High cpu interrrupt



  • Hi, i have added a quad port fast ethernet card, this is the dmesg log:

    pci3: <acpi pci="" bus="">on pcib3
    sf0: <adaptec 10="" ana-62044="" 100basetx="">port 0xcc00-0xccff mem 0xf7f80000-0xf7ffffff irq 5 at device 4.0 on pci3
    miibus1: <mii bus="">on sf0
    ukphy0: <generic ieee="" 802.3u="" media="" interface="">on miibus1
    ukphy0:  10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto
    sf0: Ethernet address: 00:00:d1:ed:66:7d
    sf1: <adaptec 10="" ana-62044="" 100basetx="">port 0xc800-0xc8ff mem 0xf7f00000-0xf7f7ffff irq 5 at device 5.0 on pci3
    miibus2: <mii bus="">on sf1
    ukphy1: <generic ieee="" 802.3u="" media="" interface="">on miibus2
    ukphy1:  10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto
    sf1: Ethernet address: 00:00:d1:ed:66:7e
    sf2: <adaptec 10="" ana-62044="" 100basetx="">port 0xc400-0xc4ff mem 0xf7e80000-0xf7efffff irq 5 at device 6.0 on pci3
    miibus3: <mii bus="">on sf2
    ukphy2: <generic ieee="" 802.3u="" media="" interface="">on miibus3
    ukphy2:  10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto
    sf2: Ethernet address: 00:00:d1:ed:66:7f
    sf3: <adaptec 10="" ana-62044="" 100basetx="">port 0xc000-0xc0ff mem 0xf7e00000-0xf7e7ffff irq 10 at device 7.0 on pci3
    miibus4: <mii bus="">on sf3
    ukphy3: <generic ieee="" 802.3u="" media="" interface="">on miibus4
    ukphy3:  10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto
    sf3: Ethernet address: 00:00:d1:ed:66:80

    This was because i need to connect another 3 networks, after i enabled nat for each of them, the cpu interrrupt rate goes crazy, aroud 80% with peaks at 100%
    Before it was at 15% - 25%, i didnt customize anything, just pluged in the card and confiured the aditional opt interfaces, did i  miss something?
    Regards</generic></mii></adaptec></generic></mii></adaptec></generic></mii></adaptec></generic></mii></adaptec></acpi>



  • Is there traffic on these?  If so, and if you're not running polling, I'd expect an increase in interrupts - you've just added 4 more devices that generate them after all!



  • yes, there is 2-3 Mb in every one. So it is "normal", there is nothing i can do?



  • Normal varies a lot - you've missed out just about all useful information to help define that, however…

    Try enabling polling.  It can hurt throughput, but it does reduce interrupts.  You'd probably also find a better result with a better card, such as an Intel Server NIC.


Log in to reply