netdev - using iperf over a veth pair

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Message-ID: <CAFmWiaSu-Foij1EGm5kby7gjDd2qeaR5Fo1oAVus2GRmkEar7w@mail.gmail.com>
Date:	Sun, 30 Aug 2015 16:49:21 +0300
From:	Ido Barkan <ibarkan@...hat.com>
To:	netdev@...r.kernel.org
Subject: using iperf over a veth pair

Hi everyone,
I am trying to use iperf over a veth pair. while iperf is pleased (it
reports a  suspicious very high bandwidth), according to tcpdump, no
traffic is going via the veth pair.

Also 'ping -I' refuses to send a ping via my veth ('destination is
unreachable' iirc).

/sys/class/net../statistics also shows no high counters.

Also, even when connecting to veth pairs to a Linux bridge and running
iperf 'via the bridge', tcpdump on the bridge yields nothing.
an important thing to noe here is that iperf api only accepts ip
addresses, not interfaces.
Routing ruls seems right, as they are automatically being created upon
assigning ip addresses to the veth pair ends.

Does the kernel short-circuits traffic here? How can I Tell it to pass
traffic via my virtual devices?

--
Thanks,
Ido Barkan
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html