Messages in this thread | | | Date | Thu, 5 Aug 2010 22:55:04 +0900 | From | Minchan Kim <> | Subject | Re: [PATCH 2/7] vmscan: synchronous lumpy reclaim don't call congestion_wait() |
| |
On Thu, Aug 05, 2010 at 03:13:03PM +0900, KOSAKI Motohiro wrote: > congestion_wait() mean "waiting quueue congestion is cleared". > That said, if the system have plenty dirty pages and flusher thread push > new request to IO queue conteniously, IO queue are not cleared > congestion status for long time. thus, congestion_wait(HZ/10) become > almostly equivalent schedule_timeout(HZ/10). > > However, synchronous lumpy reclaim donesn't need this > congestion_wait() at all. shrink_page_list(PAGEOUT_IO_SYNC) are > using wait_on_page_writeback() and it provide sufficient waiting. > > Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
-- Kind regards, Minchan Kim
| |