Re: [PATCH 1/5] vmscan: remove all_unreclaimable check from direct reclaim path completely

[KOSAKI Motohiro]

> > Reported-by: Andrey Vagin <avagin@xxxxxxxxxx>
> > Cc: Nick Piggin <npiggin@xxxxxxxxx>
> > Cc: Minchan Kim <minchan.kim@xxxxxxxxx>
> > Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
> > Cc: Rik van Riel <riel@xxxxxxxxxx>
> > Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
> > Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
> 
> IIUC, I saw the pehnomenon which you pointed out, as
>  - all zone->all_unreclaimable = yes
>  - zone_reclaimable() returns true
>  - no pgscan proceeds.
> 
> on a swapless system. So, I'd like to vote for this patch.
> 
> But hmm...what happens all of pages are isolated or locked and now under freeing ?
> I think we should have alternative safe-guard logic for avoiding to call
> oom-killer. Hmm.

Yes, this patch has small risk. but 1) this logic didn't work about two
years (see changelog) 2) memcg haven't use this logic and I haven't get
any bug report from memcg developers. therefore I decided to take most
simple way.

Of cource, I'll make another protection if I'll get any regression report.



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/