On 2012-11-26, Mihai Popescu <[email protected]> wrote: >> Yes - it is a work around for broken/incomplete emulation or incorrect >> interrupt routing. Always doing this would result in a performance hit on all >> systems. As shown in your dmesg, both em(4) devices are using the same IRQ: > > Long time ago I tried five Intel network cards in the same computer,
em0 at pci2 dev 4 function 0 "Intel PRO/1000MT (82546EB)" rev 0x03: apic 0 int 17, address 00:12:c0:08:39:ee em1 at pci2 dev 4 function 1 "Intel PRO/1000MT (82546EB)" rev 0x03: apic 0 int 17, address 00:12:c0:08:39:ef em2 at pci3 dev 4 function 0 "Intel PRO/1000MT (82546EB)" rev 0x03: apic 0 int 17, address 00:12:c0:08:39:ec em3 at pci3 dev 4 function 1 "Intel PRO/1000MT (82546EB)" rev 0x03: apic 0 int 17, address 00:12:c0:08:39:ed em4 at pci3 dev 5 function 0 "Intel PRO/1000MT (82546EB)" rev 0x03: apic 0 int 18, address 00:12:c0:08:39:ea em5 at pci3 dev 5 function 1 "Intel PRO/1000MT (82546EB)" rev 0x03: apic 0 int 18, address 00:12:c0:08:39:eb (OK admittedly they are all on one card...)
