bcache: set max writeback rate when I/O request is idle

Commit b1092c9af9ed ("bcache: allow quick writeback when backing idle")
allows the writeback rate to be faster if there is no I/O request on a
bcache device. It works well if there is only one bcache device attached
to the cache set. If there are many bcache devices attached to a cache
set, it may introduce performance regression because multiple faster
writeback threads of the idle bcache devices will compete the btree level
locks with the bcache device who have I/O requests coming.

This patch fixes the above issue by only permitting fast writebac when
all bcache devices attached on the cache set are idle. And if one of the
bcache devices has new I/O request coming, minimized all writeback
throughput immediately and let PI controller __update_writeback_rate()
to decide the upcoming writeback rate for each bcache device.

Also when all bcache devices are idle, limited wrieback rate to a small
number is wast of thoughput, especially when backing devices are slower
non-rotation devices (e.g. SATA SSD). This patch sets a max writeback
rate for each backing device if the whole cache set is idle. A faster
writeback rate in idle time means new I/Os may have more available space
for dirty data, and people may observe a better write performance then.

Please note bcache may change its cache mode in run time, and this patch
still works if the cache mode is switched from writeback mode and there
is still dirty data on cache.

Fixes: Commit b1092c9af9ed ("bcache: allow quick writeback when backing idle")
Cc: stable@vger.kernel.org #4.16+
Signed-off-by: Coly Li <colyli@suse.de>
Tested-by: Kai Krakow <kai@kaishome.de>
Tested-by: Stefan Priebe <s.priebe@profihost.ag>
Cc: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 57 insertions, 2 deletions

diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 914d501ad1e0..7dbe8b6316a0 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1103,6 +1103,44 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio)
 		generic_make_request(bio);
 }
 
+static void quit_max_writeback_rate(struct cache_set *c,
+				    struct cached_dev *this_dc)
+{
+	int i;
+	struct bcache_device *d;
+	struct cached_dev *dc;
+
+	/*
+	 * mutex bch_register_lock may compete with other parallel requesters,
+	 * or attach/detach operations on other backing device. Waiting to
+	 * the mutex lock may increase I/O request latency for seconds or more.
+	 * To avoid such situation, if mutext_trylock() failed, only writeback
+	 * rate of current cached device is set to 1, and __update_write_back()
+	 * will decide writeback rate of other cached devices (remember now
+	 * c->idle_counter is 0 already).
+	 */
+	if (mutex_trylock(&bch_register_lock)) {
+		for (i = 0; i < c->devices_max_used; i++) {
+			if (!c->devices[i])
+				continue;
+
+			if (UUID_FLASH_ONLY(&c->uuids[i]))
+				continue;
+
+			d = c->devices[i];
+			dc = container_of(d, struct cached_dev, disk);
+			/*
+			 * set writeback rate to default minimum value,
+			 * then let update_writeback_rate() to decide the
+			 * upcoming rate.
+			 */
+			atomic_long_set(&dc->writeback_rate.rate, 1);
+		}
+		mutex_unlock(&bch_register_lock);
+	} else
+		atomic_long_set(&this_dc->writeback_rate.rate, 1);
+}
+
 /* Cached devices - read & write stuff */
 
 static blk_qc_t cached_dev_make_request(struct request_queue *q,
@@ -1120,8 +1158,25 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q,
 		return BLK_QC_T_NONE;
 	}
 
-	atomic_set(&dc->backing_idle, 0);
-	generic_start_io_acct(q, bio_op(bio), bio_sectors(bio), &d->disk->part0);
+	if (likely(d->c)) {
+		if (atomic_read(&d->c->idle_counter))
+			atomic_set(&d->c->idle_counter, 0);
+		/*
+		 * If at_max_writeback_rate of cache set is true and new I/O
+		 * comes, quit max writeback rate of all cached devices
+		 * attached to this cache set, and set at_max_writeback_rate
+		 * to false.
+		 */
+		if (unlikely(atomic_read(&d->c->at_max_writeback_rate) == 1)) {
+			atomic_set(&d->c->at_max_writeback_rate, 0);
+			quit_max_writeback_rate(d->c, dc);
+		}
+	}
+
+	generic_start_io_acct(q,
+			      bio_op(bio),
+			      bio_sectors(bio),
+			      &d->disk->part0);
 
 	bio_set_dev(bio, dc->bdev);
 	bio->bi_iter.bi_sector += dc->sb.data_offset;