From: Minchan Kim on
On Thu, Aug 5, 2010 at 11:17 PM, Minchan Kim <minchan.kim(a)gmail.com> wrote:
> On Thu, Aug 05, 2010 at 03:13:39PM +0900, KOSAKI Motohiro wrote:
>> When synchrounous lumpy reclaim, there is no reason to give up to
>> reclaim pages even if page is locked. We use lock_page() instead
>> trylock_page() in this case.
>>
>> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro(a)jp.fujitsu.com>
>> ---
>> �mm/vmscan.c | � �4 +++-
>> �1 files changed, 3 insertions(+), 1 deletions(-)
>>
>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>> index 1cdc3db..833b6ad 100644
>> --- a/mm/vmscan.c
>> +++ b/mm/vmscan.c
>> @@ -665,7 +665,9 @@ static unsigned long shrink_page_list(struct list_head *page_list,
>> � � � � � � � page = lru_to_page(page_list);
>> � � � � � � � list_del(&page->lru);
>>
>> - � � � � � � if (!trylock_page(page))
>> + � � � � � � if (sync_writeback == PAGEOUT_IO_SYNC)
>> + � � � � � � � � � � lock_page(page);
>> + � � � � � � else if (!trylock_page(page))
>> � � � � � � � � � � � goto keep;
>>
>> � � � � � � � VM_BUG_ON(PageActive(page));
>> --
>> 1.6.5.2
>>
>>
>>
>
> Hmm. We can make sure lumpy already doesn't select the page locked?
> I mean below scenario.
>
> LRU head -> page A -> page B -> LRU tail
>
> lock_page(page A)
> some_function()
> direct reclaim
> select victim page B
> enter lumpy mode
> select victim page A as well as page B
> shrink_page_list
> lock_page(page A)
>
>
> --
> Kind regards,
> Minchan Kim
>

Ignore above comment.
lock_page doesn't have a deadlock problem. My bad.

Reviewed-by: Minchan Kim <minchan.kim(a)gmail.com>



--
Kind regards,
Minchan Kim
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/