On Fri, Jan 06, 2012 at 12:57:41PM +0800, Huang Shijie wrote: > In the real tests, there are maybe many times the cc->nr_migratepages is zero, > but isolate_migratepages() returns ISOLATE_SUCCESS. Odd choice of language. Are there or are there not many times that cc->nr_migratepages is zero? It does not affect the patch but it is a slightly confusing changelog. > In order to get better performance, we should check the number of the > really isolated pages. And do the optimazition for this case. > It's not critical for this patch but in the future it is preferred if the performance impact can be quantified if that is your justification for merging. I would expect the performance impact of this patch to be marginal. > Also fix the confused comments(from Mel Gorman). > > Tested this patch in MX6Q board. > > Signed-off-by: Huang Shijie <b32955@xxxxxxxxxxxxx> Acked-by: Mel Gorman <mgorman@xxxxxxx> -- Mel Gorman SUSE Labs -- 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/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>