Re: [PATCH v3 2/2] tmpfs: Make tmpfs scalable with percpu_counter for used blocks

[Andrew Morton <akpm@linux-foundation.org>]

On Thu, 17 Jun 2010 16:56:33 -0700
Tim Chen <tim.c.chen@linux.intel.com> wrote:

> The current implementation of tmpfs is not scalable.
> We found that stat_lock is contended by multiple threads
> when we need to get a new page, leading to useless spinning
> inside this spin lock.  
> 
> This patch makes use of the percpu_counter library to maintain local
> count of used blocks to speed up getting and returning
> of pages.  So the acquisition of stat_lock is unnecessary
> for getting and returning blocks, improving the performance 
> of tmpfs on system with large number of cpus.  On a 4 socket
> 32 core NHM-EX system, we saw improvement of 270%.

So it had exactly the same performance as the token-jar approach?

It'd be good if the changelog were to mention the inaccuracy issues. 
Describe their impact, if any.

Are you actually happy with this overall approach?

>
> ...
>
> @@ -2258,9 +2254,8 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
>  		return error;
>  
>  	spin_lock(&sbinfo->stat_lock);
> -	blocks = sbinfo->max_blocks - sbinfo->free_blocks;
>  	inodes = sbinfo->max_inodes - sbinfo->free_inodes;
> -	if (config.max_blocks < blocks)
> +	if (config.max_blocks < percpu_counter_sum(&sbinfo->used_blocks))

This could actually use percpu_counter_compare()?

>  		goto out;
>  	if (config.max_inodes < inodes)
>  		goto out;