Re: Load balancing across multiple network paths

"Also sprach Peter T. Breuer:"
> "Also sprach Nikos Gkorogiannis:"
> > After a reboot, and zero counters on the two interfaces (eth1 and eth2),
> > I run on the client 
> > 
> > # dd if=/dev/nda of=/dev/null bs=64k count=8k
> > 8192+0 records in
> > 8192+0 records out
> 
> That would be 64MB? Or about 48K full-sized ethernet packets.

Uh duh, I miscounted. bs 64k, not 8k.  512MB. 380K ethernet packets.

> 
> > <snip>
> > eth1      Link encap:Ethernet  HWaddr 00:04:75:AF:A1:C3
> >           RX packets:255815 errors:0 dropped:0 overruns:0 frame:0

255K of them.

> >           TX packets:130671 errors:0 dropped:0 overruns:0 carrier:0
> >           collisions:0 txqueuelen:1000
> 
> >           RX bytes:381316317 (363.6 MiB)  TX bytes:8981356 (8.5 MiB)
> >           Interrupt:10 Base address:0x1400
> > 
> > eth2      Link encap:Ethernet  HWaddr 00:04:75:AF:A5:C9
> >           RX packets:121458 errors:0 dropped:0 overruns:0 frame:0

122K more. About right.

> >           TX packets:62040 errors:0 dropped:0 overruns:0 carrier:0
> >           collisions:0 txqueuelen:1000
> >           RX bytes:180925040 (172.5 MiB)  TX bytes:4265598 (4.0 MiB)
> >           Interrupt:5 Base address:0x1480
> > 
> > which surprisingly shows a 2:1 ratio! /proc/nbdinfo says 

There  must be some reason why one is consistently slower than the
other. Which order are the interrupts attended in?

Peter