ixgbe & msi/x

Luigi Rizzo rizzo at iet.unipi.it
Mon Jan 28 19:32:55 UTC 2013


On Mon, Jan 28, 2013 at 9:15 AM, Vijay Singh <vijju.singh at gmail.com> wrote:

> > just curious, is this happening under behyve or also native,
> > and is it always occurring or it is occasional ?
>
> Native, and it happens when the pps rate is high, even if the
> aggregate bandwidth is low.
>
>
that was my case too. I have not gone too far into my investigation but
should
note that not _all_ interrupts were lost; my symptoms were queue overflows
under netmap even at a low 2 Mpps, which with 2k entries in the rx ring
means
that the interrupt was delayed for more than 1ms, well above the moderation
delay.

With these symptoms I would normally blame the os scheduler,
but in this case it seems a bit hard given that the machine
has 4 cores at 2.8 GHz and no other processes running.


So just to clarify, which one of these symptoms did you see
1) no rx interrupts at all at any rx rate
2) occasional missing interrupts/drops as the rx pps increase
3) complete loss of rx interrupts above some pps threshold ?


cheers
luigi


More information about the freebsd-net mailing list