提交 4813962b 编写于 作者: J Joseph Qi 提交者: Linus Torvalds

ocfs2: wait for orphan recovery first once append O_DIRECT write crash

If one node has crashed with orphan entry leftover, another node which do
append O_DIRECT write to the same file will override the
i_dio_orphaned_slot.  Then the old entry won't be cleaned forever.  If
this case happens, we let it wait for orphan recovery first.
Signed-off-by: NJoseph Qi <joseph.qi@huawei.com>
Cc: Weiwei Wang <wangww631@huawei.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Xuejiufei <xuejiufei@huawei.com>
Cc: alex chen <alex.chen@huawei.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
上级 3a83b342
......@@ -81,6 +81,8 @@ struct ocfs2_inode_info
tid_t i_sync_tid;
tid_t i_datasync_tid;
wait_queue_head_t append_dio_wq;
struct dquot *i_dquot[MAXQUOTAS];
};
......
......@@ -2204,6 +2204,8 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
ret = ocfs2_del_inode_from_orphan(osb, inode, 0, 0);
if (ret)
mlog_errno(ret);
wake_up(&OCFS2_I(inode)->append_dio_wq);
} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
next:
......
......@@ -2577,6 +2577,27 @@ int ocfs2_create_inode_in_orphan(struct inode *dir,
return status;
}
static int ocfs2_dio_orphan_recovered(struct inode *inode)
{
int ret;
struct buffer_head *di_bh = NULL;
struct ocfs2_dinode *di = NULL;
ret = ocfs2_inode_lock(inode, &di_bh, 1);
if (ret < 0) {
mlog_errno(ret);
return 0;
}
di = (struct ocfs2_dinode *) di_bh->b_data;
ret = !(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL));
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
return ret;
}
#define OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL 10000
int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
struct inode *inode)
{
......@@ -2586,13 +2607,29 @@ int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
struct buffer_head *di_bh = NULL;
int status = 0;
handle_t *handle = NULL;
struct ocfs2_dinode *di = NULL;
restart:
status = ocfs2_inode_lock(inode, &di_bh, 1);
if (status < 0) {
mlog_errno(status);
goto bail;
}
di = (struct ocfs2_dinode *) di_bh->b_data;
/*
* Another append dio crashed?
* If so, wait for recovery first.
*/
if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
wait_event_interruptible_timeout(OCFS2_I(inode)->append_dio_wq,
ocfs2_dio_orphan_recovered(inode),
msecs_to_jiffies(OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL));
goto restart;
}
status = ocfs2_prepare_orphan_dir(osb, &orphan_dir_inode,
OCFS2_I(inode)->ip_blkno,
orphan_name,
......
......@@ -1746,6 +1746,8 @@ static void ocfs2_inode_init_once(void *data)
ocfs2_lock_res_init_once(&oi->ip_inode_lockres);
ocfs2_lock_res_init_once(&oi->ip_open_lockres);
init_waitqueue_head(&oi->append_dio_wq);
ocfs2_metadata_cache_init(INODE_CACHE(&oi->vfs_inode),
&ocfs2_inode_caching_ops);
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册