| Message ID | f39c2c07f2dba2732fd9c0843572e5bef96f7f67.1685018752.git.baolin.wang@linux.alibaba.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Misc cleanups and improvements for compaction | expand |
On 5/25/23 14:54, Baolin Wang wrote: > I've observed that fast isolation often isolates more pages than > cc->migratepages, and the excess freepages will be released back to the > buddy system. So skip fast freepages isolation if enough freepages are > isolated to save some CPU cycles. > > Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> > --- > mm/compaction.c | 4 ++++ > 1 file changed, 4 insertions(+) > > diff --git a/mm/compaction.c b/mm/compaction.c > index eccec84dae82..3ade4c095ed2 100644 > --- a/mm/compaction.c > +++ b/mm/compaction.c > @@ -1550,6 +1550,10 @@ static void fast_isolate_freepages(struct compact_control *cc) > > spin_unlock_irqrestore(&cc->zone->lock, flags); > > + /* Skip fast search if enough freepages isolated */ > + if (cc->nr_freepages >= cc->nr_migratepages) > + break; > + > /* > * Smaller scan on next order so the total scan is related > * to freelist_scan_limit.
diff --git a/mm/compaction.c b/mm/compaction.c index eccec84dae82..3ade4c095ed2 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1550,6 +1550,10 @@ static void fast_isolate_freepages(struct compact_control *cc) spin_unlock_irqrestore(&cc->zone->lock, flags); + /* Skip fast search if enough freepages isolated */ + if (cc->nr_freepages >= cc->nr_migratepages) + break; + /* * Smaller scan on next order so the total scan is related * to freelist_scan_limit.
I've observed that fast isolation often isolates more pages than cc->migratepages, and the excess freepages will be released back to the buddy system. So skip fast freepages isolation if enough freepages are isolated to save some CPU cycles. Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> --- mm/compaction.c | 4 ++++ 1 file changed, 4 insertions(+)