Re: data vs overhead bytes, netperf aggregate RR and retransmissions

On Tue, Aug 2, 2011 at 2:39 PM, Rick Jones [off-list ref] wrote:

driver: igb
version: 2.1.0-k2
firmware-version: 1.8-2
bus-info: 0000:05:00.0

One of the things fixed recently in netperf (top-of-trunk, beyond 2.5.0) is
I actually have reporting of per-connection TCP retransmissions working.  I
was looking at that, and noticed a bunch of retransmissions at the 256 burst
level with 24 concurrent netperfs.  I figured it was simple overload of say
the switch or the one port active on the SUT (I do have one system talking
to two, so perhaps some incast).  Burst 64 had retrans as well.  Burst 16
and below did not.  That pattern repeated at 12 concurrent netperfs, and 8,
and 4 and 2 and even 1 - yes, a single netperf aggregate TCP_RR test with a
burst of 64 was reporting TCP retransmissions.  No incasting issues there.
 The network was otherwise clean.

Rick, can you reboot and try with idle=poll OR set ethtool -C ethX rx-usecs 0
both tests would be interesting, possibly relating your issue to cpu
power management and/or interrupt throttling, or some combo of both.

Also please check the ethtool -S ethX stats from the hardware, and
include them in your reply.