On Wed, May 18, 2011 at 6:58 PM, Mel Gorman [off-list ref] wrote:

On Wed, May 18, 2011 at 02:44:48PM +0900, Minchan Kim wrote:

quoted

On Wed, May 18, 2011 at 10:05 AM, KOSAKI Motohiro
[off-list ref] wrote:

quoted

quoted

It would be better to put cond_resched after balance_pgdat?

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 292582c..61c45d0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c

@@ -2753,6 +2753,7 @@ static int kswapd(void *p)

                if (!ret) {
                        trace_mm_vmscan_kswapd_wake(pgdat->node_id,
order);
                        order = balance_pgdat(pgdat,
order,&classzone_idx);
+                       cond_resched();
                }
        }
        return 0;

quoted

quoted

quoted

While it appears unlikely, there are bad conditions which can result

in cond_resched() being avoided.

Every reclaim priority decreasing or every shrink_zone() calling makes more
fine grained preemption. I think.

It could be.
But in direct reclaim case, I have a concern about losing pages
reclaimed to other tasks by preemption.

Hmm,, anyway, we also needs test.
Hmm,, how long should we bother them(Colins and James)?
First of all, Let's fix one just between us and ask test to them and
send the last patch to akpm.

1. shrink_slab
2. right after balance_pgdat
3. shrink_zone
4. reclaim priority decreasing routine.

Now, I vote 1) and 2).

I've already submitted a pair of patches for option 1. I don't think
option 2 gains us anything. I think it's more likely we should worry
about all_unreclaimable being set when shrink_slab is returning 0 and we
are encountering so many dirty pages that pages_scanned is high enough.

Okay.

Colin reported he had no problem with patch 1 in this series and
mine(ie, just cond_resched right after balance_pgdat call without no
patch of shrink_slab).

If Colin's test is successful, I don't insist on mine.
(I don't want to drag on for days :( )
If KOSAKI agree, let's ask the test to Colin and confirm our last test.

KOSAKI. Could you post a your opinion?

-- 
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>