Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-07 Thread Eric W. Biederman
Ingo Molnar <[EMAIL PROTECTED]> writes: > * Eric W. Biederman <[EMAIL PROTECTED]> wrote: > >> Attached below is my patch from last time I was looking at this >> problem, it doesn't quite apply but it is gives a good idea of where I >> think we should go. > > merged it up to x86.git - see below.

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-07 Thread Ingo Molnar
* Ingo Molnar <[EMAIL PROTECTED]> wrote: > > * Eric W. Biederman <[EMAIL PROTECTED]> wrote: > > > Attached below is my patch from last time I was looking at this > > problem, it doesn't quite apply but it is gives a good idea of where I > > think we should go. > > merged it up to x86.git -

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-07 Thread Ingo Molnar
* Eric W. Biederman <[EMAIL PROTECTED]> wrote: > Attached below is my patch from last time I was looking at this > problem, it doesn't quite apply but it is gives a good idea of where I > think we should go. merged it up to x86.git - see below. Alan, have no tried to build, let alone boot

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-07 Thread Eric W. Biederman
Len Brown <[EMAIL PROTECTED]> writes: > On Wednesday 05 December 2007 04:48, Ingo Molnar wrote: >> >> * Andrew Morton <[EMAIL PROTECTED]> wrote: >> >> > On Tue, 4 Dec 2007 13:26:49 +0100 >> > Ingo Molnar <[EMAIL PROTECTED]> wrote: >> > >> > > * Len Brown <[EMAIL PROTECTED]> wrote: >> > > >> >

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-07 Thread Eric W. Biederman
Ingo Molnar [EMAIL PROTECTED] writes: * Eric W. Biederman [EMAIL PROTECTED] wrote: Attached below is my patch from last time I was looking at this problem, it doesn't quite apply but it is gives a good idea of where I think we should go. merged it up to x86.git - see below. Alas, have no

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-07 Thread Ingo Molnar
* Ingo Molnar [EMAIL PROTECTED] wrote: * Eric W. Biederman [EMAIL PROTECTED] wrote: Attached below is my patch from last time I was looking at this problem, it doesn't quite apply but it is gives a good idea of where I think we should go. merged it up to x86.git - see below.

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-07 Thread Eric W. Biederman
Len Brown [EMAIL PROTECTED] writes: On Wednesday 05 December 2007 04:48, Ingo Molnar wrote: * Andrew Morton [EMAIL PROTECTED] wrote: On Tue, 4 Dec 2007 13:26:49 +0100 Ingo Molnar [EMAIL PROTECTED] wrote: * Len Brown [EMAIL PROTECTED] wrote: So while the irq compression

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-07 Thread Ingo Molnar
* Eric W. Biederman [EMAIL PROTECTED] wrote: Attached below is my patch from last time I was looking at this problem, it doesn't quite apply but it is gives a good idea of where I think we should go. merged it up to x86.git - see below. Alan, have no tried to build, let alone boot it.

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-06 Thread Len Brown
On Wednesday 05 December 2007 04:48, Ingo Molnar wrote: > > * Andrew Morton <[EMAIL PROTECTED]> wrote: > > > On Tue, 4 Dec 2007 13:26:49 +0100 > > Ingo Molnar <[EMAIL PROTECTED]> wrote: > > > > > * Len Brown <[EMAIL PROTECTED]> wrote: > > > > > > > So while the irq compression code on i386

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-06 Thread Len Brown
On Wednesday 05 December 2007 04:48, Ingo Molnar wrote: * Andrew Morton [EMAIL PROTECTED] wrote: On Tue, 4 Dec 2007 13:26:49 +0100 Ingo Molnar [EMAIL PROTECTED] wrote: * Len Brown [EMAIL PROTECTED] wrote: So while the irq compression code on i386 should really be

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-05 Thread Eric W. Biederman
"Natalie Protasevich" <[EMAIL PROTECTED]> writes: > I think we counted them in the order of 1400 external IRQs (actual > ioapics/slots plus possible on-card bridges), and yes numbers for used > IRQs were close to 250. Actual customer configurations could've big > bigger, I don't have such data. >

