Messages in this thread | | | Date | Thu, 11 Jun 2009 20:13:46 +0900 (JST) | Subject | Re: [PATCH 1/3] remove wrong rotation at lumpy reclaim | From | "KAMEZAWA Hiroyuki" <> |
| |
Minchan Kim wrote: > On Thu, Jun 11, 2009 at 5:00 PM, KAMEZAWA > Hiroyuki<kamezawa.hiroyu@jp.fujitsu.com> wrote: >> From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> >> >> At lumpy reclaim, a page failed to be taken by __isolate_lru_page() can >> be pushed back to "src" list by list_move(). But the page may not be >> from >> "src" list. And list_move() itself is unnecessary because the page is >> not on top of LRU. Then, leave it as it is if __isolate_lru_page() >> fails. >> >> This patch doesn't change the logic as "we should exit loop or not" and >> just fixes buggy list_move(). >> >> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> >> --- >> ?mm/vmscan.c | ? ?9 +-------- >> ?1 file changed, 1 insertion(+), 8 deletions(-) >> >> Index: lumpy-reclaim-trial/mm/vmscan.c >> =================================================================== >> --- lumpy-reclaim-trial.orig/mm/vmscan.c >> +++ lumpy-reclaim-trial/mm/vmscan.c >> @@ -936,18 +936,11 @@ static unsigned long isolate_lru_pages(u >> ? ? ? ? ? ? ? ? ? ? ? ?/* Check that we have not crossed a zone >> boundary. */ >> ? ? ? ? ? ? ? ? ? ? ? ?if (unlikely(page_zone_id(cursor_page) != >> zone_id)) >> ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?continue; >> - ? ? ? ? ? ? ? ? ? ? ? switch (__isolate_lru_page(cursor_page, mode, >> file)) { >> - ? ? ? ? ? ? ? ? ? ? ? case 0: >> + ? ? ? ? ? ? ? ? ? ? ? if (__isolate_lru_page(cursor_page, mode, file) >> == 0) { >> ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?list_move(&cursor_page->lru, dst); >> ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?nr_taken++; >> ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?scan++; >> ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?break; > > break ?? > good catch. I'll post updated one tomorrow. I'm very sorry ;(
Thanks, -Kame
| |