On Tue, Jun 19, 2012 at 11:29 AM, KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx> wrote: > On 6/18/2012 12:47 PM, Ying Han wrote: >> Currently, do_try_to_free_pages() can enter livelock. Because of, >> now vmscan has two conflicted policies. >> >> 1) kswapd sleep when it couldn't reclaim any page even though >> reach priority 0. This is because to avoid kswapd() infinite >> loop. That said, kswapd assume direct reclaim makes enough >> free pages either regular page reclaim or oom-killer. >> This logic makes kswapd -> direct-reclaim dependency. >> 2) direct reclaim continue to reclaim without oom-killer until >> kswapd turn on zone->all_unreclaimble. This is because >> to avoid too early oom-kill. >> This logic makes direct-reclaim -> kswapd dependency. >> >> In worst case, direct-reclaim may continue to page reclaim forever >> when kswapd is slept and any other thread don't wakeup kswapd. >> >> We can't turn on zone->all_unreclaimable because this is racy. >> direct reclaim path don't take any lock. Thus this patch removes >> zone->all_unreclaimable field completely and recalculates every >> time. >> >> Note: we can't take the idea that direct-reclaim see zone->pages_scanned >> directly and kswapd continue to use zone->all_unreclaimable. Because, >> it is racy. commit 929bea7c71 (vmscan: all_unreclaimable() use >> zone->all_unreclaimable as a name) describes the detail. >> >> Reported-by: Aaditya Kumar <aaditya.kumar.30@xxxxxxxxx> >> Reported-by: Ying Han <yinghan@xxxxxxxxxx> >> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx> >> Acked-by: Rik van Riel <riel@xxxxxxxxxx> > > Please drop this. I've got some review comment about this patch and > i need respin. but thank you for paying attention this. Thanks for the heads up. Are you working on the new version of it, since I included this patch in my softlimit reclaim patchset as a replacement of one patch i had. --Ying > > > -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href