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-05 Thread Natalie Protasevich
On Dec 5, 2007 3:25 PM, Eric W. Biederman <[EMAIL PROTECTED]> wrote: > > "Natalie Protasevich" <[EMAIL PROTECTED]> writes: > > > On Nov 27, 2007 10:21 PM, Len Brown <[EMAIL PROTECTED]> wrote: > >> commit c434b7a6aedfe428ad17cd61b21b125a7b7a29ce > >> (x86: avoid wasting IRQs for PCI

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-05 Thread Eric W. Biederman
"Natalie Protasevich" <[EMAIL PROTECTED]> writes: > On Nov 27, 2007 10:21 PM, Len Brown <[EMAIL PROTECTED]> wrote: >> commit c434b7a6aedfe428ad17cd61b21b125a7b7a29ce >> (x86: avoid wasting IRQs for PCI devices) >> created a concept of "IRQ compression" on i386 >> to conserve IRQ

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-05 Thread Natalie Protasevich
On Nov 27, 2007 10:21 PM, Len Brown <[EMAIL PROTECTED]> wrote: > commit c434b7a6aedfe428ad17cd61b21b125a7b7a29ce > (x86: avoid wasting IRQs for PCI devices) > created a concept of "IRQ compression" on i386 > to conserve IRQ numbers on systems with many > sparsely populated IO

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-05 Thread Ingo Molnar
* Andrew Morton <[EMAIL PROTECTED]> wrote: > On Tue, 4 Dec 2007 13:26:49 +0100 > Ingo Molnar <[EMAIL PROTECTED]> wrote: > > > * Len Brown <[EMAIL PROTECTED]> wrote: > > > > > So while the irq compression code on i386 should really > > > be deleted -- even before merging the x86_64

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-05 Thread Eric W. Biederman
Natalie Protasevich [EMAIL PROTECTED] writes: On Nov 27, 2007 10:21 PM, Len Brown [EMAIL PROTECTED] wrote: commit c434b7a6aedfe428ad17cd61b21b125a7b7a29ce (x86: avoid wasting IRQs for PCI devices) created a concept of IRQ compression on i386 to conserve IRQ numbers on systems

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-05 Thread Natalie Protasevich
On Nov 27, 2007 10:21 PM, Len Brown [EMAIL PROTECTED] wrote: commit c434b7a6aedfe428ad17cd61b21b125a7b7a29ce (x86: avoid wasting IRQs for PCI devices) created a concept of IRQ compression on i386 to conserve IRQ numbers on systems with many sparsely populated IO APICs.

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-05 Thread Ingo Molnar
* Andrew Morton [EMAIL PROTECTED] wrote: On Tue, 4 Dec 2007 13:26:49 +0100 Ingo Molnar [EMAIL PROTECTED] wrote: * Len Brown [EMAIL PROTECTED] wrote: So while the irq compression code on i386 should really be deleted -- even before merging the x86_64 irq-overhaul,

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-05 Thread Natalie Protasevich
On Dec 5, 2007 3:25 PM, Eric W. Biederman [EMAIL PROTECTED] wrote: Natalie Protasevich [EMAIL PROTECTED] writes: On Nov 27, 2007 10:21 PM, Len Brown [EMAIL PROTECTED] wrote: commit c434b7a6aedfe428ad17cd61b21b125a7b7a29ce (x86: avoid wasting IRQs for PCI devices) created a

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-05 Thread Eric W. Biederman
Natalie Protasevich [EMAIL PROTECTED] writes: I think we counted them in the order of 1400 external IRQs (actual ioapics/slots plus possible on-card bridges), and yes numbers for used IRQs were close to 250. Actual customer configurations could've big bigger, I don't have such data. In

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-04 Thread Andrew Morton
On Tue, 4 Dec 2007 13:26:49 +0100 Ingo Molnar <[EMAIL PROTECTED]> wrote: > * Len Brown <[EMAIL PROTECTED]> wrote: > > > So while the irq compression code on i386 should really > > be deleted -- even before merging the x86_64 irq-overhaul, > > this patch simply disables it on all high

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-04 Thread Ingo Molnar
* Christian Kujau <[EMAIL PROTECTED]> wrote: > On Tue, 4 Dec 2007, Ingo Molnar wrote: >> thanks for the patch and the extensive description. I've applied this to >> x86.git. Do you agree that this has no urgency for v2.6.24 and is thus >> v2.6.25 material? > > Pardon my ignorance, but: aren't we

