mm: compaction: skip memory hole rapidly when isolating migratable pages

On some machines, the normal zone can have a large memory hole like below
memory layout, and we can see the range from 0x100000000 to 0x1800000000
is a hole.  So when isolating some migratable pages, the scanner can meet
the hole and it will take more time to skip the large hole.  From my
measurement, I can see the isolation scanner will take 80us ~ 100us to
skip the large hole [0x100000000 - 0x1800000000].

So adding a new helper to fast search next online memory section to skip
the large hole can help to find next suitable pageblock efficiently.  With
this patch, I can see the large hole scanning only takes < 1us.

[    0.000000] Zone ranges:
[    0.000000]   DMA      [mem 0x0000000040000000-0x00000000ffffffff]
[    0.000000]   DMA32    empty
[    0.000000]   Normal   [mem 0x0000000100000000-0x0000001fa7ffffff]
[    0.000000] Movable zone start for each node
[    0.000000] Early memory node ranges
[    0.000000]   node   0: [mem 0x0000000040000000-0x0000000fffffffff]
[    0.000000]   node   0: [mem 0x0000001800000000-0x0000001fa3c7ffff]
[    0.000000]   node   0: [mem 0x0000001fa3c80000-0x0000001fa3ffffff]
[    0.000000]   node   0: [mem 0x0000001fa4000000-0x0000001fa402ffff]
[    0.000000]   node   0: [mem 0x0000001fa4030000-0x0000001fa40effff]
[    0.000000]   node   0: [mem 0x0000001fa40f0000-0x0000001fa73cffff]
[    0.000000]   node   0: [mem 0x0000001fa73d0000-0x0000001fa745ffff]
[    0.000000]   node   0: [mem 0x0000001fa7460000-0x0000001fa746ffff]
[    0.000000]   node   0: [mem 0x0000001fa7470000-0x0000001fa758ffff]
[    0.000000]   node   0: [mem 0x0000001fa7590000-0x0000001fa7ffffff]

[baolin.wang@linux.alibaba.com: limit next_ptn to not exceed cc->free_pfn]
Link: https://lkml.kernel.org/r/a1d859c28af0c7e85e91795e7473f553eb180a9d.1686813379.git.baolin.wang@linux.alibaba.com
Link: https://lkml.kernel.org/r/75b4c8ca36bf44ad8c42bf0685ac19d272e426ec.1686705221.git.baolin.wang@linux.alibaba.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/compaction.c b/mm/compaction.c
index 6149a2d..0fb3b89 100644 (file)
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -229,6 +229,33 @@ static void reset_cached_positions(struct zone *zone)
                                pageblock_start_pfn(zone_end_pfn(zone) - 1);
 }
 
+#ifdef CONFIG_SPARSEMEM
+/*
+ * If the PFN falls into an offline section, return the start PFN of the
+ * next online section. If the PFN falls into an online section or if
+ * there is no next online section, return 0.
+ */
+static unsigned long skip_offline_sections(unsigned long start_pfn)
+{
+       unsigned long start_nr = pfn_to_section_nr(start_pfn);
+
+       if (online_section_nr(start_nr))
+               return 0;
+
+       while (++start_nr <= __highest_present_section_nr) {
+               if (online_section_nr(start_nr))
+                       return section_nr_to_pfn(start_nr);
+       }
+
+       return 0;
+}
+#else
+static unsigned long skip_offline_sections(unsigned long start_pfn)
+{
+       return 0;
+}
+#endif
+
 /*
  * Compound pages of >= pageblock_order should consistently be skipped until
  * released. It is always pointless to compact pages of such order (if they are
@@ -1955,8 +1982,14 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
 
                page = pageblock_pfn_to_page(block_start_pfn,
                                                block_end_pfn, cc->zone);
-               if (!page)
+               if (!page) {
+                       unsigned long next_pfn;
+
+                       next_pfn = skip_offline_sections(block_start_pfn);
+                       if (next_pfn)
+                               block_end_pfn = min(next_pfn, cc->free_pfn);
                        continue;
+               }
 
                /*
                 * If isolation recently failed, do not retry. Only check the