On 03/20/2015 12:33 AM, Gioh Kim wrote:
diff --git a/mm/compaction.c b/mm/compaction.c
index 8c0d945..827ec06 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1587,8 +1587,10 @@ static void __compact_pgdat(pg_data_t *pgdat, struct
compact_control *cc)
INIT_LIST_HEAD(&cc->freepages);
INIT_LIST_HEAD(&cc->migratepages);
- if (cc->order == -1 || !compaction_deferred(zone, cc->order))
+ if (cc->order == -1 || !compaction_deferred(zone, cc->order)) {
+ __reset_isolation_suitable(zone);
This will also trigger reset when called from kswapd through compact_pgdat() and
!compaction_deferred() is true.
The reset should be restricted to cc->order == -1 which only happens from /proc
trigger.
compact_zone(zone, cc);
+ }
if (cc->order > 0) {
if (zone_watermark_ok(zone, cc->order,
I've not been familiar with compaction code.
I think cc->order is -1 only if __compact_pgdat is called via /proc.
Yes that's what I meant.
This is ugly but I don't have better solution.
Do you have better idea?
It's not ugly IMHO. There are more tests for -1 like this, e.g. in
compaction_suitable(). Maybe just add some comment such as:
/*
* When called via /proc/sys/vm/compact_memory make sure we compact
* the whole zone regardless of cached scanner positions.
*/
diff --git a/mm/compaction.c b/mm/compaction.c
index 8c0d945..5b4e255 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1587,6 +1587,9 @@ static void __compact_pgdat(pg_data_t *pgdat, struct
compact_control *cc)
INIT_LIST_HEAD(&cc->freepages);
INIT_LIST_HEAD(&cc->migratepages);
+ if (cc->order == -1)
+ __reset_isolation_suitable(zone);
+
if (cc->order == -1 || !compaction_deferred(zone, cc->order))
compact_zone(zone, cc);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
