Messages in this thread | | | Date | Tue, 16 Aug 2016 15:41:04 +0900 | From | Joonsoo Kim <> | Subject | Re: [PATCH v6 08/11] mm, compaction: create compact_gap wrapper |
| |
On Tue, Aug 16, 2016 at 08:15:36AM +0200, Vlastimil Babka wrote: > 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
AFAIK, regardless of order, migration scanner isolates COMPACT_CLUSTER_MAX pages. And, freepage scanner isolates more than nr_migratepages freepages.
> free pages for probability of compaction success, so I don't think > it's worth complicating the compact_gap() formula.
I agree that it's not worth complicating the compact_gap() formula but it would be better to fix the comment?
Thanks.
| |