From: Mateusz Nosek <mateusznosek0@xxxxxxxxx> Subject: mm/compaction.c: micro-optimization remove unnecessary branch The same code can work both for 'zone->compact_considered > defer_limit' and 'zone->compact_considered >= defer_limit'. In the latter there is one branch less which is more effective considering performance. Link: https://lkml.kernel.org/r/20200913190448.28649-1-mateusznosek0@xxxxxxxxx Signed-off-by: Mateusz Nosek <mateusznosek0@xxxxxxxxx> Reviewed-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx> Cc: Vlastimil Babka <vbabka@xxxxxxx> Cc: Mel Gorman <mgorman@xxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/compaction.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) --- a/mm/compaction.c~mm-compactionc-micro-optimization-remove-unnecessary-branch +++ a/mm/compaction.c @@ -180,11 +180,10 @@ bool compaction_deferred(struct zone *zo return false; /* Avoid possible overflow */ - if (++zone->compact_considered > defer_limit) + if (++zone->compact_considered >= defer_limit) { zone->compact_considered = defer_limit; - - if (zone->compact_considered >= defer_limit) return false; + } trace_mm_compaction_deferred(zone, order); _
