Re: [PATCH 1/7] powerpc: Reduce footprint of irq_stat

2010-02-02 Thread Christoph Hellwig
On Tue, Feb 02, 2010 at 10:07:10AM +1100, Benjamin Herrenschmidt wrote: > On Mon, 2010-02-01 at 22:55 +0100, Christoph Hellwig wrote: > > > > +typedef struct { > > > + unsigned int __softirq_pending; > > > +} cacheline_aligned irq_cpustat_t; > > > > No need to bother with an irq_cpustat_t typ

Re: [PATCH 1/7] powerpc: Reduce footprint of irq_stat

2010-02-01 Thread Benjamin Herrenschmidt
On Mon, 2010-02-01 at 22:55 +0100, Christoph Hellwig wrote: > > +typedef struct { > > + unsigned int __softirq_pending; > > +} cacheline_aligned irq_cpustat_t; > > No need to bother with an irq_cpustat_t type at all in this case, just > declare a softirq_pending per-cpu variable. I think h

Re: [PATCH 1/7] powerpc: Reduce footprint of irq_stat

2010-02-01 Thread Christoph Hellwig
On Mon, Feb 01, 2010 at 05:30:23PM +1100, Anton Blanchard wrote: > > PowerPC is currently using asm-generic/hardirq.h which statically allocates an > NR_CPUS irq_stat array. Switch to an arch specific implementation which uses > per cpu data: > > On a kernel with NR_CPUS=1024, this saves quite a

[PATCH 1/7] powerpc: Reduce footprint of irq_stat

2010-01-31 Thread Anton Blanchard
PowerPC is currently using asm-generic/hardirq.h which statically allocates an NR_CPUS irq_stat array. Switch to an arch specific implementation which uses per cpu data: On a kernel with NR_CPUS=1024, this saves quite a lot of memory: textdata bss dec hexfilename 8767