RE: [PATCH] 2.5.31 Summit NUMA patch with dynamic IRQ balancing

["Grover, Andrew" <andrew.grover@intel.com>]

> From: James Cleverdon [mailto:jamesclv@us.ibm.com] 
> > What happens when you use the FULL ACPI support? I suspect 
> that you really
> > do want the interpreter, in order to evaluate _PRTs properly.

> Bingo!  With full ACPI turned on, the system does indeed 
> boot.  The extra I/O 
> APIC entries are being programmed from the PRT.
> 
> (Call chain is:  pci_acpi_init --> acpi_pci_irq_init --> 
> mp_parse_prt --> 
> io_apic_set_pci_routing)
> 
> So, given that quite a number of our customers would like to run with 
> hyperthreading turned on, but do not want full ACPI, what is 
> the right thing 
> to do in the HT-only case?  Add extra code to process the 
> PRT?  Fall back on 
> MPS's IRQ records?  Something else entirely?

The solution is ACPI. Full ACPI. What is the problem? I have devoted too
much time already to make  hybrid ACPI/MPS combos work, but that will never
be the right solution.

Please have your customers email me privately and tell me why ~100KB of mem
on a 1GB+ system is something us engineers should spend our valuable time
hacking around, when the correct solution already is implemented and
*works*.

Regards -- Andy