From 48731c8436c68ce5597dfe72f3836bd6808bedde Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 25 Jan 2023 13:44:31 +0000 Subject: [PATCH] mm, compaction: rename compact_control->rescan to finish_pageblock Patch series "Fix excessive CPU usage during compaction". Commit 7efc3b726103 ("mm/compaction: fix set skip in fast_find_migrateblock") fixed a problem where pageblocks found by fast_find_migrateblock() were ignored. Unfortunately there were numerous bug reports complaining about high CPU usage and massive stalls once 6.1 was released. Due to the severity, the patch was reverted by Vlastimil as a short-term fix[1] to -stable. The underlying problem for each of the bugs is suspected to be the repeated scanning of the same pageblocks. This series should guarantee forward progress even with commit 7efc3b726103. More information is in the changelog for patch 4. [1] http://lore.kernel.org/r/20230113173345.9692-1-vbabka@suse.cz This patch (of 4): The rescan field was not well named albeit accurate at the time. Rename the field to finish_pageblock to indicate that the remainder of the pageblock should be scanned regardless of COMPACT_CLUSTER_MAX. The intent is that pageblocks with transient failures get marked for skipping to avoid revisiting the same pageblock. Link: https://lkml.kernel.org/r/20230125134434.18017-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman Cc: Chuyi Zhou Cc: Jiri Slaby Cc: Maxim Levitsky Cc: Michal Hocko Cc: Paolo Bonzini Cc: Pedro Falcato Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/compaction.c | 24 ++++++++++++------------ mm/internal.h | 6 +++++- 2 files changed, 17 insertions(+), 13 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index b758b00a4885..28a9596609fe 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1101,12 +1101,12 @@ isolate_success_no_list: /* * Avoid isolating too much unless this block is being - * rescanned (e.g. dirty/writeback pages, parallel allocation) + * fully scanned (e.g. dirty/writeback pages, parallel allocation) * or a lock is contended. For contention, isolate quickly to * potentially remove one source of contention. */ if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX && - !cc->rescan && !cc->contended) { + !cc->finish_pageblock && !cc->contended) { ++low_pfn; break; } @@ -1171,14 +1171,14 @@ isolate_abort: } /* - * Updated the cached scanner pfn once the pageblock has been scanned + * Update the cached scanner pfn once the pageblock has been scanned. * Pages will either be migrated in which case there is no point * scanning in the near future or migration failed in which case the * failure reason may persist. The block is marked for skipping if * there were no pages isolated in the block or if the block is * rescanned twice in a row. */ - if (low_pfn == end_pfn && (!nr_isolated || cc->rescan)) { + if (low_pfn == end_pfn && (!nr_isolated || cc->finish_pageblock)) { if (valid_page && !skip_updated) set_pageblock_skip(valid_page); update_cached_migrate(cc, low_pfn); @@ -2372,17 +2372,17 @@ compact_zone(struct compact_control *cc, struct capture_control *capc) unsigned long iteration_start_pfn = cc->migrate_pfn; /* - * Avoid multiple rescans which can happen if a page cannot be - * isolated (dirty/writeback in async mode) or if the migrated - * pages are being allocated before the pageblock is cleared. - * The first rescan will capture the entire pageblock for - * migration. If it fails, it'll be marked skip and scanning - * will proceed as normal. + * Avoid multiple rescans of the same pageblock which can + * happen if a page cannot be isolated (dirty/writeback in + * async mode) or if the migrated pages are being allocated + * before the pageblock is cleared. The first rescan will + * capture the entire pageblock for migration. If it fails, + * it'll be marked skip and scanning will proceed as normal. */ - cc->rescan = false; + cc->finish_pageblock = false; if (pageblock_start_pfn(last_migrated_pfn) == pageblock_start_pfn(iteration_start_pfn)) { - cc->rescan = true; + cc->finish_pageblock = true; } switch (isolate_migratepages(cc)) { diff --git a/mm/internal.h b/mm/internal.h index ce462bf145b4..2d1b9fa8083e 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -448,7 +448,11 @@ struct compact_control { bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock contention */ - bool rescan; /* Rescanning the same pageblock */ + bool finish_pageblock; /* Scan the remainder of a pageblock. Used + * when there are potentially transient + * isolation or migration failures to + * ensure forward progress. + */ bool alloc_contig; /* alloc_contig_range allocation */ };