dummynet, em driver, device polling issues :-((

[Ferdinand Goldmann]

Jeremie Le Hen wrote:

>>> em0: Missed Packets = 39
>>> em0: Receive No Buffers = 2458
> 
> "Receive No Buffers" grows when polling is enabled and it's somewhat
> a normal behaviour.

After running with polling enabled for two hours, the statistics were:
em0: Missed Packets = 2159959
em0: Receive No Buffers = 32458174
em0: Good Packets Rcvd = 499051709
em0: Good Packets Xmtd = 466744805

That's quite a lot of missed packets in only ~two hours :-(

> I think you can slightly increase the HZ value to decrease this
> error count, but I'm not sure this will improve the bandwidth in a
> great order of magnitude.

Hm it would be interesting how to optimize the HZ value in order to prevent
lost packets, because this is not good at all.

> I know that Intel GigE NICs have a smart way to to interrupt throttling
> (that's what tx_int_delay, tx_abs_int_delay, rx_int_delay and
> rx_abs_int_delay stand for).  You should try to tune them through
> dev.em.[0-9]+. sysctl tree.
> These tresholds are very well explained here :
> http://www.intel.com/design/network/applnots/ap450.pdf

Thank you for the pointer, I will have a look at this and see whether this
helps, and post the results.

-- 
>> Ferdinand Goldmann                                   ////  |          |
>> EMail:  Ferdinand.Goldmann at zid.uni-linz.ac.at       |--00  |    UNIX  |
>> Tel. : +43/732/2468/9398 Fax. : +43/732/2468/9397   C   ^  |          |
>> EMail:  Ferdinand.Goldmann at zid.uni-linz.ac.at        \ ~/  ~~~|~~~~~~~~
>> PGP D4CF 8AA4 4B2A 7B88 65CA  5EDC 0A9B FA9A 13EA B993| |-----3