Re: [Patch V3 2/9] kernel/profile.c: Replace cpu_to_mem() with cpu_to_node()

On Mon, 17 Aug 2015, Jiang Liu wrote:

> Function profile_cpu_callback() allocates memory without specifying
> __GFP_THISNODE flag, so replace cpu_to_mem() with cpu_to_node()
> because cpu_to_mem() may cause suboptimal memory allocation if
> there's no free memory on the node returned by cpu_to_mem().
> 

Why is cpu_to_node() better with regard to free memory and NUMA locality?

> It's safe to use cpu_to_mem() because build_all_zonelists() also
> builds suitable fallback zonelist for memoryless node.
> 

Why reference that cpu_to_mem() is safe if you're changing away from it?

> Signed-off-by: Jiang Liu <[email protected]>
> ---
>  kernel/profile.c |    2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/kernel/profile.c b/kernel/profile.c
> index a7bcd28d6e9f..d14805bdcc4c 100644
> --- a/kernel/profile.c
> +++ b/kernel/profile.c
> @@ -336,7 +336,7 @@ static int profile_cpu_callback(struct notifier_block *info,
>  	switch (action) {
>  	case CPU_UP_PREPARE:
>  	case CPU_UP_PREPARE_FROZEN:
> -		node = cpu_to_mem(cpu);
> +		node = cpu_to_node(cpu);
>  		per_cpu(cpu_profile_flip, cpu) = 0;
>  		if (!per_cpu(cpu_profile_hits, cpu)[1]) {
>  			page = alloc_pages_exact_node(node,