diff mbox series

[SRU,F,3/3] bcache: reap from tail of c->btree_cache in bch_mca_scan()

Message ID 20201021015902.19223-4-matthew.ruffell@canonical.com
State New
Headers show
Series bcache: Issues with large IO wait in bch_mca_scan() when shrinker is enabled | expand

Commit Message

Matthew Ruffell Oct. 21, 2020, 1:59 a.m. UTC
From: Coly Li <colyli@suse.de>

BugLink: https://bugs.launchpad.net/bugs/1898786

When shrink btree node cache from c->btree_cache in bch_mca_scan(),
no matter the selected node is reaped or not, it will be rotated from
the head to the tail of c->btree_cache list. But in bcache journal
code, when flushing the btree nodes with oldest journal entry, btree
nodes are iterated and slected from the tail of c->btree_cache list in
btree_flush_write(). The list_rotate_left() in bch_mca_scan() will
make btree_flush_write() iterate more nodes in c->btree_list in reverse
order.

This patch just reaps the selected btree node cache, and not move it
from the head to the tail of c->btree_cache list. Then bch_mca_scan()
will not mess up c->btree_cache list to btree_flush_write().

Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
(cherry picked from commit e3de04469a49ee09c89e80bf821508df458ccee6)
Signed-off-by: Matthew Ruffell <matthew.ruffell@canonical.com>
---
 drivers/md/bcache/btree.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
diff mbox series

Patch

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index c9b87a6e1c2e..61d504b3e323 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -742,19 +742,19 @@  static unsigned long bch_mca_scan(struct shrinker *shrink,
 		i++;
 	}
 
-	for (;  (nr--) && i < btree_cache_used; i++) {
-		if (list_empty(&c->btree_cache))
+	list_for_each_entry_safe_reverse(b, t, &c->btree_cache, list) {
+		if (nr <= 0 || i >= btree_cache_used)
 			goto out;
 
-		b = list_first_entry(&c->btree_cache, struct btree, list);
-		list_rotate_left(&c->btree_cache);
-
 		if (!mca_reap(b, 0, false)) {
 			mca_bucket_free(b);
 			mca_data_free(b);
 			rw_unlock(true, b);
 			freed++;
 		}
+
+		nr--;
+		i++;
 	}
 out:
 	mutex_unlock(&c->bucket_lock);