On Wed, 23 Mar 2005 12:48:07 +0200 (EET), Turcanu Bogdan
<[EMAIL PROTECTED]> wrote:
> vmstat -i
> interrupt total rate
> irq0: clk 3671536 999
> irq1: atkbd0 116 0
> irq8: rtc 469891 127
> irq11: fxp0 atapci0 4 0
> irq12: fxp1 3 0
> irq13: npx0 1 0
> irq14: ata0 11183 3
> irq15: ata1 46 0
> Total 4152780 1130
>
kern.polling.idle_poll/kern.polling.poll_in_trap ce valori au ? Pe
5.x am sesizat efecte negative atunci cind se face polling pe timpii
de idleness. Deci primul OID ar trebui sa fie 0. Mai am un amic care
s-a izbit de aceeasi problema (top care raporteaza load mare generat
de intreruperi), insa n-am gasit inca o explicatie academica. E drept,
nici n-am investigat :)
--
If it's there, and you can see it, it's real.
If it's not there, and you can see it, it's virtual.
If it's there, and you can't see it, it's transparent.
If it's not there, and you can't see it, you erased it.
__________________________________________________________
Send 'unsubscribe rofug' to [EMAIL PROTECTED] to unsubscribe
