On 08/16/2016 08:15 AM, Joonsoo Kim wrote:
On Wed, Aug 10, 2016 at 11:12:23AM +0200, Vlastimil Babka wrote:--- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -58,6 +58,22 @@ enum compact_result {struct alloc_context; /* in mm/internal.h */ +/* + * Number of free order-0 pages that should be available above given watermark + * to make sure compaction has reasonable chance of not running out of free + * pages that it needs to isolate as migration target during its work. + */ +static inline unsigned long compact_gap(unsigned int order) +{ + /* + * Although all the isolations for migration are temporary, compaction + * may have up to 1 << order pages on its list and then try to split + * an (order - 1) free page. At that point, a gap of 1 << order might + * not be enough, so it's safer to require twice that amount. + */ + return 2UL << order; +}I agree with this wrapper function but there is a question. Could you elaborate more on this code comment? Freescanner could keep COMPACT_CLUSTER_MAX freepages on the list. It's not associated with requested order at least for now. Why compact_gap is 2UL << order in this case?
It's true that for high enough order, COMPACT_CLUSTER_MAX might be more limiting than 1 << order. But then it also helps to have more free pages for probability of compaction success, so I don't think it's worth complicating the compact_gap() formula.
Thanks.
