Re: [PATCH 1/4] vmstat: remove zone->lock from walk_zones_in_node

[Minchan Kim]

On Mon, Dec 28, 2009 at 4:47 PM, KOSAKI Motohiro
<kosaki.motohiro@xxxxxxxxxxxxxx> wrote:
> The zone->lock is one of performance critical locks. Then, it shouldn't
> be hold for long time. Currently, we have four walk_zones_in_node()
> usage and almost use-case don't need to hold zone->lock.

I agree.

We can use walk_zone_in_node freely to show the information related to zone.

- frag_show_print : the number of free pages per order.
- pagetypeinfo_showfree_print : the number of free page per migration type
- pagetypeinfo_showblockcount_print : the number of pages in zone per
migration type
- zoneinfo_show_print : many info about zone.

Do we want to show exact value? No.
If we want it, it's not enough zone->lock only.
After all, All of things would be transient value.

>
> Thus, this patch move locking responsibility from walk_zones_in_node
> to its sub function. Also this patch kill unnecessary zone->lock taking.
>
> Cc: Mel Gorman <mel@xxxxxxxxx>
> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Reviewed-by: Minchan Kim <minchan.kim@xxxxxxxxx>

-- 
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/