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-04 Thread Christian Kujau
On Tue, 4 Dec 2007, Ingo Molnar wrote: thanks for the patch and the extensive description. I've applied this to x86.git. Do you agree that this has no urgency for v2.6.24 and is thus v2.6.25 material? Pardon my ignorance, but: aren't we in -rc already? I was under the assumption that during

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-04 Thread Eric W. Biederman
Ingo Molnar <[EMAIL PROTECTED]> writes: > * Len Brown <[EMAIL PROTECTED]> wrote: > >> So while the irq compression code on i386 should really >> be deleted -- even before merging the x86_64 irq-overhaul, >> this patch simply disables it on all high volume systems >> to avoid

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-04 Thread Ingo Molnar
* Len Brown <[EMAIL PROTECTED]> wrote: > So while the irq compression code on i386 should really > be deleted -- even before merging the x86_64 irq-overhaul, > this patch simply disables it on all high volume systems > to avoid problems #1 and #2 on most all i386 systems. >

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-04 Thread Ingo Molnar
* Len Brown [EMAIL PROTECTED] wrote: So while the irq compression code on i386 should really be deleted -- even before merging the x86_64 irq-overhaul, this patch simply disables it on all high volume systems to avoid problems #1 and #2 on most all i386 systems. A

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-04 Thread Eric W. Biederman
Ingo Molnar [EMAIL PROTECTED] writes: * Len Brown [EMAIL PROTECTED] wrote: So while the irq compression code on i386 should really be deleted -- even before merging the x86_64 irq-overhaul, this patch simply disables it on all high volume systems to avoid problems #1 and #2

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-04 Thread Christian Kujau
On Tue, 4 Dec 2007, Ingo Molnar wrote: thanks for the patch and the extensive description. I've applied this to x86.git. Do you agree that this has no urgency for v2.6.24 and is thus v2.6.25 material? Pardon my ignorance, but: aren't we in -rc already? I was under the assumption that during

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-04 Thread Ingo Molnar
* Christian Kujau [EMAIL PROTECTED] wrote: On Tue, 4 Dec 2007, Ingo Molnar wrote: thanks for the patch and the extensive description. I've applied this to x86.git. Do you agree that this has no urgency for v2.6.24 and is thus v2.6.25 material? Pardon my ignorance, but: aren't we in -rc

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-12-04 Thread Andrew Morton
On Tue, 4 Dec 2007 13:26:49 +0100 Ingo Molnar [EMAIL PROTECTED] wrote: * Len Brown [EMAIL PROTECTED] wrote: So while the irq compression code on i386 should really be deleted -- even before merging the x86_64 irq-overhaul, this patch simply disables it on all high volume

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-11-27 Thread Eric W. Biederman
Len Brown <[EMAIL PROTECTED]> writes: > commit c434b7a6aedfe428ad17cd61b21b125a7b7a29ce > (x86: avoid wasting IRQs for PCI devices) > created a concept of "IRQ compression" on i386 > to conserve IRQ numbers on systems with many > sparsely populated IO APICs. > > The

[PATCH] i386 IOAPIC: de-fang IRQ compression

2007-11-27 Thread Len Brown
commit c434b7a6aedfe428ad17cd61b21b125a7b7a29ce (x86: avoid wasting IRQs for PCI devices) created a concept of "IRQ compression" on i386 to conserve IRQ numbers on systems with many sparsely populated IO APICs. The same scheme was also added to x86_64, but later

[PATCH] i386 IOAPIC: de-fang IRQ compression

2007-11-27 Thread Len Brown
commit c434b7a6aedfe428ad17cd61b21b125a7b7a29ce (x86: avoid wasting IRQs for PCI devices) created a concept of IRQ compression on i386 to conserve IRQ numbers on systems with many sparsely populated IO APICs. The same scheme was also added to x86_64, but later

Re: [PATCH] i386 IOAPIC: de-fang IRQ compression

2007-11-27 Thread Eric W. Biederman
Len Brown [EMAIL PROTECTED] writes: commit c434b7a6aedfe428ad17cd61b21b125a7b7a29ce (x86: avoid wasting IRQs for PCI devices) created a concept of IRQ compression on i386 to conserve IRQ numbers on systems with many sparsely populated IO APICs. The same scheme