Hugh Dickins wrote:

On Sat, 10 Mar 2012, Konstantin Khlebnikov wrote:

quoted

Konstantin Khlebnikov wrote:

quoted

No, for non-lumpy isolation we don't need this check at all,
because all pages already picked from right lru list.

I'll send separate patch for this (on top v5 patchset), after meditation =)

Heh, looks like we don't need these checks at all:
without RECLAIM_MODE_LUMPYRECLAIM we isolate only pages from right lru,
with RECLAIM_MODE_LUMPYRECLAIM we isolate pages from all evictable lru.
Thus we should check only PageUnevictable() on lumpy reclaim.

Yes, those were great simplfying insights: I'm puzzling over why you
didn't follow through on them in your otherwise nice 4.5/7, which
still involves lru bits in the isolate mode?

Actually filter is required for single case: lumpy isolation for shrink_active_list().
Maybe I'm wrong, or this is bug, but I don't see any reasons why this can not happen:
sc->reclaim_mode manipulations are very tricky.

Hugh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email:<a href=mailto:"dont@kvack.org">  email@kvack.org</a>

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>