5cuQA@mail.gmail.com> <CALCpEUH-5vWoU-Q-fWsmUGLrS3H--4WXcbejf1TQc=ZNmFOXvQ@mail.gmail.com> <CALCpEUEZmMvVRAf8DtRBpPtYgZDB3ufNaAhDpmrnVaiPXv3veg@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Alright. I am having a "mind blown" moment right now. While reporting this checksum error issue, I always had ix3 (the culprit interface) being monitored via tcpdump in other tmux session. Something gotten into me and I stopped monitoring it and everything was kosher after that. Not a single checksum error! Just to be sure, I kldunloaded/loaded if_ixgbe (as I've built that as a module) to reset all the stat counters and ran my tests again using both iperf3 and netperf - and saw same behavior. If I start tcpdump on interface again, the dev.ix.3.mac_stats.checksum_errs starts going up. Stopping tcpdump would stop the counter from incrementing. Why is that happening? I have no clue. How/why is tcpdump affecting this interface traffic stats in such a way? Just as a recap, bridge0 has ix1 as a member and ix2 as a span interface. ix2 and ix3 are connected back to back so that I can monitor traffic coming to bridge0 on ix3 (as ix2 will forward it all being a span interface). cheers, Hiren
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CALCpEUG09C773XKWA=tpeE42AbEvF1y9ipqPROP3rZoe-ZNu9g>