Re: CPU count vs. CPU clock speed

always snacked up the interrupts...and if you were
some poor Oracle shadow process with affinity to that
CPU, uh, well, let's just say that you get an unfair
amount of starvation...and oh my the chaos that ensues
when processes held latches on the "pregnant CPUs".

And the CPU time spent servicing interrupts (or at least their top halves) was reported under the unlucky process'es system time?



Nowdays? APIC my friend, APIC...oh, and, aaargh, there are mitigating efforts like intrd (not initrd) on Sol, etc ...

I'll probably have to do some reading on it, but does APIC allow dynamically specifying which interrupts are picked up/sent so which CPU?


Tanel.

--
http://www.freelists.org/webpage/oracle-l


Other related posts: