I am troubled by the number of data points flent reports for some pings and uploads in this setup. A typical ack-filter result, similar to rrul2 I posted before, looks like this:
Summary of rrul test run 'rrul_cakeeth_ds3_900mbit_45mbit_ack' (at 2017-11-29 14:37:5
5.719180):

                             avg       median          # data pts
 Ping (ms) ICMP   :       100.29       100.00 ms              337
 Ping (ms) UDP BE :       297.62       100.20 ms              156
 Ping (ms) UDP BK :       409.84       100.20 ms              109
 Ping (ms) UDP EF :       414.94       100.20 ms              121
 Ping (ms) avg    :       374.13       100.05 ms              343
 TCP download BE  :       206.39       217.48 Mbits/s         301
 TCP download BK  :       163.05       163.81 Mbits/s         301
 TCP download CS5 :       206.40       217.50 Mbits/s         301
 TCP download EF  :       203.18       215.23 Mbits/s         301
 TCP download avg :       194.75       202.59 Mbits/s         301
 TCP download sum :       779.02       810.36 Mbits/s         301
 TCP totals       :       781.55       810.66 Mbits/s         301
 TCP upload BE    :         1.86        24.68 Mbits/s          23
 TCP upload BK    :         0.15         1.72 Mbits/s          24
 TCP upload CS5   :         0.25         2.26 Mbits/s          30
 TCP upload EF    :         0.27         2.15 Mbits/s          29
 TCP upload avg   :         0.63         7.59 Mbits/s          36
 TCP upload sum   :         2.53        30.38 Mbits/s          36

Shouldn't all "# data pts" be ~300?

George

On Wed, Nov 29, 2017 at 9:34 AM, Georgios Amanakis <gamanakis@gmail.com> wrote:
With ack-filter-aggressive I get results similar to rrul1 in ~10% of the runs, 90% are similar to rrul2.
With ack-filter I haven't managed yet to get a rrul1 result, all of them are similar to rrul2.
Will experiment more today.

George

On Tue, Nov 28, 2017 at 11:01 PM, Dave Taht <dave.taht@gmail.com> wrote:
the astounding figure is dropping ~70% of all packets, and tcp still
works at all.

682411 pkt (dropped 1511579 ...)

is your 2nd result repeatable? What happens with just "ack-filter" not
aggressive?

I keep thinking that a way to coax more performance out of 40GigE+
might be to drop more acks (as correctly as possible) before they even
hit the server.