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