Re: [PATCH] kmalloc_percpu

[Dipankar Sarma]

On Tue, May 06, 2003 at 03:04:11PM +0530, Ravikiran G Thirumalai wrote:
> > Doesn't break with sparce CPU #s, but yes, it is inefficient.
> > 
> 
> If you don't reduce NR_CPUS with CONFIG_NR_CPUS, you waste space (32 bit folks
> won't like it) and if you say change CONFIG_NR_CPUS to 2, 
> and we have cpuid 4 on a 2 way you break right?  If we have to address these
> issues at all, why can't we use the simpler kmalloc_percpu patch
> which  I posted in the morning and avoid so much complexity and arch
> dependency?  

We can have something like that for !CONFIG_NUMA and a NUMA-aware
allocator with additional dereferencing cost for CONFIG_NUMA.
Hopefully gains from numa-awareness will more than offset
dereferencing costs.

Thanks
Dipankar