Re: [PATCH 04/12] Export fragmentation index via /proc/pagetypeinfo

[Minchan Kim]

On Fri, 2010-02-12 at 12:00 +0000, Mel Gorman wrote:
> Fragmentation index is a value that makes sense when an allocation of a
> given size would fail. The index indicates whether an allocation failure is
> due to a lack of memory (values towards 0) or due to external fragmentation
> (value towards 1).  For the most part, the huge page size will be the size
> of interest but not necessarily so it is exported on a per-order and per-zone
> basis via /proc/pagetypeinfo.
> 
> The index is normally calculated as a value between 0 and 1 which is
> obviously unsuitable within the kernel. Instead, the first three decimal
> places are used as a value between 0 and 1000 for an integer approximation.
> 
> Signed-off-by: Mel Gorman <mel@xxxxxxxxx>
Reviewed-by: Minchan Kim <minchan.kim@xxxxxxxxx>

> ---
>  Documentation/filesystems/proc.txt |   11 ++++++
>  mm/vmstat.c                        |   63 ++++++++++++++++++++++++++++++++++++
>  2 files changed, 74 insertions(+), 0 deletions(-)
> 
> diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
> index 0968a81..06bf53c 100644
> --- a/Documentation/filesystems/proc.txt
> +++ b/Documentation/filesystems/proc.txt
> @@ -618,6 +618,10 @@ Unusable free space index at order
>  Node    0, zone      DMA                         0      0      0      2      6     18     34     67     99    227    485
>  Node    0, zone    DMA32                         0      0      1      2      4      7     10     17     23     31     34
>  
> +Fragmentation index at order
> +Node    0, zone      DMA                        -1     -1     -1     -1     -1     -1     -1     -1     -1     -1     -1
> +Node    0, zone    DMA32                        -1     -1     -1     -1     -1     -1     -1     -1     -1     -1     -1
> +
>  Number of blocks type     Unmovable  Reclaimable      Movable      Reserve      Isolate
>  Node 0, zone      DMA            2            0            5            1            0
>  Node 0, zone    DMA32           41            6          967            2            0
> @@ -639,6 +643,13 @@ value between 0 and 1000. The higher the value, the more of free memory is
>  unusable and by implication, the worse the external fragmentation is. The
>  percentage of unusable free memory can be found by dividing this value by 10.
>  
> +The fragmentation index, is only meaningful if an allocation would fail and
> +indicates what the failure is due to. A value of -1 such as in the example
> +states that the allocation would succeed. If it would fail, the value is
> +between 0 and 1000. A value tending towards 0 implies the allocation failed
> +due to a lack of memory. A value tending towards 1000 implies it failed
> +due to external fragmentation.
> +
>  If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
>  from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
>  make an estimate of the likely number of huge pages that can be allocated
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index d05d610..e2d0cc1 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -494,6 +494,35 @@ static void fill_contig_page_info(struct zone *zone,
>  }
>  
>  /*
> + * A fragmentation index only makes sense if an allocation of a requested
> + * size would fail. If that is true, the fragmentation index indicates
> + * whether external fragmentation or a lack of memory was the problem.
> + * The value can be used to determine if page reclaim or compaction
> + * should be used
> + */
> +int fragmentation_index(struct zone *zone,

Like previous [3/12], why do you remain "zone" argument?
If you will use it in future, I don't care. It's just trivial. 

-- 
Kind regards,
Minchan Kim


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/