[PATCH][RFC][0/2] per-CPU IDTs aka booting high irq count ia32 boxes

• Next message: Zwane Mwaikambo: "[PATCH][2.5][RFC][2/2] per node vector spaces"
• Previous message: Zwane Mwaikambo: "[PATCH][2.5][RFC][1/2] per-CPU IDTs"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

I'm currently tackling booting a box with over 8 IOAPICs which results in
320 interrupt sources. We won't be able to take all 320 obviously and
stuck with 255 but i have a scheme for trying to 'increase' the global
vector space by only installing vectors for irqs which the cpus on that
node will be servicing. To achieve this i've first setup per cpu IDTs and
then splitting up vector allocation to allocate per node.

I'm currently booting on a 16way but will be wiring up a 32way over the
weekend.

dmesg: http://function.linuxpower.ca/patches/numaq/dmesg-4quad-percpu_idt
mptable: http://function.linuxpower.ca/patches/numaq/mptables-numaq-4quad

I'd appreciate any comments on the following patches. Boot and run on UP,
SMP, NUMAQ/SMP

Thanks,
        Zwane

-- 
function.linuxpower.ca
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

• Next message: Zwane Mwaikambo: "[PATCH][2.5][RFC][2/2] per node vector spaces"
• Previous message: Zwane Mwaikambo: "[PATCH][2.5][RFC][1/2] per-CPU IDTs"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Fri Mar 07 2003 - 22:00:15 EST