Hi! On Mon, Aug 05, 2013 at 02:45:59PM -0400, Johannes Weiner wrote: > On Fri, Aug 02, 2013 at 06:06:29PM +0200, Andrea Arcangeli wrote: > > Reset the stats so /proc/sys/vm/compact_memory will scan all memory. > > > > Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx> > > Reviewed-by: Rik van Riel <riel@xxxxxxxxxx> > > Acked-by: Rafael Aquini <aquini@xxxxxxxxxx> > > Acked-by: Mel Gorman <mgorman@xxxxxxx> > > It somehow feels wrong that this operation should have a destructive > side effect, rather than just ignore the cached info for the one run > (like cc.ignore_skip_hint). But I don't really have a strong reason > against it, so... But what benefit would provide to keep the cached cursor positions alive after we already compacted the whole memory from the start to the end? The cached cursors provide useful information when we compact in small steps and they represent the unscanned part of the memory. But after a full compaction completed unless some memory activity has happened there will be nothing to compact anymore. So we just need to find what may have changed as result of the memory activity and in turn there should be no benefit in starting at the previously cached cursors positions. > > Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx> Thanks! Andrea -- 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=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>