lkml.org 
[lkml]   [2010]   [Aug]   [5]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 6/7] vmscan: remove PF_SWAPWRITE from __zone_reclaim()
Date
When zone_reclaim() was merged at first, It always order-0
allocation with PF_SWAPWRITE flag. (probably they are both
unintional).

Former was fixed commit bd2f6199cf (vmscan: respect higher
order in zone_reclaim()). However it expose latter mistake
because !order-0 reclaim often cause dirty pages isolation
and large latency.

Now, we have good opportunity to fix latter too.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
---
mm/vmscan.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index f21dbeb..e043e97 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2663,7 +2663,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
* and we also need to be able to write out pages for RECLAIM_WRITE
* and RECLAIM_SWAP.
*/
- p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
+ p->flags |= PF_MEMALLOC;
lockdep_set_current_reclaim_state(gfp_mask);
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
@@ -2716,7 +2716,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
}

p->reclaim_state = NULL;
- current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
+ current->flags &= ~PF_MEMALLOC;
lockdep_clear_current_reclaim_state();
return sc.nr_reclaimed >= nr_pages;
}
--
1.6.5.2




\
 
 \ /
  Last update: 2010-08-05 08:17    [W:0.095 / U:6.260 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site