Re: [PATCH] memcg: consider "scanned < reclaimed" case when calculating

[Minchan Kim <minchan@kernel.org>]

On Sat, Jun 22, 2013 at 02:50:06PM +0900, Hyunhee Kim wrote:
> In vmpressure, the pressure level is calculated based on the ratio
> of how many pages were scanned vs. reclaimed in a given time window.
> However, there is a possibility that "scanned < reclaimed" in such
> a case, THP page is reclaimed or reclaiming is abandoned by fatal
> signal in shrink_inactive_list, etc. So, with this patch, we just
> return "low" level when "scanned < reclaimed" by assuming that
> there are enough reclaimed pages.

I agree send lowevent in this case but you should write down why
lowevent send is better than ignoring in description. 

> 
> Signed-off-by: Hyunhee Kim <hyunhee.kim@samsung.com>
> Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
> ---
>  mm/vmpressure.c |    3 +++
>  1 file changed, 3 insertions(+)
> 
> diff --git a/mm/vmpressure.c b/mm/vmpressure.c
> index 736a601..c6560f3 100644
> --- a/mm/vmpressure.c
> +++ b/mm/vmpressure.c
> @@ -118,6 +118,9 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned,
>  	unsigned long scale = scanned + reclaimed;
>  	unsigned long pressure;
>  

Please write when we encounter this case.

> +	if (reclaimed > scanned)
> +		return VMPRESSURE_LOW;
> +
>  	/*
>  	 * We calculate the ratio (in percents) of how many pages were
>  	 * scanned vs. reclaimed in a given time frame (window). Note that
> -- 
> 1.7.9.5
> 
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

-- 
Kind regards,
Minchan Kim

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>