raid1/raid10: slow down resync if there is non-resync activity pending (7ac50447) · Commits · 戴 / test

A performance drop of mkfs has been observed on RAID10 during resync since commit ("md: remove 'go_faster' option from ->sync_request()"). Resync sends so many IOs it slows down non-resync IOs significantly (few times). Add a short delay to a resync. The previous long sleep (1s) has proven unnecessary, even very short delay brings performance right. The change also applied to raid1. The problem has not been observed on raid1, however it shares barriers code with raid10 so it might be an issue for some setup too. Suggested-by:

NeilBrown <neilb@suse.com> Link: http://lkml.kernel.org/r/20160609134555.GA9104@proton.igk.intel.com Signed-off-by:

Tomasz Majchrzak <tomasz.majchrzak@intel.com> Signed-off-by:

Shaohua Li <shli@fb.com>

drivers/md/raid1.c

+7 −0

Original line number	Diff line number	Diff line
		@@ -2535,6 +2535,13 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
		return sync_blocks;
		}

		/*
		* If there is non-resync activity waiting for a turn, then let it
		* though before starting on this new sync request.
		*/
		if (conf->nr_waiting)
		schedule_timeout_uninterruptible(1);

		/* we are incrementing sector_nr below. To be safe, we check against
		* sector_nr + two times RESYNC_SECTORS
		*/

drivers/md/raid10.c

+7 −0

Original line number	Diff line number	Diff line
		@@ -2912,6 +2912,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
		max_sector > (sector_nr \| chunk_mask))
		max_sector = (sector_nr \| chunk_mask) + 1;

		/*
		* If there is non-resync activity waiting for a turn, then let it
		* though before starting on this new sync request.
		*/
		if (conf->nr_waiting)
		schedule_timeout_uninterruptible(1);

		/* Again, very different code for resync and recovery.
		* Both must result in an r10bio with a list of bios that
		* have bi_end_io, bi_sector, bi_bdev set,

Admin message