Commit f484697e authored by Ming-Hung Tsai's avatar Ming-Hung Tsai Committed by Mikulas Patocka
Browse files

dm cache: optimize dirty bit checking with find_next_bit when resizing 



When shrinking the fast device, dm-cache iteratively searches for a
dirty bit among the cache blocks to be dropped, which is less efficient.
Use find_next_bit instead, as it is twice as fast as the iterative
approach with test_bit.

Signed-off-by: default avatarMing-Hung Tsai <mtsai@redhat.com>
Fixes: f494a9c6 ("dm cache: cache shrinking support")
Cc: stable@vger.kernel.org
Signed-off-by: default avatarMikulas Patocka <mpatocka@redhat.com>
Acked-by: default avatarJoe Thornber <thornber@redhat.com>
parent 79222771

drivers/md/dm-cache-target.c

+8 −8
Original line number Diff line number Diff line
@@ -2911,15 +2911,15 @@ static bool can_resize(struct cache *cache, dm_cblock_t new_size) 
	/*

	 * We can't drop a dirty block when shrinking the cache.

	 */

	while (from_cblock(new_size) < from_cblock(cache->cache_size)) {

		if (is_dirty(cache, new_size)) {

	new_size = to_cblock(find_next_bit(cache->dirty_bitset,

					   from_cblock(cache->cache_size),

					   from_cblock(new_size)));

	if (new_size != cache->cache_size) {

		DMERR("%s: unable to shrink cache; cache block %llu is dirty",

		      cache_device_name(cache),

		      (unsigned long long) from_cblock(new_size));

		return false;

	}

		new_size = to_cblock(from_cblock(new_size) + 1);

	}



	return true;

}