It needs to double cache size of write_io_dummy mempool, otherwise we may
run out of cache in scenraio of Data/Node IOs were issued concurrently.

Signed-off-by: Chao Yu <yuch...@huawei.com>
---
 fs/f2fs/super.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 53305880c455..7571eb297b21 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1929,7 +1929,7 @@ static int f2fs_fill_super(struct super_block *sb, void 
*data, int silent)
 
        if (F2FS_IO_SIZE(sbi) > 1) {
                sbi->write_io_dummy =
-                       mempool_create_page_pool(F2FS_IO_SIZE(sbi) - 1, 0);
+                       mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 
0);
                if (!sbi->write_io_dummy)
                        goto free_options;
        }
-- 
2.8.2.295.g3f1c1d0

Reply via email to