On Fri, Aug 02, 2013 at 06:06:31PM +0200, Andrea Arcangeli wrote: > Correct the location where we reset the scan cursors, otherwise the > first iteration of compaction (after restarting it) will only do a > partial scan. > > Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx> > Reviewed-by: Rik van Riel <riel@xxxxxxxxxx> > Acked-by: Mel Gorman <mgorman@xxxxxxx> > Acked-by: Rafael Aquini <aquini@xxxxxxxxxx> Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx> Yes, it does not make sense to read the situation from the cache first, then two lines later invalidate it because it's stale data. That being said, why are we maintaining the pageblock skip bits in addition to the scanner offset caches? Sometimes we only set the pageblock skip bit and not update the position cache, but the next invocation will skip over these blocks anyway because of !isolation_suitable(). And they are invalidated together. Aren't they redundant? -- 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>